diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-13 13:44:03 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-13 13:44:03 +0000 |
commit | 293913568e6a7a86fd1479e1cff8e2ecb58d6568 (patch) | |
tree | fc3b469a3ec5ab71b36ea97cc7aaddb838423a0c /src/include/nodes | |
parent | Initial commit. (diff) | |
download | postgresql-16-293913568e6a7a86fd1479e1cff8e2ecb58d6568.tar.xz postgresql-16-293913568e6a7a86fd1479e1cff8e2ecb58d6568.zip |
Adding upstream version 16.2.upstream/16.2
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'src/include/nodes')
26 files changed, 17002 insertions, 0 deletions
diff --git a/src/include/nodes/.gitignore b/src/include/nodes/.gitignore new file mode 100644 index 0000000..99fb1d3 --- /dev/null +++ b/src/include/nodes/.gitignore @@ -0,0 +1,2 @@ +/nodetags.h +/header-stamp diff --git a/src/include/nodes/bitmapset.h b/src/include/nodes/bitmapset.h new file mode 100644 index 0000000..14de6a9 --- /dev/null +++ b/src/include/nodes/bitmapset.h @@ -0,0 +1,126 @@ +/*------------------------------------------------------------------------- + * + * bitmapset.h + * PostgreSQL generic bitmap set package + * + * A bitmap set can represent any set of nonnegative integers, although + * it is mainly intended for sets where the maximum value is not large, + * say at most a few hundred. By convention, we always represent the + * empty set by a NULL pointer. + * + * + * Copyright (c) 2003-2023, PostgreSQL Global Development Group + * + * src/include/nodes/bitmapset.h + * + *------------------------------------------------------------------------- + */ +#ifndef BITMAPSET_H +#define BITMAPSET_H + +#include "nodes/nodes.h" + +/* + * Forward decl to save including pg_list.h + */ +struct List; + +/* + * Data representation + * + * Larger bitmap word sizes generally give better performance, so long as + * they're not wider than the processor can handle efficiently. We use + * 64-bit words if pointers are that large, else 32-bit words. + */ +#if SIZEOF_VOID_P >= 8 + +#define BITS_PER_BITMAPWORD 64 +typedef uint64 bitmapword; /* must be an unsigned type */ +typedef int64 signedbitmapword; /* must be the matching signed type */ + +#else + +#define BITS_PER_BITMAPWORD 32 +typedef uint32 bitmapword; /* must be an unsigned type */ +typedef int32 signedbitmapword; /* must be the matching signed type */ + +#endif + +typedef struct Bitmapset +{ + pg_node_attr(custom_copy_equal, special_read_write, no_query_jumble) + + NodeTag type; + int nwords; /* number of words in array */ + bitmapword words[FLEXIBLE_ARRAY_MEMBER]; /* really [nwords] */ +} Bitmapset; + + +/* result of bms_subset_compare */ +typedef enum +{ + BMS_EQUAL, /* sets are equal */ + BMS_SUBSET1, /* first set is a subset of the second */ + BMS_SUBSET2, /* second set is a subset of the first */ + BMS_DIFFERENT /* neither set is a subset of the other */ +} BMS_Comparison; + +/* result of bms_membership */ +typedef enum +{ + BMS_EMPTY_SET, /* 0 members */ + BMS_SINGLETON, /* 1 member */ + BMS_MULTIPLE /* >1 member */ +} BMS_Membership; + + +/* + * function prototypes in nodes/bitmapset.c + */ + +extern Bitmapset *bms_copy(const Bitmapset *a); +extern bool bms_equal(const Bitmapset *a, const Bitmapset *b); +extern int bms_compare(const Bitmapset *a, const Bitmapset *b); +extern Bitmapset *bms_make_singleton(int x); +extern void bms_free(Bitmapset *a); + +extern Bitmapset *bms_union(const Bitmapset *a, const Bitmapset *b); +extern Bitmapset *bms_intersect(const Bitmapset *a, const Bitmapset *b); +extern Bitmapset *bms_difference(const Bitmapset *a, const Bitmapset *b); +extern bool bms_is_subset(const Bitmapset *a, const Bitmapset *b); +extern BMS_Comparison bms_subset_compare(const Bitmapset *a, const Bitmapset *b); +extern bool bms_is_member(int x, const Bitmapset *a); +extern int bms_member_index(Bitmapset *a, int x); +extern bool bms_overlap(const Bitmapset *a, const Bitmapset *b); +extern bool bms_overlap_list(const Bitmapset *a, const struct List *b); +extern bool bms_nonempty_difference(const Bitmapset *a, const Bitmapset *b); +extern int bms_singleton_member(const Bitmapset *a); +extern bool bms_get_singleton_member(const Bitmapset *a, int *member); +extern int bms_num_members(const Bitmapset *a); + +/* optimized tests when we don't need to know exact membership count: */ +extern BMS_Membership bms_membership(const Bitmapset *a); + +/* NULL is now the only allowed representation of an empty bitmapset */ +#define bms_is_empty(a) ((a) == NULL) + +/* these routines recycle (modify or free) their non-const inputs: */ + +extern Bitmapset *bms_add_member(Bitmapset *a, int x); +extern Bitmapset *bms_del_member(Bitmapset *a, int x); +extern Bitmapset *bms_add_members(Bitmapset *a, const Bitmapset *b); +extern Bitmapset *bms_add_range(Bitmapset *a, int lower, int upper); +extern Bitmapset *bms_int_members(Bitmapset *a, const Bitmapset *b); +extern Bitmapset *bms_del_members(Bitmapset *a, const Bitmapset *b); +extern Bitmapset *bms_join(Bitmapset *a, Bitmapset *b); + +/* support for iterating through the integer elements of a set: */ +extern int bms_next_member(const Bitmapset *a, int prevbit); +extern int bms_prev_member(const Bitmapset *a, int prevbit); + +/* support for hashtables using Bitmapsets as keys: */ +extern uint32 bms_hash_value(const Bitmapset *a); +extern uint32 bitmap_hash(const void *key, Size keysize); +extern int bitmap_match(const void *key1, const void *key2, Size keysize); + +#endif /* BITMAPSET_H */ diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h new file mode 100644 index 0000000..869465d --- /dev/null +++ b/src/include/nodes/execnodes.h @@ -0,0 +1,2768 @@ +/*------------------------------------------------------------------------- + * + * execnodes.h + * definitions for executor state nodes + * + * Most plan node types declared in plannodes.h have a corresponding + * execution-state node type declared here. An exception is that + * expression nodes (subtypes of Expr) are usually represented by steps + * of an ExprState, and fully handled within execExpr* - but sometimes + * their state needs to be shared with other parts of the executor, as + * for example with SubPlanState, which nodeSubplan.c has to modify. + * + * Node types declared in this file do not have any copy/equal/out/read + * support. (That is currently hard-wired in gen_node_support.pl, rather + * than being explicitly represented by pg_node_attr decorations here.) + * There is no need for copy, equal, or read support for executor trees. + * Output support could be useful for debugging; but there are a lot of + * specialized fields that would require custom code, so for now it's + * not provided. + * + * + * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/nodes/execnodes.h + * + *------------------------------------------------------------------------- + */ +#ifndef EXECNODES_H +#define EXECNODES_H + +#include "access/tupconvert.h" +#include "executor/instrument.h" +#include "fmgr.h" +#include "lib/ilist.h" +#include "lib/pairingheap.h" +#include "nodes/params.h" +#include "nodes/plannodes.h" +#include "nodes/tidbitmap.h" +#include "partitioning/partdefs.h" +#include "storage/condition_variable.h" +#include "utils/hsearch.h" +#include "utils/queryenvironment.h" +#include "utils/reltrigger.h" +#include "utils/sharedtuplestore.h" +#include "utils/snapshot.h" +#include "utils/sortsupport.h" +#include "utils/tuplesort.h" +#include "utils/tuplestore.h" + +struct PlanState; /* forward references in this file */ +struct ParallelHashJoinState; +struct ExecRowMark; +struct ExprState; +struct ExprContext; +struct RangeTblEntry; /* avoid including parsenodes.h here */ +struct ExprEvalStep; /* avoid including execExpr.h everywhere */ +struct CopyMultiInsertBuffer; +struct LogicalTapeSet; + + +/* ---------------- + * ExprState node + * + * ExprState represents the evaluation state for a whole expression tree. + * It contains instructions (in ->steps) to evaluate the expression. + * ---------------- + */ +typedef Datum (*ExprStateEvalFunc) (struct ExprState *expression, + struct ExprContext *econtext, + bool *isNull); + +/* Bits in ExprState->flags (see also execExpr.h for private flag bits): */ +/* expression is for use with ExecQual() */ +#define EEO_FLAG_IS_QUAL (1 << 0) + +typedef struct ExprState +{ + NodeTag type; + + uint8 flags; /* bitmask of EEO_FLAG_* bits, see above */ + + /* + * Storage for result value of a scalar expression, or for individual + * column results within expressions built by ExecBuildProjectionInfo(). + */ +#define FIELDNO_EXPRSTATE_RESNULL 2 + bool resnull; +#define FIELDNO_EXPRSTATE_RESVALUE 3 + Datum resvalue; + + /* + * If projecting a tuple result, this slot holds the result; else NULL. + */ +#define FIELDNO_EXPRSTATE_RESULTSLOT 4 + TupleTableSlot *resultslot; + + /* + * Instructions to compute expression's return value. + */ + struct ExprEvalStep *steps; + + /* + * Function that actually evaluates the expression. This can be set to + * different values depending on the complexity of the expression. + */ + ExprStateEvalFunc evalfunc; + + /* original expression tree, for debugging only */ + Expr *expr; + + /* private state for an evalfunc */ + void *evalfunc_private; + + /* + * XXX: following fields only needed during "compilation" (ExecInitExpr); + * could be thrown away afterwards. + */ + + int steps_len; /* number of steps currently */ + int steps_alloc; /* allocated length of steps array */ + +#define FIELDNO_EXPRSTATE_PARENT 11 + struct PlanState *parent; /* parent PlanState node, if any */ + ParamListInfo ext_params; /* for compiling PARAM_EXTERN nodes */ + + Datum *innermost_caseval; + bool *innermost_casenull; + + Datum *innermost_domainval; + bool *innermost_domainnull; +} ExprState; + + +/* ---------------- + * IndexInfo information + * + * this struct holds the information needed to construct new index + * entries for a particular index. Used for both index_build and + * retail creation of index entries. + * + * NumIndexAttrs total number of columns in this index + * NumIndexKeyAttrs number of key columns in index + * IndexAttrNumbers underlying-rel attribute numbers used as keys + * (zeroes indicate expressions). It also contains + * info about included columns. + * Expressions expr trees for expression entries, or NIL if none + * ExpressionsState exec state for expressions, or NIL if none + * Predicate partial-index predicate, or NIL if none + * PredicateState exec state for predicate, or NIL if none + * ExclusionOps Per-column exclusion operators, or NULL if none + * ExclusionProcs Underlying function OIDs for ExclusionOps + * ExclusionStrats Opclass strategy numbers for ExclusionOps + * UniqueOps These are like Exclusion*, but for unique indexes + * UniqueProcs + * UniqueStrats + * Unique is it a unique index? + * OpclassOptions opclass-specific options, or NULL if none + * ReadyForInserts is it valid for inserts? + * CheckedUnchanged IndexUnchanged status determined yet? + * IndexUnchanged aminsert hint, cached for retail inserts + * Concurrent are we doing a concurrent index build? + * BrokenHotChain did we detect any broken HOT chains? + * Summarizing is it a summarizing index? + * ParallelWorkers # of workers requested (excludes leader) + * Am Oid of index AM + * AmCache private cache area for index AM + * Context memory context holding this IndexInfo + * + * ii_Concurrent, ii_BrokenHotChain, and ii_ParallelWorkers are used only + * during index build; they're conventionally zeroed otherwise. + * ---------------- + */ +typedef struct IndexInfo +{ + NodeTag type; + int ii_NumIndexAttrs; /* total number of columns in index */ + int ii_NumIndexKeyAttrs; /* number of key columns in index */ + AttrNumber ii_IndexAttrNumbers[INDEX_MAX_KEYS]; + List *ii_Expressions; /* list of Expr */ + List *ii_ExpressionsState; /* list of ExprState */ + List *ii_Predicate; /* list of Expr */ + ExprState *ii_PredicateState; + Oid *ii_ExclusionOps; /* array with one entry per column */ + Oid *ii_ExclusionProcs; /* array with one entry per column */ + uint16 *ii_ExclusionStrats; /* array with one entry per column */ + Oid *ii_UniqueOps; /* array with one entry per column */ + Oid *ii_UniqueProcs; /* array with one entry per column */ + uint16 *ii_UniqueStrats; /* array with one entry per column */ + Datum *ii_OpclassOptions; /* array with one entry per column */ + bool ii_Unique; + bool ii_NullsNotDistinct; + bool ii_ReadyForInserts; + bool ii_CheckedUnchanged; + bool ii_IndexUnchanged; + bool ii_Concurrent; + bool ii_BrokenHotChain; + bool ii_Summarizing; + int ii_ParallelWorkers; + Oid ii_Am; + void *ii_AmCache; + MemoryContext ii_Context; +} IndexInfo; + +/* ---------------- + * ExprContext_CB + * + * List of callbacks to be called at ExprContext shutdown. + * ---------------- + */ +typedef void (*ExprContextCallbackFunction) (Datum arg); + +typedef struct ExprContext_CB +{ + struct ExprContext_CB *next; + ExprContextCallbackFunction function; + Datum arg; +} ExprContext_CB; + +/* ---------------- + * ExprContext + * + * This class holds the "current context" information + * needed to evaluate expressions for doing tuple qualifications + * and tuple projections. For example, if an expression refers + * to an attribute in the current inner tuple then we need to know + * what the current inner tuple is and so we look at the expression + * context. + * + * There are two memory contexts associated with an ExprContext: + * * ecxt_per_query_memory is a query-lifespan context, typically the same + * context the ExprContext node itself is allocated in. This context + * can be used for purposes such as storing function call cache info. + * * ecxt_per_tuple_memory is a short-term context for expression results. + * As the name suggests, it will typically be reset once per tuple, + * before we begin to evaluate expressions for that tuple. Each + * ExprContext normally has its very own per-tuple memory context. + * + * CurrentMemoryContext should be set to ecxt_per_tuple_memory before + * calling ExecEvalExpr() --- see ExecEvalExprSwitchContext(). + * ---------------- + */ +typedef struct ExprContext +{ + NodeTag type; + + /* Tuples that Var nodes in expression may refer to */ +#define FIELDNO_EXPRCONTEXT_SCANTUPLE 1 + TupleTableSlot *ecxt_scantuple; +#define FIELDNO_EXPRCONTEXT_INNERTUPLE 2 + TupleTableSlot *ecxt_innertuple; +#define FIELDNO_EXPRCONTEXT_OUTERTUPLE 3 + TupleTableSlot *ecxt_outertuple; + + /* Memory contexts for expression evaluation --- see notes above */ + MemoryContext ecxt_per_query_memory; + MemoryContext ecxt_per_tuple_memory; + + /* Values to substitute for Param nodes in expression */ + ParamExecData *ecxt_param_exec_vals; /* for PARAM_EXEC params */ + ParamListInfo ecxt_param_list_info; /* for other param types */ + + /* + * Values to substitute for Aggref nodes in the expressions of an Agg + * node, or for WindowFunc nodes within a WindowAgg node. + */ +#define FIELDNO_EXPRCONTEXT_AGGVALUES 8 + Datum *ecxt_aggvalues; /* precomputed values for aggs/windowfuncs */ +#define FIELDNO_EXPRCONTEXT_AGGNULLS 9 + bool *ecxt_aggnulls; /* null flags for aggs/windowfuncs */ + + /* Value to substitute for CaseTestExpr nodes in expression */ +#define FIELDNO_EXPRCONTEXT_CASEDATUM 10 + Datum caseValue_datum; +#define FIELDNO_EXPRCONTEXT_CASENULL 11 + bool caseValue_isNull; + + /* Value to substitute for CoerceToDomainValue nodes in expression */ +#define FIELDNO_EXPRCONTEXT_DOMAINDATUM 12 + Datum domainValue_datum; +#define FIELDNO_EXPRCONTEXT_DOMAINNULL 13 + bool domainValue_isNull; + + /* Link to containing EState (NULL if a standalone ExprContext) */ + struct EState *ecxt_estate; + + /* Functions to call back when ExprContext is shut down or rescanned */ + ExprContext_CB *ecxt_callbacks; +} ExprContext; + +/* + * Set-result status used when evaluating functions potentially returning a + * set. + */ +typedef enum +{ + ExprSingleResult, /* expression does not return a set */ + ExprMultipleResult, /* this result is an element of a set */ + ExprEndResult /* there are no more elements in the set */ +} ExprDoneCond; + +/* + * Return modes for functions returning sets. Note values must be chosen + * as separate bits so that a bitmask can be formed to indicate supported + * modes. SFRM_Materialize_Random and SFRM_Materialize_Preferred are + * auxiliary flags about SFRM_Materialize mode, rather than separate modes. + */ +typedef enum +{ + SFRM_ValuePerCall = 0x01, /* one value returned per call */ + SFRM_Materialize = 0x02, /* result set instantiated in Tuplestore */ + SFRM_Materialize_Random = 0x04, /* Tuplestore needs randomAccess */ + SFRM_Materialize_Preferred = 0x08 /* caller prefers Tuplestore */ +} SetFunctionReturnMode; + +/* + * When calling a function that might return a set (multiple rows), + * a node of this type is passed as fcinfo->resultinfo to allow + * return status to be passed back. A function returning set should + * raise an error if no such resultinfo is provided. + */ +typedef struct ReturnSetInfo +{ + NodeTag type; + /* values set by caller: */ + ExprContext *econtext; /* context function is being called in */ + TupleDesc expectedDesc; /* tuple descriptor expected by caller */ + int allowedModes; /* bitmask: return modes caller can handle */ + /* result status from function (but pre-initialized by caller): */ + SetFunctionReturnMode returnMode; /* actual return mode */ + ExprDoneCond isDone; /* status for ValuePerCall mode */ + /* fields filled by function in Materialize return mode: */ + Tuplestorestate *setResult; /* holds the complete returned tuple set */ + TupleDesc setDesc; /* actual descriptor for returned tuples */ +} ReturnSetInfo; + +/* ---------------- + * ProjectionInfo node information + * + * This is all the information needed to perform projections --- + * that is, form new tuples by evaluation of targetlist expressions. + * Nodes which need to do projections create one of these. + * + * The target tuple slot is kept in ProjectionInfo->pi_state.resultslot. + * ExecProject() evaluates the tlist, forms a tuple, and stores it + * in the given slot. Note that the result will be a "virtual" tuple + * unless ExecMaterializeSlot() is then called to force it to be + * converted to a physical tuple. The slot must have a tupledesc + * that matches the output of the tlist! + * ---------------- + */ +typedef struct ProjectionInfo +{ + NodeTag type; + /* instructions to evaluate projection */ + ExprState pi_state; + /* expression context in which to evaluate expression */ + ExprContext *pi_exprContext; +} ProjectionInfo; + +/* ---------------- + * JunkFilter + * + * This class is used to store information regarding junk attributes. + * A junk attribute is an attribute in a tuple that is needed only for + * storing intermediate information in the executor, and does not belong + * in emitted tuples. For example, when we do an UPDATE query, + * the planner adds a "junk" entry to the targetlist so that the tuples + * returned to ExecutePlan() contain an extra attribute: the ctid of + * the tuple to be updated. This is needed to do the update, but we + * don't want the ctid to be part of the stored new tuple! So, we + * apply a "junk filter" to remove the junk attributes and form the + * real output tuple. The junkfilter code also provides routines to + * extract the values of the junk attribute(s) from the input tuple. + * + * targetList: the original target list (including junk attributes). + * cleanTupType: the tuple descriptor for the "clean" tuple (with + * junk attributes removed). + * cleanMap: A map with the correspondence between the non-junk + * attribute numbers of the "original" tuple and the + * attribute numbers of the "clean" tuple. + * resultSlot: tuple slot used to hold cleaned tuple. + * ---------------- + */ +typedef struct JunkFilter +{ + NodeTag type; + List *jf_targetList; + TupleDesc jf_cleanTupType; + AttrNumber *jf_cleanMap; + TupleTableSlot *jf_resultSlot; +} JunkFilter; + +/* + * OnConflictSetState + * + * Executor state of an ON CONFLICT DO UPDATE operation. + */ +typedef struct OnConflictSetState +{ + NodeTag type; + + TupleTableSlot *oc_Existing; /* slot to store existing target tuple in */ + TupleTableSlot *oc_ProjSlot; /* CONFLICT ... SET ... projection target */ + ProjectionInfo *oc_ProjInfo; /* for ON CONFLICT DO UPDATE SET */ + ExprState *oc_WhereClause; /* state for the WHERE clause */ +} OnConflictSetState; + +/* ---------------- + * MergeActionState information + * + * Executor state for a MERGE action. + * ---------------- + */ +typedef struct MergeActionState +{ + NodeTag type; + + MergeAction *mas_action; /* associated MergeAction node */ + ProjectionInfo *mas_proj; /* projection of the action's targetlist for + * this rel */ + ExprState *mas_whenqual; /* WHEN [NOT] MATCHED AND conditions */ +} MergeActionState; + +/* + * ResultRelInfo + * + * Whenever we update an existing relation, we have to update indexes on the + * relation, and perhaps also fire triggers. ResultRelInfo holds all the + * information needed about a result relation, including indexes. + * + * Normally, a ResultRelInfo refers to a table that is in the query's range + * table; then ri_RangeTableIndex is the RT index and ri_RelationDesc is + * just a copy of the relevant es_relations[] entry. However, in some + * situations we create ResultRelInfos for relations that are not in the + * range table, namely for targets of tuple routing in a partitioned table, + * and when firing triggers in tables other than the target tables (See + * ExecGetTriggerResultRel). In these situations, ri_RangeTableIndex is 0 + * and ri_RelationDesc is a separately-opened relcache pointer that needs to + * be separately closed. + */ +typedef struct ResultRelInfo +{ + NodeTag type; + + /* result relation's range table index, or 0 if not in range table */ + Index ri_RangeTableIndex; + + /* relation descriptor for result relation */ + Relation ri_RelationDesc; + + /* # of indices existing on result relation */ + int ri_NumIndices; + + /* array of relation descriptors for indices */ + RelationPtr ri_IndexRelationDescs; + + /* array of key/attr info for indices */ + IndexInfo **ri_IndexRelationInfo; + + /* + * For UPDATE/DELETE result relations, the attribute number of the row + * identity junk attribute in the source plan's output tuples + */ + AttrNumber ri_RowIdAttNo; + + /* For UPDATE, attnums of generated columns to be computed */ + Bitmapset *ri_extraUpdatedCols; + + /* Projection to generate new tuple in an INSERT/UPDATE */ + ProjectionInfo *ri_projectNew; + /* Slot to hold that tuple */ + TupleTableSlot *ri_newTupleSlot; + /* Slot to hold the old tuple being updated */ + TupleTableSlot *ri_oldTupleSlot; + /* Have the projection and the slots above been initialized? */ + bool ri_projectNewInfoValid; + + /* triggers to be fired, if any */ + TriggerDesc *ri_TrigDesc; + + /* cached lookup info for trigger functions */ + FmgrInfo *ri_TrigFunctions; + + /* array of trigger WHEN expr states */ + ExprState **ri_TrigWhenExprs; + + /* optional runtime measurements for triggers */ + Instrumentation *ri_TrigInstrument; + + /* On-demand created slots for triggers / returning processing */ + TupleTableSlot *ri_ReturningSlot; /* for trigger output tuples */ + TupleTableSlot *ri_TrigOldSlot; /* for a trigger's old tuple */ + TupleTableSlot *ri_TrigNewSlot; /* for a trigger's new tuple */ + + /* FDW callback functions, if foreign table */ + struct FdwRoutine *ri_FdwRoutine; + + /* available to save private state of FDW */ + void *ri_FdwState; + + /* true when modifying foreign table directly */ + bool ri_usesFdwDirectModify; + + /* batch insert stuff */ + int ri_NumSlots; /* number of slots in the array */ + int ri_NumSlotsInitialized; /* number of initialized slots */ + int ri_BatchSize; /* max slots inserted in a single batch */ + TupleTableSlot **ri_Slots; /* input tuples for batch insert */ + TupleTableSlot **ri_PlanSlots; + + /* list of WithCheckOption's to be checked */ + List *ri_WithCheckOptions; + + /* list of WithCheckOption expr states */ + List *ri_WithCheckOptionExprs; + + /* array of constraint-checking expr states */ + ExprState **ri_ConstraintExprs; + + /* arrays of stored generated columns expr states, for INSERT and UPDATE */ + ExprState **ri_GeneratedExprsI; + ExprState **ri_GeneratedExprsU; + + /* number of stored generated columns we need to compute */ + int ri_NumGeneratedNeededI; + int ri_NumGeneratedNeededU; + + /* list of RETURNING expressions */ + List *ri_returningList; + + /* for computing a RETURNING list */ + ProjectionInfo *ri_projectReturning; + + /* list of arbiter indexes to use to check conflicts */ + List *ri_onConflictArbiterIndexes; + + /* ON CONFLICT evaluation state */ + OnConflictSetState *ri_onConflict; + + /* for MERGE, lists of MergeActionState */ + List *ri_matchedMergeAction; + List *ri_notMatchedMergeAction; + + /* partition check expression state (NULL if not set up yet) */ + ExprState *ri_PartitionCheckExpr; + + /* + * Map to convert child result relation tuples to the format of the table + * actually mentioned in the query (called "root"). Computed only if + * needed. A NULL map value indicates that no conversion is needed, so we + * must have a separate flag to show if the map has been computed. + */ + TupleConversionMap *ri_ChildToRootMap; + bool ri_ChildToRootMapValid; + + /* + * As above, but in the other direction. + */ + TupleConversionMap *ri_RootToChildMap; + bool ri_RootToChildMapValid; + + /* + * Information needed by tuple routing target relations + * + * RootResultRelInfo gives the target relation mentioned in the query, if + * it's a partitioned table. It is not set if the target relation + * mentioned in the query is an inherited table, nor when tuple routing is + * not needed. + * + * PartitionTupleSlot is non-NULL if RootToChild conversion is needed and + * the relation is a partition. + */ + struct ResultRelInfo *ri_RootResultRelInfo; + TupleTableSlot *ri_PartitionTupleSlot; + + /* for use by copyfrom.c when performing multi-inserts */ + struct CopyMultiInsertBuffer *ri_CopyMultiInsertBuffer; + + /* + * Used when a leaf partition is involved in a cross-partition update of + * one of its ancestors; see ExecCrossPartitionUpdateForeignKey(). + */ + List *ri_ancestorResultRels; +} ResultRelInfo; + +/* ---------------- + * AsyncRequest + * + * State for an asynchronous tuple request. + * ---------------- + */ +typedef struct AsyncRequest +{ + struct PlanState *requestor; /* Node that wants a tuple */ + struct PlanState *requestee; /* Node from which a tuple is wanted */ + int request_index; /* Scratch space for requestor */ + bool callback_pending; /* Callback is needed */ + bool request_complete; /* Request complete, result valid */ + TupleTableSlot *result; /* Result (NULL or an empty slot if no more + * tuples) */ +} AsyncRequest; + +/* ---------------- + * EState information + * + * Working state for an Executor invocation + * ---------------- + */ +typedef struct EState +{ + NodeTag type; + + /* Basic state for all query types: */ + ScanDirection es_direction; /* current scan direction */ + Snapshot es_snapshot; /* time qual to use */ + Snapshot es_crosscheck_snapshot; /* crosscheck time qual for RI */ + List *es_range_table; /* List of RangeTblEntry */ + Index es_range_table_size; /* size of the range table arrays */ + Relation *es_relations; /* Array of per-range-table-entry Relation + * pointers, or NULL if not yet opened */ + struct ExecRowMark **es_rowmarks; /* Array of per-range-table-entry + * ExecRowMarks, or NULL if none */ + List *es_rteperminfos; /* List of RTEPermissionInfo */ + PlannedStmt *es_plannedstmt; /* link to top of plan tree */ + const char *es_sourceText; /* Source text from QueryDesc */ + + JunkFilter *es_junkFilter; /* top-level junk filter, if any */ + + /* If query can insert/delete tuples, the command ID to mark them with */ + CommandId es_output_cid; + + /* Info about target table(s) for insert/update/delete queries: */ + ResultRelInfo **es_result_relations; /* Array of per-range-table-entry + * ResultRelInfo pointers, or NULL + * if not a target table */ + List *es_opened_result_relations; /* List of non-NULL entries in + * es_result_relations in no + * specific order */ + + PartitionDirectory es_partition_directory; /* for PartitionDesc lookup */ + + /* + * The following list contains ResultRelInfos created by the tuple routing + * code for partitions that aren't found in the es_result_relations array. + */ + List *es_tuple_routing_result_relations; + + /* Stuff used for firing triggers: */ + List *es_trig_target_relations; /* trigger-only ResultRelInfos */ + + /* Parameter info: */ + ParamListInfo es_param_list_info; /* values of external params */ + ParamExecData *es_param_exec_vals; /* values of internal params */ + + QueryEnvironment *es_queryEnv; /* query environment */ + + /* Other working state: */ + MemoryContext es_query_cxt; /* per-query context in which EState lives */ + + List *es_tupleTable; /* List of TupleTableSlots */ + + uint64 es_processed; /* # of tuples processed during one + * ExecutorRun() call. */ + uint64 es_total_processed; /* total # of tuples aggregated across all + * ExecutorRun() calls. */ + + int es_top_eflags; /* eflags passed to ExecutorStart */ + int es_instrument; /* OR of InstrumentOption flags */ + bool es_finished; /* true when ExecutorFinish is done */ + + List *es_exprcontexts; /* List of ExprContexts within EState */ + + List *es_subplanstates; /* List of PlanState for SubPlans */ + + List *es_auxmodifytables; /* List of secondary ModifyTableStates */ + + /* + * this ExprContext is for per-output-tuple operations, such as constraint + * checks and index-value computations. It will be reset for each output + * tuple. Note that it will be created only if needed. + */ + ExprContext *es_per_tuple_exprcontext; + + /* + * If not NULL, this is an EPQState's EState. This is a field in EState + * both to allow EvalPlanQual aware executor nodes to detect that they + * need to perform EPQ related work, and to provide necessary information + * to do so. + */ + struct EPQState *es_epq_active; + + bool es_use_parallel_mode; /* can we use parallel workers? */ + + /* The per-query shared memory area to use for parallel execution. */ + struct dsa_area *es_query_dsa; + + /* + * JIT information. es_jit_flags indicates whether JIT should be performed + * and with which options. es_jit is created on-demand when JITing is + * performed. + * + * es_jit_worker_instr is the combined, on demand allocated, + * instrumentation from all workers. The leader's instrumentation is kept + * separate, and is combined on demand by ExplainPrintJITSummary(). + */ + int es_jit_flags; + struct JitContext *es_jit; + struct JitInstrumentation *es_jit_worker_instr; + + /* + * Lists of ResultRelInfos for foreign tables on which batch-inserts are + * to be executed and owning ModifyTableStates, stored in the same order. + */ + List *es_insert_pending_result_relations; + List *es_insert_pending_modifytables; +} EState; + + +/* + * ExecRowMark - + * runtime representation of FOR [KEY] UPDATE/SHARE clauses + * + * When doing UPDATE/DELETE/MERGE/SELECT FOR [KEY] UPDATE/SHARE, we will have + * an ExecRowMark for each non-target relation in the query (except inheritance + * parent RTEs, which can be ignored at runtime). Virtual relations such as + * subqueries-in-FROM will have an ExecRowMark with relation == NULL. See + * PlanRowMark for details about most of the fields. In addition to fields + * directly derived from PlanRowMark, we store an activity flag (to denote + * inactive children of inheritance trees), curCtid, which is used by the + * WHERE CURRENT OF code, and ermExtra, which is available for use by the plan + * node that sources the relation (e.g., for a foreign table the FDW can use + * ermExtra to hold information). + * + * EState->es_rowmarks is an array of these structs, indexed by RT index, + * with NULLs for irrelevant RT indexes. es_rowmarks itself is NULL if + * there are no rowmarks. + */ +typedef struct ExecRowMark +{ + Relation relation; /* opened and suitably locked relation */ + Oid relid; /* its OID (or InvalidOid, if subquery) */ + Index rti; /* its range table index */ + Index prti; /* parent range table index, if child */ + Index rowmarkId; /* unique identifier for resjunk columns */ + RowMarkType markType; /* see enum in nodes/plannodes.h */ + LockClauseStrength strength; /* LockingClause's strength, or LCS_NONE */ + LockWaitPolicy waitPolicy; /* NOWAIT and SKIP LOCKED */ + bool ermActive; /* is this mark relevant for current tuple? */ + ItemPointerData curCtid; /* ctid of currently locked tuple, if any */ + void *ermExtra; /* available for use by relation source node */ +} ExecRowMark; + +/* + * ExecAuxRowMark - + * additional runtime representation of FOR [KEY] UPDATE/SHARE clauses + * + * Each LockRows and ModifyTable node keeps a list of the rowmarks it needs to + * deal with. In addition to a pointer to the related entry in es_rowmarks, + * this struct carries the column number(s) of the resjunk columns associated + * with the rowmark (see comments for PlanRowMark for more detail). + */ +typedef struct ExecAuxRowMark +{ + ExecRowMark *rowmark; /* related entry in es_rowmarks */ + AttrNumber ctidAttNo; /* resno of ctid junk attribute, if any */ + AttrNumber toidAttNo; /* resno of tableoid junk attribute, if any */ + AttrNumber wholeAttNo; /* resno of whole-row junk attribute, if any */ +} ExecAuxRowMark; + + +/* ---------------------------------------------------------------- + * Tuple Hash Tables + * + * All-in-memory tuple hash tables are used for a number of purposes. + * + * Note: tab_hash_funcs are for the key datatype(s) stored in the table, + * and tab_eq_funcs are non-cross-type equality operators for those types. + * Normally these are the only functions used, but FindTupleHashEntry() + * supports searching a hashtable using cross-data-type hashing. For that, + * the caller must supply hash functions for the LHS datatype as well as + * the cross-type equality operators to use. in_hash_funcs and cur_eq_func + * are set to point to the caller's function arrays while doing such a search. + * During LookupTupleHashEntry(), they point to tab_hash_funcs and + * tab_eq_func respectively. + * ---------------------------------------------------------------- + */ +typedef struct TupleHashEntryData *TupleHashEntry; +typedef struct TupleHashTableData *TupleHashTable; + +typedef struct TupleHashEntryData +{ + MinimalTuple firstTuple; /* copy of first tuple in this group */ + void *additional; /* user data */ + uint32 status; /* hash status */ + uint32 hash; /* hash value (cached) */ +} TupleHashEntryData; + +/* define parameters necessary to generate the tuple hash table interface */ +#define SH_PREFIX tuplehash +#define SH_ELEMENT_TYPE TupleHashEntryData +#define SH_KEY_TYPE MinimalTuple +#define SH_SCOPE extern +#define SH_DECLARE +#include "lib/simplehash.h" + +typedef struct TupleHashTableData +{ + tuplehash_hash *hashtab; /* underlying hash table */ + int numCols; /* number of columns in lookup key */ + AttrNumber *keyColIdx; /* attr numbers of key columns */ + FmgrInfo *tab_hash_funcs; /* hash functions for table datatype(s) */ + ExprState *tab_eq_func; /* comparator for table datatype(s) */ + Oid *tab_collations; /* collations for hash and comparison */ + MemoryContext tablecxt; /* memory context containing table */ + MemoryContext tempcxt; /* context for function evaluations */ + Size entrysize; /* actual size to make each hash entry */ + TupleTableSlot *tableslot; /* slot for referencing table entries */ + /* The following fields are set transiently for each table search: */ + TupleTableSlot *inputslot; /* current input tuple's slot */ + FmgrInfo *in_hash_funcs; /* hash functions for input datatype(s) */ + ExprState *cur_eq_func; /* comparator for input vs. table */ + uint32 hash_iv; /* hash-function IV */ + ExprContext *exprcontext; /* expression context */ +} TupleHashTableData; + +typedef tuplehash_iterator TupleHashIterator; + +/* + * Use InitTupleHashIterator/TermTupleHashIterator for a read/write scan. + * Use ResetTupleHashIterator if the table can be frozen (in this case no + * explicit scan termination is needed). + */ +#define InitTupleHashIterator(htable, iter) \ + tuplehash_start_iterate(htable->hashtab, iter) +#define TermTupleHashIterator(iter) \ + ((void) 0) +#define ResetTupleHashIterator(htable, iter) \ + InitTupleHashIterator(htable, iter) +#define ScanTupleHashTable(htable, iter) \ + tuplehash_iterate(htable->hashtab, iter) + + +/* ---------------------------------------------------------------- + * Expression State Nodes + * + * Formerly, there was a separate executor expression state node corresponding + * to each node in a planned expression tree. That's no longer the case; for + * common expression node types, all the execution info is embedded into + * step(s) in a single ExprState node. But we still have a few executor state + * node types for selected expression node types, mostly those in which info + * has to be shared with other parts of the execution state tree. + * ---------------------------------------------------------------- + */ + +/* ---------------- + * WindowFuncExprState node + * ---------------- + */ +typedef struct WindowFuncExprState +{ + NodeTag type; + WindowFunc *wfunc; /* expression plan node */ + List *args; /* ExprStates for argument expressions */ + ExprState *aggfilter; /* FILTER expression */ + int wfuncno; /* ID number for wfunc within its plan node */ +} WindowFuncExprState; + + +/* ---------------- + * SetExprState node + * + * State for evaluating a potentially set-returning expression (like FuncExpr + * or OpExpr). In some cases, like some of the expressions in ROWS FROM(...) + * the expression might not be a SRF, but nonetheless it uses the same + * machinery as SRFs; it will be treated as a SRF returning a single row. + * ---------------- + */ +typedef struct SetExprState +{ + NodeTag type; + Expr *expr; /* expression plan node */ + List *args; /* ExprStates for argument expressions */ + + /* + * In ROWS FROM, functions can be inlined, removing the FuncExpr normally + * inside. In such a case this is the compiled expression (which cannot + * return a set), which'll be evaluated using regular ExecEvalExpr(). + */ + ExprState *elidedFuncState; + + /* + * Function manager's lookup info for the target function. If func.fn_oid + * is InvalidOid, we haven't initialized it yet (nor any of the following + * fields, except funcReturnsSet). + */ + FmgrInfo func; + + /* + * For a set-returning function (SRF) that returns a tuplestore, we keep + * the tuplestore here and dole out the result rows one at a time. The + * slot holds the row currently being returned. + */ + Tuplestorestate *funcResultStore; + TupleTableSlot *funcResultSlot; + + /* + * In some cases we need to compute a tuple descriptor for the function's + * output. If so, it's stored here. + */ + TupleDesc funcResultDesc; + bool funcReturnsTuple; /* valid when funcResultDesc isn't NULL */ + + /* + * Remember whether the function is declared to return a set. This is set + * by ExecInitExpr, and is valid even before the FmgrInfo is set up. + */ + bool funcReturnsSet; + + /* + * setArgsValid is true when we are evaluating a set-returning function + * that uses value-per-call mode and we are in the middle of a call + * series; we want to pass the same argument values to the function again + * (and again, until it returns ExprEndResult). This indicates that + * fcinfo_data already contains valid argument data. + */ + bool setArgsValid; + + /* + * Flag to remember whether we have registered a shutdown callback for + * this SetExprState. We do so only if funcResultStore or setArgsValid + * has been set at least once (since all the callback is for is to release + * the tuplestore or clear setArgsValid). + */ + bool shutdown_reg; /* a shutdown callback is registered */ + + /* + * Call parameter structure for the function. This has been initialized + * (by InitFunctionCallInfoData) if func.fn_oid is valid. It also saves + * argument values between calls, when setArgsValid is true. + */ + FunctionCallInfo fcinfo; +} SetExprState; + +/* ---------------- + * SubPlanState node + * ---------------- + */ +typedef struct SubPlanState +{ + NodeTag type; + SubPlan *subplan; /* expression plan node */ + struct PlanState *planstate; /* subselect plan's state tree */ + struct PlanState *parent; /* parent plan node's state tree */ + ExprState *testexpr; /* state of combining expression */ + List *args; /* states of argument expression(s) */ + HeapTuple curTuple; /* copy of most recent tuple from subplan */ + Datum curArray; /* most recent array from ARRAY() subplan */ + /* these are used when hashing the subselect's output: */ + TupleDesc descRight; /* subselect desc after projection */ + ProjectionInfo *projLeft; /* for projecting lefthand exprs */ + ProjectionInfo *projRight; /* for projecting subselect output */ + TupleHashTable hashtable; /* hash table for no-nulls subselect rows */ + TupleHashTable hashnulls; /* hash table for rows with null(s) */ + bool havehashrows; /* true if hashtable is not empty */ + bool havenullrows; /* true if hashnulls is not empty */ + MemoryContext hashtablecxt; /* memory context containing hash tables */ + MemoryContext hashtempcxt; /* temp memory context for hash tables */ + ExprContext *innerecontext; /* econtext for computing inner tuples */ + int numCols; /* number of columns being hashed */ + /* each of the remaining fields is an array of length numCols: */ + AttrNumber *keyColIdx; /* control data for hash tables */ + Oid *tab_eq_funcoids; /* equality func oids for table + * datatype(s) */ + Oid *tab_collations; /* collations for hash and comparison */ + FmgrInfo *tab_hash_funcs; /* hash functions for table datatype(s) */ + FmgrInfo *tab_eq_funcs; /* equality functions for table datatype(s) */ + FmgrInfo *lhs_hash_funcs; /* hash functions for lefthand datatype(s) */ + FmgrInfo *cur_eq_funcs; /* equality functions for LHS vs. table */ + ExprState *cur_eq_comp; /* equality comparator for LHS vs. table */ +} SubPlanState; + +/* + * DomainConstraintState - one item to check during CoerceToDomain + * + * Note: we consider this to be part of an ExprState tree, so we give it + * a name following the xxxState convention. But there's no directly + * associated plan-tree node. + */ +typedef enum DomainConstraintType +{ + DOM_CONSTRAINT_NOTNULL, + DOM_CONSTRAINT_CHECK +} DomainConstraintType; + +typedef struct DomainConstraintState +{ + NodeTag type; + DomainConstraintType constrainttype; /* constraint type */ + char *name; /* name of constraint (for error msgs) */ + Expr *check_expr; /* for CHECK, a boolean expression */ + ExprState *check_exprstate; /* check_expr's eval state, or NULL */ +} DomainConstraintState; + + +/* ---------------------------------------------------------------- + * Executor State Trees + * + * An executing query has a PlanState tree paralleling the Plan tree + * that describes the plan. + * ---------------------------------------------------------------- + */ + +/* ---------------- + * ExecProcNodeMtd + * + * This is the method called by ExecProcNode to return the next tuple + * from an executor node. It returns NULL, or an empty TupleTableSlot, + * if no more tuples are available. + * ---------------- + */ +typedef TupleTableSlot *(*ExecProcNodeMtd) (struct PlanState *pstate); + +/* ---------------- + * PlanState node + * + * We never actually instantiate any PlanState nodes; this is just the common + * abstract superclass for all PlanState-type nodes. + * ---------------- + */ +typedef struct PlanState +{ + pg_node_attr(abstract) + + NodeTag type; + + Plan *plan; /* associated Plan node */ + + EState *state; /* at execution time, states of individual + * nodes point to one EState for the whole + * top-level plan */ + + ExecProcNodeMtd ExecProcNode; /* function to return next tuple */ + ExecProcNodeMtd ExecProcNodeReal; /* actual function, if above is a + * wrapper */ + + Instrumentation *instrument; /* Optional runtime stats for this node */ + WorkerInstrumentation *worker_instrument; /* per-worker instrumentation */ + + /* Per-worker JIT instrumentation */ + struct SharedJitInstrumentation *worker_jit_instrument; + + /* + * Common structural data for all Plan types. These links to subsidiary + * state trees parallel links in the associated plan tree (except for the + * subPlan list, which does not exist in the plan tree). + */ + ExprState *qual; /* boolean qual condition */ + struct PlanState *lefttree; /* input plan tree(s) */ + struct PlanState *righttree; + + List *initPlan; /* Init SubPlanState nodes (un-correlated expr + * subselects) */ + List *subPlan; /* SubPlanState nodes in my expressions */ + + /* + * State for management of parameter-change-driven rescanning + */ + Bitmapset *chgParam; /* set of IDs of changed Params */ + + /* + * Other run-time state needed by most if not all node types. + */ + TupleDesc ps_ResultTupleDesc; /* node's return type */ + TupleTableSlot *ps_ResultTupleSlot; /* slot for my result tuples */ + ExprContext *ps_ExprContext; /* node's expression-evaluation context */ + ProjectionInfo *ps_ProjInfo; /* info for doing tuple projection */ + + bool async_capable; /* true if node is async-capable */ + + /* + * Scanslot's descriptor if known. This is a bit of a hack, but otherwise + * it's hard for expression compilation to optimize based on the + * descriptor, without encoding knowledge about all executor nodes. + */ + TupleDesc scandesc; + + /* + * Define the slot types for inner, outer and scanslots for expression + * contexts with this state as a parent. If *opsset is set, then + * *opsfixed indicates whether *ops is guaranteed to be the type of slot + * used. That means that every slot in the corresponding + * ExprContext.ecxt_*tuple will point to a slot of that type, while + * evaluating the expression. If *opsfixed is false, but *ops is set, + * that indicates the most likely type of slot. + * + * The scan* fields are set by ExecInitScanTupleSlot(). If that's not + * called, nodes can initialize the fields themselves. + * + * If outer/inneropsset is false, the information is inferred on-demand + * using ExecGetResultSlotOps() on ->righttree/lefttree, using the + * corresponding node's resultops* fields. + * + * The result* fields are automatically set when ExecInitResultSlot is + * used (be it directly or when the slot is created by + * ExecAssignScanProjectionInfo() / + * ExecConditionalAssignProjectionInfo()). If no projection is necessary + * ExecConditionalAssignProjectionInfo() defaults those fields to the scan + * operations. + */ + const TupleTableSlotOps *scanops; + const TupleTableSlotOps *outerops; + const TupleTableSlotOps *innerops; + const TupleTableSlotOps *resultops; + bool scanopsfixed; + bool outeropsfixed; + bool inneropsfixed; + bool resultopsfixed; + bool scanopsset; + bool outeropsset; + bool inneropsset; + bool resultopsset; +} PlanState; + +/* ---------------- + * these are defined to avoid confusion problems with "left" + * and "right" and "inner" and "outer". The convention is that + * the "left" plan is the "outer" plan and the "right" plan is + * the inner plan, but these make the code more readable. + * ---------------- + */ +#define innerPlanState(node) (((PlanState *)(node))->righttree) +#define outerPlanState(node) (((PlanState *)(node))->lefttree) + +/* Macros for inline access to certain instrumentation counters */ +#define InstrCountTuples2(node, delta) \ + do { \ + if (((PlanState *)(node))->instrument) \ + ((PlanState *)(node))->instrument->ntuples2 += (delta); \ + } while (0) +#define InstrCountFiltered1(node, delta) \ + do { \ + if (((PlanState *)(node))->instrument) \ + ((PlanState *)(node))->instrument->nfiltered1 += (delta); \ + } while(0) +#define InstrCountFiltered2(node, delta) \ + do { \ + if (((PlanState *)(node))->instrument) \ + ((PlanState *)(node))->instrument->nfiltered2 += (delta); \ + } while(0) + +/* + * EPQState is state for executing an EvalPlanQual recheck on a candidate + * tuples e.g. in ModifyTable or LockRows. + * + * To execute EPQ a separate EState is created (stored in ->recheckestate), + * which shares some resources, like the rangetable, with the main query's + * EState (stored in ->parentestate). The (sub-)tree of the plan that needs to + * be rechecked (in ->plan), is separately initialized (into + * ->recheckplanstate), but shares plan nodes with the corresponding nodes in + * the main query. The scan nodes in that separate executor tree are changed + * to return only the current tuple of interest for the respective + * table. Those tuples are either provided by the caller (using + * EvalPlanQualSlot), and/or found using the rowmark mechanism (non-locking + * rowmarks by the EPQ machinery itself, locking ones by the caller). + * + * While the plan to be checked may be changed using EvalPlanQualSetPlan(), + * all such plans need to share the same EState. + */ +typedef struct EPQState +{ + /* These are initialized by EvalPlanQualInit() and do not change later: */ + EState *parentestate; /* main query's EState */ + int epqParam; /* ID of Param to force scan node re-eval */ + List *resultRelations; /* integer list of RT indexes, or NIL */ + + /* + * relsubs_slot[scanrelid - 1] holds the EPQ test tuple to be returned by + * the scan node for the scanrelid'th RT index, in place of performing an + * actual table scan. Callers should use EvalPlanQualSlot() to fetch + * these slots. + */ + List *tuple_table; /* tuple table for relsubs_slot */ + TupleTableSlot **relsubs_slot; + + /* + * Initialized by EvalPlanQualInit(), may be changed later with + * EvalPlanQualSetPlan(): + */ + + Plan *plan; /* plan tree to be executed */ + List *arowMarks; /* ExecAuxRowMarks (non-locking only) */ + + + /* + * The original output tuple to be rechecked. Set by + * EvalPlanQualSetSlot(), before EvalPlanQualNext() or EvalPlanQual() may + * be called. + */ + TupleTableSlot *origslot; + + + /* Initialized or reset by EvalPlanQualBegin(): */ + + EState *recheckestate; /* EState for EPQ execution, see above */ + + /* + * Rowmarks that can be fetched on-demand using + * EvalPlanQualFetchRowMark(), indexed by scanrelid - 1. Only non-locking + * rowmarks. + */ + ExecAuxRowMark **relsubs_rowmark; + + /* + * relsubs_done[scanrelid - 1] is true if there is no EPQ tuple for this + * target relation or it has already been fetched in the current scan of + * this target relation within the current EvalPlanQual test. + */ + bool *relsubs_done; + + /* + * relsubs_blocked[scanrelid - 1] is true if there is no EPQ tuple for + * this target relation during the current EvalPlanQual test. We keep + * these flags set for all relids listed in resultRelations, but + * transiently clear the one for the relation whose tuple is actually + * passed to EvalPlanQual(). + */ + bool *relsubs_blocked; + + PlanState *recheckplanstate; /* EPQ specific exec nodes, for ->plan */ +} EPQState; + + +/* ---------------- + * ResultState information + * ---------------- + */ +typedef struct ResultState +{ + PlanState ps; /* its first field is NodeTag */ + ExprState *resconstantqual; + bool rs_done; /* are we done? */ + bool rs_checkqual; /* do we need to check the qual? */ +} ResultState; + +/* ---------------- + * ProjectSetState information + * + * Note: at least one of the "elems" will be a SetExprState; the rest are + * regular ExprStates. + * ---------------- + */ +typedef struct ProjectSetState +{ + PlanState ps; /* its first field is NodeTag */ + Node **elems; /* array of expression states */ + ExprDoneCond *elemdone; /* array of per-SRF is-done states */ + int nelems; /* length of elemdone[] array */ + bool pending_srf_tuples; /* still evaluating srfs in tlist? */ + MemoryContext argcontext; /* context for SRF arguments */ +} ProjectSetState; + + +/* flags for mt_merge_subcommands */ +#define MERGE_INSERT 0x01 +#define MERGE_UPDATE 0x02 +#define MERGE_DELETE 0x04 + +/* ---------------- + * ModifyTableState information + * ---------------- + */ +typedef struct ModifyTableState +{ + PlanState ps; /* its first field is NodeTag */ + CmdType operation; /* INSERT, UPDATE, DELETE, or MERGE */ + bool canSetTag; /* do we set the command tag/es_processed? */ + bool mt_done; /* are we done? */ + int mt_nrels; /* number of entries in resultRelInfo[] */ + ResultRelInfo *resultRelInfo; /* info about target relation(s) */ + + /* + * Target relation mentioned in the original statement, used to fire + * statement-level triggers and as the root for tuple routing. (This + * might point to one of the resultRelInfo[] entries, but it can also be a + * distinct struct.) + */ + ResultRelInfo *rootResultRelInfo; + + EPQState mt_epqstate; /* for evaluating EvalPlanQual rechecks */ + bool fireBSTriggers; /* do we need to fire stmt triggers? */ + + /* + * These fields are used for inherited UPDATE and DELETE, to track which + * target relation a given tuple is from. If there are a lot of target + * relations, we use a hash table to translate table OIDs to + * resultRelInfo[] indexes; otherwise mt_resultOidHash is NULL. + */ + int mt_resultOidAttno; /* resno of "tableoid" junk attr */ + Oid mt_lastResultOid; /* last-seen value of tableoid */ + int mt_lastResultIndex; /* corresponding index in resultRelInfo[] */ + HTAB *mt_resultOidHash; /* optional hash table to speed lookups */ + + /* + * Slot for storing tuples in the root partitioned table's rowtype during + * an UPDATE of a partitioned table. + */ + TupleTableSlot *mt_root_tuple_slot; + + /* Tuple-routing support info */ + struct PartitionTupleRouting *mt_partition_tuple_routing; + + /* controls transition table population for specified operation */ + struct TransitionCaptureState *mt_transition_capture; + + /* controls transition table population for INSERT...ON CONFLICT UPDATE */ + struct TransitionCaptureState *mt_oc_transition_capture; + + /* Flags showing which subcommands are present INS/UPD/DEL/DO NOTHING */ + int mt_merge_subcommands; + + /* tuple counters for MERGE */ + double mt_merge_inserted; + double mt_merge_updated; + double mt_merge_deleted; +} ModifyTableState; + +/* ---------------- + * AppendState information + * + * nplans how many plans are in the array + * whichplan which synchronous plan is being executed (0 .. n-1) + * or a special negative value. See nodeAppend.c. + * prune_state details required to allow partitions to be + * eliminated from the scan, or NULL if not possible. + * valid_subplans for runtime pruning, valid synchronous appendplans + * indexes to scan. + * ---------------- + */ + +struct AppendState; +typedef struct AppendState AppendState; +struct ParallelAppendState; +typedef struct ParallelAppendState ParallelAppendState; +struct PartitionPruneState; + +struct AppendState +{ + PlanState ps; /* its first field is NodeTag */ + PlanState **appendplans; /* array of PlanStates for my inputs */ + int as_nplans; + int as_whichplan; + bool as_begun; /* false means need to initialize */ + Bitmapset *as_asyncplans; /* asynchronous plans indexes */ + int as_nasyncplans; /* # of asynchronous plans */ + AsyncRequest **as_asyncrequests; /* array of AsyncRequests */ + TupleTableSlot **as_asyncresults; /* unreturned results of async plans */ + int as_nasyncresults; /* # of valid entries in as_asyncresults */ + bool as_syncdone; /* true if all synchronous plans done in + * asynchronous mode, else false */ + int as_nasyncremain; /* # of remaining asynchronous plans */ + Bitmapset *as_needrequest; /* asynchronous plans needing a new request */ + struct WaitEventSet *as_eventset; /* WaitEventSet used to configure file + * descriptor wait events */ + int as_first_partial_plan; /* Index of 'appendplans' containing + * the first partial plan */ + ParallelAppendState *as_pstate; /* parallel coordination info */ + Size pstate_len; /* size of parallel coordination info */ + struct PartitionPruneState *as_prune_state; + bool as_valid_subplans_identified; /* is as_valid_subplans valid? */ + Bitmapset *as_valid_subplans; + Bitmapset *as_valid_asyncplans; /* valid asynchronous plans indexes */ + bool (*choose_next_subplan) (AppendState *); +}; + +/* ---------------- + * MergeAppendState information + * + * nplans how many plans are in the array + * nkeys number of sort key columns + * sortkeys sort keys in SortSupport representation + * slots current output tuple of each subplan + * heap heap of active tuples + * initialized true if we have fetched first tuple from each subplan + * prune_state details required to allow partitions to be + * eliminated from the scan, or NULL if not possible. + * valid_subplans for runtime pruning, valid mergeplans indexes to + * scan. + * ---------------- + */ +typedef struct MergeAppendState +{ + PlanState ps; /* its first field is NodeTag */ + PlanState **mergeplans; /* array of PlanStates for my inputs */ + int ms_nplans; + int ms_nkeys; + SortSupport ms_sortkeys; /* array of length ms_nkeys */ + TupleTableSlot **ms_slots; /* array of length ms_nplans */ + struct binaryheap *ms_heap; /* binary heap of slot indices */ + bool ms_initialized; /* are subplans started? */ + struct PartitionPruneState *ms_prune_state; + Bitmapset *ms_valid_subplans; +} MergeAppendState; + +/* ---------------- + * RecursiveUnionState information + * + * RecursiveUnionState is used for performing a recursive union. + * + * recursing T when we're done scanning the non-recursive term + * intermediate_empty T if intermediate_table is currently empty + * working_table working table (to be scanned by recursive term) + * intermediate_table current recursive output (next generation of WT) + * ---------------- + */ +typedef struct RecursiveUnionState +{ + PlanState ps; /* its first field is NodeTag */ + bool recursing; + bool intermediate_empty; + Tuplestorestate *working_table; + Tuplestorestate *intermediate_table; + /* Remaining fields are unused in UNION ALL case */ + Oid *eqfuncoids; /* per-grouping-field equality fns */ + FmgrInfo *hashfunctions; /* per-grouping-field hash fns */ + MemoryContext tempContext; /* short-term context for comparisons */ + TupleHashTable hashtable; /* hash table for tuples already seen */ + MemoryContext tableContext; /* memory context containing hash table */ +} RecursiveUnionState; + +/* ---------------- + * BitmapAndState information + * ---------------- + */ +typedef struct BitmapAndState +{ + PlanState ps; /* its first field is NodeTag */ + PlanState **bitmapplans; /* array of PlanStates for my inputs */ + int nplans; /* number of input plans */ +} BitmapAndState; + +/* ---------------- + * BitmapOrState information + * ---------------- + */ +typedef struct BitmapOrState +{ + PlanState ps; /* its first field is NodeTag */ + PlanState **bitmapplans; /* array of PlanStates for my inputs */ + int nplans; /* number of input plans */ +} BitmapOrState; + +/* ---------------------------------------------------------------- + * Scan State Information + * ---------------------------------------------------------------- + */ + +/* ---------------- + * ScanState information + * + * ScanState extends PlanState for node types that represent + * scans of an underlying relation. It can also be used for nodes + * that scan the output of an underlying plan node --- in that case, + * only ScanTupleSlot is actually useful, and it refers to the tuple + * retrieved from the subplan. + * + * currentRelation relation being scanned (NULL if none) + * currentScanDesc current scan descriptor for scan (NULL if none) + * ScanTupleSlot pointer to slot in tuple table holding scan tuple + * ---------------- + */ +typedef struct ScanState +{ + PlanState ps; /* its first field is NodeTag */ + Relation ss_currentRelation; + struct TableScanDescData *ss_currentScanDesc; + TupleTableSlot *ss_ScanTupleSlot; +} ScanState; + +/* ---------------- + * SeqScanState information + * ---------------- + */ +typedef struct SeqScanState +{ + ScanState ss; /* its first field is NodeTag */ + Size pscan_len; /* size of parallel heap scan descriptor */ +} SeqScanState; + +/* ---------------- + * SampleScanState information + * ---------------- + */ +typedef struct SampleScanState +{ + ScanState ss; + List *args; /* expr states for TABLESAMPLE params */ + ExprState *repeatable; /* expr state for REPEATABLE expr */ + /* use struct pointer to avoid including tsmapi.h here */ + struct TsmRoutine *tsmroutine; /* descriptor for tablesample method */ + void *tsm_state; /* tablesample method can keep state here */ + bool use_bulkread; /* use bulkread buffer access strategy? */ + bool use_pagemode; /* use page-at-a-time visibility checking? */ + bool begun; /* false means need to call BeginSampleScan */ + uint32 seed; /* random seed */ + int64 donetuples; /* number of tuples already returned */ + bool haveblock; /* has a block for sampling been determined */ + bool done; /* exhausted all tuples? */ +} SampleScanState; + +/* + * These structs store information about index quals that don't have simple + * constant right-hand sides. See comments for ExecIndexBuildScanKeys() + * for discussion. + */ +typedef struct +{ + struct ScanKeyData *scan_key; /* scankey to put value into */ + ExprState *key_expr; /* expr to evaluate to get value */ + bool key_toastable; /* is expr's result a toastable datatype? */ +} IndexRuntimeKeyInfo; + +typedef struct +{ + struct ScanKeyData *scan_key; /* scankey to put value into */ + ExprState *array_expr; /* expr to evaluate to get array value */ + int next_elem; /* next array element to use */ + int num_elems; /* number of elems in current array value */ + Datum *elem_values; /* array of num_elems Datums */ + bool *elem_nulls; /* array of num_elems is-null flags */ +} IndexArrayKeyInfo; + +/* ---------------- + * IndexScanState information + * + * indexqualorig execution state for indexqualorig expressions + * indexorderbyorig execution state for indexorderbyorig expressions + * ScanKeys Skey structures for index quals + * NumScanKeys number of ScanKeys + * OrderByKeys Skey structures for index ordering operators + * NumOrderByKeys number of OrderByKeys + * RuntimeKeys info about Skeys that must be evaluated at runtime + * NumRuntimeKeys number of RuntimeKeys + * RuntimeKeysReady true if runtime Skeys have been computed + * RuntimeContext expr context for evaling runtime Skeys + * RelationDesc index relation descriptor + * ScanDesc index scan descriptor + * + * ReorderQueue tuples that need reordering due to re-check + * ReachedEnd have we fetched all tuples from index already? + * OrderByValues values of ORDER BY exprs of last fetched tuple + * OrderByNulls null flags for OrderByValues + * SortSupport for reordering ORDER BY exprs + * OrderByTypByVals is the datatype of order by expression pass-by-value? + * OrderByTypLens typlens of the datatypes of order by expressions + * PscanLen size of parallel index scan descriptor + * ---------------- + */ +typedef struct IndexScanState +{ + ScanState ss; /* its first field is NodeTag */ + ExprState *indexqualorig; + List *indexorderbyorig; + struct ScanKeyData *iss_ScanKeys; + int iss_NumScanKeys; + struct ScanKeyData *iss_OrderByKeys; + int iss_NumOrderByKeys; + IndexRuntimeKeyInfo *iss_RuntimeKeys; + int iss_NumRuntimeKeys; + bool iss_RuntimeKeysReady; + ExprContext *iss_RuntimeContext; + Relation iss_RelationDesc; + struct IndexScanDescData *iss_ScanDesc; + + /* These are needed for re-checking ORDER BY expr ordering */ + pairingheap *iss_ReorderQueue; + bool iss_ReachedEnd; + Datum *iss_OrderByValues; + bool *iss_OrderByNulls; + SortSupport iss_SortSupport; + bool *iss_OrderByTypByVals; + int16 *iss_OrderByTypLens; + Size iss_PscanLen; +} IndexScanState; + +/* ---------------- + * IndexOnlyScanState information + * + * recheckqual execution state for recheckqual expressions + * ScanKeys Skey structures for index quals + * NumScanKeys number of ScanKeys + * OrderByKeys Skey structures for index ordering operators + * NumOrderByKeys number of OrderByKeys + * RuntimeKeys info about Skeys that must be evaluated at runtime + * NumRuntimeKeys number of RuntimeKeys + * RuntimeKeysReady true if runtime Skeys have been computed + * RuntimeContext expr context for evaling runtime Skeys + * RelationDesc index relation descriptor + * ScanDesc index scan descriptor + * TableSlot slot for holding tuples fetched from the table + * VMBuffer buffer in use for visibility map testing, if any + * PscanLen size of parallel index-only scan descriptor + * ---------------- + */ +typedef struct IndexOnlyScanState +{ + ScanState ss; /* its first field is NodeTag */ + ExprState *recheckqual; + struct ScanKeyData *ioss_ScanKeys; + int ioss_NumScanKeys; + struct ScanKeyData *ioss_OrderByKeys; + int ioss_NumOrderByKeys; + IndexRuntimeKeyInfo *ioss_RuntimeKeys; + int ioss_NumRuntimeKeys; + bool ioss_RuntimeKeysReady; + ExprContext *ioss_RuntimeContext; + Relation ioss_RelationDesc; + struct IndexScanDescData *ioss_ScanDesc; + TupleTableSlot *ioss_TableSlot; + Buffer ioss_VMBuffer; + Size ioss_PscanLen; +} IndexOnlyScanState; + +/* ---------------- + * BitmapIndexScanState information + * + * result bitmap to return output into, or NULL + * ScanKeys Skey structures for index quals + * NumScanKeys number of ScanKeys + * RuntimeKeys info about Skeys that must be evaluated at runtime + * NumRuntimeKeys number of RuntimeKeys + * ArrayKeys info about Skeys that come from ScalarArrayOpExprs + * NumArrayKeys number of ArrayKeys + * RuntimeKeysReady true if runtime Skeys have been computed + * RuntimeContext expr context for evaling runtime Skeys + * RelationDesc index relation descriptor + * ScanDesc index scan descriptor + * ---------------- + */ +typedef struct BitmapIndexScanState +{ + ScanState ss; /* its first field is NodeTag */ + TIDBitmap *biss_result; + struct ScanKeyData *biss_ScanKeys; + int biss_NumScanKeys; + IndexRuntimeKeyInfo *biss_RuntimeKeys; + int biss_NumRuntimeKeys; + IndexArrayKeyInfo *biss_ArrayKeys; + int biss_NumArrayKeys; + bool biss_RuntimeKeysReady; + ExprContext *biss_RuntimeContext; + Relation biss_RelationDesc; + struct IndexScanDescData *biss_ScanDesc; +} BitmapIndexScanState; + +/* ---------------- + * SharedBitmapState information + * + * BM_INITIAL TIDBitmap creation is not yet started, so first worker + * to see this state will set the state to BM_INPROGRESS + * and that process will be responsible for creating + * TIDBitmap. + * BM_INPROGRESS TIDBitmap creation is in progress; workers need to + * sleep until it's finished. + * BM_FINISHED TIDBitmap creation is done, so now all workers can + * proceed to iterate over TIDBitmap. + * ---------------- + */ +typedef enum +{ + BM_INITIAL, + BM_INPROGRESS, + BM_FINISHED +} SharedBitmapState; + +/* ---------------- + * ParallelBitmapHeapState information + * tbmiterator iterator for scanning current pages + * prefetch_iterator iterator for prefetching ahead of current page + * mutex mutual exclusion for the prefetching variable + * and state + * prefetch_pages # pages prefetch iterator is ahead of current + * prefetch_target current target prefetch distance + * state current state of the TIDBitmap + * cv conditional wait variable + * phs_snapshot_data snapshot data shared to workers + * ---------------- + */ +typedef struct ParallelBitmapHeapState +{ + dsa_pointer tbmiterator; + dsa_pointer prefetch_iterator; + slock_t mutex; + int prefetch_pages; + int prefetch_target; + SharedBitmapState state; + ConditionVariable cv; + char phs_snapshot_data[FLEXIBLE_ARRAY_MEMBER]; +} ParallelBitmapHeapState; + +/* ---------------- + * BitmapHeapScanState information + * + * bitmapqualorig execution state for bitmapqualorig expressions + * tbm bitmap obtained from child index scan(s) + * tbmiterator iterator for scanning current pages + * tbmres current-page data + * can_skip_fetch can we potentially skip tuple fetches in this scan? + * return_empty_tuples number of empty tuples to return + * vmbuffer buffer for visibility-map lookups + * pvmbuffer ditto, for prefetched pages + * exact_pages total number of exact pages retrieved + * lossy_pages total number of lossy pages retrieved + * prefetch_iterator iterator for prefetching ahead of current page + * prefetch_pages # pages prefetch iterator is ahead of current + * prefetch_target current target prefetch distance + * prefetch_maximum maximum value for prefetch_target + * pscan_len size of the shared memory for parallel bitmap + * initialized is node is ready to iterate + * shared_tbmiterator shared iterator + * shared_prefetch_iterator shared iterator for prefetching + * pstate shared state for parallel bitmap scan + * ---------------- + */ +typedef struct BitmapHeapScanState +{ + ScanState ss; /* its first field is NodeTag */ + ExprState *bitmapqualorig; + TIDBitmap *tbm; + TBMIterator *tbmiterator; + TBMIterateResult *tbmres; + bool can_skip_fetch; + int return_empty_tuples; + Buffer vmbuffer; + Buffer pvmbuffer; + long exact_pages; + long lossy_pages; + TBMIterator *prefetch_iterator; + int prefetch_pages; + int prefetch_target; + int prefetch_maximum; + Size pscan_len; + bool initialized; + TBMSharedIterator *shared_tbmiterator; + TBMSharedIterator *shared_prefetch_iterator; + ParallelBitmapHeapState *pstate; +} BitmapHeapScanState; + +/* ---------------- + * TidScanState information + * + * tidexprs list of TidExpr structs (see nodeTidscan.c) + * isCurrentOf scan has a CurrentOfExpr qual + * NumTids number of tids in this scan + * TidPtr index of currently fetched tid + * TidList evaluated item pointers (array of size NumTids) + * htup currently-fetched tuple, if any + * ---------------- + */ +typedef struct TidScanState +{ + ScanState ss; /* its first field is NodeTag */ + List *tss_tidexprs; + bool tss_isCurrentOf; + int tss_NumTids; + int tss_TidPtr; + ItemPointerData *tss_TidList; + HeapTupleData tss_htup; +} TidScanState; + +/* ---------------- + * TidRangeScanState information + * + * trss_tidexprs list of TidOpExpr structs (see nodeTidrangescan.c) + * trss_mintid the lowest TID in the scan range + * trss_maxtid the highest TID in the scan range + * trss_inScan is a scan currently in progress? + * ---------------- + */ +typedef struct TidRangeScanState +{ + ScanState ss; /* its first field is NodeTag */ + List *trss_tidexprs; + ItemPointerData trss_mintid; + ItemPointerData trss_maxtid; + bool trss_inScan; +} TidRangeScanState; + +/* ---------------- + * SubqueryScanState information + * + * SubqueryScanState is used for scanning a sub-query in the range table. + * ScanTupleSlot references the current output tuple of the sub-query. + * ---------------- + */ +typedef struct SubqueryScanState +{ + ScanState ss; /* its first field is NodeTag */ + PlanState *subplan; +} SubqueryScanState; + +/* ---------------- + * FunctionScanState information + * + * Function nodes are used to scan the results of a + * function appearing in FROM (typically a function returning set). + * + * eflags node's capability flags + * ordinality is this scan WITH ORDINALITY? + * simple true if we have 1 function and no ordinality + * ordinal current ordinal column value + * nfuncs number of functions being executed + * funcstates per-function execution states (private in + * nodeFunctionscan.c) + * argcontext memory context to evaluate function arguments in + * ---------------- + */ +struct FunctionScanPerFuncState; + +typedef struct FunctionScanState +{ + ScanState ss; /* its first field is NodeTag */ + int eflags; + bool ordinality; + bool simple; + int64 ordinal; + int nfuncs; + struct FunctionScanPerFuncState *funcstates; /* array of length nfuncs */ + MemoryContext argcontext; +} FunctionScanState; + +/* ---------------- + * ValuesScanState information + * + * ValuesScan nodes are used to scan the results of a VALUES list + * + * rowcontext per-expression-list context + * exprlists array of expression lists being evaluated + * exprstatelists array of expression state lists, for SubPlans only + * array_len size of above arrays + * curr_idx current array index (0-based) + * + * Note: ss.ps.ps_ExprContext is used to evaluate any qual or projection + * expressions attached to the node. We create a second ExprContext, + * rowcontext, in which to build the executor expression state for each + * Values sublist. Resetting this context lets us get rid of expression + * state for each row, avoiding major memory leakage over a long values list. + * However, that doesn't work for sublists containing SubPlans, because a + * SubPlan has to be connected up to the outer plan tree to work properly. + * Therefore, for only those sublists containing SubPlans, we do expression + * state construction at executor start, and store those pointers in + * exprstatelists[]. NULL entries in that array correspond to simple + * subexpressions that are handled as described above. + * ---------------- + */ +typedef struct ValuesScanState +{ + ScanState ss; /* its first field is NodeTag */ + ExprContext *rowcontext; + List **exprlists; + List **exprstatelists; + int array_len; + int curr_idx; +} ValuesScanState; + +/* ---------------- + * TableFuncScanState node + * + * Used in table-expression functions like XMLTABLE. + * ---------------- + */ +typedef struct TableFuncScanState +{ + ScanState ss; /* its first field is NodeTag */ + ExprState *docexpr; /* state for document expression */ + ExprState *rowexpr; /* state for row-generating expression */ + List *colexprs; /* state for column-generating expression */ + List *coldefexprs; /* state for column default expressions */ + List *ns_names; /* same as TableFunc.ns_names */ + List *ns_uris; /* list of states of namespace URI exprs */ + Bitmapset *notnulls; /* nullability flag for each output column */ + void *opaque; /* table builder private space */ + const struct TableFuncRoutine *routine; /* table builder methods */ + FmgrInfo *in_functions; /* input function for each column */ + Oid *typioparams; /* typioparam for each column */ + int64 ordinal; /* row number to be output next */ + MemoryContext perTableCxt; /* per-table context */ + Tuplestorestate *tupstore; /* output tuple store */ +} TableFuncScanState; + +/* ---------------- + * CteScanState information + * + * CteScan nodes are used to scan a CommonTableExpr query. + * + * Multiple CteScan nodes can read out from the same CTE query. We use + * a tuplestore to hold rows that have been read from the CTE query but + * not yet consumed by all readers. + * ---------------- + */ +typedef struct CteScanState +{ + ScanState ss; /* its first field is NodeTag */ + int eflags; /* capability flags to pass to tuplestore */ + int readptr; /* index of my tuplestore read pointer */ + PlanState *cteplanstate; /* PlanState for the CTE query itself */ + /* Link to the "leader" CteScanState (possibly this same node) */ + struct CteScanState *leader; + /* The remaining fields are only valid in the "leader" CteScanState */ + Tuplestorestate *cte_table; /* rows already read from the CTE query */ + bool eof_cte; /* reached end of CTE query? */ +} CteScanState; + +/* ---------------- + * NamedTuplestoreScanState information + * + * NamedTuplestoreScan nodes are used to scan a Tuplestore created and + * named prior to execution of the query. An example is a transition + * table for an AFTER trigger. + * + * Multiple NamedTuplestoreScan nodes can read out from the same Tuplestore. + * ---------------- + */ +typedef struct NamedTuplestoreScanState +{ + ScanState ss; /* its first field is NodeTag */ + int readptr; /* index of my tuplestore read pointer */ + TupleDesc tupdesc; /* format of the tuples in the tuplestore */ + Tuplestorestate *relation; /* the rows */ +} NamedTuplestoreScanState; + +/* ---------------- + * WorkTableScanState information + * + * WorkTableScan nodes are used to scan the work table created by + * a RecursiveUnion node. We locate the RecursiveUnion node + * during executor startup. + * ---------------- + */ +typedef struct WorkTableScanState +{ + ScanState ss; /* its first field is NodeTag */ + RecursiveUnionState *rustate; +} WorkTableScanState; + +/* ---------------- + * ForeignScanState information + * + * ForeignScan nodes are used to scan foreign-data tables. + * ---------------- + */ +typedef struct ForeignScanState +{ + ScanState ss; /* its first field is NodeTag */ + ExprState *fdw_recheck_quals; /* original quals not in ss.ps.qual */ + Size pscan_len; /* size of parallel coordination information */ + ResultRelInfo *resultRelInfo; /* result rel info, if UPDATE or DELETE */ + /* use struct pointer to avoid including fdwapi.h here */ + struct FdwRoutine *fdwroutine; + void *fdw_state; /* foreign-data wrapper can keep state here */ +} ForeignScanState; + +/* ---------------- + * CustomScanState information + * + * CustomScan nodes are used to execute custom code within executor. + * + * Core code must avoid assuming that the CustomScanState is only as large as + * the structure declared here; providers are allowed to make it the first + * element in a larger structure, and typically would need to do so. The + * struct is actually allocated by the CreateCustomScanState method associated + * with the plan node. Any additional fields can be initialized there, or in + * the BeginCustomScan method. + * ---------------- + */ +struct CustomExecMethods; + +typedef struct CustomScanState +{ + ScanState ss; + uint32 flags; /* mask of CUSTOMPATH_* flags, see + * nodes/extensible.h */ + List *custom_ps; /* list of child PlanState nodes, if any */ + Size pscan_len; /* size of parallel coordination information */ + const struct CustomExecMethods *methods; + const struct TupleTableSlotOps *slotOps; +} CustomScanState; + +/* ---------------------------------------------------------------- + * Join State Information + * ---------------------------------------------------------------- + */ + +/* ---------------- + * JoinState information + * + * Superclass for state nodes of join plans. + * ---------------- + */ +typedef struct JoinState +{ + PlanState ps; + JoinType jointype; + bool single_match; /* True if we should skip to next outer tuple + * after finding one inner match */ + ExprState *joinqual; /* JOIN quals (in addition to ps.qual) */ +} JoinState; + +/* ---------------- + * NestLoopState information + * + * NeedNewOuter true if need new outer tuple on next call + * MatchedOuter true if found a join match for current outer tuple + * NullInnerTupleSlot prepared null tuple for left outer joins + * ---------------- + */ +typedef struct NestLoopState +{ + JoinState js; /* its first field is NodeTag */ + bool nl_NeedNewOuter; + bool nl_MatchedOuter; + TupleTableSlot *nl_NullInnerTupleSlot; +} NestLoopState; + +/* ---------------- + * MergeJoinState information + * + * NumClauses number of mergejoinable join clauses + * Clauses info for each mergejoinable clause + * JoinState current state of ExecMergeJoin state machine + * SkipMarkRestore true if we may skip Mark and Restore operations + * ExtraMarks true to issue extra Mark operations on inner scan + * ConstFalseJoin true if we have a constant-false joinqual + * FillOuter true if should emit unjoined outer tuples anyway + * FillInner true if should emit unjoined inner tuples anyway + * MatchedOuter true if found a join match for current outer tuple + * MatchedInner true if found a join match for current inner tuple + * OuterTupleSlot slot in tuple table for cur outer tuple + * InnerTupleSlot slot in tuple table for cur inner tuple + * MarkedTupleSlot slot in tuple table for marked tuple + * NullOuterTupleSlot prepared null tuple for right outer joins + * NullInnerTupleSlot prepared null tuple for left outer joins + * OuterEContext workspace for computing outer tuple's join values + * InnerEContext workspace for computing inner tuple's join values + * ---------------- + */ +/* private in nodeMergejoin.c: */ +typedef struct MergeJoinClauseData *MergeJoinClause; + +typedef struct MergeJoinState +{ + JoinState js; /* its first field is NodeTag */ + int mj_NumClauses; + MergeJoinClause mj_Clauses; /* array of length mj_NumClauses */ + int mj_JoinState; + bool mj_SkipMarkRestore; + bool mj_ExtraMarks; + bool mj_ConstFalseJoin; + bool mj_FillOuter; + bool mj_FillInner; + bool mj_MatchedOuter; + bool mj_MatchedInner; + TupleTableSlot *mj_OuterTupleSlot; + TupleTableSlot *mj_InnerTupleSlot; + TupleTableSlot *mj_MarkedTupleSlot; + TupleTableSlot *mj_NullOuterTupleSlot; + TupleTableSlot *mj_NullInnerTupleSlot; + ExprContext *mj_OuterEContext; + ExprContext *mj_InnerEContext; +} MergeJoinState; + +/* ---------------- + * HashJoinState information + * + * hashclauses original form of the hashjoin condition + * hj_OuterHashKeys the outer hash keys in the hashjoin condition + * hj_HashOperators the join operators in the hashjoin condition + * hj_HashTable hash table for the hashjoin + * (NULL if table not built yet) + * hj_CurHashValue hash value for current outer tuple + * hj_CurBucketNo regular bucket# for current outer tuple + * hj_CurSkewBucketNo skew bucket# for current outer tuple + * hj_CurTuple last inner tuple matched to current outer + * tuple, or NULL if starting search + * (hj_CurXXX variables are undefined if + * OuterTupleSlot is empty!) + * hj_OuterTupleSlot tuple slot for outer tuples + * hj_HashTupleSlot tuple slot for inner (hashed) tuples + * hj_NullOuterTupleSlot prepared null tuple for right/right-anti/full + * outer joins + * hj_NullInnerTupleSlot prepared null tuple for left/full outer joins + * hj_FirstOuterTupleSlot first tuple retrieved from outer plan + * hj_JoinState current state of ExecHashJoin state machine + * hj_MatchedOuter true if found a join match for current outer + * hj_OuterNotEmpty true if outer relation known not empty + * ---------------- + */ + +/* these structs are defined in executor/hashjoin.h: */ +typedef struct HashJoinTupleData *HashJoinTuple; +typedef struct HashJoinTableData *HashJoinTable; + +typedef struct HashJoinState +{ + JoinState js; /* its first field is NodeTag */ + ExprState *hashclauses; + List *hj_OuterHashKeys; /* list of ExprState nodes */ + List *hj_HashOperators; /* list of operator OIDs */ + List *hj_Collations; + HashJoinTable hj_HashTable; + uint32 hj_CurHashValue; + int hj_CurBucketNo; + int hj_CurSkewBucketNo; + HashJoinTuple hj_CurTuple; + TupleTableSlot *hj_OuterTupleSlot; + TupleTableSlot *hj_HashTupleSlot; + TupleTableSlot *hj_NullOuterTupleSlot; + TupleTableSlot *hj_NullInnerTupleSlot; + TupleTableSlot *hj_FirstOuterTupleSlot; + int hj_JoinState; + bool hj_MatchedOuter; + bool hj_OuterNotEmpty; +} HashJoinState; + + +/* ---------------------------------------------------------------- + * Materialization State Information + * ---------------------------------------------------------------- + */ + +/* ---------------- + * MaterialState information + * + * materialize nodes are used to materialize the results + * of a subplan into a temporary file. + * + * ss.ss_ScanTupleSlot refers to output of underlying plan. + * ---------------- + */ +typedef struct MaterialState +{ + ScanState ss; /* its first field is NodeTag */ + int eflags; /* capability flags to pass to tuplestore */ + bool eof_underlying; /* reached end of underlying plan? */ + Tuplestorestate *tuplestorestate; +} MaterialState; + +struct MemoizeEntry; +struct MemoizeTuple; +struct MemoizeKey; + +typedef struct MemoizeInstrumentation +{ + uint64 cache_hits; /* number of rescans where we've found the + * scan parameter values to be cached */ + uint64 cache_misses; /* number of rescans where we've not found the + * scan parameter values to be cached. */ + uint64 cache_evictions; /* number of cache entries removed due to + * the need to free memory */ + uint64 cache_overflows; /* number of times we've had to bypass the + * cache when filling it due to not being + * able to free enough space to store the + * current scan's tuples. */ + uint64 mem_peak; /* peak memory usage in bytes */ +} MemoizeInstrumentation; + +/* ---------------- + * Shared memory container for per-worker memoize information + * ---------------- + */ +typedef struct SharedMemoizeInfo +{ + int num_workers; + MemoizeInstrumentation sinstrument[FLEXIBLE_ARRAY_MEMBER]; +} SharedMemoizeInfo; + +/* ---------------- + * MemoizeState information + * + * memoize nodes are used to cache recent and commonly seen results from + * a parameterized scan. + * ---------------- + */ +typedef struct MemoizeState +{ + ScanState ss; /* its first field is NodeTag */ + int mstatus; /* value of ExecMemoize state machine */ + int nkeys; /* number of cache keys */ + struct memoize_hash *hashtable; /* hash table for cache entries */ + TupleDesc hashkeydesc; /* tuple descriptor for cache keys */ + TupleTableSlot *tableslot; /* min tuple slot for existing cache entries */ + TupleTableSlot *probeslot; /* virtual slot used for hash lookups */ + ExprState *cache_eq_expr; /* Compare exec params to hash key */ + ExprState **param_exprs; /* exprs containing the parameters to this + * node */ + FmgrInfo *hashfunctions; /* lookup data for hash funcs nkeys in size */ + Oid *collations; /* collation for comparisons nkeys in size */ + uint64 mem_used; /* bytes of memory used by cache */ + uint64 mem_limit; /* memory limit in bytes for the cache */ + MemoryContext tableContext; /* memory context to store cache data */ + dlist_head lru_list; /* least recently used entry list */ + struct MemoizeTuple *last_tuple; /* Used to point to the last tuple + * returned during a cache hit and the + * tuple we last stored when + * populating the cache. */ + struct MemoizeEntry *entry; /* the entry that 'last_tuple' belongs to or + * NULL if 'last_tuple' is NULL. */ + bool singlerow; /* true if the cache entry is to be marked as + * complete after caching the first tuple. */ + bool binary_mode; /* true when cache key should be compared bit + * by bit, false when using hash equality ops */ + MemoizeInstrumentation stats; /* execution statistics */ + SharedMemoizeInfo *shared_info; /* statistics for parallel workers */ + Bitmapset *keyparamids; /* Param->paramids of expressions belonging to + * param_exprs */ +} MemoizeState; + +/* ---------------- + * When performing sorting by multiple keys, it's possible that the input + * dataset is already sorted on a prefix of those keys. We call these + * "presorted keys". + * PresortedKeyData represents information about one such key. + * ---------------- + */ +typedef struct PresortedKeyData +{ + FmgrInfo flinfo; /* comparison function info */ + FunctionCallInfo fcinfo; /* comparison function call info */ + OffsetNumber attno; /* attribute number in tuple */ +} PresortedKeyData; + +/* ---------------- + * Shared memory container for per-worker sort information + * ---------------- + */ +typedef struct SharedSortInfo +{ + int num_workers; + TuplesortInstrumentation sinstrument[FLEXIBLE_ARRAY_MEMBER]; +} SharedSortInfo; + +/* ---------------- + * SortState information + * ---------------- + */ +typedef struct SortState +{ + ScanState ss; /* its first field is NodeTag */ + bool randomAccess; /* need random access to sort output? */ + bool bounded; /* is the result set bounded? */ + int64 bound; /* if bounded, how many tuples are needed */ + bool sort_Done; /* sort completed yet? */ + bool bounded_Done; /* value of bounded we did the sort with */ + int64 bound_Done; /* value of bound we did the sort with */ + void *tuplesortstate; /* private state of tuplesort.c */ + bool am_worker; /* are we a worker? */ + bool datumSort; /* Datum sort instead of tuple sort? */ + SharedSortInfo *shared_info; /* one entry per worker */ +} SortState; + +/* ---------------- + * Instrumentation information for IncrementalSort + * ---------------- + */ +typedef struct IncrementalSortGroupInfo +{ + int64 groupCount; + int64 maxDiskSpaceUsed; + int64 totalDiskSpaceUsed; + int64 maxMemorySpaceUsed; + int64 totalMemorySpaceUsed; + bits32 sortMethods; /* bitmask of TuplesortMethod */ +} IncrementalSortGroupInfo; + +typedef struct IncrementalSortInfo +{ + IncrementalSortGroupInfo fullsortGroupInfo; + IncrementalSortGroupInfo prefixsortGroupInfo; +} IncrementalSortInfo; + +/* ---------------- + * Shared memory container for per-worker incremental sort information + * ---------------- + */ +typedef struct SharedIncrementalSortInfo +{ + int num_workers; + IncrementalSortInfo sinfo[FLEXIBLE_ARRAY_MEMBER]; +} SharedIncrementalSortInfo; + +/* ---------------- + * IncrementalSortState information + * ---------------- + */ +typedef enum +{ + INCSORT_LOADFULLSORT, + INCSORT_LOADPREFIXSORT, + INCSORT_READFULLSORT, + INCSORT_READPREFIXSORT, +} IncrementalSortExecutionStatus; + +typedef struct IncrementalSortState +{ + ScanState ss; /* its first field is NodeTag */ + bool bounded; /* is the result set bounded? */ + int64 bound; /* if bounded, how many tuples are needed */ + bool outerNodeDone; /* finished fetching tuples from outer node */ + int64 bound_Done; /* value of bound we did the sort with */ + IncrementalSortExecutionStatus execution_status; + int64 n_fullsort_remaining; + Tuplesortstate *fullsort_state; /* private state of tuplesort.c */ + Tuplesortstate *prefixsort_state; /* private state of tuplesort.c */ + /* the keys by which the input path is already sorted */ + PresortedKeyData *presorted_keys; + + IncrementalSortInfo incsort_info; + + /* slot for pivot tuple defining values of presorted keys within group */ + TupleTableSlot *group_pivot; + TupleTableSlot *transfer_tuple; + bool am_worker; /* are we a worker? */ + SharedIncrementalSortInfo *shared_info; /* one entry per worker */ +} IncrementalSortState; + +/* --------------------- + * GroupState information + * --------------------- + */ +typedef struct GroupState +{ + ScanState ss; /* its first field is NodeTag */ + ExprState *eqfunction; /* equality function */ + bool grp_done; /* indicates completion of Group scan */ +} GroupState; + +/* --------------------- + * per-worker aggregate information + * --------------------- + */ +typedef struct AggregateInstrumentation +{ + Size hash_mem_peak; /* peak hash table memory usage */ + uint64 hash_disk_used; /* kB of disk space used */ + int hash_batches_used; /* batches used during entire execution */ +} AggregateInstrumentation; + +/* ---------------- + * Shared memory container for per-worker aggregate information + * ---------------- + */ +typedef struct SharedAggInfo +{ + int num_workers; + AggregateInstrumentation sinstrument[FLEXIBLE_ARRAY_MEMBER]; +} SharedAggInfo; + +/* --------------------- + * AggState information + * + * ss.ss_ScanTupleSlot refers to output of underlying plan. + * + * Note: ss.ps.ps_ExprContext contains ecxt_aggvalues and + * ecxt_aggnulls arrays, which hold the computed agg values for the current + * input group during evaluation of an Agg node's output tuple(s). We + * create a second ExprContext, tmpcontext, in which to evaluate input + * expressions and run the aggregate transition functions. + * --------------------- + */ +/* these structs are private in nodeAgg.c: */ +typedef struct AggStatePerAggData *AggStatePerAgg; +typedef struct AggStatePerTransData *AggStatePerTrans; +typedef struct AggStatePerGroupData *AggStatePerGroup; +typedef struct AggStatePerPhaseData *AggStatePerPhase; +typedef struct AggStatePerHashData *AggStatePerHash; + +typedef struct AggState +{ + ScanState ss; /* its first field is NodeTag */ + List *aggs; /* all Aggref nodes in targetlist & quals */ + int numaggs; /* length of list (could be zero!) */ + int numtrans; /* number of pertrans items */ + AggStrategy aggstrategy; /* strategy mode */ + AggSplit aggsplit; /* agg-splitting mode, see nodes.h */ + AggStatePerPhase phase; /* pointer to current phase data */ + int numphases; /* number of phases (including phase 0) */ + int current_phase; /* current phase number */ + AggStatePerAgg peragg; /* per-Aggref information */ + AggStatePerTrans pertrans; /* per-Trans state information */ + ExprContext *hashcontext; /* econtexts for long-lived data (hashtable) */ + ExprContext **aggcontexts; /* econtexts for long-lived data (per GS) */ + ExprContext *tmpcontext; /* econtext for input expressions */ +#define FIELDNO_AGGSTATE_CURAGGCONTEXT 14 + ExprContext *curaggcontext; /* currently active aggcontext */ + AggStatePerAgg curperagg; /* currently active aggregate, if any */ +#define FIELDNO_AGGSTATE_CURPERTRANS 16 + AggStatePerTrans curpertrans; /* currently active trans state, if any */ + bool input_done; /* indicates end of input */ + bool agg_done; /* indicates completion of Agg scan */ + int projected_set; /* The last projected grouping set */ +#define FIELDNO_AGGSTATE_CURRENT_SET 20 + int current_set; /* The current grouping set being evaluated */ + Bitmapset *grouped_cols; /* grouped cols in current projection */ + List *all_grouped_cols; /* list of all grouped cols in DESC order */ + Bitmapset *colnos_needed; /* all columns needed from the outer plan */ + int max_colno_needed; /* highest colno needed from outer plan */ + bool all_cols_needed; /* are all cols from outer plan needed? */ + /* These fields are for grouping set phase data */ + int maxsets; /* The max number of sets in any phase */ + AggStatePerPhase phases; /* array of all phases */ + Tuplesortstate *sort_in; /* sorted input to phases > 1 */ + Tuplesortstate *sort_out; /* input is copied here for next phase */ + TupleTableSlot *sort_slot; /* slot for sort results */ + /* these fields are used in AGG_PLAIN and AGG_SORTED modes: */ + AggStatePerGroup *pergroups; /* grouping set indexed array of per-group + * pointers */ + HeapTuple grp_firstTuple; /* copy of first tuple of current group */ + /* these fields are used in AGG_HASHED and AGG_MIXED modes: */ + bool table_filled; /* hash table filled yet? */ + int num_hashes; + MemoryContext hash_metacxt; /* memory for hash table itself */ + struct LogicalTapeSet *hash_tapeset; /* tape set for hash spill tapes */ + struct HashAggSpill *hash_spills; /* HashAggSpill for each grouping set, + * exists only during first pass */ + TupleTableSlot *hash_spill_rslot; /* for reading spill files */ + TupleTableSlot *hash_spill_wslot; /* for writing spill files */ + List *hash_batches; /* hash batches remaining to be processed */ + bool hash_ever_spilled; /* ever spilled during this execution? */ + bool hash_spill_mode; /* we hit a limit during the current batch + * and we must not create new groups */ + Size hash_mem_limit; /* limit before spilling hash table */ + uint64 hash_ngroups_limit; /* limit before spilling hash table */ + int hash_planned_partitions; /* number of partitions planned + * for first pass */ + double hashentrysize; /* estimate revised during execution */ + Size hash_mem_peak; /* peak hash table memory usage */ + uint64 hash_ngroups_current; /* number of groups currently in + * memory in all hash tables */ + uint64 hash_disk_used; /* kB of disk space used */ + int hash_batches_used; /* batches used during entire execution */ + + AggStatePerHash perhash; /* array of per-hashtable data */ + AggStatePerGroup *hash_pergroup; /* grouping set indexed array of + * per-group pointers */ + + /* support for evaluation of agg input expressions: */ +#define FIELDNO_AGGSTATE_ALL_PERGROUPS 53 + AggStatePerGroup *all_pergroups; /* array of first ->pergroups, than + * ->hash_pergroup */ + ProjectionInfo *combinedproj; /* projection machinery */ + SharedAggInfo *shared_info; /* one entry per worker */ +} AggState; + +/* ---------------- + * WindowAggState information + * ---------------- + */ +/* these structs are private in nodeWindowAgg.c: */ +typedef struct WindowStatePerFuncData *WindowStatePerFunc; +typedef struct WindowStatePerAggData *WindowStatePerAgg; + +/* + * WindowAggStatus -- Used to track the status of WindowAggState + */ +typedef enum WindowAggStatus +{ + WINDOWAGG_DONE, /* No more processing to do */ + WINDOWAGG_RUN, /* Normal processing of window funcs */ + WINDOWAGG_PASSTHROUGH, /* Don't eval window funcs */ + WINDOWAGG_PASSTHROUGH_STRICT /* Pass-through plus don't store new + * tuples during spool */ +} WindowAggStatus; + +typedef struct WindowAggState +{ + ScanState ss; /* its first field is NodeTag */ + + /* these fields are filled in by ExecInitExpr: */ + List *funcs; /* all WindowFunc nodes in targetlist */ + int numfuncs; /* total number of window functions */ + int numaggs; /* number that are plain aggregates */ + + WindowStatePerFunc perfunc; /* per-window-function information */ + WindowStatePerAgg peragg; /* per-plain-aggregate information */ + ExprState *partEqfunction; /* equality funcs for partition columns */ + ExprState *ordEqfunction; /* equality funcs for ordering columns */ + Tuplestorestate *buffer; /* stores rows of current partition */ + int current_ptr; /* read pointer # for current row */ + int framehead_ptr; /* read pointer # for frame head, if used */ + int frametail_ptr; /* read pointer # for frame tail, if used */ + int grouptail_ptr; /* read pointer # for group tail, if used */ + int64 spooled_rows; /* total # of rows in buffer */ + int64 currentpos; /* position of current row in partition */ + int64 frameheadpos; /* current frame head position */ + int64 frametailpos; /* current frame tail position (frame end+1) */ + /* use struct pointer to avoid including windowapi.h here */ + struct WindowObjectData *agg_winobj; /* winobj for aggregate fetches */ + int64 aggregatedbase; /* start row for current aggregates */ + int64 aggregatedupto; /* rows before this one are aggregated */ + WindowAggStatus status; /* run status of WindowAggState */ + + int frameOptions; /* frame_clause options, see WindowDef */ + ExprState *startOffset; /* expression for starting bound offset */ + ExprState *endOffset; /* expression for ending bound offset */ + Datum startOffsetValue; /* result of startOffset evaluation */ + Datum endOffsetValue; /* result of endOffset evaluation */ + + /* these fields are used with RANGE offset PRECEDING/FOLLOWING: */ + FmgrInfo startInRangeFunc; /* in_range function for startOffset */ + FmgrInfo endInRangeFunc; /* in_range function for endOffset */ + Oid inRangeColl; /* collation for in_range tests */ + bool inRangeAsc; /* use ASC sort order for in_range tests? */ + bool inRangeNullsFirst; /* nulls sort first for in_range tests? */ + + /* these fields are used in GROUPS mode: */ + int64 currentgroup; /* peer group # of current row in partition */ + int64 frameheadgroup; /* peer group # of frame head row */ + int64 frametailgroup; /* peer group # of frame tail row */ + int64 groupheadpos; /* current row's peer group head position */ + int64 grouptailpos; /* " " " " tail position (group end+1) */ + + MemoryContext partcontext; /* context for partition-lifespan data */ + MemoryContext aggcontext; /* shared context for aggregate working data */ + MemoryContext curaggcontext; /* current aggregate's working data */ + ExprContext *tmpcontext; /* short-term evaluation context */ + + ExprState *runcondition; /* Condition which must remain true otherwise + * execution of the WindowAgg will finish or + * go into pass-through mode. NULL when there + * is no such condition. */ + + bool use_pass_through; /* When false, stop execution when + * runcondition is no longer true. Else + * just stop evaluating window funcs. */ + bool top_window; /* true if this is the top-most WindowAgg or + * the only WindowAgg in this query level */ + bool all_first; /* true if the scan is starting */ + bool partition_spooled; /* true if all tuples in current partition + * have been spooled into tuplestore */ + bool more_partitions; /* true if there's more partitions after + * this one */ + bool framehead_valid; /* true if frameheadpos is known up to + * date for current row */ + bool frametail_valid; /* true if frametailpos is known up to + * date for current row */ + bool grouptail_valid; /* true if grouptailpos is known up to + * date for current row */ + + TupleTableSlot *first_part_slot; /* first tuple of current or next + * partition */ + TupleTableSlot *framehead_slot; /* first tuple of current frame */ + TupleTableSlot *frametail_slot; /* first tuple after current frame */ + + /* temporary slots for tuples fetched back from tuplestore */ + TupleTableSlot *agg_row_slot; + TupleTableSlot *temp_slot_1; + TupleTableSlot *temp_slot_2; +} WindowAggState; + +/* ---------------- + * UniqueState information + * + * Unique nodes are used "on top of" sort nodes to discard + * duplicate tuples returned from the sort phase. Basically + * all it does is compare the current tuple from the subplan + * with the previously fetched tuple (stored in its result slot). + * If the two are identical in all interesting fields, then + * we just fetch another tuple from the sort and try again. + * ---------------- + */ +typedef struct UniqueState +{ + PlanState ps; /* its first field is NodeTag */ + ExprState *eqfunction; /* tuple equality qual */ +} UniqueState; + +/* ---------------- + * GatherState information + * + * Gather nodes launch 1 or more parallel workers, run a subplan + * in those workers, and collect the results. + * ---------------- + */ +typedef struct GatherState +{ + PlanState ps; /* its first field is NodeTag */ + bool initialized; /* workers launched? */ + bool need_to_scan_locally; /* need to read from local plan? */ + int64 tuples_needed; /* tuple bound, see ExecSetTupleBound */ + /* these fields are set up once: */ + TupleTableSlot *funnel_slot; + struct ParallelExecutorInfo *pei; + /* all remaining fields are reinitialized during a rescan: */ + int nworkers_launched; /* original number of workers */ + int nreaders; /* number of still-active workers */ + int nextreader; /* next one to try to read from */ + struct TupleQueueReader **reader; /* array with nreaders active entries */ +} GatherState; + +/* ---------------- + * GatherMergeState information + * + * Gather merge nodes launch 1 or more parallel workers, run a + * subplan which produces sorted output in each worker, and then + * merge the results into a single sorted stream. + * ---------------- + */ +struct GMReaderTupleBuffer; /* private in nodeGatherMerge.c */ + +typedef struct GatherMergeState +{ + PlanState ps; /* its first field is NodeTag */ + bool initialized; /* workers launched? */ + bool gm_initialized; /* gather_merge_init() done? */ + bool need_to_scan_locally; /* need to read from local plan? */ + int64 tuples_needed; /* tuple bound, see ExecSetTupleBound */ + /* these fields are set up once: */ + TupleDesc tupDesc; /* descriptor for subplan result tuples */ + int gm_nkeys; /* number of sort columns */ + SortSupport gm_sortkeys; /* array of length gm_nkeys */ + struct ParallelExecutorInfo *pei; + /* all remaining fields are reinitialized during a rescan */ + /* (but the arrays are not reallocated, just cleared) */ + int nworkers_launched; /* original number of workers */ + int nreaders; /* number of active workers */ + TupleTableSlot **gm_slots; /* array with nreaders+1 entries */ + struct TupleQueueReader **reader; /* array with nreaders active entries */ + struct GMReaderTupleBuffer *gm_tuple_buffers; /* nreaders tuple buffers */ + struct binaryheap *gm_heap; /* binary heap of slot indices */ +} GatherMergeState; + +/* ---------------- + * Values displayed by EXPLAIN ANALYZE + * ---------------- + */ +typedef struct HashInstrumentation +{ + int nbuckets; /* number of buckets at end of execution */ + int nbuckets_original; /* planned number of buckets */ + int nbatch; /* number of batches at end of execution */ + int nbatch_original; /* planned number of batches */ + Size space_peak; /* peak memory usage in bytes */ +} HashInstrumentation; + +/* ---------------- + * Shared memory container for per-worker hash information + * ---------------- + */ +typedef struct SharedHashInfo +{ + int num_workers; + HashInstrumentation hinstrument[FLEXIBLE_ARRAY_MEMBER]; +} SharedHashInfo; + +/* ---------------- + * HashState information + * ---------------- + */ +typedef struct HashState +{ + PlanState ps; /* its first field is NodeTag */ + HashJoinTable hashtable; /* hash table for the hashjoin */ + List *hashkeys; /* list of ExprState nodes */ + + /* + * In a parallelized hash join, the leader retains a pointer to the + * shared-memory stats area in its shared_info field, and then copies the + * shared-memory info back to local storage before DSM shutdown. The + * shared_info field remains NULL in workers, or in non-parallel joins. + */ + SharedHashInfo *shared_info; + + /* + * If we are collecting hash stats, this points to an initially-zeroed + * collection area, which could be either local storage or in shared + * memory; either way it's for just one process. + */ + HashInstrumentation *hinstrument; + + /* Parallel hash state. */ + struct ParallelHashJoinState *parallel_state; +} HashState; + +/* ---------------- + * SetOpState information + * + * Even in "sorted" mode, SetOp nodes are more complex than a simple + * Unique, since we have to count how many duplicates to return. But + * we also support hashing, so this is really more like a cut-down + * form of Agg. + * ---------------- + */ +/* this struct is private in nodeSetOp.c: */ +typedef struct SetOpStatePerGroupData *SetOpStatePerGroup; + +typedef struct SetOpState +{ + PlanState ps; /* its first field is NodeTag */ + ExprState *eqfunction; /* equality comparator */ + Oid *eqfuncoids; /* per-grouping-field equality fns */ + FmgrInfo *hashfunctions; /* per-grouping-field hash fns */ + bool setop_done; /* indicates completion of output scan */ + long numOutput; /* number of dups left to output */ + /* these fields are used in SETOP_SORTED mode: */ + SetOpStatePerGroup pergroup; /* per-group working state */ + HeapTuple grp_firstTuple; /* copy of first tuple of current group */ + /* these fields are used in SETOP_HASHED mode: */ + TupleHashTable hashtable; /* hash table with one entry per group */ + MemoryContext tableContext; /* memory context containing hash table */ + bool table_filled; /* hash table filled yet? */ + TupleHashIterator hashiter; /* for iterating through hash table */ +} SetOpState; + +/* ---------------- + * LockRowsState information + * + * LockRows nodes are used to enforce FOR [KEY] UPDATE/SHARE locking. + * ---------------- + */ +typedef struct LockRowsState +{ + PlanState ps; /* its first field is NodeTag */ + List *lr_arowMarks; /* List of ExecAuxRowMarks */ + EPQState lr_epqstate; /* for evaluating EvalPlanQual rechecks */ +} LockRowsState; + +/* ---------------- + * LimitState information + * + * Limit nodes are used to enforce LIMIT/OFFSET clauses. + * They just select the desired subrange of their subplan's output. + * + * offset is the number of initial tuples to skip (0 does nothing). + * count is the number of tuples to return after skipping the offset tuples. + * If no limit count was specified, count is undefined and noCount is true. + * When lstate == LIMIT_INITIAL, offset/count/noCount haven't been set yet. + * ---------------- + */ +typedef enum +{ + LIMIT_INITIAL, /* initial state for LIMIT node */ + LIMIT_RESCAN, /* rescan after recomputing parameters */ + LIMIT_EMPTY, /* there are no returnable rows */ + LIMIT_INWINDOW, /* have returned a row in the window */ + LIMIT_WINDOWEND_TIES, /* have returned a tied row */ + LIMIT_SUBPLANEOF, /* at EOF of subplan (within window) */ + LIMIT_WINDOWEND, /* stepped off end of window */ + LIMIT_WINDOWSTART /* stepped off beginning of window */ +} LimitStateCond; + +typedef struct LimitState +{ + PlanState ps; /* its first field is NodeTag */ + ExprState *limitOffset; /* OFFSET parameter, or NULL if none */ + ExprState *limitCount; /* COUNT parameter, or NULL if none */ + LimitOption limitOption; /* limit specification type */ + int64 offset; /* current OFFSET value */ + int64 count; /* current COUNT, if any */ + bool noCount; /* if true, ignore count */ + LimitStateCond lstate; /* state machine status, as above */ + int64 position; /* 1-based index of last tuple returned */ + TupleTableSlot *subSlot; /* tuple last obtained from subplan */ + ExprState *eqfunction; /* tuple equality qual in case of WITH TIES + * option */ + TupleTableSlot *last_slot; /* slot for evaluation of ties */ +} LimitState; + +#endif /* EXECNODES_H */ diff --git a/src/include/nodes/extensible.h b/src/include/nodes/extensible.h new file mode 100644 index 0000000..7d51c60 --- /dev/null +++ b/src/include/nodes/extensible.h @@ -0,0 +1,164 @@ +/*------------------------------------------------------------------------- + * + * extensible.h + * Definitions for extensible nodes and custom scans + * + * + * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/nodes/extensible.h + * + *------------------------------------------------------------------------- + */ +#ifndef EXTENSIBLE_H +#define EXTENSIBLE_H + +#include "access/parallel.h" +#include "commands/explain.h" +#include "nodes/execnodes.h" +#include "nodes/pathnodes.h" +#include "nodes/plannodes.h" + +/* maximum length of an extensible node identifier */ +#define EXTNODENAME_MAX_LEN 64 + +/* + * An extensible node is a new type of node defined by an extension. The + * type is always T_ExtensibleNode, while the extnodename identifies the + * specific type of node. extnodename can be looked up to find the + * ExtensibleNodeMethods for this node type. + */ +typedef struct ExtensibleNode +{ + pg_node_attr(custom_copy_equal, custom_read_write) + + NodeTag type; + const char *extnodename; /* identifier of ExtensibleNodeMethods */ +} ExtensibleNode; + +/* + * node_size is the size of an extensible node of this type in bytes. + * + * nodeCopy is a function which performs a deep copy from oldnode to newnode. + * It does not need to copy type or extnodename, which are copied by the + * core system. + * + * nodeEqual is a function which performs a deep equality comparison between + * a and b and returns true or false accordingly. It does not need to compare + * type or extnodename, which are compared by the core system. + * + * nodeOut is a serialization function for the node type. It should use the + * output conventions typical for outfuncs.c. It does not need to output + * type or extnodename; the core system handles those. + * + * nodeRead is a deserialization function for the node type. It does not need + * to read type or extnodename; the core system handles those. It should fetch + * the next token using pg_strtok() from the current input stream, and then + * reconstruct the private fields according to the manner in readfuncs.c. + * + * All callbacks are mandatory. + */ +typedef struct ExtensibleNodeMethods +{ + const char *extnodename; + Size node_size; + void (*nodeCopy) (struct ExtensibleNode *newnode, + const struct ExtensibleNode *oldnode); + bool (*nodeEqual) (const struct ExtensibleNode *a, + const struct ExtensibleNode *b); + void (*nodeOut) (struct StringInfoData *str, + const struct ExtensibleNode *node); + void (*nodeRead) (struct ExtensibleNode *node); +} ExtensibleNodeMethods; + +extern void RegisterExtensibleNodeMethods(const ExtensibleNodeMethods *methods); +extern const ExtensibleNodeMethods *GetExtensibleNodeMethods(const char *extnodename, + bool missing_ok); + +/* + * Flags for custom paths, indicating what capabilities the resulting scan + * will have. The flags fields of CustomPath and CustomScan nodes are + * bitmasks of these flags. + */ +#define CUSTOMPATH_SUPPORT_BACKWARD_SCAN 0x0001 +#define CUSTOMPATH_SUPPORT_MARK_RESTORE 0x0002 +#define CUSTOMPATH_SUPPORT_PROJECTION 0x0004 + +/* + * Custom path methods. Mostly, we just need to know how to convert a + * CustomPath to a plan. + */ +typedef struct CustomPathMethods +{ + const char *CustomName; + + /* Convert Path to a Plan */ + struct Plan *(*PlanCustomPath) (PlannerInfo *root, + RelOptInfo *rel, + struct CustomPath *best_path, + List *tlist, + List *clauses, + List *custom_plans); + struct List *(*ReparameterizeCustomPathByChild) (PlannerInfo *root, + List *custom_private, + RelOptInfo *child_rel); +} CustomPathMethods; + +/* + * Custom scan. Here again, there's not much to do: we need to be able to + * generate a ScanState corresponding to the scan. + */ +typedef struct CustomScanMethods +{ + const char *CustomName; + + /* Create execution state (CustomScanState) from a CustomScan plan node */ + Node *(*CreateCustomScanState) (CustomScan *cscan); +} CustomScanMethods; + +/* + * Execution-time methods for a CustomScanState. This is more complex than + * what we need for a custom path or scan. + */ +typedef struct CustomExecMethods +{ + const char *CustomName; + + /* Required executor methods */ + void (*BeginCustomScan) (CustomScanState *node, + EState *estate, + int eflags); + TupleTableSlot *(*ExecCustomScan) (CustomScanState *node); + void (*EndCustomScan) (CustomScanState *node); + void (*ReScanCustomScan) (CustomScanState *node); + + /* Optional methods: needed if mark/restore is supported */ + void (*MarkPosCustomScan) (CustomScanState *node); + void (*RestrPosCustomScan) (CustomScanState *node); + + /* Optional methods: needed if parallel execution is supported */ + Size (*EstimateDSMCustomScan) (CustomScanState *node, + ParallelContext *pcxt); + void (*InitializeDSMCustomScan) (CustomScanState *node, + ParallelContext *pcxt, + void *coordinate); + void (*ReInitializeDSMCustomScan) (CustomScanState *node, + ParallelContext *pcxt, + void *coordinate); + void (*InitializeWorkerCustomScan) (CustomScanState *node, + shm_toc *toc, + void *coordinate); + void (*ShutdownCustomScan) (CustomScanState *node); + + /* Optional: print additional information in EXPLAIN */ + void (*ExplainCustomScan) (CustomScanState *node, + List *ancestors, + ExplainState *es); +} CustomExecMethods; + +extern void RegisterCustomScanMethods(const CustomScanMethods *methods); +extern const CustomScanMethods *GetCustomScanMethods(const char *CustomName, + bool missing_ok); + +#endif /* EXTENSIBLE_H */ diff --git a/src/include/nodes/lockoptions.h b/src/include/nodes/lockoptions.h new file mode 100644 index 0000000..bc5e983 --- /dev/null +++ b/src/include/nodes/lockoptions.h @@ -0,0 +1,61 @@ +/*------------------------------------------------------------------------- + * + * lockoptions.h + * Common header for some locking-related declarations. + * + * + * Copyright (c) 2014-2023, PostgreSQL Global Development Group + * + * src/include/nodes/lockoptions.h + * + *------------------------------------------------------------------------- + */ +#ifndef LOCKOPTIONS_H +#define LOCKOPTIONS_H + +/* + * This enum represents the different strengths of FOR UPDATE/SHARE clauses. + * The ordering here is important, because the highest numerical value takes + * precedence when a RTE is specified multiple ways. See applyLockingClause. + */ +typedef enum LockClauseStrength +{ + LCS_NONE, /* no such clause - only used in PlanRowMark */ + LCS_FORKEYSHARE, /* FOR KEY SHARE */ + LCS_FORSHARE, /* FOR SHARE */ + LCS_FORNOKEYUPDATE, /* FOR NO KEY UPDATE */ + LCS_FORUPDATE /* FOR UPDATE */ +} LockClauseStrength; + +/* + * This enum controls how to deal with rows being locked by FOR UPDATE/SHARE + * clauses (i.e., it represents the NOWAIT and SKIP LOCKED options). + * The ordering here is important, because the highest numerical value takes + * precedence when a RTE is specified multiple ways. See applyLockingClause. + */ +typedef enum LockWaitPolicy +{ + /* Wait for the lock to become available (default behavior) */ + LockWaitBlock, + /* Skip rows that can't be locked (SKIP LOCKED) */ + LockWaitSkip, + /* Raise an error if a row cannot be locked (NOWAIT) */ + LockWaitError +} LockWaitPolicy; + +/* + * Possible lock modes for a tuple. + */ +typedef enum LockTupleMode +{ + /* SELECT FOR KEY SHARE */ + LockTupleKeyShare, + /* SELECT FOR SHARE */ + LockTupleShare, + /* SELECT FOR NO KEY UPDATE, and UPDATEs that don't modify key columns */ + LockTupleNoKeyExclusive, + /* SELECT FOR UPDATE, UPDATEs that modify key columns, and DELETE */ + LockTupleExclusive +} LockTupleMode; + +#endif /* LOCKOPTIONS_H */ diff --git a/src/include/nodes/makefuncs.h b/src/include/nodes/makefuncs.h new file mode 100644 index 0000000..3180703 --- /dev/null +++ b/src/include/nodes/makefuncs.h @@ -0,0 +1,121 @@ +/*------------------------------------------------------------------------- + * + * makefuncs.h + * prototypes for the creator functions of various nodes + * + * + * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/nodes/makefuncs.h + * + *------------------------------------------------------------------------- + */ +#ifndef MAKEFUNC_H +#define MAKEFUNC_H + +#include "nodes/execnodes.h" +#include "nodes/parsenodes.h" + + +extern A_Expr *makeA_Expr(A_Expr_Kind kind, List *name, + Node *lexpr, Node *rexpr, int location); + +extern A_Expr *makeSimpleA_Expr(A_Expr_Kind kind, char *name, + Node *lexpr, Node *rexpr, int location); + +extern Var *makeVar(int varno, + AttrNumber varattno, + Oid vartype, + int32 vartypmod, + Oid varcollid, + Index varlevelsup); + +extern Var *makeVarFromTargetEntry(int varno, + TargetEntry *tle); + +extern Var *makeWholeRowVar(RangeTblEntry *rte, + int varno, + Index varlevelsup, + bool allowScalar); + +extern TargetEntry *makeTargetEntry(Expr *expr, + AttrNumber resno, + char *resname, + bool resjunk); + +extern TargetEntry *flatCopyTargetEntry(TargetEntry *src_tle); + +extern FromExpr *makeFromExpr(List *fromlist, Node *quals); + +extern Const *makeConst(Oid consttype, + int32 consttypmod, + Oid constcollid, + int constlen, + Datum constvalue, + bool constisnull, + bool constbyval); + +extern Const *makeNullConst(Oid consttype, int32 consttypmod, Oid constcollid); + +extern Node *makeBoolConst(bool value, bool isnull); + +extern Expr *makeBoolExpr(BoolExprType boolop, List *args, int location); + +extern Alias *makeAlias(const char *aliasname, List *colnames); + +extern RelabelType *makeRelabelType(Expr *arg, Oid rtype, int32 rtypmod, + Oid rcollid, CoercionForm rformat); + +extern RangeVar *makeRangeVar(char *schemaname, char *relname, int location); + +extern TypeName *makeTypeName(char *typnam); +extern TypeName *makeTypeNameFromNameList(List *names); +extern TypeName *makeTypeNameFromOid(Oid typeOid, int32 typmod); + +extern ColumnDef *makeColumnDef(const char *colname, + Oid typeOid, int32 typmod, Oid collOid); + +extern FuncExpr *makeFuncExpr(Oid funcid, Oid rettype, List *args, + Oid funccollid, Oid inputcollid, CoercionForm fformat); + +extern FuncCall *makeFuncCall(List *name, List *args, + CoercionForm funcformat, int location); + +extern Expr *make_opclause(Oid opno, Oid opresulttype, bool opretset, + Expr *leftop, Expr *rightop, + Oid opcollid, Oid inputcollid); + +extern Expr *make_andclause(List *andclauses); +extern Expr *make_orclause(List *orclauses); +extern Expr *make_notclause(Expr *notclause); + +extern Node *make_and_qual(Node *qual1, Node *qual2); +extern Expr *make_ands_explicit(List *andclauses); +extern List *make_ands_implicit(Expr *clause); + +extern IndexInfo *makeIndexInfo(int numattrs, int numkeyattrs, Oid amoid, + List *expressions, List *predicates, + bool unique, bool nulls_not_distinct, + bool isready, bool concurrent, + bool summarizing); + +extern DefElem *makeDefElem(char *name, Node *arg, int location); +extern DefElem *makeDefElemExtended(char *nameSpace, char *name, Node *arg, + DefElemAction defaction, int location); + +extern GroupingSet *makeGroupingSet(GroupingSetKind kind, List *content, int location); + +extern VacuumRelation *makeVacuumRelation(RangeVar *relation, Oid oid, List *va_cols); + +extern JsonFormat *makeJsonFormat(JsonFormatType type, JsonEncoding encoding, + int location); +extern JsonValueExpr *makeJsonValueExpr(Expr *raw_expr, Expr *formatted_expr, + JsonFormat *format); +extern Node *makeJsonKeyValue(Node *key, Node *value); +extern Node *makeJsonIsPredicate(Node *expr, JsonFormat *format, + JsonValueType item_type, bool unique_keys, + int location); +extern JsonEncoding makeJsonEncoding(char *name); + +#endif /* MAKEFUNC_H */ diff --git a/src/include/nodes/memnodes.h b/src/include/nodes/memnodes.h new file mode 100644 index 0000000..ff6453b --- /dev/null +++ b/src/include/nodes/memnodes.h @@ -0,0 +1,113 @@ +/*------------------------------------------------------------------------- + * + * memnodes.h + * POSTGRES memory context node definitions. + * + * + * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/nodes/memnodes.h + * + *------------------------------------------------------------------------- + */ +#ifndef MEMNODES_H +#define MEMNODES_H + +#include "nodes/nodes.h" + +/* + * MemoryContextCounters + * Summarization state for MemoryContextStats collection. + * + * The set of counters in this struct is biased towards AllocSet; if we ever + * add any context types that are based on fundamentally different approaches, + * we might need more or different counters here. A possible API spec then + * would be to print only nonzero counters, but for now we just summarize in + * the format historically used by AllocSet. + */ +typedef struct MemoryContextCounters +{ + Size nblocks; /* Total number of malloc blocks */ + Size freechunks; /* Total number of free chunks */ + Size totalspace; /* Total bytes requested from malloc */ + Size freespace; /* The unused portion of totalspace */ +} MemoryContextCounters; + +/* + * MemoryContext + * A logical context in which memory allocations occur. + * + * MemoryContext itself is an abstract type that can have multiple + * implementations. + * The function pointers in MemoryContextMethods define one specific + * implementation of MemoryContext --- they are a virtual function table + * in C++ terms. + * + * Node types that are actual implementations of memory contexts must + * begin with the same fields as MemoryContextData. + * + * Note: for largely historical reasons, typedef MemoryContext is a pointer + * to the context struct rather than the struct type itself. + */ + +typedef void (*MemoryStatsPrintFunc) (MemoryContext context, void *passthru, + const char *stats_string, + bool print_to_stderr); + +typedef struct MemoryContextMethods +{ + void *(*alloc) (MemoryContext context, Size size); + /* call this free_p in case someone #define's free() */ + void (*free_p) (void *pointer); + void *(*realloc) (void *pointer, Size size); + void (*reset) (MemoryContext context); + void (*delete_context) (MemoryContext context); + MemoryContext (*get_chunk_context) (void *pointer); + Size (*get_chunk_space) (void *pointer); + bool (*is_empty) (MemoryContext context); + void (*stats) (MemoryContext context, + MemoryStatsPrintFunc printfunc, void *passthru, + MemoryContextCounters *totals, + bool print_to_stderr); +#ifdef MEMORY_CONTEXT_CHECKING + void (*check) (MemoryContext context); +#endif +} MemoryContextMethods; + + +typedef struct MemoryContextData +{ + pg_node_attr(abstract) /* there are no nodes of this type */ + + NodeTag type; /* identifies exact kind of context */ + /* these two fields are placed here to minimize alignment wastage: */ + bool isReset; /* T = no space alloced since last reset */ + bool allowInCritSection; /* allow palloc in critical section */ + Size mem_allocated; /* track memory allocated for this context */ + const MemoryContextMethods *methods; /* virtual function table */ + MemoryContext parent; /* NULL if no parent (toplevel context) */ + MemoryContext firstchild; /* head of linked list of children */ + MemoryContext prevchild; /* previous child of same parent */ + MemoryContext nextchild; /* next child of same parent */ + const char *name; /* context name (just for debugging) */ + const char *ident; /* context ID if any (just for debugging) */ + MemoryContextCallback *reset_cbs; /* list of reset/delete callbacks */ +} MemoryContextData; + +/* utils/palloc.h contains typedef struct MemoryContextData *MemoryContext */ + + +/* + * MemoryContextIsValid + * True iff memory context is valid. + * + * Add new context types to the set accepted by this macro. + */ +#define MemoryContextIsValid(context) \ + ((context) != NULL && \ + (IsA((context), AllocSetContext) || \ + IsA((context), SlabContext) || \ + IsA((context), GenerationContext))) + +#endif /* MEMNODES_H */ diff --git a/src/include/nodes/meson.build b/src/include/nodes/meson.build new file mode 100644 index 0000000..626dc69 --- /dev/null +++ b/src/include/nodes/meson.build @@ -0,0 +1,65 @@ +# Copyright (c) 2022-2023, PostgreSQL Global Development Group + +node_support_input_i = [ + 'nodes/nodes.h', + 'nodes/primnodes.h', + 'nodes/parsenodes.h', + 'nodes/pathnodes.h', + 'nodes/plannodes.h', + 'nodes/execnodes.h', + 'access/amapi.h', + 'access/sdir.h', + 'access/tableam.h', + 'access/tsmapi.h', + 'commands/event_trigger.h', + 'commands/trigger.h', + 'executor/tuptable.h', + 'foreign/fdwapi.h', + 'nodes/bitmapset.h', + 'nodes/extensible.h', + 'nodes/lockoptions.h', + 'nodes/miscnodes.h', + 'nodes/replnodes.h', + 'nodes/supportnodes.h', + 'nodes/value.h', + 'utils/rel.h', +] + +node_support_input = [] +foreach i : node_support_input_i + node_support_input += meson.source_root() / 'src' / 'include' / i +endforeach + +node_support_output = [ + 'nodetags.h', + 'outfuncs.funcs.c', 'outfuncs.switch.c', + 'readfuncs.funcs.c', 'readfuncs.switch.c', + 'copyfuncs.funcs.c', 'copyfuncs.switch.c', + 'equalfuncs.funcs.c', 'equalfuncs.switch.c', + 'queryjumblefuncs.funcs.c', 'queryjumblefuncs.switch.c', +] +node_support_install = [ + dir_include_server / 'nodes', + false, false, + false, false, + false, false, + false, false, + false, false, +] + +generated_nodes = custom_target('nodetags.h', + input: node_support_input, + output: node_support_output, + depend_files: catalog_pm, + command: [ + perl, files('../../backend/nodes/gen_node_support.pl'), + '-o', '@OUTDIR@', + '@INPUT@'], + install: true, + install_dir: node_support_install, +) +generated_headers += generated_nodes[0] + +# autoconf generates the file there, ensure we get a conflict +generated_sources_ac += {'src/backend/nodes': node_support_output + ['node-support-stamp']} +generated_sources_ac += {'src/include/nodes': ['header-stamp']} diff --git a/src/include/nodes/miscnodes.h b/src/include/nodes/miscnodes.h new file mode 100644 index 0000000..79cc0db --- /dev/null +++ b/src/include/nodes/miscnodes.h @@ -0,0 +1,56 @@ +/*------------------------------------------------------------------------- + * + * miscnodes.h + * Definitions for hard-to-classify node types. + * + * Node types declared here are not part of parse trees, plan trees, + * or execution state trees. We only assign them NodeTag values because + * IsA() tests provide a convenient way to disambiguate what kind of + * structure is being passed through assorted APIs, such as function + * "context" pointers. + * + * + * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/nodes/miscnodes.h + * + *------------------------------------------------------------------------- + */ +#ifndef MISCNODES_H +#define MISCNODES_H + +#include "nodes/nodes.h" + +/* + * ErrorSaveContext - + * function call context node for handling of "soft" errors + * + * A caller wishing to trap soft errors must initialize a struct like this + * with all fields zero/NULL except for the NodeTag. Optionally, set + * details_wanted = true if more than the bare knowledge that a soft error + * occurred is required. The struct is then passed to a SQL-callable function + * via the FunctionCallInfo.context field; or below the level of SQL calls, + * it could be passed to a subroutine directly. + * + * After calling code that might report an error this way, check + * error_occurred to see if an error happened. If so, and if details_wanted + * is true, error_data has been filled with error details (stored in the + * callee's memory context!). FreeErrorData() can be called to release + * error_data, although that step is typically not necessary if the called + * code was run in a short-lived context. + */ +typedef struct ErrorSaveContext +{ + NodeTag type; + bool error_occurred; /* set to true if we detect a soft error */ + bool details_wanted; /* does caller want more info than that? */ + ErrorData *error_data; /* details of error, if so */ +} ErrorSaveContext; + +/* Often-useful macro for checking if a soft error was reported */ +#define SOFT_ERROR_OCCURRED(escontext) \ + ((escontext) != NULL && IsA(escontext, ErrorSaveContext) && \ + ((ErrorSaveContext *) (escontext))->error_occurred) + +#endif /* MISCNODES_H */ diff --git a/src/include/nodes/multibitmapset.h b/src/include/nodes/multibitmapset.h new file mode 100644 index 0000000..505f017 --- /dev/null +++ b/src/include/nodes/multibitmapset.h @@ -0,0 +1,39 @@ +/*------------------------------------------------------------------------- + * + * multibitmapset.h + * Lists of Bitmapsets + * + * A multibitmapset is useful in situations where members of a set can + * be identified by two small integers; for example, varno and varattno + * of a group of Vars within a query. The implementation is a List of + * Bitmapsets, so that the empty set can be represented by NIL. (But, + * as with Bitmapsets, that's not the only allowed representation.) + * The zero-based index of a List element is the first identifying value, + * and the (also zero-based) index of a bit within that Bitmapset is + * the second identifying value. There is no expectation that the + * Bitmapsets should all be the same size. + * + * The available operations on multibitmapsets are intended to parallel + * those on bitmapsets, for example union and intersection. So far only + * a small fraction of that has been built out; we'll add more as needed. + * + * + * Copyright (c) 2022-2023, PostgreSQL Global Development Group + * + * src/include/nodes/multibitmapset.h + * + *------------------------------------------------------------------------- + */ +#ifndef MULTIBITMAPSET_H +#define MULTIBITMAPSET_H + +#include "nodes/bitmapset.h" +#include "nodes/pg_list.h" + +extern List *mbms_add_member(List *a, int listidx, int bitidx); +extern List *mbms_add_members(List *a, const List *b); +extern List *mbms_int_members(List *a, const List *b); +extern bool mbms_is_member(int listidx, int bitidx, const List *a); +extern Bitmapset *mbms_overlap_sets(const List *a, const List *b); + +#endif /* MULTIBITMAPSET_H */ diff --git a/src/include/nodes/nodeFuncs.h b/src/include/nodes/nodeFuncs.h new file mode 100644 index 0000000..20921b4 --- /dev/null +++ b/src/include/nodes/nodeFuncs.h @@ -0,0 +1,222 @@ +/*------------------------------------------------------------------------- + * + * nodeFuncs.h + * Various general-purpose manipulations of Node trees + * + * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/nodes/nodeFuncs.h + * + *------------------------------------------------------------------------- + */ +#ifndef NODEFUNCS_H +#define NODEFUNCS_H + +#include "nodes/parsenodes.h" + +struct PlanState; /* avoid including execnodes.h too */ + + +/* flags bits for query_tree_walker and query_tree_mutator */ +#define QTW_IGNORE_RT_SUBQUERIES 0x01 /* subqueries in rtable */ +#define QTW_IGNORE_CTE_SUBQUERIES 0x02 /* subqueries in cteList */ +#define QTW_IGNORE_RC_SUBQUERIES 0x03 /* both of above */ +#define QTW_IGNORE_JOINALIASES 0x04 /* JOIN alias var lists */ +#define QTW_IGNORE_RANGE_TABLE 0x08 /* skip rangetable entirely */ +#define QTW_EXAMINE_RTES_BEFORE 0x10 /* examine RTE nodes before their + * contents */ +#define QTW_EXAMINE_RTES_AFTER 0x20 /* examine RTE nodes after their + * contents */ +#define QTW_DONT_COPY_QUERY 0x40 /* do not copy top Query */ +#define QTW_EXAMINE_SORTGROUP 0x80 /* include SortGroupClause lists */ + +/* callback function for check_functions_in_node */ +typedef bool (*check_function_callback) (Oid func_id, void *context); + +/* callback functions for tree walkers */ +typedef bool (*tree_walker_callback) (Node *node, void *context); +typedef bool (*planstate_tree_walker_callback) (struct PlanState *planstate, + void *context); + +/* callback functions for tree mutators */ +typedef Node *(*tree_mutator_callback) (Node *node, void *context); + + +extern Oid exprType(const Node *expr); +extern int32 exprTypmod(const Node *expr); +extern bool exprIsLengthCoercion(const Node *expr, int32 *coercedTypmod); +extern Node *applyRelabelType(Node *arg, Oid rtype, int32 rtypmod, Oid rcollid, + CoercionForm rformat, int rlocation, + bool overwrite_ok); +extern Node *relabel_to_typmod(Node *expr, int32 typmod); +extern Node *strip_implicit_coercions(Node *node); +extern bool expression_returns_set(Node *clause); + +extern Oid exprCollation(const Node *expr); +extern Oid exprInputCollation(const Node *expr); +extern void exprSetCollation(Node *expr, Oid collation); +extern void exprSetInputCollation(Node *expr, Oid inputcollation); + +extern int exprLocation(const Node *expr); + +extern void fix_opfuncids(Node *node); +extern void set_opfuncid(OpExpr *opexpr); +extern void set_sa_opfuncid(ScalarArrayOpExpr *opexpr); + +/* Is clause a FuncExpr clause? */ +static inline bool +is_funcclause(const void *clause) +{ + return clause != NULL && IsA(clause, FuncExpr); +} + +/* Is clause an OpExpr clause? */ +static inline bool +is_opclause(const void *clause) +{ + return clause != NULL && IsA(clause, OpExpr); +} + +/* Extract left arg of a binary opclause, or only arg of a unary opclause */ +static inline Node * +get_leftop(const void *clause) +{ + const OpExpr *expr = (const OpExpr *) clause; + + if (expr->args != NIL) + return (Node *) linitial(expr->args); + else + return NULL; +} + +/* Extract right arg of a binary opclause (NULL if it's a unary opclause) */ +static inline Node * +get_rightop(const void *clause) +{ + const OpExpr *expr = (const OpExpr *) clause; + + if (list_length(expr->args) >= 2) + return (Node *) lsecond(expr->args); + else + return NULL; +} + +/* Is clause an AND clause? */ +static inline bool +is_andclause(const void *clause) +{ + return (clause != NULL && + IsA(clause, BoolExpr) && + ((const BoolExpr *) clause)->boolop == AND_EXPR); +} + +/* Is clause an OR clause? */ +static inline bool +is_orclause(const void *clause) +{ + return (clause != NULL && + IsA(clause, BoolExpr) && + ((const BoolExpr *) clause)->boolop == OR_EXPR); +} + +/* Is clause a NOT clause? */ +static inline bool +is_notclause(const void *clause) +{ + return (clause != NULL && + IsA(clause, BoolExpr) && + ((const BoolExpr *) clause)->boolop == NOT_EXPR); +} + +/* Extract argument from a clause known to be a NOT clause */ +static inline Expr * +get_notclausearg(const void *notclause) +{ + return (Expr *) linitial(((const BoolExpr *) notclause)->args); +} + +extern bool check_functions_in_node(Node *node, check_function_callback checker, + void *context); + +/* + * The following functions are usually passed walker or mutator callbacks + * that are declared like "bool walker(Node *node, my_struct *context)" + * rather than "bool walker(Node *node, void *context)" as a strict reading + * of the C standard would require. Changing the callbacks' declarations + * to "void *" would create serious hazards of passing them the wrong context + * struct type, so we respectfully decline to support the standard's position + * that a pointer to struct is incompatible with "void *". Instead, silence + * related compiler warnings by inserting casts into these macro wrappers. + */ + +#define expression_tree_walker(n, w, c) \ + expression_tree_walker_impl(n, (tree_walker_callback) (w), c) +#define expression_tree_mutator(n, m, c) \ + expression_tree_mutator_impl(n, (tree_mutator_callback) (m), c) + +#define query_tree_walker(q, w, c, f) \ + query_tree_walker_impl(q, (tree_walker_callback) (w), c, f) +#define query_tree_mutator(q, m, c, f) \ + query_tree_mutator_impl(q, (tree_mutator_callback) (m), c, f) + +#define range_table_walker(rt, w, c, f) \ + range_table_walker_impl(rt, (tree_walker_callback) (w), c, f) +#define range_table_mutator(rt, m, c, f) \ + range_table_mutator_impl(rt, (tree_mutator_callback) (m), c, f) + +#define range_table_entry_walker(r, w, c, f) \ + range_table_entry_walker_impl(r, (tree_walker_callback) (w), c, f) + +#define query_or_expression_tree_walker(n, w, c, f) \ + query_or_expression_tree_walker_impl(n, (tree_walker_callback) (w), c, f) +#define query_or_expression_tree_mutator(n, m, c, f) \ + query_or_expression_tree_mutator_impl(n, (tree_mutator_callback) (m), c, f) + +#define raw_expression_tree_walker(n, w, c) \ + raw_expression_tree_walker_impl(n, (tree_walker_callback) (w), c) + +#define planstate_tree_walker(ps, w, c) \ + planstate_tree_walker_impl(ps, (planstate_tree_walker_callback) (w), c) + +extern bool expression_tree_walker_impl(Node *node, + tree_walker_callback walker, + void *context); +extern Node *expression_tree_mutator_impl(Node *node, + tree_mutator_callback mutator, + void *context); + +extern bool query_tree_walker_impl(Query *query, + tree_walker_callback walker, + void *context, int flags); +extern Query *query_tree_mutator_impl(Query *query, + tree_mutator_callback mutator, + void *context, int flags); + +extern bool range_table_walker_impl(List *rtable, + tree_walker_callback walker, + void *context, int flags); +extern List *range_table_mutator_impl(List *rtable, + tree_mutator_callback mutator, + void *context, int flags); + +extern bool range_table_entry_walker_impl(RangeTblEntry *rte, + tree_walker_callback walker, + void *context, int flags); + +extern bool query_or_expression_tree_walker_impl(Node *node, + tree_walker_callback walker, + void *context, int flags); +extern Node *query_or_expression_tree_mutator_impl(Node *node, + tree_mutator_callback mutator, + void *context, int flags); + +extern bool raw_expression_tree_walker_impl(Node *node, + tree_walker_callback walker, + void *context); + +extern bool planstate_tree_walker_impl(struct PlanState *planstate, + planstate_tree_walker_callback walker, + void *context); + +#endif /* NODEFUNCS_H */ diff --git a/src/include/nodes/nodes.h b/src/include/nodes/nodes.h new file mode 100644 index 0000000..f8e8fe6 --- /dev/null +++ b/src/include/nodes/nodes.h @@ -0,0 +1,446 @@ +/*------------------------------------------------------------------------- + * + * nodes.h + * Definitions for tagged nodes. + * + * + * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/nodes/nodes.h + * + *------------------------------------------------------------------------- + */ +#ifndef NODES_H +#define NODES_H + +/* + * The first field of every node is NodeTag. Each node created (with makeNode) + * will have one of the following tags as the value of its first field. + * + * Note that inserting or deleting node types changes the numbers of other + * node types later in the list. This is no problem during development, since + * the node numbers are never stored on disk. But don't do it in a released + * branch, because that would represent an ABI break for extensions. + */ +typedef enum NodeTag +{ + T_Invalid = 0, + +#include "nodes/nodetags.h" +} NodeTag; + +/* + * pg_node_attr() - Used in node definitions to set extra information for + * gen_node_support.pl + * + * Attributes can be attached to a node as a whole (place the attribute + * specification on the first line after the struct's opening brace) + * or to a specific field (place it at the end of that field's line). The + * argument is a comma-separated list of attributes. Unrecognized attributes + * cause an error. + * + * Valid node attributes: + * + * - abstract: Abstract types are types that cannot be instantiated but that + * can be supertypes of other types. We track their fields, so that + * subtypes can use them, but we don't emit a node tag, so you can't + * instantiate them. + * + * - custom_copy_equal: Has custom implementations in copyfuncs.c and + * equalfuncs.c. + * + * - custom_read_write: Has custom implementations in outfuncs.c and + * readfuncs.c. + * + * - custom_query_jumble: Has custom implementation in queryjumblefuncs.c. + * + * - no_copy: Does not support copyObject() at all. + * + * - no_equal: Does not support equal() at all. + * + * - no_copy_equal: Shorthand for both no_copy and no_equal. + * + * - no_query_jumble: Does not support JumbleQuery() at all. + * + * - no_read: Does not support nodeRead() at all. + * + * - nodetag_only: Does not support copyObject(), equal(), jumbleQuery() + * outNode() or nodeRead(). + * + * - special_read_write: Has special treatment in outNode() and nodeRead(). + * + * - nodetag_number(VALUE): assign the specified nodetag number instead of + * an auto-generated number. Typically this would only be used in stable + * branches, to give a newly-added node type a number without breaking ABI + * by changing the numbers of existing node types. + * + * Node types can be supertypes of other types whether or not they are marked + * abstract: if a node struct appears as the first field of another struct + * type, then it is the supertype of that type. The no_copy, no_equal, + * no_query_jumble and no_read node attributes are automatically inherited + * from the supertype. (Notice that nodetag_only does not inherit, so it's + * not quite equivalent to a combination of other attributes.) + * + * Valid node field attributes: + * + * - array_size(OTHERFIELD): This field is a dynamically allocated array with + * size indicated by the mentioned other field. The other field is either a + * scalar or a list, in which case the length of the list is used. + * + * - copy_as(VALUE): In copyObject(), replace the field's value with VALUE. + * + * - copy_as_scalar: In copyObject(), copy the field as a scalar value + * (e.g. a pointer) even if it is a node-type pointer. + * + * - equal_as_scalar: In equal(), compare the field as a scalar value + * even if it is a node-type pointer. + * + * - equal_ignore: Ignore the field for equality. + * + * - equal_ignore_if_zero: Ignore the field for equality if it is zero. + * (Otherwise, compare normally.) + * + * - query_jumble_ignore: Ignore the field for the query jumbling. Note + * that typmod and collation information are usually irrelevant for the + * query jumbling. + * + * - query_jumble_location: Mark the field as a location to track. This is + * only allowed for integer fields that include "location" in their name. + * + * - read_as(VALUE): In nodeRead(), replace the field's value with VALUE. + * + * - read_write_ignore: Ignore the field for read/write. This is only allowed + * if the node type is marked no_read or read_as() is also specified. + * + * - write_only_relids, write_only_nondefault_pathtarget, write_only_req_outer: + * Special handling for Path struct; see there. + * + */ +#define pg_node_attr(...) + +/* + * The first field of a node of any type is guaranteed to be the NodeTag. + * Hence the type of any node can be gotten by casting it to Node. Declaring + * a variable to be of Node * (instead of void *) can also facilitate + * debugging. + */ +typedef struct Node +{ + NodeTag type; +} Node; + +#define nodeTag(nodeptr) (((const Node*)(nodeptr))->type) + +/* + * newNode - + * create a new node of the specified size and tag the node with the + * specified tag. + * + * !WARNING!: Avoid using newNode directly. You should be using the + * macro makeNode. eg. to create a Query node, use makeNode(Query) + * + * Note: the size argument should always be a compile-time constant, so the + * apparent risk of multiple evaluation doesn't matter in practice. + */ +#ifdef __GNUC__ + +/* With GCC, we can use a compound statement within an expression */ +#define newNode(size, tag) \ +({ Node *_result; \ + AssertMacro((size) >= sizeof(Node)); /* need the tag, at least */ \ + _result = (Node *) palloc0fast(size); \ + _result->type = (tag); \ + _result; \ +}) +#else + +/* + * There is no way to dereference the palloc'ed pointer to assign the + * tag, and also return the pointer itself, so we need a holder variable. + * Fortunately, this macro isn't recursive so we just define + * a global variable for this purpose. + */ +extern PGDLLIMPORT Node *newNodeMacroHolder; + +#define newNode(size, tag) \ +( \ + AssertMacro((size) >= sizeof(Node)), /* need the tag, at least */ \ + newNodeMacroHolder = (Node *) palloc0fast(size), \ + newNodeMacroHolder->type = (tag), \ + newNodeMacroHolder \ +) +#endif /* __GNUC__ */ + + +#define makeNode(_type_) ((_type_ *) newNode(sizeof(_type_),T_##_type_)) +#define NodeSetTag(nodeptr,t) (((Node*)(nodeptr))->type = (t)) + +#define IsA(nodeptr,_type_) (nodeTag(nodeptr) == T_##_type_) + +/* + * castNode(type, ptr) casts ptr to "type *", and if assertions are enabled, + * verifies that the node has the appropriate type (using its nodeTag()). + * + * Use an inline function when assertions are enabled, to avoid multiple + * evaluations of the ptr argument (which could e.g. be a function call). + */ +#ifdef USE_ASSERT_CHECKING +static inline Node * +castNodeImpl(NodeTag type, void *ptr) +{ + Assert(ptr == NULL || nodeTag(ptr) == type); + return (Node *) ptr; +} +#define castNode(_type_, nodeptr) ((_type_ *) castNodeImpl(T_##_type_, nodeptr)) +#else +#define castNode(_type_, nodeptr) ((_type_ *) (nodeptr)) +#endif /* USE_ASSERT_CHECKING */ + + +/* ---------------------------------------------------------------- + * extern declarations follow + * ---------------------------------------------------------------- + */ + +/* + * nodes/{outfuncs.c,print.c} + */ +struct Bitmapset; /* not to include bitmapset.h here */ +struct StringInfoData; /* not to include stringinfo.h here */ + +extern void outNode(struct StringInfoData *str, const void *obj); +extern void outToken(struct StringInfoData *str, const char *s); +extern void outBitmapset(struct StringInfoData *str, + const struct Bitmapset *bms); +extern void outDatum(struct StringInfoData *str, uintptr_t value, + int typlen, bool typbyval); +extern char *nodeToString(const void *obj); +extern char *bmsToString(const struct Bitmapset *bms); + +/* + * nodes/{readfuncs.c,read.c} + */ +extern void *stringToNode(const char *str); +#ifdef WRITE_READ_PARSE_PLAN_TREES +extern void *stringToNodeWithLocations(const char *str); +#endif +extern struct Bitmapset *readBitmapset(void); +extern uintptr_t readDatum(bool typbyval); +extern bool *readBoolCols(int numCols); +extern int *readIntCols(int numCols); +extern Oid *readOidCols(int numCols); +extern int16 *readAttrNumberCols(int numCols); + +/* + * nodes/copyfuncs.c + */ +extern void *copyObjectImpl(const void *from); + +/* cast result back to argument type, if supported by compiler */ +#ifdef HAVE_TYPEOF +#define copyObject(obj) ((typeof(obj)) copyObjectImpl(obj)) +#else +#define copyObject(obj) copyObjectImpl(obj) +#endif + +/* + * nodes/equalfuncs.c + */ +extern bool equal(const void *a, const void *b); + + +/* + * Typedefs for identifying qualifier selectivities and plan costs as such. + * These are just plain "double"s, but declaring a variable as Selectivity + * or Cost makes the intent more obvious. + * + * These could have gone into plannodes.h or some such, but many files + * depend on them... + */ +typedef double Selectivity; /* fraction of tuples a qualifier will pass */ +typedef double Cost; /* execution cost (in page-access units) */ +typedef double Cardinality; /* (estimated) number of rows or other integer + * count */ + + +/* + * CmdType - + * enums for type of operation represented by a Query or PlannedStmt + * + * This is needed in both parsenodes.h and plannodes.h, so put it here... + */ +typedef enum CmdType +{ + CMD_UNKNOWN, + CMD_SELECT, /* select stmt */ + CMD_UPDATE, /* update stmt */ + CMD_INSERT, /* insert stmt */ + CMD_DELETE, /* delete stmt */ + CMD_MERGE, /* merge stmt */ + CMD_UTILITY, /* cmds like create, destroy, copy, vacuum, + * etc. */ + CMD_NOTHING /* dummy command for instead nothing rules + * with qual */ +} CmdType; + + +/* + * JoinType - + * enums for types of relation joins + * + * JoinType determines the exact semantics of joining two relations using + * a matching qualification. For example, it tells what to do with a tuple + * that has no match in the other relation. + * + * This is needed in both parsenodes.h and plannodes.h, so put it here... + */ +typedef enum JoinType +{ + /* + * The canonical kinds of joins according to the SQL JOIN syntax. Only + * these codes can appear in parser output (e.g., JoinExpr nodes). + */ + JOIN_INNER, /* matching tuple pairs only */ + JOIN_LEFT, /* pairs + unmatched LHS tuples */ + JOIN_FULL, /* pairs + unmatched LHS + unmatched RHS */ + JOIN_RIGHT, /* pairs + unmatched RHS tuples */ + + /* + * Semijoins and anti-semijoins (as defined in relational theory) do not + * appear in the SQL JOIN syntax, but there are standard idioms for + * representing them (e.g., using EXISTS). The planner recognizes these + * cases and converts them to joins. So the planner and executor must + * support these codes. NOTE: in JOIN_SEMI output, it is unspecified + * which matching RHS row is joined to. In JOIN_ANTI output, the row is + * guaranteed to be null-extended. + */ + JOIN_SEMI, /* 1 copy of each LHS row that has match(es) */ + JOIN_ANTI, /* 1 copy of each LHS row that has no match */ + JOIN_RIGHT_ANTI, /* 1 copy of each RHS row that has no match */ + + /* + * These codes are used internally in the planner, but are not supported + * by the executor (nor, indeed, by most of the planner). + */ + JOIN_UNIQUE_OUTER, /* LHS path must be made unique */ + JOIN_UNIQUE_INNER /* RHS path must be made unique */ + + /* + * We might need additional join types someday. + */ +} JoinType; + +/* + * OUTER joins are those for which pushed-down quals must behave differently + * from the join's own quals. This is in fact everything except INNER and + * SEMI joins. However, this macro must also exclude the JOIN_UNIQUE symbols + * since those are temporary proxies for what will eventually be an INNER + * join. + * + * Note: semijoins are a hybrid case, but we choose to treat them as not + * being outer joins. This is okay principally because the SQL syntax makes + * it impossible to have a pushed-down qual that refers to the inner relation + * of a semijoin; so there is no strong need to distinguish join quals from + * pushed-down quals. This is convenient because for almost all purposes, + * quals attached to a semijoin can be treated the same as innerjoin quals. + */ +#define IS_OUTER_JOIN(jointype) \ + (((1 << (jointype)) & \ + ((1 << JOIN_LEFT) | \ + (1 << JOIN_FULL) | \ + (1 << JOIN_RIGHT) | \ + (1 << JOIN_ANTI) | \ + (1 << JOIN_RIGHT_ANTI))) != 0) + +/* + * AggStrategy - + * overall execution strategies for Agg plan nodes + * + * This is needed in both pathnodes.h and plannodes.h, so put it here... + */ +typedef enum AggStrategy +{ + AGG_PLAIN, /* simple agg across all input rows */ + AGG_SORTED, /* grouped agg, input must be sorted */ + AGG_HASHED, /* grouped agg, use internal hashtable */ + AGG_MIXED /* grouped agg, hash and sort both used */ +} AggStrategy; + +/* + * AggSplit - + * splitting (partial aggregation) modes for Agg plan nodes + * + * This is needed in both pathnodes.h and plannodes.h, so put it here... + */ + +/* Primitive options supported by nodeAgg.c: */ +#define AGGSPLITOP_COMBINE 0x01 /* substitute combinefn for transfn */ +#define AGGSPLITOP_SKIPFINAL 0x02 /* skip finalfn, return state as-is */ +#define AGGSPLITOP_SERIALIZE 0x04 /* apply serialfn to output */ +#define AGGSPLITOP_DESERIALIZE 0x08 /* apply deserialfn to input */ + +/* Supported operating modes (i.e., useful combinations of these options): */ +typedef enum AggSplit +{ + /* Basic, non-split aggregation: */ + AGGSPLIT_SIMPLE = 0, + /* Initial phase of partial aggregation, with serialization: */ + AGGSPLIT_INITIAL_SERIAL = AGGSPLITOP_SKIPFINAL | AGGSPLITOP_SERIALIZE, + /* Final phase of partial aggregation, with deserialization: */ + AGGSPLIT_FINAL_DESERIAL = AGGSPLITOP_COMBINE | AGGSPLITOP_DESERIALIZE +} AggSplit; + +/* Test whether an AggSplit value selects each primitive option: */ +#define DO_AGGSPLIT_COMBINE(as) (((as) & AGGSPLITOP_COMBINE) != 0) +#define DO_AGGSPLIT_SKIPFINAL(as) (((as) & AGGSPLITOP_SKIPFINAL) != 0) +#define DO_AGGSPLIT_SERIALIZE(as) (((as) & AGGSPLITOP_SERIALIZE) != 0) +#define DO_AGGSPLIT_DESERIALIZE(as) (((as) & AGGSPLITOP_DESERIALIZE) != 0) + +/* + * SetOpCmd and SetOpStrategy - + * overall semantics and execution strategies for SetOp plan nodes + * + * This is needed in both pathnodes.h and plannodes.h, so put it here... + */ +typedef enum SetOpCmd +{ + SETOPCMD_INTERSECT, + SETOPCMD_INTERSECT_ALL, + SETOPCMD_EXCEPT, + SETOPCMD_EXCEPT_ALL +} SetOpCmd; + +typedef enum SetOpStrategy +{ + SETOP_SORTED, /* input must be sorted */ + SETOP_HASHED /* use internal hashtable */ +} SetOpStrategy; + +/* + * OnConflictAction - + * "ON CONFLICT" clause type of query + * + * This is needed in both parsenodes.h and plannodes.h, so put it here... + */ +typedef enum OnConflictAction +{ + ONCONFLICT_NONE, /* No "ON CONFLICT" clause */ + ONCONFLICT_NOTHING, /* ON CONFLICT ... DO NOTHING */ + ONCONFLICT_UPDATE /* ON CONFLICT ... DO UPDATE */ +} OnConflictAction; + +/* + * LimitOption - + * LIMIT option of query + * + * This is needed in both parsenodes.h and plannodes.h, so put it here... + */ +typedef enum LimitOption +{ + LIMIT_OPTION_COUNT, /* FETCH FIRST... ONLY */ + LIMIT_OPTION_WITH_TIES, /* FETCH FIRST... WITH TIES */ + LIMIT_OPTION_DEFAULT, /* No limit present */ +} LimitOption; + +#endif /* NODES_H */ diff --git a/src/include/nodes/params.h b/src/include/nodes/params.h new file mode 100644 index 0000000..ad23113 --- /dev/null +++ b/src/include/nodes/params.h @@ -0,0 +1,170 @@ +/*------------------------------------------------------------------------- + * + * params.h + * Support for finding the values associated with Param nodes. + * + * + * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/nodes/params.h + * + *------------------------------------------------------------------------- + */ +#ifndef PARAMS_H +#define PARAMS_H + +/* Forward declarations, to avoid including other headers */ +struct Bitmapset; +struct ExprState; +struct Param; +struct ParseState; + + +/* + * ParamListInfo + * + * ParamListInfo structures are used to pass parameters into the executor + * for parameterized plans. We support two basic approaches to supplying + * parameter values, the "static" way and the "dynamic" way. + * + * In the static approach, per-parameter data is stored in an array of + * ParamExternData structs appended to the ParamListInfo struct. + * Each entry in the array defines the value to be substituted for a + * PARAM_EXTERN parameter. The "paramid" of a PARAM_EXTERN Param + * can range from 1 to numParams. + * + * Although parameter numbers are normally consecutive, we allow + * ptype == InvalidOid to signal an unused array entry. + * + * pflags is a flags field. Currently the only used bit is: + * PARAM_FLAG_CONST signals the planner that it may treat this parameter + * as a constant (i.e., generate a plan that works only for this value + * of the parameter). + * + * In the dynamic approach, all access to parameter values is done through + * hook functions found in the ParamListInfo struct. In this case, + * the ParamExternData array is typically unused and not allocated; + * but the legal range of paramid is still 1 to numParams. + * + * Although the data structure is really an array, not a list, we keep + * the old typedef name to avoid unnecessary code changes. + * + * There are 3 hook functions that can be associated with a ParamListInfo + * structure: + * + * If paramFetch isn't null, it is called to fetch the ParamExternData + * for a particular param ID, rather than accessing the relevant element + * of the ParamExternData array. This supports the case where the array + * isn't there at all, as well as cases where the data in the array + * might be obsolete or lazily evaluated. paramFetch must return the + * address of a ParamExternData struct describing the specified param ID; + * the convention above about ptype == InvalidOid signaling an invalid + * param ID still applies. The returned struct can either be placed in + * the "workspace" supplied by the caller, or it can be in storage + * controlled by the paramFetch hook if that's more convenient. + * (In either case, the struct is not expected to be long-lived.) + * If "speculative" is true, the paramFetch hook should not risk errors + * in trying to fetch the parameter value, and should report an invalid + * parameter instead. + * + * If paramCompile isn't null, then it controls what execExpr.c compiles + * for PARAM_EXTERN Param nodes --- typically, this hook would emit a + * EEOP_PARAM_CALLBACK step. This allows unnecessary work to be + * optimized away in compiled expressions. + * + * If parserSetup isn't null, then it is called to re-instantiate the + * original parsing hooks when a query needs to be re-parsed/planned. + * This is especially useful if the types of parameters might change + * from time to time, since it can replace the need to supply a fixed + * list of parameter types to the parser. + * + * Notice that the paramFetch and paramCompile hooks are actually passed + * the ParamListInfo struct's address; they can therefore access all + * three of the "arg" fields, and the distinction between paramFetchArg + * and paramCompileArg is rather arbitrary. + */ + +#define PARAM_FLAG_CONST 0x0001 /* parameter is constant */ + +typedef struct ParamExternData +{ + Datum value; /* parameter value */ + bool isnull; /* is it NULL? */ + uint16 pflags; /* flag bits, see above */ + Oid ptype; /* parameter's datatype, or 0 */ +} ParamExternData; + +typedef struct ParamListInfoData *ParamListInfo; + +typedef ParamExternData *(*ParamFetchHook) (ParamListInfo params, + int paramid, bool speculative, + ParamExternData *workspace); + +typedef void (*ParamCompileHook) (ParamListInfo params, struct Param *param, + struct ExprState *state, + Datum *resv, bool *resnull); + +typedef void (*ParserSetupHook) (struct ParseState *pstate, void *arg); + +typedef struct ParamListInfoData +{ + ParamFetchHook paramFetch; /* parameter fetch hook */ + void *paramFetchArg; + ParamCompileHook paramCompile; /* parameter compile hook */ + void *paramCompileArg; + ParserSetupHook parserSetup; /* parser setup hook */ + void *parserSetupArg; + char *paramValuesStr; /* params as a single string for errors */ + int numParams; /* nominal/maximum # of Params represented */ + + /* + * params[] may be of length zero if paramFetch is supplied; otherwise it + * must be of length numParams. + */ + ParamExternData params[FLEXIBLE_ARRAY_MEMBER]; +} ParamListInfoData; + + +/* ---------------- + * ParamExecData + * + * ParamExecData entries are used for executor internal parameters + * (that is, values being passed into or out of a sub-query). The + * paramid of a PARAM_EXEC Param is a (zero-based) index into an + * array of ParamExecData records, which is referenced through + * es_param_exec_vals or ecxt_param_exec_vals. + * + * If execPlan is not NULL, it points to a SubPlanState node that needs + * to be executed to produce the value. (This is done so that we can have + * lazy evaluation of InitPlans: they aren't executed until/unless a + * result value is needed.) Otherwise the value is assumed to be valid + * when needed. + * ---------------- + */ + +typedef struct ParamExecData +{ + void *execPlan; /* should be "SubPlanState *" */ + Datum value; + bool isnull; +} ParamExecData; + +/* type of argument for ParamsErrorCallback */ +typedef struct ParamsErrorCbData +{ + const char *portalName; + ParamListInfo params; +} ParamsErrorCbData; + +/* Functions found in src/backend/nodes/params.c */ +extern ParamListInfo makeParamList(int numParams); +extern ParamListInfo copyParamList(ParamListInfo from); +extern Size EstimateParamListSpace(ParamListInfo paramLI); +extern void SerializeParamList(ParamListInfo paramLI, char **start_address); +extern ParamListInfo RestoreParamList(char **start_address); +extern char *BuildParamLogString(ParamListInfo params, char **knownTextValues, + int maxlen); +extern void ParamsErrorCallback(void *arg); + +#endif /* PARAMS_H */ diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h new file mode 100644 index 0000000..9dca3b6 --- /dev/null +++ b/src/include/nodes/parsenodes.h @@ -0,0 +1,4050 @@ +/*------------------------------------------------------------------------- + * + * parsenodes.h + * definitions for parse tree nodes + * + * Many of the node types used in parsetrees include a "location" field. + * This is a byte (not character) offset in the original source text, to be + * used for positioning an error cursor when there is an error related to + * the node. Access to the original source text is needed to make use of + * the location. At the topmost (statement) level, we also provide a + * statement length, likewise measured in bytes, for convenience in + * identifying statement boundaries in multi-statement source strings. + * + * + * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/nodes/parsenodes.h + * + *------------------------------------------------------------------------- + */ +#ifndef PARSENODES_H +#define PARSENODES_H + +#include "common/relpath.h" +#include "nodes/bitmapset.h" +#include "nodes/lockoptions.h" +#include "nodes/primnodes.h" +#include "nodes/value.h" +#include "partitioning/partdefs.h" + + +typedef enum OverridingKind +{ + OVERRIDING_NOT_SET = 0, + OVERRIDING_USER_VALUE, + OVERRIDING_SYSTEM_VALUE +} OverridingKind; + +/* Possible sources of a Query */ +typedef enum QuerySource +{ + QSRC_ORIGINAL, /* original parsetree (explicit query) */ + QSRC_PARSER, /* added by parse analysis (now unused) */ + QSRC_INSTEAD_RULE, /* added by unconditional INSTEAD rule */ + QSRC_QUAL_INSTEAD_RULE, /* added by conditional INSTEAD rule */ + QSRC_NON_INSTEAD_RULE /* added by non-INSTEAD rule */ +} QuerySource; + +/* Sort ordering options for ORDER BY and CREATE INDEX */ +typedef enum SortByDir +{ + SORTBY_DEFAULT, + SORTBY_ASC, + SORTBY_DESC, + SORTBY_USING /* not allowed in CREATE INDEX ... */ +} SortByDir; + +typedef enum SortByNulls +{ + SORTBY_NULLS_DEFAULT, + SORTBY_NULLS_FIRST, + SORTBY_NULLS_LAST +} SortByNulls; + +/* Options for [ ALL | DISTINCT ] */ +typedef enum SetQuantifier +{ + SET_QUANTIFIER_DEFAULT, + SET_QUANTIFIER_ALL, + SET_QUANTIFIER_DISTINCT +} SetQuantifier; + +/* + * Grantable rights are encoded so that we can OR them together in a bitmask. + * The present representation of AclItem limits us to 32 distinct rights, + * even though AclMode is defined as uint64. See utils/acl.h. + * + * Caution: changing these codes breaks stored ACLs, hence forces initdb. + */ +typedef uint64 AclMode; /* a bitmask of privilege bits */ + +#define ACL_INSERT (1<<0) /* for relations */ +#define ACL_SELECT (1<<1) +#define ACL_UPDATE (1<<2) +#define ACL_DELETE (1<<3) +#define ACL_TRUNCATE (1<<4) +#define ACL_REFERENCES (1<<5) +#define ACL_TRIGGER (1<<6) +#define ACL_EXECUTE (1<<7) /* for functions */ +#define ACL_USAGE (1<<8) /* for various object types */ +#define ACL_CREATE (1<<9) /* for namespaces and databases */ +#define ACL_CREATE_TEMP (1<<10) /* for databases */ +#define ACL_CONNECT (1<<11) /* for databases */ +#define ACL_SET (1<<12) /* for configuration parameters */ +#define ACL_ALTER_SYSTEM (1<<13) /* for configuration parameters */ +#define N_ACL_RIGHTS 14 /* 1 plus the last 1<<x */ +#define ACL_NO_RIGHTS 0 +/* Currently, SELECT ... FOR [KEY] UPDATE/SHARE requires UPDATE privileges */ +#define ACL_SELECT_FOR_UPDATE ACL_UPDATE + + +/***************************************************************************** + * Query Tree + *****************************************************************************/ + +/* + * Query - + * Parse analysis turns all statements into a Query tree + * for further processing by the rewriter and planner. + * + * Utility statements (i.e. non-optimizable statements) have the + * utilityStmt field set, and the rest of the Query is mostly dummy. + * + * Planning converts a Query tree into a Plan tree headed by a PlannedStmt + * node --- the Query structure is not used by the executor. + * + * All the fields ignored for the query jumbling are not semantically + * significant (such as alias names), as is ignored anything that can + * be deduced from child nodes (else we'd just be double-hashing that + * piece of information). + */ +typedef struct Query +{ + NodeTag type; + + CmdType commandType; /* select|insert|update|delete|merge|utility */ + + /* where did I come from? */ + QuerySource querySource pg_node_attr(query_jumble_ignore); + + /* + * query identifier (can be set by plugins); ignored for equal, as it + * might not be set; also not stored. This is the result of the query + * jumble, hence ignored. + */ + uint64 queryId pg_node_attr(equal_ignore, query_jumble_ignore, read_write_ignore, read_as(0)); + + /* do I set the command result tag? */ + bool canSetTag pg_node_attr(query_jumble_ignore); + + Node *utilityStmt; /* non-null if commandType == CMD_UTILITY */ + + /* + * rtable index of target relation for INSERT/UPDATE/DELETE/MERGE; 0 for + * SELECT. This is ignored in the query jumble as unrelated to the + * compilation of the query ID. + */ + int resultRelation pg_node_attr(query_jumble_ignore); + + /* has aggregates in tlist or havingQual */ + bool hasAggs pg_node_attr(query_jumble_ignore); + /* has window functions in tlist */ + bool hasWindowFuncs pg_node_attr(query_jumble_ignore); + /* has set-returning functions in tlist */ + bool hasTargetSRFs pg_node_attr(query_jumble_ignore); + /* has subquery SubLink */ + bool hasSubLinks pg_node_attr(query_jumble_ignore); + /* distinctClause is from DISTINCT ON */ + bool hasDistinctOn pg_node_attr(query_jumble_ignore); + /* WITH RECURSIVE was specified */ + bool hasRecursive pg_node_attr(query_jumble_ignore); + /* has INSERT/UPDATE/DELETE in WITH */ + bool hasModifyingCTE pg_node_attr(query_jumble_ignore); + /* FOR [KEY] UPDATE/SHARE was specified */ + bool hasForUpdate pg_node_attr(query_jumble_ignore); + /* rewriter has applied some RLS policy */ + bool hasRowSecurity pg_node_attr(query_jumble_ignore); + /* is a RETURN statement */ + bool isReturn pg_node_attr(query_jumble_ignore); + + List *cteList; /* WITH list (of CommonTableExpr's) */ + + List *rtable; /* list of range table entries */ + + /* + * list of RTEPermissionInfo nodes for the rtable entries having + * perminfoindex > 0 + */ + List *rteperminfos pg_node_attr(query_jumble_ignore); + FromExpr *jointree; /* table join tree (FROM and WHERE clauses); + * also USING clause for MERGE */ + + List *mergeActionList; /* list of actions for MERGE (only) */ + /* whether to use outer join */ + bool mergeUseOuterJoin pg_node_attr(query_jumble_ignore); + + List *targetList; /* target list (of TargetEntry) */ + + /* OVERRIDING clause */ + OverridingKind override pg_node_attr(query_jumble_ignore); + + OnConflictExpr *onConflict; /* ON CONFLICT DO [NOTHING | UPDATE] */ + + List *returningList; /* return-values list (of TargetEntry) */ + + List *groupClause; /* a list of SortGroupClause's */ + bool groupDistinct; /* is the group by clause distinct? */ + + List *groupingSets; /* a list of GroupingSet's if present */ + + Node *havingQual; /* qualifications applied to groups */ + + List *windowClause; /* a list of WindowClause's */ + + List *distinctClause; /* a list of SortGroupClause's */ + + List *sortClause; /* a list of SortGroupClause's */ + + Node *limitOffset; /* # of result tuples to skip (int8 expr) */ + Node *limitCount; /* # of result tuples to return (int8 expr) */ + LimitOption limitOption; /* limit type */ + + List *rowMarks; /* a list of RowMarkClause's */ + + Node *setOperations; /* set-operation tree if this is top level of + * a UNION/INTERSECT/EXCEPT query */ + + /* + * A list of pg_constraint OIDs that the query depends on to be + * semantically valid + */ + List *constraintDeps pg_node_attr(query_jumble_ignore); + + /* a list of WithCheckOption's (added during rewrite) */ + List *withCheckOptions pg_node_attr(query_jumble_ignore); + + /* + * The following two fields identify the portion of the source text string + * containing this query. They are typically only populated in top-level + * Queries, not in sub-queries. When not set, they might both be zero, or + * both be -1 meaning "unknown". + */ + /* start location, or -1 if unknown */ + int stmt_location; + /* length in bytes; 0 means "rest of string" */ + int stmt_len pg_node_attr(query_jumble_ignore); +} Query; + + +/**************************************************************************** + * Supporting data structures for Parse Trees + * + * Most of these node types appear in raw parsetrees output by the grammar, + * and get transformed to something else by the analyzer. A few of them + * are used as-is in transformed querytrees. + ****************************************************************************/ + +/* + * TypeName - specifies a type in definitions + * + * For TypeName structures generated internally, it is often easier to + * specify the type by OID than by name. If "names" is NIL then the + * actual type OID is given by typeOid, otherwise typeOid is unused. + * Similarly, if "typmods" is NIL then the actual typmod is expected to + * be prespecified in typemod, otherwise typemod is unused. + * + * If pct_type is true, then names is actually a field name and we look up + * the type of that field. Otherwise (the normal case), names is a type + * name possibly qualified with schema and database name. + */ +typedef struct TypeName +{ + NodeTag type; + List *names; /* qualified name (list of String nodes) */ + Oid typeOid; /* type identified by OID */ + bool setof; /* is a set? */ + bool pct_type; /* %TYPE specified? */ + List *typmods; /* type modifier expression(s) */ + int32 typemod; /* prespecified type modifier */ + List *arrayBounds; /* array bounds */ + int location; /* token location, or -1 if unknown */ +} TypeName; + +/* + * ColumnRef - specifies a reference to a column, or possibly a whole tuple + * + * The "fields" list must be nonempty. It can contain String nodes + * (representing names) and A_Star nodes (representing occurrence of a '*'). + * Currently, A_Star must appear only as the last list element --- the grammar + * is responsible for enforcing this! + * + * Note: any container subscripting or selection of fields from composite columns + * is represented by an A_Indirection node above the ColumnRef. However, + * for simplicity in the normal case, initial field selection from a table + * name is represented within ColumnRef and not by adding A_Indirection. + */ +typedef struct ColumnRef +{ + NodeTag type; + List *fields; /* field names (String nodes) or A_Star */ + int location; /* token location, or -1 if unknown */ +} ColumnRef; + +/* + * ParamRef - specifies a $n parameter reference + */ +typedef struct ParamRef +{ + NodeTag type; + int number; /* the number of the parameter */ + int location; /* token location, or -1 if unknown */ +} ParamRef; + +/* + * A_Expr - infix, prefix, and postfix expressions + */ +typedef enum A_Expr_Kind +{ + AEXPR_OP, /* normal operator */ + AEXPR_OP_ANY, /* scalar op ANY (array) */ + AEXPR_OP_ALL, /* scalar op ALL (array) */ + AEXPR_DISTINCT, /* IS DISTINCT FROM - name must be "=" */ + AEXPR_NOT_DISTINCT, /* IS NOT DISTINCT FROM - name must be "=" */ + AEXPR_NULLIF, /* NULLIF - name must be "=" */ + AEXPR_IN, /* [NOT] IN - name must be "=" or "<>" */ + AEXPR_LIKE, /* [NOT] LIKE - name must be "~~" or "!~~" */ + AEXPR_ILIKE, /* [NOT] ILIKE - name must be "~~*" or "!~~*" */ + AEXPR_SIMILAR, /* [NOT] SIMILAR - name must be "~" or "!~" */ + AEXPR_BETWEEN, /* name must be "BETWEEN" */ + AEXPR_NOT_BETWEEN, /* name must be "NOT BETWEEN" */ + AEXPR_BETWEEN_SYM, /* name must be "BETWEEN SYMMETRIC" */ + AEXPR_NOT_BETWEEN_SYM /* name must be "NOT BETWEEN SYMMETRIC" */ +} A_Expr_Kind; + +typedef struct A_Expr +{ + pg_node_attr(custom_read_write) + + NodeTag type; + A_Expr_Kind kind; /* see above */ + List *name; /* possibly-qualified name of operator */ + Node *lexpr; /* left argument, or NULL if none */ + Node *rexpr; /* right argument, or NULL if none */ + int location; /* token location, or -1 if unknown */ +} A_Expr; + +/* + * A_Const - a literal constant + * + * Value nodes are inline for performance. You can treat 'val' as a node, + * as in IsA(&val, Integer). 'val' is not valid if isnull is true. + */ +union ValUnion +{ + Node node; + Integer ival; + Float fval; + Boolean boolval; + String sval; + BitString bsval; +}; + +typedef struct A_Const +{ + pg_node_attr(custom_copy_equal, custom_read_write, custom_query_jumble) + + NodeTag type; + union ValUnion val; + bool isnull; /* SQL NULL constant */ + int location; /* token location, or -1 if unknown */ +} A_Const; + +/* + * TypeCast - a CAST expression + */ +typedef struct TypeCast +{ + NodeTag type; + Node *arg; /* the expression being casted */ + TypeName *typeName; /* the target type */ + int location; /* token location, or -1 if unknown */ +} TypeCast; + +/* + * CollateClause - a COLLATE expression + */ +typedef struct CollateClause +{ + NodeTag type; + Node *arg; /* input expression */ + List *collname; /* possibly-qualified collation name */ + int location; /* token location, or -1 if unknown */ +} CollateClause; + +/* + * RoleSpec - a role name or one of a few special values. + */ +typedef enum RoleSpecType +{ + ROLESPEC_CSTRING, /* role name is stored as a C string */ + ROLESPEC_CURRENT_ROLE, /* role spec is CURRENT_ROLE */ + ROLESPEC_CURRENT_USER, /* role spec is CURRENT_USER */ + ROLESPEC_SESSION_USER, /* role spec is SESSION_USER */ + ROLESPEC_PUBLIC /* role name is "public" */ +} RoleSpecType; + +typedef struct RoleSpec +{ + NodeTag type; + RoleSpecType roletype; /* Type of this rolespec */ + char *rolename; /* filled only for ROLESPEC_CSTRING */ + int location; /* token location, or -1 if unknown */ +} RoleSpec; + +/* + * FuncCall - a function or aggregate invocation + * + * agg_order (if not NIL) indicates we saw 'foo(... ORDER BY ...)', or if + * agg_within_group is true, it was 'foo(...) WITHIN GROUP (ORDER BY ...)'. + * agg_star indicates we saw a 'foo(*)' construct, while agg_distinct + * indicates we saw 'foo(DISTINCT ...)'. In any of these cases, the + * construct *must* be an aggregate call. Otherwise, it might be either an + * aggregate or some other kind of function. However, if FILTER or OVER is + * present it had better be an aggregate or window function. + * + * Normally, you'd initialize this via makeFuncCall() and then only change the + * parts of the struct its defaults don't match afterwards, as needed. + */ +typedef struct FuncCall +{ + NodeTag type; + List *funcname; /* qualified name of function */ + List *args; /* the arguments (list of exprs) */ + List *agg_order; /* ORDER BY (list of SortBy) */ + Node *agg_filter; /* FILTER clause, if any */ + struct WindowDef *over; /* OVER clause, if any */ + bool agg_within_group; /* ORDER BY appeared in WITHIN GROUP */ + bool agg_star; /* argument was really '*' */ + bool agg_distinct; /* arguments were labeled DISTINCT */ + bool func_variadic; /* last argument was labeled VARIADIC */ + CoercionForm funcformat; /* how to display this node */ + int location; /* token location, or -1 if unknown */ +} FuncCall; + +/* + * A_Star - '*' representing all columns of a table or compound field + * + * This can appear within ColumnRef.fields, A_Indirection.indirection, and + * ResTarget.indirection lists. + */ +typedef struct A_Star +{ + NodeTag type; +} A_Star; + +/* + * A_Indices - array subscript or slice bounds ([idx] or [lidx:uidx]) + * + * In slice case, either or both of lidx and uidx can be NULL (omitted). + * In non-slice case, uidx holds the single subscript and lidx is always NULL. + */ +typedef struct A_Indices +{ + NodeTag type; + bool is_slice; /* true if slice (i.e., colon present) */ + Node *lidx; /* slice lower bound, if any */ + Node *uidx; /* subscript, or slice upper bound if any */ +} A_Indices; + +/* + * A_Indirection - select a field and/or array element from an expression + * + * The indirection list can contain A_Indices nodes (representing + * subscripting), String nodes (representing field selection --- the + * string value is the name of the field to select), and A_Star nodes + * (representing selection of all fields of a composite type). + * For example, a complex selection operation like + * (foo).field1[42][7].field2 + * would be represented with a single A_Indirection node having a 4-element + * indirection list. + * + * Currently, A_Star must appear only as the last list element --- the grammar + * is responsible for enforcing this! + */ +typedef struct A_Indirection +{ + NodeTag type; + Node *arg; /* the thing being selected from */ + List *indirection; /* subscripts and/or field names and/or * */ +} A_Indirection; + +/* + * A_ArrayExpr - an ARRAY[] construct + */ +typedef struct A_ArrayExpr +{ + NodeTag type; + List *elements; /* array element expressions */ + int location; /* token location, or -1 if unknown */ +} A_ArrayExpr; + +/* + * ResTarget - + * result target (used in target list of pre-transformed parse trees) + * + * In a SELECT target list, 'name' is the column label from an + * 'AS ColumnLabel' clause, or NULL if there was none, and 'val' is the + * value expression itself. The 'indirection' field is not used. + * + * INSERT uses ResTarget in its target-column-names list. Here, 'name' is + * the name of the destination column, 'indirection' stores any subscripts + * attached to the destination, and 'val' is not used. + * + * In an UPDATE target list, 'name' is the name of the destination column, + * 'indirection' stores any subscripts attached to the destination, and + * 'val' is the expression to assign. + * + * See A_Indirection for more info about what can appear in 'indirection'. + */ +typedef struct ResTarget +{ + NodeTag type; + char *name; /* column name or NULL */ + List *indirection; /* subscripts, field names, and '*', or NIL */ + Node *val; /* the value expression to compute or assign */ + int location; /* token location, or -1 if unknown */ +} ResTarget; + +/* + * MultiAssignRef - element of a row source expression for UPDATE + * + * In an UPDATE target list, when we have SET (a,b,c) = row-valued-expression, + * we generate separate ResTarget items for each of a,b,c. Their "val" trees + * are MultiAssignRef nodes numbered 1..n, linking to a common copy of the + * row-valued-expression (which parse analysis will process only once, when + * handling the MultiAssignRef with colno=1). + */ +typedef struct MultiAssignRef +{ + NodeTag type; + Node *source; /* the row-valued expression */ + int colno; /* column number for this target (1..n) */ + int ncolumns; /* number of targets in the construct */ +} MultiAssignRef; + +/* + * SortBy - for ORDER BY clause + */ +typedef struct SortBy +{ + NodeTag type; + Node *node; /* expression to sort on */ + SortByDir sortby_dir; /* ASC/DESC/USING/default */ + SortByNulls sortby_nulls; /* NULLS FIRST/LAST */ + List *useOp; /* name of op to use, if SORTBY_USING */ + int location; /* operator location, or -1 if none/unknown */ +} SortBy; + +/* + * WindowDef - raw representation of WINDOW and OVER clauses + * + * For entries in a WINDOW list, "name" is the window name being defined. + * For OVER clauses, we use "name" for the "OVER window" syntax, or "refname" + * for the "OVER (window)" syntax, which is subtly different --- the latter + * implies overriding the window frame clause. + */ +typedef struct WindowDef +{ + NodeTag type; + char *name; /* window's own name */ + char *refname; /* referenced window name, if any */ + List *partitionClause; /* PARTITION BY expression list */ + List *orderClause; /* ORDER BY (list of SortBy) */ + int frameOptions; /* frame_clause options, see below */ + Node *startOffset; /* expression for starting bound, if any */ + Node *endOffset; /* expression for ending bound, if any */ + int location; /* parse location, or -1 if none/unknown */ +} WindowDef; + +/* + * frameOptions is an OR of these bits. The NONDEFAULT and BETWEEN bits are + * used so that ruleutils.c can tell which properties were specified and + * which were defaulted; the correct behavioral bits must be set either way. + * The START_foo and END_foo options must come in pairs of adjacent bits for + * the convenience of gram.y, even though some of them are useless/invalid. + */ +#define FRAMEOPTION_NONDEFAULT 0x00001 /* any specified? */ +#define FRAMEOPTION_RANGE 0x00002 /* RANGE behavior */ +#define FRAMEOPTION_ROWS 0x00004 /* ROWS behavior */ +#define FRAMEOPTION_GROUPS 0x00008 /* GROUPS behavior */ +#define FRAMEOPTION_BETWEEN 0x00010 /* BETWEEN given? */ +#define FRAMEOPTION_START_UNBOUNDED_PRECEDING 0x00020 /* start is U. P. */ +#define FRAMEOPTION_END_UNBOUNDED_PRECEDING 0x00040 /* (disallowed) */ +#define FRAMEOPTION_START_UNBOUNDED_FOLLOWING 0x00080 /* (disallowed) */ +#define FRAMEOPTION_END_UNBOUNDED_FOLLOWING 0x00100 /* end is U. F. */ +#define FRAMEOPTION_START_CURRENT_ROW 0x00200 /* start is C. R. */ +#define FRAMEOPTION_END_CURRENT_ROW 0x00400 /* end is C. R. */ +#define FRAMEOPTION_START_OFFSET_PRECEDING 0x00800 /* start is O. P. */ +#define FRAMEOPTION_END_OFFSET_PRECEDING 0x01000 /* end is O. P. */ +#define FRAMEOPTION_START_OFFSET_FOLLOWING 0x02000 /* start is O. F. */ +#define FRAMEOPTION_END_OFFSET_FOLLOWING 0x04000 /* end is O. F. */ +#define FRAMEOPTION_EXCLUDE_CURRENT_ROW 0x08000 /* omit C.R. */ +#define FRAMEOPTION_EXCLUDE_GROUP 0x10000 /* omit C.R. & peers */ +#define FRAMEOPTION_EXCLUDE_TIES 0x20000 /* omit C.R.'s peers */ + +#define FRAMEOPTION_START_OFFSET \ + (FRAMEOPTION_START_OFFSET_PRECEDING | FRAMEOPTION_START_OFFSET_FOLLOWING) +#define FRAMEOPTION_END_OFFSET \ + (FRAMEOPTION_END_OFFSET_PRECEDING | FRAMEOPTION_END_OFFSET_FOLLOWING) +#define FRAMEOPTION_EXCLUSION \ + (FRAMEOPTION_EXCLUDE_CURRENT_ROW | FRAMEOPTION_EXCLUDE_GROUP | \ + FRAMEOPTION_EXCLUDE_TIES) + +#define FRAMEOPTION_DEFAULTS \ + (FRAMEOPTION_RANGE | FRAMEOPTION_START_UNBOUNDED_PRECEDING | \ + FRAMEOPTION_END_CURRENT_ROW) + +/* + * RangeSubselect - subquery appearing in a FROM clause + */ +typedef struct RangeSubselect +{ + NodeTag type; + bool lateral; /* does it have LATERAL prefix? */ + Node *subquery; /* the untransformed sub-select clause */ + Alias *alias; /* table alias & optional column aliases */ +} RangeSubselect; + +/* + * RangeFunction - function call appearing in a FROM clause + * + * functions is a List because we use this to represent the construct + * ROWS FROM(func1(...), func2(...), ...). Each element of this list is a + * two-element sublist, the first element being the untransformed function + * call tree, and the second element being a possibly-empty list of ColumnDef + * nodes representing any columndef list attached to that function within the + * ROWS FROM() syntax. + * + * alias and coldeflist represent any alias and/or columndef list attached + * at the top level. (We disallow coldeflist appearing both here and + * per-function, but that's checked in parse analysis, not by the grammar.) + */ +typedef struct RangeFunction +{ + NodeTag type; + bool lateral; /* does it have LATERAL prefix? */ + bool ordinality; /* does it have WITH ORDINALITY suffix? */ + bool is_rowsfrom; /* is result of ROWS FROM() syntax? */ + List *functions; /* per-function information, see above */ + Alias *alias; /* table alias & optional column aliases */ + List *coldeflist; /* list of ColumnDef nodes to describe result + * of function returning RECORD */ +} RangeFunction; + +/* + * RangeTableFunc - raw form of "table functions" such as XMLTABLE + */ +typedef struct RangeTableFunc +{ + NodeTag type; + bool lateral; /* does it have LATERAL prefix? */ + Node *docexpr; /* document expression */ + Node *rowexpr; /* row generator expression */ + List *namespaces; /* list of namespaces as ResTarget */ + List *columns; /* list of RangeTableFuncCol */ + Alias *alias; /* table alias & optional column aliases */ + int location; /* token location, or -1 if unknown */ +} RangeTableFunc; + +/* + * RangeTableFuncCol - one column in a RangeTableFunc->columns + * + * If for_ordinality is true (FOR ORDINALITY), then the column is an int4 + * column and the rest of the fields are ignored. + */ +typedef struct RangeTableFuncCol +{ + NodeTag type; + char *colname; /* name of generated column */ + TypeName *typeName; /* type of generated column */ + bool for_ordinality; /* does it have FOR ORDINALITY? */ + bool is_not_null; /* does it have NOT NULL? */ + Node *colexpr; /* column filter expression */ + Node *coldefexpr; /* column default value expression */ + int location; /* token location, or -1 if unknown */ +} RangeTableFuncCol; + +/* + * RangeTableSample - TABLESAMPLE appearing in a raw FROM clause + * + * This node, appearing only in raw parse trees, represents + * <relation> TABLESAMPLE <method> (<params>) REPEATABLE (<num>) + * Currently, the <relation> can only be a RangeVar, but we might in future + * allow RangeSubselect and other options. Note that the RangeTableSample + * is wrapped around the node representing the <relation>, rather than being + * a subfield of it. + */ +typedef struct RangeTableSample +{ + NodeTag type; + Node *relation; /* relation to be sampled */ + List *method; /* sampling method name (possibly qualified) */ + List *args; /* argument(s) for sampling method */ + Node *repeatable; /* REPEATABLE expression, or NULL if none */ + int location; /* method name location, or -1 if unknown */ +} RangeTableSample; + +/* + * ColumnDef - column definition (used in various creates) + * + * If the column has a default value, we may have the value expression + * in either "raw" form (an untransformed parse tree) or "cooked" form + * (a post-parse-analysis, executable expression tree), depending on + * how this ColumnDef node was created (by parsing, or by inheritance + * from an existing relation). We should never have both in the same node! + * + * Similarly, we may have a COLLATE specification in either raw form + * (represented as a CollateClause with arg==NULL) or cooked form + * (the collation's OID). + * + * The constraints list may contain a CONSTR_DEFAULT item in a raw + * parsetree produced by gram.y, but transformCreateStmt will remove + * the item and set raw_default instead. CONSTR_DEFAULT items + * should not appear in any subsequent processing. + */ +typedef struct ColumnDef +{ + NodeTag type; + char *colname; /* name of column */ + TypeName *typeName; /* type of column */ + char *compression; /* compression method for column */ + int inhcount; /* number of times column is inherited */ + bool is_local; /* column has local (non-inherited) def'n */ + bool is_not_null; /* NOT NULL constraint specified? */ + bool is_from_type; /* column definition came from table type */ + char storage; /* attstorage setting, or 0 for default */ + char *storage_name; /* attstorage setting name or NULL for default */ + Node *raw_default; /* default value (untransformed parse tree) */ + Node *cooked_default; /* default value (transformed expr tree) */ + char identity; /* attidentity setting */ + RangeVar *identitySequence; /* to store identity sequence name for + * ALTER TABLE ... ADD COLUMN */ + char generated; /* attgenerated setting */ + CollateClause *collClause; /* untransformed COLLATE spec, if any */ + Oid collOid; /* collation OID (InvalidOid if not set) */ + List *constraints; /* other constraints on column */ + List *fdwoptions; /* per-column FDW options */ + int location; /* parse location, or -1 if none/unknown */ +} ColumnDef; + +/* + * TableLikeClause - CREATE TABLE ( ... LIKE ... ) clause + */ +typedef struct TableLikeClause +{ + NodeTag type; + RangeVar *relation; + bits32 options; /* OR of TableLikeOption flags */ + Oid relationOid; /* If table has been looked up, its OID */ +} TableLikeClause; + +typedef enum TableLikeOption +{ + CREATE_TABLE_LIKE_COMMENTS = 1 << 0, + CREATE_TABLE_LIKE_COMPRESSION = 1 << 1, + CREATE_TABLE_LIKE_CONSTRAINTS = 1 << 2, + CREATE_TABLE_LIKE_DEFAULTS = 1 << 3, + CREATE_TABLE_LIKE_GENERATED = 1 << 4, + CREATE_TABLE_LIKE_IDENTITY = 1 << 5, + CREATE_TABLE_LIKE_INDEXES = 1 << 6, + CREATE_TABLE_LIKE_STATISTICS = 1 << 7, + CREATE_TABLE_LIKE_STORAGE = 1 << 8, + CREATE_TABLE_LIKE_ALL = PG_INT32_MAX +} TableLikeOption; + +/* + * IndexElem - index parameters (used in CREATE INDEX, and in ON CONFLICT) + * + * For a plain index attribute, 'name' is the name of the table column to + * index, and 'expr' is NULL. For an index expression, 'name' is NULL and + * 'expr' is the expression tree. + */ +typedef struct IndexElem +{ + NodeTag type; + char *name; /* name of attribute to index, or NULL */ + Node *expr; /* expression to index, or NULL */ + char *indexcolname; /* name for index column; NULL = default */ + List *collation; /* name of collation; NIL = default */ + List *opclass; /* name of desired opclass; NIL = default */ + List *opclassopts; /* opclass-specific options, or NIL */ + SortByDir ordering; /* ASC/DESC/default */ + SortByNulls nulls_ordering; /* FIRST/LAST/default */ +} IndexElem; + +/* + * DefElem - a generic "name = value" option definition + * + * In some contexts the name can be qualified. Also, certain SQL commands + * allow a SET/ADD/DROP action to be attached to option settings, so it's + * convenient to carry a field for that too. (Note: currently, it is our + * practice that the grammar allows namespace and action only in statements + * where they are relevant; C code can just ignore those fields in other + * statements.) + */ +typedef enum DefElemAction +{ + DEFELEM_UNSPEC, /* no action given */ + DEFELEM_SET, + DEFELEM_ADD, + DEFELEM_DROP +} DefElemAction; + +typedef struct DefElem +{ + NodeTag type; + char *defnamespace; /* NULL if unqualified name */ + char *defname; + Node *arg; /* typically Integer, Float, String, or + * TypeName */ + DefElemAction defaction; /* unspecified action, or SET/ADD/DROP */ + int location; /* token location, or -1 if unknown */ +} DefElem; + +/* + * LockingClause - raw representation of FOR [NO KEY] UPDATE/[KEY] SHARE + * options + * + * Note: lockedRels == NIL means "all relations in query". Otherwise it + * is a list of RangeVar nodes. (We use RangeVar mainly because it carries + * a location field --- currently, parse analysis insists on unqualified + * names in LockingClause.) + */ +typedef struct LockingClause +{ + NodeTag type; + List *lockedRels; /* FOR [KEY] UPDATE/SHARE relations */ + LockClauseStrength strength; + LockWaitPolicy waitPolicy; /* NOWAIT and SKIP LOCKED */ +} LockingClause; + +/* + * XMLSERIALIZE (in raw parse tree only) + */ +typedef struct XmlSerialize +{ + NodeTag type; + XmlOptionType xmloption; /* DOCUMENT or CONTENT */ + Node *expr; + TypeName *typeName; + bool indent; /* [NO] INDENT */ + int location; /* token location, or -1 if unknown */ +} XmlSerialize; + +/* Partitioning related definitions */ + +/* + * PartitionElem - parse-time representation of a single partition key + * + * expr can be either a raw expression tree or a parse-analyzed expression. + * We don't store these on-disk, though. + */ +typedef struct PartitionElem +{ + NodeTag type; + char *name; /* name of column to partition on, or NULL */ + Node *expr; /* expression to partition on, or NULL */ + List *collation; /* name of collation; NIL = default */ + List *opclass; /* name of desired opclass; NIL = default */ + int location; /* token location, or -1 if unknown */ +} PartitionElem; + +typedef enum PartitionStrategy +{ + PARTITION_STRATEGY_LIST = 'l', + PARTITION_STRATEGY_RANGE = 'r', + PARTITION_STRATEGY_HASH = 'h' +} PartitionStrategy; + +/* + * PartitionSpec - parse-time representation of a partition key specification + * + * This represents the key space we will be partitioning on. + */ +typedef struct PartitionSpec +{ + NodeTag type; + PartitionStrategy strategy; + List *partParams; /* List of PartitionElems */ + int location; /* token location, or -1 if unknown */ +} PartitionSpec; + +/* + * PartitionBoundSpec - a partition bound specification + * + * This represents the portion of the partition key space assigned to a + * particular partition. These are stored on disk in pg_class.relpartbound. + */ +struct PartitionBoundSpec +{ + NodeTag type; + + char strategy; /* see PARTITION_STRATEGY codes above */ + bool is_default; /* is it a default partition bound? */ + + /* Partitioning info for HASH strategy: */ + int modulus; + int remainder; + + /* Partitioning info for LIST strategy: */ + List *listdatums; /* List of Consts (or A_Consts in raw tree) */ + + /* Partitioning info for RANGE strategy: */ + List *lowerdatums; /* List of PartitionRangeDatums */ + List *upperdatums; /* List of PartitionRangeDatums */ + + int location; /* token location, or -1 if unknown */ +}; + +/* + * PartitionRangeDatum - one of the values in a range partition bound + * + * This can be MINVALUE, MAXVALUE or a specific bounded value. + */ +typedef enum PartitionRangeDatumKind +{ + PARTITION_RANGE_DATUM_MINVALUE = -1, /* less than any other value */ + PARTITION_RANGE_DATUM_VALUE = 0, /* a specific (bounded) value */ + PARTITION_RANGE_DATUM_MAXVALUE = 1 /* greater than any other value */ +} PartitionRangeDatumKind; + +typedef struct PartitionRangeDatum +{ + NodeTag type; + + PartitionRangeDatumKind kind; + Node *value; /* Const (or A_Const in raw tree), if kind is + * PARTITION_RANGE_DATUM_VALUE, else NULL */ + + int location; /* token location, or -1 if unknown */ +} PartitionRangeDatum; + +/* + * PartitionCmd - info for ALTER TABLE/INDEX ATTACH/DETACH PARTITION commands + */ +typedef struct PartitionCmd +{ + NodeTag type; + RangeVar *name; /* name of partition to attach/detach */ + PartitionBoundSpec *bound; /* FOR VALUES, if attaching */ + bool concurrent; +} PartitionCmd; + +/**************************************************************************** + * Nodes for a Query tree + ****************************************************************************/ + +/*-------------------- + * RangeTblEntry - + * A range table is a List of RangeTblEntry nodes. + * + * A range table entry may represent a plain relation, a sub-select in + * FROM, or the result of a JOIN clause. (Only explicit JOIN syntax + * produces an RTE, not the implicit join resulting from multiple FROM + * items. This is because we only need the RTE to deal with SQL features + * like outer joins and join-output-column aliasing.) Other special + * RTE types also exist, as indicated by RTEKind. + * + * Note that we consider RTE_RELATION to cover anything that has a pg_class + * entry. relkind distinguishes the sub-cases. + * + * alias is an Alias node representing the AS alias-clause attached to the + * FROM expression, or NULL if no clause. + * + * eref is the table reference name and column reference names (either + * real or aliases). Note that system columns (OID etc) are not included + * in the column list. + * eref->aliasname is required to be present, and should generally be used + * to identify the RTE for error messages etc. + * + * In RELATION RTEs, the colnames in both alias and eref are indexed by + * physical attribute number; this means there must be colname entries for + * dropped columns. When building an RTE we insert empty strings ("") for + * dropped columns. Note however that a stored rule may have nonempty + * colnames for columns dropped since the rule was created (and for that + * matter the colnames might be out of date due to column renamings). + * The same comments apply to FUNCTION RTEs when a function's return type + * is a named composite type. + * + * In JOIN RTEs, the colnames in both alias and eref are one-to-one with + * joinaliasvars entries. A JOIN RTE will omit columns of its inputs when + * those columns are known to be dropped at parse time. Again, however, + * a stored rule might contain entries for columns dropped since the rule + * was created. (This is only possible for columns not actually referenced + * in the rule.) When loading a stored rule, we replace the joinaliasvars + * items for any such columns with null pointers. (We can't simply delete + * them from the joinaliasvars list, because that would affect the attnums + * of Vars referencing the rest of the list.) + * + * inh is true for relation references that should be expanded to include + * inheritance children, if the rel has any. This *must* be false for + * RTEs other than RTE_RELATION entries. + * + * inFromCl marks those range variables that are listed in the FROM clause. + * It's false for RTEs that are added to a query behind the scenes, such + * as the NEW and OLD variables for a rule, or the subqueries of a UNION. + * This flag is not used during parsing (except in transformLockingClause, + * q.v.); the parser now uses a separate "namespace" data structure to + * control visibility. But it is needed by ruleutils.c to determine + * whether RTEs should be shown in decompiled queries. + * + * securityQuals is a list of security barrier quals (boolean expressions), + * to be tested in the listed order before returning a row from the + * relation. It is always NIL in parser output. Entries are added by the + * rewriter to implement security-barrier views and/or row-level security. + * Note that the planner turns each boolean expression into an implicitly + * AND'ed sublist, as is its usual habit with qualification expressions. + *-------------------- + */ +typedef enum RTEKind +{ + RTE_RELATION, /* ordinary relation reference */ + RTE_SUBQUERY, /* subquery in FROM */ + RTE_JOIN, /* join */ + RTE_FUNCTION, /* function in FROM */ + RTE_TABLEFUNC, /* TableFunc(.., column list) */ + RTE_VALUES, /* VALUES (<exprlist>), (<exprlist>), ... */ + RTE_CTE, /* common table expr (WITH list element) */ + RTE_NAMEDTUPLESTORE, /* tuplestore, e.g. for AFTER triggers */ + RTE_RESULT /* RTE represents an empty FROM clause; such + * RTEs are added by the planner, they're not + * present during parsing or rewriting */ +} RTEKind; + +typedef struct RangeTblEntry +{ + pg_node_attr(custom_read_write, custom_query_jumble) + + NodeTag type; + + RTEKind rtekind; /* see above */ + + /* + * XXX the fields applicable to only some rte kinds should be merged into + * a union. I didn't do this yet because the diffs would impact a lot of + * code that is being actively worked on. FIXME someday. + */ + + /* + * Fields valid for a plain relation RTE (else zero): + * + * rellockmode is really LOCKMODE, but it's declared int to avoid having + * to include lock-related headers here. It must be RowExclusiveLock if + * the RTE is an INSERT/UPDATE/DELETE/MERGE target, else RowShareLock if + * the RTE is a SELECT FOR UPDATE/FOR SHARE target, else AccessShareLock. + * + * Note: in some cases, rule expansion may result in RTEs that are marked + * with RowExclusiveLock even though they are not the target of the + * current query; this happens if a DO ALSO rule simply scans the original + * target table. We leave such RTEs with their original lockmode so as to + * avoid getting an additional, lesser lock. + * + * perminfoindex is 1-based index of the RTEPermissionInfo belonging to + * this RTE in the containing struct's list of same; 0 if permissions need + * not be checked for this RTE. + * + * As a special case, relid, relkind, rellockmode, and perminfoindex can + * also be set (nonzero) in an RTE_SUBQUERY RTE. This occurs when we + * convert an RTE_RELATION RTE naming a view into an RTE_SUBQUERY + * containing the view's query. We still need to perform run-time locking + * and permission checks on the view, even though it's not directly used + * in the query anymore, and the most expedient way to do that is to + * retain these fields from the old state of the RTE. + * + * As a special case, RTE_NAMEDTUPLESTORE can also set relid to indicate + * that the tuple format of the tuplestore is the same as the referenced + * relation. This allows plans referencing AFTER trigger transition + * tables to be invalidated if the underlying table is altered. + */ + Oid relid; /* OID of the relation */ + char relkind; /* relation kind (see pg_class.relkind) */ + int rellockmode; /* lock level that query requires on the rel */ + struct TableSampleClause *tablesample; /* sampling info, or NULL */ + Index perminfoindex; + + /* + * Fields valid for a subquery RTE (else NULL): + */ + Query *subquery; /* the sub-query */ + bool security_barrier; /* is from security_barrier view? */ + + /* + * Fields valid for a join RTE (else NULL/zero): + * + * joinaliasvars is a list of (usually) Vars corresponding to the columns + * of the join result. An alias Var referencing column K of the join + * result can be replaced by the K'th element of joinaliasvars --- but to + * simplify the task of reverse-listing aliases correctly, we do not do + * that until planning time. In detail: an element of joinaliasvars can + * be a Var of one of the join's input relations, or such a Var with an + * implicit coercion to the join's output column type, or a COALESCE + * expression containing the two input column Vars (possibly coerced). + * Elements beyond the first joinmergedcols entries are always just Vars, + * and are never referenced from elsewhere in the query (that is, join + * alias Vars are generated only for merged columns). We keep these + * entries only because they're needed in expandRTE() and similar code. + * + * Vars appearing within joinaliasvars are marked with varnullingrels sets + * that describe the nulling effects of this join and lower ones. This is + * essential for FULL JOIN cases, because the COALESCE expression only + * describes the semantics correctly if its inputs have been nulled by the + * join. For other cases, it allows expandRTE() to generate a valid + * representation of the join's output without consulting additional + * parser state. + * + * Within a Query loaded from a stored rule, it is possible for non-merged + * joinaliasvars items to be null pointers, which are placeholders for + * (necessarily unreferenced) columns dropped since the rule was made. + * Also, once planning begins, joinaliasvars items can be almost anything, + * as a result of subquery-flattening substitutions. + * + * joinleftcols is an integer list of physical column numbers of the left + * join input rel that are included in the join; likewise joinrighttcols + * for the right join input rel. (Which rels those are can be determined + * from the associated JoinExpr.) If the join is USING/NATURAL, then the + * first joinmergedcols entries in each list identify the merged columns. + * The merged columns come first in the join output, then remaining + * columns of the left input, then remaining columns of the right. + * + * Note that input columns could have been dropped after creation of a + * stored rule, if they are not referenced in the query (in particular, + * merged columns could not be dropped); this is not accounted for in + * joinleftcols/joinrighttcols. + */ + JoinType jointype; /* type of join */ + int joinmergedcols; /* number of merged (JOIN USING) columns */ + List *joinaliasvars; /* list of alias-var expansions */ + List *joinleftcols; /* left-side input column numbers */ + List *joinrightcols; /* right-side input column numbers */ + + /* + * join_using_alias is an alias clause attached directly to JOIN/USING. It + * is different from the alias field (below) in that it does not hide the + * range variables of the tables being joined. + */ + Alias *join_using_alias; + + /* + * Fields valid for a function RTE (else NIL/zero): + * + * When funcordinality is true, the eref->colnames list includes an alias + * for the ordinality column. The ordinality column is otherwise + * implicit, and must be accounted for "by hand" in places such as + * expandRTE(). + */ + List *functions; /* list of RangeTblFunction nodes */ + bool funcordinality; /* is this called WITH ORDINALITY? */ + + /* + * Fields valid for a TableFunc RTE (else NULL): + */ + TableFunc *tablefunc; + + /* + * Fields valid for a values RTE (else NIL): + */ + List *values_lists; /* list of expression lists */ + + /* + * Fields valid for a CTE RTE (else NULL/zero): + */ + char *ctename; /* name of the WITH list item */ + Index ctelevelsup; /* number of query levels up */ + bool self_reference; /* is this a recursive self-reference? */ + + /* + * Fields valid for CTE, VALUES, ENR, and TableFunc RTEs (else NIL): + * + * We need these for CTE RTEs so that the types of self-referential + * columns are well-defined. For VALUES RTEs, storing these explicitly + * saves having to re-determine the info by scanning the values_lists. For + * ENRs, we store the types explicitly here (we could get the information + * from the catalogs if 'relid' was supplied, but we'd still need these + * for TupleDesc-based ENRs, so we might as well always store the type + * info here). For TableFuncs, these fields are redundant with data in + * the TableFunc node, but keeping them here allows some code sharing with + * the other cases. + * + * For ENRs only, we have to consider the possibility of dropped columns. + * A dropped column is included in these lists, but it will have zeroes in + * all three lists (as well as an empty-string entry in eref). Testing + * for zero coltype is the standard way to detect a dropped column. + */ + List *coltypes; /* OID list of column type OIDs */ + List *coltypmods; /* integer list of column typmods */ + List *colcollations; /* OID list of column collation OIDs */ + + /* + * Fields valid for ENR RTEs (else NULL/zero): + */ + char *enrname; /* name of ephemeral named relation */ + Cardinality enrtuples; /* estimated or actual from caller */ + + /* + * Fields valid in all RTEs: + */ + Alias *alias; /* user-written alias clause, if any */ + Alias *eref; /* expanded reference names */ + bool lateral; /* subquery, function, or values is LATERAL? */ + bool inh; /* inheritance requested? */ + bool inFromCl; /* present in FROM clause? */ + List *securityQuals; /* security barrier quals to apply, if any */ +} RangeTblEntry; + +/* + * RTEPermissionInfo + * Per-relation information for permission checking. Added to the Query + * node by the parser when adding the corresponding RTE to the query + * range table and subsequently editorialized on by the rewriter if + * needed after rule expansion. + * + * Only the relations directly mentioned in the query are checked for + * access permissions by the core executor, so only their RTEPermissionInfos + * are present in the Query. However, extensions may want to check inheritance + * children too, depending on the value of rte->inh, so it's copied in 'inh' + * for their perusal. + * + * requiredPerms and checkAsUser specify run-time access permissions checks + * to be performed at query startup. The user must have *all* of the + * permissions that are OR'd together in requiredPerms (never 0!). If + * checkAsUser is not zero, then do the permissions checks using the access + * rights of that user, not the current effective user ID. (This allows rules + * to act as setuid gateways.) + * + * For SELECT/INSERT/UPDATE permissions, if the user doesn't have table-wide + * permissions then it is sufficient to have the permissions on all columns + * identified in selectedCols (for SELECT) and/or insertedCols and/or + * updatedCols (INSERT with ON CONFLICT DO UPDATE may have all 3). + * selectedCols, insertedCols and updatedCols are bitmapsets, which cannot have + * negative integer members, so we subtract FirstLowInvalidHeapAttributeNumber + * from column numbers before storing them in these fields. A whole-row Var + * reference is represented by setting the bit for InvalidAttrNumber. + * + * updatedCols is also used in some other places, for example, to determine + * which triggers to fire and in FDWs to know which changed columns they need + * to ship off. + */ +typedef struct RTEPermissionInfo +{ + NodeTag type; + + Oid relid; /* relation OID */ + bool inh; /* separately check inheritance children? */ + AclMode requiredPerms; /* bitmask of required access permissions */ + Oid checkAsUser; /* if valid, check access as this role */ + Bitmapset *selectedCols; /* columns needing SELECT permission */ + Bitmapset *insertedCols; /* columns needing INSERT permission */ + Bitmapset *updatedCols; /* columns needing UPDATE permission */ +} RTEPermissionInfo; + +/* + * RangeTblFunction - + * RangeTblEntry subsidiary data for one function in a FUNCTION RTE. + * + * If the function had a column definition list (required for an + * otherwise-unspecified RECORD result), funccolnames lists the names given + * in the definition list, funccoltypes lists their declared column types, + * funccoltypmods lists their typmods, funccolcollations their collations. + * Otherwise, those fields are NIL. + * + * Notice we don't attempt to store info about the results of functions + * returning named composite types, because those can change from time to + * time. We do however remember how many columns we thought the type had + * (including dropped columns!), so that we can successfully ignore any + * columns added after the query was parsed. + * + * The query jumbling only needs to track the function expression. + */ +typedef struct RangeTblFunction +{ + NodeTag type; + + Node *funcexpr; /* expression tree for func call */ + /* number of columns it contributes to RTE */ + int funccolcount pg_node_attr(query_jumble_ignore); + /* These fields record the contents of a column definition list, if any: */ + /* column names (list of String) */ + List *funccolnames pg_node_attr(query_jumble_ignore); + /* OID list of column type OIDs */ + List *funccoltypes pg_node_attr(query_jumble_ignore); + /* integer list of column typmods */ + List *funccoltypmods pg_node_attr(query_jumble_ignore); + /* OID list of column collation OIDs */ + List *funccolcollations pg_node_attr(query_jumble_ignore); + + /* This is set during planning for use by the executor: */ + /* PARAM_EXEC Param IDs affecting this func */ + Bitmapset *funcparams pg_node_attr(query_jumble_ignore); +} RangeTblFunction; + +/* + * TableSampleClause - TABLESAMPLE appearing in a transformed FROM clause + * + * Unlike RangeTableSample, this is a subnode of the relevant RangeTblEntry. + */ +typedef struct TableSampleClause +{ + NodeTag type; + Oid tsmhandler; /* OID of the tablesample handler function */ + List *args; /* tablesample argument expression(s) */ + Expr *repeatable; /* REPEATABLE expression, or NULL if none */ +} TableSampleClause; + +/* + * WithCheckOption - + * representation of WITH CHECK OPTION checks to be applied to new tuples + * when inserting/updating an auto-updatable view, or RLS WITH CHECK + * policies to be applied when inserting/updating a relation with RLS. + */ +typedef enum WCOKind +{ + WCO_VIEW_CHECK, /* WCO on an auto-updatable view */ + WCO_RLS_INSERT_CHECK, /* RLS INSERT WITH CHECK policy */ + WCO_RLS_UPDATE_CHECK, /* RLS UPDATE WITH CHECK policy */ + WCO_RLS_CONFLICT_CHECK, /* RLS ON CONFLICT DO UPDATE USING policy */ + WCO_RLS_MERGE_UPDATE_CHECK, /* RLS MERGE UPDATE USING policy */ + WCO_RLS_MERGE_DELETE_CHECK /* RLS MERGE DELETE USING policy */ +} WCOKind; + +typedef struct WithCheckOption +{ + NodeTag type; + WCOKind kind; /* kind of WCO */ + char *relname; /* name of relation that specified the WCO */ + char *polname; /* name of RLS policy being checked */ + Node *qual; /* constraint qual to check */ + bool cascaded; /* true for a cascaded WCO on a view */ +} WithCheckOption; + +/* + * SortGroupClause - + * representation of ORDER BY, GROUP BY, PARTITION BY, + * DISTINCT, DISTINCT ON items + * + * You might think that ORDER BY is only interested in defining ordering, + * and GROUP/DISTINCT are only interested in defining equality. However, + * one way to implement grouping is to sort and then apply a "uniq"-like + * filter. So it's also interesting to keep track of possible sort operators + * for GROUP/DISTINCT, and in particular to try to sort for the grouping + * in a way that will also yield a requested ORDER BY ordering. So we need + * to be able to compare ORDER BY and GROUP/DISTINCT lists, which motivates + * the decision to give them the same representation. + * + * tleSortGroupRef must match ressortgroupref of exactly one entry of the + * query's targetlist; that is the expression to be sorted or grouped by. + * eqop is the OID of the equality operator. + * sortop is the OID of the ordering operator (a "<" or ">" operator), + * or InvalidOid if not available. + * nulls_first means about what you'd expect. If sortop is InvalidOid + * then nulls_first is meaningless and should be set to false. + * hashable is true if eqop is hashable (note this condition also depends + * on the datatype of the input expression). + * + * In an ORDER BY item, all fields must be valid. (The eqop isn't essential + * here, but it's cheap to get it along with the sortop, and requiring it + * to be valid eases comparisons to grouping items.) Note that this isn't + * actually enough information to determine an ordering: if the sortop is + * collation-sensitive, a collation OID is needed too. We don't store the + * collation in SortGroupClause because it's not available at the time the + * parser builds the SortGroupClause; instead, consult the exposed collation + * of the referenced targetlist expression to find out what it is. + * + * In a grouping item, eqop must be valid. If the eqop is a btree equality + * operator, then sortop should be set to a compatible ordering operator. + * We prefer to set eqop/sortop/nulls_first to match any ORDER BY item that + * the query presents for the same tlist item. If there is none, we just + * use the default ordering op for the datatype. + * + * If the tlist item's type has a hash opclass but no btree opclass, then + * we will set eqop to the hash equality operator, sortop to InvalidOid, + * and nulls_first to false. A grouping item of this kind can only be + * implemented by hashing, and of course it'll never match an ORDER BY item. + * + * The hashable flag is provided since we generally have the requisite + * information readily available when the SortGroupClause is constructed, + * and it's relatively expensive to get it again later. Note there is no + * need for a "sortable" flag since OidIsValid(sortop) serves the purpose. + * + * A query might have both ORDER BY and DISTINCT (or DISTINCT ON) clauses. + * In SELECT DISTINCT, the distinctClause list is as long or longer than the + * sortClause list, while in SELECT DISTINCT ON it's typically shorter. + * The two lists must match up to the end of the shorter one --- the parser + * rearranges the distinctClause if necessary to make this true. (This + * restriction ensures that only one sort step is needed to both satisfy the + * ORDER BY and set up for the Unique step. This is semantically necessary + * for DISTINCT ON, and presents no real drawback for DISTINCT.) + */ +typedef struct SortGroupClause +{ + NodeTag type; + Index tleSortGroupRef; /* reference into targetlist */ + Oid eqop; /* the equality operator ('=' op) */ + Oid sortop; /* the ordering operator ('<' op), or 0 */ + bool nulls_first; /* do NULLs come before normal values? */ + /* can eqop be implemented by hashing? */ + bool hashable pg_node_attr(query_jumble_ignore); +} SortGroupClause; + +/* + * GroupingSet - + * representation of CUBE, ROLLUP and GROUPING SETS clauses + * + * In a Query with grouping sets, the groupClause contains a flat list of + * SortGroupClause nodes for each distinct expression used. The actual + * structure of the GROUP BY clause is given by the groupingSets tree. + * + * In the raw parser output, GroupingSet nodes (of all types except SIMPLE + * which is not used) are potentially mixed in with the expressions in the + * groupClause of the SelectStmt. (An expression can't contain a GroupingSet, + * but a list may mix GroupingSet and expression nodes.) At this stage, the + * content of each node is a list of expressions, some of which may be RowExprs + * which represent sublists rather than actual row constructors, and nested + * GroupingSet nodes where legal in the grammar. The structure directly + * reflects the query syntax. + * + * In parse analysis, the transformed expressions are used to build the tlist + * and groupClause list (of SortGroupClause nodes), and the groupingSets tree + * is eventually reduced to a fixed format: + * + * EMPTY nodes represent (), and obviously have no content + * + * SIMPLE nodes represent a list of one or more expressions to be treated as an + * atom by the enclosing structure; the content is an integer list of + * ressortgroupref values (see SortGroupClause) + * + * CUBE and ROLLUP nodes contain a list of one or more SIMPLE nodes. + * + * SETS nodes contain a list of EMPTY, SIMPLE, CUBE or ROLLUP nodes, but after + * parse analysis they cannot contain more SETS nodes; enough of the syntactic + * transforms of the spec have been applied that we no longer have arbitrarily + * deep nesting (though we still preserve the use of cube/rollup). + * + * Note that if the groupingSets tree contains no SIMPLE nodes (only EMPTY + * nodes at the leaves), then the groupClause will be empty, but this is still + * an aggregation query (similar to using aggs or HAVING without GROUP BY). + * + * As an example, the following clause: + * + * GROUP BY GROUPING SETS ((a,b), CUBE(c,(d,e))) + * + * looks like this after raw parsing: + * + * SETS( RowExpr(a,b) , CUBE( c, RowExpr(d,e) ) ) + * + * and parse analysis converts it to: + * + * SETS( SIMPLE(1,2), CUBE( SIMPLE(3), SIMPLE(4,5) ) ) + */ +typedef enum GroupingSetKind +{ + GROUPING_SET_EMPTY, + GROUPING_SET_SIMPLE, + GROUPING_SET_ROLLUP, + GROUPING_SET_CUBE, + GROUPING_SET_SETS +} GroupingSetKind; + +typedef struct GroupingSet +{ + NodeTag type; + GroupingSetKind kind pg_node_attr(query_jumble_ignore); + List *content; + int location; +} GroupingSet; + +/* + * WindowClause - + * transformed representation of WINDOW and OVER clauses + * + * A parsed Query's windowClause list contains these structs. "name" is set + * if the clause originally came from WINDOW, and is NULL if it originally + * was an OVER clause (but note that we collapse out duplicate OVERs). + * partitionClause and orderClause are lists of SortGroupClause structs. + * If we have RANGE with offset PRECEDING/FOLLOWING, the semantics of that are + * specified by startInRangeFunc/inRangeColl/inRangeAsc/inRangeNullsFirst + * for the start offset, or endInRangeFunc/inRange* for the end offset. + * winref is an ID number referenced by WindowFunc nodes; it must be unique + * among the members of a Query's windowClause list. + * When refname isn't null, the partitionClause is always copied from there; + * the orderClause might or might not be copied (see copiedOrder); the framing + * options are never copied, per spec. + * + * The information relevant for the query jumbling is the partition clause + * type and its bounds. + */ +typedef struct WindowClause +{ + NodeTag type; + /* window name (NULL in an OVER clause) */ + char *name pg_node_attr(query_jumble_ignore); + /* referenced window name, if any */ + char *refname pg_node_attr(query_jumble_ignore); + List *partitionClause; /* PARTITION BY list */ + /* ORDER BY list */ + List *orderClause; + int frameOptions; /* frame_clause options, see WindowDef */ + Node *startOffset; /* expression for starting bound, if any */ + Node *endOffset; /* expression for ending bound, if any */ + /* qual to help short-circuit execution */ + List *runCondition pg_node_attr(query_jumble_ignore); + /* in_range function for startOffset */ + Oid startInRangeFunc pg_node_attr(query_jumble_ignore); + /* in_range function for endOffset */ + Oid endInRangeFunc pg_node_attr(query_jumble_ignore); + /* collation for in_range tests */ + Oid inRangeColl pg_node_attr(query_jumble_ignore); + /* use ASC sort order for in_range tests? */ + bool inRangeAsc pg_node_attr(query_jumble_ignore); + /* nulls sort first for in_range tests? */ + bool inRangeNullsFirst pg_node_attr(query_jumble_ignore); + Index winref; /* ID referenced by window functions */ + /* did we copy orderClause from refname? */ + bool copiedOrder pg_node_attr(query_jumble_ignore); +} WindowClause; + +/* + * RowMarkClause - + * parser output representation of FOR [KEY] UPDATE/SHARE clauses + * + * Query.rowMarks contains a separate RowMarkClause node for each relation + * identified as a FOR [KEY] UPDATE/SHARE target. If one of these clauses + * is applied to a subquery, we generate RowMarkClauses for all normal and + * subquery rels in the subquery, but they are marked pushedDown = true to + * distinguish them from clauses that were explicitly written at this query + * level. Also, Query.hasForUpdate tells whether there were explicit FOR + * UPDATE/SHARE/KEY SHARE clauses in the current query level. + */ +typedef struct RowMarkClause +{ + NodeTag type; + Index rti; /* range table index of target relation */ + LockClauseStrength strength; + LockWaitPolicy waitPolicy; /* NOWAIT and SKIP LOCKED */ + bool pushedDown; /* pushed down from higher query level? */ +} RowMarkClause; + +/* + * WithClause - + * representation of WITH clause + * + * Note: WithClause does not propagate into the Query representation; + * but CommonTableExpr does. + */ +typedef struct WithClause +{ + NodeTag type; + List *ctes; /* list of CommonTableExprs */ + bool recursive; /* true = WITH RECURSIVE */ + int location; /* token location, or -1 if unknown */ +} WithClause; + +/* + * InferClause - + * ON CONFLICT unique index inference clause + * + * Note: InferClause does not propagate into the Query representation. + */ +typedef struct InferClause +{ + NodeTag type; + List *indexElems; /* IndexElems to infer unique index */ + Node *whereClause; /* qualification (partial-index predicate) */ + char *conname; /* Constraint name, or NULL if unnamed */ + int location; /* token location, or -1 if unknown */ +} InferClause; + +/* + * OnConflictClause - + * representation of ON CONFLICT clause + * + * Note: OnConflictClause does not propagate into the Query representation. + */ +typedef struct OnConflictClause +{ + NodeTag type; + OnConflictAction action; /* DO NOTHING or UPDATE? */ + InferClause *infer; /* Optional index inference clause */ + List *targetList; /* the target list (of ResTarget) */ + Node *whereClause; /* qualifications */ + int location; /* token location, or -1 if unknown */ +} OnConflictClause; + +/* + * CommonTableExpr - + * representation of WITH list element + */ + +typedef enum CTEMaterialize +{ + CTEMaterializeDefault, /* no option specified */ + CTEMaterializeAlways, /* MATERIALIZED */ + CTEMaterializeNever /* NOT MATERIALIZED */ +} CTEMaterialize; + +typedef struct CTESearchClause +{ + NodeTag type; + List *search_col_list; + bool search_breadth_first; + char *search_seq_column; + int location; +} CTESearchClause; + +typedef struct CTECycleClause +{ + NodeTag type; + List *cycle_col_list; + char *cycle_mark_column; + Node *cycle_mark_value; + Node *cycle_mark_default; + char *cycle_path_column; + int location; + /* These fields are set during parse analysis: */ + Oid cycle_mark_type; /* common type of _value and _default */ + int cycle_mark_typmod; + Oid cycle_mark_collation; + Oid cycle_mark_neop; /* <> operator for type */ +} CTECycleClause; + +typedef struct CommonTableExpr +{ + NodeTag type; + + /* + * Query name (never qualified). The string name is included in the query + * jumbling because RTE_CTE RTEs need it. + */ + char *ctename; + /* optional list of column names */ + List *aliascolnames pg_node_attr(query_jumble_ignore); + CTEMaterialize ctematerialized; /* is this an optimization fence? */ + /* SelectStmt/InsertStmt/etc before parse analysis, Query afterwards: */ + Node *ctequery; /* the CTE's subquery */ + CTESearchClause *search_clause pg_node_attr(query_jumble_ignore); + CTECycleClause *cycle_clause pg_node_attr(query_jumble_ignore); + int location; /* token location, or -1 if unknown */ + /* These fields are set during parse analysis: */ + /* is this CTE actually recursive? */ + bool cterecursive pg_node_attr(query_jumble_ignore); + + /* + * Number of RTEs referencing this CTE (excluding internal + * self-references), irrelevant for query jumbling. + */ + int cterefcount pg_node_attr(query_jumble_ignore); + /* list of output column names */ + List *ctecolnames pg_node_attr(query_jumble_ignore); + /* OID list of output column type OIDs */ + List *ctecoltypes pg_node_attr(query_jumble_ignore); + /* integer list of output column typmods */ + List *ctecoltypmods pg_node_attr(query_jumble_ignore); + /* OID list of column collation OIDs */ + List *ctecolcollations pg_node_attr(query_jumble_ignore); +} CommonTableExpr; + +/* Convenience macro to get the output tlist of a CTE's query */ +#define GetCTETargetList(cte) \ + (AssertMacro(IsA((cte)->ctequery, Query)), \ + ((Query *) (cte)->ctequery)->commandType == CMD_SELECT ? \ + ((Query *) (cte)->ctequery)->targetList : \ + ((Query *) (cte)->ctequery)->returningList) + +/* + * MergeWhenClause - + * raw parser representation of a WHEN clause in a MERGE statement + * + * This is transformed into MergeAction by parse analysis + */ +typedef struct MergeWhenClause +{ + NodeTag type; + bool matched; /* true=MATCHED, false=NOT MATCHED */ + CmdType commandType; /* INSERT/UPDATE/DELETE/DO NOTHING */ + OverridingKind override; /* OVERRIDING clause */ + Node *condition; /* WHEN conditions (raw parser) */ + List *targetList; /* INSERT/UPDATE targetlist */ + /* the following members are only used in INSERT actions */ + List *values; /* VALUES to INSERT, or NULL */ +} MergeWhenClause; + +/* + * MergeAction - + * Transformed representation of a WHEN clause in a MERGE statement + */ +typedef struct MergeAction +{ + NodeTag type; + bool matched; /* true=MATCHED, false=NOT MATCHED */ + CmdType commandType; /* INSERT/UPDATE/DELETE/DO NOTHING */ + /* OVERRIDING clause */ + OverridingKind override pg_node_attr(query_jumble_ignore); + Node *qual; /* transformed WHEN conditions */ + List *targetList; /* the target list (of TargetEntry) */ + /* target attribute numbers of an UPDATE */ + List *updateColnos pg_node_attr(query_jumble_ignore); +} MergeAction; + +/* + * TriggerTransition - + * representation of transition row or table naming clause + * + * Only transition tables are initially supported in the syntax, and only for + * AFTER triggers, but other permutations are accepted by the parser so we can + * give a meaningful message from C code. + */ +typedef struct TriggerTransition +{ + NodeTag type; + char *name; + bool isNew; + bool isTable; +} TriggerTransition; + +/* Nodes for SQL/JSON support */ + +/* + * JsonOutput - + * representation of JSON output clause (RETURNING type [FORMAT format]) + */ +typedef struct JsonOutput +{ + NodeTag type; + TypeName *typeName; /* RETURNING type name, if specified */ + JsonReturning *returning; /* RETURNING FORMAT clause and type Oids */ +} JsonOutput; + +/* + * JsonKeyValue - + * untransformed representation of JSON object key-value pair for + * JSON_OBJECT() and JSON_OBJECTAGG() + */ +typedef struct JsonKeyValue +{ + NodeTag type; + Expr *key; /* key expression */ + JsonValueExpr *value; /* JSON value expression */ +} JsonKeyValue; + +/* + * JsonObjectConstructor - + * untransformed representation of JSON_OBJECT() constructor + */ +typedef struct JsonObjectConstructor +{ + NodeTag type; + List *exprs; /* list of JsonKeyValue pairs */ + JsonOutput *output; /* RETURNING clause, if specified */ + bool absent_on_null; /* skip NULL values? */ + bool unique; /* check key uniqueness? */ + int location; /* token location, or -1 if unknown */ +} JsonObjectConstructor; + +/* + * JsonArrayConstructor - + * untransformed representation of JSON_ARRAY(element,...) constructor + */ +typedef struct JsonArrayConstructor +{ + NodeTag type; + List *exprs; /* list of JsonValueExpr elements */ + JsonOutput *output; /* RETURNING clause, if specified */ + bool absent_on_null; /* skip NULL elements? */ + int location; /* token location, or -1 if unknown */ +} JsonArrayConstructor; + +/* + * JsonArrayQueryConstructor - + * untransformed representation of JSON_ARRAY(subquery) constructor + */ +typedef struct JsonArrayQueryConstructor +{ + NodeTag type; + Node *query; /* subquery */ + JsonOutput *output; /* RETURNING clause, if specified */ + JsonFormat *format; /* FORMAT clause for subquery, if specified */ + bool absent_on_null; /* skip NULL elements? */ + int location; /* token location, or -1 if unknown */ +} JsonArrayQueryConstructor; + +/* + * JsonAggConstructor - + * common fields of untransformed representation of + * JSON_ARRAYAGG() and JSON_OBJECTAGG() + */ +typedef struct JsonAggConstructor +{ + NodeTag type; + JsonOutput *output; /* RETURNING clause, if any */ + Node *agg_filter; /* FILTER clause, if any */ + List *agg_order; /* ORDER BY clause, if any */ + struct WindowDef *over; /* OVER clause, if any */ + int location; /* token location, or -1 if unknown */ +} JsonAggConstructor; + +/* + * JsonObjectAgg - + * untransformed representation of JSON_OBJECTAGG() + */ +typedef struct JsonObjectAgg +{ + NodeTag type; + JsonAggConstructor *constructor; /* common fields */ + JsonKeyValue *arg; /* object key-value pair */ + bool absent_on_null; /* skip NULL values? */ + bool unique; /* check key uniqueness? */ +} JsonObjectAgg; + +/* + * JsonArrayAgg - + * untransformed representation of JSON_ARRAYAGG() + */ +typedef struct JsonArrayAgg +{ + NodeTag type; + JsonAggConstructor *constructor; /* common fields */ + JsonValueExpr *arg; /* array element expression */ + bool absent_on_null; /* skip NULL elements? */ +} JsonArrayAgg; + + +/***************************************************************************** + * Raw Grammar Output Statements + *****************************************************************************/ + +/* + * RawStmt --- container for any one statement's raw parse tree + * + * Parse analysis converts a raw parse tree headed by a RawStmt node into + * an analyzed statement headed by a Query node. For optimizable statements, + * the conversion is complex. For utility statements, the parser usually just + * transfers the raw parse tree (sans RawStmt) into the utilityStmt field of + * the Query node, and all the useful work happens at execution time. + * + * stmt_location/stmt_len identify the portion of the source text string + * containing this raw statement (useful for multi-statement strings). + * + * This is irrelevant for query jumbling, as this is not used in parsed + * queries. + */ +typedef struct RawStmt +{ + pg_node_attr(no_query_jumble) + + NodeTag type; + Node *stmt; /* raw parse tree */ + int stmt_location; /* start location, or -1 if unknown */ + int stmt_len; /* length in bytes; 0 means "rest of string" */ +} RawStmt; + +/***************************************************************************** + * Optimizable Statements + *****************************************************************************/ + +/* ---------------------- + * Insert Statement + * + * The source expression is represented by SelectStmt for both the + * SELECT and VALUES cases. If selectStmt is NULL, then the query + * is INSERT ... DEFAULT VALUES. + * ---------------------- + */ +typedef struct InsertStmt +{ + NodeTag type; + RangeVar *relation; /* relation to insert into */ + List *cols; /* optional: names of the target columns */ + Node *selectStmt; /* the source SELECT/VALUES, or NULL */ + OnConflictClause *onConflictClause; /* ON CONFLICT clause */ + List *returningList; /* list of expressions to return */ + WithClause *withClause; /* WITH clause */ + OverridingKind override; /* OVERRIDING clause */ +} InsertStmt; + +/* ---------------------- + * Delete Statement + * ---------------------- + */ +typedef struct DeleteStmt +{ + NodeTag type; + RangeVar *relation; /* relation to delete from */ + List *usingClause; /* optional using clause for more tables */ + Node *whereClause; /* qualifications */ + List *returningList; /* list of expressions to return */ + WithClause *withClause; /* WITH clause */ +} DeleteStmt; + +/* ---------------------- + * Update Statement + * ---------------------- + */ +typedef struct UpdateStmt +{ + NodeTag type; + RangeVar *relation; /* relation to update */ + List *targetList; /* the target list (of ResTarget) */ + Node *whereClause; /* qualifications */ + List *fromClause; /* optional from clause for more tables */ + List *returningList; /* list of expressions to return */ + WithClause *withClause; /* WITH clause */ +} UpdateStmt; + +/* ---------------------- + * Merge Statement + * ---------------------- + */ +typedef struct MergeStmt +{ + NodeTag type; + RangeVar *relation; /* target relation to merge into */ + Node *sourceRelation; /* source relation */ + Node *joinCondition; /* join condition between source and target */ + List *mergeWhenClauses; /* list of MergeWhenClause(es) */ + WithClause *withClause; /* WITH clause */ +} MergeStmt; + +/* ---------------------- + * Select Statement + * + * A "simple" SELECT is represented in the output of gram.y by a single + * SelectStmt node; so is a VALUES construct. A query containing set + * operators (UNION, INTERSECT, EXCEPT) is represented by a tree of SelectStmt + * nodes, in which the leaf nodes are component SELECTs and the internal nodes + * represent UNION, INTERSECT, or EXCEPT operators. Using the same node + * type for both leaf and internal nodes allows gram.y to stick ORDER BY, + * LIMIT, etc, clause values into a SELECT statement without worrying + * whether it is a simple or compound SELECT. + * ---------------------- + */ +typedef enum SetOperation +{ + SETOP_NONE = 0, + SETOP_UNION, + SETOP_INTERSECT, + SETOP_EXCEPT +} SetOperation; + +typedef struct SelectStmt +{ + NodeTag type; + + /* + * These fields are used only in "leaf" SelectStmts. + */ + List *distinctClause; /* NULL, list of DISTINCT ON exprs, or + * lcons(NIL,NIL) for all (SELECT DISTINCT) */ + IntoClause *intoClause; /* target for SELECT INTO */ + List *targetList; /* the target list (of ResTarget) */ + List *fromClause; /* the FROM clause */ + Node *whereClause; /* WHERE qualification */ + List *groupClause; /* GROUP BY clauses */ + bool groupDistinct; /* Is this GROUP BY DISTINCT? */ + Node *havingClause; /* HAVING conditional-expression */ + List *windowClause; /* WINDOW window_name AS (...), ... */ + + /* + * In a "leaf" node representing a VALUES list, the above fields are all + * null, and instead this field is set. Note that the elements of the + * sublists are just expressions, without ResTarget decoration. Also note + * that a list element can be DEFAULT (represented as a SetToDefault + * node), regardless of the context of the VALUES list. It's up to parse + * analysis to reject that where not valid. + */ + List *valuesLists; /* untransformed list of expression lists */ + + /* + * These fields are used in both "leaf" SelectStmts and upper-level + * SelectStmts. + */ + List *sortClause; /* sort clause (a list of SortBy's) */ + Node *limitOffset; /* # of result tuples to skip */ + Node *limitCount; /* # of result tuples to return */ + LimitOption limitOption; /* limit type */ + List *lockingClause; /* FOR UPDATE (list of LockingClause's) */ + WithClause *withClause; /* WITH clause */ + + /* + * These fields are used only in upper-level SelectStmts. + */ + SetOperation op; /* type of set op */ + bool all; /* ALL specified? */ + struct SelectStmt *larg; /* left child */ + struct SelectStmt *rarg; /* right child */ + /* Eventually add fields for CORRESPONDING spec here */ +} SelectStmt; + + +/* ---------------------- + * Set Operation node for post-analysis query trees + * + * After parse analysis, a SELECT with set operations is represented by a + * top-level Query node containing the leaf SELECTs as subqueries in its + * range table. Its setOperations field shows the tree of set operations, + * with leaf SelectStmt nodes replaced by RangeTblRef nodes, and internal + * nodes replaced by SetOperationStmt nodes. Information about the output + * column types is added, too. (Note that the child nodes do not necessarily + * produce these types directly, but we've checked that their output types + * can be coerced to the output column type.) Also, if it's not UNION ALL, + * information about the types' sort/group semantics is provided in the form + * of a SortGroupClause list (same representation as, eg, DISTINCT). + * The resolved common column collations are provided too; but note that if + * it's not UNION ALL, it's okay for a column to not have a common collation, + * so a member of the colCollations list could be InvalidOid even though the + * column has a collatable type. + * ---------------------- + */ +typedef struct SetOperationStmt +{ + NodeTag type; + SetOperation op; /* type of set op */ + bool all; /* ALL specified? */ + Node *larg; /* left child */ + Node *rarg; /* right child */ + /* Eventually add fields for CORRESPONDING spec here */ + + /* Fields derived during parse analysis (irrelevant for query jumbling): */ + /* OID list of output column type OIDs */ + List *colTypes pg_node_attr(query_jumble_ignore); + /* integer list of output column typmods */ + List *colTypmods pg_node_attr(query_jumble_ignore); + /* OID list of output column collation OIDs */ + List *colCollations pg_node_attr(query_jumble_ignore); + /* a list of SortGroupClause's */ + List *groupClauses pg_node_attr(query_jumble_ignore); + /* groupClauses is NIL if UNION ALL, but must be set otherwise */ +} SetOperationStmt; + + +/* + * RETURN statement (inside SQL function body) + */ +typedef struct ReturnStmt +{ + NodeTag type; + Node *returnval; +} ReturnStmt; + + +/* ---------------------- + * PL/pgSQL Assignment Statement + * + * Like SelectStmt, this is transformed into a SELECT Query. + * However, the targetlist of the result looks more like an UPDATE. + * ---------------------- + */ +typedef struct PLAssignStmt +{ + NodeTag type; + + char *name; /* initial column name */ + List *indirection; /* subscripts and field names, if any */ + int nnames; /* number of names to use in ColumnRef */ + SelectStmt *val; /* the PL/pgSQL expression to assign */ + int location; /* name's token location, or -1 if unknown */ +} PLAssignStmt; + + +/***************************************************************************** + * Other Statements (no optimizations required) + * + * These are not touched by parser/analyze.c except to put them into + * the utilityStmt field of a Query. This is eventually passed to + * ProcessUtility (by-passing rewriting and planning). Some of the + * statements do need attention from parse analysis, and this is + * done by routines in parser/parse_utilcmd.c after ProcessUtility + * receives the command for execution. + * DECLARE CURSOR, EXPLAIN, and CREATE TABLE AS are special cases: + * they contain optimizable statements, which get processed normally + * by parser/analyze.c. + *****************************************************************************/ + +/* + * When a command can act on several kinds of objects with only one + * parse structure required, use these constants to designate the + * object type. Note that commands typically don't support all the types. + */ + +typedef enum ObjectType +{ + OBJECT_ACCESS_METHOD, + OBJECT_AGGREGATE, + OBJECT_AMOP, + OBJECT_AMPROC, + OBJECT_ATTRIBUTE, /* type's attribute, when distinct from column */ + OBJECT_CAST, + OBJECT_COLUMN, + OBJECT_COLLATION, + OBJECT_CONVERSION, + OBJECT_DATABASE, + OBJECT_DEFAULT, + OBJECT_DEFACL, + OBJECT_DOMAIN, + OBJECT_DOMCONSTRAINT, + OBJECT_EVENT_TRIGGER, + OBJECT_EXTENSION, + OBJECT_FDW, + OBJECT_FOREIGN_SERVER, + OBJECT_FOREIGN_TABLE, + OBJECT_FUNCTION, + OBJECT_INDEX, + OBJECT_LANGUAGE, + OBJECT_LARGEOBJECT, + OBJECT_MATVIEW, + OBJECT_OPCLASS, + OBJECT_OPERATOR, + OBJECT_OPFAMILY, + OBJECT_PARAMETER_ACL, + OBJECT_POLICY, + OBJECT_PROCEDURE, + OBJECT_PUBLICATION, + OBJECT_PUBLICATION_NAMESPACE, + OBJECT_PUBLICATION_REL, + OBJECT_ROLE, + OBJECT_ROUTINE, + OBJECT_RULE, + OBJECT_SCHEMA, + OBJECT_SEQUENCE, + OBJECT_SUBSCRIPTION, + OBJECT_STATISTIC_EXT, + OBJECT_TABCONSTRAINT, + OBJECT_TABLE, + OBJECT_TABLESPACE, + OBJECT_TRANSFORM, + OBJECT_TRIGGER, + OBJECT_TSCONFIGURATION, + OBJECT_TSDICTIONARY, + OBJECT_TSPARSER, + OBJECT_TSTEMPLATE, + OBJECT_TYPE, + OBJECT_USER_MAPPING, + OBJECT_VIEW +} ObjectType; + +/* ---------------------- + * Create Schema Statement + * + * NOTE: the schemaElts list contains raw parsetrees for component statements + * of the schema, such as CREATE TABLE, GRANT, etc. These are analyzed and + * executed after the schema itself is created. + * ---------------------- + */ +typedef struct CreateSchemaStmt +{ + NodeTag type; + char *schemaname; /* the name of the schema to create */ + RoleSpec *authrole; /* the owner of the created schema */ + List *schemaElts; /* schema components (list of parsenodes) */ + bool if_not_exists; /* just do nothing if schema already exists? */ +} CreateSchemaStmt; + +typedef enum DropBehavior +{ + DROP_RESTRICT, /* drop fails if any dependent objects */ + DROP_CASCADE /* remove dependent objects too */ +} DropBehavior; + +/* ---------------------- + * Alter Table + * ---------------------- + */ +typedef struct AlterTableStmt +{ + NodeTag type; + RangeVar *relation; /* table to work on */ + List *cmds; /* list of subcommands */ + ObjectType objtype; /* type of object */ + bool missing_ok; /* skip error if table missing */ +} AlterTableStmt; + +typedef enum AlterTableType +{ + AT_AddColumn, /* add column */ + AT_AddColumnToView, /* implicitly via CREATE OR REPLACE VIEW */ + AT_ColumnDefault, /* alter column default */ + AT_CookedColumnDefault, /* add a pre-cooked column default */ + AT_DropNotNull, /* alter column drop not null */ + AT_SetNotNull, /* alter column set not null */ + AT_DropExpression, /* alter column drop expression */ + AT_CheckNotNull, /* check column is already marked not null */ + AT_SetStatistics, /* alter column set statistics */ + AT_SetOptions, /* alter column set ( options ) */ + AT_ResetOptions, /* alter column reset ( options ) */ + AT_SetStorage, /* alter column set storage */ + AT_SetCompression, /* alter column set compression */ + AT_DropColumn, /* drop column */ + AT_AddIndex, /* add index */ + AT_ReAddIndex, /* internal to commands/tablecmds.c */ + AT_AddConstraint, /* add constraint */ + AT_ReAddConstraint, /* internal to commands/tablecmds.c */ + AT_ReAddDomainConstraint, /* internal to commands/tablecmds.c */ + AT_AlterConstraint, /* alter constraint */ + AT_ValidateConstraint, /* validate constraint */ + AT_AddIndexConstraint, /* add constraint using existing index */ + AT_DropConstraint, /* drop constraint */ + AT_ReAddComment, /* internal to commands/tablecmds.c */ + AT_AlterColumnType, /* alter column type */ + AT_AlterColumnGenericOptions, /* alter column OPTIONS (...) */ + AT_ChangeOwner, /* change owner */ + AT_ClusterOn, /* CLUSTER ON */ + AT_DropCluster, /* SET WITHOUT CLUSTER */ + AT_SetLogged, /* SET LOGGED */ + AT_SetUnLogged, /* SET UNLOGGED */ + AT_DropOids, /* SET WITHOUT OIDS */ + AT_SetAccessMethod, /* SET ACCESS METHOD */ + AT_SetTableSpace, /* SET TABLESPACE */ + AT_SetRelOptions, /* SET (...) -- AM specific parameters */ + AT_ResetRelOptions, /* RESET (...) -- AM specific parameters */ + AT_ReplaceRelOptions, /* replace reloption list in its entirety */ + AT_EnableTrig, /* ENABLE TRIGGER name */ + AT_EnableAlwaysTrig, /* ENABLE ALWAYS TRIGGER name */ + AT_EnableReplicaTrig, /* ENABLE REPLICA TRIGGER name */ + AT_DisableTrig, /* DISABLE TRIGGER name */ + AT_EnableTrigAll, /* ENABLE TRIGGER ALL */ + AT_DisableTrigAll, /* DISABLE TRIGGER ALL */ + AT_EnableTrigUser, /* ENABLE TRIGGER USER */ + AT_DisableTrigUser, /* DISABLE TRIGGER USER */ + AT_EnableRule, /* ENABLE RULE name */ + AT_EnableAlwaysRule, /* ENABLE ALWAYS RULE name */ + AT_EnableReplicaRule, /* ENABLE REPLICA RULE name */ + AT_DisableRule, /* DISABLE RULE name */ + AT_AddInherit, /* INHERIT parent */ + AT_DropInherit, /* NO INHERIT parent */ + AT_AddOf, /* OF <type_name> */ + AT_DropOf, /* NOT OF */ + AT_ReplicaIdentity, /* REPLICA IDENTITY */ + AT_EnableRowSecurity, /* ENABLE ROW SECURITY */ + AT_DisableRowSecurity, /* DISABLE ROW SECURITY */ + AT_ForceRowSecurity, /* FORCE ROW SECURITY */ + AT_NoForceRowSecurity, /* NO FORCE ROW SECURITY */ + AT_GenericOptions, /* OPTIONS (...) */ + AT_AttachPartition, /* ATTACH PARTITION */ + AT_DetachPartition, /* DETACH PARTITION */ + AT_DetachPartitionFinalize, /* DETACH PARTITION FINALIZE */ + AT_AddIdentity, /* ADD IDENTITY */ + AT_SetIdentity, /* SET identity column options */ + AT_DropIdentity, /* DROP IDENTITY */ + AT_ReAddStatistics /* internal to commands/tablecmds.c */ +} AlterTableType; + +typedef struct ReplicaIdentityStmt +{ + NodeTag type; + char identity_type; + char *name; +} ReplicaIdentityStmt; + +typedef struct AlterTableCmd /* one subcommand of an ALTER TABLE */ +{ + NodeTag type; + AlterTableType subtype; /* Type of table alteration to apply */ + char *name; /* column, constraint, or trigger to act on, + * or tablespace */ + int16 num; /* attribute number for columns referenced by + * number */ + RoleSpec *newowner; + Node *def; /* definition of new column, index, + * constraint, or parent table */ + DropBehavior behavior; /* RESTRICT or CASCADE for DROP cases */ + bool missing_ok; /* skip error if missing? */ + bool recurse; /* exec-time recursion */ +} AlterTableCmd; + + +/* ---------------------- + * Alter Collation + * ---------------------- + */ +typedef struct AlterCollationStmt +{ + NodeTag type; + List *collname; +} AlterCollationStmt; + + +/* ---------------------- + * Alter Domain + * + * The fields are used in different ways by the different variants of + * this command. + * ---------------------- + */ +typedef struct AlterDomainStmt +{ + NodeTag type; + char subtype; /*------------ + * T = alter column default + * N = alter column drop not null + * O = alter column set not null + * C = add constraint + * X = drop constraint + *------------ + */ + List *typeName; /* domain to work on */ + char *name; /* column or constraint name to act on */ + Node *def; /* definition of default or constraint */ + DropBehavior behavior; /* RESTRICT or CASCADE for DROP cases */ + bool missing_ok; /* skip error if missing? */ +} AlterDomainStmt; + + +/* ---------------------- + * Grant|Revoke Statement + * ---------------------- + */ +typedef enum GrantTargetType +{ + ACL_TARGET_OBJECT, /* grant on specific named object(s) */ + ACL_TARGET_ALL_IN_SCHEMA, /* grant on all objects in given schema(s) */ + ACL_TARGET_DEFAULTS /* ALTER DEFAULT PRIVILEGES */ +} GrantTargetType; + +typedef struct GrantStmt +{ + NodeTag type; + bool is_grant; /* true = GRANT, false = REVOKE */ + GrantTargetType targtype; /* type of the grant target */ + ObjectType objtype; /* kind of object being operated on */ + List *objects; /* list of RangeVar nodes, ObjectWithArgs + * nodes, or plain names (as String values) */ + List *privileges; /* list of AccessPriv nodes */ + /* privileges == NIL denotes ALL PRIVILEGES */ + List *grantees; /* list of RoleSpec nodes */ + bool grant_option; /* grant or revoke grant option */ + RoleSpec *grantor; + DropBehavior behavior; /* drop behavior (for REVOKE) */ +} GrantStmt; + +/* + * ObjectWithArgs represents a function/procedure/operator name plus parameter + * identification. + * + * objargs includes only the types of the input parameters of the object. + * In some contexts, that will be all we have, and it's enough to look up + * objects according to the traditional Postgres rules (i.e., when only input + * arguments matter). + * + * objfuncargs, if not NIL, carries the full specification of the parameter + * list, including parameter mode annotations. + * + * Some grammar productions can set args_unspecified = true instead of + * providing parameter info. In this case, lookup will succeed only if + * the object name is unique. Note that otherwise, NIL parameter lists + * mean zero arguments. + */ +typedef struct ObjectWithArgs +{ + NodeTag type; + List *objname; /* qualified name of function/operator */ + List *objargs; /* list of Typename nodes (input args only) */ + List *objfuncargs; /* list of FunctionParameter nodes */ + bool args_unspecified; /* argument list was omitted? */ +} ObjectWithArgs; + +/* + * An access privilege, with optional list of column names + * priv_name == NULL denotes ALL PRIVILEGES (only used with a column list) + * cols == NIL denotes "all columns" + * Note that simple "ALL PRIVILEGES" is represented as a NIL list, not + * an AccessPriv with both fields null. + */ +typedef struct AccessPriv +{ + NodeTag type; + char *priv_name; /* string name of privilege */ + List *cols; /* list of String */ +} AccessPriv; + +/* ---------------------- + * Grant/Revoke Role Statement + * + * Note: because of the parsing ambiguity with the GRANT <privileges> + * statement, granted_roles is a list of AccessPriv; the execution code + * should complain if any column lists appear. grantee_roles is a list + * of role names, as String values. + * ---------------------- + */ +typedef struct GrantRoleStmt +{ + NodeTag type; + List *granted_roles; /* list of roles to be granted/revoked */ + List *grantee_roles; /* list of member roles to add/delete */ + bool is_grant; /* true = GRANT, false = REVOKE */ + List *opt; /* options e.g. WITH GRANT OPTION */ + RoleSpec *grantor; /* set grantor to other than current role */ + DropBehavior behavior; /* drop behavior (for REVOKE) */ +} GrantRoleStmt; + +/* ---------------------- + * Alter Default Privileges Statement + * ---------------------- + */ +typedef struct AlterDefaultPrivilegesStmt +{ + NodeTag type; + List *options; /* list of DefElem */ + GrantStmt *action; /* GRANT/REVOKE action (with objects=NIL) */ +} AlterDefaultPrivilegesStmt; + +/* ---------------------- + * Copy Statement + * + * We support "COPY relation FROM file", "COPY relation TO file", and + * "COPY (query) TO file". In any given CopyStmt, exactly one of "relation" + * and "query" must be non-NULL. + * ---------------------- + */ +typedef struct CopyStmt +{ + NodeTag type; + RangeVar *relation; /* the relation to copy */ + Node *query; /* the query (SELECT or DML statement with + * RETURNING) to copy, as a raw parse tree */ + List *attlist; /* List of column names (as Strings), or NIL + * for all columns */ + bool is_from; /* TO or FROM */ + bool is_program; /* is 'filename' a program to popen? */ + char *filename; /* filename, or NULL for STDIN/STDOUT */ + List *options; /* List of DefElem nodes */ + Node *whereClause; /* WHERE condition (or NULL) */ +} CopyStmt; + +/* ---------------------- + * SET Statement (includes RESET) + * + * "SET var TO DEFAULT" and "RESET var" are semantically equivalent, but we + * preserve the distinction in VariableSetKind for CreateCommandTag(). + * ---------------------- + */ +typedef enum VariableSetKind +{ + VAR_SET_VALUE, /* SET var = value */ + VAR_SET_DEFAULT, /* SET var TO DEFAULT */ + VAR_SET_CURRENT, /* SET var FROM CURRENT */ + VAR_SET_MULTI, /* special case for SET TRANSACTION ... */ + VAR_RESET, /* RESET var */ + VAR_RESET_ALL /* RESET ALL */ +} VariableSetKind; + +typedef struct VariableSetStmt +{ + NodeTag type; + VariableSetKind kind; + char *name; /* variable to be set */ + List *args; /* List of A_Const nodes */ + bool is_local; /* SET LOCAL? */ +} VariableSetStmt; + +/* ---------------------- + * Show Statement + * ---------------------- + */ +typedef struct VariableShowStmt +{ + NodeTag type; + char *name; +} VariableShowStmt; + +/* ---------------------- + * Create Table Statement + * + * NOTE: in the raw gram.y output, ColumnDef and Constraint nodes are + * intermixed in tableElts, and constraints is NIL. After parse analysis, + * tableElts contains just ColumnDefs, and constraints contains just + * Constraint nodes (in fact, only CONSTR_CHECK nodes, in the present + * implementation). + * ---------------------- + */ + +typedef struct CreateStmt +{ + NodeTag type; + RangeVar *relation; /* relation to create */ + List *tableElts; /* column definitions (list of ColumnDef) */ + List *inhRelations; /* relations to inherit from (list of + * RangeVar) */ + PartitionBoundSpec *partbound; /* FOR VALUES clause */ + PartitionSpec *partspec; /* PARTITION BY clause */ + TypeName *ofTypename; /* OF typename */ + List *constraints; /* constraints (list of Constraint nodes) */ + List *options; /* options from WITH clause */ + OnCommitAction oncommit; /* what do we do at COMMIT? */ + char *tablespacename; /* table space to use, or NULL */ + char *accessMethod; /* table access method */ + bool if_not_exists; /* just do nothing if it already exists? */ +} CreateStmt; + +/* ---------- + * Definitions for constraints in CreateStmt + * + * Note that column defaults are treated as a type of constraint, + * even though that's a bit odd semantically. + * + * For constraints that use expressions (CONSTR_CHECK, CONSTR_DEFAULT) + * we may have the expression in either "raw" form (an untransformed + * parse tree) or "cooked" form (the nodeToString representation of + * an executable expression tree), depending on how this Constraint + * node was created (by parsing, or by inheritance from an existing + * relation). We should never have both in the same node! + * + * FKCONSTR_ACTION_xxx values are stored into pg_constraint.confupdtype + * and pg_constraint.confdeltype columns; FKCONSTR_MATCH_xxx values are + * stored into pg_constraint.confmatchtype. Changing the code values may + * require an initdb! + * + * If skip_validation is true then we skip checking that the existing rows + * in the table satisfy the constraint, and just install the catalog entries + * for the constraint. A new FK constraint is marked as valid iff + * initially_valid is true. (Usually skip_validation and initially_valid + * are inverses, but we can set both true if the table is known empty.) + * + * Constraint attributes (DEFERRABLE etc) are initially represented as + * separate Constraint nodes for simplicity of parsing. parse_utilcmd.c makes + * a pass through the constraints list to insert the info into the appropriate + * Constraint node. + * ---------- + */ + +typedef enum ConstrType /* types of constraints */ +{ + CONSTR_NULL, /* not standard SQL, but a lot of people + * expect it */ + CONSTR_NOTNULL, + CONSTR_DEFAULT, + CONSTR_IDENTITY, + CONSTR_GENERATED, + CONSTR_CHECK, + CONSTR_PRIMARY, + CONSTR_UNIQUE, + CONSTR_EXCLUSION, + CONSTR_FOREIGN, + CONSTR_ATTR_DEFERRABLE, /* attributes for previous constraint node */ + CONSTR_ATTR_NOT_DEFERRABLE, + CONSTR_ATTR_DEFERRED, + CONSTR_ATTR_IMMEDIATE +} ConstrType; + +/* Foreign key action codes */ +#define FKCONSTR_ACTION_NOACTION 'a' +#define FKCONSTR_ACTION_RESTRICT 'r' +#define FKCONSTR_ACTION_CASCADE 'c' +#define FKCONSTR_ACTION_SETNULL 'n' +#define FKCONSTR_ACTION_SETDEFAULT 'd' + +/* Foreign key matchtype codes */ +#define FKCONSTR_MATCH_FULL 'f' +#define FKCONSTR_MATCH_PARTIAL 'p' +#define FKCONSTR_MATCH_SIMPLE 's' + +typedef struct Constraint +{ + pg_node_attr(custom_read_write) + + NodeTag type; + ConstrType contype; /* see above */ + + /* Fields used for most/all constraint types: */ + char *conname; /* Constraint name, or NULL if unnamed */ + bool deferrable; /* DEFERRABLE? */ + bool initdeferred; /* INITIALLY DEFERRED? */ + int location; /* token location, or -1 if unknown */ + + /* Fields used for constraints with expressions (CHECK and DEFAULT): */ + bool is_no_inherit; /* is constraint non-inheritable? */ + Node *raw_expr; /* expr, as untransformed parse tree */ + char *cooked_expr; /* expr, as nodeToString representation */ + char generated_when; /* ALWAYS or BY DEFAULT */ + + /* Fields used for unique constraints (UNIQUE and PRIMARY KEY): */ + bool nulls_not_distinct; /* null treatment for UNIQUE constraints */ + List *keys; /* String nodes naming referenced key + * column(s) */ + List *including; /* String nodes naming referenced nonkey + * column(s) */ + + /* Fields used for EXCLUSION constraints: */ + List *exclusions; /* list of (IndexElem, operator name) pairs */ + + /* Fields used for index constraints (UNIQUE, PRIMARY KEY, EXCLUSION): */ + List *options; /* options from WITH clause */ + char *indexname; /* existing index to use; otherwise NULL */ + char *indexspace; /* index tablespace; NULL for default */ + bool reset_default_tblspc; /* reset default_tablespace prior to + * creating the index */ + /* These could be, but currently are not, used for UNIQUE/PKEY: */ + char *access_method; /* index access method; NULL for default */ + Node *where_clause; /* partial index predicate */ + + /* Fields used for FOREIGN KEY constraints: */ + RangeVar *pktable; /* Primary key table */ + List *fk_attrs; /* Attributes of foreign key */ + List *pk_attrs; /* Corresponding attrs in PK table */ + char fk_matchtype; /* FULL, PARTIAL, SIMPLE */ + char fk_upd_action; /* ON UPDATE action */ + char fk_del_action; /* ON DELETE action */ + List *fk_del_set_cols; /* ON DELETE SET NULL/DEFAULT (col1, col2) */ + List *old_conpfeqop; /* pg_constraint.conpfeqop of my former self */ + Oid old_pktable_oid; /* pg_constraint.confrelid of my former + * self */ + + /* Fields used for constraints that allow a NOT VALID specification */ + bool skip_validation; /* skip validation of existing rows? */ + bool initially_valid; /* mark the new constraint as valid? */ +} Constraint; + +/* ---------------------- + * Create/Drop Table Space Statements + * ---------------------- + */ + +typedef struct CreateTableSpaceStmt +{ + NodeTag type; + char *tablespacename; + RoleSpec *owner; + char *location; + List *options; +} CreateTableSpaceStmt; + +typedef struct DropTableSpaceStmt +{ + NodeTag type; + char *tablespacename; + bool missing_ok; /* skip error if missing? */ +} DropTableSpaceStmt; + +typedef struct AlterTableSpaceOptionsStmt +{ + NodeTag type; + char *tablespacename; + List *options; + bool isReset; +} AlterTableSpaceOptionsStmt; + +typedef struct AlterTableMoveAllStmt +{ + NodeTag type; + char *orig_tablespacename; + ObjectType objtype; /* Object type to move */ + List *roles; /* List of roles to move objects of */ + char *new_tablespacename; + bool nowait; +} AlterTableMoveAllStmt; + +/* ---------------------- + * Create/Alter Extension Statements + * ---------------------- + */ + +typedef struct CreateExtensionStmt +{ + NodeTag type; + char *extname; + bool if_not_exists; /* just do nothing if it already exists? */ + List *options; /* List of DefElem nodes */ +} CreateExtensionStmt; + +/* Only used for ALTER EXTENSION UPDATE; later might need an action field */ +typedef struct AlterExtensionStmt +{ + NodeTag type; + char *extname; + List *options; /* List of DefElem nodes */ +} AlterExtensionStmt; + +typedef struct AlterExtensionContentsStmt +{ + NodeTag type; + char *extname; /* Extension's name */ + int action; /* +1 = add object, -1 = drop object */ + ObjectType objtype; /* Object's type */ + Node *object; /* Qualified name of the object */ +} AlterExtensionContentsStmt; + +/* ---------------------- + * Create/Alter FOREIGN DATA WRAPPER Statements + * ---------------------- + */ + +typedef struct CreateFdwStmt +{ + NodeTag type; + char *fdwname; /* foreign-data wrapper name */ + List *func_options; /* HANDLER/VALIDATOR options */ + List *options; /* generic options to FDW */ +} CreateFdwStmt; + +typedef struct AlterFdwStmt +{ + NodeTag type; + char *fdwname; /* foreign-data wrapper name */ + List *func_options; /* HANDLER/VALIDATOR options */ + List *options; /* generic options to FDW */ +} AlterFdwStmt; + +/* ---------------------- + * Create/Alter FOREIGN SERVER Statements + * ---------------------- + */ + +typedef struct CreateForeignServerStmt +{ + NodeTag type; + char *servername; /* server name */ + char *servertype; /* optional server type */ + char *version; /* optional server version */ + char *fdwname; /* FDW name */ + bool if_not_exists; /* just do nothing if it already exists? */ + List *options; /* generic options to server */ +} CreateForeignServerStmt; + +typedef struct AlterForeignServerStmt +{ + NodeTag type; + char *servername; /* server name */ + char *version; /* optional server version */ + List *options; /* generic options to server */ + bool has_version; /* version specified */ +} AlterForeignServerStmt; + +/* ---------------------- + * Create FOREIGN TABLE Statement + * ---------------------- + */ + +typedef struct CreateForeignTableStmt +{ + CreateStmt base; + char *servername; + List *options; +} CreateForeignTableStmt; + +/* ---------------------- + * Create/Drop USER MAPPING Statements + * ---------------------- + */ + +typedef struct CreateUserMappingStmt +{ + NodeTag type; + RoleSpec *user; /* user role */ + char *servername; /* server name */ + bool if_not_exists; /* just do nothing if it already exists? */ + List *options; /* generic options to server */ +} CreateUserMappingStmt; + +typedef struct AlterUserMappingStmt +{ + NodeTag type; + RoleSpec *user; /* user role */ + char *servername; /* server name */ + List *options; /* generic options to server */ +} AlterUserMappingStmt; + +typedef struct DropUserMappingStmt +{ + NodeTag type; + RoleSpec *user; /* user role */ + char *servername; /* server name */ + bool missing_ok; /* ignore missing mappings */ +} DropUserMappingStmt; + +/* ---------------------- + * Import Foreign Schema Statement + * ---------------------- + */ + +typedef enum ImportForeignSchemaType +{ + FDW_IMPORT_SCHEMA_ALL, /* all relations wanted */ + FDW_IMPORT_SCHEMA_LIMIT_TO, /* include only listed tables in import */ + FDW_IMPORT_SCHEMA_EXCEPT /* exclude listed tables from import */ +} ImportForeignSchemaType; + +typedef struct ImportForeignSchemaStmt +{ + NodeTag type; + char *server_name; /* FDW server name */ + char *remote_schema; /* remote schema name to query */ + char *local_schema; /* local schema to create objects in */ + ImportForeignSchemaType list_type; /* type of table list */ + List *table_list; /* List of RangeVar */ + List *options; /* list of options to pass to FDW */ +} ImportForeignSchemaStmt; + +/*---------------------- + * Create POLICY Statement + *---------------------- + */ +typedef struct CreatePolicyStmt +{ + NodeTag type; + char *policy_name; /* Policy's name */ + RangeVar *table; /* the table name the policy applies to */ + char *cmd_name; /* the command name the policy applies to */ + bool permissive; /* restrictive or permissive policy */ + List *roles; /* the roles associated with the policy */ + Node *qual; /* the policy's condition */ + Node *with_check; /* the policy's WITH CHECK condition. */ +} CreatePolicyStmt; + +/*---------------------- + * Alter POLICY Statement + *---------------------- + */ +typedef struct AlterPolicyStmt +{ + NodeTag type; + char *policy_name; /* Policy's name */ + RangeVar *table; /* the table name the policy applies to */ + List *roles; /* the roles associated with the policy */ + Node *qual; /* the policy's condition */ + Node *with_check; /* the policy's WITH CHECK condition. */ +} AlterPolicyStmt; + +/*---------------------- + * Create ACCESS METHOD Statement + *---------------------- + */ +typedef struct CreateAmStmt +{ + NodeTag type; + char *amname; /* access method name */ + List *handler_name; /* handler function name */ + char amtype; /* type of access method */ +} CreateAmStmt; + +/* ---------------------- + * Create TRIGGER Statement + * ---------------------- + */ +typedef struct CreateTrigStmt +{ + NodeTag type; + bool replace; /* replace trigger if already exists */ + bool isconstraint; /* This is a constraint trigger */ + char *trigname; /* TRIGGER's name */ + RangeVar *relation; /* relation trigger is on */ + List *funcname; /* qual. name of function to call */ + List *args; /* list of String or NIL */ + bool row; /* ROW/STATEMENT */ + /* timing uses the TRIGGER_TYPE bits defined in catalog/pg_trigger.h */ + int16 timing; /* BEFORE, AFTER, or INSTEAD */ + /* events uses the TRIGGER_TYPE bits defined in catalog/pg_trigger.h */ + int16 events; /* "OR" of INSERT/UPDATE/DELETE/TRUNCATE */ + List *columns; /* column names, or NIL for all columns */ + Node *whenClause; /* qual expression, or NULL if none */ + /* explicitly named transition data */ + List *transitionRels; /* TriggerTransition nodes, or NIL if none */ + /* The remaining fields are only used for constraint triggers */ + bool deferrable; /* [NOT] DEFERRABLE */ + bool initdeferred; /* INITIALLY {DEFERRED|IMMEDIATE} */ + RangeVar *constrrel; /* opposite relation, if RI trigger */ +} CreateTrigStmt; + +/* ---------------------- + * Create EVENT TRIGGER Statement + * ---------------------- + */ +typedef struct CreateEventTrigStmt +{ + NodeTag type; + char *trigname; /* TRIGGER's name */ + char *eventname; /* event's identifier */ + List *whenclause; /* list of DefElems indicating filtering */ + List *funcname; /* qual. name of function to call */ +} CreateEventTrigStmt; + +/* ---------------------- + * Alter EVENT TRIGGER Statement + * ---------------------- + */ +typedef struct AlterEventTrigStmt +{ + NodeTag type; + char *trigname; /* TRIGGER's name */ + char tgenabled; /* trigger's firing configuration WRT + * session_replication_role */ +} AlterEventTrigStmt; + +/* ---------------------- + * Create LANGUAGE Statements + * ---------------------- + */ +typedef struct CreatePLangStmt +{ + NodeTag type; + bool replace; /* T => replace if already exists */ + char *plname; /* PL name */ + List *plhandler; /* PL call handler function (qual. name) */ + List *plinline; /* optional inline function (qual. name) */ + List *plvalidator; /* optional validator function (qual. name) */ + bool pltrusted; /* PL is trusted */ +} CreatePLangStmt; + +/* ---------------------- + * Create/Alter/Drop Role Statements + * + * Note: these node types are also used for the backwards-compatible + * Create/Alter/Drop User/Group statements. In the ALTER and DROP cases + * there's really no need to distinguish what the original spelling was, + * but for CREATE we mark the type because the defaults vary. + * ---------------------- + */ +typedef enum RoleStmtType +{ + ROLESTMT_ROLE, + ROLESTMT_USER, + ROLESTMT_GROUP +} RoleStmtType; + +typedef struct CreateRoleStmt +{ + NodeTag type; + RoleStmtType stmt_type; /* ROLE/USER/GROUP */ + char *role; /* role name */ + List *options; /* List of DefElem nodes */ +} CreateRoleStmt; + +typedef struct AlterRoleStmt +{ + NodeTag type; + RoleSpec *role; /* role */ + List *options; /* List of DefElem nodes */ + int action; /* +1 = add members, -1 = drop members */ +} AlterRoleStmt; + +typedef struct AlterRoleSetStmt +{ + NodeTag type; + RoleSpec *role; /* role */ + char *database; /* database name, or NULL */ + VariableSetStmt *setstmt; /* SET or RESET subcommand */ +} AlterRoleSetStmt; + +typedef struct DropRoleStmt +{ + NodeTag type; + List *roles; /* List of roles to remove */ + bool missing_ok; /* skip error if a role is missing? */ +} DropRoleStmt; + +/* ---------------------- + * {Create|Alter} SEQUENCE Statement + * ---------------------- + */ + +typedef struct CreateSeqStmt +{ + NodeTag type; + RangeVar *sequence; /* the sequence to create */ + List *options; + Oid ownerId; /* ID of owner, or InvalidOid for default */ + bool for_identity; + bool if_not_exists; /* just do nothing if it already exists? */ +} CreateSeqStmt; + +typedef struct AlterSeqStmt +{ + NodeTag type; + RangeVar *sequence; /* the sequence to alter */ + List *options; + bool for_identity; + bool missing_ok; /* skip error if a role is missing? */ +} AlterSeqStmt; + +/* ---------------------- + * Create {Aggregate|Operator|Type} Statement + * ---------------------- + */ +typedef struct DefineStmt +{ + NodeTag type; + ObjectType kind; /* aggregate, operator, type */ + bool oldstyle; /* hack to signal old CREATE AGG syntax */ + List *defnames; /* qualified name (list of String) */ + List *args; /* a list of TypeName (if needed) */ + List *definition; /* a list of DefElem */ + bool if_not_exists; /* just do nothing if it already exists? */ + bool replace; /* replace if already exists? */ +} DefineStmt; + +/* ---------------------- + * Create Domain Statement + * ---------------------- + */ +typedef struct CreateDomainStmt +{ + NodeTag type; + List *domainname; /* qualified name (list of String) */ + TypeName *typeName; /* the base type */ + CollateClause *collClause; /* untransformed COLLATE spec, if any */ + List *constraints; /* constraints (list of Constraint nodes) */ +} CreateDomainStmt; + +/* ---------------------- + * Create Operator Class Statement + * ---------------------- + */ +typedef struct CreateOpClassStmt +{ + NodeTag type; + List *opclassname; /* qualified name (list of String) */ + List *opfamilyname; /* qualified name (ditto); NIL if omitted */ + char *amname; /* name of index AM opclass is for */ + TypeName *datatype; /* datatype of indexed column */ + List *items; /* List of CreateOpClassItem nodes */ + bool isDefault; /* Should be marked as default for type? */ +} CreateOpClassStmt; + +#define OPCLASS_ITEM_OPERATOR 1 +#define OPCLASS_ITEM_FUNCTION 2 +#define OPCLASS_ITEM_STORAGETYPE 3 + +typedef struct CreateOpClassItem +{ + NodeTag type; + int itemtype; /* see codes above */ + ObjectWithArgs *name; /* operator or function name and args */ + int number; /* strategy num or support proc num */ + List *order_family; /* only used for ordering operators */ + List *class_args; /* amproclefttype/amprocrighttype or + * amoplefttype/amoprighttype */ + /* fields used for a storagetype item: */ + TypeName *storedtype; /* datatype stored in index */ +} CreateOpClassItem; + +/* ---------------------- + * Create Operator Family Statement + * ---------------------- + */ +typedef struct CreateOpFamilyStmt +{ + NodeTag type; + List *opfamilyname; /* qualified name (list of String) */ + char *amname; /* name of index AM opfamily is for */ +} CreateOpFamilyStmt; + +/* ---------------------- + * Alter Operator Family Statement + * ---------------------- + */ +typedef struct AlterOpFamilyStmt +{ + NodeTag type; + List *opfamilyname; /* qualified name (list of String) */ + char *amname; /* name of index AM opfamily is for */ + bool isDrop; /* ADD or DROP the items? */ + List *items; /* List of CreateOpClassItem nodes */ +} AlterOpFamilyStmt; + +/* ---------------------- + * Drop Table|Sequence|View|Index|Type|Domain|Conversion|Schema Statement + * ---------------------- + */ + +typedef struct DropStmt +{ + NodeTag type; + List *objects; /* list of names */ + ObjectType removeType; /* object type */ + DropBehavior behavior; /* RESTRICT or CASCADE behavior */ + bool missing_ok; /* skip error if object is missing? */ + bool concurrent; /* drop index concurrently? */ +} DropStmt; + +/* ---------------------- + * Truncate Table Statement + * ---------------------- + */ +typedef struct TruncateStmt +{ + NodeTag type; + List *relations; /* relations (RangeVars) to be truncated */ + bool restart_seqs; /* restart owned sequences? */ + DropBehavior behavior; /* RESTRICT or CASCADE behavior */ +} TruncateStmt; + +/* ---------------------- + * Comment On Statement + * ---------------------- + */ +typedef struct CommentStmt +{ + NodeTag type; + ObjectType objtype; /* Object's type */ + Node *object; /* Qualified name of the object */ + char *comment; /* Comment to insert, or NULL to remove */ +} CommentStmt; + +/* ---------------------- + * SECURITY LABEL Statement + * ---------------------- + */ +typedef struct SecLabelStmt +{ + NodeTag type; + ObjectType objtype; /* Object's type */ + Node *object; /* Qualified name of the object */ + char *provider; /* Label provider (or NULL) */ + char *label; /* New security label to be assigned */ +} SecLabelStmt; + +/* ---------------------- + * Declare Cursor Statement + * + * The "query" field is initially a raw parse tree, and is converted to a + * Query node during parse analysis. Note that rewriting and planning + * of the query are always postponed until execution. + * ---------------------- + */ +#define CURSOR_OPT_BINARY 0x0001 /* BINARY */ +#define CURSOR_OPT_SCROLL 0x0002 /* SCROLL explicitly given */ +#define CURSOR_OPT_NO_SCROLL 0x0004 /* NO SCROLL explicitly given */ +#define CURSOR_OPT_INSENSITIVE 0x0008 /* INSENSITIVE */ +#define CURSOR_OPT_ASENSITIVE 0x0010 /* ASENSITIVE */ +#define CURSOR_OPT_HOLD 0x0020 /* WITH HOLD */ +/* these planner-control flags do not correspond to any SQL grammar: */ +#define CURSOR_OPT_FAST_PLAN 0x0100 /* prefer fast-start plan */ +#define CURSOR_OPT_GENERIC_PLAN 0x0200 /* force use of generic plan */ +#define CURSOR_OPT_CUSTOM_PLAN 0x0400 /* force use of custom plan */ +#define CURSOR_OPT_PARALLEL_OK 0x0800 /* parallel mode OK */ + +typedef struct DeclareCursorStmt +{ + NodeTag type; + char *portalname; /* name of the portal (cursor) */ + int options; /* bitmask of options (see above) */ + Node *query; /* the query (see comments above) */ +} DeclareCursorStmt; + +/* ---------------------- + * Close Portal Statement + * ---------------------- + */ +typedef struct ClosePortalStmt +{ + NodeTag type; + char *portalname; /* name of the portal (cursor) */ + /* NULL means CLOSE ALL */ +} ClosePortalStmt; + +/* ---------------------- + * Fetch Statement (also Move) + * ---------------------- + */ +typedef enum FetchDirection +{ + /* for these, howMany is how many rows to fetch; FETCH_ALL means ALL */ + FETCH_FORWARD, + FETCH_BACKWARD, + /* for these, howMany indicates a position; only one row is fetched */ + FETCH_ABSOLUTE, + FETCH_RELATIVE +} FetchDirection; + +#define FETCH_ALL LONG_MAX + +typedef struct FetchStmt +{ + NodeTag type; + FetchDirection direction; /* see above */ + long howMany; /* number of rows, or position argument */ + char *portalname; /* name of portal (cursor) */ + bool ismove; /* true if MOVE */ +} FetchStmt; + +/* ---------------------- + * Create Index Statement + * + * This represents creation of an index and/or an associated constraint. + * If isconstraint is true, we should create a pg_constraint entry along + * with the index. But if indexOid isn't InvalidOid, we are not creating an + * index, just a UNIQUE/PKEY constraint using an existing index. isconstraint + * must always be true in this case, and the fields describing the index + * properties are empty. + * ---------------------- + */ +typedef struct IndexStmt +{ + NodeTag type; + char *idxname; /* name of new index, or NULL for default */ + RangeVar *relation; /* relation to build index on */ + char *accessMethod; /* name of access method (eg. btree) */ + char *tableSpace; /* tablespace, or NULL for default */ + List *indexParams; /* columns to index: a list of IndexElem */ + List *indexIncludingParams; /* additional columns to index: a list + * of IndexElem */ + List *options; /* WITH clause options: a list of DefElem */ + Node *whereClause; /* qualification (partial-index predicate) */ + List *excludeOpNames; /* exclusion operator names, or NIL if none */ + char *idxcomment; /* comment to apply to index, or NULL */ + Oid indexOid; /* OID of an existing index, if any */ + RelFileNumber oldNumber; /* relfilenumber of existing storage, if any */ + SubTransactionId oldCreateSubid; /* rd_createSubid of oldNumber */ + SubTransactionId oldFirstRelfilelocatorSubid; /* rd_firstRelfilelocatorSubid + * of oldNumber */ + bool unique; /* is index unique? */ + bool nulls_not_distinct; /* null treatment for UNIQUE constraints */ + bool primary; /* is index a primary key? */ + bool isconstraint; /* is it for a pkey/unique constraint? */ + bool deferrable; /* is the constraint DEFERRABLE? */ + bool initdeferred; /* is the constraint INITIALLY DEFERRED? */ + bool transformed; /* true when transformIndexStmt is finished */ + bool concurrent; /* should this be a concurrent index build? */ + bool if_not_exists; /* just do nothing if index already exists? */ + bool reset_default_tblspc; /* reset default_tablespace prior to + * executing */ +} IndexStmt; + +/* ---------------------- + * Create Statistics Statement + * ---------------------- + */ +typedef struct CreateStatsStmt +{ + NodeTag type; + List *defnames; /* qualified name (list of String) */ + List *stat_types; /* stat types (list of String) */ + List *exprs; /* expressions to build statistics on */ + List *relations; /* rels to build stats on (list of RangeVar) */ + char *stxcomment; /* comment to apply to stats, or NULL */ + bool transformed; /* true when transformStatsStmt is finished */ + bool if_not_exists; /* do nothing if stats name already exists */ +} CreateStatsStmt; + +/* + * StatsElem - statistics parameters (used in CREATE STATISTICS) + * + * For a plain attribute, 'name' is the name of the referenced table column + * and 'expr' is NULL. For an expression, 'name' is NULL and 'expr' is the + * expression tree. + */ +typedef struct StatsElem +{ + NodeTag type; + char *name; /* name of attribute to index, or NULL */ + Node *expr; /* expression to index, or NULL */ +} StatsElem; + + +/* ---------------------- + * Alter Statistics Statement + * ---------------------- + */ +typedef struct AlterStatsStmt +{ + NodeTag type; + List *defnames; /* qualified name (list of String) */ + int stxstattarget; /* statistics target */ + bool missing_ok; /* skip error if statistics object is missing */ +} AlterStatsStmt; + +/* ---------------------- + * Create Function Statement + * ---------------------- + */ +typedef struct CreateFunctionStmt +{ + NodeTag type; + bool is_procedure; /* it's really CREATE PROCEDURE */ + bool replace; /* T => replace if already exists */ + List *funcname; /* qualified name of function to create */ + List *parameters; /* a list of FunctionParameter */ + TypeName *returnType; /* the return type */ + List *options; /* a list of DefElem */ + Node *sql_body; +} CreateFunctionStmt; + +typedef enum FunctionParameterMode +{ + /* the assigned enum values appear in pg_proc, don't change 'em! */ + FUNC_PARAM_IN = 'i', /* input only */ + FUNC_PARAM_OUT = 'o', /* output only */ + FUNC_PARAM_INOUT = 'b', /* both */ + FUNC_PARAM_VARIADIC = 'v', /* variadic (always input) */ + FUNC_PARAM_TABLE = 't', /* table function output column */ + /* this is not used in pg_proc: */ + FUNC_PARAM_DEFAULT = 'd' /* default; effectively same as IN */ +} FunctionParameterMode; + +typedef struct FunctionParameter +{ + NodeTag type; + char *name; /* parameter name, or NULL if not given */ + TypeName *argType; /* TypeName for parameter type */ + FunctionParameterMode mode; /* IN/OUT/etc */ + Node *defexpr; /* raw default expr, or NULL if not given */ +} FunctionParameter; + +typedef struct AlterFunctionStmt +{ + NodeTag type; + ObjectType objtype; + ObjectWithArgs *func; /* name and args of function */ + List *actions; /* list of DefElem */ +} AlterFunctionStmt; + +/* ---------------------- + * DO Statement + * + * DoStmt is the raw parser output, InlineCodeBlock is the execution-time API + * ---------------------- + */ +typedef struct DoStmt +{ + NodeTag type; + List *args; /* List of DefElem nodes */ +} DoStmt; + +typedef struct InlineCodeBlock +{ + pg_node_attr(nodetag_only) /* this is not a member of parse trees */ + + NodeTag type; + char *source_text; /* source text of anonymous code block */ + Oid langOid; /* OID of selected language */ + bool langIsTrusted; /* trusted property of the language */ + bool atomic; /* atomic execution context */ +} InlineCodeBlock; + +/* ---------------------- + * CALL statement + * + * OUT-mode arguments are removed from the transformed funcexpr. The outargs + * list contains copies of the expressions for all output arguments, in the + * order of the procedure's declared arguments. (outargs is never evaluated, + * but is useful to the caller as a reference for what to assign to.) + * The transformed call state is not relevant in the query jumbling, only the + * function call is. + * ---------------------- + */ +typedef struct CallStmt +{ + NodeTag type; + FuncCall *funccall; /* from the parser */ + /* transformed call, with only input args */ + FuncExpr *funcexpr pg_node_attr(query_jumble_ignore); + /* transformed output-argument expressions */ + List *outargs pg_node_attr(query_jumble_ignore); +} CallStmt; + +typedef struct CallContext +{ + pg_node_attr(nodetag_only) /* this is not a member of parse trees */ + + NodeTag type; + bool atomic; +} CallContext; + +/* ---------------------- + * Alter Object Rename Statement + * ---------------------- + */ +typedef struct RenameStmt +{ + NodeTag type; + ObjectType renameType; /* OBJECT_TABLE, OBJECT_COLUMN, etc */ + ObjectType relationType; /* if column name, associated relation type */ + RangeVar *relation; /* in case it's a table */ + Node *object; /* in case it's some other object */ + char *subname; /* name of contained object (column, rule, + * trigger, etc) */ + char *newname; /* the new name */ + DropBehavior behavior; /* RESTRICT or CASCADE behavior */ + bool missing_ok; /* skip error if missing? */ +} RenameStmt; + +/* ---------------------- + * ALTER object DEPENDS ON EXTENSION extname + * ---------------------- + */ +typedef struct AlterObjectDependsStmt +{ + NodeTag type; + ObjectType objectType; /* OBJECT_FUNCTION, OBJECT_TRIGGER, etc */ + RangeVar *relation; /* in case a table is involved */ + Node *object; /* name of the object */ + String *extname; /* extension name */ + bool remove; /* set true to remove dep rather than add */ +} AlterObjectDependsStmt; + +/* ---------------------- + * ALTER object SET SCHEMA Statement + * ---------------------- + */ +typedef struct AlterObjectSchemaStmt +{ + NodeTag type; + ObjectType objectType; /* OBJECT_TABLE, OBJECT_TYPE, etc */ + RangeVar *relation; /* in case it's a table */ + Node *object; /* in case it's some other object */ + char *newschema; /* the new schema */ + bool missing_ok; /* skip error if missing? */ +} AlterObjectSchemaStmt; + +/* ---------------------- + * Alter Object Owner Statement + * ---------------------- + */ +typedef struct AlterOwnerStmt +{ + NodeTag type; + ObjectType objectType; /* OBJECT_TABLE, OBJECT_TYPE, etc */ + RangeVar *relation; /* in case it's a table */ + Node *object; /* in case it's some other object */ + RoleSpec *newowner; /* the new owner */ +} AlterOwnerStmt; + +/* ---------------------- + * Alter Operator Set ( this-n-that ) + * ---------------------- + */ +typedef struct AlterOperatorStmt +{ + NodeTag type; + ObjectWithArgs *opername; /* operator name and argument types */ + List *options; /* List of DefElem nodes */ +} AlterOperatorStmt; + +/* ------------------------ + * Alter Type Set ( this-n-that ) + * ------------------------ + */ +typedef struct AlterTypeStmt +{ + NodeTag type; + List *typeName; /* type name (possibly qualified) */ + List *options; /* List of DefElem nodes */ +} AlterTypeStmt; + +/* ---------------------- + * Create Rule Statement + * ---------------------- + */ +typedef struct RuleStmt +{ + NodeTag type; + RangeVar *relation; /* relation the rule is for */ + char *rulename; /* name of the rule */ + Node *whereClause; /* qualifications */ + CmdType event; /* SELECT, INSERT, etc */ + bool instead; /* is a 'do instead'? */ + List *actions; /* the action statements */ + bool replace; /* OR REPLACE */ +} RuleStmt; + +/* ---------------------- + * Notify Statement + * ---------------------- + */ +typedef struct NotifyStmt +{ + NodeTag type; + char *conditionname; /* condition name to notify */ + char *payload; /* the payload string, or NULL if none */ +} NotifyStmt; + +/* ---------------------- + * Listen Statement + * ---------------------- + */ +typedef struct ListenStmt +{ + NodeTag type; + char *conditionname; /* condition name to listen on */ +} ListenStmt; + +/* ---------------------- + * Unlisten Statement + * ---------------------- + */ +typedef struct UnlistenStmt +{ + NodeTag type; + char *conditionname; /* name to unlisten on, or NULL for all */ +} UnlistenStmt; + +/* ---------------------- + * {Begin|Commit|Rollback} Transaction Statement + * ---------------------- + */ +typedef enum TransactionStmtKind +{ + TRANS_STMT_BEGIN, + TRANS_STMT_START, /* semantically identical to BEGIN */ + TRANS_STMT_COMMIT, + TRANS_STMT_ROLLBACK, + TRANS_STMT_SAVEPOINT, + TRANS_STMT_RELEASE, + TRANS_STMT_ROLLBACK_TO, + TRANS_STMT_PREPARE, + TRANS_STMT_COMMIT_PREPARED, + TRANS_STMT_ROLLBACK_PREPARED +} TransactionStmtKind; + +typedef struct TransactionStmt +{ + NodeTag type; + TransactionStmtKind kind; /* see above */ + List *options; /* for BEGIN/START commands */ + char *savepoint_name; /* for savepoint commands */ + char *gid; /* for two-phase-commit related commands */ + bool chain; /* AND CHAIN option */ +} TransactionStmt; + +/* ---------------------- + * Create Type Statement, composite types + * ---------------------- + */ +typedef struct CompositeTypeStmt +{ + NodeTag type; + RangeVar *typevar; /* the composite type to be created */ + List *coldeflist; /* list of ColumnDef nodes */ +} CompositeTypeStmt; + +/* ---------------------- + * Create Type Statement, enum types + * ---------------------- + */ +typedef struct CreateEnumStmt +{ + NodeTag type; + List *typeName; /* qualified name (list of String) */ + List *vals; /* enum values (list of String) */ +} CreateEnumStmt; + +/* ---------------------- + * Create Type Statement, range types + * ---------------------- + */ +typedef struct CreateRangeStmt +{ + NodeTag type; + List *typeName; /* qualified name (list of String) */ + List *params; /* range parameters (list of DefElem) */ +} CreateRangeStmt; + +/* ---------------------- + * Alter Type Statement, enum types + * ---------------------- + */ +typedef struct AlterEnumStmt +{ + NodeTag type; + List *typeName; /* qualified name (list of String) */ + char *oldVal; /* old enum value's name, if renaming */ + char *newVal; /* new enum value's name */ + char *newValNeighbor; /* neighboring enum value, if specified */ + bool newValIsAfter; /* place new enum value after neighbor? */ + bool skipIfNewValExists; /* no error if new already exists? */ +} AlterEnumStmt; + +/* ---------------------- + * Create View Statement + * ---------------------- + */ +typedef enum ViewCheckOption +{ + NO_CHECK_OPTION, + LOCAL_CHECK_OPTION, + CASCADED_CHECK_OPTION +} ViewCheckOption; + +typedef struct ViewStmt +{ + NodeTag type; + RangeVar *view; /* the view to be created */ + List *aliases; /* target column names */ + Node *query; /* the SELECT query (as a raw parse tree) */ + bool replace; /* replace an existing view? */ + List *options; /* options from WITH clause */ + ViewCheckOption withCheckOption; /* WITH CHECK OPTION */ +} ViewStmt; + +/* ---------------------- + * Load Statement + * ---------------------- + */ +typedef struct LoadStmt +{ + NodeTag type; + char *filename; /* file to load */ +} LoadStmt; + +/* ---------------------- + * Createdb Statement + * ---------------------- + */ +typedef struct CreatedbStmt +{ + NodeTag type; + char *dbname; /* name of database to create */ + List *options; /* List of DefElem nodes */ +} CreatedbStmt; + +/* ---------------------- + * Alter Database + * ---------------------- + */ +typedef struct AlterDatabaseStmt +{ + NodeTag type; + char *dbname; /* name of database to alter */ + List *options; /* List of DefElem nodes */ +} AlterDatabaseStmt; + +typedef struct AlterDatabaseRefreshCollStmt +{ + NodeTag type; + char *dbname; +} AlterDatabaseRefreshCollStmt; + +typedef struct AlterDatabaseSetStmt +{ + NodeTag type; + char *dbname; /* database name */ + VariableSetStmt *setstmt; /* SET or RESET subcommand */ +} AlterDatabaseSetStmt; + +/* ---------------------- + * Dropdb Statement + * ---------------------- + */ +typedef struct DropdbStmt +{ + NodeTag type; + char *dbname; /* database to drop */ + bool missing_ok; /* skip error if db is missing? */ + List *options; /* currently only FORCE is supported */ +} DropdbStmt; + +/* ---------------------- + * Alter System Statement + * ---------------------- + */ +typedef struct AlterSystemStmt +{ + NodeTag type; + VariableSetStmt *setstmt; /* SET subcommand */ +} AlterSystemStmt; + +/* ---------------------- + * Cluster Statement (support pbrown's cluster index implementation) + * ---------------------- + */ +typedef struct ClusterStmt +{ + NodeTag type; + RangeVar *relation; /* relation being indexed, or NULL if all */ + char *indexname; /* original index defined */ + List *params; /* list of DefElem nodes */ +} ClusterStmt; + +/* ---------------------- + * Vacuum and Analyze Statements + * + * Even though these are nominally two statements, it's convenient to use + * just one node type for both. + * ---------------------- + */ +typedef struct VacuumStmt +{ + NodeTag type; + List *options; /* list of DefElem nodes */ + List *rels; /* list of VacuumRelation, or NIL for all */ + bool is_vacuumcmd; /* true for VACUUM, false for ANALYZE */ +} VacuumStmt; + +/* + * Info about a single target table of VACUUM/ANALYZE. + * + * If the OID field is set, it always identifies the table to process. + * Then the relation field can be NULL; if it isn't, it's used only to report + * failure to open/lock the relation. + */ +typedef struct VacuumRelation +{ + NodeTag type; + RangeVar *relation; /* table name to process, or NULL */ + Oid oid; /* table's OID; InvalidOid if not looked up */ + List *va_cols; /* list of column names, or NIL for all */ +} VacuumRelation; + +/* ---------------------- + * Explain Statement + * + * The "query" field is initially a raw parse tree, and is converted to a + * Query node during parse analysis. Note that rewriting and planning + * of the query are always postponed until execution. + * ---------------------- + */ +typedef struct ExplainStmt +{ + NodeTag type; + Node *query; /* the query (see comments above) */ + List *options; /* list of DefElem nodes */ +} ExplainStmt; + +/* ---------------------- + * CREATE TABLE AS Statement (a/k/a SELECT INTO) + * + * A query written as CREATE TABLE AS will produce this node type natively. + * A query written as SELECT ... INTO will be transformed to this form during + * parse analysis. + * A query written as CREATE MATERIALIZED view will produce this node type, + * during parse analysis, since it needs all the same data. + * + * The "query" field is handled similarly to EXPLAIN, though note that it + * can be a SELECT or an EXECUTE, but not other DML statements. + * ---------------------- + */ +typedef struct CreateTableAsStmt +{ + NodeTag type; + Node *query; /* the query (see comments above) */ + IntoClause *into; /* destination table */ + ObjectType objtype; /* OBJECT_TABLE or OBJECT_MATVIEW */ + bool is_select_into; /* it was written as SELECT INTO */ + bool if_not_exists; /* just do nothing if it already exists? */ +} CreateTableAsStmt; + +/* ---------------------- + * REFRESH MATERIALIZED VIEW Statement + * ---------------------- + */ +typedef struct RefreshMatViewStmt +{ + NodeTag type; + bool concurrent; /* allow concurrent access? */ + bool skipData; /* true for WITH NO DATA */ + RangeVar *relation; /* relation to insert into */ +} RefreshMatViewStmt; + +/* ---------------------- + * Checkpoint Statement + * ---------------------- + */ +typedef struct CheckPointStmt +{ + NodeTag type; +} CheckPointStmt; + +/* ---------------------- + * Discard Statement + * ---------------------- + */ + +typedef enum DiscardMode +{ + DISCARD_ALL, + DISCARD_PLANS, + DISCARD_SEQUENCES, + DISCARD_TEMP +} DiscardMode; + +typedef struct DiscardStmt +{ + NodeTag type; + DiscardMode target; +} DiscardStmt; + +/* ---------------------- + * LOCK Statement + * ---------------------- + */ +typedef struct LockStmt +{ + NodeTag type; + List *relations; /* relations to lock */ + int mode; /* lock mode */ + bool nowait; /* no wait mode */ +} LockStmt; + +/* ---------------------- + * SET CONSTRAINTS Statement + * ---------------------- + */ +typedef struct ConstraintsSetStmt +{ + NodeTag type; + List *constraints; /* List of names as RangeVars */ + bool deferred; +} ConstraintsSetStmt; + +/* ---------------------- + * REINDEX Statement + * ---------------------- + */ +typedef enum ReindexObjectType +{ + REINDEX_OBJECT_INDEX, /* index */ + REINDEX_OBJECT_TABLE, /* table or materialized view */ + REINDEX_OBJECT_SCHEMA, /* schema */ + REINDEX_OBJECT_SYSTEM, /* system catalogs */ + REINDEX_OBJECT_DATABASE /* database */ +} ReindexObjectType; + +typedef struct ReindexStmt +{ + NodeTag type; + ReindexObjectType kind; /* REINDEX_OBJECT_INDEX, REINDEX_OBJECT_TABLE, + * etc. */ + RangeVar *relation; /* Table or index to reindex */ + const char *name; /* name of database to reindex */ + List *params; /* list of DefElem nodes */ +} ReindexStmt; + +/* ---------------------- + * CREATE CONVERSION Statement + * ---------------------- + */ +typedef struct CreateConversionStmt +{ + NodeTag type; + List *conversion_name; /* Name of the conversion */ + char *for_encoding_name; /* source encoding name */ + char *to_encoding_name; /* destination encoding name */ + List *func_name; /* qualified conversion function name */ + bool def; /* is this a default conversion? */ +} CreateConversionStmt; + +/* ---------------------- + * CREATE CAST Statement + * ---------------------- + */ +typedef struct CreateCastStmt +{ + NodeTag type; + TypeName *sourcetype; + TypeName *targettype; + ObjectWithArgs *func; + CoercionContext context; + bool inout; +} CreateCastStmt; + +/* ---------------------- + * CREATE TRANSFORM Statement + * ---------------------- + */ +typedef struct CreateTransformStmt +{ + NodeTag type; + bool replace; + TypeName *type_name; + char *lang; + ObjectWithArgs *fromsql; + ObjectWithArgs *tosql; +} CreateTransformStmt; + +/* ---------------------- + * PREPARE Statement + * ---------------------- + */ +typedef struct PrepareStmt +{ + NodeTag type; + char *name; /* Name of plan, arbitrary */ + List *argtypes; /* Types of parameters (List of TypeName) */ + Node *query; /* The query itself (as a raw parsetree) */ +} PrepareStmt; + + +/* ---------------------- + * EXECUTE Statement + * ---------------------- + */ + +typedef struct ExecuteStmt +{ + NodeTag type; + char *name; /* The name of the plan to execute */ + List *params; /* Values to assign to parameters */ +} ExecuteStmt; + + +/* ---------------------- + * DEALLOCATE Statement + * ---------------------- + */ +typedef struct DeallocateStmt +{ + NodeTag type; + char *name; /* The name of the plan to remove */ + /* NULL means DEALLOCATE ALL */ +} DeallocateStmt; + +/* + * DROP OWNED statement + */ +typedef struct DropOwnedStmt +{ + NodeTag type; + List *roles; + DropBehavior behavior; +} DropOwnedStmt; + +/* + * REASSIGN OWNED statement + */ +typedef struct ReassignOwnedStmt +{ + NodeTag type; + List *roles; + RoleSpec *newrole; +} ReassignOwnedStmt; + +/* + * TS Dictionary stmts: DefineStmt, RenameStmt and DropStmt are default + */ +typedef struct AlterTSDictionaryStmt +{ + NodeTag type; + List *dictname; /* qualified name (list of String) */ + List *options; /* List of DefElem nodes */ +} AlterTSDictionaryStmt; + +/* + * TS Configuration stmts: DefineStmt, RenameStmt and DropStmt are default + */ +typedef enum AlterTSConfigType +{ + ALTER_TSCONFIG_ADD_MAPPING, + ALTER_TSCONFIG_ALTER_MAPPING_FOR_TOKEN, + ALTER_TSCONFIG_REPLACE_DICT, + ALTER_TSCONFIG_REPLACE_DICT_FOR_TOKEN, + ALTER_TSCONFIG_DROP_MAPPING +} AlterTSConfigType; + +typedef struct AlterTSConfigurationStmt +{ + NodeTag type; + AlterTSConfigType kind; /* ALTER_TSCONFIG_ADD_MAPPING, etc */ + List *cfgname; /* qualified name (list of String) */ + + /* + * dicts will be non-NIL if ADD/ALTER MAPPING was specified. If dicts is + * NIL, but tokentype isn't, DROP MAPPING was specified. + */ + List *tokentype; /* list of String */ + List *dicts; /* list of list of String */ + bool override; /* if true - remove old variant */ + bool replace; /* if true - replace dictionary by another */ + bool missing_ok; /* for DROP - skip error if missing? */ +} AlterTSConfigurationStmt; + +typedef struct PublicationTable +{ + NodeTag type; + RangeVar *relation; /* relation to be published */ + Node *whereClause; /* qualifications */ + List *columns; /* List of columns in a publication table */ +} PublicationTable; + +/* + * Publication object type + */ +typedef enum PublicationObjSpecType +{ + PUBLICATIONOBJ_TABLE, /* A table */ + PUBLICATIONOBJ_TABLES_IN_SCHEMA, /* All tables in schema */ + PUBLICATIONOBJ_TABLES_IN_CUR_SCHEMA, /* All tables in first element of + * search_path */ + PUBLICATIONOBJ_CONTINUATION /* Continuation of previous type */ +} PublicationObjSpecType; + +typedef struct PublicationObjSpec +{ + NodeTag type; + PublicationObjSpecType pubobjtype; /* type of this publication object */ + char *name; + PublicationTable *pubtable; + int location; /* token location, or -1 if unknown */ +} PublicationObjSpec; + +typedef struct CreatePublicationStmt +{ + NodeTag type; + char *pubname; /* Name of the publication */ + List *options; /* List of DefElem nodes */ + List *pubobjects; /* Optional list of publication objects */ + bool for_all_tables; /* Special publication for all tables in db */ +} CreatePublicationStmt; + +typedef enum AlterPublicationAction +{ + AP_AddObjects, /* add objects to publication */ + AP_DropObjects, /* remove objects from publication */ + AP_SetObjects /* set list of objects */ +} AlterPublicationAction; + +typedef struct AlterPublicationStmt +{ + NodeTag type; + char *pubname; /* Name of the publication */ + + /* parameters used for ALTER PUBLICATION ... WITH */ + List *options; /* List of DefElem nodes */ + + /* + * Parameters used for ALTER PUBLICATION ... ADD/DROP/SET publication + * objects. + */ + List *pubobjects; /* Optional list of publication objects */ + bool for_all_tables; /* Special publication for all tables in db */ + AlterPublicationAction action; /* What action to perform with the given + * objects */ +} AlterPublicationStmt; + +typedef struct CreateSubscriptionStmt +{ + NodeTag type; + char *subname; /* Name of the subscription */ + char *conninfo; /* Connection string to publisher */ + List *publication; /* One or more publication to subscribe to */ + List *options; /* List of DefElem nodes */ +} CreateSubscriptionStmt; + +typedef enum AlterSubscriptionType +{ + ALTER_SUBSCRIPTION_OPTIONS, + ALTER_SUBSCRIPTION_CONNECTION, + ALTER_SUBSCRIPTION_SET_PUBLICATION, + ALTER_SUBSCRIPTION_ADD_PUBLICATION, + ALTER_SUBSCRIPTION_DROP_PUBLICATION, + ALTER_SUBSCRIPTION_REFRESH, + ALTER_SUBSCRIPTION_ENABLED, + ALTER_SUBSCRIPTION_SKIP +} AlterSubscriptionType; + +typedef struct AlterSubscriptionStmt +{ + NodeTag type; + AlterSubscriptionType kind; /* ALTER_SUBSCRIPTION_OPTIONS, etc */ + char *subname; /* Name of the subscription */ + char *conninfo; /* Connection string to publisher */ + List *publication; /* One or more publication to subscribe to */ + List *options; /* List of DefElem nodes */ +} AlterSubscriptionStmt; + +typedef struct DropSubscriptionStmt +{ + NodeTag type; + char *subname; /* Name of the subscription */ + bool missing_ok; /* Skip error if missing? */ + DropBehavior behavior; /* RESTRICT or CASCADE behavior */ +} DropSubscriptionStmt; + +#endif /* PARSENODES_H */ diff --git a/src/include/nodes/pathnodes.h b/src/include/nodes/pathnodes.h new file mode 100644 index 0000000..94aebad --- /dev/null +++ b/src/include/nodes/pathnodes.h @@ -0,0 +1,3384 @@ +/*------------------------------------------------------------------------- + * + * pathnodes.h + * Definitions for planner's internal data structures, especially Paths. + * + * We don't support copying RelOptInfo, IndexOptInfo, or Path nodes. + * There are some subsidiary structs that are useful to copy, though. + * + * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/nodes/pathnodes.h + * + *------------------------------------------------------------------------- + */ +#ifndef PATHNODES_H +#define PATHNODES_H + +#include "access/sdir.h" +#include "lib/stringinfo.h" +#include "nodes/params.h" +#include "nodes/parsenodes.h" +#include "storage/block.h" + + +/* + * Relids + * Set of relation identifiers (indexes into the rangetable). + */ +typedef Bitmapset *Relids; + +/* + * When looking for a "cheapest path", this enum specifies whether we want + * cheapest startup cost or cheapest total cost. + */ +typedef enum CostSelector +{ + STARTUP_COST, TOTAL_COST +} CostSelector; + +/* + * The cost estimate produced by cost_qual_eval() includes both a one-time + * (startup) cost, and a per-tuple cost. + */ +typedef struct QualCost +{ + Cost startup; /* one-time cost */ + Cost per_tuple; /* per-evaluation cost */ +} QualCost; + +/* + * Costing aggregate function execution requires these statistics about + * the aggregates to be executed by a given Agg node. Note that the costs + * include the execution costs of the aggregates' argument expressions as + * well as the aggregate functions themselves. Also, the fields must be + * defined so that initializing the struct to zeroes with memset is correct. + */ +typedef struct AggClauseCosts +{ + QualCost transCost; /* total per-input-row execution costs */ + QualCost finalCost; /* total per-aggregated-row costs */ + Size transitionSpace; /* space for pass-by-ref transition data */ +} AggClauseCosts; + +/* + * This enum identifies the different types of "upper" (post-scan/join) + * relations that we might deal with during planning. + */ +typedef enum UpperRelationKind +{ + UPPERREL_SETOP, /* result of UNION/INTERSECT/EXCEPT, if any */ + UPPERREL_PARTIAL_GROUP_AGG, /* result of partial grouping/aggregation, if + * any */ + UPPERREL_GROUP_AGG, /* result of grouping/aggregation, if any */ + UPPERREL_WINDOW, /* result of window functions, if any */ + UPPERREL_PARTIAL_DISTINCT, /* result of partial "SELECT DISTINCT", if any */ + UPPERREL_DISTINCT, /* result of "SELECT DISTINCT", if any */ + UPPERREL_ORDERED, /* result of ORDER BY, if any */ + UPPERREL_FINAL /* result of any remaining top-level actions */ + /* NB: UPPERREL_FINAL must be last enum entry; it's used to size arrays */ +} UpperRelationKind; + +/*---------- + * PlannerGlobal + * Global information for planning/optimization + * + * PlannerGlobal holds state for an entire planner invocation; this state + * is shared across all levels of sub-Queries that exist in the command being + * planned. + * + * Not all fields are printed. (In some cases, there is no print support for + * the field type; in others, doing so would lead to infinite recursion.) + *---------- + */ +typedef struct PlannerGlobal +{ + pg_node_attr(no_copy_equal, no_read, no_query_jumble) + + NodeTag type; + + /* Param values provided to planner() */ + ParamListInfo boundParams pg_node_attr(read_write_ignore); + + /* Plans for SubPlan nodes */ + List *subplans; + + /* PlannerInfos for SubPlan nodes */ + List *subroots pg_node_attr(read_write_ignore); + + /* indices of subplans that require REWIND */ + Bitmapset *rewindPlanIDs; + + /* "flat" rangetable for executor */ + List *finalrtable; + + /* "flat" list of RTEPermissionInfos */ + List *finalrteperminfos; + + /* "flat" list of PlanRowMarks */ + List *finalrowmarks; + + /* "flat" list of integer RT indexes */ + List *resultRelations; + + /* "flat" list of AppendRelInfos */ + List *appendRelations; + + /* OIDs of relations the plan depends on */ + List *relationOids; + + /* other dependencies, as PlanInvalItems */ + List *invalItems; + + /* type OIDs for PARAM_EXEC Params */ + List *paramExecTypes; + + /* highest PlaceHolderVar ID assigned */ + Index lastPHId; + + /* highest PlanRowMark ID assigned */ + Index lastRowMarkId; + + /* highest plan node ID assigned */ + int lastPlanNodeId; + + /* redo plan when TransactionXmin changes? */ + bool transientPlan; + + /* is plan specific to current role? */ + bool dependsOnRole; + + /* parallel mode potentially OK? */ + bool parallelModeOK; + + /* parallel mode actually required? */ + bool parallelModeNeeded; + + /* worst PROPARALLEL hazard level */ + char maxParallelHazard; + + /* partition descriptors */ + PartitionDirectory partition_directory pg_node_attr(read_write_ignore); +} PlannerGlobal; + +/* macro for fetching the Plan associated with a SubPlan node */ +#define planner_subplan_get_plan(root, subplan) \ + ((Plan *) list_nth((root)->glob->subplans, (subplan)->plan_id - 1)) + + +/*---------- + * PlannerInfo + * Per-query information for planning/optimization + * + * This struct is conventionally called "root" in all the planner routines. + * It holds links to all of the planner's working state, in addition to the + * original Query. Note that at present the planner extensively modifies + * the passed-in Query data structure; someday that should stop. + * + * For reasons explained in optimizer/optimizer.h, we define the typedef + * either here or in that header, whichever is read first. + * + * Not all fields are printed. (In some cases, there is no print support for + * the field type; in others, doing so would lead to infinite recursion or + * bloat dump output more than seems useful.) + *---------- + */ +#ifndef HAVE_PLANNERINFO_TYPEDEF +typedef struct PlannerInfo PlannerInfo; +#define HAVE_PLANNERINFO_TYPEDEF 1 +#endif + +struct PlannerInfo +{ + pg_node_attr(no_copy_equal, no_read, no_query_jumble) + + NodeTag type; + + /* the Query being planned */ + Query *parse; + + /* global info for current planner run */ + PlannerGlobal *glob; + + /* 1 at the outermost Query */ + Index query_level; + + /* NULL at outermost Query */ + PlannerInfo *parent_root pg_node_attr(read_write_ignore); + + /* + * plan_params contains the expressions that this query level needs to + * make available to a lower query level that is currently being planned. + * outer_params contains the paramIds of PARAM_EXEC Params that outer + * query levels will make available to this query level. + */ + /* list of PlannerParamItems, see below */ + List *plan_params; + Bitmapset *outer_params; + + /* + * simple_rel_array holds pointers to "base rels" and "other rels" (see + * comments for RelOptInfo for more info). It is indexed by rangetable + * index (so entry 0 is always wasted). Entries can be NULL when an RTE + * does not correspond to a base relation, such as a join RTE or an + * unreferenced view RTE; or if the RelOptInfo hasn't been made yet. + */ + struct RelOptInfo **simple_rel_array pg_node_attr(array_size(simple_rel_array_size)); + /* allocated size of array */ + int simple_rel_array_size; + + /* + * simple_rte_array is the same length as simple_rel_array and holds + * pointers to the associated rangetable entries. Using this is a shade + * faster than using rt_fetch(), mostly due to fewer indirections. (Not + * printed because it'd be redundant with parse->rtable.) + */ + RangeTblEntry **simple_rte_array pg_node_attr(read_write_ignore); + + /* + * append_rel_array is the same length as the above arrays, and holds + * pointers to the corresponding AppendRelInfo entry indexed by + * child_relid, or NULL if the rel is not an appendrel child. The array + * itself is not allocated if append_rel_list is empty. (Not printed + * because it'd be redundant with append_rel_list.) + */ + struct AppendRelInfo **append_rel_array pg_node_attr(read_write_ignore); + + /* + * all_baserels is a Relids set of all base relids (but not joins or + * "other" rels) in the query. This is computed in deconstruct_jointree. + */ + Relids all_baserels; + + /* + * outer_join_rels is a Relids set of all outer-join relids in the query. + * This is computed in deconstruct_jointree. + */ + Relids outer_join_rels; + + /* + * all_query_rels is a Relids set of all base relids and outer join relids + * (but not "other" relids) in the query. This is the Relids identifier + * of the final join we need to form. This is computed in + * deconstruct_jointree. + */ + Relids all_query_rels; + + /* + * join_rel_list is a list of all join-relation RelOptInfos we have + * considered in this planning run. For small problems we just scan the + * list to do lookups, but when there are many join relations we build a + * hash table for faster lookups. The hash table is present and valid + * when join_rel_hash is not NULL. Note that we still maintain the list + * even when using the hash table for lookups; this simplifies life for + * GEQO. + */ + List *join_rel_list; + struct HTAB *join_rel_hash pg_node_attr(read_write_ignore); + + /* + * When doing a dynamic-programming-style join search, join_rel_level[k] + * is a list of all join-relation RelOptInfos of level k, and + * join_cur_level is the current level. New join-relation RelOptInfos are + * automatically added to the join_rel_level[join_cur_level] list. + * join_rel_level is NULL if not in use. + * + * Note: we've already printed all baserel and joinrel RelOptInfos above, + * so we don't dump join_rel_level or other lists of RelOptInfos. + */ + /* lists of join-relation RelOptInfos */ + List **join_rel_level pg_node_attr(read_write_ignore); + /* index of list being extended */ + int join_cur_level; + + /* init SubPlans for query */ + List *init_plans; + + /* + * per-CTE-item list of subplan IDs (or -1 if no subplan was made for that + * CTE) + */ + List *cte_plan_ids; + + /* List of Lists of Params for MULTIEXPR subquery outputs */ + List *multiexpr_params; + + /* list of JoinDomains used in the query (higher ones first) */ + List *join_domains; + + /* list of active EquivalenceClasses */ + List *eq_classes; + + /* set true once ECs are canonical */ + bool ec_merging_done; + + /* list of "canonical" PathKeys */ + List *canon_pathkeys; + + /* + * list of OuterJoinClauseInfos for mergejoinable outer join clauses + * w/nonnullable var on left + */ + List *left_join_clauses; + + /* + * list of OuterJoinClauseInfos for mergejoinable outer join clauses + * w/nonnullable var on right + */ + List *right_join_clauses; + + /* + * list of OuterJoinClauseInfos for mergejoinable full join clauses + */ + List *full_join_clauses; + + /* list of SpecialJoinInfos */ + List *join_info_list; + + /* counter for assigning RestrictInfo serial numbers */ + int last_rinfo_serial; + + /* + * all_result_relids is empty for SELECT, otherwise it contains at least + * parse->resultRelation. For UPDATE/DELETE/MERGE across an inheritance + * or partitioning tree, the result rel's child relids are added. When + * using multi-level partitioning, intermediate partitioned rels are + * included. leaf_result_relids is similar except that only actual result + * tables, not partitioned tables, are included in it. + */ + /* set of all result relids */ + Relids all_result_relids; + /* set of all leaf relids */ + Relids leaf_result_relids; + + /* + * list of AppendRelInfos + * + * Note: for AppendRelInfos describing partitions of a partitioned table, + * we guarantee that partitions that come earlier in the partitioned + * table's PartitionDesc will appear earlier in append_rel_list. + */ + List *append_rel_list; + + /* list of RowIdentityVarInfos */ + List *row_identity_vars; + + /* list of PlanRowMarks */ + List *rowMarks; + + /* list of PlaceHolderInfos */ + List *placeholder_list; + + /* array of PlaceHolderInfos indexed by phid */ + struct PlaceHolderInfo **placeholder_array pg_node_attr(read_write_ignore, array_size(placeholder_array_size)); + /* allocated size of array */ + int placeholder_array_size pg_node_attr(read_write_ignore); + + /* list of ForeignKeyOptInfos */ + List *fkey_list; + + /* desired pathkeys for query_planner() */ + List *query_pathkeys; + + /* groupClause pathkeys, if any */ + List *group_pathkeys; + + /* + * The number of elements in the group_pathkeys list which belong to the + * GROUP BY clause. Additional ones belong to ORDER BY / DISTINCT + * aggregates. + */ + int num_groupby_pathkeys; + + /* pathkeys of bottom window, if any */ + List *window_pathkeys; + /* distinctClause pathkeys, if any */ + List *distinct_pathkeys; + /* sortClause pathkeys, if any */ + List *sort_pathkeys; + + /* Canonicalised partition schemes used in the query. */ + List *part_schemes pg_node_attr(read_write_ignore); + + /* RelOptInfos we are now trying to join */ + List *initial_rels pg_node_attr(read_write_ignore); + + /* + * Upper-rel RelOptInfos. Use fetch_upper_rel() to get any particular + * upper rel. + */ + List *upper_rels[UPPERREL_FINAL + 1] pg_node_attr(read_write_ignore); + + /* Result tlists chosen by grouping_planner for upper-stage processing */ + struct PathTarget *upper_targets[UPPERREL_FINAL + 1] pg_node_attr(read_write_ignore); + + /* + * The fully-processed groupClause is kept here. It differs from + * parse->groupClause in that we remove any items that we can prove + * redundant, so that only the columns named here actually need to be + * compared to determine grouping. Note that it's possible for *all* the + * items to be proven redundant, implying that there is only one group + * containing all the query's rows. Hence, if you want to check whether + * GROUP BY was specified, test for nonempty parse->groupClause, not for + * nonempty processed_groupClause. + * + * Currently, when grouping sets are specified we do not attempt to + * optimize the groupClause, so that processed_groupClause will be + * identical to parse->groupClause. + */ + List *processed_groupClause; + + /* + * The fully-processed distinctClause is kept here. It differs from + * parse->distinctClause in that we remove any items that we can prove + * redundant, so that only the columns named here actually need to be + * compared to determine uniqueness. Note that it's possible for *all* + * the items to be proven redundant, implying that there should be only + * one output row. Hence, if you want to check whether DISTINCT was + * specified, test for nonempty parse->distinctClause, not for nonempty + * processed_distinctClause. + */ + List *processed_distinctClause; + + /* + * The fully-processed targetlist is kept here. It differs from + * parse->targetList in that (for INSERT) it's been reordered to match the + * target table, and defaults have been filled in. Also, additional + * resjunk targets may be present. preprocess_targetlist() does most of + * that work, but note that more resjunk targets can get added during + * appendrel expansion. (Hence, upper_targets mustn't get set up till + * after that.) + */ + List *processed_tlist; + + /* + * For UPDATE, this list contains the target table's attribute numbers to + * which the first N entries of processed_tlist are to be assigned. (Any + * additional entries in processed_tlist must be resjunk.) DO NOT use the + * resnos in processed_tlist to identify the UPDATE target columns. + */ + List *update_colnos; + + /* + * Fields filled during create_plan() for use in setrefs.c + */ + /* for GroupingFunc fixup (can't print: array length not known here) */ + AttrNumber *grouping_map pg_node_attr(read_write_ignore); + /* List of MinMaxAggInfos */ + List *minmax_aggs; + + /* context holding PlannerInfo */ + MemoryContext planner_cxt pg_node_attr(read_write_ignore); + + /* # of pages in all non-dummy tables of query */ + Cardinality total_table_pages; + + /* tuple_fraction passed to query_planner */ + Selectivity tuple_fraction; + /* limit_tuples passed to query_planner */ + Cardinality limit_tuples; + + /* + * Minimum security_level for quals. Note: qual_security_level is zero if + * there are no securityQuals. + */ + Index qual_security_level; + + /* true if any RTEs are RTE_JOIN kind */ + bool hasJoinRTEs; + /* true if any RTEs are marked LATERAL */ + bool hasLateralRTEs; + /* true if havingQual was non-null */ + bool hasHavingQual; + /* true if any RestrictInfo has pseudoconstant = true */ + bool hasPseudoConstantQuals; + /* true if we've made any of those */ + bool hasAlternativeSubPlans; + /* true once we're no longer allowed to add PlaceHolderInfos */ + bool placeholdersFrozen; + /* true if planning a recursive WITH item */ + bool hasRecursion; + + /* + * Information about aggregates. Filled by preprocess_aggrefs(). + */ + /* AggInfo structs */ + List *agginfos; + /* AggTransInfo structs */ + List *aggtransinfos; + /* number of aggs with DISTINCT/ORDER BY/WITHIN GROUP */ + int numOrderedAggs; + /* does any agg not support partial mode? */ + bool hasNonPartialAggs; + /* is any partial agg non-serializable? */ + bool hasNonSerialAggs; + + /* + * These fields are used only when hasRecursion is true: + */ + /* PARAM_EXEC ID for the work table */ + int wt_param_id; + /* a path for non-recursive term */ + struct Path *non_recursive_path; + + /* + * These fields are workspace for createplan.c + */ + /* outer rels above current node */ + Relids curOuterRels; + /* not-yet-assigned NestLoopParams */ + List *curOuterParams; + + /* + * These fields are workspace for setrefs.c. Each is an array + * corresponding to glob->subplans. (We could probably teach + * gen_node_support.pl how to determine the array length, but it doesn't + * seem worth the trouble, so just mark them read_write_ignore.) + */ + bool *isAltSubplan pg_node_attr(read_write_ignore); + bool *isUsedSubplan pg_node_attr(read_write_ignore); + + /* optional private data for join_search_hook, e.g., GEQO */ + void *join_search_private pg_node_attr(read_write_ignore); + + /* Does this query modify any partition key columns? */ + bool partColsUpdated; +}; + + +/* + * In places where it's known that simple_rte_array[] must have been prepared + * already, we just index into it to fetch RTEs. In code that might be + * executed before or after entering query_planner(), use this macro. + */ +#define planner_rt_fetch(rti, root) \ + ((root)->simple_rte_array ? (root)->simple_rte_array[rti] : \ + rt_fetch(rti, (root)->parse->rtable)) + +/* + * If multiple relations are partitioned the same way, all such partitions + * will have a pointer to the same PartitionScheme. A list of PartitionScheme + * objects is attached to the PlannerInfo. By design, the partition scheme + * incorporates only the general properties of the partition method (LIST vs. + * RANGE, number of partitioning columns and the type information for each) + * and not the specific bounds. + * + * We store the opclass-declared input data types instead of the partition key + * datatypes since the former rather than the latter are used to compare + * partition bounds. Since partition key data types and the opclass declared + * input data types are expected to be binary compatible (per ResolveOpClass), + * both of those should have same byval and length properties. + */ +typedef struct PartitionSchemeData +{ + char strategy; /* partition strategy */ + int16 partnatts; /* number of partition attributes */ + Oid *partopfamily; /* OIDs of operator families */ + Oid *partopcintype; /* OIDs of opclass declared input data types */ + Oid *partcollation; /* OIDs of partitioning collations */ + + /* Cached information about partition key data types. */ + int16 *parttyplen; + bool *parttypbyval; + + /* Cached information about partition comparison functions. */ + struct FmgrInfo *partsupfunc; +} PartitionSchemeData; + +typedef struct PartitionSchemeData *PartitionScheme; + +/*---------- + * RelOptInfo + * Per-relation information for planning/optimization + * + * For planning purposes, a "base rel" is either a plain relation (a table) + * or the output of a sub-SELECT or function that appears in the range table. + * In either case it is uniquely identified by an RT index. A "joinrel" + * is the joining of two or more base rels. A joinrel is identified by + * the set of RT indexes for its component baserels, along with RT indexes + * for any outer joins it has computed. We create RelOptInfo nodes for each + * baserel and joinrel, and store them in the PlannerInfo's simple_rel_array + * and join_rel_list respectively. + * + * Note that there is only one joinrel for any given set of component + * baserels, no matter what order we assemble them in; so an unordered + * set is the right datatype to identify it with. + * + * We also have "other rels", which are like base rels in that they refer to + * single RT indexes; but they are not part of the join tree, and are given + * a different RelOptKind to identify them. + * Currently the only kind of otherrels are those made for member relations + * of an "append relation", that is an inheritance set or UNION ALL subquery. + * An append relation has a parent RTE that is a base rel, which represents + * the entire append relation. The member RTEs are otherrels. The parent + * is present in the query join tree but the members are not. The member + * RTEs and otherrels are used to plan the scans of the individual tables or + * subqueries of the append set; then the parent baserel is given Append + * and/or MergeAppend paths comprising the best paths for the individual + * member rels. (See comments for AppendRelInfo for more information.) + * + * At one time we also made otherrels to represent join RTEs, for use in + * handling join alias Vars. Currently this is not needed because all join + * alias Vars are expanded to non-aliased form during preprocess_expression. + * + * We also have relations representing joins between child relations of + * different partitioned tables. These relations are not added to + * join_rel_level lists as they are not joined directly by the dynamic + * programming algorithm. + * + * There is also a RelOptKind for "upper" relations, which are RelOptInfos + * that describe post-scan/join processing steps, such as aggregation. + * Many of the fields in these RelOptInfos are meaningless, but their Path + * fields always hold Paths showing ways to do that processing step. + * + * Parts of this data structure are specific to various scan and join + * mechanisms. It didn't seem worth creating new node types for them. + * + * relids - Set of relation identifiers (RT indexes). This is a base + * relation if there is just one, a join relation if more; + * in the join case, RT indexes of any outer joins formed + * at or below this join are included along with baserels + * rows - estimated number of tuples in the relation after restriction + * clauses have been applied (ie, output rows of a plan for it) + * consider_startup - true if there is any value in keeping plain paths for + * this rel on the basis of having cheap startup cost + * consider_param_startup - the same for parameterized paths + * reltarget - Default Path output tlist for this rel; normally contains + * Var and PlaceHolderVar nodes for the values we need to + * output from this relation. + * List is in no particular order, but all rels of an + * appendrel set must use corresponding orders. + * NOTE: in an appendrel child relation, may contain + * arbitrary expressions pulled up from a subquery! + * pathlist - List of Path nodes, one for each potentially useful + * method of generating the relation + * ppilist - ParamPathInfo nodes for parameterized Paths, if any + * cheapest_startup_path - the pathlist member with lowest startup cost + * (regardless of ordering) among the unparameterized paths; + * or NULL if there is no unparameterized path + * cheapest_total_path - the pathlist member with lowest total cost + * (regardless of ordering) among the unparameterized paths; + * or if there is no unparameterized path, the path with lowest + * total cost among the paths with minimum parameterization + * cheapest_unique_path - for caching cheapest path to produce unique + * (no duplicates) output from relation; NULL if not yet requested + * cheapest_parameterized_paths - best paths for their parameterizations; + * always includes cheapest_total_path, even if that's unparameterized + * direct_lateral_relids - rels this rel has direct LATERAL references to + * lateral_relids - required outer rels for LATERAL, as a Relids set + * (includes both direct and indirect lateral references) + * + * If the relation is a base relation it will have these fields set: + * + * relid - RTE index (this is redundant with the relids field, but + * is provided for convenience of access) + * rtekind - copy of RTE's rtekind field + * min_attr, max_attr - range of valid AttrNumbers for rel + * attr_needed - array of bitmapsets indicating the highest joinrel + * in which each attribute is needed; if bit 0 is set then + * the attribute is needed as part of final targetlist + * attr_widths - cache space for per-attribute width estimates; + * zero means not computed yet + * nulling_relids - relids of outer joins that can null this rel + * lateral_vars - lateral cross-references of rel, if any (list of + * Vars and PlaceHolderVars) + * lateral_referencers - relids of rels that reference this one laterally + * (includes both direct and indirect lateral references) + * indexlist - list of IndexOptInfo nodes for relation's indexes + * (always NIL if it's not a table or partitioned table) + * pages - number of disk pages in relation (zero if not a table) + * tuples - number of tuples in relation (not considering restrictions) + * allvisfrac - fraction of disk pages that are marked all-visible + * eclass_indexes - EquivalenceClasses that mention this rel (filled + * only after EC merging is complete) + * subroot - PlannerInfo for subquery (NULL if it's not a subquery) + * subplan_params - list of PlannerParamItems to be passed to subquery + * + * Note: for a subquery, tuples and subroot are not set immediately + * upon creation of the RelOptInfo object; they are filled in when + * set_subquery_pathlist processes the object. + * + * For otherrels that are appendrel members, these fields are filled + * in just as for a baserel, except we don't bother with lateral_vars. + * + * If the relation is either a foreign table or a join of foreign tables that + * all belong to the same foreign server and are assigned to the same user to + * check access permissions as (cf checkAsUser), these fields will be set: + * + * serverid - OID of foreign server, if foreign table (else InvalidOid) + * userid - OID of user to check access as (InvalidOid means current user) + * useridiscurrent - we've assumed that userid equals current user + * fdwroutine - function hooks for FDW, if foreign table (else NULL) + * fdw_private - private state for FDW, if foreign table (else NULL) + * + * Two fields are used to cache knowledge acquired during the join search + * about whether this rel is provably unique when being joined to given other + * relation(s), ie, it can have at most one row matching any given row from + * that join relation. Currently we only attempt such proofs, and thus only + * populate these fields, for base rels; but someday they might be used for + * join rels too: + * + * unique_for_rels - list of Relid sets, each one being a set of other + * rels for which this one has been proven unique + * non_unique_for_rels - list of Relid sets, each one being a set of + * other rels for which we have tried and failed to prove + * this one unique + * + * The presence of the following fields depends on the restrictions + * and joins that the relation participates in: + * + * baserestrictinfo - List of RestrictInfo nodes, containing info about + * each non-join qualification clause in which this relation + * participates (only used for base rels) + * baserestrictcost - Estimated cost of evaluating the baserestrictinfo + * clauses at a single tuple (only used for base rels) + * baserestrict_min_security - Smallest security_level found among + * clauses in baserestrictinfo + * joininfo - List of RestrictInfo nodes, containing info about each + * join clause in which this relation participates (but + * note this excludes clauses that might be derivable from + * EquivalenceClasses) + * has_eclass_joins - flag that EquivalenceClass joins are possible + * + * Note: Keeping a restrictinfo list in the RelOptInfo is useful only for + * base rels, because for a join rel the set of clauses that are treated as + * restrict clauses varies depending on which sub-relations we choose to join. + * (For example, in a 3-base-rel join, a clause relating rels 1 and 2 must be + * treated as a restrictclause if we join {1} and {2 3} to make {1 2 3}; but + * if we join {1 2} and {3} then that clause will be a restrictclause in {1 2} + * and should not be processed again at the level of {1 2 3}.) Therefore, + * the restrictinfo list in the join case appears in individual JoinPaths + * (field joinrestrictinfo), not in the parent relation. But it's OK for + * the RelOptInfo to store the joininfo list, because that is the same + * for a given rel no matter how we form it. + * + * We store baserestrictcost in the RelOptInfo (for base relations) because + * we know we will need it at least once (to price the sequential scan) + * and may need it multiple times to price index scans. + * + * A join relation is considered to be partitioned if it is formed from a + * join of two relations that are partitioned, have matching partitioning + * schemes, and are joined on an equijoin of the partitioning columns. + * Under those conditions we can consider the join relation to be partitioned + * by either relation's partitioning keys, though some care is needed if + * either relation can be forced to null by outer-joining. For example, an + * outer join like (A LEFT JOIN B ON A.a = B.b) may produce rows with B.b + * NULL. These rows may not fit the partitioning conditions imposed on B. + * Hence, strictly speaking, the join is not partitioned by B.b and thus + * partition keys of an outer join should include partition key expressions + * from the non-nullable side only. However, if a subsequent join uses + * strict comparison operators (and all commonly-used equijoin operators are + * strict), the presence of nulls doesn't cause a problem: such rows couldn't + * match anything on the other side and thus they don't create a need to do + * any cross-partition sub-joins. Hence we can treat such values as still + * partitioning the join output for the purpose of additional partitionwise + * joining, so long as a strict join operator is used by the next join. + * + * If the relation is partitioned, these fields will be set: + * + * part_scheme - Partitioning scheme of the relation + * nparts - Number of partitions + * boundinfo - Partition bounds + * partbounds_merged - true if partition bounds are merged ones + * partition_qual - Partition constraint if not the root + * part_rels - RelOptInfos for each partition + * all_partrels - Relids set of all partition relids + * partexprs, nullable_partexprs - Partition key expressions + * + * The partexprs and nullable_partexprs arrays each contain + * part_scheme->partnatts elements. Each of the elements is a list of + * partition key expressions. For partitioned base relations, there is one + * expression in each partexprs element, and nullable_partexprs is empty. + * For partitioned join relations, each base relation within the join + * contributes one partition key expression per partitioning column; + * that expression goes in the partexprs[i] list if the base relation + * is not nullable by this join or any lower outer join, or in the + * nullable_partexprs[i] list if the base relation is nullable. + * Furthermore, FULL JOINs add extra nullable_partexprs expressions + * corresponding to COALESCE expressions of the left and right join columns, + * to simplify matching join clauses to those lists. + * + * Not all fields are printed. (In some cases, there is no print support for + * the field type.) + *---------- + */ + +/* Bitmask of flags supported by table AMs */ +#define AMFLAG_HAS_TID_RANGE (1 << 0) + +typedef enum RelOptKind +{ + RELOPT_BASEREL, + RELOPT_JOINREL, + RELOPT_OTHER_MEMBER_REL, + RELOPT_OTHER_JOINREL, + RELOPT_UPPER_REL, + RELOPT_OTHER_UPPER_REL +} RelOptKind; + +/* + * Is the given relation a simple relation i.e a base or "other" member + * relation? + */ +#define IS_SIMPLE_REL(rel) \ + ((rel)->reloptkind == RELOPT_BASEREL || \ + (rel)->reloptkind == RELOPT_OTHER_MEMBER_REL) + +/* Is the given relation a join relation? */ +#define IS_JOIN_REL(rel) \ + ((rel)->reloptkind == RELOPT_JOINREL || \ + (rel)->reloptkind == RELOPT_OTHER_JOINREL) + +/* Is the given relation an upper relation? */ +#define IS_UPPER_REL(rel) \ + ((rel)->reloptkind == RELOPT_UPPER_REL || \ + (rel)->reloptkind == RELOPT_OTHER_UPPER_REL) + +/* Is the given relation an "other" relation? */ +#define IS_OTHER_REL(rel) \ + ((rel)->reloptkind == RELOPT_OTHER_MEMBER_REL || \ + (rel)->reloptkind == RELOPT_OTHER_JOINREL || \ + (rel)->reloptkind == RELOPT_OTHER_UPPER_REL) + +typedef struct RelOptInfo +{ + pg_node_attr(no_copy_equal, no_read, no_query_jumble) + + NodeTag type; + + RelOptKind reloptkind; + + /* + * all relations included in this RelOptInfo; set of base + OJ relids + * (rangetable indexes) + */ + Relids relids; + + /* + * size estimates generated by planner + */ + /* estimated number of result tuples */ + Cardinality rows; + + /* + * per-relation planner control flags + */ + /* keep cheap-startup-cost paths? */ + bool consider_startup; + /* ditto, for parameterized paths? */ + bool consider_param_startup; + /* consider parallel paths? */ + bool consider_parallel; + + /* + * default result targetlist for Paths scanning this relation; list of + * Vars/Exprs, cost, width + */ + struct PathTarget *reltarget; + + /* + * materialization information + */ + List *pathlist; /* Path structures */ + List *ppilist; /* ParamPathInfos used in pathlist */ + List *partial_pathlist; /* partial Paths */ + struct Path *cheapest_startup_path; + struct Path *cheapest_total_path; + struct Path *cheapest_unique_path; + List *cheapest_parameterized_paths; + + /* + * parameterization information needed for both base rels and join rels + * (see also lateral_vars and lateral_referencers) + */ + /* rels directly laterally referenced */ + Relids direct_lateral_relids; + /* minimum parameterization of rel */ + Relids lateral_relids; + + /* + * information about a base rel (not set for join rels!) + */ + Index relid; + /* containing tablespace */ + Oid reltablespace; + /* RELATION, SUBQUERY, FUNCTION, etc */ + RTEKind rtekind; + /* smallest attrno of rel (often <0) */ + AttrNumber min_attr; + /* largest attrno of rel */ + AttrNumber max_attr; + /* array indexed [min_attr .. max_attr] */ + Relids *attr_needed pg_node_attr(read_write_ignore); + /* array indexed [min_attr .. max_attr] */ + int32 *attr_widths pg_node_attr(read_write_ignore); + /* relids of outer joins that can null this baserel */ + Relids nulling_relids; + /* LATERAL Vars and PHVs referenced by rel */ + List *lateral_vars; + /* rels that reference this baserel laterally */ + Relids lateral_referencers; + /* list of IndexOptInfo */ + List *indexlist; + /* list of StatisticExtInfo */ + List *statlist; + /* size estimates derived from pg_class */ + BlockNumber pages; + Cardinality tuples; + double allvisfrac; + /* indexes in PlannerInfo's eq_classes list of ECs that mention this rel */ + Bitmapset *eclass_indexes; + PlannerInfo *subroot; /* if subquery */ + List *subplan_params; /* if subquery */ + /* wanted number of parallel workers */ + int rel_parallel_workers; + /* Bitmask of optional features supported by the table AM */ + uint32 amflags; + + /* + * Information about foreign tables and foreign joins + */ + /* identifies server for the table or join */ + Oid serverid; + /* identifies user to check access as; 0 means to check as current user */ + Oid userid; + /* join is only valid for current user */ + bool useridiscurrent; + /* use "struct FdwRoutine" to avoid including fdwapi.h here */ + struct FdwRoutine *fdwroutine pg_node_attr(read_write_ignore); + void *fdw_private pg_node_attr(read_write_ignore); + + /* + * cache space for remembering if we have proven this relation unique + */ + /* known unique for these other relid set(s) */ + List *unique_for_rels; + /* known not unique for these set(s) */ + List *non_unique_for_rels; + + /* + * used by various scans and joins: + */ + /* RestrictInfo structures (if base rel) */ + List *baserestrictinfo; + /* cost of evaluating the above */ + QualCost baserestrictcost; + /* min security_level found in baserestrictinfo */ + Index baserestrict_min_security; + /* RestrictInfo structures for join clauses involving this rel */ + List *joininfo; + /* T means joininfo is incomplete */ + bool has_eclass_joins; + + /* + * used by partitionwise joins: + */ + /* consider partitionwise join paths? (if partitioned rel) */ + bool consider_partitionwise_join; + + /* + * inheritance links, if this is an otherrel (otherwise NULL): + */ + /* Immediate parent relation (dumping it would be too verbose) */ + struct RelOptInfo *parent pg_node_attr(read_write_ignore); + /* Topmost parent relation (dumping it would be too verbose) */ + struct RelOptInfo *top_parent pg_node_attr(read_write_ignore); + /* Relids of topmost parent (redundant, but handy) */ + Relids top_parent_relids; + + /* + * used for partitioned relations: + */ + /* Partitioning scheme */ + PartitionScheme part_scheme pg_node_attr(read_write_ignore); + + /* + * Number of partitions; -1 if not yet set; in case of a join relation 0 + * means it's considered unpartitioned + */ + int nparts; + /* Partition bounds */ + struct PartitionBoundInfoData *boundinfo pg_node_attr(read_write_ignore); + /* True if partition bounds were created by partition_bounds_merge() */ + bool partbounds_merged; + /* Partition constraint, if not the root */ + List *partition_qual; + + /* + * Array of RelOptInfos of partitions, stored in the same order as bounds + * (don't print, too bulky and duplicative) + */ + struct RelOptInfo **part_rels pg_node_attr(read_write_ignore); + + /* + * Bitmap with members acting as indexes into the part_rels[] array to + * indicate which partitions survived partition pruning. + */ + Bitmapset *live_parts; + /* Relids set of all partition relids */ + Relids all_partrels; + + /* + * These arrays are of length partkey->partnatts, which we don't have at + * hand, so don't try to print + */ + + /* Non-nullable partition key expressions */ + List **partexprs pg_node_attr(read_write_ignore); + /* Nullable partition key expressions */ + List **nullable_partexprs pg_node_attr(read_write_ignore); +} RelOptInfo; + +/* + * Is given relation partitioned? + * + * It's not enough to test whether rel->part_scheme is set, because it might + * be that the basic partitioning properties of the input relations matched + * but the partition bounds did not. Also, if we are able to prove a rel + * dummy (empty), we should henceforth treat it as unpartitioned. + */ +#define IS_PARTITIONED_REL(rel) \ + ((rel)->part_scheme && (rel)->boundinfo && (rel)->nparts > 0 && \ + (rel)->part_rels && !IS_DUMMY_REL(rel)) + +/* + * Convenience macro to make sure that a partitioned relation has all the + * required members set. + */ +#define REL_HAS_ALL_PART_PROPS(rel) \ + ((rel)->part_scheme && (rel)->boundinfo && (rel)->nparts > 0 && \ + (rel)->part_rels && (rel)->partexprs && (rel)->nullable_partexprs) + +/* + * IndexOptInfo + * Per-index information for planning/optimization + * + * indexkeys[], indexcollations[] each have ncolumns entries. + * opfamily[], and opcintype[] each have nkeycolumns entries. They do + * not contain any information about included attributes. + * + * sortopfamily[], reverse_sort[], and nulls_first[] have + * nkeycolumns entries, if the index is ordered; but if it is unordered, + * those pointers are NULL. + * + * Zeroes in the indexkeys[] array indicate index columns that are + * expressions; there is one element in indexprs for each such column. + * + * For an ordered index, reverse_sort[] and nulls_first[] describe the + * sort ordering of a forward indexscan; we can also consider a backward + * indexscan, which will generate the reverse ordering. + * + * The indexprs and indpred expressions have been run through + * prepqual.c and eval_const_expressions() for ease of matching to + * WHERE clauses. indpred is in implicit-AND form. + * + * indextlist is a TargetEntry list representing the index columns. + * It provides an equivalent base-relation Var for each simple column, + * and links to the matching indexprs element for each expression column. + * + * While most of these fields are filled when the IndexOptInfo is created + * (by plancat.c), indrestrictinfo and predOK are set later, in + * check_index_predicates(). + */ +#ifndef HAVE_INDEXOPTINFO_TYPEDEF +typedef struct IndexOptInfo IndexOptInfo; +#define HAVE_INDEXOPTINFO_TYPEDEF 1 +#endif + +struct IndexOptInfo +{ + pg_node_attr(no_copy_equal, no_read, no_query_jumble) + + NodeTag type; + + /* OID of the index relation */ + Oid indexoid; + /* tablespace of index (not table) */ + Oid reltablespace; + /* back-link to index's table; don't print, else infinite recursion */ + RelOptInfo *rel pg_node_attr(read_write_ignore); + + /* + * index-size statistics (from pg_class and elsewhere) + */ + /* number of disk pages in index */ + BlockNumber pages; + /* number of index tuples in index */ + Cardinality tuples; + /* index tree height, or -1 if unknown */ + int tree_height; + + /* + * index descriptor information + */ + /* number of columns in index */ + int ncolumns; + /* number of key columns in index */ + int nkeycolumns; + + /* + * table column numbers of index's columns (both key and included + * columns), or 0 for expression columns + */ + int *indexkeys pg_node_attr(array_size(ncolumns)); + /* OIDs of collations of index columns */ + Oid *indexcollations pg_node_attr(array_size(nkeycolumns)); + /* OIDs of operator families for columns */ + Oid *opfamily pg_node_attr(array_size(nkeycolumns)); + /* OIDs of opclass declared input data types */ + Oid *opcintype pg_node_attr(array_size(nkeycolumns)); + /* OIDs of btree opfamilies, if orderable. NULL if partitioned index */ + Oid *sortopfamily pg_node_attr(array_size(nkeycolumns)); + /* is sort order descending? or NULL if partitioned index */ + bool *reverse_sort pg_node_attr(array_size(nkeycolumns)); + /* do NULLs come first in the sort order? or NULL if partitioned index */ + bool *nulls_first pg_node_attr(array_size(nkeycolumns)); + /* opclass-specific options for columns */ + bytea **opclassoptions pg_node_attr(read_write_ignore); + /* which index cols can be returned in an index-only scan? */ + bool *canreturn pg_node_attr(array_size(ncolumns)); + /* OID of the access method (in pg_am) */ + Oid relam; + + /* + * expressions for non-simple index columns; redundant to print since we + * print indextlist + */ + List *indexprs pg_node_attr(read_write_ignore); + /* predicate if a partial index, else NIL */ + List *indpred; + + /* targetlist representing index columns */ + List *indextlist; + + /* + * parent relation's baserestrictinfo list, less any conditions implied by + * the index's predicate (unless it's a target rel, see comments in + * check_index_predicates()) + */ + List *indrestrictinfo; + + /* true if index predicate matches query */ + bool predOK; + /* true if a unique index */ + bool unique; + /* is uniqueness enforced immediately? */ + bool immediate; + /* true if index doesn't really exist */ + bool hypothetical; + + /* + * Remaining fields are copied from the index AM's API struct + * (IndexAmRoutine). These fields are not set for partitioned indexes. + */ + bool amcanorderbyop; + bool amoptionalkey; + bool amsearcharray; + bool amsearchnulls; + /* does AM have amgettuple interface? */ + bool amhasgettuple; + /* does AM have amgetbitmap interface? */ + bool amhasgetbitmap; + bool amcanparallel; + /* does AM have ammarkpos interface? */ + bool amcanmarkpos; + /* AM's cost estimator */ + /* Rather than include amapi.h here, we declare amcostestimate like this */ + void (*amcostestimate) () pg_node_attr(read_write_ignore); +}; + +/* + * ForeignKeyOptInfo + * Per-foreign-key information for planning/optimization + * + * The per-FK-column arrays can be fixed-size because we allow at most + * INDEX_MAX_KEYS columns in a foreign key constraint. Each array has + * nkeys valid entries. + */ +typedef struct ForeignKeyOptInfo +{ + pg_node_attr(custom_read_write, no_copy_equal, no_read, no_query_jumble) + + NodeTag type; + + /* + * Basic data about the foreign key (fetched from catalogs): + */ + + /* RT index of the referencing table */ + Index con_relid; + /* RT index of the referenced table */ + Index ref_relid; + /* number of columns in the foreign key */ + int nkeys; + /* cols in referencing table */ + AttrNumber conkey[INDEX_MAX_KEYS] pg_node_attr(array_size(nkeys)); + /* cols in referenced table */ + AttrNumber confkey[INDEX_MAX_KEYS] pg_node_attr(array_size(nkeys)); + /* PK = FK operator OIDs */ + Oid conpfeqop[INDEX_MAX_KEYS] pg_node_attr(array_size(nkeys)); + + /* + * Derived info about whether FK's equality conditions match the query: + */ + + /* # of FK cols matched by ECs */ + int nmatched_ec; + /* # of these ECs that are ec_has_const */ + int nconst_ec; + /* # of FK cols matched by non-EC rinfos */ + int nmatched_rcols; + /* total # of non-EC rinfos matched to FK */ + int nmatched_ri; + /* Pointer to eclass matching each column's condition, if there is one */ + struct EquivalenceClass *eclass[INDEX_MAX_KEYS]; + /* Pointer to eclass member for the referencing Var, if there is one */ + struct EquivalenceMember *fk_eclass_member[INDEX_MAX_KEYS]; + /* List of non-EC RestrictInfos matching each column's condition */ + List *rinfos[INDEX_MAX_KEYS]; +} ForeignKeyOptInfo; + +/* + * StatisticExtInfo + * Information about extended statistics for planning/optimization + * + * Each pg_statistic_ext row is represented by one or more nodes of this + * type, or even zero if ANALYZE has not computed them. + */ +typedef struct StatisticExtInfo +{ + pg_node_attr(no_copy_equal, no_read, no_query_jumble) + + NodeTag type; + + /* OID of the statistics row */ + Oid statOid; + + /* includes child relations */ + bool inherit; + + /* back-link to statistic's table; don't print, else infinite recursion */ + RelOptInfo *rel pg_node_attr(read_write_ignore); + + /* statistics kind of this entry */ + char kind; + + /* attnums of the columns covered */ + Bitmapset *keys; + + /* expressions */ + List *exprs; +} StatisticExtInfo; + +/* + * JoinDomains + * + * A "join domain" defines the scope of applicability of deductions made via + * the EquivalenceClass mechanism. Roughly speaking, a join domain is a set + * of base+OJ relations that are inner-joined together. More precisely, it is + * the set of relations at which equalities deduced from an EquivalenceClass + * can be enforced or should be expected to hold. The topmost JoinDomain + * covers the whole query (so its jd_relids should equal all_query_rels). + * An outer join creates a new JoinDomain that includes all base+OJ relids + * within its nullable side, but (by convention) not the OJ's own relid. + * A FULL join creates two new JoinDomains, one for each side. + * + * Notice that a rel that is below outer join(s) will thus appear to belong + * to multiple join domains. However, any of its Vars that appear in + * EquivalenceClasses belonging to higher join domains will have nullingrel + * bits preventing them from being evaluated at the rel's scan level, so that + * we will not be able to derive enforceable-at-the-rel-scan-level clauses + * from such ECs. We define the join domain relid sets this way so that + * domains can be said to be "higher" or "lower" when one domain relid set + * includes another. + * + * The JoinDomains for a query are computed in deconstruct_jointree. + * We do not copy JoinDomain structs once made, so they can be compared + * for equality by simple pointer equality. + */ +typedef struct JoinDomain +{ + pg_node_attr(no_copy_equal, no_read, no_query_jumble) + + NodeTag type; + + Relids jd_relids; /* all relids contained within the domain */ +} JoinDomain; + +/* + * EquivalenceClasses + * + * Whenever we identify a mergejoinable equality clause A = B that is + * not an outer-join clause, we create an EquivalenceClass containing + * the expressions A and B to record this knowledge. If we later find another + * equivalence B = C, we add C to the existing EquivalenceClass; this may + * require merging two existing EquivalenceClasses. At the end of the qual + * distribution process, we have sets of values that are known all transitively + * equal to each other, where "equal" is according to the rules of the btree + * operator family(s) shown in ec_opfamilies, as well as the collation shown + * by ec_collation. (We restrict an EC to contain only equalities whose + * operators belong to the same set of opfamilies. This could probably be + * relaxed, but for now it's not worth the trouble, since nearly all equality + * operators belong to only one btree opclass anyway. Similarly, we suppose + * that all or none of the input datatypes are collatable, so that a single + * collation value is sufficient.) + * + * Strictly speaking, deductions from an EquivalenceClass hold only within + * a "join domain", that is a set of relations that are innerjoined together + * (see JoinDomain above). For the most part we don't need to account for + * this explicitly, because equality clauses from different join domains + * will contain Vars that are not equal() because they have different + * nullingrel sets, and thus we will never falsely merge ECs from different + * join domains. But Var-free (pseudoconstant) expressions lack that safety + * feature. We handle that by marking "const" EC members with the JoinDomain + * of the clause they came from; two nominally-equal const members will be + * considered different if they came from different JoinDomains. This ensures + * no false EquivalenceClass merges will occur. + * + * We also use EquivalenceClasses as the base structure for PathKeys, letting + * us represent knowledge about different sort orderings being equivalent. + * Since every PathKey must reference an EquivalenceClass, we will end up + * with single-member EquivalenceClasses whenever a sort key expression has + * not been equivalenced to anything else. It is also possible that such an + * EquivalenceClass will contain a volatile expression ("ORDER BY random()"), + * which is a case that can't arise otherwise since clauses containing + * volatile functions are never considered mergejoinable. We mark such + * EquivalenceClasses specially to prevent them from being merged with + * ordinary EquivalenceClasses. Also, for volatile expressions we have + * to be careful to match the EquivalenceClass to the correct targetlist + * entry: consider SELECT random() AS a, random() AS b ... ORDER BY b,a. + * So we record the SortGroupRef of the originating sort clause. + * + * NB: if ec_merged isn't NULL, this class has been merged into another, and + * should be ignored in favor of using the pointed-to class. + * + * NB: EquivalenceClasses are never copied after creation. Therefore, + * copyObject() copies pointers to them as pointers, and equal() compares + * pointers to EquivalenceClasses via pointer equality. This is implemented + * by putting copy_as_scalar and equal_as_scalar attributes on fields that + * are pointers to EquivalenceClasses. The same goes for EquivalenceMembers. + */ +typedef struct EquivalenceClass +{ + pg_node_attr(custom_read_write, no_copy_equal, no_read, no_query_jumble) + + NodeTag type; + + List *ec_opfamilies; /* btree operator family OIDs */ + Oid ec_collation; /* collation, if datatypes are collatable */ + List *ec_members; /* list of EquivalenceMembers */ + List *ec_sources; /* list of generating RestrictInfos */ + List *ec_derives; /* list of derived RestrictInfos */ + Relids ec_relids; /* all relids appearing in ec_members, except + * for child members (see below) */ + bool ec_has_const; /* any pseudoconstants in ec_members? */ + bool ec_has_volatile; /* the (sole) member is a volatile expr */ + bool ec_broken; /* failed to generate needed clauses? */ + Index ec_sortref; /* originating sortclause label, or 0 */ + Index ec_min_security; /* minimum security_level in ec_sources */ + Index ec_max_security; /* maximum security_level in ec_sources */ + struct EquivalenceClass *ec_merged; /* set if merged into another EC */ +} EquivalenceClass; + +/* + * If an EC contains a constant, any PathKey depending on it must be + * redundant, since there's only one possible value of the key. + */ +#define EC_MUST_BE_REDUNDANT(eclass) \ + ((eclass)->ec_has_const) + +/* + * EquivalenceMember - one member expression of an EquivalenceClass + * + * em_is_child signifies that this element was built by transposing a member + * for an appendrel parent relation to represent the corresponding expression + * for an appendrel child. These members are used for determining the + * pathkeys of scans on the child relation and for explicitly sorting the + * child when necessary to build a MergeAppend path for the whole appendrel + * tree. An em_is_child member has no impact on the properties of the EC as a + * whole; in particular the EC's ec_relids field does NOT include the child + * relation. An em_is_child member should never be marked em_is_const nor + * cause ec_has_const or ec_has_volatile to be set, either. Thus, em_is_child + * members are not really full-fledged members of the EC, but just reflections + * or doppelgangers of real members. Most operations on EquivalenceClasses + * should ignore em_is_child members, and those that don't should test + * em_relids to make sure they only consider relevant members. + * + * em_datatype is usually the same as exprType(em_expr), but can be + * different when dealing with a binary-compatible opfamily; in particular + * anyarray_ops would never work without this. Use em_datatype when + * looking up a specific btree operator to work with this expression. + */ +typedef struct EquivalenceMember +{ + pg_node_attr(no_copy_equal, no_read, no_query_jumble) + + NodeTag type; + + Expr *em_expr; /* the expression represented */ + Relids em_relids; /* all relids appearing in em_expr */ + bool em_is_const; /* expression is pseudoconstant? */ + bool em_is_child; /* derived version for a child relation? */ + Oid em_datatype; /* the "nominal type" used by the opfamily */ + JoinDomain *em_jdomain; /* join domain containing the source clause */ + /* if em_is_child is true, this links to corresponding EM for top parent */ + struct EquivalenceMember *em_parent pg_node_attr(read_write_ignore); +} EquivalenceMember; + +/* + * PathKeys + * + * The sort ordering of a path is represented by a list of PathKey nodes. + * An empty list implies no known ordering. Otherwise the first item + * represents the primary sort key, the second the first secondary sort key, + * etc. The value being sorted is represented by linking to an + * EquivalenceClass containing that value and including pk_opfamily among its + * ec_opfamilies. The EquivalenceClass tells which collation to use, too. + * This is a convenient method because it makes it trivial to detect + * equivalent and closely-related orderings. (See optimizer/README for more + * information.) + * + * Note: pk_strategy is either BTLessStrategyNumber (for ASC) or + * BTGreaterStrategyNumber (for DESC). We assume that all ordering-capable + * index types will use btree-compatible strategy numbers. + */ +typedef struct PathKey +{ + pg_node_attr(no_read, no_query_jumble) + + NodeTag type; + + /* the value that is ordered */ + EquivalenceClass *pk_eclass pg_node_attr(copy_as_scalar, equal_as_scalar); + Oid pk_opfamily; /* btree opfamily defining the ordering */ + int pk_strategy; /* sort direction (ASC or DESC) */ + bool pk_nulls_first; /* do NULLs come before normal values? */ +} PathKey; + +/* + * VolatileFunctionStatus -- allows nodes to cache their + * contain_volatile_functions properties. VOLATILITY_UNKNOWN means not yet + * determined. + */ +typedef enum VolatileFunctionStatus +{ + VOLATILITY_UNKNOWN = 0, + VOLATILITY_VOLATILE, + VOLATILITY_NOVOLATILE +} VolatileFunctionStatus; + +/* + * PathTarget + * + * This struct contains what we need to know during planning about the + * targetlist (output columns) that a Path will compute. Each RelOptInfo + * includes a default PathTarget, which its individual Paths may simply + * reference. However, in some cases a Path may compute outputs different + * from other Paths, and in that case we make a custom PathTarget for it. + * For example, an indexscan might return index expressions that would + * otherwise need to be explicitly calculated. (Note also that "upper" + * relations generally don't have useful default PathTargets.) + * + * exprs contains bare expressions; they do not have TargetEntry nodes on top, + * though those will appear in finished Plans. + * + * sortgrouprefs[] is an array of the same length as exprs, containing the + * corresponding sort/group refnos, or zeroes for expressions not referenced + * by sort/group clauses. If sortgrouprefs is NULL (which it generally is in + * RelOptInfo.reltarget targets; only upper-level Paths contain this info), + * we have not identified sort/group columns in this tlist. This allows us to + * deal with sort/group refnos when needed with less expense than including + * TargetEntry nodes in the exprs list. + */ +typedef struct PathTarget +{ + pg_node_attr(no_copy_equal, no_read, no_query_jumble) + + NodeTag type; + + /* list of expressions to be computed */ + List *exprs; + + /* corresponding sort/group refnos, or 0 */ + Index *sortgrouprefs pg_node_attr(array_size(exprs)); + + /* cost of evaluating the expressions */ + QualCost cost; + + /* estimated avg width of result tuples */ + int width; + + /* indicates if exprs contain any volatile functions */ + VolatileFunctionStatus has_volatile_expr; +} PathTarget; + +/* Convenience macro to get a sort/group refno from a PathTarget */ +#define get_pathtarget_sortgroupref(target, colno) \ + ((target)->sortgrouprefs ? (target)->sortgrouprefs[colno] : (Index) 0) + + +/* + * ParamPathInfo + * + * All parameterized paths for a given relation with given required outer rels + * link to a single ParamPathInfo, which stores common information such as + * the estimated rowcount for this parameterization. We do this partly to + * avoid recalculations, but mostly to ensure that the estimated rowcount + * is in fact the same for every such path. + * + * Note: ppi_clauses is only used in ParamPathInfos for base relation paths; + * in join cases it's NIL because the set of relevant clauses varies depending + * on how the join is formed. The relevant clauses will appear in each + * parameterized join path's joinrestrictinfo list, instead. ParamPathInfos + * for append relations don't bother with this, either. + * + * ppi_serials is the set of rinfo_serial numbers for quals that are enforced + * by this path. As with ppi_clauses, it's only maintained for baserels. + * (We could construct it on-the-fly from ppi_clauses, but it seems better + * to materialize a copy.) + */ +typedef struct ParamPathInfo +{ + pg_node_attr(no_copy_equal, no_read, no_query_jumble) + + NodeTag type; + + Relids ppi_req_outer; /* rels supplying parameters used by path */ + Cardinality ppi_rows; /* estimated number of result tuples */ + List *ppi_clauses; /* join clauses available from outer rels */ + Bitmapset *ppi_serials; /* set of rinfo_serial for enforced quals */ +} ParamPathInfo; + + +/* + * Type "Path" is used as-is for sequential-scan paths, as well as some other + * simple plan types that we don't need any extra information in the path for. + * For other path types it is the first component of a larger struct. + * + * "pathtype" is the NodeTag of the Plan node we could build from this Path. + * It is partially redundant with the Path's NodeTag, but allows us to use + * the same Path type for multiple Plan types when there is no need to + * distinguish the Plan type during path processing. + * + * "parent" identifies the relation this Path scans, and "pathtarget" + * describes the precise set of output columns the Path would compute. + * In simple cases all Paths for a given rel share the same targetlist, + * which we represent by having path->pathtarget equal to parent->reltarget. + * + * "param_info", if not NULL, links to a ParamPathInfo that identifies outer + * relation(s) that provide parameter values to each scan of this path. + * That means this path can only be joined to those rels by means of nestloop + * joins with this path on the inside. Also note that a parameterized path + * is responsible for testing all "movable" joinclauses involving this rel + * and the specified outer rel(s). + * + * "rows" is the same as parent->rows in simple paths, but in parameterized + * paths and UniquePaths it can be less than parent->rows, reflecting the + * fact that we've filtered by extra join conditions or removed duplicates. + * + * "pathkeys" is a List of PathKey nodes (see above), describing the sort + * ordering of the path's output rows. + * + * We do not support copying Path trees, mainly because the circular linkages + * between RelOptInfo and Path nodes can't be handled easily in a simple + * depth-first traversal. We also don't have read support at the moment. + */ +typedef struct Path +{ + pg_node_attr(no_copy_equal, no_read, no_query_jumble) + + NodeTag type; + + /* tag identifying scan/join method */ + NodeTag pathtype; + + /* + * the relation this path can build + * + * We do NOT print the parent, else we'd be in infinite recursion. We can + * print the parent's relids for identification purposes, though. + */ + RelOptInfo *parent pg_node_attr(write_only_relids); + + /* + * list of Vars/Exprs, cost, width + * + * We print the pathtarget only if it's not the default one for the rel. + */ + PathTarget *pathtarget pg_node_attr(write_only_nondefault_pathtarget); + + /* + * parameterization info, or NULL if none + * + * We do not print the whole of param_info, since it's printed via + * RelOptInfo; it's sufficient and less cluttering to print just the + * required outer relids. + */ + ParamPathInfo *param_info pg_node_attr(write_only_req_outer); + + /* engage parallel-aware logic? */ + bool parallel_aware; + /* OK to use as part of parallel plan? */ + bool parallel_safe; + /* desired # of workers; 0 = not parallel */ + int parallel_workers; + + /* estimated size/costs for path (see costsize.c for more info) */ + Cardinality rows; /* estimated number of result tuples */ + Cost startup_cost; /* cost expended before fetching any tuples */ + Cost total_cost; /* total cost (assuming all tuples fetched) */ + + /* sort ordering of path's output; a List of PathKey nodes; see above */ + List *pathkeys; +} Path; + +/* Macro for extracting a path's parameterization relids; beware double eval */ +#define PATH_REQ_OUTER(path) \ + ((path)->param_info ? (path)->param_info->ppi_req_outer : (Relids) NULL) + +/*---------- + * IndexPath represents an index scan over a single index. + * + * This struct is used for both regular indexscans and index-only scans; + * path.pathtype is T_IndexScan or T_IndexOnlyScan to show which is meant. + * + * 'indexinfo' is the index to be scanned. + * + * 'indexclauses' is a list of IndexClause nodes, each representing one + * index-checkable restriction, with implicit AND semantics across the list. + * An empty list implies a full index scan. + * + * 'indexorderbys', if not NIL, is a list of ORDER BY expressions that have + * been found to be usable as ordering operators for an amcanorderbyop index. + * The list must match the path's pathkeys, ie, one expression per pathkey + * in the same order. These are not RestrictInfos, just bare expressions, + * since they generally won't yield booleans. It's guaranteed that each + * expression has the index key on the left side of the operator. + * + * 'indexorderbycols' is an integer list of index column numbers (zero-based) + * of the same length as 'indexorderbys', showing which index column each + * ORDER BY expression is meant to be used with. (There is no restriction + * on which index column each ORDER BY can be used with.) + * + * 'indexscandir' is one of: + * ForwardScanDirection: forward scan of an index + * BackwardScanDirection: backward scan of an ordered index + * Unordered indexes will always have an indexscandir of ForwardScanDirection. + * + * 'indextotalcost' and 'indexselectivity' are saved in the IndexPath so that + * we need not recompute them when considering using the same index in a + * bitmap index/heap scan (see BitmapHeapPath). The costs of the IndexPath + * itself represent the costs of an IndexScan or IndexOnlyScan plan type. + *---------- + */ +typedef struct IndexPath +{ + Path path; + IndexOptInfo *indexinfo; + List *indexclauses; + List *indexorderbys; + List *indexorderbycols; + ScanDirection indexscandir; + Cost indextotalcost; + Selectivity indexselectivity; +} IndexPath; + +/* + * Each IndexClause references a RestrictInfo node from the query's WHERE + * or JOIN conditions, and shows how that restriction can be applied to + * the particular index. We support both indexclauses that are directly + * usable by the index machinery, which are typically of the form + * "indexcol OP pseudoconstant", and those from which an indexable qual + * can be derived. The simplest such transformation is that a clause + * of the form "pseudoconstant OP indexcol" can be commuted to produce an + * indexable qual (the index machinery expects the indexcol to be on the + * left always). Another example is that we might be able to extract an + * indexable range condition from a LIKE condition, as in "x LIKE 'foo%bar'" + * giving rise to "x >= 'foo' AND x < 'fop'". Derivation of such lossy + * conditions is done by a planner support function attached to the + * indexclause's top-level function or operator. + * + * indexquals is a list of RestrictInfos for the directly-usable index + * conditions associated with this IndexClause. In the simplest case + * it's a one-element list whose member is iclause->rinfo. Otherwise, + * it contains one or more directly-usable indexqual conditions extracted + * from the given clause. The 'lossy' flag indicates whether the + * indexquals are semantically equivalent to the original clause, or + * represent a weaker condition. + * + * Normally, indexcol is the index of the single index column the clause + * works on, and indexcols is NIL. But if the clause is a RowCompareExpr, + * indexcol is the index of the leading column, and indexcols is a list of + * all the affected columns. (Note that indexcols matches up with the + * columns of the actual indexable RowCompareExpr in indexquals, which + * might be different from the original in rinfo.) + * + * An IndexPath's IndexClause list is required to be ordered by index + * column, i.e. the indexcol values must form a nondecreasing sequence. + * (The order of multiple clauses for the same index column is unspecified.) + */ +typedef struct IndexClause +{ + pg_node_attr(no_copy_equal, no_read, no_query_jumble) + + NodeTag type; + struct RestrictInfo *rinfo; /* original restriction or join clause */ + List *indexquals; /* indexqual(s) derived from it */ + bool lossy; /* are indexquals a lossy version of clause? */ + AttrNumber indexcol; /* index column the clause uses (zero-based) */ + List *indexcols; /* multiple index columns, if RowCompare */ +} IndexClause; + +/* + * BitmapHeapPath represents one or more indexscans that generate TID bitmaps + * instead of directly accessing the heap, followed by AND/OR combinations + * to produce a single bitmap, followed by a heap scan that uses the bitmap. + * Note that the output is always considered unordered, since it will come + * out in physical heap order no matter what the underlying indexes did. + * + * The individual indexscans are represented by IndexPath nodes, and any + * logic on top of them is represented by a tree of BitmapAndPath and + * BitmapOrPath nodes. Notice that we can use the same IndexPath node both + * to represent a regular (or index-only) index scan plan, and as the child + * of a BitmapHeapPath that represents scanning the same index using a + * BitmapIndexScan. The startup_cost and total_cost figures of an IndexPath + * always represent the costs to use it as a regular (or index-only) + * IndexScan. The costs of a BitmapIndexScan can be computed using the + * IndexPath's indextotalcost and indexselectivity. + */ +typedef struct BitmapHeapPath +{ + Path path; + Path *bitmapqual; /* IndexPath, BitmapAndPath, BitmapOrPath */ +} BitmapHeapPath; + +/* + * BitmapAndPath represents a BitmapAnd plan node; it can only appear as + * part of the substructure of a BitmapHeapPath. The Path structure is + * a bit more heavyweight than we really need for this, but for simplicity + * we make it a derivative of Path anyway. + */ +typedef struct BitmapAndPath +{ + Path path; + List *bitmapquals; /* IndexPaths and BitmapOrPaths */ + Selectivity bitmapselectivity; +} BitmapAndPath; + +/* + * BitmapOrPath represents a BitmapOr plan node; it can only appear as + * part of the substructure of a BitmapHeapPath. The Path structure is + * a bit more heavyweight than we really need for this, but for simplicity + * we make it a derivative of Path anyway. + */ +typedef struct BitmapOrPath +{ + Path path; + List *bitmapquals; /* IndexPaths and BitmapAndPaths */ + Selectivity bitmapselectivity; +} BitmapOrPath; + +/* + * TidPath represents a scan by TID + * + * tidquals is an implicitly OR'ed list of qual expressions of the form + * "CTID = pseudoconstant", or "CTID = ANY(pseudoconstant_array)", + * or a CurrentOfExpr for the relation. + */ +typedef struct TidPath +{ + Path path; + List *tidquals; /* qual(s) involving CTID = something */ +} TidPath; + +/* + * TidRangePath represents a scan by a contiguous range of TIDs + * + * tidrangequals is an implicitly AND'ed list of qual expressions of the form + * "CTID relop pseudoconstant", where relop is one of >,>=,<,<=. + */ +typedef struct TidRangePath +{ + Path path; + List *tidrangequals; +} TidRangePath; + +/* + * SubqueryScanPath represents a scan of an unflattened subquery-in-FROM + * + * Note that the subpath comes from a different planning domain; for example + * RTE indexes within it mean something different from those known to the + * SubqueryScanPath. path.parent->subroot is the planning context needed to + * interpret the subpath. + */ +typedef struct SubqueryScanPath +{ + Path path; + Path *subpath; /* path representing subquery execution */ +} SubqueryScanPath; + +/* + * ForeignPath represents a potential scan of a foreign table, foreign join + * or foreign upper-relation. + * + * fdw_private stores FDW private data about the scan. While fdw_private is + * not actually touched by the core code during normal operations, it's + * generally a good idea to use a representation that can be dumped by + * nodeToString(), so that you can examine the structure during debugging + * with tools like pprint(). + */ +typedef struct ForeignPath +{ + Path path; + Path *fdw_outerpath; + List *fdw_private; +} ForeignPath; + +/* + * CustomPath represents a table scan or a table join done by some out-of-core + * extension. + * + * We provide a set of hooks here - which the provider must take care to set + * up correctly - to allow extensions to supply their own methods of scanning + * a relation or joing relations. For example, a provider might provide GPU + * acceleration, a cache-based scan, or some other kind of logic we haven't + * dreamed up yet. + * + * CustomPaths can be injected into the planning process for a base or join + * relation by set_rel_pathlist_hook or set_join_pathlist_hook functions, + * respectively. + * + * Core code must avoid assuming that the CustomPath is only as large as + * the structure declared here; providers are allowed to make it the first + * element in a larger structure. (Since the planner never copies Paths, + * this doesn't add any complication.) However, for consistency with the + * FDW case, we provide a "custom_private" field in CustomPath; providers + * may prefer to use that rather than define another struct type. + */ + +struct CustomPathMethods; + +typedef struct CustomPath +{ + Path path; + uint32 flags; /* mask of CUSTOMPATH_* flags, see + * nodes/extensible.h */ + List *custom_paths; /* list of child Path nodes, if any */ + List *custom_private; + const struct CustomPathMethods *methods; +} CustomPath; + +/* + * AppendPath represents an Append plan, ie, successive execution of + * several member plans. + * + * For partial Append, 'subpaths' contains non-partial subpaths followed by + * partial subpaths. + * + * Note: it is possible for "subpaths" to contain only one, or even no, + * elements. These cases are optimized during create_append_plan. + * In particular, an AppendPath with no subpaths is a "dummy" path that + * is created to represent the case that a relation is provably empty. + * (This is a convenient representation because it means that when we build + * an appendrel and find that all its children have been excluded, no extra + * action is needed to recognize the relation as dummy.) + */ +typedef struct AppendPath +{ + Path path; + List *subpaths; /* list of component Paths */ + /* Index of first partial path in subpaths; list_length(subpaths) if none */ + int first_partial_path; + Cardinality limit_tuples; /* hard limit on output tuples, or -1 */ +} AppendPath; + +#define IS_DUMMY_APPEND(p) \ + (IsA((p), AppendPath) && ((AppendPath *) (p))->subpaths == NIL) + +/* + * A relation that's been proven empty will have one path that is dummy + * (but might have projection paths on top). For historical reasons, + * this is provided as a macro that wraps is_dummy_rel(). + */ +#define IS_DUMMY_REL(r) is_dummy_rel(r) +extern bool is_dummy_rel(RelOptInfo *rel); + +/* + * MergeAppendPath represents a MergeAppend plan, ie, the merging of sorted + * results from several member plans to produce similarly-sorted output. + */ +typedef struct MergeAppendPath +{ + Path path; + List *subpaths; /* list of component Paths */ + Cardinality limit_tuples; /* hard limit on output tuples, or -1 */ +} MergeAppendPath; + +/* + * GroupResultPath represents use of a Result plan node to compute the + * output of a degenerate GROUP BY case, wherein we know we should produce + * exactly one row, which might then be filtered by a HAVING qual. + * + * Note that quals is a list of bare clauses, not RestrictInfos. + */ +typedef struct GroupResultPath +{ + Path path; + List *quals; +} GroupResultPath; + +/* + * MaterialPath represents use of a Material plan node, i.e., caching of + * the output of its subpath. This is used when the subpath is expensive + * and needs to be scanned repeatedly, or when we need mark/restore ability + * and the subpath doesn't have it. + */ +typedef struct MaterialPath +{ + Path path; + Path *subpath; +} MaterialPath; + +/* + * MemoizePath represents a Memoize plan node, i.e., a cache that caches + * tuples from parameterized paths to save the underlying node from having to + * be rescanned for parameter values which are already cached. + */ +typedef struct MemoizePath +{ + Path path; + Path *subpath; /* outerpath to cache tuples from */ + List *hash_operators; /* OIDs of hash equality ops for cache keys */ + List *param_exprs; /* expressions that are cache keys */ + bool singlerow; /* true if the cache entry is to be marked as + * complete after caching the first record. */ + bool binary_mode; /* true when cache key should be compared bit + * by bit, false when using hash equality ops */ + Cardinality calls; /* expected number of rescans */ + uint32 est_entries; /* The maximum number of entries that the + * planner expects will fit in the cache, or 0 + * if unknown */ +} MemoizePath; + +/* + * UniquePath represents elimination of distinct rows from the output of + * its subpath. + * + * This can represent significantly different plans: either hash-based or + * sort-based implementation, or a no-op if the input path can be proven + * distinct already. The decision is sufficiently localized that it's not + * worth having separate Path node types. (Note: in the no-op case, we could + * eliminate the UniquePath node entirely and just return the subpath; but + * it's convenient to have a UniquePath in the path tree to signal upper-level + * routines that the input is known distinct.) + */ +typedef enum UniquePathMethod +{ + UNIQUE_PATH_NOOP, /* input is known unique already */ + UNIQUE_PATH_HASH, /* use hashing */ + UNIQUE_PATH_SORT /* use sorting */ +} UniquePathMethod; + +typedef struct UniquePath +{ + Path path; + Path *subpath; + UniquePathMethod umethod; + List *in_operators; /* equality operators of the IN clause */ + List *uniq_exprs; /* expressions to be made unique */ +} UniquePath; + +/* + * GatherPath runs several copies of a plan in parallel and collects the + * results. The parallel leader may also execute the plan, unless the + * single_copy flag is set. + */ +typedef struct GatherPath +{ + Path path; + Path *subpath; /* path for each worker */ + bool single_copy; /* don't execute path more than once */ + int num_workers; /* number of workers sought to help */ +} GatherPath; + +/* + * GatherMergePath runs several copies of a plan in parallel and collects + * the results, preserving their common sort order. + */ +typedef struct GatherMergePath +{ + Path path; + Path *subpath; /* path for each worker */ + int num_workers; /* number of workers sought to help */ +} GatherMergePath; + + +/* + * All join-type paths share these fields. + */ + +typedef struct JoinPath +{ + pg_node_attr(abstract) + + Path path; + + JoinType jointype; + + bool inner_unique; /* each outer tuple provably matches no more + * than one inner tuple */ + + Path *outerjoinpath; /* path for the outer side of the join */ + Path *innerjoinpath; /* path for the inner side of the join */ + + List *joinrestrictinfo; /* RestrictInfos to apply to join */ + + /* + * See the notes for RelOptInfo and ParamPathInfo to understand why + * joinrestrictinfo is needed in JoinPath, and can't be merged into the + * parent RelOptInfo. + */ +} JoinPath; + +/* + * A nested-loop path needs no special fields. + */ + +typedef struct NestPath +{ + JoinPath jpath; +} NestPath; + +/* + * A mergejoin path has these fields. + * + * Unlike other path types, a MergePath node doesn't represent just a single + * run-time plan node: it can represent up to four. Aside from the MergeJoin + * node itself, there can be a Sort node for the outer input, a Sort node + * for the inner input, and/or a Material node for the inner input. We could + * represent these nodes by separate path nodes, but considering how many + * different merge paths are investigated during a complex join problem, + * it seems better to avoid unnecessary palloc overhead. + * + * path_mergeclauses lists the clauses (in the form of RestrictInfos) + * that will be used in the merge. + * + * Note that the mergeclauses are a subset of the parent relation's + * restriction-clause list. Any join clauses that are not mergejoinable + * appear only in the parent's restrict list, and must be checked by a + * qpqual at execution time. + * + * outersortkeys (resp. innersortkeys) is NIL if the outer path + * (resp. inner path) is already ordered appropriately for the + * mergejoin. If it is not NIL then it is a PathKeys list describing + * the ordering that must be created by an explicit Sort node. + * + * skip_mark_restore is true if the executor need not do mark/restore calls. + * Mark/restore overhead is usually required, but can be skipped if we know + * that the executor need find only one match per outer tuple, and that the + * mergeclauses are sufficient to identify a match. In such cases the + * executor can immediately advance the outer relation after processing a + * match, and therefore it need never back up the inner relation. + * + * materialize_inner is true if a Material node should be placed atop the + * inner input. This may appear with or without an inner Sort step. + */ + +typedef struct MergePath +{ + JoinPath jpath; + List *path_mergeclauses; /* join clauses to be used for merge */ + List *outersortkeys; /* keys for explicit sort, if any */ + List *innersortkeys; /* keys for explicit sort, if any */ + bool skip_mark_restore; /* can executor skip mark/restore? */ + bool materialize_inner; /* add Materialize to inner? */ +} MergePath; + +/* + * A hashjoin path has these fields. + * + * The remarks above for mergeclauses apply for hashclauses as well. + * + * Hashjoin does not care what order its inputs appear in, so we have + * no need for sortkeys. + */ + +typedef struct HashPath +{ + JoinPath jpath; + List *path_hashclauses; /* join clauses used for hashing */ + int num_batches; /* number of batches expected */ + Cardinality inner_rows_total; /* total inner rows expected */ +} HashPath; + +/* + * ProjectionPath represents a projection (that is, targetlist computation) + * + * Nominally, this path node represents using a Result plan node to do a + * projection step. However, if the input plan node supports projection, + * we can just modify its output targetlist to do the required calculations + * directly, and not need a Result. In some places in the planner we can just + * jam the desired PathTarget into the input path node (and adjust its cost + * accordingly), so we don't need a ProjectionPath. But in other places + * it's necessary to not modify the input path node, so we need a separate + * ProjectionPath node, which is marked dummy to indicate that we intend to + * assign the work to the input plan node. The estimated cost for the + * ProjectionPath node will account for whether a Result will be used or not. + */ +typedef struct ProjectionPath +{ + Path path; + Path *subpath; /* path representing input source */ + bool dummypp; /* true if no separate Result is needed */ +} ProjectionPath; + +/* + * ProjectSetPath represents evaluation of a targetlist that includes + * set-returning function(s), which will need to be implemented by a + * ProjectSet plan node. + */ +typedef struct ProjectSetPath +{ + Path path; + Path *subpath; /* path representing input source */ +} ProjectSetPath; + +/* + * SortPath represents an explicit sort step + * + * The sort keys are, by definition, the same as path.pathkeys. + * + * Note: the Sort plan node cannot project, so path.pathtarget must be the + * same as the input's pathtarget. + */ +typedef struct SortPath +{ + Path path; + Path *subpath; /* path representing input source */ +} SortPath; + +/* + * IncrementalSortPath represents an incremental sort step + * + * This is like a regular sort, except some leading key columns are assumed + * to be ordered already. + */ +typedef struct IncrementalSortPath +{ + SortPath spath; + int nPresortedCols; /* number of presorted columns */ +} IncrementalSortPath; + +/* + * GroupPath represents grouping (of presorted input) + * + * groupClause represents the columns to be grouped on; the input path + * must be at least that well sorted. + * + * We can also apply a qual to the grouped rows (equivalent of HAVING) + */ +typedef struct GroupPath +{ + Path path; + Path *subpath; /* path representing input source */ + List *groupClause; /* a list of SortGroupClause's */ + List *qual; /* quals (HAVING quals), if any */ +} GroupPath; + +/* + * UpperUniquePath represents adjacent-duplicate removal (in presorted input) + * + * The columns to be compared are the first numkeys columns of the path's + * pathkeys. The input is presumed already sorted that way. + */ +typedef struct UpperUniquePath +{ + Path path; + Path *subpath; /* path representing input source */ + int numkeys; /* number of pathkey columns to compare */ +} UpperUniquePath; + +/* + * AggPath represents generic computation of aggregate functions + * + * This may involve plain grouping (but not grouping sets), using either + * sorted or hashed grouping; for the AGG_SORTED case, the input must be + * appropriately presorted. + */ +typedef struct AggPath +{ + Path path; + Path *subpath; /* path representing input source */ + AggStrategy aggstrategy; /* basic strategy, see nodes.h */ + AggSplit aggsplit; /* agg-splitting mode, see nodes.h */ + Cardinality numGroups; /* estimated number of groups in input */ + uint64 transitionSpace; /* for pass-by-ref transition data */ + List *groupClause; /* a list of SortGroupClause's */ + List *qual; /* quals (HAVING quals), if any */ +} AggPath; + +/* + * Various annotations used for grouping sets in the planner. + */ + +typedef struct GroupingSetData +{ + pg_node_attr(no_copy_equal, no_read, no_query_jumble) + + NodeTag type; + List *set; /* grouping set as list of sortgrouprefs */ + Cardinality numGroups; /* est. number of result groups */ +} GroupingSetData; + +typedef struct RollupData +{ + pg_node_attr(no_copy_equal, no_read, no_query_jumble) + + NodeTag type; + List *groupClause; /* applicable subset of parse->groupClause */ + List *gsets; /* lists of integer indexes into groupClause */ + List *gsets_data; /* list of GroupingSetData */ + Cardinality numGroups; /* est. number of result groups */ + bool hashable; /* can be hashed */ + bool is_hashed; /* to be implemented as a hashagg */ +} RollupData; + +/* + * GroupingSetsPath represents a GROUPING SETS aggregation + */ + +typedef struct GroupingSetsPath +{ + Path path; + Path *subpath; /* path representing input source */ + AggStrategy aggstrategy; /* basic strategy */ + List *rollups; /* list of RollupData */ + List *qual; /* quals (HAVING quals), if any */ + uint64 transitionSpace; /* for pass-by-ref transition data */ +} GroupingSetsPath; + +/* + * MinMaxAggPath represents computation of MIN/MAX aggregates from indexes + */ +typedef struct MinMaxAggPath +{ + Path path; + List *mmaggregates; /* list of MinMaxAggInfo */ + List *quals; /* HAVING quals, if any */ +} MinMaxAggPath; + +/* + * WindowAggPath represents generic computation of window functions + */ +typedef struct WindowAggPath +{ + Path path; + Path *subpath; /* path representing input source */ + WindowClause *winclause; /* WindowClause we'll be using */ + List *qual; /* lower-level WindowAgg runconditions */ + bool topwindow; /* false for all apart from the WindowAgg + * that's closest to the root of the plan */ +} WindowAggPath; + +/* + * SetOpPath represents a set-operation, that is INTERSECT or EXCEPT + */ +typedef struct SetOpPath +{ + Path path; + Path *subpath; /* path representing input source */ + SetOpCmd cmd; /* what to do, see nodes.h */ + SetOpStrategy strategy; /* how to do it, see nodes.h */ + List *distinctList; /* SortGroupClauses identifying target cols */ + AttrNumber flagColIdx; /* where is the flag column, if any */ + int firstFlag; /* flag value for first input relation */ + Cardinality numGroups; /* estimated number of groups in input */ +} SetOpPath; + +/* + * RecursiveUnionPath represents a recursive UNION node + */ +typedef struct RecursiveUnionPath +{ + Path path; + Path *leftpath; /* paths representing input sources */ + Path *rightpath; + List *distinctList; /* SortGroupClauses identifying target cols */ + int wtParam; /* ID of Param representing work table */ + Cardinality numGroups; /* estimated number of groups in input */ +} RecursiveUnionPath; + +/* + * LockRowsPath represents acquiring row locks for SELECT FOR UPDATE/SHARE + */ +typedef struct LockRowsPath +{ + Path path; + Path *subpath; /* path representing input source */ + List *rowMarks; /* a list of PlanRowMark's */ + int epqParam; /* ID of Param for EvalPlanQual re-eval */ +} LockRowsPath; + +/* + * ModifyTablePath represents performing INSERT/UPDATE/DELETE/MERGE + * + * We represent most things that will be in the ModifyTable plan node + * literally, except we have a child Path not Plan. But analysis of the + * OnConflictExpr is deferred to createplan.c, as is collection of FDW data. + */ +typedef struct ModifyTablePath +{ + Path path; + Path *subpath; /* Path producing source data */ + CmdType operation; /* INSERT, UPDATE, DELETE, or MERGE */ + bool canSetTag; /* do we set the command tag/es_processed? */ + Index nominalRelation; /* Parent RT index for use of EXPLAIN */ + Index rootRelation; /* Root RT index, if partitioned/inherited */ + bool partColsUpdated; /* some part key in hierarchy updated? */ + List *resultRelations; /* integer list of RT indexes */ + List *updateColnosLists; /* per-target-table update_colnos lists */ + List *withCheckOptionLists; /* per-target-table WCO lists */ + List *returningLists; /* per-target-table RETURNING tlists */ + List *rowMarks; /* PlanRowMarks (non-locking only) */ + OnConflictExpr *onconflict; /* ON CONFLICT clause, or NULL */ + int epqParam; /* ID of Param for EvalPlanQual re-eval */ + List *mergeActionLists; /* per-target-table lists of actions for + * MERGE */ +} ModifyTablePath; + +/* + * LimitPath represents applying LIMIT/OFFSET restrictions + */ +typedef struct LimitPath +{ + Path path; + Path *subpath; /* path representing input source */ + Node *limitOffset; /* OFFSET parameter, or NULL if none */ + Node *limitCount; /* COUNT parameter, or NULL if none */ + LimitOption limitOption; /* FETCH FIRST with ties or exact number */ +} LimitPath; + + +/* + * Restriction clause info. + * + * We create one of these for each AND sub-clause of a restriction condition + * (WHERE or JOIN/ON clause). Since the restriction clauses are logically + * ANDed, we can use any one of them or any subset of them to filter out + * tuples, without having to evaluate the rest. The RestrictInfo node itself + * stores data used by the optimizer while choosing the best query plan. + * + * If a restriction clause references a single base relation, it will appear + * in the baserestrictinfo list of the RelOptInfo for that base rel. + * + * If a restriction clause references more than one base+OJ relation, it will + * appear in the joininfo list of every RelOptInfo that describes a strict + * subset of the relations mentioned in the clause. The joininfo lists are + * used to drive join tree building by selecting plausible join candidates. + * The clause cannot actually be applied until we have built a join rel + * containing all the relations it references, however. + * + * When we construct a join rel that includes all the relations referenced + * in a multi-relation restriction clause, we place that clause into the + * joinrestrictinfo lists of paths for the join rel, if neither left nor + * right sub-path includes all relations referenced in the clause. The clause + * will be applied at that join level, and will not propagate any further up + * the join tree. (Note: the "predicate migration" code was once intended to + * push restriction clauses up and down the plan tree based on evaluation + * costs, but it's dead code and is unlikely to be resurrected in the + * foreseeable future.) + * + * Note that in the presence of more than two rels, a multi-rel restriction + * might reach different heights in the join tree depending on the join + * sequence we use. So, these clauses cannot be associated directly with + * the join RelOptInfo, but must be kept track of on a per-join-path basis. + * + * RestrictInfos that represent equivalence conditions (i.e., mergejoinable + * equalities that are not outerjoin-delayed) are handled a bit differently. + * Initially we attach them to the EquivalenceClasses that are derived from + * them. When we construct a scan or join path, we look through all the + * EquivalenceClasses and generate derived RestrictInfos representing the + * minimal set of conditions that need to be checked for this particular scan + * or join to enforce that all members of each EquivalenceClass are in fact + * equal in all rows emitted by the scan or join. + * + * The clause_relids field lists the base plus outer-join RT indexes that + * actually appear in the clause. required_relids lists the minimum set of + * relids needed to evaluate the clause; while this is often equal to + * clause_relids, it can be more. We will add relids to required_relids when + * we need to force an outer join ON clause to be evaluated exactly at the + * level of the outer join, which is true except when it is a "degenerate" + * condition that references only Vars from the nullable side of the join. + * + * RestrictInfo nodes contain a flag to indicate whether a qual has been + * pushed down to a lower level than its original syntactic placement in the + * join tree would suggest. If an outer join prevents us from pushing a qual + * down to its "natural" semantic level (the level associated with just the + * base rels used in the qual) then we mark the qual with a "required_relids" + * value including more than just the base rels it actually uses. By + * pretending that the qual references all the rels required to form the outer + * join, we prevent it from being evaluated below the outer join's joinrel. + * When we do form the outer join's joinrel, we still need to distinguish + * those quals that are actually in that join's JOIN/ON condition from those + * that appeared elsewhere in the tree and were pushed down to the join rel + * because they used no other rels. That's what the is_pushed_down flag is + * for; it tells us that a qual is not an OUTER JOIN qual for the set of base + * rels listed in required_relids. A clause that originally came from WHERE + * or an INNER JOIN condition will *always* have its is_pushed_down flag set. + * It's possible for an OUTER JOIN clause to be marked is_pushed_down too, + * if we decide that it can be pushed down into the nullable side of the join. + * In that case it acts as a plain filter qual for wherever it gets evaluated. + * (In short, is_pushed_down is only false for non-degenerate outer join + * conditions. Possibly we should rename it to reflect that meaning? But + * see also the comments for RINFO_IS_PUSHED_DOWN, below.) + * + * There is also an incompatible_relids field, which is a set of outer-join + * relids above which we cannot evaluate the clause (because they might null + * Vars it uses that should not be nulled yet). In principle this could be + * filled in any RestrictInfo as the set of OJ relids that appear above the + * clause and null Vars that it uses. In practice we only bother to populate + * it for "clone" clauses, as it's currently only needed to prevent multiple + * clones of the same clause from being accepted for evaluation at the same + * join level. + * + * There is also an outer_relids field, which is NULL except for outer join + * clauses; for those, it is the set of relids on the outer side of the + * clause's outer join. (These are rels that the clause cannot be applied to + * in parameterized scans, since pushing it into the join's outer side would + * lead to wrong answers.) + * + * To handle security-barrier conditions efficiently, we mark RestrictInfo + * nodes with a security_level field, in which higher values identify clauses + * coming from less-trusted sources. The exact semantics are that a clause + * cannot be evaluated before another clause with a lower security_level value + * unless the first clause is leakproof. As with outer-join clauses, this + * creates a reason for clauses to sometimes need to be evaluated higher in + * the join tree than their contents would suggest; and even at a single plan + * node, this rule constrains the order of application of clauses. + * + * In general, the referenced clause might be arbitrarily complex. The + * kinds of clauses we can handle as indexscan quals, mergejoin clauses, + * or hashjoin clauses are limited (e.g., no volatile functions). The code + * for each kind of path is responsible for identifying the restrict clauses + * it can use and ignoring the rest. Clauses not implemented by an indexscan, + * mergejoin, or hashjoin will be placed in the plan qual or joinqual field + * of the finished Plan node, where they will be enforced by general-purpose + * qual-expression-evaluation code. (But we are still entitled to count + * their selectivity when estimating the result tuple count, if we + * can guess what it is...) + * + * When the referenced clause is an OR clause, we generate a modified copy + * in which additional RestrictInfo nodes are inserted below the top-level + * OR/AND structure. This is a convenience for OR indexscan processing: + * indexquals taken from either the top level or an OR subclause will have + * associated RestrictInfo nodes. + * + * The can_join flag is set true if the clause looks potentially useful as + * a merge or hash join clause, that is if it is a binary opclause with + * nonoverlapping sets of relids referenced in the left and right sides. + * (Whether the operator is actually merge or hash joinable isn't checked, + * however.) + * + * The pseudoconstant flag is set true if the clause contains no Vars of + * the current query level and no volatile functions. Such a clause can be + * pulled out and used as a one-time qual in a gating Result node. We keep + * pseudoconstant clauses in the same lists as other RestrictInfos so that + * the regular clause-pushing machinery can assign them to the correct join + * level, but they need to be treated specially for cost and selectivity + * estimates. Note that a pseudoconstant clause can never be an indexqual + * or merge or hash join clause, so it's of no interest to large parts of + * the planner. + * + * When we generate multiple versions of a clause so as to have versions + * that will work after commuting some left joins per outer join identity 3, + * we mark the one with the fewest nullingrels bits with has_clone = true, + * and the rest with is_clone = true. This allows proper filtering of + * these redundant clauses, so that we apply only one version of them. + * + * When join clauses are generated from EquivalenceClasses, there may be + * several equally valid ways to enforce join equivalence, of which we need + * apply only one. We mark clauses of this kind by setting parent_ec to + * point to the generating EquivalenceClass. Multiple clauses with the same + * parent_ec in the same join are redundant. + * + * Most fields are ignored for equality, since they may not be set yet, and + * should be derivable from the clause anyway. + * + * parent_ec, left_ec, right_ec are not printed, lest it lead to infinite + * recursion in plan tree dump. + */ + +typedef struct RestrictInfo +{ + pg_node_attr(no_read, no_query_jumble) + + NodeTag type; + + /* the represented clause of WHERE or JOIN */ + Expr *clause; + + /* true if clause was pushed down in level */ + bool is_pushed_down; + + /* see comment above */ + bool can_join pg_node_attr(equal_ignore); + + /* see comment above */ + bool pseudoconstant pg_node_attr(equal_ignore); + + /* see comment above */ + bool has_clone; + bool is_clone; + + /* true if known to contain no leaked Vars */ + bool leakproof pg_node_attr(equal_ignore); + + /* indicates if clause contains any volatile functions */ + VolatileFunctionStatus has_volatile pg_node_attr(equal_ignore); + + /* see comment above */ + Index security_level; + + /* number of base rels in clause_relids */ + int num_base_rels pg_node_attr(equal_ignore); + + /* The relids (varnos+varnullingrels) actually referenced in the clause: */ + Relids clause_relids pg_node_attr(equal_ignore); + + /* The set of relids required to evaluate the clause: */ + Relids required_relids; + + /* Relids above which we cannot evaluate the clause (see comment above) */ + Relids incompatible_relids; + + /* If an outer-join clause, the outer-side relations, else NULL: */ + Relids outer_relids; + + /* + * Relids in the left/right side of the clause. These fields are set for + * any binary opclause. + */ + Relids left_relids pg_node_attr(equal_ignore); + Relids right_relids pg_node_attr(equal_ignore); + + /* + * Modified clause with RestrictInfos. This field is NULL unless clause + * is an OR clause. + */ + Expr *orclause pg_node_attr(equal_ignore); + + /*---------- + * Serial number of this RestrictInfo. This is unique within the current + * PlannerInfo context, with a few critical exceptions: + * 1. When we generate multiple clones of the same qual condition to + * cope with outer join identity 3, all the clones get the same serial + * number. This reflects that we only want to apply one of them in any + * given plan. + * 2. If we manufacture a commuted version of a qual to use as an index + * condition, it copies the original's rinfo_serial, since it is in + * practice the same condition. + * 3. RestrictInfos made for a child relation copy their parent's + * rinfo_serial. Likewise, when an EquivalenceClass makes a derived + * equality clause for a child relation, it copies the rinfo_serial of + * the matching equality clause for the parent. This allows detection + * of redundant pushed-down equality clauses. + *---------- + */ + int rinfo_serial; + + /* + * Generating EquivalenceClass. This field is NULL unless clause is + * potentially redundant. + */ + EquivalenceClass *parent_ec pg_node_attr(copy_as_scalar, equal_ignore, read_write_ignore); + + /* + * cache space for cost and selectivity + */ + + /* eval cost of clause; -1 if not yet set */ + QualCost eval_cost pg_node_attr(equal_ignore); + + /* selectivity for "normal" (JOIN_INNER) semantics; -1 if not yet set */ + Selectivity norm_selec pg_node_attr(equal_ignore); + /* selectivity for outer join semantics; -1 if not yet set */ + Selectivity outer_selec pg_node_attr(equal_ignore); + + /* + * opfamilies containing clause operator; valid if clause is + * mergejoinable, else NIL + */ + List *mergeopfamilies pg_node_attr(equal_ignore); + + /* + * cache space for mergeclause processing; NULL if not yet set + */ + + /* EquivalenceClass containing lefthand */ + EquivalenceClass *left_ec pg_node_attr(copy_as_scalar, equal_ignore, read_write_ignore); + /* EquivalenceClass containing righthand */ + EquivalenceClass *right_ec pg_node_attr(copy_as_scalar, equal_ignore, read_write_ignore); + /* EquivalenceMember for lefthand */ + EquivalenceMember *left_em pg_node_attr(copy_as_scalar, equal_ignore); + /* EquivalenceMember for righthand */ + EquivalenceMember *right_em pg_node_attr(copy_as_scalar, equal_ignore); + + /* + * List of MergeScanSelCache structs. Those aren't Nodes, so hard to + * copy; instead replace with NIL. That has the effect that copying will + * just reset the cache. Likewise, can't compare or print them. + */ + List *scansel_cache pg_node_attr(copy_as(NIL), equal_ignore, read_write_ignore); + + /* + * transient workspace for use while considering a specific join path; T = + * outer var on left, F = on right + */ + bool outer_is_left pg_node_attr(equal_ignore); + + /* + * copy of clause operator; valid if clause is hashjoinable, else + * InvalidOid + */ + Oid hashjoinoperator pg_node_attr(equal_ignore); + + /* + * cache space for hashclause processing; -1 if not yet set + */ + /* avg bucketsize of left side */ + Selectivity left_bucketsize pg_node_attr(equal_ignore); + /* avg bucketsize of right side */ + Selectivity right_bucketsize pg_node_attr(equal_ignore); + /* left side's most common val's freq */ + Selectivity left_mcvfreq pg_node_attr(equal_ignore); + /* right side's most common val's freq */ + Selectivity right_mcvfreq pg_node_attr(equal_ignore); + + /* hash equality operators used for memoize nodes, else InvalidOid */ + Oid left_hasheqoperator pg_node_attr(equal_ignore); + Oid right_hasheqoperator pg_node_attr(equal_ignore); +} RestrictInfo; + +/* + * This macro embodies the correct way to test whether a RestrictInfo is + * "pushed down" to a given outer join, that is, should be treated as a filter + * clause rather than a join clause at that outer join. This is certainly so + * if is_pushed_down is true; but examining that is not sufficient anymore, + * because outer-join clauses will get pushed down to lower outer joins when + * we generate a path for the lower outer join that is parameterized by the + * LHS of the upper one. We can detect such a clause by noting that its + * required_relids exceed the scope of the join. + */ +#define RINFO_IS_PUSHED_DOWN(rinfo, joinrelids) \ + ((rinfo)->is_pushed_down || \ + !bms_is_subset((rinfo)->required_relids, joinrelids)) + +/* + * Since mergejoinscansel() is a relatively expensive function, and would + * otherwise be invoked many times while planning a large join tree, + * we go out of our way to cache its results. Each mergejoinable + * RestrictInfo carries a list of the specific sort orderings that have + * been considered for use with it, and the resulting selectivities. + */ +typedef struct MergeScanSelCache +{ + /* Ordering details (cache lookup key) */ + Oid opfamily; /* btree opfamily defining the ordering */ + Oid collation; /* collation for the ordering */ + int strategy; /* sort direction (ASC or DESC) */ + bool nulls_first; /* do NULLs come before normal values? */ + /* Results */ + Selectivity leftstartsel; /* first-join fraction for clause left side */ + Selectivity leftendsel; /* last-join fraction for clause left side */ + Selectivity rightstartsel; /* first-join fraction for clause right side */ + Selectivity rightendsel; /* last-join fraction for clause right side */ +} MergeScanSelCache; + +/* + * Placeholder node for an expression to be evaluated below the top level + * of a plan tree. This is used during planning to represent the contained + * expression. At the end of the planning process it is replaced by either + * the contained expression or a Var referring to a lower-level evaluation of + * the contained expression. Generally the evaluation occurs below an outer + * join, and Var references above the outer join might thereby yield NULL + * instead of the expression value. + * + * phrels and phlevelsup correspond to the varno/varlevelsup fields of a + * plain Var, except that phrels has to be a relid set since the evaluation + * level of a PlaceHolderVar might be a join rather than a base relation. + * Likewise, phnullingrels corresponds to varnullingrels. + * + * Although the planner treats this as an expression node type, it is not + * recognized by the parser or executor, so we declare it here rather than + * in primnodes.h. + * + * We intentionally do not compare phexpr. Two PlaceHolderVars with the + * same ID and levelsup should be considered equal even if the contained + * expressions have managed to mutate to different states. This will + * happen during final plan construction when there are nested PHVs, since + * the inner PHV will get replaced by a Param in some copies of the outer + * PHV. Another way in which it can happen is that initplan sublinks + * could get replaced by differently-numbered Params when sublink folding + * is done. (The end result of such a situation would be some + * unreferenced initplans, which is annoying but not really a problem.) + * On the same reasoning, there is no need to examine phrels. But we do + * need to compare phnullingrels, as that represents effects that are + * external to the original value of the PHV. + */ + +typedef struct PlaceHolderVar +{ + pg_node_attr(no_query_jumble) + + Expr xpr; + + /* the represented expression */ + Expr *phexpr pg_node_attr(equal_ignore); + + /* base+OJ relids syntactically within expr src */ + Relids phrels pg_node_attr(equal_ignore); + + /* RT indexes of outer joins that can null PHV's value */ + Relids phnullingrels; + + /* ID for PHV (unique within planner run) */ + Index phid; + + /* > 0 if PHV belongs to outer query */ + Index phlevelsup; +} PlaceHolderVar; + +/* + * "Special join" info. + * + * One-sided outer joins constrain the order of joining partially but not + * completely. We flatten such joins into the planner's top-level list of + * relations to join, but record information about each outer join in a + * SpecialJoinInfo struct. These structs are kept in the PlannerInfo node's + * join_info_list. + * + * Similarly, semijoins and antijoins created by flattening IN (subselect) + * and EXISTS(subselect) clauses create partial constraints on join order. + * These are likewise recorded in SpecialJoinInfo structs. + * + * We make SpecialJoinInfos for FULL JOINs even though there is no flexibility + * of planning for them, because this simplifies make_join_rel()'s API. + * + * min_lefthand and min_righthand are the sets of base+OJ relids that must be + * available on each side when performing the special join. + * It is not valid for either min_lefthand or min_righthand to be empty sets; + * if they were, this would break the logic that enforces join order. + * + * syn_lefthand and syn_righthand are the sets of base+OJ relids that are + * syntactically below this special join. (These are needed to help compute + * min_lefthand and min_righthand for higher joins.) + * + * jointype is never JOIN_RIGHT; a RIGHT JOIN is handled by switching + * the inputs to make it a LEFT JOIN. It's never JOIN_RIGHT_ANTI either. + * So the allowed values of jointype in a join_info_list member are only + * LEFT, FULL, SEMI, or ANTI. + * + * ojrelid is the RT index of the join RTE representing this outer join, + * if there is one. It is zero when jointype is INNER or SEMI, and can be + * zero for jointype ANTI (if the join was transformed from a SEMI join). + * One use for this field is that when constructing the output targetlist of a + * join relation that implements this OJ, we add ojrelid to the varnullingrels + * and phnullingrels fields of nullable (RHS) output columns, so that the + * output Vars and PlaceHolderVars correctly reflect the nulling that has + * potentially happened to them. + * + * commute_above_l is filled with the relids of syntactically-higher outer + * joins that have been found to commute with this one per outer join identity + * 3 (see optimizer/README), when this join is in the LHS of the upper join + * (so, this is the lower join in the first form of the identity). + * + * commute_above_r is filled with the relids of syntactically-higher outer + * joins that have been found to commute with this one per outer join identity + * 3, when this join is in the RHS of the upper join (so, this is the lower + * join in the second form of the identity). + * + * commute_below_l is filled with the relids of syntactically-lower outer + * joins that have been found to commute with this one per outer join identity + * 3 and are in the LHS of this join (so, this is the upper join in the first + * form of the identity). + * + * commute_below_r is filled with the relids of syntactically-lower outer + * joins that have been found to commute with this one per outer join identity + * 3 and are in the RHS of this join (so, this is the upper join in the second + * form of the identity). + * + * lhs_strict is true if the special join's condition cannot succeed when the + * LHS variables are all NULL (this means that an outer join can commute with + * upper-level outer joins even if it appears in their RHS). We don't bother + * to set lhs_strict for FULL JOINs, however. + * + * For a semijoin, we also extract the join operators and their RHS arguments + * and set semi_operators, semi_rhs_exprs, semi_can_btree, and semi_can_hash. + * This is done in support of possibly unique-ifying the RHS, so we don't + * bother unless at least one of semi_can_btree and semi_can_hash can be set + * true. (You might expect that this information would be computed during + * join planning; but it's helpful to have it available during planning of + * parameterized table scans, so we store it in the SpecialJoinInfo structs.) + * + * For purposes of join selectivity estimation, we create transient + * SpecialJoinInfo structures for regular inner joins; so it is possible + * to have jointype == JOIN_INNER in such a structure, even though this is + * not allowed within join_info_list. We also create transient + * SpecialJoinInfos with jointype == JOIN_INNER for outer joins, since for + * cost estimation purposes it is sometimes useful to know the join size under + * plain innerjoin semantics. Note that lhs_strict and the semi_xxx fields + * are not set meaningfully within such structs. + */ +#ifndef HAVE_SPECIALJOININFO_TYPEDEF +typedef struct SpecialJoinInfo SpecialJoinInfo; +#define HAVE_SPECIALJOININFO_TYPEDEF 1 +#endif + +struct SpecialJoinInfo +{ + pg_node_attr(no_read, no_query_jumble) + + NodeTag type; + Relids min_lefthand; /* base+OJ relids in minimum LHS for join */ + Relids min_righthand; /* base+OJ relids in minimum RHS for join */ + Relids syn_lefthand; /* base+OJ relids syntactically within LHS */ + Relids syn_righthand; /* base+OJ relids syntactically within RHS */ + JoinType jointype; /* always INNER, LEFT, FULL, SEMI, or ANTI */ + Index ojrelid; /* outer join's RT index; 0 if none */ + Relids commute_above_l; /* commuting OJs above this one, if LHS */ + Relids commute_above_r; /* commuting OJs above this one, if RHS */ + Relids commute_below_l; /* commuting OJs in this one's LHS */ + Relids commute_below_r; /* commuting OJs in this one's RHS */ + bool lhs_strict; /* joinclause is strict for some LHS rel */ + /* Remaining fields are set only for JOIN_SEMI jointype: */ + bool semi_can_btree; /* true if semi_operators are all btree */ + bool semi_can_hash; /* true if semi_operators are all hash */ + List *semi_operators; /* OIDs of equality join operators */ + List *semi_rhs_exprs; /* righthand-side expressions of these ops */ +}; + +/* + * Transient outer-join clause info. + * + * We set aside every outer join ON clause that looks mergejoinable, + * and process it specially at the end of qual distribution. + */ +typedef struct OuterJoinClauseInfo +{ + pg_node_attr(no_copy_equal, no_read, no_query_jumble) + + NodeTag type; + RestrictInfo *rinfo; /* a mergejoinable outer-join clause */ + SpecialJoinInfo *sjinfo; /* the outer join's SpecialJoinInfo */ +} OuterJoinClauseInfo; + +/* + * Append-relation info. + * + * When we expand an inheritable table or a UNION-ALL subselect into an + * "append relation" (essentially, a list of child RTEs), we build an + * AppendRelInfo for each child RTE. The list of AppendRelInfos indicates + * which child RTEs must be included when expanding the parent, and each node + * carries information needed to translate between columns of the parent and + * columns of the child. + * + * These structs are kept in the PlannerInfo node's append_rel_list, with + * append_rel_array[] providing a convenient lookup method for the struct + * associated with a particular child relid (there can be only one, though + * parent rels may have many entries in append_rel_list). + * + * Note: after completion of the planner prep phase, any given RTE is an + * append parent having entries in append_rel_list if and only if its + * "inh" flag is set. We clear "inh" for plain tables that turn out not + * to have inheritance children, and (in an abuse of the original meaning + * of the flag) we set "inh" for subquery RTEs that turn out to be + * flattenable UNION ALL queries. This lets us avoid useless searches + * of append_rel_list. + * + * Note: the data structure assumes that append-rel members are single + * baserels. This is OK for inheritance, but it prevents us from pulling + * up a UNION ALL member subquery if it contains a join. While that could + * be fixed with a more complex data structure, at present there's not much + * point because no improvement in the plan could result. + */ + +typedef struct AppendRelInfo +{ + pg_node_attr(no_query_jumble) + + NodeTag type; + + /* + * These fields uniquely identify this append relationship. There can be + * (in fact, always should be) multiple AppendRelInfos for the same + * parent_relid, but never more than one per child_relid, since a given + * RTE cannot be a child of more than one append parent. + */ + Index parent_relid; /* RT index of append parent rel */ + Index child_relid; /* RT index of append child rel */ + + /* + * For an inheritance appendrel, the parent and child are both regular + * relations, and we store their rowtype OIDs here for use in translating + * whole-row Vars. For a UNION-ALL appendrel, the parent and child are + * both subqueries with no named rowtype, and we store InvalidOid here. + */ + Oid parent_reltype; /* OID of parent's composite type */ + Oid child_reltype; /* OID of child's composite type */ + + /* + * The N'th element of this list is a Var or expression representing the + * child column corresponding to the N'th column of the parent. This is + * used to translate Vars referencing the parent rel into references to + * the child. A list element is NULL if it corresponds to a dropped + * column of the parent (this is only possible for inheritance cases, not + * UNION ALL). The list elements are always simple Vars for inheritance + * cases, but can be arbitrary expressions in UNION ALL cases. + * + * Notice we only store entries for user columns (attno > 0). Whole-row + * Vars are special-cased, and system columns (attno < 0) need no special + * translation since their attnos are the same for all tables. + * + * Caution: the Vars have varlevelsup = 0. Be careful to adjust as needed + * when copying into a subquery. + */ + List *translated_vars; /* Expressions in the child's Vars */ + + /* + * This array simplifies translations in the reverse direction, from + * child's column numbers to parent's. The entry at [ccolno - 1] is the + * 1-based parent column number for child column ccolno, or zero if that + * child column is dropped or doesn't exist in the parent. + */ + int num_child_cols; /* length of array */ + AttrNumber *parent_colnos pg_node_attr(array_size(num_child_cols)); + + /* + * We store the parent table's OID here for inheritance, or InvalidOid for + * UNION ALL. This is only needed to help in generating error messages if + * an attempt is made to reference a dropped parent column. + */ + Oid parent_reloid; /* OID of parent relation */ +} AppendRelInfo; + +/* + * Information about a row-identity "resjunk" column in UPDATE/DELETE/MERGE. + * + * In partitioned UPDATE/DELETE/MERGE it's important for child partitions to + * share row-identity columns whenever possible, so as not to chew up too many + * targetlist columns. We use these structs to track which identity columns + * have been requested. In the finished plan, each of these will give rise + * to one resjunk entry in the targetlist of the ModifyTable's subplan node. + * + * All the Vars stored in RowIdentityVarInfos must have varno ROWID_VAR, for + * convenience of detecting duplicate requests. We'll replace that, in the + * final plan, with the varno of the generating rel. + * + * Outside this list, a Var with varno ROWID_VAR and varattno k is a reference + * to the k-th element of the row_identity_vars list (k counting from 1). + * We add such a reference to root->processed_tlist when creating the entry, + * and it propagates into the plan tree from there. + */ +typedef struct RowIdentityVarInfo +{ + pg_node_attr(no_copy_equal, no_read, no_query_jumble) + + NodeTag type; + + Var *rowidvar; /* Var to be evaluated (but varno=ROWID_VAR) */ + int32 rowidwidth; /* estimated average width */ + char *rowidname; /* name of the resjunk column */ + Relids rowidrels; /* RTE indexes of target rels using this */ +} RowIdentityVarInfo; + +/* + * For each distinct placeholder expression generated during planning, we + * store a PlaceHolderInfo node in the PlannerInfo node's placeholder_list. + * This stores info that is needed centrally rather than in each copy of the + * PlaceHolderVar. The phid fields identify which PlaceHolderInfo goes with + * each PlaceHolderVar. Note that phid is unique throughout a planner run, + * not just within a query level --- this is so that we need not reassign ID's + * when pulling a subquery into its parent. + * + * The idea is to evaluate the expression at (only) the ph_eval_at join level, + * then allow it to bubble up like a Var until the ph_needed join level. + * ph_needed has the same definition as attr_needed for a regular Var. + * + * The PlaceHolderVar's expression might contain LATERAL references to vars + * coming from outside its syntactic scope. If so, those rels are *not* + * included in ph_eval_at, but they are recorded in ph_lateral. + * + * Notice that when ph_eval_at is a join rather than a single baserel, the + * PlaceHolderInfo may create constraints on join order: the ph_eval_at join + * has to be formed below any outer joins that should null the PlaceHolderVar. + * + * We create a PlaceHolderInfo only after determining that the PlaceHolderVar + * is actually referenced in the plan tree, so that unreferenced placeholders + * don't result in unnecessary constraints on join order. + */ + +typedef struct PlaceHolderInfo +{ + pg_node_attr(no_read, no_query_jumble) + + NodeTag type; + + /* ID for PH (unique within planner run) */ + Index phid; + + /* + * copy of PlaceHolderVar tree (should be redundant for comparison, could + * be ignored) + */ + PlaceHolderVar *ph_var; + + /* lowest level we can evaluate value at */ + Relids ph_eval_at; + + /* relids of contained lateral refs, if any */ + Relids ph_lateral; + + /* highest level the value is needed at */ + Relids ph_needed; + + /* estimated attribute width */ + int32 ph_width; +} PlaceHolderInfo; + +/* + * This struct describes one potentially index-optimizable MIN/MAX aggregate + * function. MinMaxAggPath contains a list of these, and if we accept that + * path, the list is stored into root->minmax_aggs for use during setrefs.c. + */ +typedef struct MinMaxAggInfo +{ + pg_node_attr(no_copy_equal, no_read, no_query_jumble) + + NodeTag type; + + /* pg_proc Oid of the aggregate */ + Oid aggfnoid; + + /* Oid of its sort operator */ + Oid aggsortop; + + /* expression we are aggregating on */ + Expr *target; + + /* + * modified "root" for planning the subquery; not printed, too large, not + * interesting enough + */ + PlannerInfo *subroot pg_node_attr(read_write_ignore); + + /* access path for subquery */ + Path *path; + + /* estimated cost to fetch first row */ + Cost pathcost; + + /* param for subplan's output */ + Param *param; +} MinMaxAggInfo; + +/* + * At runtime, PARAM_EXEC slots are used to pass values around from one plan + * node to another. They can be used to pass values down into subqueries (for + * outer references in subqueries), or up out of subqueries (for the results + * of a subplan), or from a NestLoop plan node into its inner relation (when + * the inner scan is parameterized with values from the outer relation). + * The planner is responsible for assigning nonconflicting PARAM_EXEC IDs to + * the PARAM_EXEC Params it generates. + * + * Outer references are managed via root->plan_params, which is a list of + * PlannerParamItems. While planning a subquery, each parent query level's + * plan_params contains the values required from it by the current subquery. + * During create_plan(), we use plan_params to track values that must be + * passed from outer to inner sides of NestLoop plan nodes. + * + * The item a PlannerParamItem represents can be one of three kinds: + * + * A Var: the slot represents a variable of this level that must be passed + * down because subqueries have outer references to it, or must be passed + * from a NestLoop node to its inner scan. The varlevelsup value in the Var + * will always be zero. + * + * A PlaceHolderVar: this works much like the Var case, except that the + * entry is a PlaceHolderVar node with a contained expression. The PHV + * will have phlevelsup = 0, and the contained expression is adjusted + * to match in level. + * + * An Aggref (with an expression tree representing its argument): the slot + * represents an aggregate expression that is an outer reference for some + * subquery. The Aggref itself has agglevelsup = 0, and its argument tree + * is adjusted to match in level. + * + * Note: we detect duplicate Var and PlaceHolderVar parameters and coalesce + * them into one slot, but we do not bother to do that for Aggrefs. + * The scope of duplicate-elimination only extends across the set of + * parameters passed from one query level into a single subquery, or for + * nestloop parameters across the set of nestloop parameters used in a single + * query level. So there is no possibility of a PARAM_EXEC slot being used + * for conflicting purposes. + * + * In addition, PARAM_EXEC slots are assigned for Params representing outputs + * from subplans (values that are setParam items for those subplans). These + * IDs need not be tracked via PlannerParamItems, since we do not need any + * duplicate-elimination nor later processing of the represented expressions. + * Instead, we just record the assignment of the slot number by appending to + * root->glob->paramExecTypes. + */ +typedef struct PlannerParamItem +{ + pg_node_attr(no_copy_equal, no_read, no_query_jumble) + + NodeTag type; + + Node *item; /* the Var, PlaceHolderVar, or Aggref */ + int paramId; /* its assigned PARAM_EXEC slot number */ +} PlannerParamItem; + +/* + * When making cost estimates for a SEMI/ANTI/inner_unique join, there are + * some correction factors that are needed in both nestloop and hash joins + * to account for the fact that the executor can stop scanning inner rows + * as soon as it finds a match to the current outer row. These numbers + * depend only on the selected outer and inner join relations, not on the + * particular paths used for them, so it's worthwhile to calculate them + * just once per relation pair not once per considered path. This struct + * is filled by compute_semi_anti_join_factors and must be passed along + * to the join cost estimation functions. + * + * outer_match_frac is the fraction of the outer tuples that are + * expected to have at least one match. + * match_count is the average number of matches expected for + * outer tuples that have at least one match. + */ +typedef struct SemiAntiJoinFactors +{ + Selectivity outer_match_frac; + Selectivity match_count; +} SemiAntiJoinFactors; + +/* + * Struct for extra information passed to subroutines of add_paths_to_joinrel + * + * restrictlist contains all of the RestrictInfo nodes for restriction + * clauses that apply to this join + * mergeclause_list is a list of RestrictInfo nodes for available + * mergejoin clauses in this join + * inner_unique is true if each outer tuple provably matches no more + * than one inner tuple + * sjinfo is extra info about special joins for selectivity estimation + * semifactors is as shown above (only valid for SEMI/ANTI/inner_unique joins) + * param_source_rels are OK targets for parameterization of result paths + */ +typedef struct JoinPathExtraData +{ + List *restrictlist; + List *mergeclause_list; + bool inner_unique; + SpecialJoinInfo *sjinfo; + SemiAntiJoinFactors semifactors; + Relids param_source_rels; +} JoinPathExtraData; + +/* + * Various flags indicating what kinds of grouping are possible. + * + * GROUPING_CAN_USE_SORT should be set if it's possible to perform + * sort-based implementations of grouping. When grouping sets are in use, + * this will be true if sorting is potentially usable for any of the grouping + * sets, even if it's not usable for all of them. + * + * GROUPING_CAN_USE_HASH should be set if it's possible to perform + * hash-based implementations of grouping. + * + * GROUPING_CAN_PARTIAL_AGG should be set if the aggregation is of a type + * for which we support partial aggregation (not, for example, grouping sets). + * It says nothing about parallel-safety or the availability of suitable paths. + */ +#define GROUPING_CAN_USE_SORT 0x0001 +#define GROUPING_CAN_USE_HASH 0x0002 +#define GROUPING_CAN_PARTIAL_AGG 0x0004 + +/* + * What kind of partitionwise aggregation is in use? + * + * PARTITIONWISE_AGGREGATE_NONE: Not used. + * + * PARTITIONWISE_AGGREGATE_FULL: Aggregate each partition separately, and + * append the results. + * + * PARTITIONWISE_AGGREGATE_PARTIAL: Partially aggregate each partition + * separately, append the results, and then finalize aggregation. + */ +typedef enum +{ + PARTITIONWISE_AGGREGATE_NONE, + PARTITIONWISE_AGGREGATE_FULL, + PARTITIONWISE_AGGREGATE_PARTIAL +} PartitionwiseAggregateType; + +/* + * Struct for extra information passed to subroutines of create_grouping_paths + * + * flags indicating what kinds of grouping are possible. + * partial_costs_set is true if the agg_partial_costs and agg_final_costs + * have been initialized. + * agg_partial_costs gives partial aggregation costs. + * agg_final_costs gives finalization costs. + * target_parallel_safe is true if target is parallel safe. + * havingQual gives list of quals to be applied after aggregation. + * targetList gives list of columns to be projected. + * patype is the type of partitionwise aggregation that is being performed. + */ +typedef struct +{ + /* Data which remains constant once set. */ + int flags; + bool partial_costs_set; + AggClauseCosts agg_partial_costs; + AggClauseCosts agg_final_costs; + + /* Data which may differ across partitions. */ + bool target_parallel_safe; + Node *havingQual; + List *targetList; + PartitionwiseAggregateType patype; +} GroupPathExtraData; + +/* + * Struct for extra information passed to subroutines of grouping_planner + * + * limit_needed is true if we actually need a Limit plan node. + * limit_tuples is an estimated bound on the number of output tuples, + * or -1 if no LIMIT or couldn't estimate. + * count_est and offset_est are the estimated values of the LIMIT and OFFSET + * expressions computed by preprocess_limit() (see comments for + * preprocess_limit() for more information). + */ +typedef struct +{ + bool limit_needed; + Cardinality limit_tuples; + int64 count_est; + int64 offset_est; +} FinalPathExtraData; + +/* + * For speed reasons, cost estimation for join paths is performed in two + * phases: the first phase tries to quickly derive a lower bound for the + * join cost, and then we check if that's sufficient to reject the path. + * If not, we come back for a more refined cost estimate. The first phase + * fills a JoinCostWorkspace struct with its preliminary cost estimates + * and possibly additional intermediate values. The second phase takes + * these values as inputs to avoid repeating work. + * + * (Ideally we'd declare this in cost.h, but it's also needed in pathnode.h, + * so seems best to put it here.) + */ +typedef struct JoinCostWorkspace +{ + /* Preliminary cost estimates --- must not be larger than final ones! */ + Cost startup_cost; /* cost expended before fetching any tuples */ + Cost total_cost; /* total cost (assuming all tuples fetched) */ + + /* Fields below here should be treated as private to costsize.c */ + Cost run_cost; /* non-startup cost components */ + + /* private for cost_nestloop code */ + Cost inner_run_cost; /* also used by cost_mergejoin code */ + Cost inner_rescan_run_cost; + + /* private for cost_mergejoin code */ + Cardinality outer_rows; + Cardinality inner_rows; + Cardinality outer_skip_rows; + Cardinality inner_skip_rows; + + /* private for cost_hashjoin code */ + int numbuckets; + int numbatches; + Cardinality inner_rows_total; +} JoinCostWorkspace; + +/* + * AggInfo holds information about an aggregate that needs to be computed. + * Multiple Aggrefs in a query can refer to the same AggInfo by having the + * same 'aggno' value, so that the aggregate is computed only once. + */ +typedef struct AggInfo +{ + pg_node_attr(no_copy_equal, no_read, no_query_jumble) + + NodeTag type; + + /* + * List of Aggref exprs that this state value is for. + * + * There will always be at least one, but there can be multiple identical + * Aggref's sharing the same per-agg. + */ + List *aggrefs; + + /* Transition state number for this aggregate */ + int transno; + + /* + * "shareable" is false if this agg cannot share state values with other + * aggregates because the final function is read-write. + */ + bool shareable; + + /* Oid of the final function, or InvalidOid if none */ + Oid finalfn_oid; +} AggInfo; + +/* + * AggTransInfo holds information about transition state that is used by one + * or more aggregates in the query. Multiple aggregates can share the same + * transition state, if they have the same inputs and the same transition + * function. Aggrefs that share the same transition info have the same + * 'aggtransno' value. + */ +typedef struct AggTransInfo +{ + pg_node_attr(no_copy_equal, no_read, no_query_jumble) + + NodeTag type; + + /* Inputs for this transition state */ + List *args; + Expr *aggfilter; + + /* Oid of the state transition function */ + Oid transfn_oid; + + /* Oid of the serialization function, or InvalidOid if none */ + Oid serialfn_oid; + + /* Oid of the deserialization function, or InvalidOid if none */ + Oid deserialfn_oid; + + /* Oid of the combine function, or InvalidOid if none */ + Oid combinefn_oid; + + /* Oid of state value's datatype */ + Oid aggtranstype; + + /* Additional data about transtype */ + int32 aggtranstypmod; + int transtypeLen; + bool transtypeByVal; + + /* Space-consumption estimate */ + int32 aggtransspace; + + /* Initial value from pg_aggregate entry */ + Datum initValue pg_node_attr(read_write_ignore); + bool initValueIsNull; +} AggTransInfo; + +#endif /* PATHNODES_H */ diff --git a/src/include/nodes/pg_list.h b/src/include/nodes/pg_list.h new file mode 100644 index 0000000..529a382 --- /dev/null +++ b/src/include/nodes/pg_list.h @@ -0,0 +1,635 @@ +/*------------------------------------------------------------------------- + * + * pg_list.h + * interface for PostgreSQL generic list package + * + * Once upon a time, parts of Postgres were written in Lisp and used real + * cons-cell lists for major data structures. When that code was rewritten + * in C, we initially had a faithful emulation of cons-cell lists, which + * unsurprisingly was a performance bottleneck. A couple of major rewrites + * later, these data structures are actually simple expansible arrays; + * but the "List" name and a lot of the notation survives. + * + * One important concession to the original implementation is that an empty + * list is always represented by a null pointer (preferentially written NIL). + * Non-empty lists have a header, which will not be relocated as long as the + * list remains non-empty, and an expansible data array. + * + * We support four types of lists: + * + * T_List: lists of pointers + * (in practice usually pointers to Nodes, but not always; + * declared as "void *" to minimize casting annoyances) + * T_IntList: lists of integers + * T_OidList: lists of Oids + * T_XidList: lists of TransactionIds + * (the XidList infrastructure is less complete than the other cases) + * + * (At the moment, ints, Oids, and XIDs are the same size, but they may not + * always be so; be careful to use the appropriate list type for your data.) + * + * + * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/nodes/pg_list.h + * + *------------------------------------------------------------------------- + */ +#ifndef PG_LIST_H +#define PG_LIST_H + +#include "nodes/nodes.h" + + +typedef union ListCell +{ + void *ptr_value; + int int_value; + Oid oid_value; + TransactionId xid_value; +} ListCell; + +typedef struct List +{ + NodeTag type; /* T_List, T_IntList, T_OidList, or T_XidList */ + int length; /* number of elements currently present */ + int max_length; /* allocated length of elements[] */ + ListCell *elements; /* re-allocatable array of cells */ + /* We may allocate some cells along with the List header: */ + ListCell initial_elements[FLEXIBLE_ARRAY_MEMBER]; + /* If elements == initial_elements, it's not a separate allocation */ +} List; + +/* + * The *only* valid representation of an empty list is NIL; in other + * words, a non-NIL list is guaranteed to have length >= 1. + */ +#define NIL ((List *) NULL) + +/* + * State structs for various looping macros below. + */ +typedef struct ForEachState +{ + const List *l; /* list we're looping through */ + int i; /* current element index */ +} ForEachState; + +typedef struct ForBothState +{ + const List *l1; /* lists we're looping through */ + const List *l2; + int i; /* common element index */ +} ForBothState; + +typedef struct ForBothCellState +{ + const List *l1; /* lists we're looping through */ + const List *l2; + int i1; /* current element indexes */ + int i2; +} ForBothCellState; + +typedef struct ForThreeState +{ + const List *l1; /* lists we're looping through */ + const List *l2; + const List *l3; + int i; /* common element index */ +} ForThreeState; + +typedef struct ForFourState +{ + const List *l1; /* lists we're looping through */ + const List *l2; + const List *l3; + const List *l4; + int i; /* common element index */ +} ForFourState; + +typedef struct ForFiveState +{ + const List *l1; /* lists we're looping through */ + const List *l2; + const List *l3; + const List *l4; + const List *l5; + int i; /* common element index */ +} ForFiveState; + +/* + * These routines are small enough, and used often enough, to justify being + * inline. + */ + +/* Fetch address of list's first cell; NULL if empty list */ +static inline ListCell * +list_head(const List *l) +{ + return l ? &l->elements[0] : NULL; +} + +/* Fetch address of list's last cell; NULL if empty list */ +static inline ListCell * +list_tail(const List *l) +{ + return l ? &l->elements[l->length - 1] : NULL; +} + +/* Fetch address of list's second cell, if it has one, else NULL */ +static inline ListCell * +list_second_cell(const List *l) +{ + if (l && l->length >= 2) + return &l->elements[1]; + else + return NULL; +} + +/* Fetch list's length */ +static inline int +list_length(const List *l) +{ + return l ? l->length : 0; +} + +/* + * Macros to access the data values within List cells. + * + * Note that with the exception of the "xxx_node" macros, these are + * lvalues and can be assigned to. + * + * NB: There is an unfortunate legacy from a previous incarnation of + * the List API: the macro lfirst() was used to mean "the data in this + * cons cell". To avoid changing every usage of lfirst(), that meaning + * has been kept. As a result, lfirst() takes a ListCell and returns + * the data it contains; to get the data in the first cell of a + * List, use linitial(). Worse, lsecond() is more closely related to + * linitial() than lfirst(): given a List, lsecond() returns the data + * in the second list cell. + */ +#define lfirst(lc) ((lc)->ptr_value) +#define lfirst_int(lc) ((lc)->int_value) +#define lfirst_oid(lc) ((lc)->oid_value) +#define lfirst_xid(lc) ((lc)->xid_value) +#define lfirst_node(type,lc) castNode(type, lfirst(lc)) + +#define linitial(l) lfirst(list_nth_cell(l, 0)) +#define linitial_int(l) lfirst_int(list_nth_cell(l, 0)) +#define linitial_oid(l) lfirst_oid(list_nth_cell(l, 0)) +#define linitial_node(type,l) castNode(type, linitial(l)) + +#define lsecond(l) lfirst(list_nth_cell(l, 1)) +#define lsecond_int(l) lfirst_int(list_nth_cell(l, 1)) +#define lsecond_oid(l) lfirst_oid(list_nth_cell(l, 1)) +#define lsecond_node(type,l) castNode(type, lsecond(l)) + +#define lthird(l) lfirst(list_nth_cell(l, 2)) +#define lthird_int(l) lfirst_int(list_nth_cell(l, 2)) +#define lthird_oid(l) lfirst_oid(list_nth_cell(l, 2)) +#define lthird_node(type,l) castNode(type, lthird(l)) + +#define lfourth(l) lfirst(list_nth_cell(l, 3)) +#define lfourth_int(l) lfirst_int(list_nth_cell(l, 3)) +#define lfourth_oid(l) lfirst_oid(list_nth_cell(l, 3)) +#define lfourth_node(type,l) castNode(type, lfourth(l)) + +#define llast(l) lfirst(list_last_cell(l)) +#define llast_int(l) lfirst_int(list_last_cell(l)) +#define llast_oid(l) lfirst_oid(list_last_cell(l)) +#define llast_xid(l) lfirst_xid(list_last_cell(l)) +#define llast_node(type,l) castNode(type, llast(l)) + +/* + * Convenience macros for building fixed-length lists + */ +#define list_make_ptr_cell(v) ((ListCell) {.ptr_value = (v)}) +#define list_make_int_cell(v) ((ListCell) {.int_value = (v)}) +#define list_make_oid_cell(v) ((ListCell) {.oid_value = (v)}) +#define list_make_xid_cell(v) ((ListCell) {.xid_value = (v)}) + +#define list_make1(x1) \ + list_make1_impl(T_List, list_make_ptr_cell(x1)) +#define list_make2(x1,x2) \ + list_make2_impl(T_List, list_make_ptr_cell(x1), list_make_ptr_cell(x2)) +#define list_make3(x1,x2,x3) \ + list_make3_impl(T_List, list_make_ptr_cell(x1), list_make_ptr_cell(x2), \ + list_make_ptr_cell(x3)) +#define list_make4(x1,x2,x3,x4) \ + list_make4_impl(T_List, list_make_ptr_cell(x1), list_make_ptr_cell(x2), \ + list_make_ptr_cell(x3), list_make_ptr_cell(x4)) +#define list_make5(x1,x2,x3,x4,x5) \ + list_make5_impl(T_List, list_make_ptr_cell(x1), list_make_ptr_cell(x2), \ + list_make_ptr_cell(x3), list_make_ptr_cell(x4), \ + list_make_ptr_cell(x5)) + +#define list_make1_int(x1) \ + list_make1_impl(T_IntList, list_make_int_cell(x1)) +#define list_make2_int(x1,x2) \ + list_make2_impl(T_IntList, list_make_int_cell(x1), list_make_int_cell(x2)) +#define list_make3_int(x1,x2,x3) \ + list_make3_impl(T_IntList, list_make_int_cell(x1), list_make_int_cell(x2), \ + list_make_int_cell(x3)) +#define list_make4_int(x1,x2,x3,x4) \ + list_make4_impl(T_IntList, list_make_int_cell(x1), list_make_int_cell(x2), \ + list_make_int_cell(x3), list_make_int_cell(x4)) +#define list_make5_int(x1,x2,x3,x4,x5) \ + list_make5_impl(T_IntList, list_make_int_cell(x1), list_make_int_cell(x2), \ + list_make_int_cell(x3), list_make_int_cell(x4), \ + list_make_int_cell(x5)) + +#define list_make1_oid(x1) \ + list_make1_impl(T_OidList, list_make_oid_cell(x1)) +#define list_make2_oid(x1,x2) \ + list_make2_impl(T_OidList, list_make_oid_cell(x1), list_make_oid_cell(x2)) +#define list_make3_oid(x1,x2,x3) \ + list_make3_impl(T_OidList, list_make_oid_cell(x1), list_make_oid_cell(x2), \ + list_make_oid_cell(x3)) +#define list_make4_oid(x1,x2,x3,x4) \ + list_make4_impl(T_OidList, list_make_oid_cell(x1), list_make_oid_cell(x2), \ + list_make_oid_cell(x3), list_make_oid_cell(x4)) +#define list_make5_oid(x1,x2,x3,x4,x5) \ + list_make5_impl(T_OidList, list_make_oid_cell(x1), list_make_oid_cell(x2), \ + list_make_oid_cell(x3), list_make_oid_cell(x4), \ + list_make_oid_cell(x5)) + +#define list_make1_xid(x1) \ + list_make1_impl(T_XidList, list_make_xid_cell(x1)) +#define list_make2_xid(x1,x2) \ + list_make2_impl(T_XidList, list_make_xid_cell(x1), list_make_xid_cell(x2)) +#define list_make3_xid(x1,x2,x3) \ + list_make3_impl(T_XidList, list_make_xid_cell(x1), list_make_xid_cell(x2), \ + list_make_xid_cell(x3)) +#define list_make4_xid(x1,x2,x3,x4) \ + list_make4_impl(T_XidList, list_make_xid_cell(x1), list_make_xid_cell(x2), \ + list_make_xid_cell(x3), list_make_xid_cell(x4)) +#define list_make5_xid(x1,x2,x3,x4,x5) \ + list_make5_impl(T_XidList, list_make_xid_cell(x1), list_make_xid_cell(x2), \ + list_make_xid_cell(x3), list_make_xid_cell(x4), \ + list_make_xid_cell(x5)) + +/* + * Locate the n'th cell (counting from 0) of the list. + * It is an assertion failure if there is no such cell. + */ +static inline ListCell * +list_nth_cell(const List *list, int n) +{ + Assert(list != NIL); + Assert(n >= 0 && n < list->length); + return &list->elements[n]; +} + +/* + * Return the last cell in a non-NIL List. + */ +static inline ListCell * +list_last_cell(const List *list) +{ + Assert(list != NIL); + return &list->elements[list->length - 1]; +} + +/* + * Return the pointer value contained in the n'th element of the + * specified list. (List elements begin at 0.) + */ +static inline void * +list_nth(const List *list, int n) +{ + Assert(IsA(list, List)); + return lfirst(list_nth_cell(list, n)); +} + +/* + * Return the integer value contained in the n'th element of the + * specified list. + */ +static inline int +list_nth_int(const List *list, int n) +{ + Assert(IsA(list, IntList)); + return lfirst_int(list_nth_cell(list, n)); +} + +/* + * Return the OID value contained in the n'th element of the specified + * list. + */ +static inline Oid +list_nth_oid(const List *list, int n) +{ + Assert(IsA(list, OidList)); + return lfirst_oid(list_nth_cell(list, n)); +} + +#define list_nth_node(type,list,n) castNode(type, list_nth(list, n)) + +/* + * Get the given ListCell's index (from 0) in the given List. + */ +static inline int +list_cell_number(const List *l, const ListCell *c) +{ + Assert(c >= &l->elements[0] && c < &l->elements[l->length]); + return c - l->elements; +} + +/* + * Get the address of the next cell after "c" within list "l", or NULL if none. + */ +static inline ListCell * +lnext(const List *l, const ListCell *c) +{ + Assert(c >= &l->elements[0] && c < &l->elements[l->length]); + c++; + if (c < &l->elements[l->length]) + return (ListCell *) c; + else + return NULL; +} + +/* + * foreach - + * a convenience macro for looping through a list + * + * "cell" must be the name of a "ListCell *" variable; it's made to point + * to each List element in turn. "cell" will be NULL after normal exit from + * the loop, but an early "break" will leave it pointing at the current + * List element. + * + * Beware of changing the List object while the loop is iterating. + * The current semantics are that we examine successive list indices in + * each iteration, so that insertion or deletion of list elements could + * cause elements to be re-visited or skipped unexpectedly. Previous + * implementations of foreach() behaved differently. However, it's safe + * to append elements to the List (or in general, insert them after the + * current element); such new elements are guaranteed to be visited. + * Also, the current element of the List can be deleted, if you use + * foreach_delete_current() to do so. BUT: either of these actions will + * invalidate the "cell" pointer for the remainder of the current iteration. + */ +#define foreach(cell, lst) \ + for (ForEachState cell##__state = {(lst), 0}; \ + (cell##__state.l != NIL && \ + cell##__state.i < cell##__state.l->length) ? \ + (cell = &cell##__state.l->elements[cell##__state.i], true) : \ + (cell = NULL, false); \ + cell##__state.i++) + +/* + * foreach_delete_current - + * delete the current list element from the List associated with a + * surrounding foreach() loop, returning the new List pointer. + * + * This is equivalent to list_delete_cell(), but it also adjusts the foreach + * loop's state so that no list elements will be missed. Do not delete + * elements from an active foreach loop's list in any other way! + */ +#define foreach_delete_current(lst, cell) \ + (cell##__state.i--, \ + (List *) (cell##__state.l = list_delete_cell(lst, cell))) + +/* + * foreach_current_index - + * get the zero-based list index of a surrounding foreach() loop's + * current element; pass the name of the "ListCell *" iterator variable. + * + * Beware of using this after foreach_delete_current(); the value will be + * out of sync for the rest of the current loop iteration. Anyway, since + * you just deleted the current element, the value is pretty meaningless. + */ +#define foreach_current_index(cell) (cell##__state.i) + +/* + * for_each_from - + * Like foreach(), but start from the N'th (zero-based) list element, + * not necessarily the first one. + * + * It's okay for N to exceed the list length, but not for it to be negative. + * + * The caveats for foreach() apply equally here. + */ +#define for_each_from(cell, lst, N) \ + for (ForEachState cell##__state = for_each_from_setup(lst, N); \ + (cell##__state.l != NIL && \ + cell##__state.i < cell##__state.l->length) ? \ + (cell = &cell##__state.l->elements[cell##__state.i], true) : \ + (cell = NULL, false); \ + cell##__state.i++) + +static inline ForEachState +for_each_from_setup(const List *lst, int N) +{ + ForEachState r = {lst, N}; + + Assert(N >= 0); + return r; +} + +/* + * for_each_cell - + * a convenience macro which loops through a list starting from a + * specified cell + * + * The caveats for foreach() apply equally here. + */ +#define for_each_cell(cell, lst, initcell) \ + for (ForEachState cell##__state = for_each_cell_setup(lst, initcell); \ + (cell##__state.l != NIL && \ + cell##__state.i < cell##__state.l->length) ? \ + (cell = &cell##__state.l->elements[cell##__state.i], true) : \ + (cell = NULL, false); \ + cell##__state.i++) + +static inline ForEachState +for_each_cell_setup(const List *lst, const ListCell *initcell) +{ + ForEachState r = {lst, + initcell ? list_cell_number(lst, initcell) : list_length(lst)}; + + return r; +} + +/* + * forboth - + * a convenience macro for advancing through two linked lists + * simultaneously. This macro loops through both lists at the same + * time, stopping when either list runs out of elements. Depending + * on the requirements of the call site, it may also be wise to + * assert that the lengths of the two lists are equal. (But, if they + * are not, some callers rely on the ending cell values being separately + * NULL or non-NULL as defined here; don't try to optimize that.) + * + * The caveats for foreach() apply equally here. + */ +#define forboth(cell1, list1, cell2, list2) \ + for (ForBothState cell1##__state = {(list1), (list2), 0}; \ + multi_for_advance_cell(cell1, cell1##__state, l1, i), \ + multi_for_advance_cell(cell2, cell1##__state, l2, i), \ + (cell1 != NULL && cell2 != NULL); \ + cell1##__state.i++) + +#define multi_for_advance_cell(cell, state, l, i) \ + (cell = (state.l != NIL && state.i < state.l->length) ? \ + &state.l->elements[state.i] : NULL) + +/* + * for_both_cell - + * a convenience macro which loops through two lists starting from the + * specified cells of each. This macro loops through both lists at the same + * time, stopping when either list runs out of elements. Depending on the + * requirements of the call site, it may also be wise to assert that the + * lengths of the two lists are equal, and initcell1 and initcell2 are at + * the same position in the respective lists. + * + * The caveats for foreach() apply equally here. + */ +#define for_both_cell(cell1, list1, initcell1, cell2, list2, initcell2) \ + for (ForBothCellState cell1##__state = \ + for_both_cell_setup(list1, initcell1, list2, initcell2); \ + multi_for_advance_cell(cell1, cell1##__state, l1, i1), \ + multi_for_advance_cell(cell2, cell1##__state, l2, i2), \ + (cell1 != NULL && cell2 != NULL); \ + cell1##__state.i1++, cell1##__state.i2++) + +static inline ForBothCellState +for_both_cell_setup(const List *list1, const ListCell *initcell1, + const List *list2, const ListCell *initcell2) +{ + ForBothCellState r = {list1, list2, + initcell1 ? list_cell_number(list1, initcell1) : list_length(list1), + initcell2 ? list_cell_number(list2, initcell2) : list_length(list2)}; + + return r; +} + +/* + * forthree - + * the same for three lists + */ +#define forthree(cell1, list1, cell2, list2, cell3, list3) \ + for (ForThreeState cell1##__state = {(list1), (list2), (list3), 0}; \ + multi_for_advance_cell(cell1, cell1##__state, l1, i), \ + multi_for_advance_cell(cell2, cell1##__state, l2, i), \ + multi_for_advance_cell(cell3, cell1##__state, l3, i), \ + (cell1 != NULL && cell2 != NULL && cell3 != NULL); \ + cell1##__state.i++) + +/* + * forfour - + * the same for four lists + */ +#define forfour(cell1, list1, cell2, list2, cell3, list3, cell4, list4) \ + for (ForFourState cell1##__state = {(list1), (list2), (list3), (list4), 0}; \ + multi_for_advance_cell(cell1, cell1##__state, l1, i), \ + multi_for_advance_cell(cell2, cell1##__state, l2, i), \ + multi_for_advance_cell(cell3, cell1##__state, l3, i), \ + multi_for_advance_cell(cell4, cell1##__state, l4, i), \ + (cell1 != NULL && cell2 != NULL && cell3 != NULL && cell4 != NULL); \ + cell1##__state.i++) + +/* + * forfive - + * the same for five lists + */ +#define forfive(cell1, list1, cell2, list2, cell3, list3, cell4, list4, cell5, list5) \ + for (ForFiveState cell1##__state = {(list1), (list2), (list3), (list4), (list5), 0}; \ + multi_for_advance_cell(cell1, cell1##__state, l1, i), \ + multi_for_advance_cell(cell2, cell1##__state, l2, i), \ + multi_for_advance_cell(cell3, cell1##__state, l3, i), \ + multi_for_advance_cell(cell4, cell1##__state, l4, i), \ + multi_for_advance_cell(cell5, cell1##__state, l5, i), \ + (cell1 != NULL && cell2 != NULL && cell3 != NULL && \ + cell4 != NULL && cell5 != NULL); \ + cell1##__state.i++) + +/* Functions in src/backend/nodes/list.c */ + +extern List *list_make1_impl(NodeTag t, ListCell datum1); +extern List *list_make2_impl(NodeTag t, ListCell datum1, ListCell datum2); +extern List *list_make3_impl(NodeTag t, ListCell datum1, ListCell datum2, + ListCell datum3); +extern List *list_make4_impl(NodeTag t, ListCell datum1, ListCell datum2, + ListCell datum3, ListCell datum4); +extern List *list_make5_impl(NodeTag t, ListCell datum1, ListCell datum2, + ListCell datum3, ListCell datum4, + ListCell datum5); + +extern pg_nodiscard List *lappend(List *list, void *datum); +extern pg_nodiscard List *lappend_int(List *list, int datum); +extern pg_nodiscard List *lappend_oid(List *list, Oid datum); +extern pg_nodiscard List *lappend_xid(List *list, TransactionId datum); + +extern pg_nodiscard List *list_insert_nth(List *list, int pos, void *datum); +extern pg_nodiscard List *list_insert_nth_int(List *list, int pos, int datum); +extern pg_nodiscard List *list_insert_nth_oid(List *list, int pos, Oid datum); + +extern pg_nodiscard List *lcons(void *datum, List *list); +extern pg_nodiscard List *lcons_int(int datum, List *list); +extern pg_nodiscard List *lcons_oid(Oid datum, List *list); + +extern pg_nodiscard List *list_concat(List *list1, const List *list2); +extern pg_nodiscard List *list_concat_copy(const List *list1, const List *list2); + +extern pg_nodiscard List *list_truncate(List *list, int new_size); + +extern bool list_member(const List *list, const void *datum); +extern bool list_member_ptr(const List *list, const void *datum); +extern bool list_member_int(const List *list, int datum); +extern bool list_member_oid(const List *list, Oid datum); +extern bool list_member_xid(const List *list, TransactionId datum); + +extern pg_nodiscard List *list_delete(List *list, void *datum); +extern pg_nodiscard List *list_delete_ptr(List *list, void *datum); +extern pg_nodiscard List *list_delete_int(List *list, int datum); +extern pg_nodiscard List *list_delete_oid(List *list, Oid datum); +extern pg_nodiscard List *list_delete_first(List *list); +extern pg_nodiscard List *list_delete_last(List *list); +extern pg_nodiscard List *list_delete_first_n(List *list, int n); +extern pg_nodiscard List *list_delete_nth_cell(List *list, int n); +extern pg_nodiscard List *list_delete_cell(List *list, ListCell *cell); + +extern List *list_union(const List *list1, const List *list2); +extern List *list_union_ptr(const List *list1, const List *list2); +extern List *list_union_int(const List *list1, const List *list2); +extern List *list_union_oid(const List *list1, const List *list2); + +extern List *list_intersection(const List *list1, const List *list2); +extern List *list_intersection_int(const List *list1, const List *list2); + +/* currently, there's no need for list_intersection_ptr etc */ + +extern List *list_difference(const List *list1, const List *list2); +extern List *list_difference_ptr(const List *list1, const List *list2); +extern List *list_difference_int(const List *list1, const List *list2); +extern List *list_difference_oid(const List *list1, const List *list2); + +extern pg_nodiscard List *list_append_unique(List *list, void *datum); +extern pg_nodiscard List *list_append_unique_ptr(List *list, void *datum); +extern pg_nodiscard List *list_append_unique_int(List *list, int datum); +extern pg_nodiscard List *list_append_unique_oid(List *list, Oid datum); + +extern pg_nodiscard List *list_concat_unique(List *list1, const List *list2); +extern pg_nodiscard List *list_concat_unique_ptr(List *list1, const List *list2); +extern pg_nodiscard List *list_concat_unique_int(List *list1, const List *list2); +extern pg_nodiscard List *list_concat_unique_oid(List *list1, const List *list2); + +extern void list_deduplicate_oid(List *list); + +extern void list_free(List *list); +extern void list_free_deep(List *list); + +extern pg_nodiscard List *list_copy(const List *oldlist); +extern pg_nodiscard List *list_copy_head(const List *oldlist, int len); +extern pg_nodiscard List *list_copy_tail(const List *oldlist, int nskip); +extern pg_nodiscard List *list_copy_deep(const List *oldlist); + +typedef int (*list_sort_comparator) (const ListCell *a, const ListCell *b); +extern void list_sort(List *list, list_sort_comparator cmp); + +extern int list_int_cmp(const ListCell *p1, const ListCell *p2); +extern int list_oid_cmp(const ListCell *p1, const ListCell *p2); + +#endif /* PG_LIST_H */ diff --git a/src/include/nodes/plannodes.h b/src/include/nodes/plannodes.h new file mode 100644 index 0000000..d64fe6a --- /dev/null +++ b/src/include/nodes/plannodes.h @@ -0,0 +1,1592 @@ +/*------------------------------------------------------------------------- + * + * plannodes.h + * definitions for query plan nodes + * + * + * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/nodes/plannodes.h + * + *------------------------------------------------------------------------- + */ +#ifndef PLANNODES_H +#define PLANNODES_H + +#include "access/sdir.h" +#include "access/stratnum.h" +#include "common/relpath.h" +#include "lib/stringinfo.h" +#include "nodes/bitmapset.h" +#include "nodes/lockoptions.h" +#include "nodes/parsenodes.h" +#include "nodes/primnodes.h" + + +/* ---------------------------------------------------------------- + * node definitions + * ---------------------------------------------------------------- + */ + +/* ---------------- + * PlannedStmt node + * + * The output of the planner is a Plan tree headed by a PlannedStmt node. + * PlannedStmt holds the "one time" information needed by the executor. + * + * For simplicity in APIs, we also wrap utility statements in PlannedStmt + * nodes; in such cases, commandType == CMD_UTILITY, the statement itself + * is in the utilityStmt field, and the rest of the struct is mostly dummy. + * (We do use canSetTag, stmt_location, stmt_len, and possibly queryId.) + * + * PlannedStmt, as well as all varieties of Plan, do not support equal(), + * not because it's not sensible but because we currently have no need. + * ---------------- + */ +typedef struct PlannedStmt +{ + pg_node_attr(no_equal, no_query_jumble) + + NodeTag type; + + CmdType commandType; /* select|insert|update|delete|merge|utility */ + + uint64 queryId; /* query identifier (copied from Query) */ + + bool hasReturning; /* is it insert|update|delete RETURNING? */ + + bool hasModifyingCTE; /* has insert|update|delete in WITH? */ + + bool canSetTag; /* do I set the command result tag? */ + + bool transientPlan; /* redo plan when TransactionXmin changes? */ + + bool dependsOnRole; /* is plan specific to current role? */ + + bool parallelModeNeeded; /* parallel mode required to execute? */ + + int jitFlags; /* which forms of JIT should be performed */ + + struct Plan *planTree; /* tree of Plan nodes */ + + List *rtable; /* list of RangeTblEntry nodes */ + + List *permInfos; /* list of RTEPermissionInfo nodes for rtable + * entries needing one */ + + /* rtable indexes of target relations for INSERT/UPDATE/DELETE/MERGE */ + List *resultRelations; /* integer list of RT indexes, or NIL */ + + List *appendRelations; /* list of AppendRelInfo nodes */ + + List *subplans; /* Plan trees for SubPlan expressions; note + * that some could be NULL */ + + Bitmapset *rewindPlanIDs; /* indices of subplans that require REWIND */ + + List *rowMarks; /* a list of PlanRowMark's */ + + List *relationOids; /* OIDs of relations the plan depends on */ + + List *invalItems; /* other dependencies, as PlanInvalItems */ + + List *paramExecTypes; /* type OIDs for PARAM_EXEC Params */ + + Node *utilityStmt; /* non-null if this is utility stmt */ + + /* statement location in source string (copied from Query) */ + int stmt_location; /* start location, or -1 if unknown */ + int stmt_len; /* length in bytes; 0 means "rest of string" */ +} PlannedStmt; + +/* macro for fetching the Plan associated with a SubPlan node */ +#define exec_subplan_get_plan(plannedstmt, subplan) \ + ((Plan *) list_nth((plannedstmt)->subplans, (subplan)->plan_id - 1)) + + +/* ---------------- + * Plan node + * + * All plan nodes "derive" from the Plan structure by having the + * Plan structure as the first field. This ensures that everything works + * when nodes are cast to Plan's. (node pointers are frequently cast to Plan* + * when passed around generically in the executor) + * + * We never actually instantiate any Plan nodes; this is just the common + * abstract superclass for all Plan-type nodes. + * ---------------- + */ +typedef struct Plan +{ + pg_node_attr(abstract, no_equal, no_query_jumble) + + NodeTag type; + + /* + * estimated execution costs for plan (see costsize.c for more info) + */ + Cost startup_cost; /* cost expended before fetching any tuples */ + Cost total_cost; /* total cost (assuming all tuples fetched) */ + + /* + * planner's estimate of result size of this plan step + */ + Cardinality plan_rows; /* number of rows plan is expected to emit */ + int plan_width; /* average row width in bytes */ + + /* + * information needed for parallel query + */ + bool parallel_aware; /* engage parallel-aware logic? */ + bool parallel_safe; /* OK to use as part of parallel plan? */ + + /* + * information needed for asynchronous execution + */ + bool async_capable; /* engage asynchronous-capable logic? */ + + /* + * Common structural data for all Plan types. + */ + int plan_node_id; /* unique across entire final plan tree */ + List *targetlist; /* target list to be computed at this node */ + List *qual; /* implicitly-ANDed qual conditions */ + struct Plan *lefttree; /* input plan tree(s) */ + struct Plan *righttree; + List *initPlan; /* Init Plan nodes (un-correlated expr + * subselects) */ + + /* + * Information for management of parameter-change-driven rescanning + * + * extParam includes the paramIDs of all external PARAM_EXEC params + * affecting this plan node or its children. setParam params from the + * node's initPlans are not included, but their extParams are. + * + * allParam includes all the extParam paramIDs, plus the IDs of local + * params that affect the node (i.e., the setParams of its initplans). + * These are _all_ the PARAM_EXEC params that affect this node. + */ + Bitmapset *extParam; + Bitmapset *allParam; +} Plan; + +/* ---------------- + * these are defined to avoid confusion problems with "left" + * and "right" and "inner" and "outer". The convention is that + * the "left" plan is the "outer" plan and the "right" plan is + * the inner plan, but these make the code more readable. + * ---------------- + */ +#define innerPlan(node) (((Plan *)(node))->righttree) +#define outerPlan(node) (((Plan *)(node))->lefttree) + + +/* ---------------- + * Result node - + * If no outer plan, evaluate a variable-free targetlist. + * If outer plan, return tuples from outer plan (after a level of + * projection as shown by targetlist). + * + * If resconstantqual isn't NULL, it represents a one-time qualification + * test (i.e., one that doesn't depend on any variables from the outer plan, + * so needs to be evaluated only once). + * ---------------- + */ +typedef struct Result +{ + Plan plan; + Node *resconstantqual; +} Result; + +/* ---------------- + * ProjectSet node - + * Apply a projection that includes set-returning functions to the + * output tuples of the outer plan. + * ---------------- + */ +typedef struct ProjectSet +{ + Plan plan; +} ProjectSet; + +/* ---------------- + * ModifyTable node - + * Apply rows produced by outer plan to result table(s), + * by inserting, updating, or deleting. + * + * If the originally named target table is a partitioned table or inheritance + * tree, both nominalRelation and rootRelation contain the RT index of the + * partition root or appendrel RTE, which is not otherwise mentioned in the + * plan. Otherwise rootRelation is zero. However, nominalRelation will + * always be set, as it's the rel that EXPLAIN should claim is the + * INSERT/UPDATE/DELETE/MERGE target. + * + * Note that rowMarks and epqParam are presumed to be valid for all the + * table(s); they can't contain any info that varies across tables. + * ---------------- + */ +typedef struct ModifyTable +{ + Plan plan; + CmdType operation; /* INSERT, UPDATE, DELETE, or MERGE */ + bool canSetTag; /* do we set the command tag/es_processed? */ + Index nominalRelation; /* Parent RT index for use of EXPLAIN */ + Index rootRelation; /* Root RT index, if partitioned/inherited */ + bool partColsUpdated; /* some part key in hierarchy updated? */ + List *resultRelations; /* integer list of RT indexes */ + List *updateColnosLists; /* per-target-table update_colnos lists */ + List *withCheckOptionLists; /* per-target-table WCO lists */ + List *returningLists; /* per-target-table RETURNING tlists */ + List *fdwPrivLists; /* per-target-table FDW private data lists */ + Bitmapset *fdwDirectModifyPlans; /* indices of FDW DM plans */ + List *rowMarks; /* PlanRowMarks (non-locking only) */ + int epqParam; /* ID of Param for EvalPlanQual re-eval */ + OnConflictAction onConflictAction; /* ON CONFLICT action */ + List *arbiterIndexes; /* List of ON CONFLICT arbiter index OIDs */ + List *onConflictSet; /* INSERT ON CONFLICT DO UPDATE targetlist */ + List *onConflictCols; /* target column numbers for onConflictSet */ + Node *onConflictWhere; /* WHERE for ON CONFLICT UPDATE */ + Index exclRelRTI; /* RTI of the EXCLUDED pseudo relation */ + List *exclRelTlist; /* tlist of the EXCLUDED pseudo relation */ + List *mergeActionLists; /* per-target-table lists of actions for + * MERGE */ +} ModifyTable; + +struct PartitionPruneInfo; /* forward reference to struct below */ + +/* ---------------- + * Append node - + * Generate the concatenation of the results of sub-plans. + * ---------------- + */ +typedef struct Append +{ + Plan plan; + Bitmapset *apprelids; /* RTIs of appendrel(s) formed by this node */ + List *appendplans; + int nasyncplans; /* # of asynchronous plans */ + + /* + * All 'appendplans' preceding this index are non-partial plans. All + * 'appendplans' from this index onwards are partial plans. + */ + int first_partial_plan; + + /* Info for run-time subplan pruning; NULL if we're not doing that */ + struct PartitionPruneInfo *part_prune_info; +} Append; + +/* ---------------- + * MergeAppend node - + * Merge the results of pre-sorted sub-plans to preserve the ordering. + * ---------------- + */ +typedef struct MergeAppend +{ + Plan plan; + + /* RTIs of appendrel(s) formed by this node */ + Bitmapset *apprelids; + + List *mergeplans; + + /* these fields are just like the sort-key info in struct Sort: */ + + /* number of sort-key columns */ + int numCols; + + /* their indexes in the target list */ + AttrNumber *sortColIdx pg_node_attr(array_size(numCols)); + + /* OIDs of operators to sort them by */ + Oid *sortOperators pg_node_attr(array_size(numCols)); + + /* OIDs of collations */ + Oid *collations pg_node_attr(array_size(numCols)); + + /* NULLS FIRST/LAST directions */ + bool *nullsFirst pg_node_attr(array_size(numCols)); + + /* Info for run-time subplan pruning; NULL if we're not doing that */ + struct PartitionPruneInfo *part_prune_info; +} MergeAppend; + +/* ---------------- + * RecursiveUnion node - + * Generate a recursive union of two subplans. + * + * The "outer" subplan is always the non-recursive term, and the "inner" + * subplan is the recursive term. + * ---------------- + */ +typedef struct RecursiveUnion +{ + Plan plan; + + /* ID of Param representing work table */ + int wtParam; + + /* Remaining fields are zero/null in UNION ALL case */ + + /* number of columns to check for duplicate-ness */ + int numCols; + + /* their indexes in the target list */ + AttrNumber *dupColIdx pg_node_attr(array_size(numCols)); + + /* equality operators to compare with */ + Oid *dupOperators pg_node_attr(array_size(numCols)); + Oid *dupCollations pg_node_attr(array_size(numCols)); + + /* estimated number of groups in input */ + long numGroups; +} RecursiveUnion; + +/* ---------------- + * BitmapAnd node - + * Generate the intersection of the results of sub-plans. + * + * The subplans must be of types that yield tuple bitmaps. The targetlist + * and qual fields of the plan are unused and are always NIL. + * ---------------- + */ +typedef struct BitmapAnd +{ + Plan plan; + List *bitmapplans; +} BitmapAnd; + +/* ---------------- + * BitmapOr node - + * Generate the union of the results of sub-plans. + * + * The subplans must be of types that yield tuple bitmaps. The targetlist + * and qual fields of the plan are unused and are always NIL. + * ---------------- + */ +typedef struct BitmapOr +{ + Plan plan; + bool isshared; + List *bitmapplans; +} BitmapOr; + +/* + * ========== + * Scan nodes + * + * Scan is an abstract type that all relation scan plan types inherit from. + * ========== + */ +typedef struct Scan +{ + pg_node_attr(abstract) + + Plan plan; + Index scanrelid; /* relid is index into the range table */ +} Scan; + +/* ---------------- + * sequential scan node + * ---------------- + */ +typedef struct SeqScan +{ + Scan scan; +} SeqScan; + +/* ---------------- + * table sample scan node + * ---------------- + */ +typedef struct SampleScan +{ + Scan scan; + /* use struct pointer to avoid including parsenodes.h here */ + struct TableSampleClause *tablesample; +} SampleScan; + +/* ---------------- + * index scan node + * + * indexqualorig is an implicitly-ANDed list of index qual expressions, each + * in the same form it appeared in the query WHERE condition. Each should + * be of the form (indexkey OP comparisonval) or (comparisonval OP indexkey). + * The indexkey is a Var or expression referencing column(s) of the index's + * base table. The comparisonval might be any expression, but it won't use + * any columns of the base table. The expressions are ordered by index + * column position (but items referencing the same index column can appear + * in any order). indexqualorig is used at runtime only if we have to recheck + * a lossy indexqual. + * + * indexqual has the same form, but the expressions have been commuted if + * necessary to put the indexkeys on the left, and the indexkeys are replaced + * by Var nodes identifying the index columns (their varno is INDEX_VAR and + * their varattno is the index column number). + * + * indexorderbyorig is similarly the original form of any ORDER BY expressions + * that are being implemented by the index, while indexorderby is modified to + * have index column Vars on the left-hand side. Here, multiple expressions + * must appear in exactly the ORDER BY order, and this is not necessarily the + * index column order. Only the expressions are provided, not the auxiliary + * sort-order information from the ORDER BY SortGroupClauses; it's assumed + * that the sort ordering is fully determinable from the top-level operators. + * indexorderbyorig is used at runtime to recheck the ordering, if the index + * cannot calculate an accurate ordering. It is also needed for EXPLAIN. + * + * indexorderbyops is a list of the OIDs of the operators used to sort the + * ORDER BY expressions. This is used together with indexorderbyorig to + * recheck ordering at run time. (Note that indexorderby, indexorderbyorig, + * and indexorderbyops are used for amcanorderbyop cases, not amcanorder.) + * + * indexorderdir specifies the scan ordering, for indexscans on amcanorder + * indexes (for other indexes it should be "don't care"). + * ---------------- + */ +typedef struct IndexScan +{ + Scan scan; + Oid indexid; /* OID of index to scan */ + List *indexqual; /* list of index quals (usually OpExprs) */ + List *indexqualorig; /* the same in original form */ + List *indexorderby; /* list of index ORDER BY exprs */ + List *indexorderbyorig; /* the same in original form */ + List *indexorderbyops; /* OIDs of sort ops for ORDER BY exprs */ + ScanDirection indexorderdir; /* forward or backward or don't care */ +} IndexScan; + +/* ---------------- + * index-only scan node + * + * IndexOnlyScan is very similar to IndexScan, but it specifies an + * index-only scan, in which the data comes from the index not the heap. + * Because of this, *all* Vars in the plan node's targetlist, qual, and + * index expressions reference index columns and have varno = INDEX_VAR. + * + * We could almost use indexqual directly against the index's output tuple + * when rechecking lossy index operators, but that won't work for quals on + * index columns that are not retrievable. Hence, recheckqual is needed + * for rechecks: it expresses the same condition as indexqual, but using + * only index columns that are retrievable. (We will not generate an + * index-only scan if this is not possible. An example is that if an + * index has table column "x" in a retrievable index column "ind1", plus + * an expression f(x) in a non-retrievable column "ind2", an indexable + * query on f(x) will use "ind2" in indexqual and f(ind1) in recheckqual. + * Without the "ind1" column, an index-only scan would be disallowed.) + * + * We don't currently need a recheckable equivalent of indexorderby, + * because we don't support lossy operators in index ORDER BY. + * + * To help EXPLAIN interpret the index Vars for display, we provide + * indextlist, which represents the contents of the index as a targetlist + * with one TLE per index column. Vars appearing in this list reference + * the base table, and this is the only field in the plan node that may + * contain such Vars. Also, for the convenience of setrefs.c, TLEs in + * indextlist are marked as resjunk if they correspond to columns that + * the index AM cannot reconstruct. + * ---------------- + */ +typedef struct IndexOnlyScan +{ + Scan scan; + Oid indexid; /* OID of index to scan */ + List *indexqual; /* list of index quals (usually OpExprs) */ + List *recheckqual; /* index quals in recheckable form */ + List *indexorderby; /* list of index ORDER BY exprs */ + List *indextlist; /* TargetEntry list describing index's cols */ + ScanDirection indexorderdir; /* forward or backward or don't care */ +} IndexOnlyScan; + +/* ---------------- + * bitmap index scan node + * + * BitmapIndexScan delivers a bitmap of potential tuple locations; + * it does not access the heap itself. The bitmap is used by an + * ancestor BitmapHeapScan node, possibly after passing through + * intermediate BitmapAnd and/or BitmapOr nodes to combine it with + * the results of other BitmapIndexScans. + * + * The fields have the same meanings as for IndexScan, except we don't + * store a direction flag because direction is uninteresting. + * + * In a BitmapIndexScan plan node, the targetlist and qual fields are + * not used and are always NIL. The indexqualorig field is unused at + * run time too, but is saved for the benefit of EXPLAIN. + * ---------------- + */ +typedef struct BitmapIndexScan +{ + Scan scan; + Oid indexid; /* OID of index to scan */ + bool isshared; /* Create shared bitmap if set */ + List *indexqual; /* list of index quals (OpExprs) */ + List *indexqualorig; /* the same in original form */ +} BitmapIndexScan; + +/* ---------------- + * bitmap sequential scan node + * + * This needs a copy of the qual conditions being used by the input index + * scans because there are various cases where we need to recheck the quals; + * for example, when the bitmap is lossy about the specific rows on a page + * that meet the index condition. + * ---------------- + */ +typedef struct BitmapHeapScan +{ + Scan scan; + List *bitmapqualorig; /* index quals, in standard expr form */ +} BitmapHeapScan; + +/* ---------------- + * tid scan node + * + * tidquals is an implicitly OR'ed list of qual expressions of the form + * "CTID = pseudoconstant", or "CTID = ANY(pseudoconstant_array)", + * or a CurrentOfExpr for the relation. + * ---------------- + */ +typedef struct TidScan +{ + Scan scan; + List *tidquals; /* qual(s) involving CTID = something */ +} TidScan; + +/* ---------------- + * tid range scan node + * + * tidrangequals is an implicitly AND'ed list of qual expressions of the form + * "CTID relop pseudoconstant", where relop is one of >,>=,<,<=. + * ---------------- + */ +typedef struct TidRangeScan +{ + Scan scan; + List *tidrangequals; /* qual(s) involving CTID op something */ +} TidRangeScan; + +/* ---------------- + * subquery scan node + * + * SubqueryScan is for scanning the output of a sub-query in the range table. + * We often need an extra plan node above the sub-query's plan to perform + * expression evaluations (which we can't push into the sub-query without + * risking changing its semantics). Although we are not scanning a physical + * relation, we make this a descendant of Scan anyway for code-sharing + * purposes. + * + * SubqueryScanStatus caches the trivial_subqueryscan property of the node. + * SUBQUERY_SCAN_UNKNOWN means not yet determined. This is only used during + * planning. + * + * Note: we store the sub-plan in the type-specific subplan field, not in + * the generic lefttree field as you might expect. This is because we do + * not want plan-tree-traversal routines to recurse into the subplan without + * knowing that they are changing Query contexts. + * ---------------- + */ +typedef enum SubqueryScanStatus +{ + SUBQUERY_SCAN_UNKNOWN, + SUBQUERY_SCAN_TRIVIAL, + SUBQUERY_SCAN_NONTRIVIAL +} SubqueryScanStatus; + +typedef struct SubqueryScan +{ + Scan scan; + Plan *subplan; + SubqueryScanStatus scanstatus; +} SubqueryScan; + +/* ---------------- + * FunctionScan node + * ---------------- + */ +typedef struct FunctionScan +{ + Scan scan; + List *functions; /* list of RangeTblFunction nodes */ + bool funcordinality; /* WITH ORDINALITY */ +} FunctionScan; + +/* ---------------- + * ValuesScan node + * ---------------- + */ +typedef struct ValuesScan +{ + Scan scan; + List *values_lists; /* list of expression lists */ +} ValuesScan; + +/* ---------------- + * TableFunc scan node + * ---------------- + */ +typedef struct TableFuncScan +{ + Scan scan; + TableFunc *tablefunc; /* table function node */ +} TableFuncScan; + +/* ---------------- + * CteScan node + * ---------------- + */ +typedef struct CteScan +{ + Scan scan; + int ctePlanId; /* ID of init SubPlan for CTE */ + int cteParam; /* ID of Param representing CTE output */ +} CteScan; + +/* ---------------- + * NamedTuplestoreScan node + * ---------------- + */ +typedef struct NamedTuplestoreScan +{ + Scan scan; + char *enrname; /* Name given to Ephemeral Named Relation */ +} NamedTuplestoreScan; + +/* ---------------- + * WorkTableScan node + * ---------------- + */ +typedef struct WorkTableScan +{ + Scan scan; + int wtParam; /* ID of Param representing work table */ +} WorkTableScan; + +/* ---------------- + * ForeignScan node + * + * fdw_exprs and fdw_private are both under the control of the foreign-data + * wrapper, but fdw_exprs is presumed to contain expression trees and will + * be post-processed accordingly by the planner; fdw_private won't be. + * Note that everything in both lists must be copiable by copyObject(). + * One way to store an arbitrary blob of bytes is to represent it as a bytea + * Const. Usually, though, you'll be better off choosing a representation + * that can be dumped usefully by nodeToString(). + * + * fdw_scan_tlist is a targetlist describing the contents of the scan tuple + * returned by the FDW; it can be NIL if the scan tuple matches the declared + * rowtype of the foreign table, which is the normal case for a simple foreign + * table scan. (If the plan node represents a foreign join, fdw_scan_tlist + * is required since there is no rowtype available from the system catalogs.) + * When fdw_scan_tlist is provided, Vars in the node's tlist and quals must + * have varno INDEX_VAR, and their varattnos correspond to resnos in the + * fdw_scan_tlist (which are also column numbers in the actual scan tuple). + * fdw_scan_tlist is never actually executed; it just holds expression trees + * describing what is in the scan tuple's columns. + * + * fdw_recheck_quals should contain any quals which the core system passed to + * the FDW but which were not added to scan.plan.qual; that is, it should + * contain the quals being checked remotely. This is needed for correct + * behavior during EvalPlanQual rechecks. + * + * When the plan node represents a foreign join, scan.scanrelid is zero and + * fs_relids must be consulted to identify the join relation. (fs_relids + * is valid for simple scans as well, but will always match scan.scanrelid.) + * fs_relids includes outer joins; fs_base_relids does not. + * + * If the FDW's PlanDirectModify() callback decides to repurpose a ForeignScan + * node to perform the UPDATE or DELETE operation directly in the remote + * server, it sets 'operation' and 'resultRelation' to identify the operation + * type and target relation. Note that these fields are only set if the + * modification is performed *fully* remotely; otherwise, the modification is + * driven by a local ModifyTable node and 'operation' is left to CMD_SELECT. + * ---------------- + */ +typedef struct ForeignScan +{ + Scan scan; + CmdType operation; /* SELECT/INSERT/UPDATE/DELETE */ + Index resultRelation; /* direct modification target's RT index */ + Oid checkAsUser; /* user to perform the scan as; 0 means to + * check as current user */ + Oid fs_server; /* OID of foreign server */ + List *fdw_exprs; /* expressions that FDW may evaluate */ + List *fdw_private; /* private data for FDW */ + List *fdw_scan_tlist; /* optional tlist describing scan tuple */ + List *fdw_recheck_quals; /* original quals not in scan.plan.qual */ + Bitmapset *fs_relids; /* base+OJ RTIs generated by this scan */ + Bitmapset *fs_base_relids; /* base RTIs generated by this scan */ + bool fsSystemCol; /* true if any "system column" is needed */ +} ForeignScan; + +/* ---------------- + * CustomScan node + * + * The comments for ForeignScan's fdw_exprs, fdw_private, fdw_scan_tlist, + * and fs_relids fields apply equally to CustomScan's custom_exprs, + * custom_private, custom_scan_tlist, and custom_relids fields. The + * convention of setting scan.scanrelid to zero for joins applies as well. + * + * Note that since Plan trees can be copied, custom scan providers *must* + * fit all plan data they need into those fields; embedding CustomScan in + * a larger struct will not work. + * ---------------- + */ +struct CustomScanMethods; + +typedef struct CustomScan +{ + Scan scan; + uint32 flags; /* mask of CUSTOMPATH_* flags, see + * nodes/extensible.h */ + List *custom_plans; /* list of Plan nodes, if any */ + List *custom_exprs; /* expressions that custom code may evaluate */ + List *custom_private; /* private data for custom code */ + List *custom_scan_tlist; /* optional tlist describing scan tuple */ + Bitmapset *custom_relids; /* RTIs generated by this scan */ + + /* + * NOTE: The method field of CustomScan is required to be a pointer to a + * static table of callback functions. So we don't copy the table itself, + * just reference the original one. + */ + const struct CustomScanMethods *methods; +} CustomScan; + +/* + * ========== + * Join nodes + * ========== + */ + +/* ---------------- + * Join node + * + * jointype: rule for joining tuples from left and right subtrees + * inner_unique each outer tuple can match to no more than one inner tuple + * joinqual: qual conditions that came from JOIN/ON or JOIN/USING + * (plan.qual contains conditions that came from WHERE) + * + * When jointype is INNER, joinqual and plan.qual are semantically + * interchangeable. For OUTER jointypes, the two are *not* interchangeable; + * only joinqual is used to determine whether a match has been found for + * the purpose of deciding whether to generate null-extended tuples. + * (But plan.qual is still applied before actually returning a tuple.) + * For an outer join, only joinquals are allowed to be used as the merge + * or hash condition of a merge or hash join. + * + * inner_unique is set if the joinquals are such that no more than one inner + * tuple could match any given outer tuple. This allows the executor to + * skip searching for additional matches. (This must be provable from just + * the joinquals, ignoring plan.qual, due to where the executor tests it.) + * ---------------- + */ +typedef struct Join +{ + pg_node_attr(abstract) + + Plan plan; + JoinType jointype; + bool inner_unique; + List *joinqual; /* JOIN quals (in addition to plan.qual) */ +} Join; + +/* ---------------- + * nest loop join node + * + * The nestParams list identifies any executor Params that must be passed + * into execution of the inner subplan carrying values from the current row + * of the outer subplan. Currently we restrict these values to be simple + * Vars, but perhaps someday that'd be worth relaxing. (Note: during plan + * creation, the paramval can actually be a PlaceHolderVar expression; but it + * must be a Var with varno OUTER_VAR by the time it gets to the executor.) + * ---------------- + */ +typedef struct NestLoop +{ + Join join; + List *nestParams; /* list of NestLoopParam nodes */ +} NestLoop; + +typedef struct NestLoopParam +{ + pg_node_attr(no_equal, no_query_jumble) + + NodeTag type; + int paramno; /* number of the PARAM_EXEC Param to set */ + Var *paramval; /* outer-relation Var to assign to Param */ +} NestLoopParam; + +/* ---------------- + * merge join node + * + * The expected ordering of each mergeable column is described by a btree + * opfamily OID, a collation OID, a direction (BTLessStrategyNumber or + * BTGreaterStrategyNumber) and a nulls-first flag. Note that the two sides + * of each mergeclause may be of different datatypes, but they are ordered the + * same way according to the common opfamily and collation. The operator in + * each mergeclause must be an equality operator of the indicated opfamily. + * ---------------- + */ +typedef struct MergeJoin +{ + Join join; + + /* Can we skip mark/restore calls? */ + bool skip_mark_restore; + + /* mergeclauses as expression trees */ + List *mergeclauses; + + /* these are arrays, but have the same length as the mergeclauses list: */ + + /* per-clause OIDs of btree opfamilies */ + Oid *mergeFamilies pg_node_attr(array_size(mergeclauses)); + + /* per-clause OIDs of collations */ + Oid *mergeCollations pg_node_attr(array_size(mergeclauses)); + + /* per-clause ordering (ASC or DESC) */ + int *mergeStrategies pg_node_attr(array_size(mergeclauses)); + + /* per-clause nulls ordering */ + bool *mergeNullsFirst pg_node_attr(array_size(mergeclauses)); +} MergeJoin; + +/* ---------------- + * hash join node + * ---------------- + */ +typedef struct HashJoin +{ + Join join; + List *hashclauses; + List *hashoperators; + List *hashcollations; + + /* + * List of expressions to be hashed for tuples from the outer plan, to + * perform lookups in the hashtable over the inner plan. + */ + List *hashkeys; +} HashJoin; + +/* ---------------- + * materialization node + * ---------------- + */ +typedef struct Material +{ + Plan plan; +} Material; + +/* ---------------- + * memoize node + * ---------------- + */ +typedef struct Memoize +{ + Plan plan; + + /* size of the two arrays below */ + int numKeys; + + /* hash operators for each key */ + Oid *hashOperators pg_node_attr(array_size(numKeys)); + + /* collations for each key */ + Oid *collations pg_node_attr(array_size(numKeys)); + + /* cache keys in the form of exprs containing parameters */ + List *param_exprs; + + /* + * true if the cache entry should be marked as complete after we store the + * first tuple in it. + */ + bool singlerow; + + /* + * true when cache key should be compared bit by bit, false when using + * hash equality ops + */ + bool binary_mode; + + /* + * The maximum number of entries that the planner expects will fit in the + * cache, or 0 if unknown + */ + uint32 est_entries; + + /* paramids from param_exprs */ + Bitmapset *keyparamids; +} Memoize; + +/* ---------------- + * sort node + * ---------------- + */ +typedef struct Sort +{ + Plan plan; + + /* number of sort-key columns */ + int numCols; + + /* their indexes in the target list */ + AttrNumber *sortColIdx pg_node_attr(array_size(numCols)); + + /* OIDs of operators to sort them by */ + Oid *sortOperators pg_node_attr(array_size(numCols)); + + /* OIDs of collations */ + Oid *collations pg_node_attr(array_size(numCols)); + + /* NULLS FIRST/LAST directions */ + bool *nullsFirst pg_node_attr(array_size(numCols)); +} Sort; + +/* ---------------- + * incremental sort node + * ---------------- + */ +typedef struct IncrementalSort +{ + Sort sort; + int nPresortedCols; /* number of presorted columns */ +} IncrementalSort; + +/* --------------- + * group node - + * Used for queries with GROUP BY (but no aggregates) specified. + * The input must be presorted according to the grouping columns. + * --------------- + */ +typedef struct Group +{ + Plan plan; + + /* number of grouping columns */ + int numCols; + + /* their indexes in the target list */ + AttrNumber *grpColIdx pg_node_attr(array_size(numCols)); + + /* equality operators to compare with */ + Oid *grpOperators pg_node_attr(array_size(numCols)); + Oid *grpCollations pg_node_attr(array_size(numCols)); +} Group; + +/* --------------- + * aggregate node + * + * An Agg node implements plain or grouped aggregation. For grouped + * aggregation, we can work with presorted input or unsorted input; + * the latter strategy uses an internal hashtable. + * + * Notice the lack of any direct info about the aggregate functions to be + * computed. They are found by scanning the node's tlist and quals during + * executor startup. (It is possible that there are no aggregate functions; + * this could happen if they get optimized away by constant-folding, or if + * we are using the Agg node to implement hash-based grouping.) + * --------------- + */ +typedef struct Agg +{ + Plan plan; + + /* basic strategy, see nodes.h */ + AggStrategy aggstrategy; + + /* agg-splitting mode, see nodes.h */ + AggSplit aggsplit; + + /* number of grouping columns */ + int numCols; + + /* their indexes in the target list */ + AttrNumber *grpColIdx pg_node_attr(array_size(numCols)); + + /* equality operators to compare with */ + Oid *grpOperators pg_node_attr(array_size(numCols)); + Oid *grpCollations pg_node_attr(array_size(numCols)); + + /* estimated number of groups in input */ + long numGroups; + + /* for pass-by-ref transition data */ + uint64 transitionSpace; + + /* IDs of Params used in Aggref inputs */ + Bitmapset *aggParams; + + /* Note: planner provides numGroups & aggParams only in HASHED/MIXED case */ + + /* grouping sets to use */ + List *groupingSets; + + /* chained Agg/Sort nodes */ + List *chain; +} Agg; + +/* ---------------- + * window aggregate node + * ---------------- + */ +typedef struct WindowAgg +{ + Plan plan; + + /* ID referenced by window functions */ + Index winref; + + /* number of columns in partition clause */ + int partNumCols; + + /* their indexes in the target list */ + AttrNumber *partColIdx pg_node_attr(array_size(partNumCols)); + + /* equality operators for partition columns */ + Oid *partOperators pg_node_attr(array_size(partNumCols)); + + /* collations for partition columns */ + Oid *partCollations pg_node_attr(array_size(partNumCols)); + + /* number of columns in ordering clause */ + int ordNumCols; + + /* their indexes in the target list */ + AttrNumber *ordColIdx pg_node_attr(array_size(ordNumCols)); + + /* equality operators for ordering columns */ + Oid *ordOperators pg_node_attr(array_size(ordNumCols)); + + /* collations for ordering columns */ + Oid *ordCollations pg_node_attr(array_size(ordNumCols)); + + /* frame_clause options, see WindowDef */ + int frameOptions; + + /* expression for starting bound, if any */ + Node *startOffset; + + /* expression for ending bound, if any */ + Node *endOffset; + + /* qual to help short-circuit execution */ + List *runCondition; + + /* runCondition for display in EXPLAIN */ + List *runConditionOrig; + + /* these fields are used with RANGE offset PRECEDING/FOLLOWING: */ + + /* in_range function for startOffset */ + Oid startInRangeFunc; + + /* in_range function for endOffset */ + Oid endInRangeFunc; + + /* collation for in_range tests */ + Oid inRangeColl; + + /* use ASC sort order for in_range tests? */ + bool inRangeAsc; + + /* nulls sort first for in_range tests? */ + bool inRangeNullsFirst; + + /* + * false for all apart from the WindowAgg that's closest to the root of + * the plan + */ + bool topWindow; +} WindowAgg; + +/* ---------------- + * unique node + * ---------------- + */ +typedef struct Unique +{ + Plan plan; + + /* number of columns to check for uniqueness */ + int numCols; + + /* their indexes in the target list */ + AttrNumber *uniqColIdx pg_node_attr(array_size(numCols)); + + /* equality operators to compare with */ + Oid *uniqOperators pg_node_attr(array_size(numCols)); + + /* collations for equality comparisons */ + Oid *uniqCollations pg_node_attr(array_size(numCols)); +} Unique; + +/* ------------ + * gather node + * + * Note: rescan_param is the ID of a PARAM_EXEC parameter slot. That slot + * will never actually contain a value, but the Gather node must flag it as + * having changed whenever it is rescanned. The child parallel-aware scan + * nodes are marked as depending on that parameter, so that the rescan + * machinery is aware that their output is likely to change across rescans. + * In some cases we don't need a rescan Param, so rescan_param is set to -1. + * ------------ + */ +typedef struct Gather +{ + Plan plan; + int num_workers; /* planned number of worker processes */ + int rescan_param; /* ID of Param that signals a rescan, or -1 */ + bool single_copy; /* don't execute plan more than once */ + bool invisible; /* suppress EXPLAIN display (for testing)? */ + Bitmapset *initParam; /* param id's of initplans which are referred + * at gather or one of it's child node */ +} Gather; + +/* ------------ + * gather merge node + * ------------ + */ +typedef struct GatherMerge +{ + Plan plan; + + /* planned number of worker processes */ + int num_workers; + + /* ID of Param that signals a rescan, or -1 */ + int rescan_param; + + /* remaining fields are just like the sort-key info in struct Sort */ + + /* number of sort-key columns */ + int numCols; + + /* their indexes in the target list */ + AttrNumber *sortColIdx pg_node_attr(array_size(numCols)); + + /* OIDs of operators to sort them by */ + Oid *sortOperators pg_node_attr(array_size(numCols)); + + /* OIDs of collations */ + Oid *collations pg_node_attr(array_size(numCols)); + + /* NULLS FIRST/LAST directions */ + bool *nullsFirst pg_node_attr(array_size(numCols)); + + /* + * param id's of initplans which are referred at gather merge or one of + * it's child node + */ + Bitmapset *initParam; +} GatherMerge; + +/* ---------------- + * hash build node + * + * If the executor is supposed to try to apply skew join optimization, then + * skewTable/skewColumn/skewInherit identify the outer relation's join key + * column, from which the relevant MCV statistics can be fetched. + * ---------------- + */ +typedef struct Hash +{ + Plan plan; + + /* + * List of expressions to be hashed for tuples from Hash's outer plan, + * needed to put them into the hashtable. + */ + List *hashkeys; /* hash keys for the hashjoin condition */ + Oid skewTable; /* outer join key's table OID, or InvalidOid */ + AttrNumber skewColumn; /* outer join key's column #, or zero */ + bool skewInherit; /* is outer join rel an inheritance tree? */ + /* all other info is in the parent HashJoin node */ + Cardinality rows_total; /* estimate total rows if parallel_aware */ +} Hash; + +/* ---------------- + * setop node + * ---------------- + */ +typedef struct SetOp +{ + Plan plan; + + /* what to do, see nodes.h */ + SetOpCmd cmd; + + /* how to do it, see nodes.h */ + SetOpStrategy strategy; + + /* number of columns to check for duplicate-ness */ + int numCols; + + /* their indexes in the target list */ + AttrNumber *dupColIdx pg_node_attr(array_size(numCols)); + + /* equality operators to compare with */ + Oid *dupOperators pg_node_attr(array_size(numCols)); + Oid *dupCollations pg_node_attr(array_size(numCols)); + + /* where is the flag column, if any */ + AttrNumber flagColIdx; + + /* flag value for first input relation */ + int firstFlag; + + /* estimated number of groups in input */ + long numGroups; +} SetOp; + +/* ---------------- + * lock-rows node + * + * rowMarks identifies the rels to be locked by this node; it should be + * a subset of the rowMarks listed in the top-level PlannedStmt. + * epqParam is a Param that all scan nodes below this one must depend on. + * It is used to force re-evaluation of the plan during EvalPlanQual. + * ---------------- + */ +typedef struct LockRows +{ + Plan plan; + List *rowMarks; /* a list of PlanRowMark's */ + int epqParam; /* ID of Param for EvalPlanQual re-eval */ +} LockRows; + +/* ---------------- + * limit node + * + * Note: as of Postgres 8.2, the offset and count expressions are expected + * to yield int8, rather than int4 as before. + * ---------------- + */ +typedef struct Limit +{ + Plan plan; + + /* OFFSET parameter, or NULL if none */ + Node *limitOffset; + + /* COUNT parameter, or NULL if none */ + Node *limitCount; + + /* limit type */ + LimitOption limitOption; + + /* number of columns to check for similarity */ + int uniqNumCols; + + /* their indexes in the target list */ + AttrNumber *uniqColIdx pg_node_attr(array_size(uniqNumCols)); + + /* equality operators to compare with */ + Oid *uniqOperators pg_node_attr(array_size(uniqNumCols)); + + /* collations for equality comparisons */ + Oid *uniqCollations pg_node_attr(array_size(uniqNumCols)); +} Limit; + + +/* + * RowMarkType - + * enums for types of row-marking operations + * + * The first four of these values represent different lock strengths that + * we can take on tuples according to SELECT FOR [KEY] UPDATE/SHARE requests. + * We support these on regular tables, as well as on foreign tables whose FDWs + * report support for late locking. For other foreign tables, any locking + * that might be done for such requests must happen during the initial row + * fetch; their FDWs provide no mechanism for going back to lock a row later. + * This means that the semantics will be a bit different than for a local + * table; in particular we are likely to lock more rows than would be locked + * locally, since remote rows will be locked even if they then fail + * locally-checked restriction or join quals. However, the prospect of + * doing a separate remote query to lock each selected row is usually pretty + * unappealing, so early locking remains a credible design choice for FDWs. + * + * When doing UPDATE/DELETE/MERGE/SELECT FOR UPDATE/SHARE, we have to uniquely + * identify all the source rows, not only those from the target relations, so + * that we can perform EvalPlanQual rechecking at need. For plain tables we + * can just fetch the TID, much as for a target relation; this case is + * represented by ROW_MARK_REFERENCE. Otherwise (for example for VALUES or + * FUNCTION scans) we have to copy the whole row value. ROW_MARK_COPY is + * pretty inefficient, since most of the time we'll never need the data; but + * fortunately the overhead is usually not performance-critical in practice. + * By default we use ROW_MARK_COPY for foreign tables, but if the FDW has + * a concept of rowid it can request to use ROW_MARK_REFERENCE instead. + * (Again, this probably doesn't make sense if a physical remote fetch is + * needed, but for FDWs that map to local storage it might be credible.) + */ +typedef enum RowMarkType +{ + ROW_MARK_EXCLUSIVE, /* obtain exclusive tuple lock */ + ROW_MARK_NOKEYEXCLUSIVE, /* obtain no-key exclusive tuple lock */ + ROW_MARK_SHARE, /* obtain shared tuple lock */ + ROW_MARK_KEYSHARE, /* obtain keyshare tuple lock */ + ROW_MARK_REFERENCE, /* just fetch the TID, don't lock it */ + ROW_MARK_COPY /* physically copy the row value */ +} RowMarkType; + +#define RowMarkRequiresRowShareLock(marktype) ((marktype) <= ROW_MARK_KEYSHARE) + +/* + * PlanRowMark - + * plan-time representation of FOR [KEY] UPDATE/SHARE clauses + * + * When doing UPDATE/DELETE/MERGE/SELECT FOR UPDATE/SHARE, we create a separate + * PlanRowMark node for each non-target relation in the query. Relations that + * are not specified as FOR UPDATE/SHARE are marked ROW_MARK_REFERENCE (if + * regular tables or supported foreign tables) or ROW_MARK_COPY (if not). + * + * Initially all PlanRowMarks have rti == prti and isParent == false. + * When the planner discovers that a relation is the root of an inheritance + * tree, it sets isParent true, and adds an additional PlanRowMark to the + * list for each child relation (including the target rel itself in its role + * as a child, if it is not a partitioned table). Any non-leaf partitioned + * child relations will also have entries with isParent = true. The child + * entries have rti == child rel's RT index and prti == top parent's RT index, + * and can therefore be recognized as children by the fact that prti != rti. + * The parent's allMarkTypes field gets the OR of (1<<markType) across all + * its children (this definition allows children to use different markTypes). + * + * The planner also adds resjunk output columns to the plan that carry + * information sufficient to identify the locked or fetched rows. When + * markType != ROW_MARK_COPY, these columns are named + * tableoid%u OID of table + * ctid%u TID of row + * The tableoid column is only present for an inheritance hierarchy. + * When markType == ROW_MARK_COPY, there is instead a single column named + * wholerow%u whole-row value of relation + * (An inheritance hierarchy could have all three resjunk output columns, + * if some children use a different markType than others.) + * In all three cases, %u represents the rowmark ID number (rowmarkId). + * This number is unique within a plan tree, except that child relation + * entries copy their parent's rowmarkId. (Assigning unique numbers + * means we needn't renumber rowmarkIds when flattening subqueries, which + * would require finding and renaming the resjunk columns as well.) + * Note this means that all tables in an inheritance hierarchy share the + * same resjunk column names. + */ +typedef struct PlanRowMark +{ + pg_node_attr(no_equal, no_query_jumble) + + NodeTag type; + Index rti; /* range table index of markable relation */ + Index prti; /* range table index of parent relation */ + Index rowmarkId; /* unique identifier for resjunk columns */ + RowMarkType markType; /* see enum above */ + int allMarkTypes; /* OR of (1<<markType) for all children */ + LockClauseStrength strength; /* LockingClause's strength, or LCS_NONE */ + LockWaitPolicy waitPolicy; /* NOWAIT and SKIP LOCKED options */ + bool isParent; /* true if this is a "dummy" parent entry */ +} PlanRowMark; + + +/* + * Node types to represent partition pruning information. + */ + +/* + * PartitionPruneInfo - Details required to allow the executor to prune + * partitions. + * + * Here we store mapping details to allow translation of a partitioned table's + * index as returned by the partition pruning code into subplan indexes for + * plan types which support arbitrary numbers of subplans, such as Append. + * We also store various details to tell the executor when it should be + * performing partition pruning. + * + * Each PartitionedRelPruneInfo describes the partitioning rules for a single + * partitioned table (a/k/a level of partitioning). Since a partitioning + * hierarchy could contain multiple levels, we represent it by a List of + * PartitionedRelPruneInfos, where the first entry represents the topmost + * partitioned table and additional entries represent non-leaf child + * partitions, ordered such that parents appear before their children. + * Then, since an Append-type node could have multiple partitioning + * hierarchies among its children, we have an unordered List of those Lists. + * + * prune_infos List of Lists containing PartitionedRelPruneInfo nodes, + * one sublist per run-time-prunable partition hierarchy + * appearing in the parent plan node's subplans. + * other_subplans Indexes of any subplans that are not accounted for + * by any of the PartitionedRelPruneInfo nodes in + * "prune_infos". These subplans must not be pruned. + */ +typedef struct PartitionPruneInfo +{ + pg_node_attr(no_equal, no_query_jumble) + + NodeTag type; + List *prune_infos; + Bitmapset *other_subplans; +} PartitionPruneInfo; + +/* + * PartitionedRelPruneInfo - Details required to allow the executor to prune + * partitions for a single partitioned table. + * + * subplan_map[] and subpart_map[] are indexed by partition index of the + * partitioned table referenced by 'rtindex', the partition index being the + * order that the partitions are defined in the table's PartitionDesc. For a + * leaf partition p, subplan_map[p] contains the zero-based index of the + * partition's subplan in the parent plan's subplan list; it is -1 if the + * partition is non-leaf or has been pruned. For a non-leaf partition p, + * subpart_map[p] contains the zero-based index of that sub-partition's + * PartitionedRelPruneInfo in the hierarchy's PartitionedRelPruneInfo list; + * it is -1 if the partition is a leaf or has been pruned. Note that subplan + * indexes, as stored in 'subplan_map', are global across the parent plan + * node, but partition indexes are valid only within a particular hierarchy. + * relid_map[p] contains the partition's OID, or 0 if the partition was pruned. + */ +typedef struct PartitionedRelPruneInfo +{ + pg_node_attr(no_equal, no_query_jumble) + + NodeTag type; + + /* RT index of partition rel for this level */ + Index rtindex; + + /* Indexes of all partitions which subplans or subparts are present for */ + Bitmapset *present_parts; + + /* Length of the following arrays: */ + int nparts; + + /* subplan index by partition index, or -1 */ + int *subplan_map pg_node_attr(array_size(nparts)); + + /* subpart index by partition index, or -1 */ + int *subpart_map pg_node_attr(array_size(nparts)); + + /* relation OID by partition index, or 0 */ + Oid *relid_map pg_node_attr(array_size(nparts)); + + /* + * initial_pruning_steps shows how to prune during executor startup (i.e., + * without use of any PARAM_EXEC Params); it is NIL if no startup pruning + * is required. exec_pruning_steps shows how to prune with PARAM_EXEC + * Params; it is NIL if no per-scan pruning is required. + */ + List *initial_pruning_steps; /* List of PartitionPruneStep */ + List *exec_pruning_steps; /* List of PartitionPruneStep */ + + /* All PARAM_EXEC Param IDs in exec_pruning_steps */ + Bitmapset *execparamids; +} PartitionedRelPruneInfo; + +/* + * Abstract Node type for partition pruning steps (there are no concrete + * Nodes of this type). + * + * step_id is the global identifier of the step within its pruning context. + */ +typedef struct PartitionPruneStep +{ + pg_node_attr(abstract, no_equal, no_query_jumble) + + NodeTag type; + int step_id; +} PartitionPruneStep; + +/* + * PartitionPruneStepOp - Information to prune using a set of mutually ANDed + * OpExpr clauses + * + * This contains information extracted from up to partnatts OpExpr clauses, + * where partnatts is the number of partition key columns. 'opstrategy' is the + * strategy of the operator in the clause matched to the last partition key. + * 'exprs' contains expressions which comprise the lookup key to be passed to + * the partition bound search function. 'cmpfns' contains the OIDs of + * comparison functions used to compare aforementioned expressions with + * partition bounds. Both 'exprs' and 'cmpfns' contain the same number of + * items, up to partnatts items. + * + * Once we find the offset of a partition bound using the lookup key, we + * determine which partitions to include in the result based on the value of + * 'opstrategy'. For example, if it were equality, we'd return just the + * partition that would contain that key or a set of partitions if the key + * didn't consist of all partitioning columns. For non-equality strategies, + * we'd need to include other partitions as appropriate. + * + * 'nullkeys' is the set containing the offset of the partition keys (0 to + * partnatts - 1) that were matched to an IS NULL clause. This is only + * considered for hash partitioning as we need to pass which keys are null + * to the hash partition bound search function. It is never possible to + * have an expression be present in 'exprs' for a given partition key and + * the corresponding bit set in 'nullkeys'. + */ +typedef struct PartitionPruneStepOp +{ + PartitionPruneStep step; + + StrategyNumber opstrategy; + List *exprs; + List *cmpfns; + Bitmapset *nullkeys; +} PartitionPruneStepOp; + +/* + * PartitionPruneStepCombine - Information to prune using a BoolExpr clause + * + * For BoolExpr clauses, we combine the set of partitions determined for each + * of the argument clauses. + */ +typedef enum PartitionPruneCombineOp +{ + PARTPRUNE_COMBINE_UNION, + PARTPRUNE_COMBINE_INTERSECT +} PartitionPruneCombineOp; + +typedef struct PartitionPruneStepCombine +{ + PartitionPruneStep step; + + PartitionPruneCombineOp combineOp; + List *source_stepids; +} PartitionPruneStepCombine; + + +/* + * Plan invalidation info + * + * We track the objects on which a PlannedStmt depends in two ways: + * relations are recorded as a simple list of OIDs, and everything else + * is represented as a list of PlanInvalItems. A PlanInvalItem is designed + * to be used with the syscache invalidation mechanism, so it identifies a + * system catalog entry by cache ID and hash value. + */ +typedef struct PlanInvalItem +{ + pg_node_attr(no_equal, no_query_jumble) + + NodeTag type; + int cacheId; /* a syscache ID, see utils/syscache.h */ + uint32 hashValue; /* hash value of object's cache lookup key */ +} PlanInvalItem; + +/* + * MonotonicFunction + * + * Allows the planner to track monotonic properties of functions. A function + * is monotonically increasing if a subsequent call cannot yield a lower value + * than the previous call. A monotonically decreasing function cannot yield a + * higher value on subsequent calls, and a function which is both must return + * the same value on each call. + */ +typedef enum MonotonicFunction +{ + MONOTONICFUNC_NONE = 0, + MONOTONICFUNC_INCREASING = (1 << 0), + MONOTONICFUNC_DECREASING = (1 << 1), + MONOTONICFUNC_BOTH = MONOTONICFUNC_INCREASING | MONOTONICFUNC_DECREASING +} MonotonicFunction; + +#endif /* PLANNODES_H */ diff --git a/src/include/nodes/primnodes.h b/src/include/nodes/primnodes.h new file mode 100644 index 0000000..e1aadc3 --- /dev/null +++ b/src/include/nodes/primnodes.h @@ -0,0 +1,2041 @@ +/*------------------------------------------------------------------------- + * + * primnodes.h + * Definitions for "primitive" node types, those that are used in more + * than one of the parse/plan/execute stages of the query pipeline. + * Currently, these are mostly nodes for executable expressions + * and join trees. + * + * + * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/nodes/primnodes.h + * + *------------------------------------------------------------------------- + */ +#ifndef PRIMNODES_H +#define PRIMNODES_H + +#include "access/attnum.h" +#include "nodes/bitmapset.h" +#include "nodes/pg_list.h" + + +/* ---------------------------------------------------------------- + * node definitions + * ---------------------------------------------------------------- + */ + +/* + * Alias - + * specifies an alias for a range variable; the alias might also + * specify renaming of columns within the table. + * + * Note: colnames is a list of String nodes. In Alias structs + * associated with RTEs, there may be entries corresponding to dropped + * columns; these are normally empty strings (""). See parsenodes.h for info. + */ +typedef struct Alias +{ + NodeTag type; + char *aliasname; /* aliased rel name (never qualified) */ + List *colnames; /* optional list of column aliases */ +} Alias; + +/* What to do at commit time for temporary relations */ +typedef enum OnCommitAction +{ + ONCOMMIT_NOOP, /* No ON COMMIT clause (do nothing) */ + ONCOMMIT_PRESERVE_ROWS, /* ON COMMIT PRESERVE ROWS (do nothing) */ + ONCOMMIT_DELETE_ROWS, /* ON COMMIT DELETE ROWS */ + ONCOMMIT_DROP /* ON COMMIT DROP */ +} OnCommitAction; + +/* + * RangeVar - range variable, used in FROM clauses + * + * Also used to represent table names in utility statements; there, the alias + * field is not used, and inh tells whether to apply the operation + * recursively to child tables. In some contexts it is also useful to carry + * a TEMP table indication here. + */ +typedef struct RangeVar +{ + NodeTag type; + + /* the catalog (database) name, or NULL */ + char *catalogname; + + /* the schema name, or NULL */ + char *schemaname; + + /* the relation/sequence name */ + char *relname; + + /* expand rel by inheritance? recursively act on children? */ + bool inh; + + /* see RELPERSISTENCE_* in pg_class.h */ + char relpersistence; + + /* table alias & optional column aliases */ + Alias *alias; + + /* token location, or -1 if unknown */ + int location; +} RangeVar; + +/* + * TableFunc - node for a table function, such as XMLTABLE. + * + * Entries in the ns_names list are either String nodes containing + * literal namespace names, or NULL pointers to represent DEFAULT. + */ +typedef struct TableFunc +{ + NodeTag type; + /* list of namespace URI expressions */ + List *ns_uris pg_node_attr(query_jumble_ignore); + /* list of namespace names or NULL */ + List *ns_names pg_node_attr(query_jumble_ignore); + /* input document expression */ + Node *docexpr; + /* row filter expression */ + Node *rowexpr; + /* column names (list of String) */ + List *colnames pg_node_attr(query_jumble_ignore); + /* OID list of column type OIDs */ + List *coltypes pg_node_attr(query_jumble_ignore); + /* integer list of column typmods */ + List *coltypmods pg_node_attr(query_jumble_ignore); + /* OID list of column collation OIDs */ + List *colcollations pg_node_attr(query_jumble_ignore); + /* list of column filter expressions */ + List *colexprs; + /* list of column default expressions */ + List *coldefexprs pg_node_attr(query_jumble_ignore); + /* nullability flag for each output column */ + Bitmapset *notnulls pg_node_attr(query_jumble_ignore); + /* counts from 0; -1 if none specified */ + int ordinalitycol pg_node_attr(query_jumble_ignore); + /* token location, or -1 if unknown */ + int location; +} TableFunc; + +/* + * IntoClause - target information for SELECT INTO, CREATE TABLE AS, and + * CREATE MATERIALIZED VIEW + * + * For CREATE MATERIALIZED VIEW, viewQuery is the parsed-but-not-rewritten + * SELECT Query for the view; otherwise it's NULL. This is irrelevant in + * the query jumbling as CreateTableAsStmt already includes a reference to + * its own Query, so ignore it. (Although it's actually Query*, we declare + * it as Node* to avoid a forward reference.) + */ +typedef struct IntoClause +{ + NodeTag type; + + RangeVar *rel; /* target relation name */ + List *colNames; /* column names to assign, or NIL */ + char *accessMethod; /* table access method */ + List *options; /* options from WITH clause */ + OnCommitAction onCommit; /* what do we do at COMMIT? */ + char *tableSpaceName; /* table space to use, or NULL */ + /* materialized view's SELECT query */ + Node *viewQuery pg_node_attr(query_jumble_ignore); + bool skipData; /* true for WITH NO DATA */ +} IntoClause; + + +/* ---------------------------------------------------------------- + * node types for executable expressions + * ---------------------------------------------------------------- + */ + +/* + * Expr - generic superclass for executable-expression nodes + * + * All node types that are used in executable expression trees should derive + * from Expr (that is, have Expr as their first field). Since Expr only + * contains NodeTag, this is a formality, but it is an easy form of + * documentation. See also the ExprState node types in execnodes.h. + */ +typedef struct Expr +{ + pg_node_attr(abstract) + + NodeTag type; +} Expr; + +/* + * Var - expression node representing a variable (ie, a table column) + * + * In the parser and planner, varno and varattno identify the semantic + * referent, which is a base-relation column unless the reference is to a join + * USING column that isn't semantically equivalent to either join input column + * (because it is a FULL join or the input column requires a type coercion). + * In those cases varno and varattno refer to the JOIN RTE. (Early in the + * planner, we replace such join references by the implied expression; but up + * till then we want join reference Vars to keep their original identity for + * query-printing purposes.) + * + * At the end of planning, Var nodes appearing in upper-level plan nodes are + * reassigned to point to the outputs of their subplans; for example, in a + * join node varno becomes INNER_VAR or OUTER_VAR and varattno becomes the + * index of the proper element of that subplan's target list. Similarly, + * INDEX_VAR is used to identify Vars that reference an index column rather + * than a heap column. (In ForeignScan and CustomScan plan nodes, INDEX_VAR + * is abused to signify references to columns of a custom scan tuple type.) + * + * ROWID_VAR is used in the planner to identify nonce variables that carry + * row identity information during UPDATE/DELETE/MERGE. This value should + * never be seen outside the planner. + * + * varnullingrels is the set of RT indexes of outer joins that can force + * the Var's value to null (at the point where it appears in the query). + * See optimizer/README for discussion of that. + * + * varlevelsup is greater than zero in Vars that represent outer references. + * Note that it affects the meaning of all of varno, varnullingrels, and + * varnosyn, all of which refer to the range table of that query level. + * + * In the parser, varnosyn and varattnosyn are either identical to + * varno/varattno, or they specify the column's position in an aliased JOIN + * RTE that hides the semantic referent RTE's refname. This is a syntactic + * identifier as opposed to the semantic identifier; it tells ruleutils.c + * how to print the Var properly. varnosyn/varattnosyn retain their values + * throughout planning and execution, so they are particularly helpful to + * identify Vars when debugging. Note, however, that a Var that is generated + * in the planner and doesn't correspond to any simple relation column may + * have varnosyn = varattnosyn = 0. + */ +#define INNER_VAR (-1) /* reference to inner subplan */ +#define OUTER_VAR (-2) /* reference to outer subplan */ +#define INDEX_VAR (-3) /* reference to index column */ +#define ROWID_VAR (-4) /* row identity column during planning */ + +#define IS_SPECIAL_VARNO(varno) ((int) (varno) < 0) + +/* Symbols for the indexes of the special RTE entries in rules */ +#define PRS2_OLD_VARNO 1 +#define PRS2_NEW_VARNO 2 + +typedef struct Var +{ + Expr xpr; + + /* + * index of this var's relation in the range table, or + * INNER_VAR/OUTER_VAR/etc + */ + int varno; + + /* + * attribute number of this var, or zero for all attrs ("whole-row Var") + */ + AttrNumber varattno; + + /* pg_type OID for the type of this var */ + Oid vartype pg_node_attr(query_jumble_ignore); + /* pg_attribute typmod value */ + int32 vartypmod pg_node_attr(query_jumble_ignore); + /* OID of collation, or InvalidOid if none */ + Oid varcollid pg_node_attr(query_jumble_ignore); + + /* + * RT indexes of outer joins that can replace the Var's value with null. + * We can omit varnullingrels in the query jumble, because it's fully + * determined by varno/varlevelsup plus the Var's query location. + */ + Bitmapset *varnullingrels pg_node_attr(query_jumble_ignore); + + /* + * for subquery variables referencing outer relations; 0 in a normal var, + * >0 means N levels up + */ + Index varlevelsup; + + /* + * varnosyn/varattnosyn are ignored for equality, because Vars with + * different syntactic identifiers are semantically the same as long as + * their varno/varattno match. + */ + /* syntactic relation index (0 if unknown) */ + Index varnosyn pg_node_attr(equal_ignore, query_jumble_ignore); + /* syntactic attribute number */ + AttrNumber varattnosyn pg_node_attr(equal_ignore, query_jumble_ignore); + + /* token location, or -1 if unknown */ + int location; +} Var; + +/* + * Const + * + * Note: for varlena data types, we make a rule that a Const node's value + * must be in non-extended form (4-byte header, no compression or external + * references). This ensures that the Const node is self-contained and makes + * it more likely that equal() will see logically identical values as equal. + * + * Only the constant type OID is relevant for the query jumbling. + */ +typedef struct Const +{ + pg_node_attr(custom_copy_equal, custom_read_write) + + Expr xpr; + /* pg_type OID of the constant's datatype */ + Oid consttype; + /* typmod value, if any */ + int32 consttypmod pg_node_attr(query_jumble_ignore); + /* OID of collation, or InvalidOid if none */ + Oid constcollid pg_node_attr(query_jumble_ignore); + /* typlen of the constant's datatype */ + int constlen pg_node_attr(query_jumble_ignore); + /* the constant's value */ + Datum constvalue pg_node_attr(query_jumble_ignore); + /* whether the constant is null (if true, constvalue is undefined) */ + bool constisnull pg_node_attr(query_jumble_ignore); + + /* + * Whether this datatype is passed by value. If true, then all the + * information is stored in the Datum. If false, then the Datum contains + * a pointer to the information. + */ + bool constbyval pg_node_attr(query_jumble_ignore); + + /* + * token location, or -1 if unknown. All constants are tracked as + * locations in query jumbling, to be marked as parameters. + */ + int location pg_node_attr(query_jumble_location); +} Const; + +/* + * Param + * + * paramkind specifies the kind of parameter. The possible values + * for this field are: + * + * PARAM_EXTERN: The parameter value is supplied from outside the plan. + * Such parameters are numbered from 1 to n. + * + * PARAM_EXEC: The parameter is an internal executor parameter, used + * for passing values into and out of sub-queries or from + * nestloop joins to their inner scans. + * For historical reasons, such parameters are numbered from 0. + * These numbers are independent of PARAM_EXTERN numbers. + * + * PARAM_SUBLINK: The parameter represents an output column of a SubLink + * node's sub-select. The column number is contained in the + * `paramid' field. (This type of Param is converted to + * PARAM_EXEC during planning.) + * + * PARAM_MULTIEXPR: Like PARAM_SUBLINK, the parameter represents an + * output column of a SubLink node's sub-select, but here, the + * SubLink is always a MULTIEXPR SubLink. The high-order 16 bits + * of the `paramid' field contain the SubLink's subLinkId, and + * the low-order 16 bits contain the column number. (This type + * of Param is also converted to PARAM_EXEC during planning.) + */ +typedef enum ParamKind +{ + PARAM_EXTERN, + PARAM_EXEC, + PARAM_SUBLINK, + PARAM_MULTIEXPR +} ParamKind; + +typedef struct Param +{ + Expr xpr; + ParamKind paramkind; /* kind of parameter. See above */ + int paramid; /* numeric ID for parameter */ + Oid paramtype; /* pg_type OID of parameter's datatype */ + /* typmod value, if known */ + int32 paramtypmod pg_node_attr(query_jumble_ignore); + /* OID of collation, or InvalidOid if none */ + Oid paramcollid pg_node_attr(query_jumble_ignore); + /* token location, or -1 if unknown */ + int location; +} Param; + +/* + * Aggref + * + * The aggregate's args list is a targetlist, ie, a list of TargetEntry nodes. + * + * For a normal (non-ordered-set) aggregate, the non-resjunk TargetEntries + * represent the aggregate's regular arguments (if any) and resjunk TLEs can + * be added at the end to represent ORDER BY expressions that are not also + * arguments. As in a top-level Query, the TLEs can be marked with + * ressortgroupref indexes to let them be referenced by SortGroupClause + * entries in the aggorder and/or aggdistinct lists. This represents ORDER BY + * and DISTINCT operations to be applied to the aggregate input rows before + * they are passed to the transition function. The grammar only allows a + * simple "DISTINCT" specifier for the arguments, but we use the full + * query-level representation to allow more code sharing. + * + * For an ordered-set aggregate, the args list represents the WITHIN GROUP + * (aggregated) arguments, all of which will be listed in the aggorder list. + * DISTINCT is not supported in this case, so aggdistinct will be NIL. + * The direct arguments appear in aggdirectargs (as a list of plain + * expressions, not TargetEntry nodes). + * + * aggtranstype is the data type of the state transition values for this + * aggregate (resolved to an actual type, if agg's transtype is polymorphic). + * This is determined during planning and is InvalidOid before that. + * + * aggargtypes is an OID list of the data types of the direct and regular + * arguments. Normally it's redundant with the aggdirectargs and args lists, + * but in a combining aggregate, it's not because the args list has been + * replaced with a single argument representing the partial-aggregate + * transition values. + * + * aggpresorted is set by the query planner for ORDER BY and DISTINCT + * aggregates where the chosen plan provides presorted input for this + * aggregate during execution. + * + * aggsplit indicates the expected partial-aggregation mode for the Aggref's + * parent plan node. It's always set to AGGSPLIT_SIMPLE in the parser, but + * the planner might change it to something else. We use this mainly as + * a crosscheck that the Aggrefs match the plan; but note that when aggsplit + * indicates a non-final mode, aggtype reflects the transition data type + * not the SQL-level output type of the aggregate. + * + * aggno and aggtransno are -1 in the parse stage, and are set in planning. + * Aggregates with the same 'aggno' represent the same aggregate expression, + * and can share the result. Aggregates with same 'transno' but different + * 'aggno' can share the same transition state, only the final function needs + * to be called separately. + * + * Information related to collations, transition types and internal states + * are irrelevant for the query jumbling. + */ +typedef struct Aggref +{ + Expr xpr; + + /* pg_proc Oid of the aggregate */ + Oid aggfnoid; + + /* type Oid of result of the aggregate */ + Oid aggtype pg_node_attr(query_jumble_ignore); + + /* OID of collation of result */ + Oid aggcollid pg_node_attr(query_jumble_ignore); + + /* OID of collation that function should use */ + Oid inputcollid pg_node_attr(query_jumble_ignore); + + /* + * type Oid of aggregate's transition value; ignored for equal since it + * might not be set yet + */ + Oid aggtranstype pg_node_attr(equal_ignore, query_jumble_ignore); + + /* type Oids of direct and aggregated args */ + List *aggargtypes pg_node_attr(query_jumble_ignore); + + /* direct arguments, if an ordered-set agg */ + List *aggdirectargs; + + /* aggregated arguments and sort expressions */ + List *args; + + /* ORDER BY (list of SortGroupClause) */ + List *aggorder; + + /* DISTINCT (list of SortGroupClause) */ + List *aggdistinct; + + /* FILTER expression, if any */ + Expr *aggfilter; + + /* true if argument list was really '*' */ + bool aggstar pg_node_attr(query_jumble_ignore); + + /* + * true if variadic arguments have been combined into an array last + * argument + */ + bool aggvariadic pg_node_attr(query_jumble_ignore); + + /* aggregate kind (see pg_aggregate.h) */ + char aggkind pg_node_attr(query_jumble_ignore); + + /* aggregate input already sorted */ + bool aggpresorted pg_node_attr(equal_ignore, query_jumble_ignore); + + /* > 0 if agg belongs to outer query */ + Index agglevelsup pg_node_attr(query_jumble_ignore); + + /* expected agg-splitting mode of parent Agg */ + AggSplit aggsplit pg_node_attr(query_jumble_ignore); + + /* unique ID within the Agg node */ + int aggno pg_node_attr(query_jumble_ignore); + + /* unique ID of transition state in the Agg */ + int aggtransno pg_node_attr(query_jumble_ignore); + + /* token location, or -1 if unknown */ + int location; +} Aggref; + +/* + * GroupingFunc + * + * A GroupingFunc is a GROUPING(...) expression, which behaves in many ways + * like an aggregate function (e.g. it "belongs" to a specific query level, + * which might not be the one immediately containing it), but also differs in + * an important respect: it never evaluates its arguments, they merely + * designate expressions from the GROUP BY clause of the query level to which + * it belongs. + * + * The spec defines the evaluation of GROUPING() purely by syntactic + * replacement, but we make it a real expression for optimization purposes so + * that one Agg node can handle multiple grouping sets at once. Evaluating the + * result only needs the column positions to check against the grouping set + * being projected. However, for EXPLAIN to produce meaningful output, we have + * to keep the original expressions around, since expression deparse does not + * give us any feasible way to get at the GROUP BY clause. + * + * Also, we treat two GroupingFunc nodes as equal if they have equal arguments + * lists and agglevelsup, without comparing the refs and cols annotations. + * + * In raw parse output we have only the args list; parse analysis fills in the + * refs list, and the planner fills in the cols list. + * + * All the fields used as information for an internal state are irrelevant + * for the query jumbling. + */ +typedef struct GroupingFunc +{ + Expr xpr; + + /* arguments, not evaluated but kept for benefit of EXPLAIN etc. */ + List *args pg_node_attr(query_jumble_ignore); + + /* ressortgrouprefs of arguments */ + List *refs pg_node_attr(equal_ignore); + + /* actual column positions set by planner */ + List *cols pg_node_attr(equal_ignore, query_jumble_ignore); + + /* same as Aggref.agglevelsup */ + Index agglevelsup; + + /* token location */ + int location; +} GroupingFunc; + +/* + * WindowFunc + * + * Collation information is irrelevant for the query jumbling, as is the + * internal state information of the node like "winstar" and "winagg". + */ +typedef struct WindowFunc +{ + Expr xpr; + /* pg_proc Oid of the function */ + Oid winfnoid; + /* type Oid of result of the window function */ + Oid wintype pg_node_attr(query_jumble_ignore); + /* OID of collation of result */ + Oid wincollid pg_node_attr(query_jumble_ignore); + /* OID of collation that function should use */ + Oid inputcollid pg_node_attr(query_jumble_ignore); + /* arguments to the window function */ + List *args; + /* FILTER expression, if any */ + Expr *aggfilter; + /* index of associated WindowClause */ + Index winref; + /* true if argument list was really '*' */ + bool winstar pg_node_attr(query_jumble_ignore); + /* is function a simple aggregate? */ + bool winagg pg_node_attr(query_jumble_ignore); + /* token location, or -1 if unknown */ + int location; +} WindowFunc; + +/* + * SubscriptingRef: describes a subscripting operation over a container + * (array, etc). + * + * A SubscriptingRef can describe fetching a single element from a container, + * fetching a part of a container (e.g. an array slice), storing a single + * element into a container, or storing a slice. The "store" cases work with + * an initial container value and a source value that is inserted into the + * appropriate part of the container; the result of the operation is an + * entire new modified container value. + * + * If reflowerindexpr = NIL, then we are fetching or storing a single container + * element at the subscripts given by refupperindexpr. Otherwise we are + * fetching or storing a container slice, that is a rectangular subcontainer + * with lower and upper bounds given by the index expressions. + * reflowerindexpr must be the same length as refupperindexpr when it + * is not NIL. + * + * In the slice case, individual expressions in the subscript lists can be + * NULL, meaning "substitute the array's current lower or upper bound". + * (Non-array containers may or may not support this.) + * + * refcontainertype is the actual container type that determines the + * subscripting semantics. (This will generally be either the exposed type of + * refexpr, or the base type if that is a domain.) refelemtype is the type of + * the container's elements; this is saved for the use of the subscripting + * functions, but is not used by the core code. refrestype, reftypmod, and + * refcollid describe the type of the SubscriptingRef's result. In a store + * expression, refrestype will always match refcontainertype; in a fetch, + * it could be refelemtype for an element fetch, or refcontainertype for a + * slice fetch, or possibly something else as determined by type-specific + * subscripting logic. Likewise, reftypmod and refcollid will match the + * container's properties in a store, but could be different in a fetch. + * + * Any internal state data is ignored for the query jumbling. + * + * Note: for the cases where a container is returned, if refexpr yields a R/W + * expanded container, then the implementation is allowed to modify that + * object in-place and return the same object. + */ +typedef struct SubscriptingRef +{ + Expr xpr; + /* type of the container proper */ + Oid refcontainertype pg_node_attr(query_jumble_ignore); + /* the container type's pg_type.typelem */ + Oid refelemtype pg_node_attr(query_jumble_ignore); + /* type of the SubscriptingRef's result */ + Oid refrestype pg_node_attr(query_jumble_ignore); + /* typmod of the result */ + int32 reftypmod pg_node_attr(query_jumble_ignore); + /* collation of result, or InvalidOid if none */ + Oid refcollid pg_node_attr(query_jumble_ignore); + /* expressions that evaluate to upper container indexes */ + List *refupperindexpr; + + /* + * expressions that evaluate to lower container indexes, or NIL for single + * container element. + */ + List *reflowerindexpr; + /* the expression that evaluates to a container value */ + Expr *refexpr; + /* expression for the source value, or NULL if fetch */ + Expr *refassgnexpr; +} SubscriptingRef; + +/* + * CoercionContext - distinguishes the allowed set of type casts + * + * NB: ordering of the alternatives is significant; later (larger) values + * allow more casts than earlier ones. + */ +typedef enum CoercionContext +{ + COERCION_IMPLICIT, /* coercion in context of expression */ + COERCION_ASSIGNMENT, /* coercion in context of assignment */ + COERCION_PLPGSQL, /* if no assignment cast, use CoerceViaIO */ + COERCION_EXPLICIT /* explicit cast operation */ +} CoercionContext; + +/* + * CoercionForm - how to display a FuncExpr or related node + * + * "Coercion" is a bit of a misnomer, since this value records other + * special syntaxes besides casts, but for now we'll keep this naming. + * + * NB: equal() ignores CoercionForm fields, therefore this *must* not carry + * any semantically significant information. We need that behavior so that + * the planner will consider equivalent implicit and explicit casts to be + * equivalent. In cases where those actually behave differently, the coercion + * function's arguments will be different. + */ +typedef enum CoercionForm +{ + COERCE_EXPLICIT_CALL, /* display as a function call */ + COERCE_EXPLICIT_CAST, /* display as an explicit cast */ + COERCE_IMPLICIT_CAST, /* implicit cast, so hide it */ + COERCE_SQL_SYNTAX /* display with SQL-mandated special syntax */ +} CoercionForm; + +/* + * FuncExpr - expression node for a function call + * + * Collation information is irrelevant for the query jumbling, only the + * arguments and the function OID matter. + */ +typedef struct FuncExpr +{ + Expr xpr; + /* PG_PROC OID of the function */ + Oid funcid; + /* PG_TYPE OID of result value */ + Oid funcresulttype pg_node_attr(query_jumble_ignore); + /* true if function returns set */ + bool funcretset pg_node_attr(query_jumble_ignore); + + /* + * true if variadic arguments have been combined into an array last + * argument + */ + bool funcvariadic pg_node_attr(query_jumble_ignore); + /* how to display this function call */ + CoercionForm funcformat pg_node_attr(query_jumble_ignore); + /* OID of collation of result */ + Oid funccollid pg_node_attr(query_jumble_ignore); + /* OID of collation that function should use */ + Oid inputcollid pg_node_attr(query_jumble_ignore); + /* arguments to the function */ + List *args; + /* token location, or -1 if unknown */ + int location; +} FuncExpr; + +/* + * NamedArgExpr - a named argument of a function + * + * This node type can only appear in the args list of a FuncCall or FuncExpr + * node. We support pure positional call notation (no named arguments), + * named notation (all arguments are named), and mixed notation (unnamed + * arguments followed by named ones). + * + * Parse analysis sets argnumber to the positional index of the argument, + * but doesn't rearrange the argument list. + * + * The planner will convert argument lists to pure positional notation + * during expression preprocessing, so execution never sees a NamedArgExpr. + */ +typedef struct NamedArgExpr +{ + Expr xpr; + /* the argument expression */ + Expr *arg; + /* the name */ + char *name pg_node_attr(query_jumble_ignore); + /* argument's number in positional notation */ + int argnumber; + /* argument name location, or -1 if unknown */ + int location; +} NamedArgExpr; + +/* + * OpExpr - expression node for an operator invocation + * + * Semantically, this is essentially the same as a function call. + * + * Note that opfuncid is not necessarily filled in immediately on creation + * of the node. The planner makes sure it is valid before passing the node + * tree to the executor, but during parsing/planning opfuncid can be 0. + * Therefore, equal() will accept a zero value as being equal to other values. + * + * Internal state information and collation data is irrelevant for the query + * jumbling. + */ +typedef struct OpExpr +{ + Expr xpr; + + /* PG_OPERATOR OID of the operator */ + Oid opno; + + /* PG_PROC OID of underlying function */ + Oid opfuncid pg_node_attr(equal_ignore_if_zero, query_jumble_ignore); + + /* PG_TYPE OID of result value */ + Oid opresulttype pg_node_attr(query_jumble_ignore); + + /* true if operator returns set */ + bool opretset pg_node_attr(query_jumble_ignore); + + /* OID of collation of result */ + Oid opcollid pg_node_attr(query_jumble_ignore); + + /* OID of collation that operator should use */ + Oid inputcollid pg_node_attr(query_jumble_ignore); + + /* arguments to the operator (1 or 2) */ + List *args; + + /* token location, or -1 if unknown */ + int location; +} OpExpr; + +/* + * DistinctExpr - expression node for "x IS DISTINCT FROM y" + * + * Except for the nodetag, this is represented identically to an OpExpr + * referencing the "=" operator for x and y. + * We use "=", not the more obvious "<>", because more datatypes have "=" + * than "<>". This means the executor must invert the operator result. + * Note that the operator function won't be called at all if either input + * is NULL, since then the result can be determined directly. + */ +typedef OpExpr DistinctExpr; + +/* + * NullIfExpr - a NULLIF expression + * + * Like DistinctExpr, this is represented the same as an OpExpr referencing + * the "=" operator for x and y. + */ +typedef OpExpr NullIfExpr; + +/* + * ScalarArrayOpExpr - expression node for "scalar op ANY/ALL (array)" + * + * The operator must yield boolean. It is applied to the left operand + * and each element of the righthand array, and the results are combined + * with OR or AND (for ANY or ALL respectively). The node representation + * is almost the same as for the underlying operator, but we need a useOr + * flag to remember whether it's ANY or ALL, and we don't have to store + * the result type (or the collation) because it must be boolean. + * + * A ScalarArrayOpExpr with a valid hashfuncid is evaluated during execution + * by building a hash table containing the Const values from the RHS arg. + * This table is probed during expression evaluation. The planner will set + * hashfuncid to the hash function which must be used to build and probe the + * hash table. The executor determines if it should use hash-based checks or + * the more traditional means based on if the hashfuncid is set or not. + * + * When performing hashed NOT IN, the negfuncid will also be set to the + * equality function which the hash table must use to build and probe the hash + * table. opno and opfuncid will remain set to the <> operator and its + * corresponding function and won't be used during execution. For + * non-hashtable based NOT INs, negfuncid will be set to InvalidOid. See + * convert_saop_to_hashed_saop(). + * + * Similar to OpExpr, opfuncid, hashfuncid, and negfuncid are not necessarily + * filled in right away, so will be ignored for equality if they are not set + * yet. + * + * OID entries of the internal function types are irrelevant for the query + * jumbling, but the operator OID and the arguments are. + */ +typedef struct ScalarArrayOpExpr +{ + Expr xpr; + + /* PG_OPERATOR OID of the operator */ + Oid opno; + + /* PG_PROC OID of comparison function */ + Oid opfuncid pg_node_attr(equal_ignore_if_zero, query_jumble_ignore); + + /* PG_PROC OID of hash func or InvalidOid */ + Oid hashfuncid pg_node_attr(equal_ignore_if_zero, query_jumble_ignore); + + /* PG_PROC OID of negator of opfuncid function or InvalidOid. See above */ + Oid negfuncid pg_node_attr(equal_ignore_if_zero, query_jumble_ignore); + + /* true for ANY, false for ALL */ + bool useOr; + + /* OID of collation that operator should use */ + Oid inputcollid pg_node_attr(query_jumble_ignore); + + /* the scalar and array operands */ + List *args; + + /* token location, or -1 if unknown */ + int location; +} ScalarArrayOpExpr; + +/* + * BoolExpr - expression node for the basic Boolean operators AND, OR, NOT + * + * Notice the arguments are given as a List. For NOT, of course the list + * must always have exactly one element. For AND and OR, there can be two + * or more arguments. + */ +typedef enum BoolExprType +{ + AND_EXPR, OR_EXPR, NOT_EXPR +} BoolExprType; + +typedef struct BoolExpr +{ + pg_node_attr(custom_read_write) + + Expr xpr; + BoolExprType boolop; + List *args; /* arguments to this expression */ + int location; /* token location, or -1 if unknown */ +} BoolExpr; + +/* + * SubLink + * + * A SubLink represents a subselect appearing in an expression, and in some + * cases also the combining operator(s) just above it. The subLinkType + * indicates the form of the expression represented: + * EXISTS_SUBLINK EXISTS(SELECT ...) + * ALL_SUBLINK (lefthand) op ALL (SELECT ...) + * ANY_SUBLINK (lefthand) op ANY (SELECT ...) + * ROWCOMPARE_SUBLINK (lefthand) op (SELECT ...) + * EXPR_SUBLINK (SELECT with single targetlist item ...) + * MULTIEXPR_SUBLINK (SELECT with multiple targetlist items ...) + * ARRAY_SUBLINK ARRAY(SELECT with single targetlist item ...) + * CTE_SUBLINK WITH query (never actually part of an expression) + * For ALL, ANY, and ROWCOMPARE, the lefthand is a list of expressions of the + * same length as the subselect's targetlist. ROWCOMPARE will *always* have + * a list with more than one entry; if the subselect has just one target + * then the parser will create an EXPR_SUBLINK instead (and any operator + * above the subselect will be represented separately). + * ROWCOMPARE, EXPR, and MULTIEXPR require the subselect to deliver at most + * one row (if it returns no rows, the result is NULL). + * ALL, ANY, and ROWCOMPARE require the combining operators to deliver boolean + * results. ALL and ANY combine the per-row results using AND and OR + * semantics respectively. + * ARRAY requires just one target column, and creates an array of the target + * column's type using any number of rows resulting from the subselect. + * + * SubLink is classed as an Expr node, but it is not actually executable; + * it must be replaced in the expression tree by a SubPlan node during + * planning. + * + * NOTE: in the raw output of gram.y, testexpr contains just the raw form + * of the lefthand expression (if any), and operName is the String name of + * the combining operator. Also, subselect is a raw parsetree. During parse + * analysis, the parser transforms testexpr into a complete boolean expression + * that compares the lefthand value(s) to PARAM_SUBLINK nodes representing the + * output columns of the subselect. And subselect is transformed to a Query. + * This is the representation seen in saved rules and in the rewriter. + * + * In EXISTS, EXPR, MULTIEXPR, and ARRAY SubLinks, testexpr and operName + * are unused and are always null. + * + * subLinkId is currently used only for MULTIEXPR SubLinks, and is zero in + * other SubLinks. This number identifies different multiple-assignment + * subqueries within an UPDATE statement's SET list. It is unique only + * within a particular targetlist. The output column(s) of the MULTIEXPR + * are referenced by PARAM_MULTIEXPR Params appearing elsewhere in the tlist. + * + * The CTE_SUBLINK case never occurs in actual SubLink nodes, but it is used + * in SubPlans generated for WITH subqueries. + */ +typedef enum SubLinkType +{ + EXISTS_SUBLINK, + ALL_SUBLINK, + ANY_SUBLINK, + ROWCOMPARE_SUBLINK, + EXPR_SUBLINK, + MULTIEXPR_SUBLINK, + ARRAY_SUBLINK, + CTE_SUBLINK /* for SubPlans only */ +} SubLinkType; + + +typedef struct SubLink +{ + Expr xpr; + SubLinkType subLinkType; /* see above */ + int subLinkId; /* ID (1..n); 0 if not MULTIEXPR */ + Node *testexpr; /* outer-query test for ALL/ANY/ROWCOMPARE */ + /* originally specified operator name */ + List *operName pg_node_attr(query_jumble_ignore); + /* subselect as Query* or raw parsetree */ + Node *subselect; + int location; /* token location, or -1 if unknown */ +} SubLink; + +/* + * SubPlan - executable expression node for a subplan (sub-SELECT) + * + * The planner replaces SubLink nodes in expression trees with SubPlan + * nodes after it has finished planning the subquery. SubPlan references + * a sub-plantree stored in the subplans list of the toplevel PlannedStmt. + * (We avoid a direct link to make it easier to copy expression trees + * without causing multiple processing of the subplan.) + * + * In an ordinary subplan, testexpr points to an executable expression + * (OpExpr, an AND/OR tree of OpExprs, or RowCompareExpr) for the combining + * operator(s); the left-hand arguments are the original lefthand expressions, + * and the right-hand arguments are PARAM_EXEC Param nodes representing the + * outputs of the sub-select. (NOTE: runtime coercion functions may be + * inserted as well.) This is just the same expression tree as testexpr in + * the original SubLink node, but the PARAM_SUBLINK nodes are replaced by + * suitably numbered PARAM_EXEC nodes. + * + * If the sub-select becomes an initplan rather than a subplan, the executable + * expression is part of the outer plan's expression tree (and the SubPlan + * node itself is not, but rather is found in the outer plan's initPlan + * list). In this case testexpr is NULL to avoid duplication. + * + * The planner also derives lists of the values that need to be passed into + * and out of the subplan. Input values are represented as a list "args" of + * expressions to be evaluated in the outer-query context (currently these + * args are always just Vars, but in principle they could be any expression). + * The values are assigned to the global PARAM_EXEC params indexed by parParam + * (the parParam and args lists must have the same ordering). setParam is a + * list of the PARAM_EXEC params that are computed by the sub-select, if it + * is an initplan or MULTIEXPR plan; they are listed in order by sub-select + * output column position. (parParam and setParam are integer Lists, not + * Bitmapsets, because their ordering is significant.) + * + * Also, the planner computes startup and per-call costs for use of the + * SubPlan. Note that these include the cost of the subquery proper, + * evaluation of the testexpr if any, and any hashtable management overhead. + */ +typedef struct SubPlan +{ + pg_node_attr(no_query_jumble) + + Expr xpr; + /* Fields copied from original SubLink: */ + SubLinkType subLinkType; /* see above */ + /* The combining operators, transformed to an executable expression: */ + Node *testexpr; /* OpExpr or RowCompareExpr expression tree */ + List *paramIds; /* IDs of Params embedded in the above */ + /* Identification of the Plan tree to use: */ + int plan_id; /* Index (from 1) in PlannedStmt.subplans */ + /* Identification of the SubPlan for EXPLAIN and debugging purposes: */ + char *plan_name; /* A name assigned during planning */ + /* Extra data useful for determining subplan's output type: */ + Oid firstColType; /* Type of first column of subplan result */ + int32 firstColTypmod; /* Typmod of first column of subplan result */ + Oid firstColCollation; /* Collation of first column of subplan + * result */ + /* Information about execution strategy: */ + bool useHashTable; /* true to store subselect output in a hash + * table (implies we are doing "IN") */ + bool unknownEqFalse; /* true if it's okay to return FALSE when the + * spec result is UNKNOWN; this allows much + * simpler handling of null values */ + bool parallel_safe; /* is the subplan parallel-safe? */ + /* Note: parallel_safe does not consider contents of testexpr or args */ + /* Information for passing params into and out of the subselect: */ + /* setParam and parParam are lists of integers (param IDs) */ + List *setParam; /* initplan and MULTIEXPR subqueries have to + * set these Params for parent plan */ + List *parParam; /* indices of input Params from parent plan */ + List *args; /* exprs to pass as parParam values */ + /* Estimated execution costs: */ + Cost startup_cost; /* one-time setup cost */ + Cost per_call_cost; /* cost for each subplan evaluation */ +} SubPlan; + +/* + * AlternativeSubPlan - expression node for a choice among SubPlans + * + * This is used only transiently during planning: by the time the plan + * reaches the executor, all AlternativeSubPlan nodes have been removed. + * + * The subplans are given as a List so that the node definition need not + * change if there's ever more than two alternatives. For the moment, + * though, there are always exactly two; and the first one is the fast-start + * plan. + */ +typedef struct AlternativeSubPlan +{ + pg_node_attr(no_query_jumble) + + Expr xpr; + List *subplans; /* SubPlan(s) with equivalent results */ +} AlternativeSubPlan; + +/* ---------------- + * FieldSelect + * + * FieldSelect represents the operation of extracting one field from a tuple + * value. At runtime, the input expression is expected to yield a rowtype + * Datum. The specified field number is extracted and returned as a Datum. + * ---------------- + */ + +typedef struct FieldSelect +{ + Expr xpr; + Expr *arg; /* input expression */ + AttrNumber fieldnum; /* attribute number of field to extract */ + /* type of the field (result type of this node) */ + Oid resulttype pg_node_attr(query_jumble_ignore); + /* output typmod (usually -1) */ + int32 resulttypmod pg_node_attr(query_jumble_ignore); + /* OID of collation of the field */ + Oid resultcollid pg_node_attr(query_jumble_ignore); +} FieldSelect; + +/* ---------------- + * FieldStore + * + * FieldStore represents the operation of modifying one field in a tuple + * value, yielding a new tuple value (the input is not touched!). Like + * the assign case of SubscriptingRef, this is used to implement UPDATE of a + * portion of a column. + * + * resulttype is always a named composite type (not a domain). To update + * a composite domain value, apply CoerceToDomain to the FieldStore. + * + * A single FieldStore can actually represent updates of several different + * fields. The parser only generates FieldStores with single-element lists, + * but the planner will collapse multiple updates of the same base column + * into one FieldStore. + * ---------------- + */ + +typedef struct FieldStore +{ + Expr xpr; + Expr *arg; /* input tuple value */ + List *newvals; /* new value(s) for field(s) */ + /* integer list of field attnums */ + List *fieldnums pg_node_attr(query_jumble_ignore); + /* type of result (same as type of arg) */ + Oid resulttype pg_node_attr(query_jumble_ignore); + /* Like RowExpr, we deliberately omit a typmod and collation here */ +} FieldStore; + +/* ---------------- + * RelabelType + * + * RelabelType represents a "dummy" type coercion between two binary- + * compatible datatypes, such as reinterpreting the result of an OID + * expression as an int4. It is a no-op at runtime; we only need it + * to provide a place to store the correct type to be attributed to + * the expression result during type resolution. (We can't get away + * with just overwriting the type field of the input expression node, + * so we need a separate node to show the coercion's result type.) + * ---------------- + */ + +typedef struct RelabelType +{ + Expr xpr; + Expr *arg; /* input expression */ + Oid resulttype; /* output type of coercion expression */ + /* output typmod (usually -1) */ + int32 resulttypmod pg_node_attr(query_jumble_ignore); + /* OID of collation, or InvalidOid if none */ + Oid resultcollid pg_node_attr(query_jumble_ignore); + /* how to display this node */ + CoercionForm relabelformat pg_node_attr(query_jumble_ignore); + int location; /* token location, or -1 if unknown */ +} RelabelType; + +/* ---------------- + * CoerceViaIO + * + * CoerceViaIO represents a type coercion between two types whose textual + * representations are compatible, implemented by invoking the source type's + * typoutput function then the destination type's typinput function. + * ---------------- + */ + +typedef struct CoerceViaIO +{ + Expr xpr; + Expr *arg; /* input expression */ + Oid resulttype; /* output type of coercion */ + /* output typmod is not stored, but is presumed -1 */ + /* OID of collation, or InvalidOid if none */ + Oid resultcollid pg_node_attr(query_jumble_ignore); + /* how to display this node */ + CoercionForm coerceformat pg_node_attr(query_jumble_ignore); + int location; /* token location, or -1 if unknown */ +} CoerceViaIO; + +/* ---------------- + * ArrayCoerceExpr + * + * ArrayCoerceExpr represents a type coercion from one array type to another, + * which is implemented by applying the per-element coercion expression + * "elemexpr" to each element of the source array. Within elemexpr, the + * source element is represented by a CaseTestExpr node. Note that even if + * elemexpr is a no-op (that is, just CaseTestExpr + RelabelType), the + * coercion still requires some effort: we have to fix the element type OID + * stored in the array header. + * ---------------- + */ + +typedef struct ArrayCoerceExpr +{ + Expr xpr; + Expr *arg; /* input expression (yields an array) */ + Expr *elemexpr; /* expression representing per-element work */ + Oid resulttype; /* output type of coercion (an array type) */ + /* output typmod (also element typmod) */ + int32 resulttypmod pg_node_attr(query_jumble_ignore); + /* OID of collation, or InvalidOid if none */ + Oid resultcollid pg_node_attr(query_jumble_ignore); + /* how to display this node */ + CoercionForm coerceformat pg_node_attr(query_jumble_ignore); + int location; /* token location, or -1 if unknown */ +} ArrayCoerceExpr; + +/* ---------------- + * ConvertRowtypeExpr + * + * ConvertRowtypeExpr represents a type coercion from one composite type + * to another, where the source type is guaranteed to contain all the columns + * needed for the destination type plus possibly others; the columns need not + * be in the same positions, but are matched up by name. This is primarily + * used to convert a whole-row value of an inheritance child table into a + * valid whole-row value of its parent table's rowtype. Both resulttype + * and the exposed type of "arg" must be named composite types (not domains). + * ---------------- + */ + +typedef struct ConvertRowtypeExpr +{ + Expr xpr; + Expr *arg; /* input expression */ + Oid resulttype; /* output type (always a composite type) */ + /* Like RowExpr, we deliberately omit a typmod and collation here */ + /* how to display this node */ + CoercionForm convertformat pg_node_attr(query_jumble_ignore); + int location; /* token location, or -1 if unknown */ +} ConvertRowtypeExpr; + +/*---------- + * CollateExpr - COLLATE + * + * The planner replaces CollateExpr with RelabelType during expression + * preprocessing, so execution never sees a CollateExpr. + *---------- + */ +typedef struct CollateExpr +{ + Expr xpr; + Expr *arg; /* input expression */ + Oid collOid; /* collation's OID */ + int location; /* token location, or -1 if unknown */ +} CollateExpr; + +/*---------- + * CaseExpr - a CASE expression + * + * We support two distinct forms of CASE expression: + * CASE WHEN boolexpr THEN expr [ WHEN boolexpr THEN expr ... ] + * CASE testexpr WHEN compexpr THEN expr [ WHEN compexpr THEN expr ... ] + * These are distinguishable by the "arg" field being NULL in the first case + * and the testexpr in the second case. + * + * In the raw grammar output for the second form, the condition expressions + * of the WHEN clauses are just the comparison values. Parse analysis + * converts these to valid boolean expressions of the form + * CaseTestExpr '=' compexpr + * where the CaseTestExpr node is a placeholder that emits the correct + * value at runtime. This structure is used so that the testexpr need be + * evaluated only once. Note that after parse analysis, the condition + * expressions always yield boolean. + * + * Note: we can test whether a CaseExpr has been through parse analysis + * yet by checking whether casetype is InvalidOid or not. + *---------- + */ +typedef struct CaseExpr +{ + Expr xpr; + /* type of expression result */ + Oid casetype pg_node_attr(query_jumble_ignore); + /* OID of collation, or InvalidOid if none */ + Oid casecollid pg_node_attr(query_jumble_ignore); + Expr *arg; /* implicit equality comparison argument */ + List *args; /* the arguments (list of WHEN clauses) */ + Expr *defresult; /* the default result (ELSE clause) */ + int location; /* token location, or -1 if unknown */ +} CaseExpr; + +/* + * CaseWhen - one arm of a CASE expression + */ +typedef struct CaseWhen +{ + Expr xpr; + Expr *expr; /* condition expression */ + Expr *result; /* substitution result */ + int location; /* token location, or -1 if unknown */ +} CaseWhen; + +/* + * Placeholder node for the test value to be processed by a CASE expression. + * This is effectively like a Param, but can be implemented more simply + * since we need only one replacement value at a time. + * + * We also abuse this node type for some other purposes, including: + * * Placeholder for the current array element value in ArrayCoerceExpr; + * see build_coercion_expression(). + * * Nested FieldStore/SubscriptingRef assignment expressions in INSERT/UPDATE; + * see transformAssignmentIndirection(). + * * Placeholder for intermediate results in some SQL/JSON expression nodes, + * such as JsonConstructorExpr. + * + * The uses in CaseExpr and ArrayCoerceExpr are safe only to the extent that + * there is not any other CaseExpr or ArrayCoerceExpr between the value source + * node and its child CaseTestExpr(s). This is true in the parse analysis + * output, but the planner's function-inlining logic has to be careful not to + * break it. + * + * The nested-assignment-expression case is safe because the only node types + * that can be above such CaseTestExprs are FieldStore and SubscriptingRef. + */ +typedef struct CaseTestExpr +{ + Expr xpr; + Oid typeId; /* type for substituted value */ + /* typemod for substituted value */ + int32 typeMod pg_node_attr(query_jumble_ignore); + /* collation for the substituted value */ + Oid collation pg_node_attr(query_jumble_ignore); +} CaseTestExpr; + +/* + * ArrayExpr - an ARRAY[] expression + * + * Note: if multidims is false, the constituent expressions all yield the + * scalar type identified by element_typeid. If multidims is true, the + * constituent expressions all yield arrays of element_typeid (ie, the same + * type as array_typeid); at runtime we must check for compatible subscripts. + */ +typedef struct ArrayExpr +{ + Expr xpr; + /* type of expression result */ + Oid array_typeid pg_node_attr(query_jumble_ignore); + /* OID of collation, or InvalidOid if none */ + Oid array_collid pg_node_attr(query_jumble_ignore); + /* common type of array elements */ + Oid element_typeid pg_node_attr(query_jumble_ignore); + /* the array elements or sub-arrays */ + List *elements; + /* true if elements are sub-arrays */ + bool multidims pg_node_attr(query_jumble_ignore); + /* token location, or -1 if unknown */ + int location; +} ArrayExpr; + +/* + * RowExpr - a ROW() expression + * + * Note: the list of fields must have a one-for-one correspondence with + * physical fields of the associated rowtype, although it is okay for it + * to be shorter than the rowtype. That is, the N'th list element must + * match up with the N'th physical field. When the N'th physical field + * is a dropped column (attisdropped) then the N'th list element can just + * be a NULL constant. (This case can only occur for named composite types, + * not RECORD types, since those are built from the RowExpr itself rather + * than vice versa.) It is important not to assume that length(args) is + * the same as the number of columns logically present in the rowtype. + * + * colnames provides field names if the ROW() result is of type RECORD. + * Names *must* be provided if row_typeid is RECORDOID; but if it is a + * named composite type, colnames will be ignored in favor of using the + * type's cataloged field names, so colnames should be NIL. Like the + * args list, colnames is defined to be one-for-one with physical fields + * of the rowtype (although dropped columns shouldn't appear in the + * RECORD case, so this fine point is currently moot). + */ +typedef struct RowExpr +{ + Expr xpr; + List *args; /* the fields */ + + /* RECORDOID or a composite type's ID */ + Oid row_typeid pg_node_attr(query_jumble_ignore); + + /* + * row_typeid cannot be a domain over composite, only plain composite. To + * create a composite domain value, apply CoerceToDomain to the RowExpr. + * + * Note: we deliberately do NOT store a typmod. Although a typmod will be + * associated with specific RECORD types at runtime, it will differ for + * different backends, and so cannot safely be stored in stored + * parsetrees. We must assume typmod -1 for a RowExpr node. + * + * We don't need to store a collation either. The result type is + * necessarily composite, and composite types never have a collation. + */ + + /* how to display this node */ + CoercionForm row_format pg_node_attr(query_jumble_ignore); + + /* list of String, or NIL */ + List *colnames pg_node_attr(query_jumble_ignore); + + int location; /* token location, or -1 if unknown */ +} RowExpr; + +/* + * RowCompareExpr - row-wise comparison, such as (a, b) <= (1, 2) + * + * We support row comparison for any operator that can be determined to + * act like =, <>, <, <=, >, or >= (we determine this by looking for the + * operator in btree opfamilies). Note that the same operator name might + * map to a different operator for each pair of row elements, since the + * element datatypes can vary. + * + * A RowCompareExpr node is only generated for the < <= > >= cases; + * the = and <> cases are translated to simple AND or OR combinations + * of the pairwise comparisons. However, we include = and <> in the + * RowCompareType enum for the convenience of parser logic. + */ +typedef enum RowCompareType +{ + /* Values of this enum are chosen to match btree strategy numbers */ + ROWCOMPARE_LT = 1, /* BTLessStrategyNumber */ + ROWCOMPARE_LE = 2, /* BTLessEqualStrategyNumber */ + ROWCOMPARE_EQ = 3, /* BTEqualStrategyNumber */ + ROWCOMPARE_GE = 4, /* BTGreaterEqualStrategyNumber */ + ROWCOMPARE_GT = 5, /* BTGreaterStrategyNumber */ + ROWCOMPARE_NE = 6 /* no such btree strategy */ +} RowCompareType; + +typedef struct RowCompareExpr +{ + Expr xpr; + + /* LT LE GE or GT, never EQ or NE */ + RowCompareType rctype; + /* OID list of pairwise comparison ops */ + List *opnos pg_node_attr(query_jumble_ignore); + /* OID list of containing operator families */ + List *opfamilies pg_node_attr(query_jumble_ignore); + /* OID list of collations for comparisons */ + List *inputcollids pg_node_attr(query_jumble_ignore); + /* the left-hand input arguments */ + List *largs; + /* the right-hand input arguments */ + List *rargs; +} RowCompareExpr; + +/* + * CoalesceExpr - a COALESCE expression + */ +typedef struct CoalesceExpr +{ + Expr xpr; + /* type of expression result */ + Oid coalescetype pg_node_attr(query_jumble_ignore); + /* OID of collation, or InvalidOid if none */ + Oid coalescecollid pg_node_attr(query_jumble_ignore); + /* the arguments */ + List *args; + /* token location, or -1 if unknown */ + int location; +} CoalesceExpr; + +/* + * MinMaxExpr - a GREATEST or LEAST function + */ +typedef enum MinMaxOp +{ + IS_GREATEST, + IS_LEAST +} MinMaxOp; + +typedef struct MinMaxExpr +{ + Expr xpr; + /* common type of arguments and result */ + Oid minmaxtype pg_node_attr(query_jumble_ignore); + /* OID of collation of result */ + Oid minmaxcollid pg_node_attr(query_jumble_ignore); + /* OID of collation that function should use */ + Oid inputcollid pg_node_attr(query_jumble_ignore); + /* function to execute */ + MinMaxOp op; + /* the arguments */ + List *args; + /* token location, or -1 if unknown */ + int location; +} MinMaxExpr; + +/* + * SQLValueFunction - parameterless functions with special grammar productions + * + * The SQL standard categorizes some of these as <datetime value function> + * and others as <general value specification>. We call 'em SQLValueFunctions + * for lack of a better term. We store type and typmod of the result so that + * some code doesn't need to know each function individually, and because + * we would need to store typmod anyway for some of the datetime functions. + * Note that currently, all variants return non-collating datatypes, so we do + * not need a collation field; also, all these functions are stable. + */ +typedef enum SQLValueFunctionOp +{ + SVFOP_CURRENT_DATE, + SVFOP_CURRENT_TIME, + SVFOP_CURRENT_TIME_N, + SVFOP_CURRENT_TIMESTAMP, + SVFOP_CURRENT_TIMESTAMP_N, + SVFOP_LOCALTIME, + SVFOP_LOCALTIME_N, + SVFOP_LOCALTIMESTAMP, + SVFOP_LOCALTIMESTAMP_N, + SVFOP_CURRENT_ROLE, + SVFOP_CURRENT_USER, + SVFOP_USER, + SVFOP_SESSION_USER, + SVFOP_CURRENT_CATALOG, + SVFOP_CURRENT_SCHEMA +} SQLValueFunctionOp; + +typedef struct SQLValueFunction +{ + Expr xpr; + SQLValueFunctionOp op; /* which function this is */ + + /* + * Result type/typmod. Type is fully determined by "op", so no need to + * include this Oid in the query jumbling. + */ + Oid type pg_node_attr(query_jumble_ignore); + int32 typmod; + int location; /* token location, or -1 if unknown */ +} SQLValueFunction; + +/* + * XmlExpr - various SQL/XML functions requiring special grammar productions + * + * 'name' carries the "NAME foo" argument (already XML-escaped). + * 'named_args' and 'arg_names' represent an xml_attribute list. + * 'args' carries all other arguments. + * + * Note: result type/typmod/collation are not stored, but can be deduced + * from the XmlExprOp. The type/typmod fields are just used for display + * purposes, and are NOT necessarily the true result type of the node. + */ +typedef enum XmlExprOp +{ + IS_XMLCONCAT, /* XMLCONCAT(args) */ + IS_XMLELEMENT, /* XMLELEMENT(name, xml_attributes, args) */ + IS_XMLFOREST, /* XMLFOREST(xml_attributes) */ + IS_XMLPARSE, /* XMLPARSE(text, is_doc, preserve_ws) */ + IS_XMLPI, /* XMLPI(name [, args]) */ + IS_XMLROOT, /* XMLROOT(xml, version, standalone) */ + IS_XMLSERIALIZE, /* XMLSERIALIZE(is_document, xmlval, indent) */ + IS_DOCUMENT /* xmlval IS DOCUMENT */ +} XmlExprOp; + +typedef enum XmlOptionType +{ + XMLOPTION_DOCUMENT, + XMLOPTION_CONTENT +} XmlOptionType; + +typedef struct XmlExpr +{ + Expr xpr; + /* xml function ID */ + XmlExprOp op; + /* name in xml(NAME foo ...) syntaxes */ + char *name pg_node_attr(query_jumble_ignore); + /* non-XML expressions for xml_attributes */ + List *named_args; + /* parallel list of String values */ + List *arg_names pg_node_attr(query_jumble_ignore); + /* list of expressions */ + List *args; + /* DOCUMENT or CONTENT */ + XmlOptionType xmloption pg_node_attr(query_jumble_ignore); + /* INDENT option for XMLSERIALIZE */ + bool indent; + /* target type/typmod for XMLSERIALIZE */ + Oid type pg_node_attr(query_jumble_ignore); + int32 typmod pg_node_attr(query_jumble_ignore); + /* token location, or -1 if unknown */ + int location; +} XmlExpr; + +/* + * JsonEncoding - + * representation of JSON ENCODING clause + */ +typedef enum JsonEncoding +{ + JS_ENC_DEFAULT, /* unspecified */ + JS_ENC_UTF8, + JS_ENC_UTF16, + JS_ENC_UTF32, +} JsonEncoding; + +/* + * JsonFormatType - + * enumeration of JSON formats used in JSON FORMAT clause + */ +typedef enum JsonFormatType +{ + JS_FORMAT_DEFAULT, /* unspecified */ + JS_FORMAT_JSON, /* FORMAT JSON [ENCODING ...] */ + JS_FORMAT_JSONB /* implicit internal format for RETURNING + * jsonb */ +} JsonFormatType; + +/* + * JsonFormat - + * representation of JSON FORMAT clause + */ +typedef struct JsonFormat +{ + NodeTag type; + JsonFormatType format_type; /* format type */ + JsonEncoding encoding; /* JSON encoding */ + int location; /* token location, or -1 if unknown */ +} JsonFormat; + +/* + * JsonReturning - + * transformed representation of JSON RETURNING clause + */ +typedef struct JsonReturning +{ + NodeTag type; + JsonFormat *format; /* output JSON format */ + Oid typid; /* target type Oid */ + int32 typmod; /* target type modifier */ +} JsonReturning; + +/* + * JsonValueExpr - + * representation of JSON value expression (expr [FORMAT JsonFormat]) + * + * The actual value is obtained by evaluating formatted_expr. raw_expr is + * only there for displaying the original user-written expression and is not + * evaluated by ExecInterpExpr() and eval_const_exprs_mutator(). + */ +typedef struct JsonValueExpr +{ + NodeTag type; + Expr *raw_expr; /* raw expression */ + Expr *formatted_expr; /* formatted expression */ + JsonFormat *format; /* FORMAT clause, if specified */ +} JsonValueExpr; + +typedef enum JsonConstructorType +{ + JSCTOR_JSON_OBJECT = 1, + JSCTOR_JSON_ARRAY = 2, + JSCTOR_JSON_OBJECTAGG = 3, + JSCTOR_JSON_ARRAYAGG = 4 +} JsonConstructorType; + +/* + * JsonConstructorExpr - + * wrapper over FuncExpr/Aggref/WindowFunc for SQL/JSON constructors + */ +typedef struct JsonConstructorExpr +{ + Expr xpr; + JsonConstructorType type; /* constructor type */ + List *args; + Expr *func; /* underlying json[b]_xxx() function call */ + Expr *coercion; /* coercion to RETURNING type */ + JsonReturning *returning; /* RETURNING clause */ + bool absent_on_null; /* ABSENT ON NULL? */ + bool unique; /* WITH UNIQUE KEYS? (JSON_OBJECT[AGG] only) */ + int location; +} JsonConstructorExpr; + +/* + * JsonValueType - + * representation of JSON item type in IS JSON predicate + */ +typedef enum JsonValueType +{ + JS_TYPE_ANY, /* IS JSON [VALUE] */ + JS_TYPE_OBJECT, /* IS JSON OBJECT */ + JS_TYPE_ARRAY, /* IS JSON ARRAY */ + JS_TYPE_SCALAR /* IS JSON SCALAR */ +} JsonValueType; + +/* + * JsonIsPredicate - + * representation of IS JSON predicate + */ +typedef struct JsonIsPredicate +{ + NodeTag type; + Node *expr; /* subject expression */ + JsonFormat *format; /* FORMAT clause, if specified */ + JsonValueType item_type; /* JSON item type */ + bool unique_keys; /* check key uniqueness? */ + int location; /* token location, or -1 if unknown */ +} JsonIsPredicate; + +/* ---------------- + * NullTest + * + * NullTest represents the operation of testing a value for NULLness. + * The appropriate test is performed and returned as a boolean Datum. + * + * When argisrow is false, this simply represents a test for the null value. + * + * When argisrow is true, the input expression must yield a rowtype, and + * the node implements "row IS [NOT] NULL" per the SQL standard. This + * includes checking individual fields for NULLness when the row datum + * itself isn't NULL. + * + * NOTE: the combination of a rowtype input and argisrow==false does NOT + * correspond to the SQL notation "row IS [NOT] NULL"; instead, this case + * represents the SQL notation "row IS [NOT] DISTINCT FROM NULL". + * ---------------- + */ + +typedef enum NullTestType +{ + IS_NULL, IS_NOT_NULL +} NullTestType; + +typedef struct NullTest +{ + Expr xpr; + Expr *arg; /* input expression */ + NullTestType nulltesttype; /* IS NULL, IS NOT NULL */ + /* T to perform field-by-field null checks */ + bool argisrow pg_node_attr(query_jumble_ignore); + int location; /* token location, or -1 if unknown */ +} NullTest; + +/* + * BooleanTest + * + * BooleanTest represents the operation of determining whether a boolean + * is TRUE, FALSE, or UNKNOWN (ie, NULL). All six meaningful combinations + * are supported. Note that a NULL input does *not* cause a NULL result. + * The appropriate test is performed and returned as a boolean Datum. + */ + +typedef enum BoolTestType +{ + IS_TRUE, IS_NOT_TRUE, IS_FALSE, IS_NOT_FALSE, IS_UNKNOWN, IS_NOT_UNKNOWN +} BoolTestType; + +typedef struct BooleanTest +{ + Expr xpr; + Expr *arg; /* input expression */ + BoolTestType booltesttype; /* test type */ + int location; /* token location, or -1 if unknown */ +} BooleanTest; + +/* + * CoerceToDomain + * + * CoerceToDomain represents the operation of coercing a value to a domain + * type. At runtime (and not before) the precise set of constraints to be + * checked will be determined. If the value passes, it is returned as the + * result; if not, an error is raised. Note that this is equivalent to + * RelabelType in the scenario where no constraints are applied. + */ +typedef struct CoerceToDomain +{ + Expr xpr; + Expr *arg; /* input expression */ + Oid resulttype; /* domain type ID (result type) */ + /* output typmod (currently always -1) */ + int32 resulttypmod pg_node_attr(query_jumble_ignore); + /* OID of collation, or InvalidOid if none */ + Oid resultcollid pg_node_attr(query_jumble_ignore); + /* how to display this node */ + CoercionForm coercionformat pg_node_attr(query_jumble_ignore); + int location; /* token location, or -1 if unknown */ +} CoerceToDomain; + +/* + * Placeholder node for the value to be processed by a domain's check + * constraint. This is effectively like a Param, but can be implemented more + * simply since we need only one replacement value at a time. + * + * Note: the typeId/typeMod/collation will be set from the domain's base type, + * not the domain itself. This is because we shouldn't consider the value + * to be a member of the domain if we haven't yet checked its constraints. + */ +typedef struct CoerceToDomainValue +{ + Expr xpr; + /* type for substituted value */ + Oid typeId; + /* typemod for substituted value */ + int32 typeMod pg_node_attr(query_jumble_ignore); + /* collation for the substituted value */ + Oid collation pg_node_attr(query_jumble_ignore); + /* token location, or -1 if unknown */ + int location; +} CoerceToDomainValue; + +/* + * Placeholder node for a DEFAULT marker in an INSERT or UPDATE command. + * + * This is not an executable expression: it must be replaced by the actual + * column default expression during rewriting. But it is convenient to + * treat it as an expression node during parsing and rewriting. + */ +typedef struct SetToDefault +{ + Expr xpr; + /* type for substituted value */ + Oid typeId; + /* typemod for substituted value */ + int32 typeMod pg_node_attr(query_jumble_ignore); + /* collation for the substituted value */ + Oid collation pg_node_attr(query_jumble_ignore); + /* token location, or -1 if unknown */ + int location; +} SetToDefault; + +/* + * Node representing [WHERE] CURRENT OF cursor_name + * + * CURRENT OF is a bit like a Var, in that it carries the rangetable index + * of the target relation being constrained; this aids placing the expression + * correctly during planning. We can assume however that its "levelsup" is + * always zero, due to the syntactic constraints on where it can appear. + * Also, cvarno will always be a true RT index, never INNER_VAR etc. + * + * The referenced cursor can be represented either as a hardwired string + * or as a reference to a run-time parameter of type REFCURSOR. The latter + * case is for the convenience of plpgsql. + */ +typedef struct CurrentOfExpr +{ + Expr xpr; + Index cvarno; /* RT index of target relation */ + char *cursor_name; /* name of referenced cursor, or NULL */ + int cursor_param; /* refcursor parameter number, or 0 */ +} CurrentOfExpr; + +/* + * NextValueExpr - get next value from sequence + * + * This has the same effect as calling the nextval() function, but it does not + * check permissions on the sequence. This is used for identity columns, + * where the sequence is an implicit dependency without its own permissions. + */ +typedef struct NextValueExpr +{ + Expr xpr; + Oid seqid; + Oid typeId; +} NextValueExpr; + +/* + * InferenceElem - an element of a unique index inference specification + * + * This mostly matches the structure of IndexElems, but having a dedicated + * primnode allows for a clean separation between the use of index parameters + * by utility commands, and this node. + */ +typedef struct InferenceElem +{ + Expr xpr; + Node *expr; /* expression to infer from, or NULL */ + Oid infercollid; /* OID of collation, or InvalidOid */ + Oid inferopclass; /* OID of att opclass, or InvalidOid */ +} InferenceElem; + +/*-------------------- + * TargetEntry - + * a target entry (used in query target lists) + * + * Strictly speaking, a TargetEntry isn't an expression node (since it can't + * be evaluated by ExecEvalExpr). But we treat it as one anyway, since in + * very many places it's convenient to process a whole query targetlist as a + * single expression tree. + * + * In a SELECT's targetlist, resno should always be equal to the item's + * ordinal position (counting from 1). However, in an INSERT or UPDATE + * targetlist, resno represents the attribute number of the destination + * column for the item; so there may be missing or out-of-order resnos. + * It is even legal to have duplicated resnos; consider + * UPDATE table SET arraycol[1] = ..., arraycol[2] = ..., ... + * In an INSERT, the rewriter and planner will normalize the tlist by + * reordering it into physical column order and filling in default values + * for any columns not assigned values by the original query. In an UPDATE, + * after the rewriter merges multiple assignments for the same column, the + * planner extracts the target-column numbers into a separate "update_colnos" + * list, and then renumbers the tlist elements serially. Thus, tlist resnos + * match ordinal position in all tlists seen by the executor; but it is wrong + * to assume that before planning has happened. + * + * resname is required to represent the correct column name in non-resjunk + * entries of top-level SELECT targetlists, since it will be used as the + * column title sent to the frontend. In most other contexts it is only + * a debugging aid, and may be wrong or even NULL. (In particular, it may + * be wrong in a tlist from a stored rule, if the referenced column has been + * renamed by ALTER TABLE since the rule was made. Also, the planner tends + * to store NULL rather than look up a valid name for tlist entries in + * non-toplevel plan nodes.) In resjunk entries, resname should be either + * a specific system-generated name (such as "ctid") or NULL; anything else + * risks confusing ExecGetJunkAttribute! + * + * ressortgroupref is used in the representation of ORDER BY, GROUP BY, and + * DISTINCT items. Targetlist entries with ressortgroupref=0 are not + * sort/group items. If ressortgroupref>0, then this item is an ORDER BY, + * GROUP BY, and/or DISTINCT target value. No two entries in a targetlist + * may have the same nonzero ressortgroupref --- but there is no particular + * meaning to the nonzero values, except as tags. (For example, one must + * not assume that lower ressortgroupref means a more significant sort key.) + * The order of the associated SortGroupClause lists determine the semantics. + * + * resorigtbl/resorigcol identify the source of the column, if it is a + * simple reference to a column of a base table (or view). If it is not + * a simple reference, these fields are zeroes. + * + * If resjunk is true then the column is a working column (such as a sort key) + * that should be removed from the final output of the query. Resjunk columns + * must have resnos that cannot duplicate any regular column's resno. Also + * note that there are places that assume resjunk columns come after non-junk + * columns. + *-------------------- + */ +typedef struct TargetEntry +{ + Expr xpr; + /* expression to evaluate */ + Expr *expr; + /* attribute number (see notes above) */ + AttrNumber resno; + /* name of the column (could be NULL) */ + char *resname pg_node_attr(query_jumble_ignore); + /* nonzero if referenced by a sort/group clause */ + Index ressortgroupref; + /* OID of column's source table */ + Oid resorigtbl pg_node_attr(query_jumble_ignore); + /* column's number in source table */ + AttrNumber resorigcol pg_node_attr(query_jumble_ignore); + /* set to true to eliminate the attribute from final target list */ + bool resjunk pg_node_attr(query_jumble_ignore); +} TargetEntry; + + +/* ---------------------------------------------------------------- + * node types for join trees + * + * The leaves of a join tree structure are RangeTblRef nodes. Above + * these, JoinExpr nodes can appear to denote a specific kind of join + * or qualified join. Also, FromExpr nodes can appear to denote an + * ordinary cross-product join ("FROM foo, bar, baz WHERE ..."). + * FromExpr is like a JoinExpr of jointype JOIN_INNER, except that it + * may have any number of child nodes, not just two. + * + * NOTE: the top level of a Query's jointree is always a FromExpr. + * Even if the jointree contains no rels, there will be a FromExpr. + * + * NOTE: the qualification expressions present in JoinExpr nodes are + * *in addition to* the query's main WHERE clause, which appears as the + * qual of the top-level FromExpr. The reason for associating quals with + * specific nodes in the jointree is that the position of a qual is critical + * when outer joins are present. (If we enforce a qual too soon or too late, + * that may cause the outer join to produce the wrong set of NULL-extended + * rows.) If all joins are inner joins then all the qual positions are + * semantically interchangeable. + * + * NOTE: in the raw output of gram.y, a join tree contains RangeVar, + * RangeSubselect, and RangeFunction nodes, which are all replaced by + * RangeTblRef nodes during the parse analysis phase. Also, the top-level + * FromExpr is added during parse analysis; the grammar regards FROM and + * WHERE as separate. + * ---------------------------------------------------------------- + */ + +/* + * RangeTblRef - reference to an entry in the query's rangetable + * + * We could use direct pointers to the RT entries and skip having these + * nodes, but multiple pointers to the same node in a querytree cause + * lots of headaches, so it seems better to store an index into the RT. + */ +typedef struct RangeTblRef +{ + NodeTag type; + int rtindex; +} RangeTblRef; + +/*---------- + * JoinExpr - for SQL JOIN expressions + * + * isNatural, usingClause, and quals are interdependent. The user can write + * only one of NATURAL, USING(), or ON() (this is enforced by the grammar). + * If he writes NATURAL then parse analysis generates the equivalent USING() + * list, and from that fills in "quals" with the right equality comparisons. + * If he writes USING() then "quals" is filled with equality comparisons. + * If he writes ON() then only "quals" is set. Note that NATURAL/USING + * are not equivalent to ON() since they also affect the output column list. + * + * alias is an Alias node representing the AS alias-clause attached to the + * join expression, or NULL if no clause. NB: presence or absence of the + * alias has a critical impact on semantics, because a join with an alias + * restricts visibility of the tables/columns inside it. + * + * join_using_alias is an Alias node representing the join correlation + * name that SQL:2016 and later allow to be attached to JOIN/USING. + * Its column alias list includes only the common column names from USING, + * and it does not restrict visibility of the join's input tables. + * + * During parse analysis, an RTE is created for the Join, and its index + * is filled into rtindex. This RTE is present mainly so that Vars can + * be created that refer to the outputs of the join. The planner sometimes + * generates JoinExprs internally; these can have rtindex = 0 if there are + * no join alias variables referencing such joins. + *---------- + */ +typedef struct JoinExpr +{ + NodeTag type; + JoinType jointype; /* type of join */ + bool isNatural; /* Natural join? Will need to shape table */ + Node *larg; /* left subtree */ + Node *rarg; /* right subtree */ + /* USING clause, if any (list of String) */ + List *usingClause pg_node_attr(query_jumble_ignore); + /* alias attached to USING clause, if any */ + Alias *join_using_alias pg_node_attr(query_jumble_ignore); + /* qualifiers on join, if any */ + Node *quals; + /* user-written alias clause, if any */ + Alias *alias pg_node_attr(query_jumble_ignore); + /* RT index assigned for join, or 0 */ + int rtindex; +} JoinExpr; + +/*---------- + * FromExpr - represents a FROM ... WHERE ... construct + * + * This is both more flexible than a JoinExpr (it can have any number of + * children, including zero) and less so --- we don't need to deal with + * aliases and so on. The output column set is implicitly just the union + * of the outputs of the children. + *---------- + */ +typedef struct FromExpr +{ + NodeTag type; + List *fromlist; /* List of join subtrees */ + Node *quals; /* qualifiers on join, if any */ +} FromExpr; + +/*---------- + * OnConflictExpr - represents an ON CONFLICT DO ... expression + * + * The optimizer requires a list of inference elements, and optionally a WHERE + * clause to infer a unique index. The unique index (or, occasionally, + * indexes) inferred are used to arbitrate whether or not the alternative ON + * CONFLICT path is taken. + *---------- + */ +typedef struct OnConflictExpr +{ + NodeTag type; + OnConflictAction action; /* DO NOTHING or UPDATE? */ + + /* Arbiter */ + List *arbiterElems; /* unique index arbiter list (of + * InferenceElem's) */ + Node *arbiterWhere; /* unique index arbiter WHERE clause */ + Oid constraint; /* pg_constraint OID for arbiter */ + + /* ON CONFLICT UPDATE */ + List *onConflictSet; /* List of ON CONFLICT SET TargetEntrys */ + Node *onConflictWhere; /* qualifiers to restrict UPDATE to */ + int exclRelIndex; /* RT index of 'excluded' relation */ + List *exclRelTlist; /* tlist of the EXCLUDED pseudo relation */ +} OnConflictExpr; + +#endif /* PRIMNODES_H */ diff --git a/src/include/nodes/print.h b/src/include/nodes/print.h new file mode 100644 index 0000000..3c0473f --- /dev/null +++ b/src/include/nodes/print.h @@ -0,0 +1,34 @@ +/*------------------------------------------------------------------------- + * + * print.h + * definitions for nodes/print.c + * + * + * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/nodes/print.h + * + *------------------------------------------------------------------------- + */ +#ifndef PRINT_H +#define PRINT_H + +#include "executor/tuptable.h" + + +#define nodeDisplay(x) pprint(x) + +extern void print(const void *obj); +extern void pprint(const void *obj); +extern void elog_node_display(int lev, const char *title, + const void *obj, bool pretty); +extern char *format_node_dump(const char *dump); +extern char *pretty_format_node_dump(const char *dump); +extern void print_rt(const List *rtable); +extern void print_expr(const Node *expr, const List *rtable); +extern void print_pathkeys(const List *pathkeys, const List *rtable); +extern void print_tl(const List *tlist, const List *rtable); +extern void print_slot(TupleTableSlot *slot); + +#endif /* PRINT_H */ diff --git a/src/include/nodes/queryjumble.h b/src/include/nodes/queryjumble.h new file mode 100644 index 0000000..7649e09 --- /dev/null +++ b/src/include/nodes/queryjumble.h @@ -0,0 +1,86 @@ +/*------------------------------------------------------------------------- + * + * queryjumble.h + * Query normalization and fingerprinting. + * + * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * IDENTIFICATION + * src/include/nodes/queryjumble.h + * + *------------------------------------------------------------------------- + */ +#ifndef QUERYJUMBLE_H +#define QUERYJUMBLE_H + +#include "nodes/parsenodes.h" + +/* + * Struct for tracking locations/lengths of constants during normalization + */ +typedef struct LocationLen +{ + int location; /* start offset in query text */ + int length; /* length in bytes, or -1 to ignore */ +} LocationLen; + +/* + * Working state for computing a query jumble and producing a normalized + * query string + */ +typedef struct JumbleState +{ + /* Jumble of current query tree */ + unsigned char *jumble; + + /* Number of bytes used in jumble[] */ + Size jumble_len; + + /* Array of locations of constants that should be removed */ + LocationLen *clocations; + + /* Allocated length of clocations array */ + int clocations_buf_size; + + /* Current number of valid entries in clocations array */ + int clocations_count; + + /* highest Param id we've seen, in order to start normalization correctly */ + int highest_extern_param_id; +} JumbleState; + +/* Values for the compute_query_id GUC */ +enum ComputeQueryIdType +{ + COMPUTE_QUERY_ID_OFF, + COMPUTE_QUERY_ID_ON, + COMPUTE_QUERY_ID_AUTO, + COMPUTE_QUERY_ID_REGRESS +}; + +/* GUC parameters */ +extern PGDLLIMPORT int compute_query_id; + + +extern const char *CleanQuerytext(const char *query, int *location, int *len); +extern JumbleState *JumbleQuery(Query *query); +extern void EnableQueryId(void); + +extern PGDLLIMPORT bool query_id_enabled; + +/* + * Returns whether query identifier computation has been enabled, either + * directly in the GUC or by a module when the setting is 'auto'. + */ +static inline bool +IsQueryIdEnabled(void) +{ + if (compute_query_id == COMPUTE_QUERY_ID_OFF) + return false; + if (compute_query_id == COMPUTE_QUERY_ID_ON) + return true; + return query_id_enabled; +} + +#endif /* QUERYJUMBLE_H */ diff --git a/src/include/nodes/readfuncs.h b/src/include/nodes/readfuncs.h new file mode 100644 index 0000000..cba6f0b --- /dev/null +++ b/src/include/nodes/readfuncs.h @@ -0,0 +1,38 @@ +/*------------------------------------------------------------------------- + * + * readfuncs.h + * header file for read.c and readfuncs.c. These functions are internal + * to the stringToNode interface and should not be used by anyone else. + * + * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/nodes/readfuncs.h + * + *------------------------------------------------------------------------- + */ +#ifndef READFUNCS_H +#define READFUNCS_H + +#include "nodes/nodes.h" + +/* + * variable in read.c that needs to be accessible to readfuncs.c + */ +#ifdef WRITE_READ_PARSE_PLAN_TREES +extern PGDLLIMPORT bool restore_location_fields; +#endif + +/* + * prototypes for functions in read.c (the lisp token parser) + */ +extern const char *pg_strtok(int *length); +extern char *debackslash(const char *token, int length); +extern void *nodeRead(const char *token, int tok_len); + +/* + * prototypes for functions in readfuncs.c + */ +extern Node *parseNodeString(void); + +#endif /* READFUNCS_H */ diff --git a/src/include/nodes/replnodes.h b/src/include/nodes/replnodes.h new file mode 100644 index 0000000..4321ba8 --- /dev/null +++ b/src/include/nodes/replnodes.h @@ -0,0 +1,111 @@ +/*------------------------------------------------------------------------- + * + * replnodes.h + * definitions for replication grammar parse nodes + * + * + * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/nodes/replnodes.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPLNODES_H +#define REPLNODES_H + +#include "access/xlogdefs.h" +#include "nodes/pg_list.h" + +typedef enum ReplicationKind +{ + REPLICATION_KIND_PHYSICAL, + REPLICATION_KIND_LOGICAL +} ReplicationKind; + + +/* ---------------------- + * IDENTIFY_SYSTEM command + * ---------------------- + */ +typedef struct IdentifySystemCmd +{ + NodeTag type; +} IdentifySystemCmd; + + +/* ---------------------- + * BASE_BACKUP command + * ---------------------- + */ +typedef struct BaseBackupCmd +{ + NodeTag type; + List *options; +} BaseBackupCmd; + + +/* ---------------------- + * CREATE_REPLICATION_SLOT command + * ---------------------- + */ +typedef struct CreateReplicationSlotCmd +{ + NodeTag type; + char *slotname; + ReplicationKind kind; + char *plugin; + bool temporary; + List *options; +} CreateReplicationSlotCmd; + + +/* ---------------------- + * DROP_REPLICATION_SLOT command + * ---------------------- + */ +typedef struct DropReplicationSlotCmd +{ + NodeTag type; + char *slotname; + bool wait; +} DropReplicationSlotCmd; + + +/* ---------------------- + * START_REPLICATION command + * ---------------------- + */ +typedef struct StartReplicationCmd +{ + NodeTag type; + ReplicationKind kind; + char *slotname; + TimeLineID timeline; + XLogRecPtr startpoint; + List *options; +} StartReplicationCmd; + + +/* ---------------------- + * READ_REPLICATION_SLOT command + * ---------------------- + */ +typedef struct ReadReplicationSlotCmd +{ + NodeTag type; + char *slotname; +} ReadReplicationSlotCmd; + + +/* ---------------------- + * TIMELINE_HISTORY command + * ---------------------- + */ +typedef struct TimeLineHistoryCmd +{ + NodeTag type; + TimeLineID timeline; +} TimeLineHistoryCmd; + +#endif /* REPLNODES_H */ diff --git a/src/include/nodes/subscripting.h b/src/include/nodes/subscripting.h new file mode 100644 index 0000000..02d98f2 --- /dev/null +++ b/src/include/nodes/subscripting.h @@ -0,0 +1,167 @@ +/*------------------------------------------------------------------------- + * + * subscripting.h + * API for generic type subscripting + * + * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/nodes/subscripting.h + * + *------------------------------------------------------------------------- + */ +#ifndef SUBSCRIPTING_H +#define SUBSCRIPTING_H + +#include "nodes/primnodes.h" + +/* Forward declarations, to avoid including other headers */ +struct ParseState; +struct SubscriptingRefState; +struct SubscriptExecSteps; + +/* + * The SQL-visible function that defines a subscripting method is declared + * subscripting_function(internal) returns internal + * but it actually is not passed any parameter. It must return a pointer + * to a "struct SubscriptRoutines" that provides pointers to the individual + * subscript parsing and execution methods. Typically the pointer will point + * to a "static const" variable, but at need it can point to palloc'd space. + * The type (after domain-flattening) of the head variable or expression + * of a subscripting construct determines which subscripting function is + * called for that construct. + * + * In addition to the method pointers, struct SubscriptRoutines includes + * several bool flags that specify properties of the subscripting actions + * this data type can perform: + * + * fetch_strict indicates that a fetch SubscriptRef is strict, i.e., returns + * NULL if any input (either the container or any subscript) is NULL. + * + * fetch_leakproof indicates that a fetch SubscriptRef is leakproof, i.e., + * will not throw any data-value-dependent errors. Typically this requires + * silently returning NULL for invalid subscripts. + * + * store_leakproof similarly indicates whether an assignment SubscriptRef is + * leakproof. (It is common to prefer throwing errors for invalid subscripts + * in assignments; that's fine, but it makes the operation not leakproof. + * In current usage there is no advantage in making assignments leakproof.) + * + * There is no store_strict flag. Such behavior would generally be + * undesirable, since for example a null subscript in an assignment would + * cause the entire container to become NULL. + * + * Regardless of these flags, all SubscriptRefs are expected to be immutable, + * that is they must always give the same results for the same inputs. + * They are expected to always be parallel-safe, as well. + */ + +/* + * The transform method is called during parse analysis of a subscripting + * construct. The SubscriptingRef node has been constructed, but some of + * its fields still need to be filled in, and the subscript expression(s) + * are still in raw form. The transform method is responsible for doing + * parse analysis of each subscript expression (using transformExpr), + * coercing the subscripts to whatever type it needs, and building the + * refupperindexpr and reflowerindexpr lists from those results. The + * reflowerindexpr list must be empty for an element operation, or the + * same length as refupperindexpr for a slice operation. Insert NULLs + * (that is, an empty parse tree, not a null Const node) for any omitted + * subscripts in a slice operation. (Of course, if the transform method + * does not care to support slicing, it can just throw an error if isSlice.) + * See array_subscript_transform() for sample code. + * + * The transform method is also responsible for identifying the result type + * of the subscripting operation. At call, refcontainertype and reftypmod + * describe the container type (this will be a base type not a domain), and + * refelemtype is set to the container type's pg_type.typelem value. The + * transform method must set refrestype and reftypmod to describe the result + * of subscripting. For arrays, refrestype is set to refelemtype for an + * element operation or refcontainertype for a slice, while reftypmod stays + * the same in either case; but other types might use other rules. The + * transform method should ignore refcollid, as that's determined later on + * during parsing. + * + * At call, refassgnexpr has not been filled in, so the SubscriptingRef node + * always looks like a fetch; refrestype should be set as though for a + * fetch, too. (The isAssignment parameter is typically only useful if the + * transform method wishes to throw an error for not supporting assignment.) + * To complete processing of an assignment, the core parser will coerce the + * element/slice source expression to the returned refrestype and reftypmod + * before putting it into refassgnexpr. It will then set refrestype and + * reftypmod to again describe the container type, since that's what an + * assignment must return. + */ +typedef void (*SubscriptTransform) (SubscriptingRef *sbsref, + List *indirection, + struct ParseState *pstate, + bool isSlice, + bool isAssignment); + +/* + * The exec_setup method is called during executor-startup compilation of a + * SubscriptingRef node in an expression. It must fill *methods with pointers + * to functions that can be called for execution of the node. Optionally, + * exec_setup can initialize sbsrefstate->workspace to point to some palloc'd + * workspace for execution. (Typically, such workspace is used to hold + * looked-up catalog data and/or provide space for the check_subscripts step + * to pass data forward to the other step functions.) See executor/execExpr.h + * for the definitions of these structs and other ones used in expression + * execution. + * + * The methods to be provided are: + * + * sbs_check_subscripts: examine the just-computed subscript values available + * in sbsrefstate's arrays, and possibly convert them into another form + * (stored in sbsrefstate->workspace). Return TRUE to continue with + * evaluation of the subscripting construct, or FALSE to skip it and return an + * overall NULL result. If this is a fetch and the data type's fetch_strict + * flag is true, then sbs_check_subscripts must return FALSE if there are any + * NULL subscripts. Otherwise it can choose to throw an error, or return + * FALSE, or let sbs_fetch or sbs_assign deal with the null subscripts. + * + * sbs_fetch: perform a subscripting fetch, using the container value in + * *op->resvalue and the subscripts from sbs_check_subscripts. If + * fetch_strict is true then all these inputs can be assumed non-NULL, + * otherwise sbs_fetch must check for null inputs. Place the result in + * *op->resvalue / *op->resnull. + * + * sbs_assign: perform a subscripting assignment, using the original + * container value in *op->resvalue / *op->resnull, the subscripts from + * sbs_check_subscripts, and the new element/slice value in + * sbsrefstate->replacevalue/replacenull. Any of these inputs might be NULL + * (unless sbs_check_subscripts rejected null subscripts). Place the result + * (an entire new container value) in *op->resvalue / *op->resnull. + * + * sbs_fetch_old: this is only used in cases where an element or slice + * assignment involves an assignment to a sub-field or sub-element + * (i.e., nested containers are involved). It must fetch the existing + * value of the target element or slice. This is exactly the same as + * sbs_fetch except that (a) it must cope with a NULL container, and + * with NULL subscripts if sbs_check_subscripts allows them (typically, + * returning NULL is good enough); and (b) the result must be placed in + * sbsrefstate->prevvalue/prevnull, without overwriting *op->resvalue. + * + * Subscripting implementations that do not support assignment need not + * provide sbs_assign or sbs_fetch_old methods. It might be reasonable + * to also omit sbs_check_subscripts, in which case the sbs_fetch method must + * combine the functionality of sbs_check_subscripts and sbs_fetch. (The + * main reason to have a separate sbs_check_subscripts method is so that + * sbs_fetch_old and sbs_assign need not duplicate subscript processing.) + * Set the relevant pointers to NULL for any omitted methods. + */ +typedef void (*SubscriptExecSetup) (const SubscriptingRef *sbsref, + struct SubscriptingRefState *sbsrefstate, + struct SubscriptExecSteps *methods); + +/* Struct returned by the SQL-visible subscript handler function */ +typedef struct SubscriptRoutines +{ + SubscriptTransform transform; /* parse analysis function */ + SubscriptExecSetup exec_setup; /* expression compilation function */ + bool fetch_strict; /* is fetch SubscriptRef strict? */ + bool fetch_leakproof; /* is fetch SubscriptRef leakproof? */ + bool store_leakproof; /* is assignment SubscriptRef leakproof? */ +} SubscriptRoutines; + +#endif /* SUBSCRIPTING_H */ diff --git a/src/include/nodes/supportnodes.h b/src/include/nodes/supportnodes.h new file mode 100644 index 0000000..4cfa661 --- /dev/null +++ b/src/include/nodes/supportnodes.h @@ -0,0 +1,346 @@ +/*------------------------------------------------------------------------- + * + * supportnodes.h + * Definitions for planner support functions. + * + * This file defines the API for "planner support functions", which + * are SQL functions (normally written in C) that can be attached to + * another "target" function to give the system additional knowledge + * about the target function. All the current capabilities have to do + * with planning queries that use the target function, though it is + * possible that future extensions will add functionality to be invoked + * by the parser or executor. + * + * A support function must have the SQL signature + * supportfn(internal) returns internal + * The argument is a pointer to one of the Node types defined in this file. + * The result is usually also a Node pointer, though its type depends on + * which capability is being invoked. In all cases, a NULL pointer result + * (that's PG_RETURN_POINTER(NULL), not PG_RETURN_NULL()) indicates that + * the support function cannot do anything useful for the given request. + * Support functions must return a NULL pointer, not fail, if they do not + * recognize the request node type or cannot handle the given case; this + * allows for future extensions of the set of request cases. + * + * + * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/nodes/supportnodes.h + * + *------------------------------------------------------------------------- + */ +#ifndef SUPPORTNODES_H +#define SUPPORTNODES_H + +#include "nodes/plannodes.h" + +struct PlannerInfo; /* avoid including pathnodes.h here */ +struct IndexOptInfo; +struct SpecialJoinInfo; +struct WindowClause; + +/* + * The Simplify request allows the support function to perform plan-time + * simplification of a call to its target function. For example, a varchar + * length coercion that does not decrease the allowed length of its argument + * could be replaced by a RelabelType node, or "x + 0" could be replaced by + * "x". This is invoked during the planner's constant-folding pass, so the + * function's arguments can be presumed already simplified. + * + * The planner's PlannerInfo "root" is typically not needed, but can be + * consulted if it's necessary to obtain info about Vars present in + * the given node tree. Beware that root could be NULL in some usages. + * + * "fcall" will be a FuncExpr invoking the support function's target + * function. (This is true even if the original parsetree node was an + * operator call; a FuncExpr is synthesized for this purpose.) + * + * The result should be a semantically-equivalent transformed node tree, + * or NULL if no simplification could be performed. Do *not* return or + * modify *fcall, as it isn't really a separately allocated Node. But + * it's okay to use fcall->args, or parts of it, in the result tree. + */ +typedef struct SupportRequestSimplify +{ + NodeTag type; + + struct PlannerInfo *root; /* Planner's infrastructure */ + FuncExpr *fcall; /* Function call to be simplified */ +} SupportRequestSimplify; + +/* + * The Selectivity request allows the support function to provide a + * selectivity estimate for a function appearing at top level of a WHERE + * clause (so it applies only to functions returning boolean). + * + * The input arguments are the same as are supplied to operator restriction + * and join estimators, except that we unify those two APIs into just one + * request type. See clause_selectivity() for the details. + * + * If an estimate can be made, store it into the "selectivity" field and + * return the address of the SupportRequestSelectivity node; the estimate + * must be between 0 and 1 inclusive. Return NULL if no estimate can be + * made (in which case the planner will fall back to a default estimate, + * traditionally 1/3). + * + * If the target function is being used as the implementation of an operator, + * the support function will not be used for this purpose; the operator's + * restriction or join estimator is consulted instead. + */ +typedef struct SupportRequestSelectivity +{ + NodeTag type; + + /* Input fields: */ + struct PlannerInfo *root; /* Planner's infrastructure */ + Oid funcid; /* function we are inquiring about */ + List *args; /* pre-simplified arguments to function */ + Oid inputcollid; /* function's input collation */ + bool is_join; /* is this a join or restriction case? */ + int varRelid; /* if restriction, RTI of target relation */ + JoinType jointype; /* if join, outer join type */ + struct SpecialJoinInfo *sjinfo; /* if outer join, info about join */ + + /* Output fields: */ + Selectivity selectivity; /* returned selectivity estimate */ +} SupportRequestSelectivity; + +/* + * The Cost request allows the support function to provide an execution + * cost estimate for its target function. The cost estimate can include + * both a one-time (query startup) component and a per-execution component. + * The estimate should *not* include the costs of evaluating the target + * function's arguments, only the target function itself. + * + * The "node" argument is normally the parse node that is invoking the + * target function. This is a FuncExpr in the simplest case, but it could + * also be an OpExpr, DistinctExpr, NullIfExpr, or WindowFunc, or possibly + * other cases in future. NULL is passed if the function cannot presume + * its arguments to be equivalent to what the calling node presents as + * arguments; that happens for, e.g., aggregate support functions and + * per-column comparison operators used by RowExprs. + * + * If an estimate can be made, store it into the cost fields and return the + * address of the SupportRequestCost node. Return NULL if no estimate can be + * made, in which case the planner will rely on the target function's procost + * field. (Note: while procost is automatically scaled by cpu_operator_cost, + * this is not the case for the outputs of the Cost request; the support + * function must scale its results appropriately on its own.) + */ +typedef struct SupportRequestCost +{ + NodeTag type; + + /* Input fields: */ + struct PlannerInfo *root; /* Planner's infrastructure (could be NULL) */ + Oid funcid; /* function we are inquiring about */ + Node *node; /* parse node invoking function, or NULL */ + + /* Output fields: */ + Cost startup; /* one-time cost */ + Cost per_tuple; /* per-evaluation cost */ +} SupportRequestCost; + +/* + * The Rows request allows the support function to provide an output rowcount + * estimate for its target function (so it applies only to set-returning + * functions). + * + * The "node" argument is the parse node that is invoking the target function; + * currently this will always be a FuncExpr or OpExpr. + * + * If an estimate can be made, store it into the rows field and return the + * address of the SupportRequestRows node. Return NULL if no estimate can be + * made, in which case the planner will rely on the target function's prorows + * field. + */ +typedef struct SupportRequestRows +{ + NodeTag type; + + /* Input fields: */ + struct PlannerInfo *root; /* Planner's infrastructure (could be NULL) */ + Oid funcid; /* function we are inquiring about */ + Node *node; /* parse node invoking function */ + + /* Output fields: */ + double rows; /* number of rows expected to be returned */ +} SupportRequestRows; + +/* + * The IndexCondition request allows the support function to generate + * a directly-indexable condition based on a target function call that is + * not itself indexable. The target function call must appear at the top + * level of WHERE or JOIN/ON, so this applies only to functions returning + * boolean. + * + * The "node" argument is the parse node that is invoking the target function; + * currently this will always be a FuncExpr or OpExpr. The call is made + * only if at least one function argument matches an index column's variable + * or expression. "indexarg" identifies the matching argument (it's the + * argument's zero-based index in the node's args list). + * + * If the transformation is possible, return a List of directly-indexable + * condition expressions, else return NULL. (A List is used because it's + * sometimes useful to generate more than one indexable condition, such as + * when a LIKE with constant prefix gives rise to both >= and < conditions.) + * + * "Directly indexable" means that the condition must be directly executable + * by the index machinery. Typically this means that it is a binary OpExpr + * with the index column value on the left, a pseudo-constant on the right, + * and an operator that is in the index column's operator family. Other + * possibilities include RowCompareExpr, ScalarArrayOpExpr, and NullTest, + * depending on the index type; but those seem less likely to be useful for + * derived index conditions. "Pseudo-constant" means that the right-hand + * expression must not contain any volatile functions, nor any Vars of the + * table the index is for; use is_pseudo_constant_for_index() to check this. + * (Note: if the passed "node" is an OpExpr, the core planner already verified + * that the non-indexkey operand is pseudo-constant; but when the "node" + * is a FuncExpr, it does not check, since it doesn't know which of the + * function's arguments you might need to use in an index comparison value.) + * + * In many cases, an index condition can be generated but it is weaker than + * the function condition itself; for example, a LIKE with a constant prefix + * can produce an index range check based on the prefix, but we still need + * to execute the LIKE operator to verify the rest of the pattern. We say + * that such an index condition is "lossy". When returning an index condition, + * you should set the "lossy" request field to true if the condition is lossy, + * or false if it is an exact equivalent of the function's result. The core + * code will initialize that field to true, which is the common case. + * + * It is important to verify that the index operator family is the correct + * one for the condition you want to generate. Core support functions tend + * to use the known OID of a built-in opfamily for this, but extensions need + * to work harder, since their OIDs aren't fixed. A possibly workable + * answer for an index on an extension datatype is to verify the index AM's + * OID instead, and then assume that there's only one relevant opclass for + * your datatype so the opfamily must be the right one. Generating OpExpr + * nodes may also require knowing extension datatype OIDs (often you can + * find these out by applying exprType() to a function argument) and + * operator OIDs (which you can look up using get_opfamily_member). + */ +typedef struct SupportRequestIndexCondition +{ + NodeTag type; + + /* Input fields: */ + struct PlannerInfo *root; /* Planner's infrastructure */ + Oid funcid; /* function we are inquiring about */ + Node *node; /* parse node invoking function */ + int indexarg; /* index of function arg matching indexcol */ + struct IndexOptInfo *index; /* planner's info about target index */ + int indexcol; /* index of target index column (0-based) */ + Oid opfamily; /* index column's operator family */ + Oid indexcollation; /* index column's collation */ + + /* Output fields: */ + bool lossy; /* set to false if index condition is an exact + * equivalent of the function call */ +} SupportRequestIndexCondition; + +/* ---------- + * To support more efficient query execution of any monotonically increasing + * and/or monotonically decreasing window functions, we support calling the + * window function's prosupport function passing along this struct whenever + * the planner sees an OpExpr qual directly reference a window function in a + * subquery. When the planner encounters this, we populate this struct and + * pass it along to the window function's prosupport function so that it can + * evaluate if the given WindowFunc is; + * + * a) monotonically increasing, or + * b) monotonically decreasing, or + * c) both monotonically increasing and decreasing, or + * d) none of the above. + * + * A function that is monotonically increasing can never return a value that + * is lower than a value returned in a "previous call". A monotonically + * decreasing function can never return a value higher than a value returned + * in a previous call. A function that is both must return the same value + * each time. + * + * We define "previous call" to mean a previous call to the same WindowFunc + * struct in the same window partition. + * + * row_number() is an example of a monotonically increasing function. The + * return value will be reset back to 1 in each new partition. An example of + * a monotonically increasing and decreasing function is COUNT(*) OVER (). + * Since there is no ORDER BY clause in this example, all rows in the + * partition are peers and all rows within the partition will be within the + * frame bound. Likewise for COUNT(*) OVER(ORDER BY a ROWS BETWEEN UNBOUNDED + * PRECEDING AND UNBOUNDED FOLLOWING). + * + * COUNT(*) OVER (ORDER BY a ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING) + * is an example of a monotonically decreasing function. + * + * Implementations must only concern themselves with the given WindowFunc + * being monotonic in a single partition. + * + * Inputs: + * 'window_func' is the pointer to the window function being called. + * + * 'window_clause' pointer to the WindowClause data. Support functions can + * use this to check frame bounds, etc. + * + * Outputs: + * 'monotonic' the resulting MonotonicFunction value for the given input + * window function and window clause. + * ---------- + */ +typedef struct SupportRequestWFuncMonotonic +{ + NodeTag type; + + /* Input fields: */ + WindowFunc *window_func; /* Pointer to the window function data */ + struct WindowClause *window_clause; /* Pointer to the window clause data */ + + /* Output fields: */ + MonotonicFunction monotonic; +} SupportRequestWFuncMonotonic; + +/* + * Some WindowFunc behavior might not be affected by certain variations in + * the WindowClause's frameOptions. For example, row_number() is coded in + * such a way that the frame options don't change the returned row number. + * nodeWindowAgg.c will have less work to do if the ROWS option is used + * instead of the RANGE option as no check needs to be done for peer rows. + * Since RANGE is included in the default frame options, window functions + * such as row_number() might want to change that to ROW. + * + * Here we allow a WindowFunc's support function to determine which, if + * anything, can be changed about the WindowClause which the WindowFunc + * belongs to. Currently only the frameOptions can be modified. However, + * we may want to allow more optimizations in the future. + * + * The support function is responsible for ensuring the optimized version of + * the frameOptions doesn't affect the result of the window function. The + * planner is responsible for only changing the frame options when all + * WindowFuncs using this particular WindowClause agree on what the optimized + * version of the frameOptions are. If a particular WindowFunc being used + * does not have a support function then the planner will not make any changes + * to the WindowClause's frameOptions. + * + * 'window_func' and 'window_clause' are set by the planner before calling the + * support function so that the support function has these fields available. + * These may be required in order to determine which optimizations are + * possible. + * + * 'frameOptions' is set by the planner to WindowClause.frameOptions. The + * support function must only adjust this if optimizations are possible for + * the given WindowFunc. + */ +typedef struct SupportRequestOptimizeWindowClause +{ + NodeTag type; + + /* Input fields: */ + WindowFunc *window_func; /* Pointer to the window function data */ + struct WindowClause *window_clause; /* Pointer to the window clause data */ + + /* Input/Output fields: */ + int frameOptions; /* New frameOptions, or left untouched if no + * optimizations are possible. */ +} SupportRequestOptimizeWindowClause; + +#endif /* SUPPORTNODES_H */ diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h new file mode 100644 index 0000000..b64e364 --- /dev/null +++ b/src/include/nodes/tidbitmap.h @@ -0,0 +1,75 @@ +/*------------------------------------------------------------------------- + * + * tidbitmap.h + * PostgreSQL tuple-id (TID) bitmap package + * + * This module provides bitmap data structures that are spiritually + * similar to Bitmapsets, but are specially adapted to store sets of + * tuple identifiers (TIDs), or ItemPointers. In particular, the division + * of an ItemPointer into BlockNumber and OffsetNumber is catered for. + * Also, since we wish to be able to store very large tuple sets in + * memory with this data structure, we support "lossy" storage, in which + * we no longer remember individual tuple offsets on a page but only the + * fact that a particular page needs to be visited. + * + * + * Copyright (c) 2003-2023, PostgreSQL Global Development Group + * + * src/include/nodes/tidbitmap.h + * + *------------------------------------------------------------------------- + */ +#ifndef TIDBITMAP_H +#define TIDBITMAP_H + +#include "storage/itemptr.h" +#include "utils/dsa.h" + + +/* + * Actual bitmap representation is private to tidbitmap.c. Callers can + * do IsA(x, TIDBitmap) on it, but nothing else. + */ +typedef struct TIDBitmap TIDBitmap; + +/* Likewise, TBMIterator is private */ +typedef struct TBMIterator TBMIterator; +typedef struct TBMSharedIterator TBMSharedIterator; + +/* Result structure for tbm_iterate */ +typedef struct TBMIterateResult +{ + BlockNumber blockno; /* page number containing tuples */ + int ntuples; /* -1 indicates lossy result */ + bool recheck; /* should the tuples be rechecked? */ + /* Note: recheck is always true if ntuples < 0 */ + OffsetNumber offsets[FLEXIBLE_ARRAY_MEMBER]; +} TBMIterateResult; + +/* function prototypes in nodes/tidbitmap.c */ + +extern TIDBitmap *tbm_create(long maxbytes, dsa_area *dsa); +extern void tbm_free(TIDBitmap *tbm); +extern void tbm_free_shared_area(dsa_area *dsa, dsa_pointer dp); + +extern void tbm_add_tuples(TIDBitmap *tbm, + const ItemPointer tids, int ntids, + bool recheck); +extern void tbm_add_page(TIDBitmap *tbm, BlockNumber pageno); + +extern void tbm_union(TIDBitmap *a, const TIDBitmap *b); +extern void tbm_intersect(TIDBitmap *a, const TIDBitmap *b); + +extern bool tbm_is_empty(const TIDBitmap *tbm); + +extern TBMIterator *tbm_begin_iterate(TIDBitmap *tbm); +extern dsa_pointer tbm_prepare_shared_iterate(TIDBitmap *tbm); +extern TBMIterateResult *tbm_iterate(TBMIterator *iterator); +extern TBMIterateResult *tbm_shared_iterate(TBMSharedIterator *iterator); +extern void tbm_end_iterate(TBMIterator *iterator); +extern void tbm_end_shared_iterate(TBMSharedIterator *iterator); +extern TBMSharedIterator *tbm_attach_shared_iterate(dsa_area *dsa, + dsa_pointer dp); +extern long tbm_calculate_entries(double maxbytes); + +#endif /* TIDBITMAP_H */ diff --git a/src/include/nodes/value.h b/src/include/nodes/value.h new file mode 100644 index 0000000..b24c4c1 --- /dev/null +++ b/src/include/nodes/value.h @@ -0,0 +1,90 @@ +/*------------------------------------------------------------------------- + * + * value.h + * interface for value nodes + * + * + * Copyright (c) 2003-2023, PostgreSQL Global Development Group + * + * src/include/nodes/value.h + * + *------------------------------------------------------------------------- + */ + +#ifndef VALUE_H +#define VALUE_H + +#include "nodes/nodes.h" + +/* + * The node types Integer, Float, String, and BitString are used to represent + * literals in the lexer and are also used to pass constants around in the + * parser. One difference between these node types and, say, a plain int or + * char * is that the nodes can be put into a List. + * + * (There used to be a Value node, which encompassed all these different node types. Hence the name of this file.) + */ + +typedef struct Integer +{ + pg_node_attr(special_read_write) + + NodeTag type; + int ival; +} Integer; + +/* + * Float is internally represented as string. Using T_Float as the node type + * simply indicates that the contents of the string look like a valid numeric + * literal. The value might end up being converted to NUMERIC, so we can't + * store it internally as a C double, since that could lose precision. Since + * these nodes are generally only used in the parsing process, not for runtime + * data, it's better to use the more general representation. + * + * Note that an integer-looking string will get lexed as T_Float if the value + * is too large to fit in an 'int'. + */ +typedef struct Float +{ + pg_node_attr(special_read_write) + + NodeTag type; + char *fval; +} Float; + +typedef struct Boolean +{ + pg_node_attr(special_read_write) + + NodeTag type; + bool boolval; +} Boolean; + +typedef struct String +{ + pg_node_attr(special_read_write) + + NodeTag type; + char *sval; +} String; + +typedef struct BitString +{ + pg_node_attr(special_read_write) + + NodeTag type; + char *bsval; +} BitString; + +#define intVal(v) (castNode(Integer, v)->ival) +#define floatVal(v) atof(castNode(Float, v)->fval) +#define boolVal(v) (castNode(Boolean, v)->boolval) +#define strVal(v) (castNode(String, v)->sval) + +extern Integer *makeInteger(int i); +extern Float *makeFloat(char *numericStr); +extern Boolean *makeBoolean(bool val); +extern String *makeString(char *str); +extern BitString *makeBitString(char *str); + +#endif /* VALUE_H */ |