Edit on GitHub

sqlglot.dialects.starrocks

View Source

 1from __future__ import annotations
 2
 3from sqlglot import exp
 4from sqlglot.dialects.dialect import (
 5    approx_count_distinct_sql,
 6    arrow_json_extract_sql,
 7    rename_func,
 8)
 9from sqlglot.dialects.mysql import MySQL
10from sqlglot.helper import seq_get
11
12
13class StarRocks(MySQL):
14    class Parser(MySQL.Parser):
15        FUNCTIONS = {
16            **MySQL.Parser.FUNCTIONS,
17            "DATE_TRUNC": lambda args: exp.TimestampTrunc(
18                this=seq_get(args, 1), unit=seq_get(args, 0)
19            ),
20        }
21
22    class Generator(MySQL.Generator):
23        TYPE_MAPPING = {
24            **MySQL.Generator.TYPE_MAPPING,
25            exp.DataType.Type.TEXT: "STRING",
26            exp.DataType.Type.TIMESTAMP: "DATETIME",
27            exp.DataType.Type.TIMESTAMPTZ: "DATETIME",
28        }
29
30        TRANSFORMS = {
31            **MySQL.Generator.TRANSFORMS,
32            exp.ApproxDistinct: approx_count_distinct_sql,
33            exp.JSONExtractScalar: arrow_json_extract_sql,
34            exp.JSONExtract: arrow_json_extract_sql,
35            exp.DateDiff: rename_func("DATEDIFF"),
36            exp.RegexpLike: rename_func("REGEXP"),
37            exp.StrToUnix: lambda self, e: f"UNIX_TIMESTAMP({self.sql(e, 'this')}, {self.format_time(e)})",
38            exp.TimestampTrunc: lambda self, e: self.func(
39                "DATE_TRUNC", exp.Literal.string(e.text("unit")), e.this
40            ),
41            exp.TimeStrToDate: rename_func("TO_DATE"),
42            exp.UnixToStr: lambda self, e: f"FROM_UNIXTIME({self.sql(e, 'this')}, {self.format_time(e)})",
43            exp.UnixToTime: rename_func("FROM_UNIXTIME"),
44        }
45
46        TRANSFORMS.pop(exp.DateTrunc)

class StarRocks(sqlglot.dialects.mysql.MySQL): View Source

14class StarRocks(MySQL):
15    class Parser(MySQL.Parser):
16        FUNCTIONS = {
17            **MySQL.Parser.FUNCTIONS,
18            "DATE_TRUNC": lambda args: exp.TimestampTrunc(
19                this=seq_get(args, 1), unit=seq_get(args, 0)
20            ),
21        }
22
23    class Generator(MySQL.Generator):
24        TYPE_MAPPING = {
25            **MySQL.Generator.TYPE_MAPPING,
26            exp.DataType.Type.TEXT: "STRING",
27            exp.DataType.Type.TIMESTAMP: "DATETIME",
28            exp.DataType.Type.TIMESTAMPTZ: "DATETIME",
29        }
30
31        TRANSFORMS = {
32            **MySQL.Generator.TRANSFORMS,
33            exp.ApproxDistinct: approx_count_distinct_sql,
34            exp.JSONExtractScalar: arrow_json_extract_sql,
35            exp.JSONExtract: arrow_json_extract_sql,
36            exp.DateDiff: rename_func("DATEDIFF"),
37            exp.RegexpLike: rename_func("REGEXP"),
38            exp.StrToUnix: lambda self, e: f"UNIX_TIMESTAMP({self.sql(e, 'this')}, {self.format_time(e)})",
39            exp.TimestampTrunc: lambda self, e: self.func(
40                "DATE_TRUNC", exp.Literal.string(e.text("unit")), e.this
41            ),
42            exp.TimeStrToDate: rename_func("TO_DATE"),
43            exp.UnixToStr: lambda self, e: f"FROM_UNIXTIME({self.sql(e, 'this')}, {self.format_time(e)})",
44            exp.UnixToTime: rename_func("FROM_UNIXTIME"),
45        }
46
47        TRANSFORMS.pop(exp.DateTrunc)

Inherited Members

sqlglot.dialects.mysql.MySQL: Tokenizer
sqlglot.dialects.dialect.Dialect: get_or_raise; format_time; normalize_identifier; case_sensitive; can_identify; quote_identifier; parse; parse_into; generate; transpile; tokenize; parser; generator

class StarRocks.Parser(sqlglot.dialects.mysql.MySQL.Parser): View Source

15    class Parser(MySQL.Parser):
16        FUNCTIONS = {
17            **MySQL.Parser.FUNCTIONS,
18            "DATE_TRUNC": lambda args: exp.TimestampTrunc(
19                this=seq_get(args, 1), unit=seq_get(args, 0)
20            ),
21        }

Parser consumes a list of tokens produced by the Tokenizer and produces a parsed syntax tree.

Arguments:

error_level: The desired error level. Default: ErrorLevel.IMMEDIATE
error_message_context: Determines the amount of context to capture from a query string when displaying the error message (in number of characters). Default: 100
max_errors: Maximum number of error messages to include in a raised ParseError. This is only relevant if error_level is ErrorLevel.RAISE. Default: 3

Inherited Members

sqlglot.parser.Parser: Parser; reset; parse; parse_into; check_errors; raise_error; expression; validate_expression

class StarRocks.Generator(sqlglot.dialects.mysql.MySQL.Generator): View Source

23    class Generator(MySQL.Generator):
24        TYPE_MAPPING = {
25            **MySQL.Generator.TYPE_MAPPING,
26            exp.DataType.Type.TEXT: "STRING",
27            exp.DataType.Type.TIMESTAMP: "DATETIME",
28            exp.DataType.Type.TIMESTAMPTZ: "DATETIME",
29        }
30
31        TRANSFORMS = {
32            **MySQL.Generator.TRANSFORMS,
33            exp.ApproxDistinct: approx_count_distinct_sql,
34            exp.JSONExtractScalar: arrow_json_extract_sql,
35            exp.JSONExtract: arrow_json_extract_sql,
36            exp.DateDiff: rename_func("DATEDIFF"),
37            exp.RegexpLike: rename_func("REGEXP"),
38            exp.StrToUnix: lambda self, e: f"UNIX_TIMESTAMP({self.sql(e, 'this')}, {self.format_time(e)})",
39            exp.TimestampTrunc: lambda self, e: self.func(
40                "DATE_TRUNC", exp.Literal.string(e.text("unit")), e.this
41            ),
42            exp.TimeStrToDate: rename_func("TO_DATE"),
43            exp.UnixToStr: lambda self, e: f"FROM_UNIXTIME({self.sql(e, 'this')}, {self.format_time(e)})",
44            exp.UnixToTime: rename_func("FROM_UNIXTIME"),
45        }
46
47        TRANSFORMS.pop(exp.DateTrunc)

Generator converts a given syntax tree to the corresponding SQL string.

Arguments:

pretty: Whether or not to format the produced SQL string. Default: False.
identify: Determines when an identifier should be quoted. Possible values are: False (default): Never quote, except in cases where it's mandatory by the dialect. True or 'always': Always quote. 'safe': Only quote identifiers that are case insensitive.
normalize: Whether or not to normalize identifiers to lowercase. Default: False.
pad: Determines the pad size in a formatted string. Default: 2.
indent: Determines the indentation size in a formatted string. Default: 2.
normalize_functions: Whether or not to normalize all function names. Possible values are: "upper" or True (default): Convert names to uppercase. "lower": Convert names to lowercase. False: Disables function name normalization.
unsupported_level: Determines the generator's behavior when it encounters unsupported expressions. Default ErrorLevel.WARN.
max_unsupported: Maximum number of unsupported messages to include in a raised UnsupportedError. This is only relevant if unsupported_level is ErrorLevel.RAISE. Default: 3
leading_comma: Determines whether or not the comma is leading or trailing in select expressions. This is only relevant when generating in pretty mode. Default: False
max_text_width: The max number of characters in a segment before creating new lines in pretty mode. The default is on the smaller end because the length only represents a segment and not the true line length. Default: 80
comments: Whether or not to preserve comments in the output SQL code. Default: True

@classmethod

def can_identify(text: str, identify: str | bool = 'safe') -> bool: View Source

247    @classmethod
248    def can_identify(cls, text: str, identify: str | bool = "safe") -> bool:
249        """Checks if text can be identified given an identify option.
250
251        Args:
252            text: The text to check.
253            identify:
254                "always" or `True`: Always returns true.
255                "safe": True if the identifier is case-insensitive.
256
257        Returns:
258            Whether or not the given text can be identified.
259        """
260        if identify is True or identify == "always":
261            return True
262
263        if identify == "safe":
264            return not cls.case_sensitive(text)
265
266        return False

Checks if text can be identified given an identify option.

Arguments:

text: The text to check.
identify: "always" or True: Always returns true. "safe": True if the identifier is case-insensitive.

Returns:

Whether or not the given text can be identified.

Inherited Members

sqlglot.generator.Generator: Generator; generate; unsupported; sep; seg; pad_comment; maybe_comment; wrap; no_identify; normalize_func; indent; sql; uncache_sql; cache_sql; characterset_sql; column_sql; columnposition_sql; columndef_sql; columnconstraint_sql; autoincrementcolumnconstraint_sql; compresscolumnconstraint_sql; generatedasidentitycolumnconstraint_sql; notnullcolumnconstraint_sql; primarykeycolumnconstraint_sql; uniquecolumnconstraint_sql; createable_sql; create_sql; clone_sql; describe_sql; prepend_ctes; with_sql; cte_sql; tablealias_sql; bitstring_sql; hexstring_sql; bytestring_sql; rawstring_sql; datatypesize_sql; datatype_sql; directory_sql; delete_sql; drop_sql; except_sql; except_op; fetch_sql; filter_sql; hint_sql; index_sql; identifier_sql; inputoutputformat_sql; national_sql; partition_sql; properties_sql; root_properties; properties; with_properties; locate_properties; property_sql; likeproperty_sql; fallbackproperty_sql; journalproperty_sql; freespaceproperty_sql; checksumproperty_sql; mergeblockratioproperty_sql; datablocksizeproperty_sql; blockcompressionproperty_sql; isolatedloadingproperty_sql; lockingproperty_sql; withdataproperty_sql; insert_sql; intersect_sql; intersect_op; introducer_sql; pseudotype_sql; onconflict_sql; returning_sql; rowformatdelimitedproperty_sql; table_sql; tablesample_sql; pivot_sql; tuple_sql; update_sql; values_sql; var_sql; into_sql; from_sql; group_sql; having_sql; join_sql; lambda_sql; lateral_sql; limit_sql; offset_sql; setitem_sql; set_sql; pragma_sql; lock_sql; literal_sql; escape_str; loaddata_sql; null_sql; boolean_sql; order_sql; cluster_sql; distribute_sql; sort_sql; ordered_sql; matchrecognize_sql; query_modifiers; offset_limit_modifiers; after_having_modifiers; after_limit_modifiers; select_sql; schema_sql; schema_columns_sql; star_sql; parameter_sql; sessionparameter_sql; placeholder_sql; subquery_sql; qualify_sql; union_sql; union_op; unnest_sql; where_sql; window_sql; partition_by_sql; windowspec_sql; withingroup_sql; between_sql; bracket_sql; all_sql; any_sql; exists_sql; case_sql; constraint_sql; nextvaluefor_sql; extract_sql; trim_sql; safeconcat_sql; check_sql; foreignkey_sql; primarykey_sql; if_sql; matchagainst_sql; jsonkeyvalue_sql; jsonobject_sql; openjsoncolumndef_sql; openjson_sql; in_sql; in_unnest_op; interval_sql; return_sql; reference_sql; anonymous_sql; paren_sql; neg_sql; not_sql; alias_sql; aliases_sql; attimezone_sql; add_sql; and_sql; connector_sql; bitwiseand_sql; bitwiseleftshift_sql; bitwisenot_sql; bitwiseor_sql; bitwiserightshift_sql; bitwisexor_sql; cast_sql; currentdate_sql; collate_sql; command_sql; comment_sql; mergetreettlaction_sql; mergetreettl_sql; transaction_sql; commit_sql; rollback_sql; altercolumn_sql; renametable_sql; altertable_sql; droppartition_sql; addconstraint_sql; distinct_sql; ignorenulls_sql; respectnulls_sql; intdiv_sql; dpipe_sql; safedpipe_sql; div_sql; overlaps_sql; distance_sql; dot_sql; eq_sql; escape_sql; glob_sql; gt_sql; gte_sql; ilike_sql; ilikeany_sql; is_sql; like_sql; likeany_sql; similarto_sql; lt_sql; lte_sql; mod_sql; mul_sql; neq_sql; nullsafeeq_sql; nullsafeneq_sql; or_sql; slice_sql; sub_sql; trycast_sql; use_sql; binary; function_fallback_sql; func; format_args; text_width; format_time; expressions; op_expressions; naked_property; set_operation; tag_sql; token_sql; userdefinedfunction_sql; joinhint_sql; kwarg_sql; when_sql; merge_sql; tochar_sql; dictproperty_sql; dictrange_sql; dictsubproperty_sql; oncluster_sql
sqlglot.dialects.mysql.MySQL.Generator: show_sql