summaryrefslogtreecommitdiffstats
path: root/sqlglot/dialects
diff options
context:
space:
mode:
Diffstat (limited to 'sqlglot/dialects')
-rw-r--r--sqlglot/dialects/bigquery.py33
-rw-r--r--sqlglot/dialects/hive.py15
-rw-r--r--sqlglot/dialects/oracle.py1
-rw-r--r--sqlglot/dialects/redshift.py10
-rw-r--r--sqlglot/dialects/snowflake.py1
5 files changed, 47 insertions, 13 deletions
diff --git a/sqlglot/dialects/bigquery.py b/sqlglot/dialects/bigquery.py
index 5b44912..6be68ac 100644
--- a/sqlglot/dialects/bigquery.py
+++ b/sqlglot/dialects/bigquery.py
@@ -110,17 +110,17 @@ class BigQuery(Dialect):
KEYWORDS = {
**tokens.Tokenizer.KEYWORDS,
+ "BEGIN": TokenType.COMMAND,
+ "BEGIN TRANSACTION": TokenType.BEGIN,
"CURRENT_DATETIME": TokenType.CURRENT_DATETIME,
"CURRENT_TIME": TokenType.CURRENT_TIME,
"GEOGRAPHY": TokenType.GEOGRAPHY,
- "INT64": TokenType.BIGINT,
"FLOAT64": TokenType.DOUBLE,
+ "INT64": TokenType.BIGINT,
+ "NOT DETERMINISTIC": TokenType.VOLATILE,
"QUALIFY": TokenType.QUALIFY,
"UNKNOWN": TokenType.NULL,
"WINDOW": TokenType.WINDOW,
- "NOT DETERMINISTIC": TokenType.VOLATILE,
- "BEGIN": TokenType.COMMAND,
- "BEGIN TRANSACTION": TokenType.BEGIN,
}
KEYWORDS.pop("DIV")
@@ -131,6 +131,7 @@ class BigQuery(Dialect):
"DATE_ADD": _date_add(exp.DateAdd),
"DATETIME_ADD": _date_add(exp.DatetimeAdd),
"DIV": lambda args: exp.IntDiv(this=seq_get(args, 0), expression=seq_get(args, 1)),
+ "REGEXP_CONTAINS": exp.RegexpLike.from_arg_list,
"TIME_ADD": _date_add(exp.TimeAdd),
"TIMESTAMP_ADD": _date_add(exp.TimestampAdd),
"DATE_SUB": _date_add(exp.DateSub),
@@ -144,6 +145,7 @@ class BigQuery(Dialect):
FUNCTION_PARSERS = {
**parser.Parser.FUNCTION_PARSERS,
+ "ARRAY": lambda self: self.expression(exp.Array, expressions=[self._parse_statement()]),
}
FUNCTION_PARSERS.pop("TRIM")
@@ -161,7 +163,6 @@ class BigQuery(Dialect):
class Generator(generator.Generator):
TRANSFORMS = {
**generator.Generator.TRANSFORMS,
- exp.Array: inline_array_sql,
exp.ArraySize: rename_func("ARRAY_LENGTH"),
exp.DateAdd: _date_add_sql("DATE", "ADD"),
exp.DateSub: _date_add_sql("DATE", "SUB"),
@@ -183,6 +184,7 @@ class BigQuery(Dialect):
exp.VolatilityProperty: lambda self, e: f"DETERMINISTIC"
if e.name == "IMMUTABLE"
else "NOT DETERMINISTIC",
+ exp.RegexpLike: rename_func("REGEXP_CONTAINS"),
}
TYPE_MAPPING = {
@@ -210,24 +212,31 @@ class BigQuery(Dialect):
EXPLICIT_UNION = True
- def transaction_sql(self, *_):
+ def array_sql(self, expression: exp.Array) -> str:
+ first_arg = seq_get(expression.expressions, 0)
+ if isinstance(first_arg, exp.Subqueryable):
+ return f"ARRAY{self.wrap(self.sql(first_arg))}"
+
+ return inline_array_sql(self, expression)
+
+ def transaction_sql(self, *_) -> str:
return "BEGIN TRANSACTION"
- def commit_sql(self, *_):
+ def commit_sql(self, *_) -> str:
return "COMMIT TRANSACTION"
- def rollback_sql(self, *_):
+ def rollback_sql(self, *_) -> str:
return "ROLLBACK TRANSACTION"
- def in_unnest_op(self, unnest):
- return self.sql(unnest)
+ def in_unnest_op(self, expression: exp.Unnest) -> str:
+ return self.sql(expression)
- def except_op(self, expression):
+ def except_op(self, expression: exp.Except) -> str:
if not expression.args.get("distinct", False):
self.unsupported("EXCEPT without DISTINCT is not supported in BigQuery")
return f"EXCEPT{' DISTINCT' if expression.args.get('distinct') else ' ALL'}"
- def intersect_op(self, expression):
+ def intersect_op(self, expression: exp.Intersect) -> str:
if not expression.args.get("distinct", False):
self.unsupported("INTERSECT without DISTINCT is not supported in BigQuery")
return f"INTERSECT{' DISTINCT' if expression.args.get('distinct') else ' ALL'}"
diff --git a/sqlglot/dialects/hive.py b/sqlglot/dialects/hive.py
index cbb39c2..70c1c6c 100644
--- a/sqlglot/dialects/hive.py
+++ b/sqlglot/dialects/hive.py
@@ -190,6 +190,7 @@ class Hive(Dialect):
"ADD FILES": TokenType.COMMAND,
"ADD JAR": TokenType.COMMAND,
"ADD JARS": TokenType.COMMAND,
+ "WITH SERDEPROPERTIES": TokenType.SERDE_PROPERTIES,
}
class Parser(parser.Parser):
@@ -238,6 +239,13 @@ class Hive(Dialect):
"YEAR": lambda args: exp.Year(this=exp.TsOrDsToDate.from_arg_list(args)),
}
+ PROPERTY_PARSERS = {
+ **parser.Parser.PROPERTY_PARSERS,
+ TokenType.SERDE_PROPERTIES: lambda self: exp.SerdeProperties(
+ expressions=self._parse_wrapped_csv(self._parse_property)
+ ),
+ }
+
class Generator(generator.Generator):
TYPE_MAPPING = {
**generator.Generator.TYPE_MAPPING,
@@ -297,6 +305,8 @@ class Hive(Dialect):
exp.UnixToTime: rename_func("FROM_UNIXTIME"),
exp.UnixToTimeStr: rename_func("FROM_UNIXTIME"),
exp.PartitionedByProperty: lambda self, e: f"PARTITIONED BY {self.sql(e, 'this')}",
+ exp.RowFormatSerdeProperty: lambda self, e: f"ROW FORMAT SERDE {self.sql(e, 'this')}",
+ exp.SerdeProperties: lambda self, e: self.properties(e, prefix="WITH SERDEPROPERTIES"),
exp.NumberToStr: rename_func("FORMAT_NUMBER"),
}
@@ -308,12 +318,15 @@ class Hive(Dialect):
exp.SchemaCommentProperty,
exp.LocationProperty,
exp.TableFormatProperty,
+ exp.RowFormatDelimitedProperty,
+ exp.RowFormatSerdeProperty,
+ exp.SerdeProperties,
}
def with_properties(self, properties):
return self.properties(
properties,
- prefix="TBLPROPERTIES",
+ prefix=self.seg("TBLPROPERTIES"),
)
def datatype_sql(self, expression):
diff --git a/sqlglot/dialects/oracle.py b/sqlglot/dialects/oracle.py
index ceaf9ba..f507513 100644
--- a/sqlglot/dialects/oracle.py
+++ b/sqlglot/dialects/oracle.py
@@ -98,6 +98,7 @@ class Oracle(Dialect):
class Tokenizer(tokens.Tokenizer):
KEYWORDS = {
**tokens.Tokenizer.KEYWORDS,
+ "MINUS": TokenType.EXCEPT,
"START": TokenType.BEGIN,
"TOP": TokenType.TOP,
"VARCHAR2": TokenType.VARCHAR,
diff --git a/sqlglot/dialects/redshift.py b/sqlglot/dialects/redshift.py
index cd50979..55ed0a6 100644
--- a/sqlglot/dialects/redshift.py
+++ b/sqlglot/dialects/redshift.py
@@ -1,6 +1,7 @@
from __future__ import annotations
from sqlglot import exp, transforms
+from sqlglot.dialects.dialect import rename_func
from sqlglot.dialects.postgres import Postgres
from sqlglot.tokens import TokenType
@@ -13,12 +14,20 @@ class Redshift(Postgres):
"HH": "%H",
}
+ class Parser(Postgres.Parser):
+ FUNCTIONS = {
+ **Postgres.Parser.FUNCTIONS, # type: ignore
+ "DECODE": exp.Matches.from_arg_list,
+ "NVL": exp.Coalesce.from_arg_list,
+ }
+
class Tokenizer(Postgres.Tokenizer):
ESCAPES = ["\\"]
KEYWORDS = {
**Postgres.Tokenizer.KEYWORDS, # type: ignore
"COPY": TokenType.COMMAND,
+ "ENCODE": TokenType.ENCODE,
"GEOMETRY": TokenType.GEOMETRY,
"GEOGRAPHY": TokenType.GEOGRAPHY,
"HLLSKETCH": TokenType.HLLSKETCH,
@@ -50,4 +59,5 @@ class Redshift(Postgres):
exp.DistKeyProperty: lambda self, e: f"DISTKEY({e.name})",
exp.SortKeyProperty: lambda self, e: f"{'COMPOUND ' if e.args['compound'] else ''}SORTKEY({self.format_args(*e.this)})",
exp.DistStyleProperty: lambda self, e: self.naked_property(e),
+ exp.Matches: rename_func("DECODE"),
}
diff --git a/sqlglot/dialects/snowflake.py b/sqlglot/dialects/snowflake.py
index 46155ff..75dc9dc 100644
--- a/sqlglot/dialects/snowflake.py
+++ b/sqlglot/dialects/snowflake.py
@@ -198,6 +198,7 @@ class Snowflake(Dialect):
"TIMESTAMP_NTZ": TokenType.TIMESTAMP,
"TIMESTAMP_TZ": TokenType.TIMESTAMPTZ,
"TIMESTAMPNTZ": TokenType.TIMESTAMP,
+ "MINUS": TokenType.EXCEPT,
"SAMPLE": TokenType.TABLE_SAMPLE,
}
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-10 23:24:56 +0000