sqlglot 26.29.0__py3-none-any.whl → 26.30.0__py3-none-any.whl

sqlglot/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '26.29.0'
-__version_tuple__ = version_tuple = (26, 29, 0)
+__version__ = version = '26.30.0'
+__version_tuple__ = version_tuple = (26, 30, 0)

sqlglot/dialects/__init__.py

@@ -74,6 +74,7 @@ DIALECTS = [
     "Druid",
     "DuckDB",
     "Dune",
+    "Fabric",
     "Hive",
     "Materialize",
     "MySQL",

sqlglot/dialects/bigquery.py

@@ -524,6 +524,7 @@ class BigQuery(Dialect):
         PREFIXED_PIVOT_COLUMNS = True
         LOG_DEFAULTS_TO_LN = True
         SUPPORTS_IMPLICIT_UNNEST = True
+        JOINS_HAVE_EQUAL_PRECEDENCE = True
 
         # BigQuery does not allow ASC/DESC to be used as an identifier
         ID_VAR_TOKENS = parser.Parser.ID_VAR_TOKENS - {TokenType.ASC, TokenType.DESC}

sqlglot/dialects/clickhouse.py

@@ -297,6 +297,7 @@ class ClickHouse(Dialect):
         MODIFIERS_ATTACHED_TO_SET_OP = False
         INTERVAL_SPANS = False
         OPTIONAL_ALIAS_TOKEN_CTE = False
+        JOINS_HAVE_EQUAL_PRECEDENCE = True
 
         FUNCTIONS = {
             **parser.Parser.FUNCTIONS,
@@ -691,6 +692,7 @@ class ClickHouse(Dialect):
             parse_bracket: bool = False,
             is_db_reference: bool = False,
             parse_partition: bool = False,
+            consume_pipe: bool = False,
         ) -> t.Optional[exp.Expression]:
             this = super()._parse_table(
                 schema=schema,

sqlglot/dialects/dialect.py

@@ -77,6 +77,7 @@ class Dialects(str, Enum):
     DRUID = "druid"
     DUCKDB = "duckdb"
     DUNE = "dune"
+    FABRIC = "fabric"
     HIVE = "hive"
     MATERIALIZE = "materialize"
     MYSQL = "mysql"
@@ -1906,12 +1907,19 @@ def groupconcat_sql(
 
 def build_timetostr_or_tochar(args: t.List, dialect: Dialect) -> exp.TimeToStr | exp.ToChar:
     this = seq_get(args, 0)
+    format = seq_get(args, 1)
 
-    if this and not this.type:
-        from sqlglot.optimizer.annotate_types import annotate_types
+    if this:
+        if not this.type:
+            from sqlglot.optimizer.annotate_types import annotate_types
+
+            annotate_types(this, dialect=dialect)
 
-        annotate_types(this, dialect=dialect)
-        if this.is_type(*exp.DataType.TEMPORAL_TYPES):
+        from sqlglot.dialects import Snowflake
+
+        if this.is_type(*exp.DataType.TEMPORAL_TYPES) or (
+            isinstance(format, exp.Literal) and format.name in Snowflake.TIME_MAPPING
+        ):
             dialect_name = dialect.__class__.__name__.lower()
             return build_formatted_time(exp.TimeToStr, dialect_name, default=True)(args)
 

sqlglot/dialects/duckdb.py

@@ -508,6 +508,7 @@ class DuckDB(Dialect):
             parse_bracket: bool = False,
             is_db_reference: bool = False,
             parse_partition: bool = False,
+            consume_pipe: bool = False,
         ) -> t.Optional[exp.Expression]:
             # DuckDB supports prefix aliases, e.g. FROM foo: bar
             if self._next and self._next.token_type == TokenType.COLON:

sqlglot/dialects/fabric.py

@@ -0,0 +1,88 @@
+from __future__ import annotations
+
+from sqlglot import exp
+from sqlglot.dialects.dialect import NormalizationStrategy
+from sqlglot.dialects.tsql import TSQL
+
+
+class Fabric(TSQL):
+    """
+    Microsoft Fabric Data Warehouse dialect that inherits from T-SQL.
+
+    Microsoft Fabric is a cloud-based analytics platform that provides a unified
+    data warehouse experience. While it shares much of T-SQL's syntax, it has
+    specific differences and limitations that this dialect addresses.
+
+    Key differences from T-SQL:
+    - Case-sensitive identifiers (unlike T-SQL which is case-insensitive)
+    - Limited data type support with mappings to supported alternatives
+    - Temporal types (DATETIME2, DATETIMEOFFSET, TIME) limited to 6 digits precision
+    - Certain legacy types (MONEY, SMALLMONEY, etc.) are not supported
+    - Unicode types (NCHAR, NVARCHAR) are mapped to non-unicode equivalents
+
+    References:
+    - Data Types: https://learn.microsoft.com/en-us/fabric/data-warehouse/data-types
+    - T-SQL Surface Area: https://learn.microsoft.com/en-us/fabric/data-warehouse/tsql-surface-area
+    """
+
+    # Fabric is case-sensitive unlike T-SQL which is case-insensitive
+    NORMALIZATION_STRATEGY = NormalizationStrategy.CASE_SENSITIVE
+
+    class Generator(TSQL.Generator):
+        # Fabric-specific type mappings - override T-SQL types that aren't supported
+        # Reference: https://learn.microsoft.com/en-us/fabric/data-warehouse/data-types
+        TYPE_MAPPING = {
+            **TSQL.Generator.TYPE_MAPPING,
+            # Fabric doesn't support these types, map to alternatives
+            exp.DataType.Type.MONEY: "DECIMAL",
+            exp.DataType.Type.SMALLMONEY: "DECIMAL",
+            exp.DataType.Type.DATETIME: "DATETIME2(6)",
+            exp.DataType.Type.SMALLDATETIME: "DATETIME2(6)",
+            exp.DataType.Type.NCHAR: "CHAR",
+            exp.DataType.Type.NVARCHAR: "VARCHAR",
+            exp.DataType.Type.TEXT: "VARCHAR(MAX)",
+            exp.DataType.Type.IMAGE: "VARBINARY",
+            exp.DataType.Type.TINYINT: "SMALLINT",
+            exp.DataType.Type.UTINYINT: "SMALLINT",  # T-SQL parses TINYINT as UTINYINT
+            exp.DataType.Type.JSON: "VARCHAR",
+            exp.DataType.Type.XML: "VARCHAR",
+            exp.DataType.Type.UUID: "VARBINARY(MAX)",  # UNIQUEIDENTIFIER has limitations in Fabric
+            # Override T-SQL mappings that use different names in Fabric
+            exp.DataType.Type.DECIMAL: "DECIMAL",  # T-SQL uses NUMERIC
+            exp.DataType.Type.DOUBLE: "FLOAT",
+            exp.DataType.Type.INT: "INT",  # T-SQL uses INTEGER
+        }
+
+        def datatype_sql(self, expression: exp.DataType) -> str:
+            """
+            Override datatype generation to handle Fabric-specific precision limitations.
+
+            Fabric limits temporal types (TIME, DATETIME2, DATETIMEOFFSET) to max 6 digits precision.
+            When no precision is specified, we default to 6 digits.
+            """
+            if expression.is_type(
+                exp.DataType.Type.TIME,
+                exp.DataType.Type.DATETIME2,
+                exp.DataType.Type.TIMESTAMPTZ,  # DATETIMEOFFSET in Fabric
+            ):
+                # Get the current precision (first expression if it exists)
+                precision = expression.find(exp.DataTypeParam)
+
+                # Determine the target precision
+                if precision is None:
+                    # No precision specified, default to 6
+                    target_precision = 6
+                elif precision.this.is_int:
+                    # Cap precision at 6
+                    current_precision = precision.this.to_py()
+                    target_precision = min(current_precision, 6)
+
+                # Create a new expression with the target precision
+                new_expression = exp.DataType(
+                    this=expression.this,
+                    expressions=[exp.DataTypeParam(this=exp.Literal.number(target_precision))],
+                )
+
+                return super().datatype_sql(new_expression)
+
+            return super().datatype_sql(expression)

sqlglot/dialects/hive.py

@@ -305,6 +305,7 @@ class Hive(Dialect):
         LOG_DEFAULTS_TO_LN = True
         STRICT_CAST = False
         VALUES_FOLLOWED_BY_PAREN = False
+        JOINS_HAVE_EQUAL_PRECEDENCE = True
 
         FUNCTIONS = {
             **parser.Parser.FUNCTIONS,

sqlglot/dialects/oracle.py

@@ -128,6 +128,7 @@ class Oracle(Dialect):
             "NEXT": lambda self: self._parse_next_value_for(),
             "PRIOR": lambda self: self.expression(exp.Prior, this=self._parse_bitwise()),
             "SYSDATE": lambda self: self.expression(exp.CurrentTimestamp, sysdate=True),
+            "DBMS_RANDOM": lambda self: self._parse_dbms_random(),
         }
 
         FUNCTION_PARSERS: t.Dict[str, t.Callable] = {
@@ -177,6 +178,19 @@ class Oracle(Dialect):
             ),
         }
 
+        def _parse_dbms_random(self) -> t.Optional[exp.Expression]:
+            if self._match_text_seq(".", "VALUE"):
+                lower, upper = None, None
+                if self._match(TokenType.L_PAREN, advance=False):
+                    lower_upper = self._parse_wrapped_csv(self._parse_bitwise)
+                    if len(lower_upper) == 2:
+                        lower, upper = lower_upper
+
+                return exp.Rand(lower=lower, upper=upper)
+
+            self._retreat(self._index - 1)
+            return None
+
         def _parse_json_array(self, expr_type: t.Type[E], **kwargs) -> E:
             return self.expression(
                 expr_type,
@@ -299,6 +313,7 @@ class Oracle(Dialect):
             exp.LogicalOr: rename_func("MAX"),
             exp.LogicalAnd: rename_func("MIN"),
             exp.Mod: rename_func("MOD"),
+            exp.Rand: rename_func("DBMS_RANDOM.VALUE"),
             exp.Select: transforms.preprocess(
                 [
                     transforms.eliminate_distinct_on,

sqlglot/dialects/presto.py

@@ -315,6 +315,7 @@ class Presto(Dialect):
 
     class Parser(parser.Parser):
         VALUES_FOLLOWED_BY_PAREN = False
+        ZONE_AWARE_TIMESTAMP_CONSTRUCTOR = True
 
         FUNCTIONS = {
             **parser.Parser.FUNCTIONS,

sqlglot/dialects/prql.py

@@ -189,11 +189,15 @@ class PRQL(Dialect):
             parse_bracket: bool = False,
             is_db_reference: bool = False,
             parse_partition: bool = False,
+            consume_pipe: bool = False,
         ) -> t.Optional[exp.Expression]:
             return self._parse_table_parts()
 
         def _parse_from(
-            self, joins: bool = False, skip_from_token: bool = False
+            self,
+            joins: bool = False,
+            skip_from_token: bool = False,
+            consume_pipe: bool = False,
         ) -> t.Optional[exp.From]:
             if not skip_from_token and not self._match(TokenType.FROM):
                 return None

sqlglot/dialects/redshift.py

@@ -90,6 +90,7 @@ class Redshift(Postgres):
             parse_bracket: bool = False,
             is_db_reference: bool = False,
             parse_partition: bool = False,
+            consume_pipe: bool = False,
         ) -> t.Optional[exp.Expression]:
             # Redshift supports UNPIVOTing SUPER objects, e.g. `UNPIVOT foo.obj[0] AS val AT attr`
             unpivot = self._match(TokenType.UNPIVOT)

sqlglot/dialects/snowflake.py

@@ -799,6 +799,7 @@ class Snowflake(Dialect):
             parse_bracket: bool = False,
             is_db_reference: bool = False,
             parse_partition: bool = False,
+            consume_pipe: bool = False,
         ) -> t.Optional[exp.Expression]:
             table = super()._parse_table(
                 schema=schema,

sqlglot/dialects/spark.py

@@ -7,6 +7,7 @@ from sqlglot.dialects.dialect import rename_func, unit_to_var, timestampdiff_sql
 from sqlglot.dialects.hive import _build_with_ignore_nulls
 from sqlglot.dialects.spark2 import Spark2, temporary_storage_provider, _build_as_cast
 from sqlglot.helper import ensure_list, seq_get
+from sqlglot.tokens import TokenType
 from sqlglot.transforms import (
     ctas_with_tmp_tables_to_create_tmp_view,
     remove_unique_constraints,
@@ -121,6 +122,16 @@ class Spark(Spark2):
             ),
         }
 
+        PLACEHOLDER_PARSERS = {
+            **Spark2.Parser.PLACEHOLDER_PARSERS,
+            TokenType.L_BRACE: lambda self: self._parse_query_parameter(),
+        }
+
+        def _parse_query_parameter(self) -> t.Optional[exp.Expression]:
+            this = self._parse_id_var()
+            self._match(TokenType.R_BRACE)
+            return self.expression(exp.Placeholder, this=this, widget=True)
+
         def _parse_generated_as_identity(
             self,
         ) -> (
@@ -200,3 +211,9 @@ class Spark(Spark2):
                 return self.func("DATEDIFF", unit_to_var(expression), start, end)
 
             return self.func("DATEDIFF", end, start)
+
+        def placeholder_sql(self, expression: exp.Placeholder) -> str:
+            if not expression.args.get("widget"):
+                return super().placeholder_sql(expression)
+
+            return f"{{{expression.name}}}"

sqlglot/dialects/sqlite.py

@@ -102,6 +102,10 @@ class SQLite(Dialect):
         COMMANDS = {*tokens.Tokenizer.COMMANDS, TokenType.REPLACE}
 
     class Parser(parser.Parser):
+        STRING_ALIASES = True
+        ALTER_RENAME_REQUIRES_COLUMN = False
+        JOINS_HAVE_EQUAL_PRECEDENCE = True
+
         FUNCTIONS = {
             **parser.Parser.FUNCTIONS,
             "EDITDIST3": exp.Levenshtein.from_arg_list,
@@ -110,9 +114,6 @@ class SQLite(Dialect):
             "TIME": lambda args: exp.Anonymous(this="TIME", expressions=args),
         }
 
-        STRING_ALIASES = True
-        ALTER_RENAME_REQUIRES_COLUMN = False
-
         def _parse_unique(self) -> exp.UniqueColumnConstraint:
             # Do not consume more tokens if UNIQUE is used as a standalone constraint, e.g:
             # CREATE TABLE foo (bar TEXT UNIQUE REFERENCES baz ...)

sqlglot/expressions.py

@@ -4453,8 +4453,9 @@ class SessionParameter(Condition):
     arg_types = {"this": True, "kind": False}
 
 
+# https://www.databricks.com/blog/parameterized-queries-pyspark
 class Placeholder(Condition):
-    arg_types = {"this": False, "kind": False}
+    arg_types = {"this": False, "kind": False, "widget": False}
 
     @property
     def name(self) -> str:

sqlglot/parser.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import logging
+import re
 import typing as t
 import itertools
 from collections import defaultdict
@@ -23,6 +24,9 @@ logger = logging.getLogger("sqlglot")
 
 OPTIONS_TYPE = t.Dict[str, t.Sequence[t.Union[t.Sequence[str], str]]]
 
+# Used to detect alphabetical characters and +/- in timestamp literals
+TIME_ZONE_RE: t.Pattern[str] = re.compile(r":.*?[a-zA-Z\+\-]")
+
 
 def build_var_map(args: t.List) -> exp.StarMap | exp.VarMap:
     if len(args) == 1 and args[0].is_star:
@@ -935,7 +939,6 @@ class Parser(metaclass=_Parser):
         "AS": lambda self, query: self._build_pipe_cte(
             query, [exp.Star()], self._parse_table_alias()
         ),
-        "DROP": lambda self, query: self._parse_pipe_syntax_drop(query),
         "EXTEND": lambda self, query: self._parse_pipe_syntax_extend(query),
         "LIMIT": lambda self, query: self._parse_pipe_syntax_limit(query),
         "ORDER BY": lambda self, query: query.order_by(
@@ -943,7 +946,6 @@ class Parser(metaclass=_Parser):
         ),
         "PIVOT": lambda self, query: self._parse_pipe_syntax_pivot(query),
         "SELECT": lambda self, query: self._parse_pipe_syntax_select(query),
-        "SET": lambda self, query: self._parse_pipe_syntax_set(query),
         "TABLESAMPLE": lambda self, query: self._parse_pipe_syntax_tablesample(query),
         "UNPIVOT": lambda self, query: self._parse_pipe_syntax_pivot(query),
         "WHERE": lambda self, query: query.where(self._parse_where(), copy=False),
@@ -1518,6 +1520,15 @@ class Parser(metaclass=_Parser):
     # Whether renaming a column with an ALTER statement requires the presence of the COLUMN keyword
     ALTER_RENAME_REQUIRES_COLUMN = True
 
+    # Whether all join types have the same precedence, i.e., they "naturally" produce a left-deep tree.
+    # In standard SQL, joins that use the JOIN keyword take higher precedence than comma-joins. That is
+    # to say, JOIN operators happen before comma operators. This is not the case in some dialects, such
+    # as BigQuery, where all joins have the same precedence.
+    JOINS_HAVE_EQUAL_PRECEDENCE = False
+
+    # Whether TIMESTAMP <literal> can produce a zone-aware timestamp
+    ZONE_AWARE_TIMESTAMP_CONSTRUCTOR = False
+
     __slots__ = (
         "error_level",
         "error_message_context",
@@ -3142,7 +3153,7 @@ class Parser(metaclass=_Parser):
                 is_unpivot=self._prev.token_type == TokenType.UNPIVOT
             )
         elif self._match(TokenType.FROM):
-            from_ = self._parse_from(skip_from_token=True)
+            from_ = self._parse_from(skip_from_token=True, consume_pipe=True)
             # Support parentheses for duckdb FROM-first syntax
             select = self._parse_select()
             if select:
@@ -3152,7 +3163,7 @@ class Parser(metaclass=_Parser):
                 this = exp.select("*").from_(t.cast(exp.From, from_))
         else:
             this = (
-                self._parse_table()
+                self._parse_table(consume_pipe=True)
                 if table
                 else self._parse_select(nested=True, parse_set_operation=False)
             )
@@ -3173,6 +3184,31 @@ class Parser(metaclass=_Parser):
         table: bool = False,
         parse_subquery_alias: bool = True,
         parse_set_operation: bool = True,
+        consume_pipe: bool = True,
+    ) -> t.Optional[exp.Expression]:
+        query = self._parse_select_query(
+            nested=nested,
+            table=table,
+            parse_subquery_alias=parse_subquery_alias,
+            parse_set_operation=parse_set_operation,
+        )
+
+        if (
+            consume_pipe
+            and self._match(TokenType.PIPE_GT, advance=False)
+            and isinstance(query, exp.Query)
+        ):
+            query = self._parse_pipe_syntax_query(query)
+            query = query.subquery(copy=False) if query and table else query
+
+        return query
+
+    def _parse_select_query(
+        self,
+        nested: bool = False,
+        table: bool = False,
+        parse_subquery_alias: bool = True,
+        parse_set_operation: bool = True,
     ) -> t.Optional[exp.Expression]:
         cte = self._parse_with()
 
@@ -3192,7 +3228,11 @@ class Parser(metaclass=_Parser):
             return this
 
         # duckdb supports leading with FROM x
-        from_ = self._parse_from() if self._match(TokenType.FROM, advance=False) else None
+        from_ = (
+            self._parse_from(consume_pipe=True)
+            if self._match(TokenType.FROM, advance=False)
+            else None
+        )
 
         if self._match(TokenType.SELECT):
             comments = self._prev_comments
@@ -3260,8 +3300,6 @@ class Parser(metaclass=_Parser):
             this = self._parse_derived_table_values()
         elif from_:
             this = exp.select("*").from_(from_.this, copy=False)
-            if self._match(TokenType.PIPE_GT, advance=False):
-                return self._parse_pipe_syntax_query(this)
         elif self._match(TokenType.SUMMARIZE):
             table = self._match(TokenType.TABLE)
             this = self._parse_select() or self._parse_string() or self._parse_table()
@@ -3521,13 +3559,18 @@ class Parser(metaclass=_Parser):
         )
 
     def _parse_from(
-        self, joins: bool = False, skip_from_token: bool = False
+        self,
+        joins: bool = False,
+        skip_from_token: bool = False,
+        consume_pipe: bool = False,
     ) -> t.Optional[exp.From]:
         if not skip_from_token and not self._match(TokenType.FROM):
             return None
 
         return self.expression(
-            exp.From, comments=self._prev_comments, this=self._parse_table(joins=joins)
+            exp.From,
+            comments=self._prev_comments,
+            this=self._parse_table(joins=joins, consume_pipe=consume_pipe),
         )
 
     def _parse_match_recognize_measure(self) -> exp.MatchRecognizeMeasure:
@@ -3702,9 +3745,12 @@ class Parser(metaclass=_Parser):
     ) -> t.Optional[exp.Join]:
         if self._match(TokenType.COMMA):
             table = self._try_parse(self._parse_table)
-            if table:
-                return self.expression(exp.Join, this=table)
-            return None
+            cross_join = self.expression(exp.Join, this=table) if table else None
+
+            if cross_join and self.JOINS_HAVE_EQUAL_PRECEDENCE:
+                cross_join.set("kind", "CROSS")
+
+            return cross_join
 
         index = self._index
         method, side, kind = self._parse_join_parts()
@@ -3953,6 +3999,7 @@ class Parser(metaclass=_Parser):
         parse_bracket: bool = False,
         is_db_reference: bool = False,
         parse_partition: bool = False,
+        consume_pipe: bool = False,
     ) -> t.Optional[exp.Expression]:
         lateral = self._parse_lateral()
         if lateral:
@@ -3966,7 +4013,7 @@ class Parser(metaclass=_Parser):
         if values:
             return values
 
-        subquery = self._parse_select(table=True)
+        subquery = self._parse_select(table=True, consume_pipe=consume_pipe)
         if subquery:
             if not subquery.args.get("pivots"):
                 subquery.set("pivots", self._parse_pivots())
@@ -4708,7 +4755,9 @@ class Parser(metaclass=_Parser):
 
         return locks
 
-    def parse_set_operation(self, this: t.Optional[exp.Expression]) -> t.Optional[exp.Expression]:
+    def parse_set_operation(
+        self, this: t.Optional[exp.Expression], consume_pipe: bool = False
+    ) -> t.Optional[exp.Expression]:
         start = self._index
         _, side_token, kind_token = self._parse_join_parts()
 
@@ -4751,7 +4800,9 @@ class Parser(metaclass=_Parser):
         if by_name and self._match_texts(("ON", "BY")):
             on_column_list = self._parse_wrapped_csv(self._parse_column)
 
-        expression = self._parse_select(nested=True, parse_set_operation=False)
+        expression = self._parse_select(
+            nested=True, parse_set_operation=False, consume_pipe=consume_pipe
+        )
 
         return self.expression(
             operation,
@@ -5082,12 +5133,20 @@ class Parser(metaclass=_Parser):
             this = self._parse_primary()
 
             if isinstance(this, exp.Literal):
+                literal = this.name
                 this = self._parse_column_ops(this)
 
                 parser = self.TYPE_LITERAL_PARSERS.get(data_type.this)
                 if parser:
                     return parser(self, this, data_type)
 
+                if (
+                    self.ZONE_AWARE_TIMESTAMP_CONSTRUCTOR
+                    and data_type.is_type(exp.DataType.Type.TIMESTAMP)
+                    and TIME_ZONE_RE.search(literal)
+                ):
+                    data_type = exp.DataType.build("TIMESTAMPTZ")
+
                 return self.expression(exp.Cast, this=this, to=data_type)
 
             # The expressions arg gets set by the parser when we have something like DECIMAL(38, 0)
@@ -8361,34 +8420,14 @@ class Parser(metaclass=_Parser):
 
         return new_select.with_(new_cte, as_=query, copy=False)
 
-    def _build_pipe_ctes(
-        self,
-        query: exp.Select,
-        expressions: t.List[exp.Expression],
-        alias_cte: t.Optional[exp.TableAlias] = None,
-    ) -> exp.Select:
-        select = query.selects[0].assert_is(exp.Star)
-        if select.args.get("except") or select.args.get("replace"):
-            query = self._build_pipe_cte(
-                query=query.select(
-                    *[expr for expr in expressions if not expr.is_star and expr.args.get("alias")],
-                    copy=False,
-                ),
-                expressions=[
-                    projection.args.get("alias", projection) for projection in expressions
-                ],
-            )
-        else:
-            query.select(*expressions, append=False, copy=False)
-
-        return self._build_pipe_cte(query=query, expressions=[exp.Star()], alias_cte=alias_cte)
-
     def _parse_pipe_syntax_select(self, query: exp.Select) -> exp.Select:
-        select = self._parse_select()
+        select = self._parse_select(consume_pipe=False)
         if not select:
             return query
 
-        return self._build_pipe_ctes(query=query, expressions=select.expressions)
+        return self._build_pipe_cte(
+            query=query.select(*select.expressions, append=False), expressions=[exp.Star()]
+        )
 
     def _parse_pipe_syntax_limit(self, query: exp.Select) -> exp.Select:
         limit = self._parse_limit()
@@ -8437,7 +8476,7 @@ class Parser(metaclass=_Parser):
                 copy=False,
             )
         else:
-            query.select(*aggregates_or_groups, copy=False)
+            query.select(*aggregates_or_groups, append=False, copy=False)
 
         if orders:
             return query.order_by(*orders, append=False, copy=False)
@@ -8453,11 +8492,9 @@ class Parser(metaclass=_Parser):
         ):
             query = self._parse_pipe_syntax_aggregate_group_order_by(query)
 
-        return self._build_pipe_ctes(
-            query=query, expressions=[expr for expr in query.selects if not expr.is_star]
-        )
+        return self._build_pipe_cte(query=query, expressions=[exp.Star()])
 
-    def _parse_pipe_syntax_set_operator(self, query: exp.Query) -> t.Optional[exp.Select]:
+    def _parse_pipe_syntax_set_operator(self, query: exp.Query) -> t.Optional[exp.Query]:
         first_setop = self.parse_set_operation(this=query)
         if not first_setop:
             return None
@@ -8488,12 +8525,15 @@ class Parser(metaclass=_Parser):
 
         return self._build_pipe_cte(query=query, expressions=[exp.Star()])
 
-    def _parse_pipe_syntax_join(self, query: exp.Select) -> t.Optional[exp.Select]:
+    def _parse_pipe_syntax_join(self, query: exp.Query) -> t.Optional[exp.Query]:
         join = self._parse_join()
         if not join:
             return None
 
-        return query.join(join, copy=False)
+        if isinstance(query, exp.Select):
+            return query.join(join, copy=False)
+
+        return query
 
     def _parse_pipe_syntax_pivot(self, query: exp.Select) -> exp.Select:
         pivots = self._parse_pivots()
@@ -8504,37 +8544,12 @@ class Parser(metaclass=_Parser):
         if from_:
             from_.this.set("pivots", pivots)
 
-        return self._build_pipe_ctes(query=query, expressions=[exp.Star()])
+        return self._build_pipe_cte(query=query, expressions=[exp.Star()])
 
     def _parse_pipe_syntax_extend(self, query: exp.Select) -> exp.Select:
         self._match_text_seq("EXTEND")
-        return self._build_pipe_ctes(
-            query=query,
-            expressions=[query.selects[0].assert_is(exp.Star), *self._parse_expressions()],
-        )
-
-    def _parse_pipe_syntax_drop(self, query: exp.Select) -> exp.Select:
-        self._match_text_seq("DROP")
-        dropped_columns = self._parse_csv(self._parse_assignment)
-
-        select = query.selects[0].assert_is(exp.Star)
-        except_ = select.args.get("except") or []
-        select.set("except", [*except_, *dropped_columns])
-
-        return query
-
-    def _parse_pipe_syntax_set(self, query: exp.Select) -> exp.Select:
-        self._match_text_seq("SET")
-        replaced_columns = [
-            self.expression(exp.Alias, this=expr.expression, alias=expr.this)
-            for expr in self._parse_csv(self._parse_assignment)
-        ]
-
-        select = query.selects[0].assert_is(exp.Star)
-        replace_ = select.args.get("replace") or []
-        select.set("replace", [*replace_, *replaced_columns])
-
-        return query
+        query.select(*[exp.Star(), *self._parse_expressions()], append=False, copy=False)
+        return self._build_pipe_cte(query=query, expressions=[exp.Star()])
 
     def _parse_pipe_syntax_tablesample(self, query: exp.Select) -> exp.Select:
         sample = self._parse_table_sample()
@@ -8547,7 +8562,13 @@ class Parser(metaclass=_Parser):
 
         return query
 
-    def _parse_pipe_syntax_query(self, query: exp.Select) -> t.Optional[exp.Select]:
+    def _parse_pipe_syntax_query(self, query: exp.Query) -> t.Optional[exp.Query]:
+        if isinstance(query, exp.Subquery):
+            query = exp.select("*").from_(query, copy=False)
+
+        if not query.args.get("from"):
+            query = exp.select("*").from_(query.subquery(copy=False), copy=False)
+
         while self._match(TokenType.PIPE_GT):
             start = self._curr
             parser = self.PIPE_SYNTAX_TRANSFORM_PARSERS.get(self._curr.text.upper())

{sqlglot-26.29.0.dist-info → sqlglot-26.30.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sqlglot
-Version: 26.29.0
+Version: 26.30.0
 Summary: An easily customizable SQL parser and transpiler
 Author-email: Toby Mao <toby.mao@gmail.com>
 License: MIT License

{sqlglot-26.29.0.dist-info → sqlglot-26.30.0.dist-info}/RECORD

@@ -1,15 +1,15 @@
 sqlglot/__init__.py,sha256=za08rtdPh2v7dOpGdNomttlIVGgTrKja7rPd6sQwaTg,5391
 sqlglot/__main__.py,sha256=022c173KqxsiABWTEpUIq_tJUxuNiW7a7ABsxBXqvu8,2069
 sqlglot/_typing.py,sha256=-1HPyr3w5COlSJWqlgt8jhFk2dyMvBuvVBqIX1wyVCM,642
-sqlglot/_version.py,sha256=gOnetX1YzVEd7bBCS3U4KJPt8DHhhNA_iqdIiN8DYk4,515
+sqlglot/_version.py,sha256=FTiVUaTaSWoKVYxiizmUH00aN8nwszEzKZ3Dh2gUm7s,515
 sqlglot/diff.py,sha256=PtOllQMQa1Sw1-V2Y8eypmDqGujXYPaTOp_WLsWkAWk,17314
 sqlglot/errors.py,sha256=QNKMr-pzLUDR-tuMmn_GK6iMHUIVdb_YSJ_BhGEvuso,2126
-sqlglot/expressions.py,sha256=r3WkNufDInSqIoMasryY4W_XUV7DyIFU2G29jglFPqQ,243249
+sqlglot/expressions.py,sha256=QTf40Yu04Ar6en5_Ncv0bpER5PRlNYtB7S7Ocr2vScw,243330
 sqlglot/generator.py,sha256=E1LjyN49nX9XfK-hysHWvpw7-qtws4xeb85sZi5x3M0,213345
 sqlglot/helper.py,sha256=9nZjFVRBtMKFC3EdzpDQ6jkazFO19po6BF8xHiNGZIo,15111
 sqlglot/jsonpath.py,sha256=dKdI3PNINNGimmSse2IIv-GbPN_3lXncXh_70QH7Lss,7664
 sqlglot/lineage.py,sha256=kXBDSErmZZluZx_kkrMj4MPEOAbkvcbX1tbOW7Bpl-U,15303
-sqlglot/parser.py,sha256=IXOPic_GfVXDaNRna9JbxmG-l2FjxZTIlV0wtWvWnqM,323926
+sqlglot/parser.py,sha256=xWm01SCq3tSHr7WIVz-h2taaf_JW5JvADsNufE8OAEw,324529
 sqlglot/planner.py,sha256=ql7Li-bWJRcyXzNaZy_n6bQ6B2ZfunEIB8Ztv2xaxq4,14634
 sqlglot/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sqlglot/schema.py,sha256=13H2qKQs27EKdTpDLOvcNnSTDAUbYNKjWtJs4aQCSOA,20509
@@ -18,30 +18,31 @@ sqlglot/time.py,sha256=Q62gv6kL40OiRBF6BMESxKJcMVn7ZLNw7sv8H34z5FI,18400
 sqlglot/tokens.py,sha256=R0B8GQSbQ9GoDc0NlaT5Tc8RjgEOx2IYIkYU5rY8Rg8,48742
 sqlglot/transforms.py,sha256=3jpbHeVTLK9hmQi5f3_vmK-5jZB32_ittCkO7poxCs4,40631
 sqlglot/trie.py,sha256=v27uXMrHfqrXlJ6GmeTSMovsB_3o0ctnlKhdNt7W6fI,2245
-sqlglot/dialects/__init__.py,sha256=aZTLpe2SwgWqiVrRabmfV8TVLPVHFydGwb_zhcVhRss,3499
+sqlglot/dialects/__init__.py,sha256=Rcmnv_D8xjCrEPObi4R2_cs3upbfc5OrDKMIJhQTt4k,3513
 sqlglot/dialects/athena.py,sha256=gPE9ybRcbd6dVa1mrTFB_eVjsjQG36hErq5EpHyQmXo,6344
-sqlglot/dialects/bigquery.py,sha256=PIRhlNIj6I5iXPxR2_9q1OWXvy4ovVB_ae5qe8SWV80,52713
-sqlglot/dialects/clickhouse.py,sha256=0ahX0zjIwN9-RzfNyITBHs9PsgQXjL0uMRlRgYz9crI,56520
+sqlglot/dialects/bigquery.py,sha256=Dw_ZOCv_rCDiUqMBJbmkb6b_R2t9ZemiRmvqu9YLBmY,52756
+sqlglot/dialects/clickhouse.py,sha256=Dc0aXwEgN8b6coXKM6P8zh3IsyrXjBajNGB-cVhnu1Y,56603
 sqlglot/dialects/databricks.py,sha256=8PoaiP8PfiBjpheRiua-rO_HzX2TRUXqc3DnlQ8zYrg,4481
-sqlglot/dialects/dialect.py,sha256=uiRHCJ2pjIea3EnRXhizNni1o-d31X02CRBuvXXne7U,68529
+sqlglot/dialects/dialect.py,sha256=-u8403azEMX3F9KrLQnv7xOU6IaHpxL4pJH733oQlqs,68747
 sqlglot/dialects/doris.py,sha256=eC7Ct-iz7p4Usz659NkelUFhm-GmVolIZy5uaBvgjaA,14397
 sqlglot/dialects/drill.py,sha256=FOh7_KjPx_77pv0DiHKZog0CcmzqeF9_PEmGnJ1ESSM,5825
 sqlglot/dialects/druid.py,sha256=kh3snZtneehNOWqs3XcPjsrhNaRbkCQ8E4hHbWJ1fHM,690
-sqlglot/dialects/duckdb.py,sha256=rARz845jDTzx8WUncAYHZeoBcVi7WvIJlGbjnNHaxZM,47965
+sqlglot/dialects/duckdb.py,sha256=oGCgK0KjwJcCKy-YOZeiQnEo4v7Zc1r5AK0tCXO2VIc,48005
 sqlglot/dialects/dune.py,sha256=gALut-fFfN2qMsr8LvZ1NQK3F3W9z2f4PwMvTMXVVVg,375
-sqlglot/dialects/hive.py,sha256=PO6DLT1kHL-U2kFfV1CsNgQFT7A32LuGN71gnTXEOfY,31728
+sqlglot/dialects/fabric.py,sha256=RfRvQq7AVcr7yT30rqsTk-QILmhTJHECXZXMOotmL6I,4104
+sqlglot/dialects/hive.py,sha256=yKCsVN4R8pIB2Lmx1YGiSR9b8Me3li6rsGuZrKjHTo4,31771
 sqlglot/dialects/materialize.py,sha256=_DPLPt8YrdQIIXNrGJw1IMcGOoAEJ9NO9X9pDfy4hxs,3494
 sqlglot/dialects/mysql.py,sha256=prZecn3zeoifZX7l54UuLG64ar7I-or_z9lF-rT8bds,49233
-sqlglot/dialects/oracle.py,sha256=llxu2LzndrsGyceTod-Leh03vuPWEUKzVHB5gQY-tY8,15313
+sqlglot/dialects/oracle.py,sha256=o6On1cYWFt6TpQYKuzo4kCz5vKb8jQr8WSwc619h3Lg,15967
 sqlglot/dialects/postgres.py,sha256=KUyMoLkm1_sZKUbdjn6bjXx9xz7sbEMKa-fl5Mzfrsk,31025
-sqlglot/dialects/presto.py,sha256=ltKbQ44efeq1HM0T8Qq0rsBSx6B6bF9RoKtUBVeoz70,33155
-sqlglot/dialects/prql.py,sha256=OF2LfDb4uzKIF7kpCfpL5G7VP1pnzLbjfW5QFUnuPvo,7803
-sqlglot/dialects/redshift.py,sha256=H8H8lGizHIAd4qLoPeFchyiGZKO1I8U_B058woukuGw,15366
+sqlglot/dialects/presto.py,sha256=xsbYSc_1-z-jSOsG85z9Pw7pd_V_BX0Dila7KsMsS04,33203
+sqlglot/dialects/prql.py,sha256=fwN-SPEGx-drwf1K0U2MByN-PkW3C_rOgQ3xeJeychg,7908
+sqlglot/dialects/redshift.py,sha256=UwfntKCfPpX63G6ow4vjadFpfmfaKrmFOGLoOuWN8Yg,15406
 sqlglot/dialects/risingwave.py,sha256=hwEOPjMw0ZM_3fjQcBUE00oy6I8V6mzYOOYmcwwS8mw,2898
-sqlglot/dialects/snowflake.py,sha256=dP5o1sH0q5UDMxPoI5vYp1_2FQyBU7VbeYdxF1HVyEs,63398
-sqlglot/dialects/spark.py,sha256=fbmiTKAQiKqG9yE_HAxYGgQiOjdxB9tJyjOtgdqF100,7645
+sqlglot/dialects/snowflake.py,sha256=kpoWQ_w3SJyb605QWSvr-BxBR3pP9tmlDbT4ix8p484,63438
+sqlglot/dialects/spark.py,sha256=bOUSXUoWtLfWaQ9fIjWaw4zLBJY6N7vxajdMbAxLdOk,8307
 sqlglot/dialects/spark2.py,sha256=8er7nHDm5Wc57m9AOxKN0sd_DVzbhAL44H_udlFh9O8,14258
-sqlglot/dialects/sqlite.py,sha256=UzJwIdY1PsLArMxNt5lKvk8COHvXeo4FoqW41LqVmM8,12440
+sqlglot/dialects/sqlite.py,sha256=fwqmopeuoupD_2dh2q6rT3UFxWtFHkskZ1OXAYnPT9Q,12483
 sqlglot/dialects/starrocks.py,sha256=fHNgvq5Nz7dI4QUWCTOO5VDOYjasBxRRlcg9TbY0UZE,11235
 sqlglot/dialects/tableau.py,sha256=oIawDzUITxGCWaEMB8OaNMPWhbC3U-2y09pYPm4eazc,2190
 sqlglot/dialects/teradata.py,sha256=xWa-9kSTsT-eM1NePi_oIM1dPHmXW89GLU5Uda3_6Ao,14036
@@ -72,8 +73,8 @@ sqlglot/optimizer/qualify_tables.py,sha256=5f5enBAh-bpNB9ewF97W9fx9h1TGXj1Ih5fnc
 sqlglot/optimizer/scope.py,sha256=r-2PaO7-woaIWaWrKC88J9eTgdQardNYQ1rIXXaPr1w,30501
 sqlglot/optimizer/simplify.py,sha256=S0Blqg5Mq2KRRWhWz-Eivch9sBjBhg9fRJA6EdBzj2g,50704
 sqlglot/optimizer/unnest_subqueries.py,sha256=kzWUVDlxs8z9nmRx-8U-pHXPtVZhEIwkKqmKhr2QLvc,10908
-sqlglot-26.29.0.dist-info/licenses/LICENSE,sha256=AI3__mHZfOtzY3EluR_pIYBm3_pE7TbVx7qaHxoZ114,1065
-sqlglot-26.29.0.dist-info/METADATA,sha256=rc1ouFaDp1lgiQ2W3jRFM2VNj7RUrf2drwij1_rajpg,20732
-sqlglot-26.29.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-sqlglot-26.29.0.dist-info/top_level.txt,sha256=5kRskCGA_gVADF9rSfSzPdLHXqvfMusDYeHePfNY2nQ,8
-sqlglot-26.29.0.dist-info/RECORD,,
+sqlglot-26.30.0.dist-info/licenses/LICENSE,sha256=AI3__mHZfOtzY3EluR_pIYBm3_pE7TbVx7qaHxoZ114,1065
+sqlglot-26.30.0.dist-info/METADATA,sha256=rIvq32wg6apWdTgqTkYe5mYgGj5XTwMQ8rvqjoTQruI,20732
+sqlglot-26.30.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+sqlglot-26.30.0.dist-info/top_level.txt,sha256=5kRskCGA_gVADF9rSfSzPdLHXqvfMusDYeHePfNY2nQ,8
+sqlglot-26.30.0.dist-info/RECORD,,