sqlglot 27.10.0__py3-none-any.whl → 27.11.0__py3-none-any.whl

sqlglot/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '27.10.0'
-__version_tuple__ = version_tuple = (27, 10, 0)
+__version__ = version = '27.11.0'
+__version_tuple__ = version_tuple = (27, 11, 0)
 
 __commit_id__ = commit_id = None

sqlglot/dialects/bigquery.py

@@ -4,6 +4,9 @@ import logging
 import re
 import typing as t
 
+
+from sqlglot.optimizer.annotate_types import TypeAnnotator
+
 from sqlglot import exp, generator, jsonpath, parser, tokens, transforms
 from sqlglot._typing import E
 from sqlglot.dialects.dialect import (
@@ -172,6 +175,18 @@ def _build_to_hex(args: t.List) -> exp.Hex | exp.MD5:
     return exp.MD5(this=arg.this) if isinstance(arg, exp.MD5Digest) else exp.LowerHex(this=arg)
 
 
+def _build_json_strip_nulls(args: t.List) -> exp.JSONStripNulls:
+    expression = exp.JSONStripNulls(this=seq_get(args, 0))
+
+    for arg in args[1:]:
+        if isinstance(arg, exp.Kwarg):
+            expression.set(arg.this.name.lower(), arg)
+        else:
+            expression.set("expression", arg)
+
+    return expression
+
+
 def _array_contains_sql(self: BigQuery.Generator, expression: exp.ArrayContains) -> str:
     return self.sql(
         exp.Exists(
@@ -295,6 +310,24 @@ def _annotate_math_functions(self: TypeAnnotator, expression: E) -> E:
     return expression
 
 
+def _annotate_perncentile_cont(
+    self: TypeAnnotator, expression: exp.PercentileCont
+) -> exp.PercentileCont:
+    """
+    +------------+-----------+------------+---------+
+    | INPUT      | NUMERIC   | BIGNUMERIC | FLOAT64 |
+    +------------+-----------+------------+---------+
+    | NUMERIC    | NUMERIC   | BIGNUMERIC | FLOAT64 |
+    | BIGNUMERIC | BIGNUMERIC| BIGNUMERIC | FLOAT64 |
+    | FLOAT64    | FLOAT64   | FLOAT64    | FLOAT64 |
+    +------------+-----------+------------+---------+
+    """
+    self._annotate_args(expression)
+
+    self._set_type(expression, self._maybe_coerce(expression.this.type, expression.expression.type))
+    return expression
+
+
 def _annotate_by_args_approx_top(self: TypeAnnotator, expression: exp.ApproxTopK) -> exp.ApproxTopK:
     self._annotate_args(expression)
 
@@ -453,6 +486,13 @@ class BigQuery(Dialect):
     # All set operations require either a DISTINCT or ALL specifier
     SET_OP_DISTINCT_BY_DEFAULT = dict.fromkeys((exp.Except, exp.Intersect, exp.Union), None)
 
+    # https://cloud.google.com/bigquery/docs/reference/standard-sql/navigation_functions#percentile_cont
+    COERCES_TO = {
+        **TypeAnnotator.COERCES_TO,
+        exp.DataType.Type.BIGDECIMAL: {exp.DataType.Type.DOUBLE},
+    }
+    COERCES_TO[exp.DataType.Type.DECIMAL] |= {exp.DataType.Type.BIGDECIMAL}
+
     # BigQuery maps Type.TIMESTAMP to DATETIME, so we need to amend the inferred types
     TYPE_TO_EXPRESSIONS = {
         **Dialect.TYPE_TO_EXPRESSIONS,
@@ -511,37 +551,68 @@ class BigQuery(Dialect):
         exp.Corr: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.DOUBLE),
         exp.CovarPop: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.DOUBLE),
         exp.CovarSamp: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.DOUBLE),
+        exp.CumeDist: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.DOUBLE),
         exp.DateFromUnixDate: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.DATE),
         exp.DateTrunc: lambda self, e: self._annotate_by_args(e, "this"),
+        exp.DenseRank: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.BIGINT),
         exp.FarmFingerprint: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.BIGINT),
+        exp.FirstValue: lambda self, e: self._annotate_by_args(e, "this"),
         exp.Unhex: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.BINARY),
         exp.Float64: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.DOUBLE),
+        exp.Format: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.VARCHAR),
         exp.GenerateTimestampArray: lambda self, e: self._annotate_with_type(
             e, exp.DataType.build("ARRAY<TIMESTAMP>", dialect="bigquery")
         ),
         exp.Grouping: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.BIGINT),
+        exp.IgnoreNulls: lambda self, e: self._annotate_by_args(e, "this"),
         exp.JSONArray: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.JSON),
+        exp.JSONArrayAppend: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.JSON),
+        exp.JSONArrayInsert: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.JSON),
         exp.JSONBool: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.BOOLEAN),
         exp.JSONExtractScalar: lambda self, e: self._annotate_with_type(
             e, exp.DataType.Type.VARCHAR
         ),
-        exp.JSONValueArray: lambda self, e: self._annotate_with_type(
-            e, exp.DataType.build("ARRAY<VARCHAR>")
+        exp.JSONExtract: lambda self, e: self._annotate_by_args(e, "this"),
+        exp.JSONExtractArray: lambda self, e: self._annotate_by_args(e, "this", array=True),
+        exp.JSONFormat: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.VARCHAR),
+        exp.JSONKeysAtDepth: lambda self, e: self._annotate_with_type(
+            e, exp.DataType.build("ARRAY<VARCHAR>", dialect="bigquery")
         ),
+        exp.JSONObject: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.JSON),
+        exp.JSONRemove: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.JSON),
+        exp.JSONSet: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.JSON),
+        exp.JSONStripNulls: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.JSON),
         exp.JSONType: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.VARCHAR),
+        exp.JSONValueArray: lambda self, e: self._annotate_with_type(
+            e, exp.DataType.build("ARRAY<VARCHAR>", dialect="bigquery")
+        ),
         exp.Lag: lambda self, e: self._annotate_by_args(e, "this", "default"),
+        exp.Lead: lambda self, e: self._annotate_by_args(e, "this"),
         exp.LowerHex: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.VARCHAR),
+        exp.LaxBool: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.BOOLEAN),
+        exp.LaxFloat64: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.DOUBLE),
+        exp.LaxInt64: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.BIGINT),
+        exp.LaxString: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.VARCHAR),
         exp.MD5Digest: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.BINARY),
         exp.Normalize: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.VARCHAR),
+        exp.NthValue: lambda self, e: self._annotate_by_args(e, "this"),
+        exp.Ntile: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.BIGINT),
         exp.ParseTime: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.TIME),
         exp.ParseDatetime: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.DATETIME),
         exp.ParseBignumeric: lambda self, e: self._annotate_with_type(
             e, exp.DataType.Type.BIGDECIMAL
         ),
         exp.ParseNumeric: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.DECIMAL),
+        exp.PercentileCont: lambda self, e: _annotate_perncentile_cont(self, e),
+        exp.PercentileDisc: lambda self, e: self._annotate_by_args(e, "this"),
+        exp.PercentRank: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.DOUBLE),
+        exp.Rank: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.BIGINT),
         exp.RegexpExtractAll: lambda self, e: self._annotate_by_args(e, "this", array=True),
+        exp.RegexpInstr: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.BIGINT),
         exp.Replace: lambda self, e: self._annotate_by_args(e, "this"),
+        exp.RespectNulls: lambda self, e: self._annotate_by_args(e, "this"),
         exp.Reverse: lambda self, e: self._annotate_by_args(e, "this"),
+        exp.RowNumber: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.BIGINT),
         exp.SafeConvertBytesToString: lambda self, e: self._annotate_with_type(
             e, exp.DataType.Type.VARCHAR
         ),
@@ -682,8 +753,11 @@ class BigQuery(Dialect):
             "GENERATE_ARRAY": exp.GenerateSeries.from_arg_list,
             "JSON_EXTRACT_SCALAR": _build_extract_json_with_default_path(exp.JSONExtractScalar),
             "JSON_EXTRACT_ARRAY": _build_extract_json_with_default_path(exp.JSONExtractArray),
+            "JSON_EXTRACT_STRING_ARRAY": _build_extract_json_with_default_path(exp.JSONValueArray),
+            "JSON_KEYS": exp.JSONKeysAtDepth.from_arg_list,
             "JSON_QUERY": parser.build_extract_json_with_path(exp.JSONExtract),
             "JSON_QUERY_ARRAY": _build_extract_json_with_default_path(exp.JSONExtractArray),
+            "JSON_STRIP_NULLS": _build_json_strip_nulls,
             "JSON_VALUE": _build_extract_json_with_default_path(exp.JSONExtractScalar),
             "JSON_VALUE_ARRAY": _build_extract_json_with_default_path(exp.JSONValueArray),
             "LENGTH": lambda args: exp.Length(this=seq_get(args, 0), binary=True),
@@ -798,9 +872,13 @@ class BigQuery(Dialect):
             "SAFE_ORDINAL": (1, True),
         }
 
-        def _parse_for_in(self) -> exp.ForIn:
+        def _parse_for_in(self) -> t.Union[exp.ForIn, exp.Command]:
+            index = self._index
             this = self._parse_range()
             self._match_text_seq("DO")
+            if self._match(TokenType.COMMAND):
+                self._retreat(index)
+                return self._parse_as_command(self._prev)
             return self.expression(exp.ForIn, this=this, expression=self._parse_statement())
 
         def _parse_table_part(self, schema: bool = False) -> t.Optional[exp.Expression]:
@@ -1197,6 +1275,8 @@ class BigQuery(Dialect):
             exp.JSONExtractArray: _json_extract_sql,
             exp.JSONExtractScalar: _json_extract_sql,
             exp.JSONFormat: rename_func("TO_JSON_STRING"),
+            exp.JSONKeysAtDepth: rename_func("JSON_KEYS"),
+            exp.JSONValueArray: rename_func("JSON_VALUE_ARRAY"),
             exp.Levenshtein: _levenshtein_sql,
             exp.Max: max_or_greatest,
             exp.MD5: lambda self, e: self.func("TO_HEX", self.func("MD5", e.this)),

sqlglot/dialects/dremio.py

@@ -74,6 +74,27 @@ def build_date_delta_with_cast_interval(
     return _builder
 
 
+def datetype_handler(args: t.List[exp.Expression], dialect: DialectType) -> exp.Expression:
+    year, month, day = args
+
+    if all(isinstance(arg, exp.Literal) and arg.is_int for arg in (year, month, day)):
+        date_str = f"{int(year.this):04d}-{int(month.this):02d}-{int(day.this):02d}"
+        return exp.Date(this=exp.Literal.string(date_str))
+
+    return exp.Cast(
+        this=exp.Concat(
+            expressions=[
+                year,
+                exp.Literal.string("-"),
+                month,
+                exp.Literal.string("-"),
+                day,
+            ]
+        ),
+        to=exp.DataType.build("DATE"),
+    )
+
+
 class Dremio(Dialect):
     SUPPORTS_USER_DEFINED_TYPES = False
     CONCAT_COALESCE = True
@@ -145,12 +166,16 @@ class Dremio(Dialect):
 
         FUNCTIONS = {
             **parser.Parser.FUNCTIONS,
-            "TO_CHAR": to_char_is_numeric_handler,
-            "DATE_FORMAT": build_formatted_time(exp.TimeToStr, "dremio"),
-            "TO_DATE": build_formatted_time(exp.TsOrDsToDate, "dremio"),
+            "ARRAY_GENERATE_RANGE": exp.GenerateSeries.from_arg_list,
             "DATE_ADD": build_date_delta_with_cast_interval(exp.DateAdd),
+            "DATE_FORMAT": build_formatted_time(exp.TimeToStr, "dremio"),
             "DATE_SUB": build_date_delta_with_cast_interval(exp.DateSub),
-            "ARRAY_GENERATE_RANGE": exp.GenerateSeries.from_arg_list,
+            "REGEXP_MATCHES": exp.RegexpLike.from_arg_list,
+            "REPEATSTR": exp.Repeat.from_arg_list,
+            "TO_CHAR": to_char_is_numeric_handler,
+            "TO_DATE": build_formatted_time(exp.TsOrDsToDate, "dremio"),
+            "DATE_PART": exp.Extract.from_arg_list,
+            "DATETYPE": datetype_handler,
         }
 
         def _parse_current_date_utc(self) -> exp.Cast:

sqlglot/dialects/singlestore.py

@@ -10,8 +10,11 @@ from sqlglot.dialects.dialect import (
     rename_func,
     bool_xor_sql,
     count_if_to_sum,
+    timestamptrunc_sql,
+    date_add_interval_sql,
+    timestampdiff_sql,
 )
-from sqlglot.dialects.mysql import MySQL
+from sqlglot.dialects.mysql import MySQL, _remove_ts_or_ds_to_date, date_add_sql
 from sqlglot.expressions import DataType
 from sqlglot.generator import unsupported_args
 from sqlglot.helper import seq_get
@@ -55,6 +58,7 @@ class SingleStore(MySQL):
             **MySQL.Tokenizer.KEYWORDS,
             "BSON": TokenType.JSONB,
             "GEOGRAPHYPOINT": TokenType.GEOGRAPHYPOINT,
+            "TIMESTAMP": TokenType.TIMESTAMP,
             ":>": TokenType.COLON_GT,
             "!:>": TokenType.NCOLON_GT,
             "::$": TokenType.DCOLONDOLLAR,
@@ -159,6 +163,11 @@ class SingleStore(MySQL):
                 this=seq_get(args, 0),
                 format=MySQL.format_time(exp.Literal.string("%W")),
             ),
+            "TIMESTAMPDIFF": lambda args: exp.TimestampDiff(
+                this=seq_get(args, 2),
+                expression=seq_get(args, 1),
+                unit=seq_get(args, 0),
+            ),
             "APPROX_COUNT_DISTINCT": exp.Hll.from_arg_list,
             "APPROX_PERCENTILE": lambda args, dialect: exp.ApproxQuantile(
                 this=seq_get(args, 0),
@@ -189,6 +198,7 @@ class SingleStore(MySQL):
         CAST_COLUMN_OPERATORS = {TokenType.COLON_GT, TokenType.NCOLON_GT}
 
         COLUMN_OPERATORS = {
+            **MySQL.Parser.COLUMN_OPERATORS,
             TokenType.COLON_GT: lambda self, this, to: self.expression(
                 exp.Cast,
                 this=this,
@@ -209,6 +219,11 @@ class SingleStore(MySQL):
                 exp.JSONExtractScalar, json_type="DOUBLE"
             )([this, exp.Literal.string(path.name)]),
         }
+        COLUMN_OPERATORS.pop(TokenType.ARROW)
+        COLUMN_OPERATORS.pop(TokenType.DARROW)
+        COLUMN_OPERATORS.pop(TokenType.HASH_ARROW)
+        COLUMN_OPERATORS.pop(TokenType.DHASH_ARROW)
+        COLUMN_OPERATORS.pop(TokenType.PLACEHOLDER)
 
     class Generator(MySQL.Generator):
         SUPPORTED_JSON_PATH_PARTS = {
@@ -277,6 +292,28 @@ class SingleStore(MySQL):
             exp.DateBin: unsupported_args("unit", "zone")(
                 lambda self, e: self.func("TIME_BUCKET", e.this, e.expression, e.args.get("origin"))
             ),
+            exp.TimeStrToDate: lambda self, e: self.sql(exp.cast(e.this, exp.DataType.Type.DATE)),
+            exp.FromTimeZone: lambda self, e: self.func(
+                "CONVERT_TZ", e.this, e.args.get("zone"), "'UTC'"
+            ),
+            exp.DiToDate: lambda self,
+            e: f"STR_TO_DATE({self.sql(e, 'this')}, {SingleStore.DATEINT_FORMAT})",
+            exp.DateToDi: lambda self,
+            e: f"(DATE_FORMAT({self.sql(e, 'this')}, {SingleStore.DATEINT_FORMAT}) :> INT)",
+            exp.TsOrDiToDi: lambda self,
+            e: f"(DATE_FORMAT({self.sql(e, 'this')}, {SingleStore.DATEINT_FORMAT}) :> INT)",
+            exp.Time: unsupported_args("zone")(lambda self, e: f"{self.sql(e, 'this')} :> TIME"),
+            exp.DatetimeAdd: _remove_ts_or_ds_to_date(date_add_sql("ADD")),
+            exp.DatetimeTrunc: unsupported_args("zone")(timestamptrunc_sql()),
+            exp.DatetimeSub: date_add_interval_sql("DATE", "SUB"),
+            exp.DatetimeDiff: timestampdiff_sql,
+            exp.DateTrunc: unsupported_args("zone")(timestamptrunc_sql()),
+            exp.DateDiff: unsupported_args("zone")(
+                lambda self, e: timestampdiff_sql(self, e)
+                if e.unit is not None
+                else self.func("DATEDIFF", e.this, e.expression)
+            ),
+            exp.TimestampTrunc: unsupported_args("zone")(timestamptrunc_sql()),
             exp.JSONExtract: unsupported_args(
                 "only_json_types",
                 "expressions",
@@ -353,6 +390,94 @@ class SingleStore(MySQL):
         }
         TRANSFORMS.pop(exp.JSONExtractScalar)
 
+        UNSUPPORTED_TYPES = {
+            exp.DataType.Type.ARRAY,
+            exp.DataType.Type.AGGREGATEFUNCTION,
+            exp.DataType.Type.SIMPLEAGGREGATEFUNCTION,
+            exp.DataType.Type.BIGSERIAL,
+            exp.DataType.Type.BPCHAR,
+            exp.DataType.Type.DATEMULTIRANGE,
+            exp.DataType.Type.DATERANGE,
+            exp.DataType.Type.DYNAMIC,
+            exp.DataType.Type.HLLSKETCH,
+            exp.DataType.Type.HSTORE,
+            exp.DataType.Type.IMAGE,
+            exp.DataType.Type.INET,
+            exp.DataType.Type.INT128,
+            exp.DataType.Type.INT256,
+            exp.DataType.Type.INT4MULTIRANGE,
+            exp.DataType.Type.INT4RANGE,
+            exp.DataType.Type.INT8MULTIRANGE,
+            exp.DataType.Type.INT8RANGE,
+            exp.DataType.Type.INTERVAL,
+            exp.DataType.Type.IPADDRESS,
+            exp.DataType.Type.IPPREFIX,
+            exp.DataType.Type.IPV4,
+            exp.DataType.Type.IPV6,
+            exp.DataType.Type.LIST,
+            exp.DataType.Type.MAP,
+            exp.DataType.Type.LOWCARDINALITY,
+            exp.DataType.Type.MONEY,
+            exp.DataType.Type.MULTILINESTRING,
+            exp.DataType.Type.NAME,
+            exp.DataType.Type.NESTED,
+            exp.DataType.Type.NOTHING,
+            exp.DataType.Type.NULL,
+            exp.DataType.Type.NUMMULTIRANGE,
+            exp.DataType.Type.NUMRANGE,
+            exp.DataType.Type.OBJECT,
+            exp.DataType.Type.RANGE,
+            exp.DataType.Type.ROWVERSION,
+            exp.DataType.Type.SERIAL,
+            exp.DataType.Type.SMALLSERIAL,
+            exp.DataType.Type.SMALLMONEY,
+            exp.DataType.Type.STRUCT,
+            exp.DataType.Type.SUPER,
+            exp.DataType.Type.TIMETZ,
+            exp.DataType.Type.TIMESTAMPNTZ,
+            exp.DataType.Type.TIMESTAMPLTZ,
+            exp.DataType.Type.TIMESTAMPTZ,
+            exp.DataType.Type.TIMESTAMP_NS,
+            exp.DataType.Type.TSMULTIRANGE,
+            exp.DataType.Type.TSRANGE,
+            exp.DataType.Type.TSTZMULTIRANGE,
+            exp.DataType.Type.TSTZRANGE,
+            exp.DataType.Type.UINT128,
+            exp.DataType.Type.UINT256,
+            exp.DataType.Type.UNION,
+            exp.DataType.Type.UNKNOWN,
+            exp.DataType.Type.USERDEFINED,
+            exp.DataType.Type.UUID,
+            exp.DataType.Type.VARIANT,
+            exp.DataType.Type.XML,
+            exp.DataType.Type.TDIGEST,
+        }
+
+        TYPE_MAPPING = {
+            **MySQL.Generator.TYPE_MAPPING,
+            exp.DataType.Type.BIGDECIMAL: "DECIMAL",
+            exp.DataType.Type.BIT: "BOOLEAN",
+            exp.DataType.Type.DATE32: "DATE",
+            exp.DataType.Type.DATETIME64: "DATETIME",
+            exp.DataType.Type.DECIMAL32: "DECIMAL",
+            exp.DataType.Type.DECIMAL64: "DECIMAL",
+            exp.DataType.Type.DECIMAL128: "DECIMAL",
+            exp.DataType.Type.DECIMAL256: "DECIMAL",
+            exp.DataType.Type.ENUM8: "ENUM",
+            exp.DataType.Type.ENUM16: "ENUM",
+            exp.DataType.Type.FIXEDSTRING: "TEXT",
+            exp.DataType.Type.GEOMETRY: "GEOGRAPHY",
+            exp.DataType.Type.POINT: "GEOGRAPHYPOINT",
+            exp.DataType.Type.RING: "GEOGRAPHY",
+            exp.DataType.Type.LINESTRING: "GEOGRAPHY",
+            exp.DataType.Type.POLYGON: "GEOGRAPHY",
+            exp.DataType.Type.MULTIPOLYGON: "GEOGRAPHY",
+            exp.DataType.Type.JSONB: "BSON",
+            exp.DataType.Type.TIMESTAMP: "TIMESTAMP",
+            exp.DataType.Type.TIMESTAMP_S: "TIMESTAMP",
+            exp.DataType.Type.TIMESTAMP_MS: "TIMESTAMP(6)",
+        }
+
         # https://docs.singlestore.com/cloud/reference/sql-reference/restricted-keywords/list-of-restricted-keywords/
         RESERVED_KEYWORDS = {
             "abs",
@@ -1452,3 +1577,32 @@ class SingleStore(MySQL):
                 expression.expression,
                 self.func("TO_JSON", expression.this),
             )
+
+        @unsupported_args("kind", "nested", "values")
+        def datatype_sql(self, expression: exp.DataType) -> str:
+            if expression.is_type(exp.DataType.Type.VARBINARY) and not expression.expressions:
+                # `VARBINARY` must always have a size - if it doesn't, we always generate `BLOB`
+                return "BLOB"
+            if expression.is_type(
+                exp.DataType.Type.DECIMAL32,
+                exp.DataType.Type.DECIMAL64,
+                exp.DataType.Type.DECIMAL128,
+                exp.DataType.Type.DECIMAL256,
+            ):
+                scale = self.expressions(expression, flat=True)
+
+                if expression.is_type(exp.DataType.Type.DECIMAL32):
+                    precision = "9"
+                elif expression.is_type(exp.DataType.Type.DECIMAL64):
+                    precision = "18"
+                elif expression.is_type(exp.DataType.Type.DECIMAL128):
+                    precision = "38"
+                else:
+                    # 65 is a maximum precision supported in SingleStore
+                    precision = "65"
+                if scale is not None:
+                    return f"DECIMAL({precision}, {scale[0]})"
+                else:
+                    return f"DECIMAL({precision})"
+
+            return super().datatype_sql(expression)

sqlglot/dialects/snowflake.py

@@ -552,6 +552,7 @@ class Snowflake(Dialect):
 
         ID_VAR_TOKENS = {
             *parser.Parser.ID_VAR_TOKENS,
+            TokenType.EXCEPT,
             TokenType.MATCH_CONDITION,
         }
 

sqlglot/dialects/spark2.py

@@ -187,6 +187,7 @@ class Spark2(Hive):
             "DAYOFYEAR": lambda args: exp.DayOfYear(this=exp.TsOrDsToDate(this=seq_get(args, 0))),
             "DOUBLE": _build_as_cast("double"),
             "FLOAT": _build_as_cast("float"),
+            "FORMAT_STRING": exp.Format.from_arg_list,
             "FROM_UTC_TIMESTAMP": lambda args, dialect: exp.AtTimeZone(
                 this=exp.cast(
                     seq_get(args, 0) or exp.Var(this=""),
@@ -292,6 +293,7 @@ class Spark2(Hive):
             # (DAY_OF_WEEK(datetime) % 7) + 1 is equivalent to DAYOFWEEK_ISO(datetime)
             exp.DayOfWeekIso: lambda self, e: f"(({self.func('DAYOFWEEK', e.this)} % 7) + 1)",
             exp.DayOfYear: rename_func("DAYOFYEAR"),
+            exp.Format: rename_func("FORMAT_STRING"),
             exp.From: transforms.preprocess([_unalias_pivot]),
             exp.FromTimeZone: lambda self, e: self.func(
                 "TO_UTC_TIMESTAMP", e.this, e.args.get("zone")

sqlglot/dialects/sqlite.py

@@ -156,6 +156,7 @@ class SQLite(Dialect):
         EXCEPT_INTERSECT_SUPPORT_ALL_CLAUSE = False
         SUPPORTS_MEDIAN = False
         JSON_KEY_VALUE_PAIR_SEP = ","
+        PARSE_JSON_NAME: t.Optional[str] = None
 
         SUPPORTED_JSON_PATH_PARTS = {
             exp.JSONPathKey,

sqlglot/expressions.py

@@ -6110,6 +6110,22 @@ class LastDay(Func, TimeUnit):
     arg_types = {"this": True, "unit": False}
 
 
+class LaxBool(Func):
+    pass
+
+
+class LaxFloat64(Func):
+    pass
+
+
+class LaxInt64(Func):
+    pass
+
+
+class LaxString(Func):
+    pass
+
+
 class Extract(Func):
     arg_types = {"this": True, "expression": True}
 
@@ -6203,6 +6219,11 @@ class DecodeCase(Func):
     is_var_len_args = True
 
 
+class DenseRank(AggFunc):
+    arg_types = {"expressions": False}
+    is_var_len_args = True
+
+
 class DiToDate(Func):
     pass
 
@@ -6438,10 +6459,20 @@ class FormatJson(Expression):
     pass
 
 
+class Format(Func):
+    arg_types = {"this": True, "expressions": True}
+    is_var_len_args = True
+
+
 class JSONKeyValue(Expression):
     arg_types = {"this": True, "expression": True}
 
 
+# https://cloud.google.com/bigquery/docs/reference/standard-sql/json_functions#json_keys
+class JSONKeysAtDepth(Func):
+    arg_types = {"this": True, "expression": False, "mode": False}
+
+
 class JSONObject(Func):
     arg_types = {
         "expressions": False,
@@ -6502,6 +6533,23 @@ class JSONSchema(Expression):
     arg_types = {"expressions": True}
 
 
+class JSONSet(Func):
+    arg_types = {"this": True, "expressions": True}
+    is_var_len_args = True
+    _sql_names = ["JSON_SET"]
+
+
+# https://cloud.google.com/bigquery/docs/reference/standard-sql/json_functions#json_strip_nulls
+class JSONStripNulls(Func):
+    arg_types = {
+        "this": True,
+        "expression": False,
+        "include_arrays": False,
+        "remove_empty": False,
+    }
+    _sql_names = ["JSON_STRIP_NULLS"]
+
+
 # https://dev.mysql.com/doc/refman/8.4/en/json-search-functions.html#function_json-value
 class JSONValue(Expression):
     arg_types = {
@@ -6516,6 +6564,12 @@ class JSONValueArray(Func):
     arg_types = {"this": True, "expression": False}
 
 
+class JSONRemove(Func):
+    arg_types = {"this": True, "expressions": True}
+    is_var_len_args = True
+    _sql_names = ["JSON_REMOVE"]
+
+
 # https://docs.oracle.com/en/database/oracle/oracle-database/19/sqlrf/JSON_TABLE.html
 class JSONTable(Func):
     arg_types = {
@@ -6625,12 +6679,24 @@ class JSONFormat(Func):
     _sql_names = ["JSON_FORMAT"]
 
 
+class JSONArrayAppend(Func):
+    arg_types = {"this": True, "expressions": True}
+    is_var_len_args = True
+    _sql_names = ["JSON_ARRAY_APPEND"]
+
+
 # https://dev.mysql.com/doc/refman/8.0/en/json-search-functions.html#operator_member-of
 class JSONArrayContains(Binary, Predicate, Func):
     arg_types = {"this": True, "expression": True, "json_type": False}
     _sql_names = ["JSON_ARRAY_CONTAINS"]
 
 
+class JSONArrayInsert(Func):
+    arg_types = {"this": True, "expressions": True}
+    is_var_len_args = True
+    _sql_names = ["JSON_ARRAY_INSERT"]
+
+
 class ParseBignumeric(Func):
     pass
 
@@ -6796,6 +6862,10 @@ class Nvl2(Func):
     arg_types = {"this": True, "true": True, "false": False}
 
 
+class Ntile(AggFunc):
+    arg_types = {"this": False}
+
+
 class Normalize(Func):
     arg_types = {"this": True, "form": False, "is_casefold": False}
 
@@ -6844,6 +6914,11 @@ class PercentileDisc(AggFunc):
     arg_types = {"this": True, "expression": False}
 
 
+class PercentRank(AggFunc):
+    arg_types = {"expressions": False}
+    is_var_len_args = True
+
+
 class Quantile(AggFunc):
     arg_types = {"this": True, "quantile": True}
 
@@ -6877,6 +6952,11 @@ class RangeN(Func):
     arg_types = {"this": True, "expressions": True, "each": False}
 
 
+class Rank(AggFunc):
+    arg_types = {"expressions": False}
+    is_var_len_args = True
+
+
 class ReadCSV(Func):
     _sql_names = ["READ_CSV"]
     is_var_len_args = True
@@ -6928,6 +7008,18 @@ class RegexpILike(Binary, Func):
     arg_types = {"this": True, "expression": True, "flag": False}
 
 
+class RegexpInstr(Func):
+    arg_types = {
+        "this": True,
+        "expression": True,
+        "position": False,
+        "occurrence": False,
+        "option": False,
+        "parameters": False,
+        "group": False,
+    }
+
+
 # https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.split.html
 # limit is the number of times a pattern is applied
 class RegexpSplit(Func):
@@ -7270,6 +7362,12 @@ class Corr(Binary, AggFunc):
     pass
 
 
+# https://docs.oracle.com/en/database/oracle/oracle-database/19/sqlrf/CUME_DIST.html
+class CumeDist(AggFunc):
+    arg_types = {"expressions": False}
+    is_var_len_args = True
+
+
 class Variance(AggFunc):
     _sql_names = ["VARIANCE", "VARIANCE_SAMP", "VAR_SAMP"]
 

sqlglot/generator.py

@@ -511,6 +511,8 @@ class Generator(metaclass=_Generator):
         exp.DataType.Type.SMALLDATETIME: "TIMESTAMP",
     }
 
+    UNSUPPORTED_TYPES: set[exp.DataType.Type] = set()
+
     TIME_PART_SINGULARS = {
         "MICROSECONDS": "MICROSECOND",
         "SECONDS": "SECOND",
@@ -1406,6 +1408,11 @@ class Generator(metaclass=_Generator):
         interior = self.expressions(expression, flat=True)
 
         type_value = expression.this
+        if type_value in self.UNSUPPORTED_TYPES:
+            self.unsupported(
+                f"Data type {type_value.value} is not supported when targeting {self.dialect.__class__.__name__}"
+            )
+
         if type_value == exp.DataType.Type.USERDEFINED and expression.args.get("kind"):
             type_sql = self.sql(expression, "kind")
         else:
@@ -4660,9 +4667,12 @@ class Generator(metaclass=_Generator):
     def arrayconcat_sql(self, expression: exp.ArrayConcat, name: str = "ARRAY_CONCAT") -> str:
         exprs = expression.expressions
         if not self.ARRAY_CONCAT_IS_VAR_LEN:
-            rhs = reduce(lambda x, y: exp.ArrayConcat(this=x, expressions=[y]), exprs)
+            if len(exprs) == 0:
+                rhs: t.Union[str, exp.Expression] = exp.Array(expressions=[])
+            else:
+                rhs = reduce(lambda x, y: exp.ArrayConcat(this=x, expressions=[y]), exprs)
         else:
-            rhs = self.expressions(expression)
+            rhs = self.expressions(expression)  # type: ignore
 
         return self.func(name, expression.this, rhs or None)
 

sqlglot/tokens.py

@@ -1427,7 +1427,7 @@ class Tokenizer(metaclass=_Tokenizer):
         self._advance(len(start))
         text = self._extract_string(end, raw_string=token_type == TokenType.RAW_STRING)
 
-        if base:
+        if base and text:
             try:
                 int(text, base)
             except Exception:

{sqlglot-27.10.0.dist-info → sqlglot-27.11.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sqlglot
-Version: 27.10.0
+Version: 27.11.0
 Summary: An easily customizable SQL parser and transpiler
 Author-email: Toby Mao <toby.mao@gmail.com>
 License-Expression: MIT
@@ -33,7 +33,7 @@ Requires-Dist: typing_extensions; extra == "dev"
 Requires-Dist: maturin<2.0,>=1.4; extra == "dev"
 Requires-Dist: pyperf; extra == "dev"
 Provides-Extra: rs
-Requires-Dist: sqlglotrs==0.6.1; extra == "rs"
+Requires-Dist: sqlglotrs==0.6.2; extra == "rs"
 Dynamic: license-file
 Dynamic: provides-extra
 

{sqlglot-27.10.0.dist-info → sqlglot-27.11.0.dist-info}/RECORD

@@ -1,11 +1,11 @@
 sqlglot/__init__.py,sha256=za08rtdPh2v7dOpGdNomttlIVGgTrKja7rPd6sQwaTg,5391
 sqlglot/__main__.py,sha256=022c173KqxsiABWTEpUIq_tJUxuNiW7a7ABsxBXqvu8,2069
 sqlglot/_typing.py,sha256=-1HPyr3w5COlSJWqlgt8jhFk2dyMvBuvVBqIX1wyVCM,642
-sqlglot/_version.py,sha256=UQWMArALhjnnjO2LJbcK8eqVDukANsZFTdd9DkZF4Vg,708
+sqlglot/_version.py,sha256=oM65QlZoKN_nkllGdqeZbvnaN1K37Ouzx2i0_B4cs3k,708
 sqlglot/diff.py,sha256=PtOllQMQa1Sw1-V2Y8eypmDqGujXYPaTOp_WLsWkAWk,17314
 sqlglot/errors.py,sha256=QNKMr-pzLUDR-tuMmn_GK6iMHUIVdb_YSJ_BhGEvuso,2126
-sqlglot/expressions.py,sha256=kgMzkI6ypuceCguV7qw8qQY-Q2LmTAnCYa17wh0hjbQ,250479
-sqlglot/generator.py,sha256=kAU58UNnAsbuP0ualoi2n4b61c2cg3C0mJJD7IjOciU,222829
+sqlglot/expressions.py,sha256=u7_1s9-VxVvo4SAqC84nktRr-3lw00OwU-_rmGiFm-c,252520
+sqlglot/generator.py,sha256=69I3fUEnnE_-JPrqf56B3x12VsN99PRlWIC_QAiFo3E,223240
 sqlglot/helper.py,sha256=9nZjFVRBtMKFC3EdzpDQ6jkazFO19po6BF8xHiNGZIo,15111
 sqlglot/jsonpath.py,sha256=SQgaxzaEYBN7At9dkTK4N1Spk6xHxvHL6QtCIP6iM30,7905
 sqlglot/lineage.py,sha256=Qj5ykuDNcATppb9vOjoIKBqRVLbu3OMPiZk9f3iyv40,15312
@@ -15,17 +15,17 @@ sqlglot/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sqlglot/schema.py,sha256=13H2qKQs27EKdTpDLOvcNnSTDAUbYNKjWtJs4aQCSOA,20509
 sqlglot/serde.py,sha256=DQVJ95WrIvhYfe02Ytb4NQug2aMwDCEwpMBW1LKDqzE,2031
 sqlglot/time.py,sha256=Q62gv6kL40OiRBF6BMESxKJcMVn7ZLNw7sv8H34z5FI,18400
-sqlglot/tokens.py,sha256=4U_eej87MjWiqruZrEqvVQGuDuIS7YfR99Kxk1aLu64,48993
+sqlglot/tokens.py,sha256=gRIc8NnZJcLPdXmsjRysoGWKrM8Fse8sLF7b-uHc6Do,49002
 sqlglot/transforms.py,sha256=utNDsCBsA7hPUK3-aby3DDgiY_XVMAKQqeoLm1EyihI,41218
 sqlglot/trie.py,sha256=v27uXMrHfqrXlJ6GmeTSMovsB_3o0ctnlKhdNt7W6fI,2245
 sqlglot/dialects/__init__.py,sha256=e3K2NHrZO7oXfBzEpRsvgWAgJ_UCEyg7SlUCRqvnPj4,3799
 sqlglot/dialects/athena.py,sha256=ofArmayYLev4qZQ15GM8mevG04qqR5WGFb2ZcuYm6x4,10966
-sqlglot/dialects/bigquery.py,sha256=66hGREFUnfora2KRBw6AqZCMc8a2Xk9XbHegRE8rLPI,64753
+sqlglot/dialects/bigquery.py,sha256=fp1uAPhRHOh5yeFtR8NbrpyJFpM-IJ8PsxzTMvSqvnk,69316
 sqlglot/dialects/clickhouse.py,sha256=OuaDWpvVrHCF9N-u3ZmHZUCs7DSKq_aaRt8yOh2CtaY,58301
 sqlglot/dialects/databricks.py,sha256=761qPlGOFHa9V8mdQYNAEw0pv4HUJYMkGEuFsdsLC7s,4714
 sqlglot/dialects/dialect.py,sha256=02W-j8nYJduA78_BMxMTMGXv2i9mcAGAmXBt1YsH0CQ,73055
 sqlglot/dialects/doris.py,sha256=NvDGHIKGJDVp0b4oOnMu1fyAprJPOiC8J6M85V75iuU,25136
-sqlglot/dialects/dremio.py,sha256=o9wqHnUXlEetOuGUWBZLER1whId9U4l1xledme7qGsg,7392
+sqlglot/dialects/dremio.py,sha256=D2YwjqbTjJ8VZ94GQs7GBRCKUiizwggcEaR_drKpnoc,8242
 sqlglot/dialects/drill.py,sha256=FOh7_KjPx_77pv0DiHKZog0CcmzqeF9_PEmGnJ1ESSM,5825
 sqlglot/dialects/druid.py,sha256=kh3snZtneehNOWqs3XcPjsrhNaRbkCQ8E4hHbWJ1fHM,690
 sqlglot/dialects/duckdb.py,sha256=vCIjZV9lszyXt-hNylVyUdHHlD_F9zsYznzcZLaqGDg,52241
@@ -41,11 +41,11 @@ sqlglot/dialects/presto.py,sha256=XVeYr2NP86x5enlRqI7MYR6le85_ucYg_BBRocGN3jM,33
 sqlglot/dialects/prql.py,sha256=fwN-SPEGx-drwf1K0U2MByN-PkW3C_rOgQ3xeJeychg,7908
 sqlglot/dialects/redshift.py,sha256=_sQTom4CGozFDZXW9y6bHQcZ-KiQ7QJjjQqM5rVagSc,15889
 sqlglot/dialects/risingwave.py,sha256=BqWwW1iT_OIVMwfRamaww79snnBwIgCfr22Go-ggO68,3289
-sqlglot/dialects/singlestore.py,sha256=rn3a9Koom9AsS3h7anZfW6AfIEmADvAJ8EuTH9NRG9s,42616
-sqlglot/dialects/snowflake.py,sha256=XPsqYGBjn3dfddF2dcuM7Ur-4sYdthjW7cSPnptWq_s,70542
+sqlglot/dialects/singlestore.py,sha256=YxBHLKOyinFbXSZ720XDzgA7g9KrI5aAnjEl0JBA01w,49592
+sqlglot/dialects/snowflake.py,sha256=QvsWQzhabC6zG7QfrBBVc_Dv6E70-xAwTjMg5ExrPeM,70572
 sqlglot/dialects/spark.py,sha256=5dKMb9cGl0GMreEyFfjClvW1Cwm1JEx3W-hFnxjqW8E,9362
-sqlglot/dialects/spark2.py,sha256=aCwPqLduLRSUSPtbI1VtBjydK6haKgEy3iahmueGRo4,14742
-sqlglot/dialects/sqlite.py,sha256=XIDmiNTswWcrDwlFm8gOODCrJ_rPmXQKkm9U_-YAlVs,13183
+sqlglot/dialects/spark2.py,sha256=qz36FT9k4iuiqboRpyG4VpKGkPR0P2fifmqgZ9gNUEU,14851
+sqlglot/dialects/sqlite.py,sha256=UIQ66shIt2bQoLd7tYG4NVzh4HwCfERgAaLyukz8HjE,13231
 sqlglot/dialects/starrocks.py,sha256=2gav0PSNgRdAGXzawdznZliBpglJoQ0wBxPI7ZIMsRw,11314
 sqlglot/dialects/tableau.py,sha256=oIawDzUITxGCWaEMB8OaNMPWhbC3U-2y09pYPm4eazc,2190
 sqlglot/dialects/teradata.py,sha256=7LxCcRwP0Idd_OnCzA57NCdheVjHcKC2aFAKG5N49IU,18202
@@ -76,8 +76,8 @@ sqlglot/optimizer/qualify_tables.py,sha256=dA4ZazL7ShQh2JgBwpHuG-4c5lBw1TNzCnuN7
 sqlglot/optimizer/scope.py,sha256=UOTrbwqcTc5iRQf0WStgYWXpE24w6riZy-tJYA18yTw,31229
 sqlglot/optimizer/simplify.py,sha256=-_yus42OYwqjQ9a2TSGhtG2G0pSkInUry1z7hEMz2pY,51062
 sqlglot/optimizer/unnest_subqueries.py,sha256=kzWUVDlxs8z9nmRx-8U-pHXPtVZhEIwkKqmKhr2QLvc,10908
-sqlglot-27.10.0.dist-info/licenses/LICENSE,sha256=p1Yk0B4oa0l8Rh-_dYyy75d8spjPd_vTloXfz4FWxys,1065
-sqlglot-27.10.0.dist-info/METADATA,sha256=FYz_px3ppPANEJZGC0NthW3Gu3LCGggxS-AaHbJrDbU,20682
-sqlglot-27.10.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-sqlglot-27.10.0.dist-info/top_level.txt,sha256=5kRskCGA_gVADF9rSfSzPdLHXqvfMusDYeHePfNY2nQ,8
-sqlglot-27.10.0.dist-info/RECORD,,
+sqlglot-27.11.0.dist-info/licenses/LICENSE,sha256=p1Yk0B4oa0l8Rh-_dYyy75d8spjPd_vTloXfz4FWxys,1065
+sqlglot-27.11.0.dist-info/METADATA,sha256=GoUJQsTzum00ctJVKTRCOnO1d19dqBDV7ptg1MKksWE,20682
+sqlglot-27.11.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+sqlglot-27.11.0.dist-info/top_level.txt,sha256=5kRskCGA_gVADF9rSfSzPdLHXqvfMusDYeHePfNY2nQ,8
+sqlglot-27.11.0.dist-info/RECORD,,