Edit on GitHub

sqlglot.dialects.clickhouse

  1from __future__ import annotations
  2
  3import typing as t
  4
  5from sqlglot import exp, generator, parser, tokens
  6from sqlglot.dialects.dialect import (
  7    Dialect,
  8    inline_array_sql,
  9    no_pivot_sql,
 10    rename_func,
 11    var_map_sql,
 12)
 13from sqlglot.errors import ParseError
 14from sqlglot.parser import parse_var_map
 15from sqlglot.tokens import Token, TokenType
 16
 17
 18def _lower_func(sql: str) -> str:
 19    index = sql.index("(")
 20    return sql[:index].lower() + sql[index:]
 21
 22
 23class ClickHouse(Dialect):
 24    NORMALIZE_FUNCTIONS: bool | str = False
 25    NULL_ORDERING = "nulls_are_last"
 26    STRICT_STRING_CONCAT = True
 27
 28    class Tokenizer(tokens.Tokenizer):
 29        COMMENTS = ["--", "#", "#!", ("/*", "*/")]
 30        IDENTIFIERS = ['"', "`"]
 31        STRING_ESCAPES = ["'", "\\"]
 32        BIT_STRINGS = [("0b", "")]
 33        HEX_STRINGS = [("0x", ""), ("0X", "")]
 34
 35        KEYWORDS = {
 36            **tokens.Tokenizer.KEYWORDS,
 37            "ATTACH": TokenType.COMMAND,
 38            "DATETIME64": TokenType.DATETIME64,
 39            "DICTIONARY": TokenType.DICTIONARY,
 40            "FINAL": TokenType.FINAL,
 41            "FLOAT32": TokenType.FLOAT,
 42            "FLOAT64": TokenType.DOUBLE,
 43            "GLOBAL": TokenType.GLOBAL,
 44            "INT128": TokenType.INT128,
 45            "INT16": TokenType.SMALLINT,
 46            "INT256": TokenType.INT256,
 47            "INT32": TokenType.INT,
 48            "INT64": TokenType.BIGINT,
 49            "INT8": TokenType.TINYINT,
 50            "MAP": TokenType.MAP,
 51            "TUPLE": TokenType.STRUCT,
 52            "UINT128": TokenType.UINT128,
 53            "UINT16": TokenType.USMALLINT,
 54            "UINT256": TokenType.UINT256,
 55            "UINT32": TokenType.UINT,
 56            "UINT64": TokenType.UBIGINT,
 57            "UINT8": TokenType.UTINYINT,
 58        }
 59
 60    class Parser(parser.Parser):
 61        FUNCTIONS = {
 62            **parser.Parser.FUNCTIONS,
 63            "ANY": exp.AnyValue.from_arg_list,
 64            "MAP": parse_var_map,
 65            "MATCH": exp.RegexpLike.from_arg_list,
 66            "UNIQ": exp.ApproxDistinct.from_arg_list,
 67        }
 68
 69        FUNCTIONS_WITH_ALIASED_ARGS = {*parser.Parser.FUNCTIONS_WITH_ALIASED_ARGS, "TUPLE"}
 70
 71        FUNCTION_PARSERS = {
 72            **parser.Parser.FUNCTION_PARSERS,
 73            "QUANTILE": lambda self: self._parse_quantile(),
 74        }
 75
 76        FUNCTION_PARSERS.pop("MATCH")
 77
 78        NO_PAREN_FUNCTION_PARSERS = parser.Parser.NO_PAREN_FUNCTION_PARSERS.copy()
 79        NO_PAREN_FUNCTION_PARSERS.pop(TokenType.ANY)
 80
 81        RANGE_PARSERS = {
 82            **parser.Parser.RANGE_PARSERS,
 83            TokenType.GLOBAL: lambda self, this: self._match(TokenType.IN)
 84            and self._parse_in(this, is_global=True),
 85        }
 86
 87        # The PLACEHOLDER entry is popped because 1) it doesn't affect Clickhouse (it corresponds to
 88        # the postgres-specific JSONBContains parser) and 2) it makes parsing the ternary op simpler.
 89        COLUMN_OPERATORS = parser.Parser.COLUMN_OPERATORS.copy()
 90        COLUMN_OPERATORS.pop(TokenType.PLACEHOLDER)
 91
 92        JOIN_KINDS = {
 93            *parser.Parser.JOIN_KINDS,
 94            TokenType.ANY,
 95            TokenType.ASOF,
 96            TokenType.ANTI,
 97            TokenType.SEMI,
 98            TokenType.ARRAY,
 99        }
100
101        TABLE_ALIAS_TOKENS = {*parser.Parser.TABLE_ALIAS_TOKENS} - {
102            TokenType.ANY,
103            TokenType.SEMI,
104            TokenType.ANTI,
105            TokenType.SETTINGS,
106            TokenType.FORMAT,
107            TokenType.ARRAY,
108        }
109
110        LOG_DEFAULTS_TO_LN = True
111
112        QUERY_MODIFIER_PARSERS = {
113            **parser.Parser.QUERY_MODIFIER_PARSERS,
114            TokenType.SETTINGS: lambda self: (
115                "settings",
116                self._advance() or self._parse_csv(self._parse_conjunction),
117            ),
118            TokenType.FORMAT: lambda self: ("format", self._advance() or self._parse_id_var()),
119        }
120
121        def _parse_conjunction(self) -> t.Optional[exp.Expression]:
122            this = super()._parse_conjunction()
123
124            if self._match(TokenType.PLACEHOLDER):
125                return self.expression(
126                    exp.If,
127                    this=this,
128                    true=self._parse_conjunction(),
129                    false=self._match(TokenType.COLON) and self._parse_conjunction(),
130                )
131
132            return this
133
134        def _parse_placeholder(self) -> t.Optional[exp.Expression]:
135            """
136            Parse a placeholder expression like SELECT {abc: UInt32} or FROM {table: Identifier}
137            https://clickhouse.com/docs/en/sql-reference/syntax#defining-and-using-query-parameters
138            """
139            if not self._match(TokenType.L_BRACE):
140                return None
141
142            this = self._parse_id_var()
143            self._match(TokenType.COLON)
144            kind = self._parse_types(check_func=False) or (
145                self._match_text_seq("IDENTIFIER") and "Identifier"
146            )
147
148            if not kind:
149                self.raise_error("Expecting a placeholder type or 'Identifier' for tables")
150            elif not self._match(TokenType.R_BRACE):
151                self.raise_error("Expecting }")
152
153            return self.expression(exp.Placeholder, this=this, kind=kind)
154
155        def _parse_in(self, this: t.Optional[exp.Expression], is_global: bool = False) -> exp.In:
156            this = super()._parse_in(this)
157            this.set("is_global", is_global)
158            return this
159
160        def _parse_table(
161            self,
162            schema: bool = False,
163            joins: bool = False,
164            alias_tokens: t.Optional[t.Collection[TokenType]] = None,
165            parse_bracket: bool = False,
166        ) -> t.Optional[exp.Expression]:
167            this = super()._parse_table(
168                schema=schema, joins=joins, alias_tokens=alias_tokens, parse_bracket=parse_bracket
169            )
170
171            if self._match(TokenType.FINAL):
172                this = self.expression(exp.Final, this=this)
173
174            return this
175
176        def _parse_position(self, haystack_first: bool = False) -> exp.StrPosition:
177            return super()._parse_position(haystack_first=True)
178
179        # https://clickhouse.com/docs/en/sql-reference/statements/select/with/
180        def _parse_cte(self) -> exp.CTE:
181            index = self._index
182            try:
183                # WITH <identifier> AS <subquery expression>
184                return super()._parse_cte()
185            except ParseError:
186                # WITH <expression> AS <identifier>
187                self._retreat(index)
188                statement = self._parse_statement()
189
190                if statement and isinstance(statement.this, exp.Alias):
191                    self.raise_error("Expected CTE to have alias")
192
193                return self.expression(exp.CTE, this=statement, alias=statement and statement.this)
194
195        def _parse_join_parts(
196            self,
197        ) -> t.Tuple[t.Optional[Token], t.Optional[Token], t.Optional[Token]]:
198            is_global = self._match(TokenType.GLOBAL) and self._prev
199            kind_pre = self._match_set(self.JOIN_KINDS, advance=False) and self._prev
200
201            if kind_pre:
202                kind = self._match_set(self.JOIN_KINDS) and self._prev
203                side = self._match_set(self.JOIN_SIDES) and self._prev
204                return is_global, side, kind
205
206            return (
207                is_global,
208                self._match_set(self.JOIN_SIDES) and self._prev,
209                self._match_set(self.JOIN_KINDS) and self._prev,
210            )
211
212        def _parse_join(
213            self, skip_join_token: bool = False, parse_bracket: bool = False
214        ) -> t.Optional[exp.Join]:
215            join = super()._parse_join(skip_join_token=skip_join_token, parse_bracket=True)
216
217            if join:
218                join.set("global", join.args.pop("method", None))
219            return join
220
221        def _parse_function(
222            self,
223            functions: t.Optional[t.Dict[str, t.Callable]] = None,
224            anonymous: bool = False,
225            optional_parens: bool = True,
226        ) -> t.Optional[exp.Expression]:
227            func = super()._parse_function(
228                functions=functions, anonymous=anonymous, optional_parens=optional_parens
229            )
230
231            if isinstance(func, exp.Anonymous):
232                params = self._parse_func_params(func)
233
234                if params:
235                    return self.expression(
236                        exp.ParameterizedAgg,
237                        this=func.this,
238                        expressions=func.expressions,
239                        params=params,
240                    )
241
242            return func
243
244        def _parse_func_params(
245            self, this: t.Optional[exp.Func] = None
246        ) -> t.Optional[t.List[t.Optional[exp.Expression]]]:
247            if self._match_pair(TokenType.R_PAREN, TokenType.L_PAREN):
248                return self._parse_csv(self._parse_lambda)
249
250            if self._match(TokenType.L_PAREN):
251                params = self._parse_csv(self._parse_lambda)
252                self._match_r_paren(this)
253                return params
254
255            return None
256
257        def _parse_quantile(self) -> exp.Quantile:
258            this = self._parse_lambda()
259            params = self._parse_func_params()
260            if params:
261                return self.expression(exp.Quantile, this=params[0], quantile=this)
262            return self.expression(exp.Quantile, this=this, quantile=exp.Literal.number(0.5))
263
264        def _parse_wrapped_id_vars(
265            self, optional: bool = False
266        ) -> t.List[t.Optional[exp.Expression]]:
267            return super()._parse_wrapped_id_vars(optional=True)
268
269        def _parse_primary_key(
270            self, wrapped_optional: bool = False, in_props: bool = False
271        ) -> exp.PrimaryKeyColumnConstraint | exp.PrimaryKey:
272            return super()._parse_primary_key(
273                wrapped_optional=wrapped_optional or in_props, in_props=in_props
274            )
275
276        def _parse_on_property(self) -> t.Optional[exp.Expression]:
277            index = self._index
278            if self._match_text_seq("CLUSTER"):
279                this = self._parse_id_var()
280                if this:
281                    return self.expression(exp.OnCluster, this=this)
282                else:
283                    self._retreat(index)
284            return None
285
286    class Generator(generator.Generator):
287        QUERY_HINTS = False
288        STRUCT_DELIMITER = ("(", ")")
289
290        TYPE_MAPPING = {
291            **generator.Generator.TYPE_MAPPING,
292            exp.DataType.Type.ARRAY: "Array",
293            exp.DataType.Type.BIGINT: "Int64",
294            exp.DataType.Type.DATETIME64: "DateTime64",
295            exp.DataType.Type.DOUBLE: "Float64",
296            exp.DataType.Type.FLOAT: "Float32",
297            exp.DataType.Type.INT: "Int32",
298            exp.DataType.Type.INT128: "Int128",
299            exp.DataType.Type.INT256: "Int256",
300            exp.DataType.Type.MAP: "Map",
301            exp.DataType.Type.NULLABLE: "Nullable",
302            exp.DataType.Type.SMALLINT: "Int16",
303            exp.DataType.Type.STRUCT: "Tuple",
304            exp.DataType.Type.TINYINT: "Int8",
305            exp.DataType.Type.UBIGINT: "UInt64",
306            exp.DataType.Type.UINT: "UInt32",
307            exp.DataType.Type.UINT128: "UInt128",
308            exp.DataType.Type.UINT256: "UInt256",
309            exp.DataType.Type.USMALLINT: "UInt16",
310            exp.DataType.Type.UTINYINT: "UInt8",
311        }
312
313        TRANSFORMS = {
314            **generator.Generator.TRANSFORMS,
315            exp.AnyValue: rename_func("any"),
316            exp.ApproxDistinct: rename_func("uniq"),
317            exp.Array: inline_array_sql,
318            exp.CastToStrType: rename_func("CAST"),
319            exp.Final: lambda self, e: f"{self.sql(e, 'this')} FINAL",
320            exp.Map: lambda self, e: _lower_func(var_map_sql(self, e)),
321            exp.PartitionedByProperty: lambda self, e: f"PARTITION BY {self.sql(e, 'this')}",
322            exp.Pivot: no_pivot_sql,
323            exp.Quantile: lambda self, e: self.func("quantile", e.args.get("quantile"))
324            + f"({self.sql(e, 'this')})",
325            exp.RegexpLike: lambda self, e: f"match({self.format_args(e.this, e.expression)})",
326            exp.StrPosition: lambda self, e: f"position({self.format_args(e.this, e.args.get('substr'), e.args.get('position'))})",
327            exp.VarMap: lambda self, e: _lower_func(var_map_sql(self, e)),
328        }
329
330        PROPERTIES_LOCATION = {
331            **generator.Generator.PROPERTIES_LOCATION,
332            exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED,
333            exp.PartitionedByProperty: exp.Properties.Location.POST_SCHEMA,
334            exp.OnCluster: exp.Properties.Location.POST_NAME,
335        }
336
337        JOIN_HINTS = False
338        TABLE_HINTS = False
339        EXPLICIT_UNION = True
340        GROUPINGS_SEP = ""
341
342        # there's no list in docs, but it can be found in Clickhouse code
343        # see `ClickHouse/src/Parsers/ParserCreate*.cpp`
344        ON_CLUSTER_TARGETS = {
345            "DATABASE",
346            "TABLE",
347            "VIEW",
348            "DICTIONARY",
349            "INDEX",
350            "FUNCTION",
351            "NAMED COLLECTION",
352        }
353
354        def safeconcat_sql(self, expression: exp.SafeConcat) -> str:
355            # Clickhouse errors out if we try to cast a NULL value to TEXT
356            return self.func(
357                "CONCAT",
358                *[
359                    exp.func("if", e.is_(exp.null()), e, exp.cast(e, "text"))
360                    for e in t.cast(t.List[exp.Condition], expression.expressions)
361                ],
362            )
363
364        def cte_sql(self, expression: exp.CTE) -> str:
365            if isinstance(expression.this, exp.Alias):
366                return self.sql(expression, "this")
367
368            return super().cte_sql(expression)
369
370        def after_limit_modifiers(self, expression: exp.Expression) -> t.List[str]:
371            return super().after_limit_modifiers(expression) + [
372                self.seg("SETTINGS ") + self.expressions(expression, key="settings", flat=True)
373                if expression.args.get("settings")
374                else "",
375                self.seg("FORMAT ") + self.sql(expression, "format")
376                if expression.args.get("format")
377                else "",
378            ]
379
380        def parameterizedagg_sql(self, expression: exp.Anonymous) -> str:
381            params = self.expressions(expression, "params", flat=True)
382            return self.func(expression.name, *expression.expressions) + f"({params})"
383
384        def placeholder_sql(self, expression: exp.Placeholder) -> str:
385            return f"{{{expression.name}: {self.sql(expression, 'kind')}}}"
386
387        def oncluster_sql(self, expression: exp.OnCluster) -> str:
388            return f"ON CLUSTER {self.sql(expression, 'this')}"
389
390        def createable_sql(
391            self,
392            expression: exp.Create,
393            locations: dict[exp.Properties.Location, list[exp.Property]],
394        ) -> str:
395            kind = self.sql(expression, "kind").upper()
396            if kind in self.ON_CLUSTER_TARGETS and locations.get(exp.Properties.Location.POST_NAME):
397                this_name = self.sql(expression.this, "this")
398                this_properties = " ".join(
399                    [self.sql(prop) for prop in locations[exp.Properties.Location.POST_NAME]]
400                )
401                this_schema = self.schema_columns_sql(expression.this)
402                return f"{this_name}{self.sep()}{this_properties}{self.sep()}{this_schema}"
403            return super().createable_sql(expression, locations)
class ClickHouse(sqlglot.dialects.dialect.Dialect):
 24class ClickHouse(Dialect):
 25    NORMALIZE_FUNCTIONS: bool | str = False
 26    NULL_ORDERING = "nulls_are_last"
 27    STRICT_STRING_CONCAT = True
 28
 29    class Tokenizer(tokens.Tokenizer):
 30        COMMENTS = ["--", "#", "#!", ("/*", "*/")]
 31        IDENTIFIERS = ['"', "`"]
 32        STRING_ESCAPES = ["'", "\\"]
 33        BIT_STRINGS = [("0b", "")]
 34        HEX_STRINGS = [("0x", ""), ("0X", "")]
 35
 36        KEYWORDS = {
 37            **tokens.Tokenizer.KEYWORDS,
 38            "ATTACH": TokenType.COMMAND,
 39            "DATETIME64": TokenType.DATETIME64,
 40            "DICTIONARY": TokenType.DICTIONARY,
 41            "FINAL": TokenType.FINAL,
 42            "FLOAT32": TokenType.FLOAT,
 43            "FLOAT64": TokenType.DOUBLE,
 44            "GLOBAL": TokenType.GLOBAL,
 45            "INT128": TokenType.INT128,
 46            "INT16": TokenType.SMALLINT,
 47            "INT256": TokenType.INT256,
 48            "INT32": TokenType.INT,
 49            "INT64": TokenType.BIGINT,
 50            "INT8": TokenType.TINYINT,
 51            "MAP": TokenType.MAP,
 52            "TUPLE": TokenType.STRUCT,
 53            "UINT128": TokenType.UINT128,
 54            "UINT16": TokenType.USMALLINT,
 55            "UINT256": TokenType.UINT256,
 56            "UINT32": TokenType.UINT,
 57            "UINT64": TokenType.UBIGINT,
 58            "UINT8": TokenType.UTINYINT,
 59        }
 60
 61    class Parser(parser.Parser):
 62        FUNCTIONS = {
 63            **parser.Parser.FUNCTIONS,
 64            "ANY": exp.AnyValue.from_arg_list,
 65            "MAP": parse_var_map,
 66            "MATCH": exp.RegexpLike.from_arg_list,
 67            "UNIQ": exp.ApproxDistinct.from_arg_list,
 68        }
 69
 70        FUNCTIONS_WITH_ALIASED_ARGS = {*parser.Parser.FUNCTIONS_WITH_ALIASED_ARGS, "TUPLE"}
 71
 72        FUNCTION_PARSERS = {
 73            **parser.Parser.FUNCTION_PARSERS,
 74            "QUANTILE": lambda self: self._parse_quantile(),
 75        }
 76
 77        FUNCTION_PARSERS.pop("MATCH")
 78
 79        NO_PAREN_FUNCTION_PARSERS = parser.Parser.NO_PAREN_FUNCTION_PARSERS.copy()
 80        NO_PAREN_FUNCTION_PARSERS.pop(TokenType.ANY)
 81
 82        RANGE_PARSERS = {
 83            **parser.Parser.RANGE_PARSERS,
 84            TokenType.GLOBAL: lambda self, this: self._match(TokenType.IN)
 85            and self._parse_in(this, is_global=True),
 86        }
 87
 88        # The PLACEHOLDER entry is popped because 1) it doesn't affect Clickhouse (it corresponds to
 89        # the postgres-specific JSONBContains parser) and 2) it makes parsing the ternary op simpler.
 90        COLUMN_OPERATORS = parser.Parser.COLUMN_OPERATORS.copy()
 91        COLUMN_OPERATORS.pop(TokenType.PLACEHOLDER)
 92
 93        JOIN_KINDS = {
 94            *parser.Parser.JOIN_KINDS,
 95            TokenType.ANY,
 96            TokenType.ASOF,
 97            TokenType.ANTI,
 98            TokenType.SEMI,
 99            TokenType.ARRAY,
100        }
101
102        TABLE_ALIAS_TOKENS = {*parser.Parser.TABLE_ALIAS_TOKENS} - {
103            TokenType.ANY,
104            TokenType.SEMI,
105            TokenType.ANTI,
106            TokenType.SETTINGS,
107            TokenType.FORMAT,
108            TokenType.ARRAY,
109        }
110
111        LOG_DEFAULTS_TO_LN = True
112
113        QUERY_MODIFIER_PARSERS = {
114            **parser.Parser.QUERY_MODIFIER_PARSERS,
115            TokenType.SETTINGS: lambda self: (
116                "settings",
117                self._advance() or self._parse_csv(self._parse_conjunction),
118            ),
119            TokenType.FORMAT: lambda self: ("format", self._advance() or self._parse_id_var()),
120        }
121
122        def _parse_conjunction(self) -> t.Optional[exp.Expression]:
123            this = super()._parse_conjunction()
124
125            if self._match(TokenType.PLACEHOLDER):
126                return self.expression(
127                    exp.If,
128                    this=this,
129                    true=self._parse_conjunction(),
130                    false=self._match(TokenType.COLON) and self._parse_conjunction(),
131                )
132
133            return this
134
135        def _parse_placeholder(self) -> t.Optional[exp.Expression]:
136            """
137            Parse a placeholder expression like SELECT {abc: UInt32} or FROM {table: Identifier}
138            https://clickhouse.com/docs/en/sql-reference/syntax#defining-and-using-query-parameters
139            """
140            if not self._match(TokenType.L_BRACE):
141                return None
142
143            this = self._parse_id_var()
144            self._match(TokenType.COLON)
145            kind = self._parse_types(check_func=False) or (
146                self._match_text_seq("IDENTIFIER") and "Identifier"
147            )
148
149            if not kind:
150                self.raise_error("Expecting a placeholder type or 'Identifier' for tables")
151            elif not self._match(TokenType.R_BRACE):
152                self.raise_error("Expecting }")
153
154            return self.expression(exp.Placeholder, this=this, kind=kind)
155
156        def _parse_in(self, this: t.Optional[exp.Expression], is_global: bool = False) -> exp.In:
157            this = super()._parse_in(this)
158            this.set("is_global", is_global)
159            return this
160
161        def _parse_table(
162            self,
163            schema: bool = False,
164            joins: bool = False,
165            alias_tokens: t.Optional[t.Collection[TokenType]] = None,
166            parse_bracket: bool = False,
167        ) -> t.Optional[exp.Expression]:
168            this = super()._parse_table(
169                schema=schema, joins=joins, alias_tokens=alias_tokens, parse_bracket=parse_bracket
170            )
171
172            if self._match(TokenType.FINAL):
173                this = self.expression(exp.Final, this=this)
174
175            return this
176
177        def _parse_position(self, haystack_first: bool = False) -> exp.StrPosition:
178            return super()._parse_position(haystack_first=True)
179
180        # https://clickhouse.com/docs/en/sql-reference/statements/select/with/
181        def _parse_cte(self) -> exp.CTE:
182            index = self._index
183            try:
184                # WITH <identifier> AS <subquery expression>
185                return super()._parse_cte()
186            except ParseError:
187                # WITH <expression> AS <identifier>
188                self._retreat(index)
189                statement = self._parse_statement()
190
191                if statement and isinstance(statement.this, exp.Alias):
192                    self.raise_error("Expected CTE to have alias")
193
194                return self.expression(exp.CTE, this=statement, alias=statement and statement.this)
195
196        def _parse_join_parts(
197            self,
198        ) -> t.Tuple[t.Optional[Token], t.Optional[Token], t.Optional[Token]]:
199            is_global = self._match(TokenType.GLOBAL) and self._prev
200            kind_pre = self._match_set(self.JOIN_KINDS, advance=False) and self._prev
201
202            if kind_pre:
203                kind = self._match_set(self.JOIN_KINDS) and self._prev
204                side = self._match_set(self.JOIN_SIDES) and self._prev
205                return is_global, side, kind
206
207            return (
208                is_global,
209                self._match_set(self.JOIN_SIDES) and self._prev,
210                self._match_set(self.JOIN_KINDS) and self._prev,
211            )
212
213        def _parse_join(
214            self, skip_join_token: bool = False, parse_bracket: bool = False
215        ) -> t.Optional[exp.Join]:
216            join = super()._parse_join(skip_join_token=skip_join_token, parse_bracket=True)
217
218            if join:
219                join.set("global", join.args.pop("method", None))
220            return join
221
222        def _parse_function(
223            self,
224            functions: t.Optional[t.Dict[str, t.Callable]] = None,
225            anonymous: bool = False,
226            optional_parens: bool = True,
227        ) -> t.Optional[exp.Expression]:
228            func = super()._parse_function(
229                functions=functions, anonymous=anonymous, optional_parens=optional_parens
230            )
231
232            if isinstance(func, exp.Anonymous):
233                params = self._parse_func_params(func)
234
235                if params:
236                    return self.expression(
237                        exp.ParameterizedAgg,
238                        this=func.this,
239                        expressions=func.expressions,
240                        params=params,
241                    )
242
243            return func
244
245        def _parse_func_params(
246            self, this: t.Optional[exp.Func] = None
247        ) -> t.Optional[t.List[t.Optional[exp.Expression]]]:
248            if self._match_pair(TokenType.R_PAREN, TokenType.L_PAREN):
249                return self._parse_csv(self._parse_lambda)
250
251            if self._match(TokenType.L_PAREN):
252                params = self._parse_csv(self._parse_lambda)
253                self._match_r_paren(this)
254                return params
255
256            return None
257
258        def _parse_quantile(self) -> exp.Quantile:
259            this = self._parse_lambda()
260            params = self._parse_func_params()
261            if params:
262                return self.expression(exp.Quantile, this=params[0], quantile=this)
263            return self.expression(exp.Quantile, this=this, quantile=exp.Literal.number(0.5))
264
265        def _parse_wrapped_id_vars(
266            self, optional: bool = False
267        ) -> t.List[t.Optional[exp.Expression]]:
268            return super()._parse_wrapped_id_vars(optional=True)
269
270        def _parse_primary_key(
271            self, wrapped_optional: bool = False, in_props: bool = False
272        ) -> exp.PrimaryKeyColumnConstraint | exp.PrimaryKey:
273            return super()._parse_primary_key(
274                wrapped_optional=wrapped_optional or in_props, in_props=in_props
275            )
276
277        def _parse_on_property(self) -> t.Optional[exp.Expression]:
278            index = self._index
279            if self._match_text_seq("CLUSTER"):
280                this = self._parse_id_var()
281                if this:
282                    return self.expression(exp.OnCluster, this=this)
283                else:
284                    self._retreat(index)
285            return None
286
287    class Generator(generator.Generator):
288        QUERY_HINTS = False
289        STRUCT_DELIMITER = ("(", ")")
290
291        TYPE_MAPPING = {
292            **generator.Generator.TYPE_MAPPING,
293            exp.DataType.Type.ARRAY: "Array",
294            exp.DataType.Type.BIGINT: "Int64",
295            exp.DataType.Type.DATETIME64: "DateTime64",
296            exp.DataType.Type.DOUBLE: "Float64",
297            exp.DataType.Type.FLOAT: "Float32",
298            exp.DataType.Type.INT: "Int32",
299            exp.DataType.Type.INT128: "Int128",
300            exp.DataType.Type.INT256: "Int256",
301            exp.DataType.Type.MAP: "Map",
302            exp.DataType.Type.NULLABLE: "Nullable",
303            exp.DataType.Type.SMALLINT: "Int16",
304            exp.DataType.Type.STRUCT: "Tuple",
305            exp.DataType.Type.TINYINT: "Int8",
306            exp.DataType.Type.UBIGINT: "UInt64",
307            exp.DataType.Type.UINT: "UInt32",
308            exp.DataType.Type.UINT128: "UInt128",
309            exp.DataType.Type.UINT256: "UInt256",
310            exp.DataType.Type.USMALLINT: "UInt16",
311            exp.DataType.Type.UTINYINT: "UInt8",
312        }
313
314        TRANSFORMS = {
315            **generator.Generator.TRANSFORMS,
316            exp.AnyValue: rename_func("any"),
317            exp.ApproxDistinct: rename_func("uniq"),
318            exp.Array: inline_array_sql,
319            exp.CastToStrType: rename_func("CAST"),
320            exp.Final: lambda self, e: f"{self.sql(e, 'this')} FINAL",
321            exp.Map: lambda self, e: _lower_func(var_map_sql(self, e)),
322            exp.PartitionedByProperty: lambda self, e: f"PARTITION BY {self.sql(e, 'this')}",
323            exp.Pivot: no_pivot_sql,
324            exp.Quantile: lambda self, e: self.func("quantile", e.args.get("quantile"))
325            + f"({self.sql(e, 'this')})",
326            exp.RegexpLike: lambda self, e: f"match({self.format_args(e.this, e.expression)})",
327            exp.StrPosition: lambda self, e: f"position({self.format_args(e.this, e.args.get('substr'), e.args.get('position'))})",
328            exp.VarMap: lambda self, e: _lower_func(var_map_sql(self, e)),
329        }
330
331        PROPERTIES_LOCATION = {
332            **generator.Generator.PROPERTIES_LOCATION,
333            exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED,
334            exp.PartitionedByProperty: exp.Properties.Location.POST_SCHEMA,
335            exp.OnCluster: exp.Properties.Location.POST_NAME,
336        }
337
338        JOIN_HINTS = False
339        TABLE_HINTS = False
340        EXPLICIT_UNION = True
341        GROUPINGS_SEP = ""
342
343        # there's no list in docs, but it can be found in Clickhouse code
344        # see `ClickHouse/src/Parsers/ParserCreate*.cpp`
345        ON_CLUSTER_TARGETS = {
346            "DATABASE",
347            "TABLE",
348            "VIEW",
349            "DICTIONARY",
350            "INDEX",
351            "FUNCTION",
352            "NAMED COLLECTION",
353        }
354
355        def safeconcat_sql(self, expression: exp.SafeConcat) -> str:
356            # Clickhouse errors out if we try to cast a NULL value to TEXT
357            return self.func(
358                "CONCAT",
359                *[
360                    exp.func("if", e.is_(exp.null()), e, exp.cast(e, "text"))
361                    for e in t.cast(t.List[exp.Condition], expression.expressions)
362                ],
363            )
364
365        def cte_sql(self, expression: exp.CTE) -> str:
366            if isinstance(expression.this, exp.Alias):
367                return self.sql(expression, "this")
368
369            return super().cte_sql(expression)
370
371        def after_limit_modifiers(self, expression: exp.Expression) -> t.List[str]:
372            return super().after_limit_modifiers(expression) + [
373                self.seg("SETTINGS ") + self.expressions(expression, key="settings", flat=True)
374                if expression.args.get("settings")
375                else "",
376                self.seg("FORMAT ") + self.sql(expression, "format")
377                if expression.args.get("format")
378                else "",
379            ]
380
381        def parameterizedagg_sql(self, expression: exp.Anonymous) -> str:
382            params = self.expressions(expression, "params", flat=True)
383            return self.func(expression.name, *expression.expressions) + f"({params})"
384
385        def placeholder_sql(self, expression: exp.Placeholder) -> str:
386            return f"{{{expression.name}: {self.sql(expression, 'kind')}}}"
387
388        def oncluster_sql(self, expression: exp.OnCluster) -> str:
389            return f"ON CLUSTER {self.sql(expression, 'this')}"
390
391        def createable_sql(
392            self,
393            expression: exp.Create,
394            locations: dict[exp.Properties.Location, list[exp.Property]],
395        ) -> str:
396            kind = self.sql(expression, "kind").upper()
397            if kind in self.ON_CLUSTER_TARGETS and locations.get(exp.Properties.Location.POST_NAME):
398                this_name = self.sql(expression.this, "this")
399                this_properties = " ".join(
400                    [self.sql(prop) for prop in locations[exp.Properties.Location.POST_NAME]]
401                )
402                this_schema = self.schema_columns_sql(expression.this)
403                return f"{this_name}{self.sep()}{this_properties}{self.sep()}{this_schema}"
404            return super().createable_sql(expression, locations)
NORMALIZE_FUNCTIONS: bool | str = False
NULL_ORDERING = 'nulls_are_last'
STRICT_STRING_CONCAT = True
TIME_TRIE: Dict = {}
FORMAT_TRIE: Dict = {}
INVERSE_TIME_MAPPING: Dict[str, str] = {}
INVERSE_TIME_TRIE: Dict = {}
QUOTE_START = "'"
QUOTE_END = "'"
IDENTIFIER_START = '"'
IDENTIFIER_END = '"'
BIT_START = '0b'
BIT_END = ''
HEX_START = '0x'
HEX_END = ''
BYTE_START = None
BYTE_END = None
class ClickHouse.Tokenizer(sqlglot.tokens.Tokenizer):
29    class Tokenizer(tokens.Tokenizer):
30        COMMENTS = ["--", "#", "#!", ("/*", "*/")]
31        IDENTIFIERS = ['"', "`"]
32        STRING_ESCAPES = ["'", "\\"]
33        BIT_STRINGS = [("0b", "")]
34        HEX_STRINGS = [("0x", ""), ("0X", "")]
35
36        KEYWORDS = {
37            **tokens.Tokenizer.KEYWORDS,
38            "ATTACH": TokenType.COMMAND,
39            "DATETIME64": TokenType.DATETIME64,
40            "DICTIONARY": TokenType.DICTIONARY,
41            "FINAL": TokenType.FINAL,
42            "FLOAT32": TokenType.FLOAT,
43            "FLOAT64": TokenType.DOUBLE,
44            "GLOBAL": TokenType.GLOBAL,
45            "INT128": TokenType.INT128,
46            "INT16": TokenType.SMALLINT,
47            "INT256": TokenType.INT256,
48            "INT32": TokenType.INT,
49            "INT64": TokenType.BIGINT,
50            "INT8": TokenType.TINYINT,
51            "MAP": TokenType.MAP,
52            "TUPLE": TokenType.STRUCT,
53            "UINT128": TokenType.UINT128,
54            "UINT16": TokenType.USMALLINT,
55            "UINT256": TokenType.UINT256,
56            "UINT32": TokenType.UINT,
57            "UINT64": TokenType.UBIGINT,
58            "UINT8": TokenType.UTINYINT,
59        }
COMMENTS = ['--', '#', '#!', ('/*', '*/')]
IDENTIFIERS = ['"', '`']
STRING_ESCAPES = ["'", '\\']
BIT_STRINGS = [('0b', '')]
HEX_STRINGS = [('0x', ''), ('0X', '')]
KEYWORDS = {'{%': <TokenType.BLOCK_START: 'BLOCK_START'>, '{%+': <TokenType.BLOCK_START: 'BLOCK_START'>, '{%-': <TokenType.BLOCK_START: 'BLOCK_START'>, '%}': <TokenType.BLOCK_END: 'BLOCK_END'>, '+%}': <TokenType.BLOCK_END: 'BLOCK_END'>, '-%}': <TokenType.BLOCK_END: 'BLOCK_END'>, '{{+': <TokenType.BLOCK_START: 'BLOCK_START'>, '{{-': <TokenType.BLOCK_START: 'BLOCK_START'>, '+}}': <TokenType.BLOCK_END: 'BLOCK_END'>, '-}}': <TokenType.BLOCK_END: 'BLOCK_END'>, '/*+': <TokenType.HINT: 'HINT'>, '==': <TokenType.EQ: 'EQ'>, '::': <TokenType.DCOLON: 'DCOLON'>, '||': <TokenType.DPIPE: 'DPIPE'>, '>=': <TokenType.GTE: 'GTE'>, '<=': <TokenType.LTE: 'LTE'>, '<>': <TokenType.NEQ: 'NEQ'>, '!=': <TokenType.NEQ: 'NEQ'>, '<=>': <TokenType.NULLSAFE_EQ: 'NULLSAFE_EQ'>, '->': <TokenType.ARROW: 'ARROW'>, '->>': <TokenType.DARROW: 'DARROW'>, '=>': <TokenType.FARROW: 'FARROW'>, '#>': <TokenType.HASH_ARROW: 'HASH_ARROW'>, '#>>': <TokenType.DHASH_ARROW: 'DHASH_ARROW'>, '<->': <TokenType.LR_ARROW: 'LR_ARROW'>, '&&': <TokenType.DAMP: 'DAMP'>, 'ALL': <TokenType.ALL: 'ALL'>, 'ALWAYS': <TokenType.ALWAYS: 'ALWAYS'>, 'AND': <TokenType.AND: 'AND'>, 'ANTI': <TokenType.ANTI: 'ANTI'>, 'ANY': <TokenType.ANY: 'ANY'>, 'ASC': <TokenType.ASC: 'ASC'>, 'AS': <TokenType.ALIAS: 'ALIAS'>, 'ASOF': <TokenType.ASOF: 'ASOF'>, 'AUTOINCREMENT': <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, 'AUTO_INCREMENT': <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, 'BEGIN': <TokenType.BEGIN: 'BEGIN'>, 'BETWEEN': <TokenType.BETWEEN: 'BETWEEN'>, 'CACHE': <TokenType.CACHE: 'CACHE'>, 'UNCACHE': <TokenType.UNCACHE: 'UNCACHE'>, 'CASE': <TokenType.CASE: 'CASE'>, 'CHARACTER SET': <TokenType.CHARACTER_SET: 'CHARACTER_SET'>, 'CLUSTER BY': <TokenType.CLUSTER_BY: 'CLUSTER_BY'>, 'COLLATE': <TokenType.COLLATE: 'COLLATE'>, 'COLUMN': <TokenType.COLUMN: 'COLUMN'>, 'COMMIT': <TokenType.COMMIT: 'COMMIT'>, 'CONSTRAINT': <TokenType.CONSTRAINT: 'CONSTRAINT'>, 'CREATE': <TokenType.CREATE: 'CREATE'>, 'CROSS': <TokenType.CROSS: 'CROSS'>, 'CUBE': <TokenType.CUBE: 'CUBE'>, 'CURRENT_DATE': <TokenType.CURRENT_DATE: 'CURRENT_DATE'>, 'CURRENT_TIME': <TokenType.CURRENT_TIME: 'CURRENT_TIME'>, 'CURRENT_TIMESTAMP': <TokenType.CURRENT_TIMESTAMP: 'CURRENT_TIMESTAMP'>, 'CURRENT_USER': <TokenType.CURRENT_USER: 'CURRENT_USER'>, 'DATABASE': <TokenType.DATABASE: 'DATABASE'>, 'DEFAULT': <TokenType.DEFAULT: 'DEFAULT'>, 'DELETE': <TokenType.DELETE: 'DELETE'>, 'DESC': <TokenType.DESC: 'DESC'>, 'DESCRIBE': <TokenType.DESCRIBE: 'DESCRIBE'>, 'DISTINCT': <TokenType.DISTINCT: 'DISTINCT'>, 'DISTRIBUTE BY': <TokenType.DISTRIBUTE_BY: 'DISTRIBUTE_BY'>, 'DIV': <TokenType.DIV: 'DIV'>, 'DROP': <TokenType.DROP: 'DROP'>, 'ELSE': <TokenType.ELSE: 'ELSE'>, 'END': <TokenType.END: 'END'>, 'ESCAPE': <TokenType.ESCAPE: 'ESCAPE'>, 'EXCEPT': <TokenType.EXCEPT: 'EXCEPT'>, 'EXECUTE': <TokenType.EXECUTE: 'EXECUTE'>, 'EXISTS': <TokenType.EXISTS: 'EXISTS'>, 'FALSE': <TokenType.FALSE: 'FALSE'>, 'FETCH': <TokenType.FETCH: 'FETCH'>, 'FILTER': <TokenType.FILTER: 'FILTER'>, 'FIRST': <TokenType.FIRST: 'FIRST'>, 'FULL': <TokenType.FULL: 'FULL'>, 'FUNCTION': <TokenType.FUNCTION: 'FUNCTION'>, 'FOR': <TokenType.FOR: 'FOR'>, 'FOREIGN KEY': <TokenType.FOREIGN_KEY: 'FOREIGN_KEY'>, 'FORMAT': <TokenType.FORMAT: 'FORMAT'>, 'FROM': <TokenType.FROM: 'FROM'>, 'GEOGRAPHY': <TokenType.GEOGRAPHY: 'GEOGRAPHY'>, 'GEOMETRY': <TokenType.GEOMETRY: 'GEOMETRY'>, 'GLOB': <TokenType.GLOB: 'GLOB'>, 'GROUP BY': <TokenType.GROUP_BY: 'GROUP_BY'>, 'GROUPING SETS': <TokenType.GROUPING_SETS: 'GROUPING_SETS'>, 'HAVING': <TokenType.HAVING: 'HAVING'>, 'IF': <TokenType.IF: 'IF'>, 'ILIKE': <TokenType.ILIKE: 'ILIKE'>, 'IN': <TokenType.IN: 'IN'>, 'INDEX': <TokenType.INDEX: 'INDEX'>, 'INET': <TokenType.INET: 'INET'>, 'INNER': <TokenType.INNER: 'INNER'>, 'INSERT': <TokenType.INSERT: 'INSERT'>, 'INTERVAL': <TokenType.INTERVAL: 'INTERVAL'>, 'INTERSECT': <TokenType.INTERSECT: 'INTERSECT'>, 'INTO': <TokenType.INTO: 'INTO'>, 'IS': <TokenType.IS: 'IS'>, 'ISNULL': <TokenType.ISNULL: 'ISNULL'>, 'JOIN': <TokenType.JOIN: 'JOIN'>, 'KEEP': <TokenType.KEEP: 'KEEP'>, 'LATERAL': <TokenType.LATERAL: 'LATERAL'>, 'LEFT': <TokenType.LEFT: 'LEFT'>, 'LIKE': <TokenType.LIKE: 'LIKE'>, 'LIMIT': <TokenType.LIMIT: 'LIMIT'>, 'LOAD': <TokenType.LOAD: 'LOAD'>, 'LOCK': <TokenType.LOCK: 'LOCK'>, 'MERGE': <TokenType.MERGE: 'MERGE'>, 'NATURAL': <TokenType.NATURAL: 'NATURAL'>, 'NEXT': <TokenType.NEXT: 'NEXT'>, 'NEXT VALUE FOR': <TokenType.NEXT_VALUE_FOR: 'NEXT_VALUE_FOR'>, 'NOT': <TokenType.NOT: 'NOT'>, 'NOTNULL': <TokenType.NOTNULL: 'NOTNULL'>, 'NULL': <TokenType.NULL: 'NULL'>, 'OBJECT': <TokenType.OBJECT: 'OBJECT'>, 'OFFSET': <TokenType.OFFSET: 'OFFSET'>, 'ON': <TokenType.ON: 'ON'>, 'OR': <TokenType.OR: 'OR'>, 'XOR': <TokenType.XOR: 'XOR'>, 'ORDER BY': <TokenType.ORDER_BY: 'ORDER_BY'>, 'ORDINALITY': <TokenType.ORDINALITY: 'ORDINALITY'>, 'OUTER': <TokenType.OUTER: 'OUTER'>, 'OVER': <TokenType.OVER: 'OVER'>, 'OVERLAPS': <TokenType.OVERLAPS: 'OVERLAPS'>, 'OVERWRITE': <TokenType.OVERWRITE: 'OVERWRITE'>, 'PARTITION': <TokenType.PARTITION: 'PARTITION'>, 'PARTITION BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PARTITIONED BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PARTITIONED_BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PERCENT': <TokenType.PERCENT: 'PERCENT'>, 'PIVOT': <TokenType.PIVOT: 'PIVOT'>, 'PRAGMA': <TokenType.PRAGMA: 'PRAGMA'>, 'PRIMARY KEY': <TokenType.PRIMARY_KEY: 'PRIMARY_KEY'>, 'PROCEDURE': <TokenType.PROCEDURE: 'PROCEDURE'>, 'QUALIFY': <TokenType.QUALIFY: 'QUALIFY'>, 'RANGE': <TokenType.RANGE: 'RANGE'>, 'RECURSIVE': <TokenType.RECURSIVE: 'RECURSIVE'>, 'REGEXP': <TokenType.RLIKE: 'RLIKE'>, 'REPLACE': <TokenType.REPLACE: 'REPLACE'>, 'RETURNING': <TokenType.RETURNING: 'RETURNING'>, 'REFERENCES': <TokenType.REFERENCES: 'REFERENCES'>, 'RIGHT': <TokenType.RIGHT: 'RIGHT'>, 'RLIKE': <TokenType.RLIKE: 'RLIKE'>, 'ROLLBACK': <TokenType.ROLLBACK: 'ROLLBACK'>, 'ROLLUP': <TokenType.ROLLUP: 'ROLLUP'>, 'ROW': <TokenType.ROW: 'ROW'>, 'ROWS': <TokenType.ROWS: 'ROWS'>, 'SCHEMA': <TokenType.SCHEMA: 'SCHEMA'>, 'SELECT': <TokenType.SELECT: 'SELECT'>, 'SEMI': <TokenType.SEMI: 'SEMI'>, 'SET': <TokenType.SET: 'SET'>, 'SETTINGS': <TokenType.SETTINGS: 'SETTINGS'>, 'SHOW': <TokenType.SHOW: 'SHOW'>, 'SIMILAR TO': <TokenType.SIMILAR_TO: 'SIMILAR_TO'>, 'SOME': <TokenType.SOME: 'SOME'>, 'SORT BY': <TokenType.SORT_BY: 'SORT_BY'>, 'TABLE': <TokenType.TABLE: 'TABLE'>, 'TABLESAMPLE': <TokenType.TABLE_SAMPLE: 'TABLE_SAMPLE'>, 'TEMP': <TokenType.TEMPORARY: 'TEMPORARY'>, 'TEMPORARY': <TokenType.TEMPORARY: 'TEMPORARY'>, 'THEN': <TokenType.THEN: 'THEN'>, 'TRUE': <TokenType.TRUE: 'TRUE'>, 'UNION': <TokenType.UNION: 'UNION'>, 'UNNEST': <TokenType.UNNEST: 'UNNEST'>, 'UNPIVOT': <TokenType.UNPIVOT: 'UNPIVOT'>, 'UPDATE': <TokenType.UPDATE: 'UPDATE'>, 'USE': <TokenType.USE: 'USE'>, 'USING': <TokenType.USING: 'USING'>, 'UUID': <TokenType.UUID: 'UUID'>, 'VALUES': <TokenType.VALUES: 'VALUES'>, 'VIEW': <TokenType.VIEW: 'VIEW'>, 'VOLATILE': <TokenType.VOLATILE: 'VOLATILE'>, 'WHEN': <TokenType.WHEN: 'WHEN'>, 'WHERE': <TokenType.WHERE: 'WHERE'>, 'WINDOW': <TokenType.WINDOW: 'WINDOW'>, 'WITH': <TokenType.WITH: 'WITH'>, 'APPLY': <TokenType.APPLY: 'APPLY'>, 'ARRAY': <TokenType.ARRAY: 'ARRAY'>, 'BIT': <TokenType.BIT: 'BIT'>, 'BOOL': <TokenType.BOOLEAN: 'BOOLEAN'>, 'BOOLEAN': <TokenType.BOOLEAN: 'BOOLEAN'>, 'BYTE': <TokenType.TINYINT: 'TINYINT'>, 'TINYINT': <TokenType.TINYINT: 'TINYINT'>, 'SHORT': <TokenType.SMALLINT: 'SMALLINT'>, 'SMALLINT': <TokenType.SMALLINT: 'SMALLINT'>, 'INT2': <TokenType.SMALLINT: 'SMALLINT'>, 'INTEGER': <TokenType.INT: 'INT'>, 'INT': <TokenType.INT: 'INT'>, 'INT4': <TokenType.INT: 'INT'>, 'LONG': <TokenType.BIGINT: 'BIGINT'>, 'BIGINT': <TokenType.BIGINT: 'BIGINT'>, 'INT8': <TokenType.TINYINT: 'TINYINT'>, 'DEC': <TokenType.DECIMAL: 'DECIMAL'>, 'DECIMAL': <TokenType.DECIMAL: 'DECIMAL'>, 'BIGDECIMAL': <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, 'BIGNUMERIC': <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, 'MAP': <TokenType.MAP: 'MAP'>, 'NULLABLE': <TokenType.NULLABLE: 'NULLABLE'>, 'NUMBER': <TokenType.DECIMAL: 'DECIMAL'>, 'NUMERIC': <TokenType.DECIMAL: 'DECIMAL'>, 'FIXED': <TokenType.DECIMAL: 'DECIMAL'>, 'REAL': <TokenType.FLOAT: 'FLOAT'>, 'FLOAT': <TokenType.FLOAT: 'FLOAT'>, 'FLOAT4': <TokenType.FLOAT: 'FLOAT'>, 'FLOAT8': <TokenType.DOUBLE: 'DOUBLE'>, 'DOUBLE': <TokenType.DOUBLE: 'DOUBLE'>, 'DOUBLE PRECISION': <TokenType.DOUBLE: 'DOUBLE'>, 'JSON': <TokenType.JSON: 'JSON'>, 'CHAR': <TokenType.CHAR: 'CHAR'>, 'CHARACTER': <TokenType.CHAR: 'CHAR'>, 'NCHAR': <TokenType.NCHAR: 'NCHAR'>, 'VARCHAR': <TokenType.VARCHAR: 'VARCHAR'>, 'VARCHAR2': <TokenType.VARCHAR: 'VARCHAR'>, 'NVARCHAR': <TokenType.NVARCHAR: 'NVARCHAR'>, 'NVARCHAR2': <TokenType.NVARCHAR: 'NVARCHAR'>, 'STR': <TokenType.TEXT: 'TEXT'>, 'STRING': <TokenType.TEXT: 'TEXT'>, 'TEXT': <TokenType.TEXT: 'TEXT'>, 'CLOB': <TokenType.TEXT: 'TEXT'>, 'LONGVARCHAR': <TokenType.TEXT: 'TEXT'>, 'BINARY': <TokenType.BINARY: 'BINARY'>, 'BLOB': <TokenType.VARBINARY: 'VARBINARY'>, 'BYTEA': <TokenType.VARBINARY: 'VARBINARY'>, 'VARBINARY': <TokenType.VARBINARY: 'VARBINARY'>, 'TIME': <TokenType.TIME: 'TIME'>, 'TIMESTAMP': <TokenType.TIMESTAMP: 'TIMESTAMP'>, 'TIMESTAMPTZ': <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>, 'TIMESTAMPLTZ': <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>, 'DATE': <TokenType.DATE: 'DATE'>, 'DATETIME': <TokenType.DATETIME: 'DATETIME'>, 'INT4RANGE': <TokenType.INT4RANGE: 'INT4RANGE'>, 'INT4MULTIRANGE': <TokenType.INT4MULTIRANGE: 'INT4MULTIRANGE'>, 'INT8RANGE': <TokenType.INT8RANGE: 'INT8RANGE'>, 'INT8MULTIRANGE': <TokenType.INT8MULTIRANGE: 'INT8MULTIRANGE'>, 'NUMRANGE': <TokenType.NUMRANGE: 'NUMRANGE'>, 'NUMMULTIRANGE': <TokenType.NUMMULTIRANGE: 'NUMMULTIRANGE'>, 'TSRANGE': <TokenType.TSRANGE: 'TSRANGE'>, 'TSMULTIRANGE': <TokenType.TSMULTIRANGE: 'TSMULTIRANGE'>, 'TSTZRANGE': <TokenType.TSTZRANGE: 'TSTZRANGE'>, 'TSTZMULTIRANGE': <TokenType.TSTZMULTIRANGE: 'TSTZMULTIRANGE'>, 'DATERANGE': <TokenType.DATERANGE: 'DATERANGE'>, 'DATEMULTIRANGE': <TokenType.DATEMULTIRANGE: 'DATEMULTIRANGE'>, 'UNIQUE': <TokenType.UNIQUE: 'UNIQUE'>, 'STRUCT': <TokenType.STRUCT: 'STRUCT'>, 'VARIANT': <TokenType.VARIANT: 'VARIANT'>, 'ALTER': <TokenType.ALTER: 'ALTER'>, 'ANALYZE': <TokenType.COMMAND: 'COMMAND'>, 'CALL': <TokenType.COMMAND: 'COMMAND'>, 'COMMENT': <TokenType.COMMENT: 'COMMENT'>, 'COPY': <TokenType.COMMAND: 'COMMAND'>, 'EXPLAIN': <TokenType.COMMAND: 'COMMAND'>, 'GRANT': <TokenType.COMMAND: 'COMMAND'>, 'OPTIMIZE': <TokenType.COMMAND: 'COMMAND'>, 'PREPARE': <TokenType.COMMAND: 'COMMAND'>, 'TRUNCATE': <TokenType.COMMAND: 'COMMAND'>, 'VACUUM': <TokenType.COMMAND: 'COMMAND'>, 'USER-DEFINED': <TokenType.USERDEFINED: 'USERDEFINED'>, 'ATTACH': <TokenType.COMMAND: 'COMMAND'>, 'DATETIME64': <TokenType.DATETIME64: 'DATETIME64'>, 'DICTIONARY': <TokenType.DICTIONARY: 'DICTIONARY'>, 'FINAL': <TokenType.FINAL: 'FINAL'>, 'FLOAT32': <TokenType.FLOAT: 'FLOAT'>, 'FLOAT64': <TokenType.DOUBLE: 'DOUBLE'>, 'GLOBAL': <TokenType.GLOBAL: 'GLOBAL'>, 'INT128': <TokenType.INT128: 'INT128'>, 'INT16': <TokenType.SMALLINT: 'SMALLINT'>, 'INT256': <TokenType.INT256: 'INT256'>, 'INT32': <TokenType.INT: 'INT'>, 'INT64': <TokenType.BIGINT: 'BIGINT'>, 'TUPLE': <TokenType.STRUCT: 'STRUCT'>, 'UINT128': <TokenType.UINT128: 'UINT128'>, 'UINT16': <TokenType.USMALLINT: 'USMALLINT'>, 'UINT256': <TokenType.UINT256: 'UINT256'>, 'UINT32': <TokenType.UINT: 'UINT'>, 'UINT64': <TokenType.UBIGINT: 'UBIGINT'>, 'UINT8': <TokenType.UTINYINT: 'UTINYINT'>}
class ClickHouse.Parser(sqlglot.parser.Parser):
 61    class Parser(parser.Parser):
 62        FUNCTIONS = {
 63            **parser.Parser.FUNCTIONS,
 64            "ANY": exp.AnyValue.from_arg_list,
 65            "MAP": parse_var_map,
 66            "MATCH": exp.RegexpLike.from_arg_list,
 67            "UNIQ": exp.ApproxDistinct.from_arg_list,
 68        }
 69
 70        FUNCTIONS_WITH_ALIASED_ARGS = {*parser.Parser.FUNCTIONS_WITH_ALIASED_ARGS, "TUPLE"}
 71
 72        FUNCTION_PARSERS = {
 73            **parser.Parser.FUNCTION_PARSERS,
 74            "QUANTILE": lambda self: self._parse_quantile(),
 75        }
 76
 77        FUNCTION_PARSERS.pop("MATCH")
 78
 79        NO_PAREN_FUNCTION_PARSERS = parser.Parser.NO_PAREN_FUNCTION_PARSERS.copy()
 80        NO_PAREN_FUNCTION_PARSERS.pop(TokenType.ANY)
 81
 82        RANGE_PARSERS = {
 83            **parser.Parser.RANGE_PARSERS,
 84            TokenType.GLOBAL: lambda self, this: self._match(TokenType.IN)
 85            and self._parse_in(this, is_global=True),
 86        }
 87
 88        # The PLACEHOLDER entry is popped because 1) it doesn't affect Clickhouse (it corresponds to
 89        # the postgres-specific JSONBContains parser) and 2) it makes parsing the ternary op simpler.
 90        COLUMN_OPERATORS = parser.Parser.COLUMN_OPERATORS.copy()
 91        COLUMN_OPERATORS.pop(TokenType.PLACEHOLDER)
 92
 93        JOIN_KINDS = {
 94            *parser.Parser.JOIN_KINDS,
 95            TokenType.ANY,
 96            TokenType.ASOF,
 97            TokenType.ANTI,
 98            TokenType.SEMI,
 99            TokenType.ARRAY,
100        }
101
102        TABLE_ALIAS_TOKENS = {*parser.Parser.TABLE_ALIAS_TOKENS} - {
103            TokenType.ANY,
104            TokenType.SEMI,
105            TokenType.ANTI,
106            TokenType.SETTINGS,
107            TokenType.FORMAT,
108            TokenType.ARRAY,
109        }
110
111        LOG_DEFAULTS_TO_LN = True
112
113        QUERY_MODIFIER_PARSERS = {
114            **parser.Parser.QUERY_MODIFIER_PARSERS,
115            TokenType.SETTINGS: lambda self: (
116                "settings",
117                self._advance() or self._parse_csv(self._parse_conjunction),
118            ),
119            TokenType.FORMAT: lambda self: ("format", self._advance() or self._parse_id_var()),
120        }
121
122        def _parse_conjunction(self) -> t.Optional[exp.Expression]:
123            this = super()._parse_conjunction()
124
125            if self._match(TokenType.PLACEHOLDER):
126                return self.expression(
127                    exp.If,
128                    this=this,
129                    true=self._parse_conjunction(),
130                    false=self._match(TokenType.COLON) and self._parse_conjunction(),
131                )
132
133            return this
134
135        def _parse_placeholder(self) -> t.Optional[exp.Expression]:
136            """
137            Parse a placeholder expression like SELECT {abc: UInt32} or FROM {table: Identifier}
138            https://clickhouse.com/docs/en/sql-reference/syntax#defining-and-using-query-parameters
139            """
140            if not self._match(TokenType.L_BRACE):
141                return None
142
143            this = self._parse_id_var()
144            self._match(TokenType.COLON)
145            kind = self._parse_types(check_func=False) or (
146                self._match_text_seq("IDENTIFIER") and "Identifier"
147            )
148
149            if not kind:
150                self.raise_error("Expecting a placeholder type or 'Identifier' for tables")
151            elif not self._match(TokenType.R_BRACE):
152                self.raise_error("Expecting }")
153
154            return self.expression(exp.Placeholder, this=this, kind=kind)
155
156        def _parse_in(self, this: t.Optional[exp.Expression], is_global: bool = False) -> exp.In:
157            this = super()._parse_in(this)
158            this.set("is_global", is_global)
159            return this
160
161        def _parse_table(
162            self,
163            schema: bool = False,
164            joins: bool = False,
165            alias_tokens: t.Optional[t.Collection[TokenType]] = None,
166            parse_bracket: bool = False,
167        ) -> t.Optional[exp.Expression]:
168            this = super()._parse_table(
169                schema=schema, joins=joins, alias_tokens=alias_tokens, parse_bracket=parse_bracket
170            )
171
172            if self._match(TokenType.FINAL):
173                this = self.expression(exp.Final, this=this)
174
175            return this
176
177        def _parse_position(self, haystack_first: bool = False) -> exp.StrPosition:
178            return super()._parse_position(haystack_first=True)
179
180        # https://clickhouse.com/docs/en/sql-reference/statements/select/with/
181        def _parse_cte(self) -> exp.CTE:
182            index = self._index
183            try:
184                # WITH <identifier> AS <subquery expression>
185                return super()._parse_cte()
186            except ParseError:
187                # WITH <expression> AS <identifier>
188                self._retreat(index)
189                statement = self._parse_statement()
190
191                if statement and isinstance(statement.this, exp.Alias):
192                    self.raise_error("Expected CTE to have alias")
193
194                return self.expression(exp.CTE, this=statement, alias=statement and statement.this)
195
196        def _parse_join_parts(
197            self,
198        ) -> t.Tuple[t.Optional[Token], t.Optional[Token], t.Optional[Token]]:
199            is_global = self._match(TokenType.GLOBAL) and self._prev
200            kind_pre = self._match_set(self.JOIN_KINDS, advance=False) and self._prev
201
202            if kind_pre:
203                kind = self._match_set(self.JOIN_KINDS) and self._prev
204                side = self._match_set(self.JOIN_SIDES) and self._prev
205                return is_global, side, kind
206
207            return (
208                is_global,
209                self._match_set(self.JOIN_SIDES) and self._prev,
210                self._match_set(self.JOIN_KINDS) and self._prev,
211            )
212
213        def _parse_join(
214            self, skip_join_token: bool = False, parse_bracket: bool = False
215        ) -> t.Optional[exp.Join]:
216            join = super()._parse_join(skip_join_token=skip_join_token, parse_bracket=True)
217
218            if join:
219                join.set("global", join.args.pop("method", None))
220            return join
221
222        def _parse_function(
223            self,
224            functions: t.Optional[t.Dict[str, t.Callable]] = None,
225            anonymous: bool = False,
226            optional_parens: bool = True,
227        ) -> t.Optional[exp.Expression]:
228            func = super()._parse_function(
229                functions=functions, anonymous=anonymous, optional_parens=optional_parens
230            )
231
232            if isinstance(func, exp.Anonymous):
233                params = self._parse_func_params(func)
234
235                if params:
236                    return self.expression(
237                        exp.ParameterizedAgg,
238                        this=func.this,
239                        expressions=func.expressions,
240                        params=params,
241                    )
242
243            return func
244
245        def _parse_func_params(
246            self, this: t.Optional[exp.Func] = None
247        ) -> t.Optional[t.List[t.Optional[exp.Expression]]]:
248            if self._match_pair(TokenType.R_PAREN, TokenType.L_PAREN):
249                return self._parse_csv(self._parse_lambda)
250
251            if self._match(TokenType.L_PAREN):
252                params = self._parse_csv(self._parse_lambda)
253                self._match_r_paren(this)
254                return params
255
256            return None
257
258        def _parse_quantile(self) -> exp.Quantile:
259            this = self._parse_lambda()
260            params = self._parse_func_params()
261            if params:
262                return self.expression(exp.Quantile, this=params[0], quantile=this)
263            return self.expression(exp.Quantile, this=this, quantile=exp.Literal.number(0.5))
264
265        def _parse_wrapped_id_vars(
266            self, optional: bool = False
267        ) -> t.List[t.Optional[exp.Expression]]:
268            return super()._parse_wrapped_id_vars(optional=True)
269
270        def _parse_primary_key(
271            self, wrapped_optional: bool = False, in_props: bool = False
272        ) -> exp.PrimaryKeyColumnConstraint | exp.PrimaryKey:
273            return super()._parse_primary_key(
274                wrapped_optional=wrapped_optional or in_props, in_props=in_props
275            )
276
277        def _parse_on_property(self) -> t.Optional[exp.Expression]:
278            index = self._index
279            if self._match_text_seq("CLUSTER"):
280                this = self._parse_id_var()
281                if this:
282                    return self.expression(exp.OnCluster, this=this)
283                else:
284                    self._retreat(index)
285            return None

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
FUNCTIONS = {'ABS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Abs'>>, 'ANY_VALUE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.AnyValue'>>, 'APPROX_DISTINCT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ApproxDistinct'>>, 'APPROX_COUNT_DISTINCT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ApproxDistinct'>>, 'APPROX_QUANTILE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ApproxQuantile'>>, 'ARRAY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Array'>>, 'ARRAY_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayAgg'>>, 'ARRAY_ALL': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayAll'>>, 'ARRAY_ANY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayAny'>>, 'ARRAY_CONCAT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayConcat'>>, 'ARRAY_CONTAINS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayContains'>>, 'FILTER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayFilter'>>, 'ARRAY_FILTER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayFilter'>>, 'ARRAY_JOIN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayJoin'>>, 'ARRAY_SIZE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArraySize'>>, 'ARRAY_SORT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArraySort'>>, 'ARRAY_SUM': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArraySum'>>, 'ARRAY_UNION_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayUnionAgg'>>, 'AVG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Avg'>>, 'CASE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Case'>>, 'CAST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Cast'>>, 'CAST_TO_STR_TYPE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CastToStrType'>>, 'CEIL': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Ceil'>>, 'CEILING': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Ceil'>>, 'COALESCE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Coalesce'>>, 'IFNULL': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Coalesce'>>, 'NVL': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Coalesce'>>, 'CONCAT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Concat'>>, 'CONCAT_WS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ConcatWs'>>, 'COUNT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Count'>>, 'COUNT_IF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CountIf'>>, 'CURRENT_DATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CurrentDate'>>, 'CURRENT_DATETIME': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CurrentDatetime'>>, 'CURRENT_TIME': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CurrentTime'>>, 'CURRENT_TIMESTAMP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CurrentTimestamp'>>, 'CURRENT_USER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CurrentUser'>>, 'DATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Date'>>, 'DATE_ADD': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateAdd'>>, 'DATEDIFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateDiff'>>, 'DATE_DIFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateDiff'>>, 'DATEFROMPARTS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateFromParts'>>, 'DATE_STR_TO_DATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateStrToDate'>>, 'DATE_SUB': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateSub'>>, 'DATE_TO_DATE_STR': <function Parser.<lambda>>, 'DATE_TO_DI': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateToDi'>>, 'DATE_TRUNC': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateTrunc'>>, 'DATETIME_ADD': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DatetimeAdd'>>, 'DATETIME_DIFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DatetimeDiff'>>, 'DATETIME_SUB': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DatetimeSub'>>, 'DATETIME_TRUNC': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DatetimeTrunc'>>, 'DAY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Day'>>, 'DAY_OF_MONTH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DayOfMonth'>>, 'DAYOFMONTH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DayOfMonth'>>, 'DAY_OF_WEEK': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DayOfWeek'>>, 'DAYOFWEEK': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DayOfWeek'>>, 'DAY_OF_YEAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DayOfYear'>>, 'DAYOFYEAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DayOfYear'>>, 'DECODE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Decode'>>, 'DI_TO_DATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DiToDate'>>, 'ENCODE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Encode'>>, 'EXP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Exp'>>, 'EXPLODE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Explode'>>, 'EXTRACT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Extract'>>, 'FLOOR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Floor'>>, 'FROM_BASE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.FromBase'>>, 'FROM_BASE64': <bound method Func.from_arg_list of <class 'sqlglot.expressions.FromBase64'>>, 'GENERATE_SERIES': <bound method Func.from_arg_list of <class 'sqlglot.expressions.GenerateSeries'>>, 'GREATEST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Greatest'>>, 'GROUP_CONCAT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.GroupConcat'>>, 'HEX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Hex'>>, 'HLL': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Hll'>>, 'IF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.If'>>, 'INITCAP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Initcap'>>, 'JSON_ARRAY_CONTAINS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONArrayContains'>>, 'JSONB_EXTRACT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONBExtract'>>, 'JSONB_EXTRACT_SCALAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONBExtractScalar'>>, 'JSON_EXTRACT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONExtract'>>, 'JSON_EXTRACT_SCALAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONExtractScalar'>>, 'JSON_FORMAT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONFormat'>>, 'J_S_O_N_OBJECT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONObject'>>, 'LAST_DATE_OF_MONTH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LastDateOfMonth'>>, 'LEAST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Least'>>, 'LEFT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Left'>>, 'LENGTH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Length'>>, 'LEN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Length'>>, 'LEVENSHTEIN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Levenshtein'>>, 'LN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Ln'>>, 'LOG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Log'>>, 'LOG10': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Log10'>>, 'LOG2': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Log2'>>, 'LOGICAL_AND': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LogicalAnd'>>, 'BOOL_AND': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LogicalAnd'>>, 'BOOLAND_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LogicalAnd'>>, 'LOGICAL_OR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LogicalOr'>>, 'BOOL_OR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LogicalOr'>>, 'BOOLOR_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LogicalOr'>>, 'LOWER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Lower'>>, 'LCASE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Lower'>>, 'MD5': <bound method Func.from_arg_list of <class 'sqlglot.expressions.MD5'>>, 'MD5_DIGEST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.MD5Digest'>>, 'MAP': <function parse_var_map>, 'MAP_FROM_ENTRIES': <bound method Func.from_arg_list of <class 'sqlglot.expressions.MapFromEntries'>>, 'MATCH_AGAINST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.MatchAgainst'>>, 'MAX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Max'>>, 'MIN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Min'>>, 'MONTH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Month'>>, 'MONTHS_BETWEEN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.MonthsBetween'>>, 'NEXT_VALUE_FOR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.NextValueFor'>>, 'NUMBER_TO_STR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.NumberToStr'>>, 'NVL2': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Nvl2'>>, 'OPEN_J_S_O_N': <bound method Func.from_arg_list of <class 'sqlglot.expressions.OpenJSON'>>, 'PARAMETERIZED_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ParameterizedAgg'>>, 'PERCENTILE_CONT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.PercentileCont'>>, 'PERCENTILE_DISC': <bound method Func.from_arg_list of <class 'sqlglot.expressions.PercentileDisc'>>, 'POSEXPLODE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Posexplode'>>, 'POWER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Pow'>>, 'POW': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Pow'>>, 'QUANTILE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Quantile'>>, 'RANGE_N': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RangeN'>>, 'READ_CSV': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ReadCSV'>>, 'REDUCE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Reduce'>>, 'REGEXP_EXTRACT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RegexpExtract'>>, 'REGEXP_I_LIKE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RegexpILike'>>, 'REGEXP_LIKE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RegexpLike'>>, 'REGEXP_REPLACE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RegexpReplace'>>, 'REGEXP_SPLIT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RegexpSplit'>>, 'REPEAT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Repeat'>>, 'RIGHT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Right'>>, 'ROUND': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Round'>>, 'ROW_NUMBER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RowNumber'>>, 'SHA': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SHA'>>, 'SHA1': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SHA'>>, 'SHA2': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SHA2'>>, 'SAFE_CONCAT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SafeConcat'>>, 'SAFE_DIVIDE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SafeDivide'>>, 'SET_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SetAgg'>>, 'SORT_ARRAY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SortArray'>>, 'SPLIT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Split'>>, 'SQRT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Sqrt'>>, 'STANDARD_HASH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StandardHash'>>, 'STAR_MAP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StarMap'>>, 'STDDEV': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Stddev'>>, 'STDDEV_POP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StddevPop'>>, 'STDDEV_SAMP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StddevSamp'>>, 'STR_POSITION': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StrPosition'>>, 'STR_TO_DATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StrToDate'>>, 'STR_TO_TIME': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StrToTime'>>, 'STR_TO_UNIX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StrToUnix'>>, 'STRUCT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Struct'>>, 'STRUCT_EXTRACT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StructExtract'>>, 'SUBSTRING': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Substring'>>, 'SUM': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Sum'>>, 'TIME_ADD': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeAdd'>>, 'TIME_DIFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeDiff'>>, 'TIME_STR_TO_DATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeStrToDate'>>, 'TIME_STR_TO_TIME': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeStrToTime'>>, 'TIME_STR_TO_UNIX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeStrToUnix'>>, 'TIME_SUB': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeSub'>>, 'TIME_TO_STR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeToStr'>>, 'TIME_TO_TIME_STR': <function Parser.<lambda>>, 'TIME_TO_UNIX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeToUnix'>>, 'TIME_TRUNC': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeTrunc'>>, 'TIMESTAMP_ADD': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimestampAdd'>>, 'TIMESTAMP_DIFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimestampDiff'>>, 'TIMESTAMP_SUB': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimestampSub'>>, 'TIMESTAMP_TRUNC': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimestampTrunc'>>, 'TO_BASE64': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ToBase64'>>, 'TO_CHAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ToChar'>>, 'TRIM': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Trim'>>, 'TRY_CAST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TryCast'>>, 'TS_OR_DI_TO_DI': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TsOrDiToDi'>>, 'TS_OR_DS_ADD': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TsOrDsAdd'>>, 'TS_OR_DS_TO_DATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TsOrDsToDate'>>, 'TS_OR_DS_TO_DATE_STR': <function Parser.<lambda>>, 'UNHEX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Unhex'>>, 'UNIX_TO_STR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.UnixToStr'>>, 'UNIX_TO_TIME': <bound method Func.from_arg_list of <class 'sqlglot.expressions.UnixToTime'>>, 'UNIX_TO_TIME_STR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.UnixToTimeStr'>>, 'UPPER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Upper'>>, 'UCASE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Upper'>>, 'VAR_MAP': <function parse_var_map>, 'VARIANCE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Variance'>>, 'VARIANCE_SAMP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Variance'>>, 'VAR_SAMP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Variance'>>, 'VARIANCE_POP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.VariancePop'>>, 'VAR_POP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.VariancePop'>>, 'WEEK': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Week'>>, 'WEEK_OF_YEAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.WeekOfYear'>>, 'WEEKOFYEAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.WeekOfYear'>>, 'WHEN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.When'>>, 'X_M_L_TABLE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.XMLTable'>>, 'YEAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Year'>>, 'GLOB': <function Parser.<lambda>>, 'LIKE': <function parse_like>, 'ANY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.AnyValue'>>, 'MATCH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RegexpLike'>>, 'UNIQ': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ApproxDistinct'>>}
FUNCTIONS_WITH_ALIASED_ARGS = {'TUPLE', 'STRUCT'}
FUNCTION_PARSERS = {'ANY_VALUE': <function Parser.<lambda>>, 'CAST': <function Parser.<lambda>>, 'CONCAT': <function Parser.<lambda>>, 'CONVERT': <function Parser.<lambda>>, 'DECODE': <function Parser.<lambda>>, 'EXTRACT': <function Parser.<lambda>>, 'JSON_OBJECT': <function Parser.<lambda>>, 'LOG': <function Parser.<lambda>>, 'OPENJSON': <function Parser.<lambda>>, 'POSITION': <function Parser.<lambda>>, 'SAFE_CAST': <function Parser.<lambda>>, 'STRING_AGG': <function Parser.<lambda>>, 'SUBSTRING': <function Parser.<lambda>>, 'TRIM': <function Parser.<lambda>>, 'TRY_CAST': <function Parser.<lambda>>, 'TRY_CONVERT': <function Parser.<lambda>>, 'QUANTILE': <function ClickHouse.Parser.<lambda>>}
NO_PAREN_FUNCTION_PARSERS = {<TokenType.CASE: 'CASE'>: <function Parser.<lambda>>, <TokenType.IF: 'IF'>: <function Parser.<lambda>>, <TokenType.NEXT_VALUE_FOR: 'NEXT_VALUE_FOR'>: <function Parser.<lambda>>}
RANGE_PARSERS = {<TokenType.BETWEEN: 'BETWEEN'>: <function Parser.<lambda>>, <TokenType.GLOB: 'GLOB'>: <function binary_range_parser.<locals>.<lambda>>, <TokenType.ILIKE: 'ILIKE'>: <function binary_range_parser.<locals>.<lambda>>, <TokenType.IN: 'IN'>: <function Parser.<lambda>>, <TokenType.IRLIKE: 'IRLIKE'>: <function binary_range_parser.<locals>.<lambda>>, <TokenType.IS: 'IS'>: <function Parser.<lambda>>, <TokenType.LIKE: 'LIKE'>: <function binary_range_parser.<locals>.<lambda>>, <TokenType.OVERLAPS: 'OVERLAPS'>: <function binary_range_parser.<locals>.<lambda>>, <TokenType.RLIKE: 'RLIKE'>: <function binary_range_parser.<locals>.<lambda>>, <TokenType.SIMILAR_TO: 'SIMILAR_TO'>: <function binary_range_parser.<locals>.<lambda>>, <TokenType.GLOBAL: 'GLOBAL'>: <function ClickHouse.Parser.<lambda>>}
COLUMN_OPERATORS = {<TokenType.DOT: 'DOT'>: None, <TokenType.DCOLON: 'DCOLON'>: <function Parser.<lambda>>, <TokenType.ARROW: 'ARROW'>: <function Parser.<lambda>>, <TokenType.DARROW: 'DARROW'>: <function Parser.<lambda>>, <TokenType.HASH_ARROW: 'HASH_ARROW'>: <function Parser.<lambda>>, <TokenType.DHASH_ARROW: 'DHASH_ARROW'>: <function Parser.<lambda>>}
JOIN_KINDS = {<TokenType.INNER: 'INNER'>, <TokenType.ANTI: 'ANTI'>, <TokenType.OUTER: 'OUTER'>, <TokenType.ARRAY: 'ARRAY'>, <TokenType.ASOF: 'ASOF'>, <TokenType.SEMI: 'SEMI'>, <TokenType.ANY: 'ANY'>, <TokenType.CROSS: 'CROSS'>}
TABLE_ALIAS_TOKENS = {<TokenType.SCHEMA: 'SCHEMA'>, <TokenType.FALSE: 'FALSE'>, <TokenType.UINT: 'UINT'>, <TokenType.SHOW: 'SHOW'>, <TokenType.TABLE: 'TABLE'>, <TokenType.COLLATE: 'COLLATE'>, <TokenType.BOOLEAN: 'BOOLEAN'>, <TokenType.DELETE: 'DELETE'>, <TokenType.DATETIME: 'DATETIME'>, <TokenType.TOP: 'TOP'>, <TokenType.DESC: 'DESC'>, <TokenType.ENUM: 'ENUM'>, <TokenType.ESCAPE: 'ESCAPE'>, <TokenType.NUMMULTIRANGE: 'NUMMULTIRANGE'>, <TokenType.NCHAR: 'NCHAR'>, <TokenType.TSTZMULTIRANGE: 'TSTZMULTIRANGE'>, <TokenType.UINT128: 'UINT128'>, <TokenType.OBJECT: 'OBJECT'>, <TokenType.MAP: 'MAP'>, <TokenType.VARIANT: 'VARIANT'>, <TokenType.DEFAULT: 'DEFAULT'>, <TokenType.TEMPORARY: 'TEMPORARY'>, <TokenType.MERGE: 'MERGE'>, <TokenType.EXISTS: 'EXISTS'>, <TokenType.SMALLMONEY: 'SMALLMONEY'>, <TokenType.TINYINT: 'TINYINT'>, <TokenType.CURRENT_TIMESTAMP: 'CURRENT_TIMESTAMP'>, <TokenType.CONSTRAINT: 'CONSTRAINT'>, <TokenType.INT8RANGE: 'INT8RANGE'>, <TokenType.DATETIME64: 'DATETIME64'>, <TokenType.PRAGMA: 'PRAGMA'>, <TokenType.UNPIVOT: 'UNPIVOT'>, <TokenType.SUPER: 'SUPER'>, <TokenType.CACHE: 'CACHE'>, <TokenType.UNIQUEIDENTIFIER: 'UNIQUEIDENTIFIER'>, <TokenType.CURRENT_DATETIME: 'CURRENT_DATETIME'>, <TokenType.INT: 'INT'>, <TokenType.FLOAT: 'FLOAT'>, <TokenType.EXECUTE: 'EXECUTE'>, <TokenType.GEOMETRY: 'GEOMETRY'>, <TokenType.TRUE: 'TRUE'>, <TokenType.FIRST: 'FIRST'>, <TokenType.HSTORE: 'HSTORE'>, <TokenType.DESCRIBE: 'DESCRIBE'>, <TokenType.GEOGRAPHY: 'GEOGRAPHY'>, <TokenType.FUNCTION: 'FUNCTION'>, <TokenType.RANGE: 'RANGE'>, <TokenType.VOLATILE: 'VOLATILE'>, <TokenType.DATE: 'DATE'>, <TokenType.INET: 'INET'>, <TokenType.CURRENT_DATE: 'CURRENT_DATE'>, <TokenType.CURRENT_USER: 'CURRENT_USER'>, <TokenType.NVARCHAR: 'NVARCHAR'>, <TokenType.COMMENT: 'COMMENT'>, <TokenType.KEEP: 'KEEP'>, <TokenType.CHAR: 'CHAR'>, <TokenType.NEXT: 'NEXT'>, <TokenType.JSONB: 'JSONB'>, <TokenType.SMALLSERIAL: 'SMALLSERIAL'>, <TokenType.TIMESTAMP: 'TIMESTAMP'>, <TokenType.INT4MULTIRANGE: 'INT4MULTIRANGE'>, <TokenType.VARBINARY: 'VARBINARY'>, <TokenType.TSMULTIRANGE: 'TSMULTIRANGE'>, <TokenType.VAR: 'VAR'>, <TokenType.USMALLINT: 'USMALLINT'>, <TokenType.BIGINT: 'BIGINT'>, <TokenType.IMAGE: 'IMAGE'>, <TokenType.BINARY: 'BINARY'>, <TokenType.UUID: 'UUID'>, <TokenType.COMMAND: 'COMMAND'>, <TokenType.INT8MULTIRANGE: 'INT8MULTIRANGE'>, <TokenType.SERIAL: 'SERIAL'>, <TokenType.END: 'END'>, <TokenType.INT128: 'INT128'>, <TokenType.BIGSERIAL: 'BIGSERIAL'>, <TokenType.TSRANGE: 'TSRANGE'>, <TokenType.UINT256: 'UINT256'>, <TokenType.DIV: 'DIV'>, <TokenType.PIVOT: 'PIVOT'>, <TokenType.XML: 'XML'>, <TokenType.LOAD: 'LOAD'>, <TokenType.ORDINALITY: 'ORDINALITY'>, <TokenType.REFERENCES: 'REFERENCES'>, <TokenType.BEGIN: 'BEGIN'>, <TokenType.IF: 'IF'>, <TokenType.UBIGINT: 'UBIGINT'>, <TokenType.ROWS: 'ROWS'>, <TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>, <TokenType.INT256: 'INT256'>, <TokenType.STRUCT: 'STRUCT'>, <TokenType.USERDEFINED: 'USERDEFINED'>, <TokenType.INDEX: 'INDEX'>, <TokenType.LONGBLOB: 'LONGBLOB'>, <TokenType.INTERVAL: 'INTERVAL'>, <TokenType.PSEUDO_TYPE: 'PSEUDO_TYPE'>, <TokenType.ROWVERSION: 'ROWVERSION'>, <TokenType.PERCENT: 'PERCENT'>, <TokenType.MONEY: 'MONEY'>, <TokenType.TIME: 'TIME'>, <TokenType.IS: 'IS'>, <TokenType.DATABASE: 'DATABASE'>, <TokenType.TEXT: 'TEXT'>, <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>, <TokenType.HLLSKETCH: 'HLLSKETCH'>, <TokenType.ISNULL: 'ISNULL'>, <TokenType.LONGTEXT: 'LONGTEXT'>, <TokenType.UPDATE: 'UPDATE'>, <TokenType.VIEW: 'VIEW'>, <TokenType.ROW: 'ROW'>, <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>, <TokenType.DATERANGE: 'DATERANGE'>, <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, <TokenType.BIT: 'BIT'>, <TokenType.VARCHAR: 'VARCHAR'>, <TokenType.DECIMAL: 'DECIMAL'>, <TokenType.ASC: 'ASC'>, <TokenType.SET: 'SET'>, <TokenType.CASE: 'CASE'>, <TokenType.NUMRANGE: 'NUMRANGE'>, <TokenType.TSTZRANGE: 'TSTZRANGE'>, <TokenType.SMALLINT: 'SMALLINT'>, <TokenType.OVERWRITE: 'OVERWRITE'>, <TokenType.ALL: 'ALL'>, <TokenType.PARTITION: 'PARTITION'>, <TokenType.FILTER: 'FILTER'>, <TokenType.COMMIT: 'COMMIT'>, <TokenType.UNIQUE: 'UNIQUE'>, <TokenType.SOME: 'SOME'>, <TokenType.PROCEDURE: 'PROCEDURE'>, <TokenType.JSON: 'JSON'>, <TokenType.NULLABLE: 'NULLABLE'>, <TokenType.CURRENT_TIME: 'CURRENT_TIME'>, <TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>, <TokenType.DOUBLE: 'DOUBLE'>, <TokenType.UTINYINT: 'UTINYINT'>, <TokenType.DICTIONARY: 'DICTIONARY'>, <TokenType.DATEMULTIRANGE: 'DATEMULTIRANGE'>, <TokenType.INT4RANGE: 'INT4RANGE'>, <TokenType.COLUMN: 'COLUMN'>, <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>}
LOG_DEFAULTS_TO_LN = True
QUERY_MODIFIER_PARSERS = {<TokenType.MATCH_RECOGNIZE: 'MATCH_RECOGNIZE'>: <function Parser.<lambda>>, <TokenType.WHERE: 'WHERE'>: <function Parser.<lambda>>, <TokenType.GROUP_BY: 'GROUP_BY'>: <function Parser.<lambda>>, <TokenType.HAVING: 'HAVING'>: <function Parser.<lambda>>, <TokenType.QUALIFY: 'QUALIFY'>: <function Parser.<lambda>>, <TokenType.WINDOW: 'WINDOW'>: <function Parser.<lambda>>, <TokenType.ORDER_BY: 'ORDER_BY'>: <function Parser.<lambda>>, <TokenType.LIMIT: 'LIMIT'>: <function Parser.<lambda>>, <TokenType.FETCH: 'FETCH'>: <function Parser.<lambda>>, <TokenType.OFFSET: 'OFFSET'>: <function Parser.<lambda>>, <TokenType.FOR: 'FOR'>: <function Parser.<lambda>>, <TokenType.LOCK: 'LOCK'>: <function Parser.<lambda>>, <TokenType.TABLE_SAMPLE: 'TABLE_SAMPLE'>: <function Parser.<lambda>>, <TokenType.USING: 'USING'>: <function Parser.<lambda>>, <TokenType.CLUSTER_BY: 'CLUSTER_BY'>: <function Parser.<lambda>>, <TokenType.DISTRIBUTE_BY: 'DISTRIBUTE_BY'>: <function Parser.<lambda>>, <TokenType.SORT_BY: 'SORT_BY'>: <function Parser.<lambda>>, <TokenType.SETTINGS: 'SETTINGS'>: <function ClickHouse.Parser.<lambda>>, <TokenType.FORMAT: 'FORMAT'>: <function ClickHouse.Parser.<lambda>>}
STRICT_STRING_CONCAT = True
NULL_ORDERING: str = 'nulls_are_last'
SHOW_TRIE: Dict = {}
SET_TRIE: Dict = {'GLOBAL': {0: True}, 'LOCAL': {0: True}, 'SESSION': {0: True}, 'TRANSACTION': {0: True}}
FORMAT_TRIE: Dict = {}
TIME_TRIE: Dict = {}
class ClickHouse.Generator(sqlglot.generator.Generator):
287    class Generator(generator.Generator):
288        QUERY_HINTS = False
289        STRUCT_DELIMITER = ("(", ")")
290
291        TYPE_MAPPING = {
292            **generator.Generator.TYPE_MAPPING,
293            exp.DataType.Type.ARRAY: "Array",
294            exp.DataType.Type.BIGINT: "Int64",
295            exp.DataType.Type.DATETIME64: "DateTime64",
296            exp.DataType.Type.DOUBLE: "Float64",
297            exp.DataType.Type.FLOAT: "Float32",
298            exp.DataType.Type.INT: "Int32",
299            exp.DataType.Type.INT128: "Int128",
300            exp.DataType.Type.INT256: "Int256",
301            exp.DataType.Type.MAP: "Map",
302            exp.DataType.Type.NULLABLE: "Nullable",
303            exp.DataType.Type.SMALLINT: "Int16",
304            exp.DataType.Type.STRUCT: "Tuple",
305            exp.DataType.Type.TINYINT: "Int8",
306            exp.DataType.Type.UBIGINT: "UInt64",
307            exp.DataType.Type.UINT: "UInt32",
308            exp.DataType.Type.UINT128: "UInt128",
309            exp.DataType.Type.UINT256: "UInt256",
310            exp.DataType.Type.USMALLINT: "UInt16",
311            exp.DataType.Type.UTINYINT: "UInt8",
312        }
313
314        TRANSFORMS = {
315            **generator.Generator.TRANSFORMS,
316            exp.AnyValue: rename_func("any"),
317            exp.ApproxDistinct: rename_func("uniq"),
318            exp.Array: inline_array_sql,
319            exp.CastToStrType: rename_func("CAST"),
320            exp.Final: lambda self, e: f"{self.sql(e, 'this')} FINAL",
321            exp.Map: lambda self, e: _lower_func(var_map_sql(self, e)),
322            exp.PartitionedByProperty: lambda self, e: f"PARTITION BY {self.sql(e, 'this')}",
323            exp.Pivot: no_pivot_sql,
324            exp.Quantile: lambda self, e: self.func("quantile", e.args.get("quantile"))
325            + f"({self.sql(e, 'this')})",
326            exp.RegexpLike: lambda self, e: f"match({self.format_args(e.this, e.expression)})",
327            exp.StrPosition: lambda self, e: f"position({self.format_args(e.this, e.args.get('substr'), e.args.get('position'))})",
328            exp.VarMap: lambda self, e: _lower_func(var_map_sql(self, e)),
329        }
330
331        PROPERTIES_LOCATION = {
332            **generator.Generator.PROPERTIES_LOCATION,
333            exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED,
334            exp.PartitionedByProperty: exp.Properties.Location.POST_SCHEMA,
335            exp.OnCluster: exp.Properties.Location.POST_NAME,
336        }
337
338        JOIN_HINTS = False
339        TABLE_HINTS = False
340        EXPLICIT_UNION = True
341        GROUPINGS_SEP = ""
342
343        # there's no list in docs, but it can be found in Clickhouse code
344        # see `ClickHouse/src/Parsers/ParserCreate*.cpp`
345        ON_CLUSTER_TARGETS = {
346            "DATABASE",
347            "TABLE",
348            "VIEW",
349            "DICTIONARY",
350            "INDEX",
351            "FUNCTION",
352            "NAMED COLLECTION",
353        }
354
355        def safeconcat_sql(self, expression: exp.SafeConcat) -> str:
356            # Clickhouse errors out if we try to cast a NULL value to TEXT
357            return self.func(
358                "CONCAT",
359                *[
360                    exp.func("if", e.is_(exp.null()), e, exp.cast(e, "text"))
361                    for e in t.cast(t.List[exp.Condition], expression.expressions)
362                ],
363            )
364
365        def cte_sql(self, expression: exp.CTE) -> str:
366            if isinstance(expression.this, exp.Alias):
367                return self.sql(expression, "this")
368
369            return super().cte_sql(expression)
370
371        def after_limit_modifiers(self, expression: exp.Expression) -> t.List[str]:
372            return super().after_limit_modifiers(expression) + [
373                self.seg("SETTINGS ") + self.expressions(expression, key="settings", flat=True)
374                if expression.args.get("settings")
375                else "",
376                self.seg("FORMAT ") + self.sql(expression, "format")
377                if expression.args.get("format")
378                else "",
379            ]
380
381        def parameterizedagg_sql(self, expression: exp.Anonymous) -> str:
382            params = self.expressions(expression, "params", flat=True)
383            return self.func(expression.name, *expression.expressions) + f"({params})"
384
385        def placeholder_sql(self, expression: exp.Placeholder) -> str:
386            return f"{{{expression.name}: {self.sql(expression, 'kind')}}}"
387
388        def oncluster_sql(self, expression: exp.OnCluster) -> str:
389            return f"ON CLUSTER {self.sql(expression, 'this')}"
390
391        def createable_sql(
392            self,
393            expression: exp.Create,
394            locations: dict[exp.Properties.Location, list[exp.Property]],
395        ) -> str:
396            kind = self.sql(expression, "kind").upper()
397            if kind in self.ON_CLUSTER_TARGETS and locations.get(exp.Properties.Location.POST_NAME):
398                this_name = self.sql(expression.this, "this")
399                this_properties = " ".join(
400                    [self.sql(prop) for prop in locations[exp.Properties.Location.POST_NAME]]
401                )
402                this_schema = self.schema_columns_sql(expression.this)
403                return f"{this_name}{self.sep()}{this_properties}{self.sep()}{this_schema}"
404            return super().createable_sql(expression, locations)

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
QUERY_HINTS = False
STRUCT_DELIMITER = ('(', ')')
TYPE_MAPPING = {<Type.NCHAR: 'NCHAR'>: 'CHAR', <Type.NVARCHAR: 'NVARCHAR'>: 'VARCHAR', <Type.MEDIUMTEXT: 'MEDIUMTEXT'>: 'TEXT', <Type.LONGTEXT: 'LONGTEXT'>: 'TEXT', <Type.MEDIUMBLOB: 'MEDIUMBLOB'>: 'BLOB', <Type.LONGBLOB: 'LONGBLOB'>: 'BLOB', <Type.INET: 'INET'>: 'INET', <Type.ARRAY: 'ARRAY'>: 'Array', <Type.BIGINT: 'BIGINT'>: 'Int64', <Type.DATETIME64: 'DATETIME64'>: 'DateTime64', <Type.DOUBLE: 'DOUBLE'>: 'Float64', <Type.FLOAT: 'FLOAT'>: 'Float32', <Type.INT: 'INT'>: 'Int32', <Type.INT128: 'INT128'>: 'Int128', <Type.INT256: 'INT256'>: 'Int256', <Type.MAP: 'MAP'>: 'Map', <Type.NULLABLE: 'NULLABLE'>: 'Nullable', <Type.SMALLINT: 'SMALLINT'>: 'Int16', <Type.STRUCT: 'STRUCT'>: 'Tuple', <Type.TINYINT: 'TINYINT'>: 'Int8', <Type.UBIGINT: 'UBIGINT'>: 'UInt64', <Type.UINT: 'UINT'>: 'UInt32', <Type.UINT128: 'UINT128'>: 'UInt128', <Type.UINT256: 'UINT256'>: 'UInt256', <Type.USMALLINT: 'USMALLINT'>: 'UInt16', <Type.UTINYINT: 'UTINYINT'>: 'UInt8'}
TRANSFORMS = {<class 'sqlglot.expressions.DateAdd'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.TsOrDsAdd'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CaseSpecificColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CharacterSetColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CharacterSetProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CheckColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CollateColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CopyGrantsProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CommentColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.DateFormatColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.DefaultColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.EncodeColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ExecuteAsProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ExternalProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.InlineLengthColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.LanguageProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.LocationProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.LogProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.MaterializedProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.NoPrimaryIndexProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.OnCommitProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.OnUpdateColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.PathColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ReturnsProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SetProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SettingsProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SqlSecurityProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.StabilityProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.TemporaryProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ToTableProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.TransientProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.TitleColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.UppercaseColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.VarMap'>: <function ClickHouse.Generator.<lambda>>, <class 'sqlglot.expressions.VolatileProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.WithJournalTableProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.AnyValue'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.ApproxDistinct'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.Array'>: <function inline_array_sql>, <class 'sqlglot.expressions.CastToStrType'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.Final'>: <function ClickHouse.Generator.<lambda>>, <class 'sqlglot.expressions.Map'>: <function ClickHouse.Generator.<lambda>>, <class 'sqlglot.expressions.PartitionedByProperty'>: <function ClickHouse.Generator.<lambda>>, <class 'sqlglot.expressions.Pivot'>: <function no_pivot_sql>, <class 'sqlglot.expressions.Quantile'>: <function ClickHouse.Generator.<lambda>>, <class 'sqlglot.expressions.RegexpLike'>: <function ClickHouse.Generator.<lambda>>, <class 'sqlglot.expressions.StrPosition'>: <function ClickHouse.Generator.<lambda>>}
PROPERTIES_LOCATION = {<class 'sqlglot.expressions.AlgorithmProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.AutoIncrementProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.BlockCompressionProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.CharacterSetProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.ChecksumProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.CollateProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.CopyGrantsProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.Cluster'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.ClusteredByProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.DataBlocksizeProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.DefinerProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.DictRange'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.DictProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.DistKeyProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.DistStyleProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.EngineProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.ExecuteAsProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.ExternalProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.FallbackProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.FileFormatProperty'>: <Location.POST_WITH: 'POST_WITH'>, <class 'sqlglot.expressions.FreespaceProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.IsolatedLoadingProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.JournalProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.LanguageProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.LikeProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.LocationProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.LockingProperty'>: <Location.POST_ALIAS: 'POST_ALIAS'>, <class 'sqlglot.expressions.LogProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.MaterializedProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.MergeBlockRatioProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.NoPrimaryIndexProperty'>: <Location.POST_EXPRESSION: 'POST_EXPRESSION'>, <class 'sqlglot.expressions.OnCommitProperty'>: <Location.POST_EXPRESSION: 'POST_EXPRESSION'>, <class 'sqlglot.expressions.Order'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.PartitionedByProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.PrimaryKey'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.Property'>: <Location.POST_WITH: 'POST_WITH'>, <class 'sqlglot.expressions.ReturnsProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.RowFormatProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.RowFormatDelimitedProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.RowFormatSerdeProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SchemaCommentProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SerdeProperties'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.Set'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SettingsProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SetProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.SortKeyProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SqlSecurityProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.StabilityProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.TemporaryProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.ToTableProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.TransientProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.MergeTreeTTL'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.VolatileProperty'>: <Location.UNSUPPORTED: 'UNSUPPORTED'>, <class 'sqlglot.expressions.WithDataProperty'>: <Location.POST_EXPRESSION: 'POST_EXPRESSION'>, <class 'sqlglot.expressions.WithJournalTableProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.OnCluster'>: <Location.POST_NAME: 'POST_NAME'>}
JOIN_HINTS = False
TABLE_HINTS = False
EXPLICIT_UNION = True
GROUPINGS_SEP = ''
ON_CLUSTER_TARGETS = {'NAMED COLLECTION', 'DATABASE', 'DICTIONARY', 'INDEX', 'TABLE', 'FUNCTION', 'VIEW'}
def safeconcat_sql(self, expression: sqlglot.expressions.SafeConcat) -> str:
355        def safeconcat_sql(self, expression: exp.SafeConcat) -> str:
356            # Clickhouse errors out if we try to cast a NULL value to TEXT
357            return self.func(
358                "CONCAT",
359                *[
360                    exp.func("if", e.is_(exp.null()), e, exp.cast(e, "text"))
361                    for e in t.cast(t.List[exp.Condition], expression.expressions)
362                ],
363            )
def cte_sql(self, expression: sqlglot.expressions.CTE) -> str:
365        def cte_sql(self, expression: exp.CTE) -> str:
366            if isinstance(expression.this, exp.Alias):
367                return self.sql(expression, "this")
368
369            return super().cte_sql(expression)
def after_limit_modifiers(self, expression: sqlglot.expressions.Expression) -> List[str]:
371        def after_limit_modifiers(self, expression: exp.Expression) -> t.List[str]:
372            return super().after_limit_modifiers(expression) + [
373                self.seg("SETTINGS ") + self.expressions(expression, key="settings", flat=True)
374                if expression.args.get("settings")
375                else "",
376                self.seg("FORMAT ") + self.sql(expression, "format")
377                if expression.args.get("format")
378                else "",
379            ]
def parameterizedagg_sql(self, expression: sqlglot.expressions.Anonymous) -> str:
381        def parameterizedagg_sql(self, expression: exp.Anonymous) -> str:
382            params = self.expressions(expression, "params", flat=True)
383            return self.func(expression.name, *expression.expressions) + f"({params})"
def placeholder_sql(self, expression: sqlglot.expressions.Placeholder) -> str:
385        def placeholder_sql(self, expression: exp.Placeholder) -> str:
386            return f"{{{expression.name}: {self.sql(expression, 'kind')}}}"
def oncluster_sql(self, expression: sqlglot.expressions.OnCluster) -> str:
388        def oncluster_sql(self, expression: exp.OnCluster) -> str:
389            return f"ON CLUSTER {self.sql(expression, 'this')}"
def createable_sql( self, expression: sqlglot.expressions.Create, locations: dict[sqlglot.expressions.Properties.Location, list[sqlglot.expressions.Property]]) -> str:
391        def createable_sql(
392            self,
393            expression: exp.Create,
394            locations: dict[exp.Properties.Location, list[exp.Property]],
395        ) -> str:
396            kind = self.sql(expression, "kind").upper()
397            if kind in self.ON_CLUSTER_TARGETS and locations.get(exp.Properties.Location.POST_NAME):
398                this_name = self.sql(expression.this, "this")
399                this_properties = " ".join(
400                    [self.sql(prop) for prop in locations[exp.Properties.Location.POST_NAME]]
401                )
402                this_schema = self.schema_columns_sql(expression.this)
403                return f"{this_name}{self.sep()}{this_properties}{self.sep()}{this_schema}"
404            return super().createable_sql(expression, locations)
SELECT_KINDS: Tuple[str, ...] = ()
INVERSE_TIME_MAPPING: Dict[str, str] = {}
INVERSE_TIME_TRIE: Dict = {}
STRICT_STRING_CONCAT = True
NORMALIZE_FUNCTIONS: bool | str = False
NULL_ORDERING = 'nulls_are_last'
@classmethod
def can_identify(text: str, identify: str | bool = 'safe') -> bool:
246    @classmethod
247    def can_identify(cls, text: str, identify: str | bool = "safe") -> bool:
248        """Checks if text can be identified given an identify option.
249
250        Args:
251            text: The text to check.
252            identify:
253                "always" or `True`: Always returns true.
254                "safe": True if the identifier is case-insensitive.
255
256        Returns:
257            Whether or not the given text can be identified.
258        """
259        if identify is True or identify == "always":
260            return True
261
262        if identify == "safe":
263            return not cls.case_sensitive(text)
264
265        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.

QUOTE_START = "'"
QUOTE_END = "'"
IDENTIFIER_START = '"'
IDENTIFIER_END = '"'
STRING_ESCAPE = "'"
IDENTIFIER_ESCAPE = '"'
BIT_START: Optional[str] = '0b'
BIT_END: Optional[str] = ''
HEX_START: Optional[str] = '0x'
HEX_END: Optional[str] = ''
BYTE_START: Optional[str] = None
BYTE_END: Optional[str] = None
Inherited Members
sqlglot.generator.Generator
Generator
NULL_ORDERING_SUPPORTED
LOCKING_READS_SUPPORTED
WRAP_DERIVED_VALUES
CREATE_FUNCTION_RETURN_AS
MATCHED_BY_SOURCE
SINGLE_STRING_INTERVAL
INTERVAL_ALLOWS_PLURAL_FORM
TABLESAMPLE_WITH_METHOD
TABLESAMPLE_SIZE_IS_PERCENT
LIMIT_FETCH
RENAME_TABLE_WITH_DB
INDEX_ON
QUERY_HINT_SEP
IS_BOOL_ALLOWED
DUPLICATE_KEY_UPDATE_WITH_SET
LIMIT_IS_TOP
RETURNING_END
COLUMN_JOIN_MARKS_SUPPORTED
STAR_MAPPING
TIME_PART_SINGULARS
TOKEN_MAPPING
PARAMETER_TOKEN
RESERVED_KEYWORDS
WITH_SEPARATED_COMMENTS
UNWRAPPED_INTERVAL_VALUES
SENTINEL_LINE_BREAK
INDEX_OFFSET
UNNEST_COLUMN_ONLY
ALIAS_POST_TABLESAMPLE
IDENTIFIERS_CAN_START_WITH_DIGIT
ESCAPE_LINE_BREAK
pretty
identify
normalize
pad
unsupported_level
max_unsupported
leading_comma
max_text_width
comments
normalize_functions
unsupported_messages
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
create_sql
clone_sql
describe_sql
prepend_ctes
with_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
withtablehint_sql
indextablehint_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
select_sql
schema_sql
schema_columns_sql
star_sql
parameter_sql
sessionparameter_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
safebracket_sql
all_sql
any_sql
exists_sql
case_sql
constraint_sql
nextvaluefor_sql
extract_sql
trim_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
xor_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
clusteredbyproperty_sql
anyvalue_sql