sqlglot.dialects.bigquery
1from __future__ import annotations 2 3import logging 4import re 5import typing as t 6 7from sqlglot import exp, generator, parser, tokens, transforms 8from sqlglot._typing import E 9from sqlglot.dialects.dialect import ( 10 Dialect, 11 binary_from_function, 12 datestrtodate_sql, 13 format_time_lambda, 14 inline_array_sql, 15 max_or_greatest, 16 min_or_least, 17 no_ilike_sql, 18 parse_date_delta_with_interval, 19 regexp_replace_sql, 20 rename_func, 21 timestrtotime_sql, 22 ts_or_ds_to_date_sql, 23) 24from sqlglot.helper import seq_get, split_num_words 25from sqlglot.tokens import TokenType 26 27logger = logging.getLogger("sqlglot") 28 29 30def _date_add_sql( 31 data_type: str, kind: str 32) -> t.Callable[[generator.Generator, exp.Expression], str]: 33 def func(self, expression): 34 this = self.sql(expression, "this") 35 unit = expression.args.get("unit") 36 unit = exp.var(unit.name.upper() if unit else "DAY") 37 interval = exp.Interval(this=expression.expression.copy(), unit=unit) 38 return f"{data_type}_{kind}({this}, {self.sql(interval)})" 39 40 return func 41 42 43def _derived_table_values_to_unnest(self: generator.Generator, expression: exp.Values) -> str: 44 if not expression.find_ancestor(exp.From, exp.Join): 45 return self.values_sql(expression) 46 47 alias = expression.args.get("alias") 48 49 structs = [ 50 exp.Struct( 51 expressions=[ 52 exp.alias_(value, column_name) 53 for value, column_name in zip( 54 t.expressions, 55 alias.columns 56 if alias and alias.columns 57 else (f"_c{i}" for i in range(len(t.expressions))), 58 ) 59 ] 60 ) 61 for t in expression.find_all(exp.Tuple) 62 ] 63 64 return self.unnest_sql(exp.Unnest(expressions=[exp.Array(expressions=structs)])) 65 66 67def _returnsproperty_sql(self: generator.Generator, expression: exp.ReturnsProperty) -> str: 68 this = expression.this 69 if isinstance(this, exp.Schema): 70 this = f"{this.this} <{self.expressions(this)}>" 71 else: 72 this = self.sql(this) 73 return f"RETURNS {this}" 74 75 76def _create_sql(self: generator.Generator, expression: exp.Create) -> str: 77 kind = expression.args["kind"] 78 returns = expression.find(exp.ReturnsProperty) 79 80 if kind.upper() == "FUNCTION" and returns and returns.args.get("is_table"): 81 expression = expression.copy() 82 expression.set("kind", "TABLE FUNCTION") 83 84 if isinstance(expression.expression, (exp.Subquery, exp.Literal)): 85 expression.set("expression", expression.expression.this) 86 87 return self.create_sql(expression) 88 89 return self.create_sql(expression) 90 91 92def _unqualify_unnest(expression: exp.Expression) -> exp.Expression: 93 """Remove references to unnest table aliases since bigquery doesn't allow them. 94 95 These are added by the optimizer's qualify_column step. 96 """ 97 from sqlglot.optimizer.scope import Scope 98 99 if isinstance(expression, exp.Select): 100 for unnest in expression.find_all(exp.Unnest): 101 if isinstance(unnest.parent, (exp.From, exp.Join)) and unnest.alias: 102 for column in Scope(expression).find_all(exp.Column): 103 if column.table == unnest.alias: 104 column.set("table", None) 105 106 return expression 107 108 109# https://issuetracker.google.com/issues/162294746 110# workaround for bigquery bug when grouping by an expression and then ordering 111# WITH x AS (SELECT 1 y) 112# SELECT y + 1 z 113# FROM x 114# GROUP BY x + 1 115# ORDER by z 116def _alias_ordered_group(expression: exp.Expression) -> exp.Expression: 117 if isinstance(expression, exp.Select): 118 group = expression.args.get("group") 119 order = expression.args.get("order") 120 121 if group and order: 122 aliases = { 123 select.this: select.args["alias"] 124 for select in expression.selects 125 if isinstance(select, exp.Alias) 126 } 127 128 for e in group.expressions: 129 alias = aliases.get(e) 130 131 if alias: 132 e.replace(exp.column(alias)) 133 134 return expression 135 136 137def _pushdown_cte_column_names(expression: exp.Expression) -> exp.Expression: 138 """BigQuery doesn't allow column names when defining a CTE, so we try to push them down.""" 139 if isinstance(expression, exp.CTE) and expression.alias_column_names: 140 cte_query = expression.this 141 142 if cte_query.is_star: 143 logger.warning( 144 "Can't push down CTE column names for star queries. Run the query through" 145 " the optimizer or use 'qualify' to expand the star projections first." 146 ) 147 return expression 148 149 column_names = expression.alias_column_names 150 expression.args["alias"].set("columns", None) 151 152 for name, select in zip(column_names, cte_query.selects): 153 to_replace = select 154 155 if isinstance(select, exp.Alias): 156 select = select.this 157 158 # Inner aliases are shadowed by the CTE column names 159 to_replace.replace(exp.alias_(select, name)) 160 161 return expression 162 163 164def _parse_timestamp(args: t.List) -> exp.StrToTime: 165 this = format_time_lambda(exp.StrToTime, "bigquery")([seq_get(args, 1), seq_get(args, 0)]) 166 this.set("zone", seq_get(args, 2)) 167 return this 168 169 170def _parse_date(args: t.List) -> exp.Date | exp.DateFromParts: 171 expr_type = exp.DateFromParts if len(args) == 3 else exp.Date 172 return expr_type.from_arg_list(args) 173 174 175def _parse_to_hex(args: t.List) -> exp.Hex | exp.MD5: 176 # TO_HEX(MD5(..)) is common in BigQuery, so it's parsed into MD5 to simplify its transpilation 177 arg = seq_get(args, 0) 178 return exp.MD5(this=arg.this) if isinstance(arg, exp.MD5Digest) else exp.Hex(this=arg) 179 180 181class BigQuery(Dialect): 182 UNNEST_COLUMN_ONLY = True 183 184 # https://cloud.google.com/bigquery/docs/reference/standard-sql/lexical#case_sensitivity 185 RESOLVES_IDENTIFIERS_AS_UPPERCASE = None 186 187 # bigquery udfs are case sensitive 188 NORMALIZE_FUNCTIONS = False 189 190 TIME_MAPPING = { 191 "%D": "%m/%d/%y", 192 } 193 194 FORMAT_MAPPING = { 195 "DD": "%d", 196 "MM": "%m", 197 "MON": "%b", 198 "MONTH": "%B", 199 "YYYY": "%Y", 200 "YY": "%y", 201 "HH": "%I", 202 "HH12": "%I", 203 "HH24": "%H", 204 "MI": "%M", 205 "SS": "%S", 206 "SSSSS": "%f", 207 "TZH": "%z", 208 } 209 210 # The _PARTITIONTIME and _PARTITIONDATE pseudo-columns are not returned by a SELECT * statement 211 # https://cloud.google.com/bigquery/docs/querying-partitioned-tables#query_an_ingestion-time_partitioned_table 212 PSEUDOCOLUMNS = {"_PARTITIONTIME", "_PARTITIONDATE"} 213 214 @classmethod 215 def normalize_identifier(cls, expression: E) -> E: 216 # In BigQuery, CTEs aren't case-sensitive, but table names are (by default, at least). 217 # The following check is essentially a heuristic to detect tables based on whether or 218 # not they're qualified. 219 if isinstance(expression, exp.Identifier): 220 parent = expression.parent 221 222 while isinstance(parent, exp.Dot): 223 parent = parent.parent 224 225 if ( 226 not isinstance(parent, exp.UserDefinedFunction) 227 and not (isinstance(parent, exp.Table) and parent.db) 228 and not expression.meta.get("is_table") 229 ): 230 expression.set("this", expression.this.lower()) 231 232 return expression 233 234 class Tokenizer(tokens.Tokenizer): 235 QUOTES = ["'", '"', '"""', "'''"] 236 COMMENTS = ["--", "#", ("/*", "*/")] 237 IDENTIFIERS = ["`"] 238 STRING_ESCAPES = ["\\"] 239 240 HEX_STRINGS = [("0x", ""), ("0X", "")] 241 242 BYTE_STRINGS = [ 243 (prefix + q, q) for q in t.cast(t.List[str], QUOTES) for prefix in ("b", "B") 244 ] 245 246 RAW_STRINGS = [ 247 (prefix + q, q) for q in t.cast(t.List[str], QUOTES) for prefix in ("r", "R") 248 ] 249 250 KEYWORDS = { 251 **tokens.Tokenizer.KEYWORDS, 252 "ANY TYPE": TokenType.VARIANT, 253 "BEGIN": TokenType.COMMAND, 254 "BEGIN TRANSACTION": TokenType.BEGIN, 255 "CURRENT_DATETIME": TokenType.CURRENT_DATETIME, 256 "BYTES": TokenType.BINARY, 257 "DECLARE": TokenType.COMMAND, 258 "FLOAT64": TokenType.DOUBLE, 259 "INT64": TokenType.BIGINT, 260 "RECORD": TokenType.STRUCT, 261 "TIMESTAMP": TokenType.TIMESTAMPTZ, 262 "NOT DETERMINISTIC": TokenType.VOLATILE, 263 "UNKNOWN": TokenType.NULL, 264 } 265 KEYWORDS.pop("DIV") 266 267 class Parser(parser.Parser): 268 PREFIXED_PIVOT_COLUMNS = True 269 270 LOG_BASE_FIRST = False 271 LOG_DEFAULTS_TO_LN = True 272 273 SUPPORTS_USER_DEFINED_TYPES = False 274 275 FUNCTIONS = { 276 **parser.Parser.FUNCTIONS, 277 "DATE": _parse_date, 278 "DATE_ADD": parse_date_delta_with_interval(exp.DateAdd), 279 "DATE_SUB": parse_date_delta_with_interval(exp.DateSub), 280 "DATE_TRUNC": lambda args: exp.DateTrunc( 281 unit=exp.Literal.string(str(seq_get(args, 1))), 282 this=seq_get(args, 0), 283 ), 284 "DATETIME_ADD": parse_date_delta_with_interval(exp.DatetimeAdd), 285 "DATETIME_SUB": parse_date_delta_with_interval(exp.DatetimeSub), 286 "DIV": binary_from_function(exp.IntDiv), 287 "GENERATE_ARRAY": exp.GenerateSeries.from_arg_list, 288 "MD5": exp.MD5Digest.from_arg_list, 289 "TO_HEX": _parse_to_hex, 290 "PARSE_DATE": lambda args: format_time_lambda(exp.StrToDate, "bigquery")( 291 [seq_get(args, 1), seq_get(args, 0)] 292 ), 293 "PARSE_TIMESTAMP": _parse_timestamp, 294 "REGEXP_CONTAINS": exp.RegexpLike.from_arg_list, 295 "REGEXP_EXTRACT": lambda args: exp.RegexpExtract( 296 this=seq_get(args, 0), 297 expression=seq_get(args, 1), 298 position=seq_get(args, 2), 299 occurrence=seq_get(args, 3), 300 group=exp.Literal.number(1) 301 if re.compile(str(seq_get(args, 1))).groups == 1 302 else None, 303 ), 304 "SHA256": lambda args: exp.SHA2(this=seq_get(args, 0), length=exp.Literal.number(256)), 305 "SHA512": lambda args: exp.SHA2(this=seq_get(args, 0), length=exp.Literal.number(512)), 306 "SPLIT": lambda args: exp.Split( 307 # https://cloud.google.com/bigquery/docs/reference/standard-sql/string_functions#split 308 this=seq_get(args, 0), 309 expression=seq_get(args, 1) or exp.Literal.string(","), 310 ), 311 "TIME_ADD": parse_date_delta_with_interval(exp.TimeAdd), 312 "TIME_SUB": parse_date_delta_with_interval(exp.TimeSub), 313 "TIMESTAMP_ADD": parse_date_delta_with_interval(exp.TimestampAdd), 314 "TIMESTAMP_SUB": parse_date_delta_with_interval(exp.TimestampSub), 315 "TO_JSON_STRING": exp.JSONFormat.from_arg_list, 316 } 317 318 FUNCTION_PARSERS = { 319 **parser.Parser.FUNCTION_PARSERS, 320 "ARRAY": lambda self: self.expression(exp.Array, expressions=[self._parse_statement()]), 321 } 322 FUNCTION_PARSERS.pop("TRIM") 323 324 NO_PAREN_FUNCTIONS = { 325 **parser.Parser.NO_PAREN_FUNCTIONS, 326 TokenType.CURRENT_DATETIME: exp.CurrentDatetime, 327 } 328 329 NESTED_TYPE_TOKENS = { 330 *parser.Parser.NESTED_TYPE_TOKENS, 331 TokenType.TABLE, 332 } 333 334 ID_VAR_TOKENS = { 335 *parser.Parser.ID_VAR_TOKENS, 336 TokenType.VALUES, 337 } 338 339 PROPERTY_PARSERS = { 340 **parser.Parser.PROPERTY_PARSERS, 341 "NOT DETERMINISTIC": lambda self: self.expression( 342 exp.StabilityProperty, this=exp.Literal.string("VOLATILE") 343 ), 344 "OPTIONS": lambda self: self._parse_with_property(), 345 } 346 347 CONSTRAINT_PARSERS = { 348 **parser.Parser.CONSTRAINT_PARSERS, 349 "OPTIONS": lambda self: exp.Properties(expressions=self._parse_with_property()), 350 } 351 352 def _parse_table_part(self, schema: bool = False) -> t.Optional[exp.Expression]: 353 this = super()._parse_table_part(schema=schema) 354 355 # https://cloud.google.com/bigquery/docs/reference/standard-sql/lexical#table_names 356 if isinstance(this, exp.Identifier): 357 table_name = this.name 358 while self._match(TokenType.DASH, advance=False) and self._next: 359 self._advance(2) 360 table_name += f"-{self._prev.text}" 361 362 this = exp.Identifier(this=table_name, quoted=this.args.get("quoted")) 363 364 return this 365 366 def _parse_table_parts(self, schema: bool = False) -> exp.Table: 367 table = super()._parse_table_parts(schema=schema) 368 if isinstance(table.this, exp.Identifier) and "." in table.name: 369 catalog, db, this, *rest = ( 370 t.cast(t.Optional[exp.Expression], exp.to_identifier(x)) 371 for x in split_num_words(table.name, ".", 3) 372 ) 373 374 if rest and this: 375 this = exp.Dot.build(t.cast(t.List[exp.Expression], [this, *rest])) 376 377 table = exp.Table(this=this, db=db, catalog=catalog) 378 379 return table 380 381 class Generator(generator.Generator): 382 EXPLICIT_UNION = True 383 INTERVAL_ALLOWS_PLURAL_FORM = False 384 JOIN_HINTS = False 385 QUERY_HINTS = False 386 TABLE_HINTS = False 387 LIMIT_FETCH = "LIMIT" 388 RENAME_TABLE_WITH_DB = False 389 ESCAPE_LINE_BREAK = True 390 NVL2_SUPPORTED = False 391 392 TRANSFORMS = { 393 **generator.Generator.TRANSFORMS, 394 exp.ApproxDistinct: rename_func("APPROX_COUNT_DISTINCT"), 395 exp.ArraySize: rename_func("ARRAY_LENGTH"), 396 exp.Cast: transforms.preprocess([transforms.remove_precision_parameterized_types]), 397 exp.Create: _create_sql, 398 exp.CTE: transforms.preprocess([_pushdown_cte_column_names]), 399 exp.DateAdd: _date_add_sql("DATE", "ADD"), 400 exp.DateDiff: lambda self, e: f"DATE_DIFF({self.sql(e, 'this')}, {self.sql(e, 'expression')}, {self.sql(e.args.get('unit', 'DAY'))})", 401 exp.DateFromParts: rename_func("DATE"), 402 exp.DateStrToDate: datestrtodate_sql, 403 exp.DateSub: _date_add_sql("DATE", "SUB"), 404 exp.DatetimeAdd: _date_add_sql("DATETIME", "ADD"), 405 exp.DatetimeSub: _date_add_sql("DATETIME", "SUB"), 406 exp.DateTrunc: lambda self, e: self.func("DATE_TRUNC", e.this, e.text("unit")), 407 exp.GenerateSeries: rename_func("GENERATE_ARRAY"), 408 exp.GroupConcat: rename_func("STRING_AGG"), 409 exp.Hex: rename_func("TO_HEX"), 410 exp.ILike: no_ilike_sql, 411 exp.IntDiv: rename_func("DIV"), 412 exp.JSONFormat: rename_func("TO_JSON_STRING"), 413 exp.Max: max_or_greatest, 414 exp.MD5: lambda self, e: self.func("TO_HEX", self.func("MD5", e.this)), 415 exp.MD5Digest: rename_func("MD5"), 416 exp.Min: min_or_least, 417 exp.PartitionedByProperty: lambda self, e: f"PARTITION BY {self.sql(e, 'this')}", 418 exp.RegexpExtract: lambda self, e: self.func( 419 "REGEXP_EXTRACT", 420 e.this, 421 e.expression, 422 e.args.get("position"), 423 e.args.get("occurrence"), 424 ), 425 exp.RegexpReplace: regexp_replace_sql, 426 exp.RegexpLike: rename_func("REGEXP_CONTAINS"), 427 exp.ReturnsProperty: _returnsproperty_sql, 428 exp.Select: transforms.preprocess( 429 [ 430 transforms.explode_to_unnest, 431 _unqualify_unnest, 432 transforms.eliminate_distinct_on, 433 _alias_ordered_group, 434 ] 435 ), 436 exp.SHA2: lambda self, e: self.func( 437 f"SHA256" if e.text("length") == "256" else "SHA512", e.this 438 ), 439 exp.StabilityProperty: lambda self, e: f"DETERMINISTIC" 440 if e.name == "IMMUTABLE" 441 else "NOT DETERMINISTIC", 442 exp.StrToDate: lambda self, e: f"PARSE_DATE({self.format_time(e)}, {self.sql(e, 'this')})", 443 exp.StrToTime: lambda self, e: self.func( 444 "PARSE_TIMESTAMP", self.format_time(e), e.this, e.args.get("zone") 445 ), 446 exp.TimeAdd: _date_add_sql("TIME", "ADD"), 447 exp.TimeSub: _date_add_sql("TIME", "SUB"), 448 exp.TimestampAdd: _date_add_sql("TIMESTAMP", "ADD"), 449 exp.TimestampSub: _date_add_sql("TIMESTAMP", "SUB"), 450 exp.TimeStrToTime: timestrtotime_sql, 451 exp.Trim: lambda self, e: self.func(f"TRIM", e.this, e.expression), 452 exp.TsOrDsAdd: _date_add_sql("DATE", "ADD"), 453 exp.TsOrDsToDate: ts_or_ds_to_date_sql("bigquery"), 454 exp.Unhex: rename_func("FROM_HEX"), 455 exp.Values: _derived_table_values_to_unnest, 456 exp.VariancePop: rename_func("VAR_POP"), 457 } 458 459 TYPE_MAPPING = { 460 **generator.Generator.TYPE_MAPPING, 461 exp.DataType.Type.BIGDECIMAL: "BIGNUMERIC", 462 exp.DataType.Type.BIGINT: "INT64", 463 exp.DataType.Type.BINARY: "BYTES", 464 exp.DataType.Type.BOOLEAN: "BOOL", 465 exp.DataType.Type.CHAR: "STRING", 466 exp.DataType.Type.DECIMAL: "NUMERIC", 467 exp.DataType.Type.DOUBLE: "FLOAT64", 468 exp.DataType.Type.FLOAT: "FLOAT64", 469 exp.DataType.Type.INT: "INT64", 470 exp.DataType.Type.NCHAR: "STRING", 471 exp.DataType.Type.NVARCHAR: "STRING", 472 exp.DataType.Type.SMALLINT: "INT64", 473 exp.DataType.Type.TEXT: "STRING", 474 exp.DataType.Type.TIMESTAMP: "DATETIME", 475 exp.DataType.Type.TIMESTAMPTZ: "TIMESTAMP", 476 exp.DataType.Type.TIMESTAMPLTZ: "TIMESTAMP", 477 exp.DataType.Type.TINYINT: "INT64", 478 exp.DataType.Type.VARBINARY: "BYTES", 479 exp.DataType.Type.VARCHAR: "STRING", 480 exp.DataType.Type.VARIANT: "ANY TYPE", 481 } 482 483 PROPERTIES_LOCATION = { 484 **generator.Generator.PROPERTIES_LOCATION, 485 exp.PartitionedByProperty: exp.Properties.Location.POST_SCHEMA, 486 exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED, 487 } 488 489 # from: https://cloud.google.com/bigquery/docs/reference/standard-sql/lexical#reserved_keywords 490 RESERVED_KEYWORDS = { 491 *generator.Generator.RESERVED_KEYWORDS, 492 "all", 493 "and", 494 "any", 495 "array", 496 "as", 497 "asc", 498 "assert_rows_modified", 499 "at", 500 "between", 501 "by", 502 "case", 503 "cast", 504 "collate", 505 "contains", 506 "create", 507 "cross", 508 "cube", 509 "current", 510 "default", 511 "define", 512 "desc", 513 "distinct", 514 "else", 515 "end", 516 "enum", 517 "escape", 518 "except", 519 "exclude", 520 "exists", 521 "extract", 522 "false", 523 "fetch", 524 "following", 525 "for", 526 "from", 527 "full", 528 "group", 529 "grouping", 530 "groups", 531 "hash", 532 "having", 533 "if", 534 "ignore", 535 "in", 536 "inner", 537 "intersect", 538 "interval", 539 "into", 540 "is", 541 "join", 542 "lateral", 543 "left", 544 "like", 545 "limit", 546 "lookup", 547 "merge", 548 "natural", 549 "new", 550 "no", 551 "not", 552 "null", 553 "nulls", 554 "of", 555 "on", 556 "or", 557 "order", 558 "outer", 559 "over", 560 "partition", 561 "preceding", 562 "proto", 563 "qualify", 564 "range", 565 "recursive", 566 "respect", 567 "right", 568 "rollup", 569 "rows", 570 "select", 571 "set", 572 "some", 573 "struct", 574 "tablesample", 575 "then", 576 "to", 577 "treat", 578 "true", 579 "unbounded", 580 "union", 581 "unnest", 582 "using", 583 "when", 584 "where", 585 "window", 586 "with", 587 "within", 588 } 589 590 def attimezone_sql(self, expression: exp.AtTimeZone) -> str: 591 parent = expression.parent 592 593 # BigQuery allows CAST(.. AS {STRING|TIMESTAMP} [FORMAT <fmt> [AT TIME ZONE <tz>]]). 594 # Only the TIMESTAMP one should use the below conversion, when AT TIME ZONE is included. 595 if not isinstance(parent, exp.Cast) or not parent.to.is_type("text"): 596 return self.func( 597 "TIMESTAMP", self.func("DATETIME", expression.this, expression.args.get("zone")) 598 ) 599 600 return super().attimezone_sql(expression) 601 602 def trycast_sql(self, expression: exp.TryCast) -> str: 603 return self.cast_sql(expression, safe_prefix="SAFE_") 604 605 def cte_sql(self, expression: exp.CTE) -> str: 606 if expression.alias_column_names: 607 self.unsupported("Column names in CTE definition are not supported.") 608 return super().cte_sql(expression) 609 610 def array_sql(self, expression: exp.Array) -> str: 611 first_arg = seq_get(expression.expressions, 0) 612 if isinstance(first_arg, exp.Subqueryable): 613 return f"ARRAY{self.wrap(self.sql(first_arg))}" 614 615 return inline_array_sql(self, expression) 616 617 def transaction_sql(self, *_) -> str: 618 return "BEGIN TRANSACTION" 619 620 def commit_sql(self, *_) -> str: 621 return "COMMIT TRANSACTION" 622 623 def rollback_sql(self, *_) -> str: 624 return "ROLLBACK TRANSACTION" 625 626 def in_unnest_op(self, expression: exp.Unnest) -> str: 627 return self.sql(expression) 628 629 def except_op(self, expression: exp.Except) -> str: 630 if not expression.args.get("distinct", False): 631 self.unsupported("EXCEPT without DISTINCT is not supported in BigQuery") 632 return f"EXCEPT{' DISTINCT' if expression.args.get('distinct') else ' ALL'}" 633 634 def intersect_op(self, expression: exp.Intersect) -> str: 635 if not expression.args.get("distinct", False): 636 self.unsupported("INTERSECT without DISTINCT is not supported in BigQuery") 637 return f"INTERSECT{' DISTINCT' if expression.args.get('distinct') else ' ALL'}" 638 639 def with_properties(self, properties: exp.Properties) -> str: 640 return self.properties(properties, prefix=self.seg("OPTIONS"))
logger =
<Logger sqlglot (WARNING)>
182class BigQuery(Dialect): 183 UNNEST_COLUMN_ONLY = True 184 185 # https://cloud.google.com/bigquery/docs/reference/standard-sql/lexical#case_sensitivity 186 RESOLVES_IDENTIFIERS_AS_UPPERCASE = None 187 188 # bigquery udfs are case sensitive 189 NORMALIZE_FUNCTIONS = False 190 191 TIME_MAPPING = { 192 "%D": "%m/%d/%y", 193 } 194 195 FORMAT_MAPPING = { 196 "DD": "%d", 197 "MM": "%m", 198 "MON": "%b", 199 "MONTH": "%B", 200 "YYYY": "%Y", 201 "YY": "%y", 202 "HH": "%I", 203 "HH12": "%I", 204 "HH24": "%H", 205 "MI": "%M", 206 "SS": "%S", 207 "SSSSS": "%f", 208 "TZH": "%z", 209 } 210 211 # The _PARTITIONTIME and _PARTITIONDATE pseudo-columns are not returned by a SELECT * statement 212 # https://cloud.google.com/bigquery/docs/querying-partitioned-tables#query_an_ingestion-time_partitioned_table 213 PSEUDOCOLUMNS = {"_PARTITIONTIME", "_PARTITIONDATE"} 214 215 @classmethod 216 def normalize_identifier(cls, expression: E) -> E: 217 # In BigQuery, CTEs aren't case-sensitive, but table names are (by default, at least). 218 # The following check is essentially a heuristic to detect tables based on whether or 219 # not they're qualified. 220 if isinstance(expression, exp.Identifier): 221 parent = expression.parent 222 223 while isinstance(parent, exp.Dot): 224 parent = parent.parent 225 226 if ( 227 not isinstance(parent, exp.UserDefinedFunction) 228 and not (isinstance(parent, exp.Table) and parent.db) 229 and not expression.meta.get("is_table") 230 ): 231 expression.set("this", expression.this.lower()) 232 233 return expression 234 235 class Tokenizer(tokens.Tokenizer): 236 QUOTES = ["'", '"', '"""', "'''"] 237 COMMENTS = ["--", "#", ("/*", "*/")] 238 IDENTIFIERS = ["`"] 239 STRING_ESCAPES = ["\\"] 240 241 HEX_STRINGS = [("0x", ""), ("0X", "")] 242 243 BYTE_STRINGS = [ 244 (prefix + q, q) for q in t.cast(t.List[str], QUOTES) for prefix in ("b", "B") 245 ] 246 247 RAW_STRINGS = [ 248 (prefix + q, q) for q in t.cast(t.List[str], QUOTES) for prefix in ("r", "R") 249 ] 250 251 KEYWORDS = { 252 **tokens.Tokenizer.KEYWORDS, 253 "ANY TYPE": TokenType.VARIANT, 254 "BEGIN": TokenType.COMMAND, 255 "BEGIN TRANSACTION": TokenType.BEGIN, 256 "CURRENT_DATETIME": TokenType.CURRENT_DATETIME, 257 "BYTES": TokenType.BINARY, 258 "DECLARE": TokenType.COMMAND, 259 "FLOAT64": TokenType.DOUBLE, 260 "INT64": TokenType.BIGINT, 261 "RECORD": TokenType.STRUCT, 262 "TIMESTAMP": TokenType.TIMESTAMPTZ, 263 "NOT DETERMINISTIC": TokenType.VOLATILE, 264 "UNKNOWN": TokenType.NULL, 265 } 266 KEYWORDS.pop("DIV") 267 268 class Parser(parser.Parser): 269 PREFIXED_PIVOT_COLUMNS = True 270 271 LOG_BASE_FIRST = False 272 LOG_DEFAULTS_TO_LN = True 273 274 SUPPORTS_USER_DEFINED_TYPES = False 275 276 FUNCTIONS = { 277 **parser.Parser.FUNCTIONS, 278 "DATE": _parse_date, 279 "DATE_ADD": parse_date_delta_with_interval(exp.DateAdd), 280 "DATE_SUB": parse_date_delta_with_interval(exp.DateSub), 281 "DATE_TRUNC": lambda args: exp.DateTrunc( 282 unit=exp.Literal.string(str(seq_get(args, 1))), 283 this=seq_get(args, 0), 284 ), 285 "DATETIME_ADD": parse_date_delta_with_interval(exp.DatetimeAdd), 286 "DATETIME_SUB": parse_date_delta_with_interval(exp.DatetimeSub), 287 "DIV": binary_from_function(exp.IntDiv), 288 "GENERATE_ARRAY": exp.GenerateSeries.from_arg_list, 289 "MD5": exp.MD5Digest.from_arg_list, 290 "TO_HEX": _parse_to_hex, 291 "PARSE_DATE": lambda args: format_time_lambda(exp.StrToDate, "bigquery")( 292 [seq_get(args, 1), seq_get(args, 0)] 293 ), 294 "PARSE_TIMESTAMP": _parse_timestamp, 295 "REGEXP_CONTAINS": exp.RegexpLike.from_arg_list, 296 "REGEXP_EXTRACT": lambda args: exp.RegexpExtract( 297 this=seq_get(args, 0), 298 expression=seq_get(args, 1), 299 position=seq_get(args, 2), 300 occurrence=seq_get(args, 3), 301 group=exp.Literal.number(1) 302 if re.compile(str(seq_get(args, 1))).groups == 1 303 else None, 304 ), 305 "SHA256": lambda args: exp.SHA2(this=seq_get(args, 0), length=exp.Literal.number(256)), 306 "SHA512": lambda args: exp.SHA2(this=seq_get(args, 0), length=exp.Literal.number(512)), 307 "SPLIT": lambda args: exp.Split( 308 # https://cloud.google.com/bigquery/docs/reference/standard-sql/string_functions#split 309 this=seq_get(args, 0), 310 expression=seq_get(args, 1) or exp.Literal.string(","), 311 ), 312 "TIME_ADD": parse_date_delta_with_interval(exp.TimeAdd), 313 "TIME_SUB": parse_date_delta_with_interval(exp.TimeSub), 314 "TIMESTAMP_ADD": parse_date_delta_with_interval(exp.TimestampAdd), 315 "TIMESTAMP_SUB": parse_date_delta_with_interval(exp.TimestampSub), 316 "TO_JSON_STRING": exp.JSONFormat.from_arg_list, 317 } 318 319 FUNCTION_PARSERS = { 320 **parser.Parser.FUNCTION_PARSERS, 321 "ARRAY": lambda self: self.expression(exp.Array, expressions=[self._parse_statement()]), 322 } 323 FUNCTION_PARSERS.pop("TRIM") 324 325 NO_PAREN_FUNCTIONS = { 326 **parser.Parser.NO_PAREN_FUNCTIONS, 327 TokenType.CURRENT_DATETIME: exp.CurrentDatetime, 328 } 329 330 NESTED_TYPE_TOKENS = { 331 *parser.Parser.NESTED_TYPE_TOKENS, 332 TokenType.TABLE, 333 } 334 335 ID_VAR_TOKENS = { 336 *parser.Parser.ID_VAR_TOKENS, 337 TokenType.VALUES, 338 } 339 340 PROPERTY_PARSERS = { 341 **parser.Parser.PROPERTY_PARSERS, 342 "NOT DETERMINISTIC": lambda self: self.expression( 343 exp.StabilityProperty, this=exp.Literal.string("VOLATILE") 344 ), 345 "OPTIONS": lambda self: self._parse_with_property(), 346 } 347 348 CONSTRAINT_PARSERS = { 349 **parser.Parser.CONSTRAINT_PARSERS, 350 "OPTIONS": lambda self: exp.Properties(expressions=self._parse_with_property()), 351 } 352 353 def _parse_table_part(self, schema: bool = False) -> t.Optional[exp.Expression]: 354 this = super()._parse_table_part(schema=schema) 355 356 # https://cloud.google.com/bigquery/docs/reference/standard-sql/lexical#table_names 357 if isinstance(this, exp.Identifier): 358 table_name = this.name 359 while self._match(TokenType.DASH, advance=False) and self._next: 360 self._advance(2) 361 table_name += f"-{self._prev.text}" 362 363 this = exp.Identifier(this=table_name, quoted=this.args.get("quoted")) 364 365 return this 366 367 def _parse_table_parts(self, schema: bool = False) -> exp.Table: 368 table = super()._parse_table_parts(schema=schema) 369 if isinstance(table.this, exp.Identifier) and "." in table.name: 370 catalog, db, this, *rest = ( 371 t.cast(t.Optional[exp.Expression], exp.to_identifier(x)) 372 for x in split_num_words(table.name, ".", 3) 373 ) 374 375 if rest and this: 376 this = exp.Dot.build(t.cast(t.List[exp.Expression], [this, *rest])) 377 378 table = exp.Table(this=this, db=db, catalog=catalog) 379 380 return table 381 382 class Generator(generator.Generator): 383 EXPLICIT_UNION = True 384 INTERVAL_ALLOWS_PLURAL_FORM = False 385 JOIN_HINTS = False 386 QUERY_HINTS = False 387 TABLE_HINTS = False 388 LIMIT_FETCH = "LIMIT" 389 RENAME_TABLE_WITH_DB = False 390 ESCAPE_LINE_BREAK = True 391 NVL2_SUPPORTED = False 392 393 TRANSFORMS = { 394 **generator.Generator.TRANSFORMS, 395 exp.ApproxDistinct: rename_func("APPROX_COUNT_DISTINCT"), 396 exp.ArraySize: rename_func("ARRAY_LENGTH"), 397 exp.Cast: transforms.preprocess([transforms.remove_precision_parameterized_types]), 398 exp.Create: _create_sql, 399 exp.CTE: transforms.preprocess([_pushdown_cte_column_names]), 400 exp.DateAdd: _date_add_sql("DATE", "ADD"), 401 exp.DateDiff: lambda self, e: f"DATE_DIFF({self.sql(e, 'this')}, {self.sql(e, 'expression')}, {self.sql(e.args.get('unit', 'DAY'))})", 402 exp.DateFromParts: rename_func("DATE"), 403 exp.DateStrToDate: datestrtodate_sql, 404 exp.DateSub: _date_add_sql("DATE", "SUB"), 405 exp.DatetimeAdd: _date_add_sql("DATETIME", "ADD"), 406 exp.DatetimeSub: _date_add_sql("DATETIME", "SUB"), 407 exp.DateTrunc: lambda self, e: self.func("DATE_TRUNC", e.this, e.text("unit")), 408 exp.GenerateSeries: rename_func("GENERATE_ARRAY"), 409 exp.GroupConcat: rename_func("STRING_AGG"), 410 exp.Hex: rename_func("TO_HEX"), 411 exp.ILike: no_ilike_sql, 412 exp.IntDiv: rename_func("DIV"), 413 exp.JSONFormat: rename_func("TO_JSON_STRING"), 414 exp.Max: max_or_greatest, 415 exp.MD5: lambda self, e: self.func("TO_HEX", self.func("MD5", e.this)), 416 exp.MD5Digest: rename_func("MD5"), 417 exp.Min: min_or_least, 418 exp.PartitionedByProperty: lambda self, e: f"PARTITION BY {self.sql(e, 'this')}", 419 exp.RegexpExtract: lambda self, e: self.func( 420 "REGEXP_EXTRACT", 421 e.this, 422 e.expression, 423 e.args.get("position"), 424 e.args.get("occurrence"), 425 ), 426 exp.RegexpReplace: regexp_replace_sql, 427 exp.RegexpLike: rename_func("REGEXP_CONTAINS"), 428 exp.ReturnsProperty: _returnsproperty_sql, 429 exp.Select: transforms.preprocess( 430 [ 431 transforms.explode_to_unnest, 432 _unqualify_unnest, 433 transforms.eliminate_distinct_on, 434 _alias_ordered_group, 435 ] 436 ), 437 exp.SHA2: lambda self, e: self.func( 438 f"SHA256" if e.text("length") == "256" else "SHA512", e.this 439 ), 440 exp.StabilityProperty: lambda self, e: f"DETERMINISTIC" 441 if e.name == "IMMUTABLE" 442 else "NOT DETERMINISTIC", 443 exp.StrToDate: lambda self, e: f"PARSE_DATE({self.format_time(e)}, {self.sql(e, 'this')})", 444 exp.StrToTime: lambda self, e: self.func( 445 "PARSE_TIMESTAMP", self.format_time(e), e.this, e.args.get("zone") 446 ), 447 exp.TimeAdd: _date_add_sql("TIME", "ADD"), 448 exp.TimeSub: _date_add_sql("TIME", "SUB"), 449 exp.TimestampAdd: _date_add_sql("TIMESTAMP", "ADD"), 450 exp.TimestampSub: _date_add_sql("TIMESTAMP", "SUB"), 451 exp.TimeStrToTime: timestrtotime_sql, 452 exp.Trim: lambda self, e: self.func(f"TRIM", e.this, e.expression), 453 exp.TsOrDsAdd: _date_add_sql("DATE", "ADD"), 454 exp.TsOrDsToDate: ts_or_ds_to_date_sql("bigquery"), 455 exp.Unhex: rename_func("FROM_HEX"), 456 exp.Values: _derived_table_values_to_unnest, 457 exp.VariancePop: rename_func("VAR_POP"), 458 } 459 460 TYPE_MAPPING = { 461 **generator.Generator.TYPE_MAPPING, 462 exp.DataType.Type.BIGDECIMAL: "BIGNUMERIC", 463 exp.DataType.Type.BIGINT: "INT64", 464 exp.DataType.Type.BINARY: "BYTES", 465 exp.DataType.Type.BOOLEAN: "BOOL", 466 exp.DataType.Type.CHAR: "STRING", 467 exp.DataType.Type.DECIMAL: "NUMERIC", 468 exp.DataType.Type.DOUBLE: "FLOAT64", 469 exp.DataType.Type.FLOAT: "FLOAT64", 470 exp.DataType.Type.INT: "INT64", 471 exp.DataType.Type.NCHAR: "STRING", 472 exp.DataType.Type.NVARCHAR: "STRING", 473 exp.DataType.Type.SMALLINT: "INT64", 474 exp.DataType.Type.TEXT: "STRING", 475 exp.DataType.Type.TIMESTAMP: "DATETIME", 476 exp.DataType.Type.TIMESTAMPTZ: "TIMESTAMP", 477 exp.DataType.Type.TIMESTAMPLTZ: "TIMESTAMP", 478 exp.DataType.Type.TINYINT: "INT64", 479 exp.DataType.Type.VARBINARY: "BYTES", 480 exp.DataType.Type.VARCHAR: "STRING", 481 exp.DataType.Type.VARIANT: "ANY TYPE", 482 } 483 484 PROPERTIES_LOCATION = { 485 **generator.Generator.PROPERTIES_LOCATION, 486 exp.PartitionedByProperty: exp.Properties.Location.POST_SCHEMA, 487 exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED, 488 } 489 490 # from: https://cloud.google.com/bigquery/docs/reference/standard-sql/lexical#reserved_keywords 491 RESERVED_KEYWORDS = { 492 *generator.Generator.RESERVED_KEYWORDS, 493 "all", 494 "and", 495 "any", 496 "array", 497 "as", 498 "asc", 499 "assert_rows_modified", 500 "at", 501 "between", 502 "by", 503 "case", 504 "cast", 505 "collate", 506 "contains", 507 "create", 508 "cross", 509 "cube", 510 "current", 511 "default", 512 "define", 513 "desc", 514 "distinct", 515 "else", 516 "end", 517 "enum", 518 "escape", 519 "except", 520 "exclude", 521 "exists", 522 "extract", 523 "false", 524 "fetch", 525 "following", 526 "for", 527 "from", 528 "full", 529 "group", 530 "grouping", 531 "groups", 532 "hash", 533 "having", 534 "if", 535 "ignore", 536 "in", 537 "inner", 538 "intersect", 539 "interval", 540 "into", 541 "is", 542 "join", 543 "lateral", 544 "left", 545 "like", 546 "limit", 547 "lookup", 548 "merge", 549 "natural", 550 "new", 551 "no", 552 "not", 553 "null", 554 "nulls", 555 "of", 556 "on", 557 "or", 558 "order", 559 "outer", 560 "over", 561 "partition", 562 "preceding", 563 "proto", 564 "qualify", 565 "range", 566 "recursive", 567 "respect", 568 "right", 569 "rollup", 570 "rows", 571 "select", 572 "set", 573 "some", 574 "struct", 575 "tablesample", 576 "then", 577 "to", 578 "treat", 579 "true", 580 "unbounded", 581 "union", 582 "unnest", 583 "using", 584 "when", 585 "where", 586 "window", 587 "with", 588 "within", 589 } 590 591 def attimezone_sql(self, expression: exp.AtTimeZone) -> str: 592 parent = expression.parent 593 594 # BigQuery allows CAST(.. AS {STRING|TIMESTAMP} [FORMAT <fmt> [AT TIME ZONE <tz>]]). 595 # Only the TIMESTAMP one should use the below conversion, when AT TIME ZONE is included. 596 if not isinstance(parent, exp.Cast) or not parent.to.is_type("text"): 597 return self.func( 598 "TIMESTAMP", self.func("DATETIME", expression.this, expression.args.get("zone")) 599 ) 600 601 return super().attimezone_sql(expression) 602 603 def trycast_sql(self, expression: exp.TryCast) -> str: 604 return self.cast_sql(expression, safe_prefix="SAFE_") 605 606 def cte_sql(self, expression: exp.CTE) -> str: 607 if expression.alias_column_names: 608 self.unsupported("Column names in CTE definition are not supported.") 609 return super().cte_sql(expression) 610 611 def array_sql(self, expression: exp.Array) -> str: 612 first_arg = seq_get(expression.expressions, 0) 613 if isinstance(first_arg, exp.Subqueryable): 614 return f"ARRAY{self.wrap(self.sql(first_arg))}" 615 616 return inline_array_sql(self, expression) 617 618 def transaction_sql(self, *_) -> str: 619 return "BEGIN TRANSACTION" 620 621 def commit_sql(self, *_) -> str: 622 return "COMMIT TRANSACTION" 623 624 def rollback_sql(self, *_) -> str: 625 return "ROLLBACK TRANSACTION" 626 627 def in_unnest_op(self, expression: exp.Unnest) -> str: 628 return self.sql(expression) 629 630 def except_op(self, expression: exp.Except) -> str: 631 if not expression.args.get("distinct", False): 632 self.unsupported("EXCEPT without DISTINCT is not supported in BigQuery") 633 return f"EXCEPT{' DISTINCT' if expression.args.get('distinct') else ' ALL'}" 634 635 def intersect_op(self, expression: exp.Intersect) -> str: 636 if not expression.args.get("distinct", False): 637 self.unsupported("INTERSECT without DISTINCT is not supported in BigQuery") 638 return f"INTERSECT{' DISTINCT' if expression.args.get('distinct') else ' ALL'}" 639 640 def with_properties(self, properties: exp.Properties) -> str: 641 return self.properties(properties, prefix=self.seg("OPTIONS"))
FORMAT_MAPPING: Dict[str, str] =
{'DD': '%d', 'MM': '%m', 'MON': '%b', 'MONTH': '%B', 'YYYY': '%Y', 'YY': '%y', 'HH': '%I', 'HH12': '%I', 'HH24': '%H', 'MI': '%M', 'SS': '%S', 'SSSSS': '%f', 'TZH': '%z'}
@classmethod
def
normalize_identifier(cls, expression: ~E) -> ~E:
215 @classmethod 216 def normalize_identifier(cls, expression: E) -> E: 217 # In BigQuery, CTEs aren't case-sensitive, but table names are (by default, at least). 218 # The following check is essentially a heuristic to detect tables based on whether or 219 # not they're qualified. 220 if isinstance(expression, exp.Identifier): 221 parent = expression.parent 222 223 while isinstance(parent, exp.Dot): 224 parent = parent.parent 225 226 if ( 227 not isinstance(parent, exp.UserDefinedFunction) 228 and not (isinstance(parent, exp.Table) and parent.db) 229 and not expression.meta.get("is_table") 230 ): 231 expression.set("this", expression.this.lower()) 232 233 return expression
Normalizes an unquoted identifier to either lower or upper case, thus essentially making it case-insensitive. If a dialect treats all identifiers as case-insensitive, they will be normalized regardless of being quoted or not.
tokenizer_class =
<class 'sqlglot.dialects.bigquery.BigQuery.Tokenizer'>
parser_class =
<class 'sqlglot.dialects.bigquery.BigQuery.Parser'>
generator_class =
<class 'sqlglot.dialects.bigquery.BigQuery.Generator'>
FORMAT_TRIE: Dict =
{'D': {'D': {0: True}}, 'M': {'M': {0: True}, 'O': {'N': {0: True, 'T': {'H': {0: True}}}}, 'I': {0: True}}, 'Y': {'Y': {'Y': {'Y': {0: True}}, 0: True}}, 'H': {'H': {0: True, '1': {'2': {0: True}}, '2': {'4': {0: True}}}}, 'S': {'S': {0: True, 'S': {'S': {'S': {0: True}}}}}, 'T': {'Z': {'H': {0: True}}}}
Inherited Members
- sqlglot.dialects.dialect.Dialect
- INDEX_OFFSET
- ALIAS_POST_TABLESAMPLE
- IDENTIFIERS_CAN_START_WITH_DIGIT
- DPIPE_IS_STRING_CONCAT
- STRICT_STRING_CONCAT
- NULL_ORDERING
- DATE_FORMAT
- DATEINT_FORMAT
- TIME_FORMAT
- get_or_raise
- format_time
- case_sensitive
- can_identify
- quote_identifier
- parse
- parse_into
- generate
- transpile
- tokenize
- tokenizer
- parser
- generator
235 class Tokenizer(tokens.Tokenizer): 236 QUOTES = ["'", '"', '"""', "'''"] 237 COMMENTS = ["--", "#", ("/*", "*/")] 238 IDENTIFIERS = ["`"] 239 STRING_ESCAPES = ["\\"] 240 241 HEX_STRINGS = [("0x", ""), ("0X", "")] 242 243 BYTE_STRINGS = [ 244 (prefix + q, q) for q in t.cast(t.List[str], QUOTES) for prefix in ("b", "B") 245 ] 246 247 RAW_STRINGS = [ 248 (prefix + q, q) for q in t.cast(t.List[str], QUOTES) for prefix in ("r", "R") 249 ] 250 251 KEYWORDS = { 252 **tokens.Tokenizer.KEYWORDS, 253 "ANY TYPE": TokenType.VARIANT, 254 "BEGIN": TokenType.COMMAND, 255 "BEGIN TRANSACTION": TokenType.BEGIN, 256 "CURRENT_DATETIME": TokenType.CURRENT_DATETIME, 257 "BYTES": TokenType.BINARY, 258 "DECLARE": TokenType.COMMAND, 259 "FLOAT64": TokenType.DOUBLE, 260 "INT64": TokenType.BIGINT, 261 "RECORD": TokenType.STRUCT, 262 "TIMESTAMP": TokenType.TIMESTAMPTZ, 263 "NOT DETERMINISTIC": TokenType.VOLATILE, 264 "UNKNOWN": TokenType.NULL, 265 } 266 KEYWORDS.pop("DIV")
BYTE_STRINGS =
[("b'", "'"), ("B'", "'"), ('b"', '"'), ('B"', '"'), ('b"""', '"""'), ('B"""', '"""'), ("b'''", "'''"), ("B'''", "'''")]
RAW_STRINGS =
[("r'", "'"), ("R'", "'"), ('r"', '"'), ('R"', '"'), ('r"""', '"""'), ('R"""', '"""'), ("r'''", "'''"), ("R'''", "'''")]
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'>, '??': <TokenType.DQMARK: 'DQMARK'>, '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.COMMAND: 'COMMAND'>, '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'>, 'CONNECT BY': <TokenType.CONNECT_BY: 'CONNECT_BY'>, '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'>, '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'>, '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'>, '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'>, 'START WITH': <TokenType.START_WITH: 'START_WITH'>, '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'>, 'UNKNOWN': <TokenType.NULL: 'NULL'>, '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'>, 'INT128': <TokenType.INT128: 'INT128'>, '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.BIGINT: 'BIGINT'>, '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'>, 'TIMETZ': <TokenType.TIMETZ: 'TIMETZ'>, 'TIMESTAMP': <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>, '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'>, 'ANY TYPE': <TokenType.VARIANT: 'VARIANT'>, 'BEGIN TRANSACTION': <TokenType.BEGIN: 'BEGIN'>, 'CURRENT_DATETIME': <TokenType.CURRENT_DATETIME: 'CURRENT_DATETIME'>, 'BYTES': <TokenType.BINARY: 'BINARY'>, 'DECLARE': <TokenType.COMMAND: 'COMMAND'>, 'FLOAT64': <TokenType.DOUBLE: 'DOUBLE'>, 'INT64': <TokenType.BIGINT: 'BIGINT'>, 'RECORD': <TokenType.STRUCT: 'STRUCT'>, 'NOT DETERMINISTIC': <TokenType.VOLATILE: 'VOLATILE'>}
268 class Parser(parser.Parser): 269 PREFIXED_PIVOT_COLUMNS = True 270 271 LOG_BASE_FIRST = False 272 LOG_DEFAULTS_TO_LN = True 273 274 SUPPORTS_USER_DEFINED_TYPES = False 275 276 FUNCTIONS = { 277 **parser.Parser.FUNCTIONS, 278 "DATE": _parse_date, 279 "DATE_ADD": parse_date_delta_with_interval(exp.DateAdd), 280 "DATE_SUB": parse_date_delta_with_interval(exp.DateSub), 281 "DATE_TRUNC": lambda args: exp.DateTrunc( 282 unit=exp.Literal.string(str(seq_get(args, 1))), 283 this=seq_get(args, 0), 284 ), 285 "DATETIME_ADD": parse_date_delta_with_interval(exp.DatetimeAdd), 286 "DATETIME_SUB": parse_date_delta_with_interval(exp.DatetimeSub), 287 "DIV": binary_from_function(exp.IntDiv), 288 "GENERATE_ARRAY": exp.GenerateSeries.from_arg_list, 289 "MD5": exp.MD5Digest.from_arg_list, 290 "TO_HEX": _parse_to_hex, 291 "PARSE_DATE": lambda args: format_time_lambda(exp.StrToDate, "bigquery")( 292 [seq_get(args, 1), seq_get(args, 0)] 293 ), 294 "PARSE_TIMESTAMP": _parse_timestamp, 295 "REGEXP_CONTAINS": exp.RegexpLike.from_arg_list, 296 "REGEXP_EXTRACT": lambda args: exp.RegexpExtract( 297 this=seq_get(args, 0), 298 expression=seq_get(args, 1), 299 position=seq_get(args, 2), 300 occurrence=seq_get(args, 3), 301 group=exp.Literal.number(1) 302 if re.compile(str(seq_get(args, 1))).groups == 1 303 else None, 304 ), 305 "SHA256": lambda args: exp.SHA2(this=seq_get(args, 0), length=exp.Literal.number(256)), 306 "SHA512": lambda args: exp.SHA2(this=seq_get(args, 0), length=exp.Literal.number(512)), 307 "SPLIT": lambda args: exp.Split( 308 # https://cloud.google.com/bigquery/docs/reference/standard-sql/string_functions#split 309 this=seq_get(args, 0), 310 expression=seq_get(args, 1) or exp.Literal.string(","), 311 ), 312 "TIME_ADD": parse_date_delta_with_interval(exp.TimeAdd), 313 "TIME_SUB": parse_date_delta_with_interval(exp.TimeSub), 314 "TIMESTAMP_ADD": parse_date_delta_with_interval(exp.TimestampAdd), 315 "TIMESTAMP_SUB": parse_date_delta_with_interval(exp.TimestampSub), 316 "TO_JSON_STRING": exp.JSONFormat.from_arg_list, 317 } 318 319 FUNCTION_PARSERS = { 320 **parser.Parser.FUNCTION_PARSERS, 321 "ARRAY": lambda self: self.expression(exp.Array, expressions=[self._parse_statement()]), 322 } 323 FUNCTION_PARSERS.pop("TRIM") 324 325 NO_PAREN_FUNCTIONS = { 326 **parser.Parser.NO_PAREN_FUNCTIONS, 327 TokenType.CURRENT_DATETIME: exp.CurrentDatetime, 328 } 329 330 NESTED_TYPE_TOKENS = { 331 *parser.Parser.NESTED_TYPE_TOKENS, 332 TokenType.TABLE, 333 } 334 335 ID_VAR_TOKENS = { 336 *parser.Parser.ID_VAR_TOKENS, 337 TokenType.VALUES, 338 } 339 340 PROPERTY_PARSERS = { 341 **parser.Parser.PROPERTY_PARSERS, 342 "NOT DETERMINISTIC": lambda self: self.expression( 343 exp.StabilityProperty, this=exp.Literal.string("VOLATILE") 344 ), 345 "OPTIONS": lambda self: self._parse_with_property(), 346 } 347 348 CONSTRAINT_PARSERS = { 349 **parser.Parser.CONSTRAINT_PARSERS, 350 "OPTIONS": lambda self: exp.Properties(expressions=self._parse_with_property()), 351 } 352 353 def _parse_table_part(self, schema: bool = False) -> t.Optional[exp.Expression]: 354 this = super()._parse_table_part(schema=schema) 355 356 # https://cloud.google.com/bigquery/docs/reference/standard-sql/lexical#table_names 357 if isinstance(this, exp.Identifier): 358 table_name = this.name 359 while self._match(TokenType.DASH, advance=False) and self._next: 360 self._advance(2) 361 table_name += f"-{self._prev.text}" 362 363 this = exp.Identifier(this=table_name, quoted=this.args.get("quoted")) 364 365 return this 366 367 def _parse_table_parts(self, schema: bool = False) -> exp.Table: 368 table = super()._parse_table_parts(schema=schema) 369 if isinstance(table.this, exp.Identifier) and "." in table.name: 370 catalog, db, this, *rest = ( 371 t.cast(t.Optional[exp.Expression], exp.to_identifier(x)) 372 for x in split_num_words(table.name, ".", 3) 373 ) 374 375 if rest and this: 376 this = exp.Dot.build(t.cast(t.List[exp.Expression], [this, *rest])) 377 378 table = exp.Table(this=this, db=db, catalog=catalog) 379 380 return table
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_CAT': <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': <function _parse_date>, 'DATE_ADD': <function parse_date_delta_with_interval.<locals>.func>, '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': <function parse_date_delta_with_interval.<locals>.func>, 'DATE_TO_DATE_STR': <function Parser.<lambda>>, 'DATE_TO_DI': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateToDi'>>, 'DATE_TRUNC': <function BigQuery.Parser.<lambda>>, 'DATETIME_ADD': <function parse_date_delta_with_interval.<locals>.func>, 'DATETIME_DIFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DatetimeDiff'>>, 'DATETIME_SUB': <function parse_date_delta_with_interval.<locals>.func>, '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'>>, 'FIRST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.First'>>, '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'>>, 'IS_NAN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.IsNan'>>, 'ISNAN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.IsNan'>>, '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': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Last'>>, '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.MD5Digest'>>, 'MD5_DIGEST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.MD5Digest'>>, 'MAP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.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': <function BigQuery.Parser.<lambda>>, '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': <function BigQuery.Parser.<lambda>>, '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'>>, 'STARTS_WITH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StartsWith'>>, 'STARTSWITH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StartsWith'>>, '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_MAP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StrToMap'>>, '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'>>, 'STUFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Stuff'>>, 'INSERT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Stuff'>>, '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': <function parse_date_delta_with_interval.<locals>.func>, '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': <function parse_date_delta_with_interval.<locals>.func>, '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': <function parse_date_delta_with_interval.<locals>.func>, 'TIMESTAMP_DIFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimestampDiff'>>, 'TIMESTAMP_SUB': <function parse_date_delta_with_interval.<locals>.func>, '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'>>, 'TRANSFORM': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Transform'>>, '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'>>, 'XOR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Xor'>>, 'YEAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Year'>>, 'GLOB': <function Parser.<lambda>>, 'LIKE': <function parse_like>, 'DIV': <function binary_from_function.<locals>.<lambda>>, 'GENERATE_ARRAY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.GenerateSeries'>>, 'TO_HEX': <function _parse_to_hex>, 'PARSE_DATE': <function BigQuery.Parser.<lambda>>, 'PARSE_TIMESTAMP': <function _parse_timestamp>, 'REGEXP_CONTAINS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RegexpLike'>>, 'SHA256': <function BigQuery.Parser.<lambda>>, 'SHA512': <function BigQuery.Parser.<lambda>>, 'TO_JSON_STRING': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONFormat'>>}
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>>, 'MATCH': <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>>, 'TRY_CAST': <function Parser.<lambda>>, 'TRY_CONVERT': <function Parser.<lambda>>, 'ARRAY': <function BigQuery.Parser.<lambda>>}
NO_PAREN_FUNCTIONS =
{<TokenType.CURRENT_DATE: 'CURRENT_DATE'>: <class 'sqlglot.expressions.CurrentDate'>, <TokenType.CURRENT_DATETIME: 'CURRENT_DATETIME'>: <class 'sqlglot.expressions.CurrentDatetime'>, <TokenType.CURRENT_TIME: 'CURRENT_TIME'>: <class 'sqlglot.expressions.CurrentTime'>, <TokenType.CURRENT_TIMESTAMP: 'CURRENT_TIMESTAMP'>: <class 'sqlglot.expressions.CurrentTimestamp'>, <TokenType.CURRENT_USER: 'CURRENT_USER'>: <class 'sqlglot.expressions.CurrentUser'>}
NESTED_TYPE_TOKENS =
{<TokenType.TABLE: 'TABLE'>, <TokenType.NULLABLE: 'NULLABLE'>, <TokenType.NESTED: 'NESTED'>, <TokenType.STRUCT: 'STRUCT'>, <TokenType.MAP: 'MAP'>, <TokenType.ARRAY: 'ARRAY'>, <TokenType.LOWCARDINALITY: 'LOWCARDINALITY'>}
ID_VAR_TOKENS =
{<TokenType.UINT: 'UINT'>, <TokenType.BIGINT: 'BIGINT'>, <TokenType.TSTZMULTIRANGE: 'TSTZMULTIRANGE'>, <TokenType.INTERVAL: 'INTERVAL'>, <TokenType.CURRENT_USER: 'CURRENT_USER'>, <TokenType.FULL: 'FULL'>, <TokenType.DICTIONARY: 'DICTIONARY'>, <TokenType.NULLABLE: 'NULLABLE'>, <TokenType.TIMETZ: 'TIMETZ'>, <TokenType.DATABASE: 'DATABASE'>, <TokenType.DECIMAL: 'DECIMAL'>, <TokenType.USMALLINT: 'USMALLINT'>, <TokenType.SHOW: 'SHOW'>, <TokenType.SUPER: 'SUPER'>, <TokenType.COMMAND: 'COMMAND'>, <TokenType.COMMIT: 'COMMIT'>, <TokenType.SET: 'SET'>, <TokenType.SCHEMA: 'SCHEMA'>, <TokenType.BOOLEAN: 'BOOLEAN'>, <TokenType.ANTI: 'ANTI'>, <TokenType.ISNULL: 'ISNULL'>, <TokenType.NUMRANGE: 'NUMRANGE'>, <TokenType.COMMENT: 'COMMENT'>, <TokenType.LONGBLOB: 'LONGBLOB'>, <TokenType.DATEMULTIRANGE: 'DATEMULTIRANGE'>, <TokenType.DOUBLE: 'DOUBLE'>, <TokenType.SMALLSERIAL: 'SMALLSERIAL'>, <TokenType.BINARY: 'BINARY'>, <TokenType.ROWS: 'ROWS'>, <TokenType.EXECUTE: 'EXECUTE'>, <TokenType.COLLATE: 'COLLATE'>, <TokenType.SETTINGS: 'SETTINGS'>, <TokenType.TABLE: 'TABLE'>, <TokenType.UTINYINT: 'UTINYINT'>, <TokenType.INT4MULTIRANGE: 'INT4MULTIRANGE'>, <TokenType.KEEP: 'KEEP'>, <TokenType.BEGIN: 'BEGIN'>, <TokenType.DATETIME64: 'DATETIME64'>, <TokenType.CHAR: 'CHAR'>, <TokenType.TEXT: 'TEXT'>, <TokenType.IMAGE: 'IMAGE'>, <TokenType.HSTORE: 'HSTORE'>, <TokenType.VIEW: 'VIEW'>, <TokenType.YEAR: 'YEAR'>, <TokenType.ALL: 'ALL'>, <TokenType.DESC: 'DESC'>, <TokenType.NATURAL: 'NATURAL'>, <TokenType.CURRENT_DATETIME: 'CURRENT_DATETIME'>, <TokenType.RIGHT: 'RIGHT'>, <TokenType.LEFT: 'LEFT'>, <TokenType.DEFAULT: 'DEFAULT'>, <TokenType.TIMESTAMP: 'TIMESTAMP'>, <TokenType.GEOMETRY: 'GEOMETRY'>, <TokenType.DESCRIBE: 'DESCRIBE'>, <TokenType.UUID: 'UUID'>, <TokenType.TINYINT: 'TINYINT'>, <TokenType.DELETE: 'DELETE'>, <TokenType.ROWVERSION: 'ROWVERSION'>, <TokenType.ENUM16: 'ENUM16'>, <TokenType.GEOGRAPHY: 'GEOGRAPHY'>, <TokenType.END: 'END'>, <TokenType.ESCAPE: 'ESCAPE'>, <TokenType.JSONB: 'JSONB'>, <TokenType.UPDATE: 'UPDATE'>, <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, <TokenType.MERGE: 'MERGE'>, <TokenType.NUMMULTIRANGE: 'NUMMULTIRANGE'>, <TokenType.UINT128: 'UINT128'>, <TokenType.VAR: 'VAR'>, <TokenType.INT: 'INT'>, <TokenType.CONSTRAINT: 'CONSTRAINT'>, <TokenType.FIRST: 'FIRST'>, <TokenType.PSEUDO_TYPE: 'PSEUDO_TYPE'>, <TokenType.NEXT: 'NEXT'>, <TokenType.UNKNOWN: 'UNKNOWN'>, <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, <TokenType.TSTZRANGE: 'TSTZRANGE'>, <TokenType.EXISTS: 'EXISTS'>, <TokenType.LOAD: 'LOAD'>, <TokenType.TOP: 'TOP'>, <TokenType.TSRANGE: 'TSRANGE'>, <TokenType.DATE: 'DATE'>, <TokenType.ANY: 'ANY'>, <TokenType.IPPREFIX: 'IPPREFIX'>, <TokenType.TSMULTIRANGE: 'TSMULTIRANGE'>, <TokenType.FLOAT: 'FLOAT'>, <TokenType.TIME: 'TIME'>, <TokenType.IS: 'IS'>, <TokenType.STRUCT: 'STRUCT'>, <TokenType.SOME: 'SOME'>, <TokenType.ROW: 'ROW'>, <TokenType.INDEX: 'INDEX'>, <TokenType.INT128: 'INT128'>, <TokenType.UINT256: 'UINT256'>, <TokenType.JSON: 'JSON'>, <TokenType.VARCHAR: 'VARCHAR'>, <TokenType.FILTER: 'FILTER'>, <TokenType.COLUMN: 'COLUMN'>, <TokenType.OVERWRITE: 'OVERWRITE'>, <TokenType.RANGE: 'RANGE'>, <TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>, <TokenType.LONGTEXT: 'LONGTEXT'>, <TokenType.ENUM8: 'ENUM8'>, <TokenType.IPADDRESS: 'IPADDRESS'>, <TokenType.VARBINARY: 'VARBINARY'>, <TokenType.MEDIUMINT: 'MEDIUMINT'>, <TokenType.SEMI: 'SEMI'>, <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>, <TokenType.NVARCHAR: 'NVARCHAR'>, <TokenType.PRAGMA: 'PRAGMA'>, <TokenType.REFERENCES: 'REFERENCES'>, <TokenType.MONEY: 'MONEY'>, <TokenType.DATETIME: 'DATETIME'>, <TokenType.FALSE: 'FALSE'>, <TokenType.INT8RANGE: 'INT8RANGE'>, <TokenType.TRUE: 'TRUE'>, <TokenType.ARRAY: 'ARRAY'>, <TokenType.FORMAT: 'FORMAT'>, <TokenType.NESTED: 'NESTED'>, <TokenType.CASE: 'CASE'>, <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>, <TokenType.VALUES: 'VALUES'>, <TokenType.SMALLMONEY: 'SMALLMONEY'>, <TokenType.ORDINALITY: 'ORDINALITY'>, <TokenType.BIT: 'BIT'>, <TokenType.OBJECT: 'OBJECT'>, <TokenType.INT256: 'INT256'>, <TokenType.VOLATILE: 'VOLATILE'>, <TokenType.FUNCTION: 'FUNCTION'>, <TokenType.ENUM: 'ENUM'>, <TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>, <TokenType.NCHAR: 'NCHAR'>, <TokenType.LOWCARDINALITY: 'LOWCARDINALITY'>, <TokenType.CURRENT_TIMESTAMP: 'CURRENT_TIMESTAMP'>, <TokenType.DATERANGE: 'DATERANGE'>, <TokenType.CACHE: 'CACHE'>, <TokenType.SMALLINT: 'SMALLINT'>, <TokenType.APPLY: 'APPLY'>, <TokenType.MAP: 'MAP'>, <TokenType.CURRENT_TIME: 'CURRENT_TIME'>, <TokenType.PROCEDURE: 'PROCEDURE'>, <TokenType.UBIGINT: 'UBIGINT'>, <TokenType.UNIQUE: 'UNIQUE'>, <TokenType.PIVOT: 'PIVOT'>, <TokenType.CURRENT_DATE: 'CURRENT_DATE'>, <TokenType.NULL: 'NULL'>, <TokenType.SERIAL: 'SERIAL'>, <TokenType.VARIANT: 'VARIANT'>, <TokenType.INT4RANGE: 'INT4RANGE'>, <TokenType.FIXEDSTRING: 'FIXEDSTRING'>, <TokenType.ASC: 'ASC'>, <TokenType.PARTITION: 'PARTITION'>, <TokenType.USERDEFINED: 'USERDEFINED'>, <TokenType.PERCENT: 'PERCENT'>, <TokenType.WINDOW: 'WINDOW'>, <TokenType.BIGSERIAL: 'BIGSERIAL'>, <TokenType.UNIQUEIDENTIFIER: 'UNIQUEIDENTIFIER'>, <TokenType.INET: 'INET'>, <TokenType.INT8MULTIRANGE: 'INT8MULTIRANGE'>, <TokenType.XML: 'XML'>, <TokenType.UNPIVOT: 'UNPIVOT'>, <TokenType.HLLSKETCH: 'HLLSKETCH'>, <TokenType.TEMPORARY: 'TEMPORARY'>, <TokenType.OFFSET: 'OFFSET'>, <TokenType.DIV: 'DIV'>}
PROPERTY_PARSERS =
{'ALGORITHM': <function Parser.<lambda>>, 'AUTO_INCREMENT': <function Parser.<lambda>>, 'BLOCKCOMPRESSION': <function Parser.<lambda>>, 'CHARACTER SET': <function Parser.<lambda>>, 'CHECKSUM': <function Parser.<lambda>>, 'CLUSTER BY': <function Parser.<lambda>>, 'CLUSTERED': <function Parser.<lambda>>, 'COLLATE': <function Parser.<lambda>>, 'COMMENT': <function Parser.<lambda>>, 'COPY': <function Parser.<lambda>>, 'DATABLOCKSIZE': <function Parser.<lambda>>, 'DEFINER': <function Parser.<lambda>>, 'DETERMINISTIC': <function Parser.<lambda>>, 'DISTKEY': <function Parser.<lambda>>, 'DISTSTYLE': <function Parser.<lambda>>, 'ENGINE': <function Parser.<lambda>>, 'EXECUTE': <function Parser.<lambda>>, 'EXTERNAL': <function Parser.<lambda>>, 'FALLBACK': <function Parser.<lambda>>, 'FORMAT': <function Parser.<lambda>>, 'FREESPACE': <function Parser.<lambda>>, 'HEAP': <function Parser.<lambda>>, 'IMMUTABLE': <function Parser.<lambda>>, 'JOURNAL': <function Parser.<lambda>>, 'LANGUAGE': <function Parser.<lambda>>, 'LAYOUT': <function Parser.<lambda>>, 'LIFETIME': <function Parser.<lambda>>, 'LIKE': <function Parser.<lambda>>, 'LOCATION': <function Parser.<lambda>>, 'LOCK': <function Parser.<lambda>>, 'LOCKING': <function Parser.<lambda>>, 'LOG': <function Parser.<lambda>>, 'MATERIALIZED': <function Parser.<lambda>>, 'MERGEBLOCKRATIO': <function Parser.<lambda>>, 'MULTISET': <function Parser.<lambda>>, 'NO': <function Parser.<lambda>>, 'ON': <function Parser.<lambda>>, 'ORDER BY': <function Parser.<lambda>>, 'PARTITION BY': <function Parser.<lambda>>, 'PARTITIONED BY': <function Parser.<lambda>>, 'PARTITIONED_BY': <function Parser.<lambda>>, 'PRIMARY KEY': <function Parser.<lambda>>, 'RANGE': <function Parser.<lambda>>, 'RETURNS': <function Parser.<lambda>>, 'ROW': <function Parser.<lambda>>, 'ROW_FORMAT': <function Parser.<lambda>>, 'SET': <function Parser.<lambda>>, 'SETTINGS': <function Parser.<lambda>>, 'SORTKEY': <function Parser.<lambda>>, 'SOURCE': <function Parser.<lambda>>, 'STABLE': <function Parser.<lambda>>, 'STORED': <function Parser.<lambda>>, 'TBLPROPERTIES': <function Parser.<lambda>>, 'TEMP': <function Parser.<lambda>>, 'TEMPORARY': <function Parser.<lambda>>, 'TO': <function Parser.<lambda>>, 'TRANSIENT': <function Parser.<lambda>>, 'TTL': <function Parser.<lambda>>, 'USING': <function Parser.<lambda>>, 'VOLATILE': <function Parser.<lambda>>, 'WITH': <function Parser.<lambda>>, 'NOT DETERMINISTIC': <function BigQuery.Parser.<lambda>>, 'OPTIONS': <function BigQuery.Parser.<lambda>>}
CONSTRAINT_PARSERS =
{'AUTOINCREMENT': <function Parser.<lambda>>, 'AUTO_INCREMENT': <function Parser.<lambda>>, 'CASESPECIFIC': <function Parser.<lambda>>, 'CHARACTER SET': <function Parser.<lambda>>, 'CHECK': <function Parser.<lambda>>, 'COLLATE': <function Parser.<lambda>>, 'COMMENT': <function Parser.<lambda>>, 'COMPRESS': <function Parser.<lambda>>, 'CLUSTERED': <function Parser.<lambda>>, 'NONCLUSTERED': <function Parser.<lambda>>, 'DEFAULT': <function Parser.<lambda>>, 'ENCODE': <function Parser.<lambda>>, 'FOREIGN KEY': <function Parser.<lambda>>, 'FORMAT': <function Parser.<lambda>>, 'GENERATED': <function Parser.<lambda>>, 'IDENTITY': <function Parser.<lambda>>, 'INLINE': <function Parser.<lambda>>, 'LIKE': <function Parser.<lambda>>, 'NOT': <function Parser.<lambda>>, 'NULL': <function Parser.<lambda>>, 'ON': <function Parser.<lambda>>, 'PATH': <function Parser.<lambda>>, 'PRIMARY KEY': <function Parser.<lambda>>, 'REFERENCES': <function Parser.<lambda>>, 'TITLE': <function Parser.<lambda>>, 'TTL': <function Parser.<lambda>>, 'UNIQUE': <function Parser.<lambda>>, 'UPPERCASE': <function Parser.<lambda>>, 'WITH': <function Parser.<lambda>>, 'OPTIONS': <function BigQuery.Parser.<lambda>>}
TOKENIZER_CLASS: Type[sqlglot.tokens.Tokenizer] =
<class 'sqlglot.dialects.bigquery.BigQuery.Tokenizer'>
SET_TRIE: Dict =
{'GLOBAL': {0: True}, 'LOCAL': {0: True}, 'SESSION': {0: True}, 'TRANSACTION': {0: True}}
FORMAT_MAPPING: Dict[str, str] =
{'DD': '%d', 'MM': '%m', 'MON': '%b', 'MONTH': '%B', 'YYYY': '%Y', 'YY': '%y', 'HH': '%I', 'HH12': '%I', 'HH24': '%H', 'MI': '%M', 'SS': '%S', 'SSSSS': '%f', 'TZH': '%z'}
FORMAT_TRIE: Dict =
{'D': {'D': {0: True}}, 'M': {'M': {0: True}, 'O': {'N': {0: True, 'T': {'H': {0: True}}}}, 'I': {0: True}}, 'Y': {'Y': {'Y': {'Y': {0: True}}, 0: True}}, 'H': {'H': {0: True, '1': {'2': {0: True}}, '2': {'4': {0: True}}}}, 'S': {'S': {0: True, 'S': {'S': {'S': {0: True}}}}}, 'T': {'Z': {'H': {0: True}}}}
Inherited Members
- sqlglot.parser.Parser
- Parser
- STRUCT_TYPE_TOKENS
- ENUM_TYPE_TOKENS
- TYPE_TOKENS
- SUBQUERY_PREDICATES
- RESERVED_KEYWORDS
- DB_CREATABLES
- CREATABLES
- INTERVAL_VARS
- TABLE_ALIAS_TOKENS
- COMMENT_TABLE_ALIAS_TOKENS
- UPDATE_ALIAS_TOKENS
- TRIM_TYPES
- FUNC_TOKENS
- CONJUNCTION
- EQUALITY
- COMPARISON
- BITWISE
- TERM
- FACTOR
- TIMES
- TIMESTAMPS
- SET_OPERATIONS
- JOIN_METHODS
- JOIN_SIDES
- JOIN_KINDS
- JOIN_HINTS
- LAMBDAS
- COLUMN_OPERATORS
- EXPRESSION_PARSERS
- STATEMENT_PARSERS
- UNARY_PARSERS
- PRIMARY_PARSERS
- PLACEHOLDER_PARSERS
- RANGE_PARSERS
- ALTER_PARSERS
- SCHEMA_UNNAMED_CONSTRAINTS
- NO_PAREN_FUNCTION_PARSERS
- INVALID_FUNC_NAME_TOKENS
- FUNCTIONS_WITH_ALIASED_ARGS
- QUERY_MODIFIER_PARSERS
- SET_PARSERS
- SHOW_PARSERS
- TYPE_LITERAL_PARSERS
- MODIFIABLES
- DDL_SELECT_TOKENS
- PRE_VOLATILE_TOKENS
- TRANSACTION_KIND
- TRANSACTION_CHARACTERISTICS
- INSERT_ALTERNATIVES
- CLONE_KINDS
- TABLE_INDEX_HINT_TOKENS
- WINDOW_ALIAS_TOKENS
- WINDOW_BEFORE_PAREN_TOKENS
- WINDOW_SIDES
- ADD_CONSTRAINT_TOKENS
- DISTINCT_TOKENS
- STRICT_CAST
- CONCAT_NULL_OUTPUTS_STRING
- IDENTIFY_PIVOT_STRINGS
- INDEX_OFFSET
- ALIAS_POST_TABLESAMPLE
- STRICT_STRING_CONCAT
- NULL_ORDERING
- error_level
- error_message_context
- max_errors
- reset
- parse
- parse_into
- check_errors
- raise_error
- expression
- validate_expression
- errors
- sql
382 class Generator(generator.Generator): 383 EXPLICIT_UNION = True 384 INTERVAL_ALLOWS_PLURAL_FORM = False 385 JOIN_HINTS = False 386 QUERY_HINTS = False 387 TABLE_HINTS = False 388 LIMIT_FETCH = "LIMIT" 389 RENAME_TABLE_WITH_DB = False 390 ESCAPE_LINE_BREAK = True 391 NVL2_SUPPORTED = False 392 393 TRANSFORMS = { 394 **generator.Generator.TRANSFORMS, 395 exp.ApproxDistinct: rename_func("APPROX_COUNT_DISTINCT"), 396 exp.ArraySize: rename_func("ARRAY_LENGTH"), 397 exp.Cast: transforms.preprocess([transforms.remove_precision_parameterized_types]), 398 exp.Create: _create_sql, 399 exp.CTE: transforms.preprocess([_pushdown_cte_column_names]), 400 exp.DateAdd: _date_add_sql("DATE", "ADD"), 401 exp.DateDiff: lambda self, e: f"DATE_DIFF({self.sql(e, 'this')}, {self.sql(e, 'expression')}, {self.sql(e.args.get('unit', 'DAY'))})", 402 exp.DateFromParts: rename_func("DATE"), 403 exp.DateStrToDate: datestrtodate_sql, 404 exp.DateSub: _date_add_sql("DATE", "SUB"), 405 exp.DatetimeAdd: _date_add_sql("DATETIME", "ADD"), 406 exp.DatetimeSub: _date_add_sql("DATETIME", "SUB"), 407 exp.DateTrunc: lambda self, e: self.func("DATE_TRUNC", e.this, e.text("unit")), 408 exp.GenerateSeries: rename_func("GENERATE_ARRAY"), 409 exp.GroupConcat: rename_func("STRING_AGG"), 410 exp.Hex: rename_func("TO_HEX"), 411 exp.ILike: no_ilike_sql, 412 exp.IntDiv: rename_func("DIV"), 413 exp.JSONFormat: rename_func("TO_JSON_STRING"), 414 exp.Max: max_or_greatest, 415 exp.MD5: lambda self, e: self.func("TO_HEX", self.func("MD5", e.this)), 416 exp.MD5Digest: rename_func("MD5"), 417 exp.Min: min_or_least, 418 exp.PartitionedByProperty: lambda self, e: f"PARTITION BY {self.sql(e, 'this')}", 419 exp.RegexpExtract: lambda self, e: self.func( 420 "REGEXP_EXTRACT", 421 e.this, 422 e.expression, 423 e.args.get("position"), 424 e.args.get("occurrence"), 425 ), 426 exp.RegexpReplace: regexp_replace_sql, 427 exp.RegexpLike: rename_func("REGEXP_CONTAINS"), 428 exp.ReturnsProperty: _returnsproperty_sql, 429 exp.Select: transforms.preprocess( 430 [ 431 transforms.explode_to_unnest, 432 _unqualify_unnest, 433 transforms.eliminate_distinct_on, 434 _alias_ordered_group, 435 ] 436 ), 437 exp.SHA2: lambda self, e: self.func( 438 f"SHA256" if e.text("length") == "256" else "SHA512", e.this 439 ), 440 exp.StabilityProperty: lambda self, e: f"DETERMINISTIC" 441 if e.name == "IMMUTABLE" 442 else "NOT DETERMINISTIC", 443 exp.StrToDate: lambda self, e: f"PARSE_DATE({self.format_time(e)}, {self.sql(e, 'this')})", 444 exp.StrToTime: lambda self, e: self.func( 445 "PARSE_TIMESTAMP", self.format_time(e), e.this, e.args.get("zone") 446 ), 447 exp.TimeAdd: _date_add_sql("TIME", "ADD"), 448 exp.TimeSub: _date_add_sql("TIME", "SUB"), 449 exp.TimestampAdd: _date_add_sql("TIMESTAMP", "ADD"), 450 exp.TimestampSub: _date_add_sql("TIMESTAMP", "SUB"), 451 exp.TimeStrToTime: timestrtotime_sql, 452 exp.Trim: lambda self, e: self.func(f"TRIM", e.this, e.expression), 453 exp.TsOrDsAdd: _date_add_sql("DATE", "ADD"), 454 exp.TsOrDsToDate: ts_or_ds_to_date_sql("bigquery"), 455 exp.Unhex: rename_func("FROM_HEX"), 456 exp.Values: _derived_table_values_to_unnest, 457 exp.VariancePop: rename_func("VAR_POP"), 458 } 459 460 TYPE_MAPPING = { 461 **generator.Generator.TYPE_MAPPING, 462 exp.DataType.Type.BIGDECIMAL: "BIGNUMERIC", 463 exp.DataType.Type.BIGINT: "INT64", 464 exp.DataType.Type.BINARY: "BYTES", 465 exp.DataType.Type.BOOLEAN: "BOOL", 466 exp.DataType.Type.CHAR: "STRING", 467 exp.DataType.Type.DECIMAL: "NUMERIC", 468 exp.DataType.Type.DOUBLE: "FLOAT64", 469 exp.DataType.Type.FLOAT: "FLOAT64", 470 exp.DataType.Type.INT: "INT64", 471 exp.DataType.Type.NCHAR: "STRING", 472 exp.DataType.Type.NVARCHAR: "STRING", 473 exp.DataType.Type.SMALLINT: "INT64", 474 exp.DataType.Type.TEXT: "STRING", 475 exp.DataType.Type.TIMESTAMP: "DATETIME", 476 exp.DataType.Type.TIMESTAMPTZ: "TIMESTAMP", 477 exp.DataType.Type.TIMESTAMPLTZ: "TIMESTAMP", 478 exp.DataType.Type.TINYINT: "INT64", 479 exp.DataType.Type.VARBINARY: "BYTES", 480 exp.DataType.Type.VARCHAR: "STRING", 481 exp.DataType.Type.VARIANT: "ANY TYPE", 482 } 483 484 PROPERTIES_LOCATION = { 485 **generator.Generator.PROPERTIES_LOCATION, 486 exp.PartitionedByProperty: exp.Properties.Location.POST_SCHEMA, 487 exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED, 488 } 489 490 # from: https://cloud.google.com/bigquery/docs/reference/standard-sql/lexical#reserved_keywords 491 RESERVED_KEYWORDS = { 492 *generator.Generator.RESERVED_KEYWORDS, 493 "all", 494 "and", 495 "any", 496 "array", 497 "as", 498 "asc", 499 "assert_rows_modified", 500 "at", 501 "between", 502 "by", 503 "case", 504 "cast", 505 "collate", 506 "contains", 507 "create", 508 "cross", 509 "cube", 510 "current", 511 "default", 512 "define", 513 "desc", 514 "distinct", 515 "else", 516 "end", 517 "enum", 518 "escape", 519 "except", 520 "exclude", 521 "exists", 522 "extract", 523 "false", 524 "fetch", 525 "following", 526 "for", 527 "from", 528 "full", 529 "group", 530 "grouping", 531 "groups", 532 "hash", 533 "having", 534 "if", 535 "ignore", 536 "in", 537 "inner", 538 "intersect", 539 "interval", 540 "into", 541 "is", 542 "join", 543 "lateral", 544 "left", 545 "like", 546 "limit", 547 "lookup", 548 "merge", 549 "natural", 550 "new", 551 "no", 552 "not", 553 "null", 554 "nulls", 555 "of", 556 "on", 557 "or", 558 "order", 559 "outer", 560 "over", 561 "partition", 562 "preceding", 563 "proto", 564 "qualify", 565 "range", 566 "recursive", 567 "respect", 568 "right", 569 "rollup", 570 "rows", 571 "select", 572 "set", 573 "some", 574 "struct", 575 "tablesample", 576 "then", 577 "to", 578 "treat", 579 "true", 580 "unbounded", 581 "union", 582 "unnest", 583 "using", 584 "when", 585 "where", 586 "window", 587 "with", 588 "within", 589 } 590 591 def attimezone_sql(self, expression: exp.AtTimeZone) -> str: 592 parent = expression.parent 593 594 # BigQuery allows CAST(.. AS {STRING|TIMESTAMP} [FORMAT <fmt> [AT TIME ZONE <tz>]]). 595 # Only the TIMESTAMP one should use the below conversion, when AT TIME ZONE is included. 596 if not isinstance(parent, exp.Cast) or not parent.to.is_type("text"): 597 return self.func( 598 "TIMESTAMP", self.func("DATETIME", expression.this, expression.args.get("zone")) 599 ) 600 601 return super().attimezone_sql(expression) 602 603 def trycast_sql(self, expression: exp.TryCast) -> str: 604 return self.cast_sql(expression, safe_prefix="SAFE_") 605 606 def cte_sql(self, expression: exp.CTE) -> str: 607 if expression.alias_column_names: 608 self.unsupported("Column names in CTE definition are not supported.") 609 return super().cte_sql(expression) 610 611 def array_sql(self, expression: exp.Array) -> str: 612 first_arg = seq_get(expression.expressions, 0) 613 if isinstance(first_arg, exp.Subqueryable): 614 return f"ARRAY{self.wrap(self.sql(first_arg))}" 615 616 return inline_array_sql(self, expression) 617 618 def transaction_sql(self, *_) -> str: 619 return "BEGIN TRANSACTION" 620 621 def commit_sql(self, *_) -> str: 622 return "COMMIT TRANSACTION" 623 624 def rollback_sql(self, *_) -> str: 625 return "ROLLBACK TRANSACTION" 626 627 def in_unnest_op(self, expression: exp.Unnest) -> str: 628 return self.sql(expression) 629 630 def except_op(self, expression: exp.Except) -> str: 631 if not expression.args.get("distinct", False): 632 self.unsupported("EXCEPT without DISTINCT is not supported in BigQuery") 633 return f"EXCEPT{' DISTINCT' if expression.args.get('distinct') else ' ALL'}" 634 635 def intersect_op(self, expression: exp.Intersect) -> str: 636 if not expression.args.get("distinct", False): 637 self.unsupported("INTERSECT without DISTINCT is not supported in BigQuery") 638 return f"INTERSECT{' DISTINCT' if expression.args.get('distinct') else ' ALL'}" 639 640 def with_properties(self, properties: exp.Properties) -> str: 641 return self.properties(properties, prefix=self.seg("OPTIONS"))
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
TRANSFORMS =
{<class 'sqlglot.expressions.DateAdd'>: <function _date_add_sql.<locals>.func>, <class 'sqlglot.expressions.TsOrDsAdd'>: <function _date_add_sql.<locals>.func>, <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.ClusteredColumnConstraint'>: <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.HeapProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.InlineLengthColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.IntervalDayToSecondSpan'>: 'DAY TO SECOND', <class 'sqlglot.expressions.IntervalYearToMonthSpan'>: 'YEAR TO MONTH', <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.NonClusteredColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.NotForReplicationColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.OnCommitProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.OnProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.OnUpdateColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.PathColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ReturnsProperty'>: <function _returnsproperty_sql>, <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 BigQuery.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 Generator.<lambda>>, <class 'sqlglot.expressions.VolatileProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.WithJournalTableProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ApproxDistinct'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.ArraySize'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.Cast'>: <function preprocess.<locals>._to_sql>, <class 'sqlglot.expressions.Create'>: <function _create_sql>, <class 'sqlglot.expressions.CTE'>: <function preprocess.<locals>._to_sql>, <class 'sqlglot.expressions.DateDiff'>: <function BigQuery.Generator.<lambda>>, <class 'sqlglot.expressions.DateFromParts'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.DateStrToDate'>: <function datestrtodate_sql>, <class 'sqlglot.expressions.DateSub'>: <function _date_add_sql.<locals>.func>, <class 'sqlglot.expressions.DatetimeAdd'>: <function _date_add_sql.<locals>.func>, <class 'sqlglot.expressions.DatetimeSub'>: <function _date_add_sql.<locals>.func>, <class 'sqlglot.expressions.DateTrunc'>: <function BigQuery.Generator.<lambda>>, <class 'sqlglot.expressions.GenerateSeries'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.GroupConcat'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.Hex'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.ILike'>: <function no_ilike_sql>, <class 'sqlglot.expressions.IntDiv'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.JSONFormat'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.Max'>: <function max_or_greatest>, <class 'sqlglot.expressions.MD5'>: <function BigQuery.Generator.<lambda>>, <class 'sqlglot.expressions.MD5Digest'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.Min'>: <function min_or_least>, <class 'sqlglot.expressions.PartitionedByProperty'>: <function BigQuery.Generator.<lambda>>, <class 'sqlglot.expressions.RegexpExtract'>: <function BigQuery.Generator.<lambda>>, <class 'sqlglot.expressions.RegexpReplace'>: <function regexp_replace_sql>, <class 'sqlglot.expressions.RegexpLike'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.Select'>: <function preprocess.<locals>._to_sql>, <class 'sqlglot.expressions.SHA2'>: <function BigQuery.Generator.<lambda>>, <class 'sqlglot.expressions.StrToDate'>: <function BigQuery.Generator.<lambda>>, <class 'sqlglot.expressions.StrToTime'>: <function BigQuery.Generator.<lambda>>, <class 'sqlglot.expressions.TimeAdd'>: <function _date_add_sql.<locals>.func>, <class 'sqlglot.expressions.TimeSub'>: <function _date_add_sql.<locals>.func>, <class 'sqlglot.expressions.TimestampAdd'>: <function _date_add_sql.<locals>.func>, <class 'sqlglot.expressions.TimestampSub'>: <function _date_add_sql.<locals>.func>, <class 'sqlglot.expressions.TimeStrToTime'>: <function timestrtotime_sql>, <class 'sqlglot.expressions.Trim'>: <function BigQuery.Generator.<lambda>>, <class 'sqlglot.expressions.TsOrDsToDate'>: <function ts_or_ds_to_date_sql.<locals>._ts_or_ds_to_date_sql>, <class 'sqlglot.expressions.Unhex'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.Values'>: <function _derived_table_values_to_unnest>, <class 'sqlglot.expressions.VariancePop'>: <function rename_func.<locals>.<lambda>>}
TYPE_MAPPING =
{<Type.NCHAR: 'NCHAR'>: 'STRING', <Type.NVARCHAR: 'NVARCHAR'>: 'STRING', <Type.MEDIUMTEXT: 'MEDIUMTEXT'>: 'TEXT', <Type.LONGTEXT: 'LONGTEXT'>: 'TEXT', <Type.MEDIUMBLOB: 'MEDIUMBLOB'>: 'BLOB', <Type.LONGBLOB: 'LONGBLOB'>: 'BLOB', <Type.INET: 'INET'>: 'INET', <Type.BIGDECIMAL: 'BIGDECIMAL'>: 'BIGNUMERIC', <Type.BIGINT: 'BIGINT'>: 'INT64', <Type.BINARY: 'BINARY'>: 'BYTES', <Type.BOOLEAN: 'BOOLEAN'>: 'BOOL', <Type.CHAR: 'CHAR'>: 'STRING', <Type.DECIMAL: 'DECIMAL'>: 'NUMERIC', <Type.DOUBLE: 'DOUBLE'>: 'FLOAT64', <Type.FLOAT: 'FLOAT'>: 'FLOAT64', <Type.INT: 'INT'>: 'INT64', <Type.SMALLINT: 'SMALLINT'>: 'INT64', <Type.TEXT: 'TEXT'>: 'STRING', <Type.TIMESTAMP: 'TIMESTAMP'>: 'DATETIME', <Type.TIMESTAMPTZ: 'TIMESTAMPTZ'>: 'TIMESTAMP', <Type.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>: 'TIMESTAMP', <Type.TINYINT: 'TINYINT'>: 'INT64', <Type.VARBINARY: 'VARBINARY'>: 'BYTES', <Type.VARCHAR: 'VARCHAR'>: 'STRING', <Type.VARIANT: 'VARIANT'>: 'ANY TYPE'}
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.HeapProperty'>: <Location.POST_WITH: 'POST_WITH'>, <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.OnProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <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'>}
RESERVED_KEYWORDS =
{'in', 'array', 'right', 'over', 'assert_rows_modified', 'join', 'escape', 'interval', 'select', 'like', 'intersect', 'recursive', 'inner', 'where', 'if', 'treat', 'collate', 'all', 'preceding', 'between', 'following', 'group', 'set', 'of', 'no', 'left', 'natural', 'union', 'cube', 'current', 'contains', 'else', 'within', 'range', 'any', 'unbounded', 'having', 'create', 'by', 'lateral', 'proto', 'grouping', 'rollup', 'extract', 'using', 'rows', 'exists', 'and', 'define', 'as', 'exclude', 'order', 'hash', 'qualify', 'is', 'for', 'window', 'enum', 'nulls', 'desc', 'not', 'except', 'full', 'or', 'fetch', 'at', 'into', 'from', 'true', 'groups', 'cross', 'unnest', 'merge', 'on', 'then', 'case', 'when', 'null', 'some', 'with', 'respect', 'cast', 'new', 'end', 'asc', 'limit', 'false', 'struct', 'to', 'ignore', 'tablesample', 'distinct', 'outer', 'partition', 'default', 'lookup'}
591 def attimezone_sql(self, expression: exp.AtTimeZone) -> str: 592 parent = expression.parent 593 594 # BigQuery allows CAST(.. AS {STRING|TIMESTAMP} [FORMAT <fmt> [AT TIME ZONE <tz>]]). 595 # Only the TIMESTAMP one should use the below conversion, when AT TIME ZONE is included. 596 if not isinstance(parent, exp.Cast) or not parent.to.is_type("text"): 597 return self.func( 598 "TIMESTAMP", self.func("DATETIME", expression.this, expression.args.get("zone")) 599 ) 600 601 return super().attimezone_sql(expression)
@classmethod
def
can_identify(text: str, identify: str | bool = 'safe') -> bool:
256 @classmethod 257 def can_identify(cls, text: str, identify: str | bool = "safe") -> bool: 258 """Checks if text can be identified given an identify option. 259 260 Args: 261 text: The text to check. 262 identify: 263 "always" or `True`: Always returns true. 264 "safe": True if the identifier is case-insensitive. 265 266 Returns: 267 Whether or not the given text can be identified. 268 """ 269 if identify is True or identify == "always": 270 return True 271 272 if identify == "safe": 273 return not cls.case_sensitive(text) 274 275 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.
TOKENIZER_CLASS =
<class 'sqlglot.dialects.bigquery.BigQuery.Tokenizer'>
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
- TABLESAMPLE_WITH_METHOD
- TABLESAMPLE_SIZE_IS_PERCENT
- GROUPINGS_SEP
- INDEX_ON
- QUERY_HINT_SEP
- IS_BOOL_ALLOWED
- DUPLICATE_KEY_UPDATE_WITH_SET
- LIMIT_IS_TOP
- RETURNING_END
- COLUMN_JOIN_MARKS_SUPPORTED
- EXTRACT_ALLOWS_QUOTES
- TZ_TO_WITH_TIME_ZONE
- SELECT_KINDS
- VALUES_AS_TABLE
- STAR_MAPPING
- TIME_PART_SINGULARS
- TOKEN_MAPPING
- STRUCT_DELIMITER
- PARAMETER_TOKEN
- WITH_SEPARATED_COMMENTS
- UNWRAPPED_INTERVAL_VALUES
- SENTINEL_LINE_BREAK
- INDEX_OFFSET
- ALIAS_POST_TABLESAMPLE
- IDENTIFIERS_CAN_START_WITH_DIGIT
- STRICT_STRING_CONCAT
- NULL_ORDERING
- 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
- computedcolumnconstraint_sql
- autoincrementcolumnconstraint_sql
- compresscolumnconstraint_sql
- generatedasidentitycolumnconstraint_sql
- notnullcolumnconstraint_sql
- primarykeycolumnconstraint_sql
- uniquecolumnconstraint_sql
- createable_sql
- create_sql
- clone_sql
- describe_sql
- prepend_ctes
- with_sql
- tablealias_sql
- bitstring_sql
- hexstring_sql
- bytestring_sql
- rawstring_sql
- datatypeparam_sql
- datatype_sql
- directory_sql
- delete_sql
- drop_sql
- except_sql
- fetch_sql
- filter_sql
- hint_sql
- index_sql
- identifier_sql
- inputoutputformat_sql
- national_sql
- partition_sql
- properties_sql
- root_properties
- 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
- 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
- connect_sql
- prior_sql
- join_sql
- lambda_sql
- lateral_sql
- limit_sql
- offset_sql
- setitem_sql
- set_sql
- pragma_sql
- lock_sql
- literal_sql
- escape_str
- loaddata_sql
- null_sql
- boolean_sql
- order_sql
- cluster_sql
- distribute_sql
- sort_sql
- ordered_sql
- matchrecognize_sql
- query_modifiers
- offset_limit_modifiers
- after_having_modifiers
- after_limit_modifiers
- select_sql
- schema_sql
- schema_columns_sql
- star_sql
- parameter_sql
- sessionparameter_sql
- placeholder_sql
- subquery_sql
- qualify_sql
- union_sql
- union_op
- unnest_sql
- where_sql
- window_sql
- partition_by_sql
- windowspec_sql
- withingroup_sql
- between_sql
- bracket_sql
- safebracket_sql
- all_sql
- any_sql
- exists_sql
- case_sql
- constraint_sql
- nextvaluefor_sql
- extract_sql
- trim_sql
- safeconcat_sql
- check_sql
- foreignkey_sql
- primarykey_sql
- if_sql
- matchagainst_sql
- jsonkeyvalue_sql
- jsonobject_sql
- openjsoncolumndef_sql
- openjson_sql
- in_sql
- interval_sql
- return_sql
- reference_sql
- anonymous_sql
- paren_sql
- neg_sql
- not_sql
- alias_sql
- aliases_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
- 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
- use_sql
- binary
- function_fallback_sql
- func
- format_args
- text_width
- format_time
- expressions
- op_expressions
- naked_property
- set_operation
- tag_sql
- token_sql
- userdefinedfunction_sql
- joinhint_sql
- kwarg_sql
- when_sql
- merge_sql
- tochar_sql
- dictproperty_sql
- dictrange_sql
- dictsubproperty_sql
- oncluster_sql
- clusteredbyproperty_sql
- anyvalue_sql
- querytransform_sql
- indexconstraintoption_sql
- indexcolumnconstraint_sql
- nvl2_sql
- comprehension_sql