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 date_add_interval_sql, 13 datestrtodate_sql, 14 format_time_lambda, 15 if_sql, 16 inline_array_sql, 17 json_keyvalue_comma_sql, 18 max_or_greatest, 19 min_or_least, 20 no_ilike_sql, 21 parse_date_delta_with_interval, 22 regexp_replace_sql, 23 rename_func, 24 timestrtotime_sql, 25 ts_or_ds_to_date_sql, 26) 27from sqlglot.helper import seq_get, split_num_words 28from sqlglot.tokens import TokenType 29 30logger = logging.getLogger("sqlglot") 31 32 33def _derived_table_values_to_unnest(self: BigQuery.Generator, expression: exp.Values) -> str: 34 if not expression.find_ancestor(exp.From, exp.Join): 35 return self.values_sql(expression) 36 37 alias = expression.args.get("alias") 38 39 structs = [ 40 exp.Struct( 41 expressions=[ 42 exp.alias_(value, column_name) 43 for value, column_name in zip( 44 t.expressions, 45 alias.columns 46 if alias and alias.columns 47 else (f"_c{i}" for i in range(len(t.expressions))), 48 ) 49 ] 50 ) 51 for t in expression.find_all(exp.Tuple) 52 ] 53 54 return self.unnest_sql(exp.Unnest(expressions=[exp.Array(expressions=structs)])) 55 56 57def _returnsproperty_sql(self: BigQuery.Generator, expression: exp.ReturnsProperty) -> str: 58 this = expression.this 59 if isinstance(this, exp.Schema): 60 this = f"{this.this} <{self.expressions(this)}>" 61 else: 62 this = self.sql(this) 63 return f"RETURNS {this}" 64 65 66def _create_sql(self: BigQuery.Generator, expression: exp.Create) -> str: 67 kind = expression.args["kind"] 68 returns = expression.find(exp.ReturnsProperty) 69 70 if kind.upper() == "FUNCTION" and returns and returns.args.get("is_table"): 71 expression = expression.copy() 72 expression.set("kind", "TABLE FUNCTION") 73 74 if isinstance(expression.expression, (exp.Subquery, exp.Literal)): 75 expression.set("expression", expression.expression.this) 76 77 return self.create_sql(expression) 78 79 return self.create_sql(expression) 80 81 82def _unqualify_unnest(expression: exp.Expression) -> exp.Expression: 83 """Remove references to unnest table aliases since bigquery doesn't allow them. 84 85 These are added by the optimizer's qualify_column step. 86 """ 87 from sqlglot.optimizer.scope import find_all_in_scope 88 89 if isinstance(expression, exp.Select): 90 unnest_aliases = { 91 unnest.alias 92 for unnest in find_all_in_scope(expression, exp.Unnest) 93 if isinstance(unnest.parent, (exp.From, exp.Join)) 94 } 95 if unnest_aliases: 96 for column in expression.find_all(exp.Column): 97 if column.table in unnest_aliases: 98 column.set("table", None) 99 elif column.db in unnest_aliases: 100 column.set("db", None) 101 102 return expression 103 104 105# https://issuetracker.google.com/issues/162294746 106# workaround for bigquery bug when grouping by an expression and then ordering 107# WITH x AS (SELECT 1 y) 108# SELECT y + 1 z 109# FROM x 110# GROUP BY x + 1 111# ORDER by z 112def _alias_ordered_group(expression: exp.Expression) -> exp.Expression: 113 if isinstance(expression, exp.Select): 114 group = expression.args.get("group") 115 order = expression.args.get("order") 116 117 if group and order: 118 aliases = { 119 select.this: select.args["alias"] 120 for select in expression.selects 121 if isinstance(select, exp.Alias) 122 } 123 124 for e in group.expressions: 125 alias = aliases.get(e) 126 127 if alias: 128 e.replace(exp.column(alias)) 129 130 return expression 131 132 133def _pushdown_cte_column_names(expression: exp.Expression) -> exp.Expression: 134 """BigQuery doesn't allow column names when defining a CTE, so we try to push them down.""" 135 if isinstance(expression, exp.CTE) and expression.alias_column_names: 136 cte_query = expression.this 137 138 if cte_query.is_star: 139 logger.warning( 140 "Can't push down CTE column names for star queries. Run the query through" 141 " the optimizer or use 'qualify' to expand the star projections first." 142 ) 143 return expression 144 145 column_names = expression.alias_column_names 146 expression.args["alias"].set("columns", None) 147 148 for name, select in zip(column_names, cte_query.selects): 149 to_replace = select 150 151 if isinstance(select, exp.Alias): 152 select = select.this 153 154 # Inner aliases are shadowed by the CTE column names 155 to_replace.replace(exp.alias_(select, name)) 156 157 return expression 158 159 160def _parse_timestamp(args: t.List) -> exp.StrToTime: 161 this = format_time_lambda(exp.StrToTime, "bigquery")([seq_get(args, 1), seq_get(args, 0)]) 162 this.set("zone", seq_get(args, 2)) 163 return this 164 165 166def _parse_date(args: t.List) -> exp.Date | exp.DateFromParts: 167 expr_type = exp.DateFromParts if len(args) == 3 else exp.Date 168 return expr_type.from_arg_list(args) 169 170 171def _parse_to_hex(args: t.List) -> exp.Hex | exp.MD5: 172 # TO_HEX(MD5(..)) is common in BigQuery, so it's parsed into MD5 to simplify its transpilation 173 arg = seq_get(args, 0) 174 return exp.MD5(this=arg.this) if isinstance(arg, exp.MD5Digest) else exp.Hex(this=arg) 175 176 177class BigQuery(Dialect): 178 UNNEST_COLUMN_ONLY = True 179 SUPPORTS_USER_DEFINED_TYPES = False 180 SUPPORTS_SEMI_ANTI_JOIN = False 181 LOG_BASE_FIRST = False 182 183 # https://cloud.google.com/bigquery/docs/reference/standard-sql/lexical#case_sensitivity 184 RESOLVES_IDENTIFIERS_AS_UPPERCASE = None 185 186 # bigquery udfs are case sensitive 187 NORMALIZE_FUNCTIONS = False 188 189 TIME_MAPPING = { 190 "%D": "%m/%d/%y", 191 } 192 193 ESCAPE_SEQUENCES = { 194 "\\a": "\a", 195 "\\b": "\b", 196 "\\f": "\f", 197 "\\n": "\n", 198 "\\r": "\r", 199 "\\t": "\t", 200 "\\v": "\v", 201 } 202 203 FORMAT_MAPPING = { 204 "DD": "%d", 205 "MM": "%m", 206 "MON": "%b", 207 "MONTH": "%B", 208 "YYYY": "%Y", 209 "YY": "%y", 210 "HH": "%I", 211 "HH12": "%I", 212 "HH24": "%H", 213 "MI": "%M", 214 "SS": "%S", 215 "SSSSS": "%f", 216 "TZH": "%z", 217 } 218 219 # The _PARTITIONTIME and _PARTITIONDATE pseudo-columns are not returned by a SELECT * statement 220 # https://cloud.google.com/bigquery/docs/querying-partitioned-tables#query_an_ingestion-time_partitioned_table 221 PSEUDOCOLUMNS = {"_PARTITIONTIME", "_PARTITIONDATE"} 222 223 @classmethod 224 def normalize_identifier(cls, expression: E) -> E: 225 if isinstance(expression, exp.Identifier): 226 parent = expression.parent 227 while isinstance(parent, exp.Dot): 228 parent = parent.parent 229 230 # In BigQuery, CTEs aren't case-sensitive, but table names are (by default, at least). 231 # The following check is essentially a heuristic to detect tables based on whether or 232 # not they're qualified. It also avoids normalizing UDFs, because they're case-sensitive. 233 if ( 234 not isinstance(parent, exp.UserDefinedFunction) 235 and not (isinstance(parent, exp.Table) and parent.db) 236 and not expression.meta.get("is_table") 237 ): 238 expression.set("this", expression.this.lower()) 239 240 return expression 241 242 class Tokenizer(tokens.Tokenizer): 243 QUOTES = ["'", '"', '"""', "'''"] 244 COMMENTS = ["--", "#", ("/*", "*/")] 245 IDENTIFIERS = ["`"] 246 STRING_ESCAPES = ["\\"] 247 248 HEX_STRINGS = [("0x", ""), ("0X", "")] 249 250 BYTE_STRINGS = [ 251 (prefix + q, q) for q in t.cast(t.List[str], QUOTES) for prefix in ("b", "B") 252 ] 253 254 RAW_STRINGS = [ 255 (prefix + q, q) for q in t.cast(t.List[str], QUOTES) for prefix in ("r", "R") 256 ] 257 258 KEYWORDS = { 259 **tokens.Tokenizer.KEYWORDS, 260 "ANY TYPE": TokenType.VARIANT, 261 "BEGIN": TokenType.COMMAND, 262 "BEGIN TRANSACTION": TokenType.BEGIN, 263 "BYTES": TokenType.BINARY, 264 "CURRENT_DATETIME": TokenType.CURRENT_DATETIME, 265 "DECLARE": TokenType.COMMAND, 266 "FLOAT64": TokenType.DOUBLE, 267 "FOR SYSTEM_TIME": TokenType.TIMESTAMP_SNAPSHOT, 268 "INT64": TokenType.BIGINT, 269 "MODEL": TokenType.MODEL, 270 "NOT DETERMINISTIC": TokenType.VOLATILE, 271 "RECORD": TokenType.STRUCT, 272 "TIMESTAMP": TokenType.TIMESTAMPTZ, 273 } 274 KEYWORDS.pop("DIV") 275 276 class Parser(parser.Parser): 277 PREFIXED_PIVOT_COLUMNS = True 278 279 LOG_DEFAULTS_TO_LN = True 280 281 FUNCTIONS = { 282 **parser.Parser.FUNCTIONS, 283 "DATE": _parse_date, 284 "DATE_ADD": parse_date_delta_with_interval(exp.DateAdd), 285 "DATE_SUB": parse_date_delta_with_interval(exp.DateSub), 286 "DATE_TRUNC": lambda args: exp.DateTrunc( 287 unit=exp.Literal.string(str(seq_get(args, 1))), 288 this=seq_get(args, 0), 289 ), 290 "DATETIME_ADD": parse_date_delta_with_interval(exp.DatetimeAdd), 291 "DATETIME_SUB": parse_date_delta_with_interval(exp.DatetimeSub), 292 "DIV": binary_from_function(exp.IntDiv), 293 "GENERATE_ARRAY": exp.GenerateSeries.from_arg_list, 294 "MD5": exp.MD5Digest.from_arg_list, 295 "TO_HEX": _parse_to_hex, 296 "PARSE_DATE": lambda args: format_time_lambda(exp.StrToDate, "bigquery")( 297 [seq_get(args, 1), seq_get(args, 0)] 298 ), 299 "PARSE_TIMESTAMP": _parse_timestamp, 300 "REGEXP_CONTAINS": exp.RegexpLike.from_arg_list, 301 "REGEXP_EXTRACT": lambda args: exp.RegexpExtract( 302 this=seq_get(args, 0), 303 expression=seq_get(args, 1), 304 position=seq_get(args, 2), 305 occurrence=seq_get(args, 3), 306 group=exp.Literal.number(1) if re.compile(args[1].name).groups == 1 else None, 307 ), 308 "SHA256": lambda args: exp.SHA2(this=seq_get(args, 0), length=exp.Literal.number(256)), 309 "SHA512": lambda args: exp.SHA2(this=seq_get(args, 0), length=exp.Literal.number(512)), 310 "SPLIT": lambda args: exp.Split( 311 # https://cloud.google.com/bigquery/docs/reference/standard-sql/string_functions#split 312 this=seq_get(args, 0), 313 expression=seq_get(args, 1) or exp.Literal.string(","), 314 ), 315 "TIME_ADD": parse_date_delta_with_interval(exp.TimeAdd), 316 "TIME_SUB": parse_date_delta_with_interval(exp.TimeSub), 317 "TIMESTAMP_ADD": parse_date_delta_with_interval(exp.TimestampAdd), 318 "TIMESTAMP_SUB": parse_date_delta_with_interval(exp.TimestampSub), 319 "TO_JSON_STRING": exp.JSONFormat.from_arg_list, 320 } 321 322 FUNCTION_PARSERS = { 323 **parser.Parser.FUNCTION_PARSERS, 324 "ARRAY": lambda self: self.expression(exp.Array, expressions=[self._parse_statement()]), 325 } 326 FUNCTION_PARSERS.pop("TRIM") 327 328 NO_PAREN_FUNCTIONS = { 329 **parser.Parser.NO_PAREN_FUNCTIONS, 330 TokenType.CURRENT_DATETIME: exp.CurrentDatetime, 331 } 332 333 NESTED_TYPE_TOKENS = { 334 *parser.Parser.NESTED_TYPE_TOKENS, 335 TokenType.TABLE, 336 } 337 338 ID_VAR_TOKENS = { 339 *parser.Parser.ID_VAR_TOKENS, 340 TokenType.VALUES, 341 } 342 343 PROPERTY_PARSERS = { 344 **parser.Parser.PROPERTY_PARSERS, 345 "NOT DETERMINISTIC": lambda self: self.expression( 346 exp.StabilityProperty, this=exp.Literal.string("VOLATILE") 347 ), 348 "OPTIONS": lambda self: self._parse_with_property(), 349 } 350 351 CONSTRAINT_PARSERS = { 352 **parser.Parser.CONSTRAINT_PARSERS, 353 "OPTIONS": lambda self: exp.Properties(expressions=self._parse_with_property()), 354 } 355 356 RANGE_PARSERS = parser.Parser.RANGE_PARSERS.copy() 357 RANGE_PARSERS.pop(TokenType.OVERLAPS, None) 358 359 NULL_TOKENS = {TokenType.NULL, TokenType.UNKNOWN} 360 361 def _parse_table_part(self, schema: bool = False) -> t.Optional[exp.Expression]: 362 this = super()._parse_table_part(schema=schema) or self._parse_number() 363 364 # https://cloud.google.com/bigquery/docs/reference/standard-sql/lexical#table_names 365 if isinstance(this, exp.Identifier): 366 table_name = this.name 367 while self._match(TokenType.DASH, advance=False) and self._next: 368 self._advance(2) 369 table_name += f"-{self._prev.text}" 370 371 this = exp.Identifier(this=table_name, quoted=this.args.get("quoted")) 372 elif isinstance(this, exp.Literal): 373 table_name = this.name 374 375 if ( 376 self._curr 377 and self._prev.end == self._curr.start - 1 378 and self._parse_var(any_token=True) 379 ): 380 table_name += self._prev.text 381 382 this = exp.Identifier(this=table_name, quoted=True) 383 384 return this 385 386 def _parse_table_parts(self, schema: bool = False) -> exp.Table: 387 table = super()._parse_table_parts(schema=schema) 388 if isinstance(table.this, exp.Identifier) and "." in table.name: 389 catalog, db, this, *rest = ( 390 t.cast(t.Optional[exp.Expression], exp.to_identifier(x)) 391 for x in split_num_words(table.name, ".", 3) 392 ) 393 394 if rest and this: 395 this = exp.Dot.build(t.cast(t.List[exp.Expression], [this, *rest])) 396 397 table = exp.Table(this=this, db=db, catalog=catalog) 398 399 return table 400 401 def _parse_json_object(self) -> exp.JSONObject: 402 json_object = super()._parse_json_object() 403 array_kv_pair = seq_get(json_object.expressions, 0) 404 405 # Converts BQ's "signature 2" of JSON_OBJECT into SQLGlot's canonical representation 406 # https://cloud.google.com/bigquery/docs/reference/standard-sql/json_functions#json_object_signature2 407 if ( 408 array_kv_pair 409 and isinstance(array_kv_pair.this, exp.Array) 410 and isinstance(array_kv_pair.expression, exp.Array) 411 ): 412 keys = array_kv_pair.this.expressions 413 values = array_kv_pair.expression.expressions 414 415 json_object.set( 416 "expressions", 417 [exp.JSONKeyValue(this=k, expression=v) for k, v in zip(keys, values)], 418 ) 419 420 return json_object 421 422 class Generator(generator.Generator): 423 EXPLICIT_UNION = True 424 INTERVAL_ALLOWS_PLURAL_FORM = False 425 JOIN_HINTS = False 426 QUERY_HINTS = False 427 TABLE_HINTS = False 428 LIMIT_FETCH = "LIMIT" 429 RENAME_TABLE_WITH_DB = False 430 NVL2_SUPPORTED = False 431 UNNEST_WITH_ORDINALITY = False 432 COLLATE_IS_FUNC = True 433 434 TRANSFORMS = { 435 **generator.Generator.TRANSFORMS, 436 exp.ApproxDistinct: rename_func("APPROX_COUNT_DISTINCT"), 437 exp.ArraySize: rename_func("ARRAY_LENGTH"), 438 exp.Cast: transforms.preprocess([transforms.remove_precision_parameterized_types]), 439 exp.CollateProperty: lambda self, e: f"DEFAULT COLLATE {self.sql(e, 'this')}" 440 if e.args.get("default") 441 else f"COLLATE {self.sql(e, 'this')}", 442 exp.Create: _create_sql, 443 exp.CTE: transforms.preprocess([_pushdown_cte_column_names]), 444 exp.DateAdd: date_add_interval_sql("DATE", "ADD"), 445 exp.DateDiff: lambda self, e: f"DATE_DIFF({self.sql(e, 'this')}, {self.sql(e, 'expression')}, {self.sql(e.args.get('unit', 'DAY'))})", 446 exp.DateFromParts: rename_func("DATE"), 447 exp.DateStrToDate: datestrtodate_sql, 448 exp.DateSub: date_add_interval_sql("DATE", "SUB"), 449 exp.DatetimeAdd: date_add_interval_sql("DATETIME", "ADD"), 450 exp.DatetimeSub: date_add_interval_sql("DATETIME", "SUB"), 451 exp.DateTrunc: lambda self, e: self.func("DATE_TRUNC", e.this, e.text("unit")), 452 exp.GenerateSeries: rename_func("GENERATE_ARRAY"), 453 exp.GroupConcat: rename_func("STRING_AGG"), 454 exp.Hex: rename_func("TO_HEX"), 455 exp.If: if_sql(false_value="NULL"), 456 exp.ILike: no_ilike_sql, 457 exp.IntDiv: rename_func("DIV"), 458 exp.JSONFormat: rename_func("TO_JSON_STRING"), 459 exp.JSONKeyValue: json_keyvalue_comma_sql, 460 exp.Max: max_or_greatest, 461 exp.MD5: lambda self, e: self.func("TO_HEX", self.func("MD5", e.this)), 462 exp.MD5Digest: rename_func("MD5"), 463 exp.Min: min_or_least, 464 exp.PartitionedByProperty: lambda self, e: f"PARTITION BY {self.sql(e, 'this')}", 465 exp.RegexpExtract: lambda self, e: self.func( 466 "REGEXP_EXTRACT", 467 e.this, 468 e.expression, 469 e.args.get("position"), 470 e.args.get("occurrence"), 471 ), 472 exp.RegexpReplace: regexp_replace_sql, 473 exp.RegexpLike: rename_func("REGEXP_CONTAINS"), 474 exp.ReturnsProperty: _returnsproperty_sql, 475 exp.Select: transforms.preprocess( 476 [ 477 transforms.explode_to_unnest(), 478 _unqualify_unnest, 479 transforms.eliminate_distinct_on, 480 _alias_ordered_group, 481 transforms.eliminate_semi_and_anti_joins, 482 ] 483 ), 484 exp.SHA2: lambda self, e: self.func( 485 f"SHA256" if e.text("length") == "256" else "SHA512", e.this 486 ), 487 exp.StabilityProperty: lambda self, e: f"DETERMINISTIC" 488 if e.name == "IMMUTABLE" 489 else "NOT DETERMINISTIC", 490 exp.StrToDate: lambda self, e: f"PARSE_DATE({self.format_time(e)}, {self.sql(e, 'this')})", 491 exp.StrToTime: lambda self, e: self.func( 492 "PARSE_TIMESTAMP", self.format_time(e), e.this, e.args.get("zone") 493 ), 494 exp.TimeAdd: date_add_interval_sql("TIME", "ADD"), 495 exp.TimeSub: date_add_interval_sql("TIME", "SUB"), 496 exp.TimestampAdd: date_add_interval_sql("TIMESTAMP", "ADD"), 497 exp.TimestampSub: date_add_interval_sql("TIMESTAMP", "SUB"), 498 exp.TimeStrToTime: timestrtotime_sql, 499 exp.Trim: lambda self, e: self.func(f"TRIM", e.this, e.expression), 500 exp.TsOrDsAdd: date_add_interval_sql("DATE", "ADD"), 501 exp.TsOrDsToDate: ts_or_ds_to_date_sql("bigquery"), 502 exp.Unhex: rename_func("FROM_HEX"), 503 exp.Values: _derived_table_values_to_unnest, 504 exp.VariancePop: rename_func("VAR_POP"), 505 } 506 507 TYPE_MAPPING = { 508 **generator.Generator.TYPE_MAPPING, 509 exp.DataType.Type.BIGDECIMAL: "BIGNUMERIC", 510 exp.DataType.Type.BIGINT: "INT64", 511 exp.DataType.Type.BINARY: "BYTES", 512 exp.DataType.Type.BOOLEAN: "BOOL", 513 exp.DataType.Type.CHAR: "STRING", 514 exp.DataType.Type.DECIMAL: "NUMERIC", 515 exp.DataType.Type.DOUBLE: "FLOAT64", 516 exp.DataType.Type.FLOAT: "FLOAT64", 517 exp.DataType.Type.INT: "INT64", 518 exp.DataType.Type.NCHAR: "STRING", 519 exp.DataType.Type.NVARCHAR: "STRING", 520 exp.DataType.Type.SMALLINT: "INT64", 521 exp.DataType.Type.TEXT: "STRING", 522 exp.DataType.Type.TIMESTAMP: "DATETIME", 523 exp.DataType.Type.TIMESTAMPTZ: "TIMESTAMP", 524 exp.DataType.Type.TIMESTAMPLTZ: "TIMESTAMP", 525 exp.DataType.Type.TINYINT: "INT64", 526 exp.DataType.Type.VARBINARY: "BYTES", 527 exp.DataType.Type.VARCHAR: "STRING", 528 exp.DataType.Type.VARIANT: "ANY TYPE", 529 } 530 531 PROPERTIES_LOCATION = { 532 **generator.Generator.PROPERTIES_LOCATION, 533 exp.PartitionedByProperty: exp.Properties.Location.POST_SCHEMA, 534 exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED, 535 } 536 537 # from: https://cloud.google.com/bigquery/docs/reference/standard-sql/lexical#reserved_keywords 538 RESERVED_KEYWORDS = { 539 *generator.Generator.RESERVED_KEYWORDS, 540 "all", 541 "and", 542 "any", 543 "array", 544 "as", 545 "asc", 546 "assert_rows_modified", 547 "at", 548 "between", 549 "by", 550 "case", 551 "cast", 552 "collate", 553 "contains", 554 "create", 555 "cross", 556 "cube", 557 "current", 558 "default", 559 "define", 560 "desc", 561 "distinct", 562 "else", 563 "end", 564 "enum", 565 "escape", 566 "except", 567 "exclude", 568 "exists", 569 "extract", 570 "false", 571 "fetch", 572 "following", 573 "for", 574 "from", 575 "full", 576 "group", 577 "grouping", 578 "groups", 579 "hash", 580 "having", 581 "if", 582 "ignore", 583 "in", 584 "inner", 585 "intersect", 586 "interval", 587 "into", 588 "is", 589 "join", 590 "lateral", 591 "left", 592 "like", 593 "limit", 594 "lookup", 595 "merge", 596 "natural", 597 "new", 598 "no", 599 "not", 600 "null", 601 "nulls", 602 "of", 603 "on", 604 "or", 605 "order", 606 "outer", 607 "over", 608 "partition", 609 "preceding", 610 "proto", 611 "qualify", 612 "range", 613 "recursive", 614 "respect", 615 "right", 616 "rollup", 617 "rows", 618 "select", 619 "set", 620 "some", 621 "struct", 622 "tablesample", 623 "then", 624 "to", 625 "treat", 626 "true", 627 "unbounded", 628 "union", 629 "unnest", 630 "using", 631 "when", 632 "where", 633 "window", 634 "with", 635 "within", 636 } 637 638 def eq_sql(self, expression: exp.EQ) -> str: 639 # Operands of = cannot be NULL in BigQuery 640 if isinstance(expression.left, exp.Null) or isinstance(expression.right, exp.Null): 641 return "NULL" 642 643 return self.binary(expression, "=") 644 645 def attimezone_sql(self, expression: exp.AtTimeZone) -> str: 646 parent = expression.parent 647 648 # BigQuery allows CAST(.. AS {STRING|TIMESTAMP} [FORMAT <fmt> [AT TIME ZONE <tz>]]). 649 # Only the TIMESTAMP one should use the below conversion, when AT TIME ZONE is included. 650 if not isinstance(parent, exp.Cast) or not parent.to.is_type("text"): 651 return self.func( 652 "TIMESTAMP", self.func("DATETIME", expression.this, expression.args.get("zone")) 653 ) 654 655 return super().attimezone_sql(expression) 656 657 def trycast_sql(self, expression: exp.TryCast) -> str: 658 return self.cast_sql(expression, safe_prefix="SAFE_") 659 660 def cte_sql(self, expression: exp.CTE) -> str: 661 if expression.alias_column_names: 662 self.unsupported("Column names in CTE definition are not supported.") 663 return super().cte_sql(expression) 664 665 def array_sql(self, expression: exp.Array) -> str: 666 first_arg = seq_get(expression.expressions, 0) 667 if isinstance(first_arg, exp.Subqueryable): 668 return f"ARRAY{self.wrap(self.sql(first_arg))}" 669 670 return inline_array_sql(self, expression) 671 672 def transaction_sql(self, *_) -> str: 673 return "BEGIN TRANSACTION" 674 675 def commit_sql(self, *_) -> str: 676 return "COMMIT TRANSACTION" 677 678 def rollback_sql(self, *_) -> str: 679 return "ROLLBACK TRANSACTION" 680 681 def in_unnest_op(self, expression: exp.Unnest) -> str: 682 return self.sql(expression) 683 684 def except_op(self, expression: exp.Except) -> str: 685 if not expression.args.get("distinct", False): 686 self.unsupported("EXCEPT without DISTINCT is not supported in BigQuery") 687 return f"EXCEPT{' DISTINCT' if expression.args.get('distinct') else ' ALL'}" 688 689 def intersect_op(self, expression: exp.Intersect) -> str: 690 if not expression.args.get("distinct", False): 691 self.unsupported("INTERSECT without DISTINCT is not supported in BigQuery") 692 return f"INTERSECT{' DISTINCT' if expression.args.get('distinct') else ' ALL'}" 693 694 def with_properties(self, properties: exp.Properties) -> str: 695 return self.properties(properties, prefix=self.seg("OPTIONS")) 696 697 def version_sql(self, expression: exp.Version) -> str: 698 if expression.name == "TIMESTAMP": 699 expression = expression.copy() 700 expression.set("this", "SYSTEM_TIME") 701 return super().version_sql(expression)
logger =
<Logger sqlglot (WARNING)>
178class BigQuery(Dialect): 179 UNNEST_COLUMN_ONLY = True 180 SUPPORTS_USER_DEFINED_TYPES = False 181 SUPPORTS_SEMI_ANTI_JOIN = False 182 LOG_BASE_FIRST = False 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 ESCAPE_SEQUENCES = { 195 "\\a": "\a", 196 "\\b": "\b", 197 "\\f": "\f", 198 "\\n": "\n", 199 "\\r": "\r", 200 "\\t": "\t", 201 "\\v": "\v", 202 } 203 204 FORMAT_MAPPING = { 205 "DD": "%d", 206 "MM": "%m", 207 "MON": "%b", 208 "MONTH": "%B", 209 "YYYY": "%Y", 210 "YY": "%y", 211 "HH": "%I", 212 "HH12": "%I", 213 "HH24": "%H", 214 "MI": "%M", 215 "SS": "%S", 216 "SSSSS": "%f", 217 "TZH": "%z", 218 } 219 220 # The _PARTITIONTIME and _PARTITIONDATE pseudo-columns are not returned by a SELECT * statement 221 # https://cloud.google.com/bigquery/docs/querying-partitioned-tables#query_an_ingestion-time_partitioned_table 222 PSEUDOCOLUMNS = {"_PARTITIONTIME", "_PARTITIONDATE"} 223 224 @classmethod 225 def normalize_identifier(cls, expression: E) -> E: 226 if isinstance(expression, exp.Identifier): 227 parent = expression.parent 228 while isinstance(parent, exp.Dot): 229 parent = parent.parent 230 231 # In BigQuery, CTEs aren't case-sensitive, but table names are (by default, at least). 232 # The following check is essentially a heuristic to detect tables based on whether or 233 # not they're qualified. It also avoids normalizing UDFs, because they're case-sensitive. 234 if ( 235 not isinstance(parent, exp.UserDefinedFunction) 236 and not (isinstance(parent, exp.Table) and parent.db) 237 and not expression.meta.get("is_table") 238 ): 239 expression.set("this", expression.this.lower()) 240 241 return expression 242 243 class Tokenizer(tokens.Tokenizer): 244 QUOTES = ["'", '"', '"""', "'''"] 245 COMMENTS = ["--", "#", ("/*", "*/")] 246 IDENTIFIERS = ["`"] 247 STRING_ESCAPES = ["\\"] 248 249 HEX_STRINGS = [("0x", ""), ("0X", "")] 250 251 BYTE_STRINGS = [ 252 (prefix + q, q) for q in t.cast(t.List[str], QUOTES) for prefix in ("b", "B") 253 ] 254 255 RAW_STRINGS = [ 256 (prefix + q, q) for q in t.cast(t.List[str], QUOTES) for prefix in ("r", "R") 257 ] 258 259 KEYWORDS = { 260 **tokens.Tokenizer.KEYWORDS, 261 "ANY TYPE": TokenType.VARIANT, 262 "BEGIN": TokenType.COMMAND, 263 "BEGIN TRANSACTION": TokenType.BEGIN, 264 "BYTES": TokenType.BINARY, 265 "CURRENT_DATETIME": TokenType.CURRENT_DATETIME, 266 "DECLARE": TokenType.COMMAND, 267 "FLOAT64": TokenType.DOUBLE, 268 "FOR SYSTEM_TIME": TokenType.TIMESTAMP_SNAPSHOT, 269 "INT64": TokenType.BIGINT, 270 "MODEL": TokenType.MODEL, 271 "NOT DETERMINISTIC": TokenType.VOLATILE, 272 "RECORD": TokenType.STRUCT, 273 "TIMESTAMP": TokenType.TIMESTAMPTZ, 274 } 275 KEYWORDS.pop("DIV") 276 277 class Parser(parser.Parser): 278 PREFIXED_PIVOT_COLUMNS = True 279 280 LOG_DEFAULTS_TO_LN = True 281 282 FUNCTIONS = { 283 **parser.Parser.FUNCTIONS, 284 "DATE": _parse_date, 285 "DATE_ADD": parse_date_delta_with_interval(exp.DateAdd), 286 "DATE_SUB": parse_date_delta_with_interval(exp.DateSub), 287 "DATE_TRUNC": lambda args: exp.DateTrunc( 288 unit=exp.Literal.string(str(seq_get(args, 1))), 289 this=seq_get(args, 0), 290 ), 291 "DATETIME_ADD": parse_date_delta_with_interval(exp.DatetimeAdd), 292 "DATETIME_SUB": parse_date_delta_with_interval(exp.DatetimeSub), 293 "DIV": binary_from_function(exp.IntDiv), 294 "GENERATE_ARRAY": exp.GenerateSeries.from_arg_list, 295 "MD5": exp.MD5Digest.from_arg_list, 296 "TO_HEX": _parse_to_hex, 297 "PARSE_DATE": lambda args: format_time_lambda(exp.StrToDate, "bigquery")( 298 [seq_get(args, 1), seq_get(args, 0)] 299 ), 300 "PARSE_TIMESTAMP": _parse_timestamp, 301 "REGEXP_CONTAINS": exp.RegexpLike.from_arg_list, 302 "REGEXP_EXTRACT": lambda args: exp.RegexpExtract( 303 this=seq_get(args, 0), 304 expression=seq_get(args, 1), 305 position=seq_get(args, 2), 306 occurrence=seq_get(args, 3), 307 group=exp.Literal.number(1) if re.compile(args[1].name).groups == 1 else None, 308 ), 309 "SHA256": lambda args: exp.SHA2(this=seq_get(args, 0), length=exp.Literal.number(256)), 310 "SHA512": lambda args: exp.SHA2(this=seq_get(args, 0), length=exp.Literal.number(512)), 311 "SPLIT": lambda args: exp.Split( 312 # https://cloud.google.com/bigquery/docs/reference/standard-sql/string_functions#split 313 this=seq_get(args, 0), 314 expression=seq_get(args, 1) or exp.Literal.string(","), 315 ), 316 "TIME_ADD": parse_date_delta_with_interval(exp.TimeAdd), 317 "TIME_SUB": parse_date_delta_with_interval(exp.TimeSub), 318 "TIMESTAMP_ADD": parse_date_delta_with_interval(exp.TimestampAdd), 319 "TIMESTAMP_SUB": parse_date_delta_with_interval(exp.TimestampSub), 320 "TO_JSON_STRING": exp.JSONFormat.from_arg_list, 321 } 322 323 FUNCTION_PARSERS = { 324 **parser.Parser.FUNCTION_PARSERS, 325 "ARRAY": lambda self: self.expression(exp.Array, expressions=[self._parse_statement()]), 326 } 327 FUNCTION_PARSERS.pop("TRIM") 328 329 NO_PAREN_FUNCTIONS = { 330 **parser.Parser.NO_PAREN_FUNCTIONS, 331 TokenType.CURRENT_DATETIME: exp.CurrentDatetime, 332 } 333 334 NESTED_TYPE_TOKENS = { 335 *parser.Parser.NESTED_TYPE_TOKENS, 336 TokenType.TABLE, 337 } 338 339 ID_VAR_TOKENS = { 340 *parser.Parser.ID_VAR_TOKENS, 341 TokenType.VALUES, 342 } 343 344 PROPERTY_PARSERS = { 345 **parser.Parser.PROPERTY_PARSERS, 346 "NOT DETERMINISTIC": lambda self: self.expression( 347 exp.StabilityProperty, this=exp.Literal.string("VOLATILE") 348 ), 349 "OPTIONS": lambda self: self._parse_with_property(), 350 } 351 352 CONSTRAINT_PARSERS = { 353 **parser.Parser.CONSTRAINT_PARSERS, 354 "OPTIONS": lambda self: exp.Properties(expressions=self._parse_with_property()), 355 } 356 357 RANGE_PARSERS = parser.Parser.RANGE_PARSERS.copy() 358 RANGE_PARSERS.pop(TokenType.OVERLAPS, None) 359 360 NULL_TOKENS = {TokenType.NULL, TokenType.UNKNOWN} 361 362 def _parse_table_part(self, schema: bool = False) -> t.Optional[exp.Expression]: 363 this = super()._parse_table_part(schema=schema) or self._parse_number() 364 365 # https://cloud.google.com/bigquery/docs/reference/standard-sql/lexical#table_names 366 if isinstance(this, exp.Identifier): 367 table_name = this.name 368 while self._match(TokenType.DASH, advance=False) and self._next: 369 self._advance(2) 370 table_name += f"-{self._prev.text}" 371 372 this = exp.Identifier(this=table_name, quoted=this.args.get("quoted")) 373 elif isinstance(this, exp.Literal): 374 table_name = this.name 375 376 if ( 377 self._curr 378 and self._prev.end == self._curr.start - 1 379 and self._parse_var(any_token=True) 380 ): 381 table_name += self._prev.text 382 383 this = exp.Identifier(this=table_name, quoted=True) 384 385 return this 386 387 def _parse_table_parts(self, schema: bool = False) -> exp.Table: 388 table = super()._parse_table_parts(schema=schema) 389 if isinstance(table.this, exp.Identifier) and "." in table.name: 390 catalog, db, this, *rest = ( 391 t.cast(t.Optional[exp.Expression], exp.to_identifier(x)) 392 for x in split_num_words(table.name, ".", 3) 393 ) 394 395 if rest and this: 396 this = exp.Dot.build(t.cast(t.List[exp.Expression], [this, *rest])) 397 398 table = exp.Table(this=this, db=db, catalog=catalog) 399 400 return table 401 402 def _parse_json_object(self) -> exp.JSONObject: 403 json_object = super()._parse_json_object() 404 array_kv_pair = seq_get(json_object.expressions, 0) 405 406 # Converts BQ's "signature 2" of JSON_OBJECT into SQLGlot's canonical representation 407 # https://cloud.google.com/bigquery/docs/reference/standard-sql/json_functions#json_object_signature2 408 if ( 409 array_kv_pair 410 and isinstance(array_kv_pair.this, exp.Array) 411 and isinstance(array_kv_pair.expression, exp.Array) 412 ): 413 keys = array_kv_pair.this.expressions 414 values = array_kv_pair.expression.expressions 415 416 json_object.set( 417 "expressions", 418 [exp.JSONKeyValue(this=k, expression=v) for k, v in zip(keys, values)], 419 ) 420 421 return json_object 422 423 class Generator(generator.Generator): 424 EXPLICIT_UNION = True 425 INTERVAL_ALLOWS_PLURAL_FORM = False 426 JOIN_HINTS = False 427 QUERY_HINTS = False 428 TABLE_HINTS = False 429 LIMIT_FETCH = "LIMIT" 430 RENAME_TABLE_WITH_DB = False 431 NVL2_SUPPORTED = False 432 UNNEST_WITH_ORDINALITY = False 433 COLLATE_IS_FUNC = True 434 435 TRANSFORMS = { 436 **generator.Generator.TRANSFORMS, 437 exp.ApproxDistinct: rename_func("APPROX_COUNT_DISTINCT"), 438 exp.ArraySize: rename_func("ARRAY_LENGTH"), 439 exp.Cast: transforms.preprocess([transforms.remove_precision_parameterized_types]), 440 exp.CollateProperty: lambda self, e: f"DEFAULT COLLATE {self.sql(e, 'this')}" 441 if e.args.get("default") 442 else f"COLLATE {self.sql(e, 'this')}", 443 exp.Create: _create_sql, 444 exp.CTE: transforms.preprocess([_pushdown_cte_column_names]), 445 exp.DateAdd: date_add_interval_sql("DATE", "ADD"), 446 exp.DateDiff: lambda self, e: f"DATE_DIFF({self.sql(e, 'this')}, {self.sql(e, 'expression')}, {self.sql(e.args.get('unit', 'DAY'))})", 447 exp.DateFromParts: rename_func("DATE"), 448 exp.DateStrToDate: datestrtodate_sql, 449 exp.DateSub: date_add_interval_sql("DATE", "SUB"), 450 exp.DatetimeAdd: date_add_interval_sql("DATETIME", "ADD"), 451 exp.DatetimeSub: date_add_interval_sql("DATETIME", "SUB"), 452 exp.DateTrunc: lambda self, e: self.func("DATE_TRUNC", e.this, e.text("unit")), 453 exp.GenerateSeries: rename_func("GENERATE_ARRAY"), 454 exp.GroupConcat: rename_func("STRING_AGG"), 455 exp.Hex: rename_func("TO_HEX"), 456 exp.If: if_sql(false_value="NULL"), 457 exp.ILike: no_ilike_sql, 458 exp.IntDiv: rename_func("DIV"), 459 exp.JSONFormat: rename_func("TO_JSON_STRING"), 460 exp.JSONKeyValue: json_keyvalue_comma_sql, 461 exp.Max: max_or_greatest, 462 exp.MD5: lambda self, e: self.func("TO_HEX", self.func("MD5", e.this)), 463 exp.MD5Digest: rename_func("MD5"), 464 exp.Min: min_or_least, 465 exp.PartitionedByProperty: lambda self, e: f"PARTITION BY {self.sql(e, 'this')}", 466 exp.RegexpExtract: lambda self, e: self.func( 467 "REGEXP_EXTRACT", 468 e.this, 469 e.expression, 470 e.args.get("position"), 471 e.args.get("occurrence"), 472 ), 473 exp.RegexpReplace: regexp_replace_sql, 474 exp.RegexpLike: rename_func("REGEXP_CONTAINS"), 475 exp.ReturnsProperty: _returnsproperty_sql, 476 exp.Select: transforms.preprocess( 477 [ 478 transforms.explode_to_unnest(), 479 _unqualify_unnest, 480 transforms.eliminate_distinct_on, 481 _alias_ordered_group, 482 transforms.eliminate_semi_and_anti_joins, 483 ] 484 ), 485 exp.SHA2: lambda self, e: self.func( 486 f"SHA256" if e.text("length") == "256" else "SHA512", e.this 487 ), 488 exp.StabilityProperty: lambda self, e: f"DETERMINISTIC" 489 if e.name == "IMMUTABLE" 490 else "NOT DETERMINISTIC", 491 exp.StrToDate: lambda self, e: f"PARSE_DATE({self.format_time(e)}, {self.sql(e, 'this')})", 492 exp.StrToTime: lambda self, e: self.func( 493 "PARSE_TIMESTAMP", self.format_time(e), e.this, e.args.get("zone") 494 ), 495 exp.TimeAdd: date_add_interval_sql("TIME", "ADD"), 496 exp.TimeSub: date_add_interval_sql("TIME", "SUB"), 497 exp.TimestampAdd: date_add_interval_sql("TIMESTAMP", "ADD"), 498 exp.TimestampSub: date_add_interval_sql("TIMESTAMP", "SUB"), 499 exp.TimeStrToTime: timestrtotime_sql, 500 exp.Trim: lambda self, e: self.func(f"TRIM", e.this, e.expression), 501 exp.TsOrDsAdd: date_add_interval_sql("DATE", "ADD"), 502 exp.TsOrDsToDate: ts_or_ds_to_date_sql("bigquery"), 503 exp.Unhex: rename_func("FROM_HEX"), 504 exp.Values: _derived_table_values_to_unnest, 505 exp.VariancePop: rename_func("VAR_POP"), 506 } 507 508 TYPE_MAPPING = { 509 **generator.Generator.TYPE_MAPPING, 510 exp.DataType.Type.BIGDECIMAL: "BIGNUMERIC", 511 exp.DataType.Type.BIGINT: "INT64", 512 exp.DataType.Type.BINARY: "BYTES", 513 exp.DataType.Type.BOOLEAN: "BOOL", 514 exp.DataType.Type.CHAR: "STRING", 515 exp.DataType.Type.DECIMAL: "NUMERIC", 516 exp.DataType.Type.DOUBLE: "FLOAT64", 517 exp.DataType.Type.FLOAT: "FLOAT64", 518 exp.DataType.Type.INT: "INT64", 519 exp.DataType.Type.NCHAR: "STRING", 520 exp.DataType.Type.NVARCHAR: "STRING", 521 exp.DataType.Type.SMALLINT: "INT64", 522 exp.DataType.Type.TEXT: "STRING", 523 exp.DataType.Type.TIMESTAMP: "DATETIME", 524 exp.DataType.Type.TIMESTAMPTZ: "TIMESTAMP", 525 exp.DataType.Type.TIMESTAMPLTZ: "TIMESTAMP", 526 exp.DataType.Type.TINYINT: "INT64", 527 exp.DataType.Type.VARBINARY: "BYTES", 528 exp.DataType.Type.VARCHAR: "STRING", 529 exp.DataType.Type.VARIANT: "ANY TYPE", 530 } 531 532 PROPERTIES_LOCATION = { 533 **generator.Generator.PROPERTIES_LOCATION, 534 exp.PartitionedByProperty: exp.Properties.Location.POST_SCHEMA, 535 exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED, 536 } 537 538 # from: https://cloud.google.com/bigquery/docs/reference/standard-sql/lexical#reserved_keywords 539 RESERVED_KEYWORDS = { 540 *generator.Generator.RESERVED_KEYWORDS, 541 "all", 542 "and", 543 "any", 544 "array", 545 "as", 546 "asc", 547 "assert_rows_modified", 548 "at", 549 "between", 550 "by", 551 "case", 552 "cast", 553 "collate", 554 "contains", 555 "create", 556 "cross", 557 "cube", 558 "current", 559 "default", 560 "define", 561 "desc", 562 "distinct", 563 "else", 564 "end", 565 "enum", 566 "escape", 567 "except", 568 "exclude", 569 "exists", 570 "extract", 571 "false", 572 "fetch", 573 "following", 574 "for", 575 "from", 576 "full", 577 "group", 578 "grouping", 579 "groups", 580 "hash", 581 "having", 582 "if", 583 "ignore", 584 "in", 585 "inner", 586 "intersect", 587 "interval", 588 "into", 589 "is", 590 "join", 591 "lateral", 592 "left", 593 "like", 594 "limit", 595 "lookup", 596 "merge", 597 "natural", 598 "new", 599 "no", 600 "not", 601 "null", 602 "nulls", 603 "of", 604 "on", 605 "or", 606 "order", 607 "outer", 608 "over", 609 "partition", 610 "preceding", 611 "proto", 612 "qualify", 613 "range", 614 "recursive", 615 "respect", 616 "right", 617 "rollup", 618 "rows", 619 "select", 620 "set", 621 "some", 622 "struct", 623 "tablesample", 624 "then", 625 "to", 626 "treat", 627 "true", 628 "unbounded", 629 "union", 630 "unnest", 631 "using", 632 "when", 633 "where", 634 "window", 635 "with", 636 "within", 637 } 638 639 def eq_sql(self, expression: exp.EQ) -> str: 640 # Operands of = cannot be NULL in BigQuery 641 if isinstance(expression.left, exp.Null) or isinstance(expression.right, exp.Null): 642 return "NULL" 643 644 return self.binary(expression, "=") 645 646 def attimezone_sql(self, expression: exp.AtTimeZone) -> str: 647 parent = expression.parent 648 649 # BigQuery allows CAST(.. AS {STRING|TIMESTAMP} [FORMAT <fmt> [AT TIME ZONE <tz>]]). 650 # Only the TIMESTAMP one should use the below conversion, when AT TIME ZONE is included. 651 if not isinstance(parent, exp.Cast) or not parent.to.is_type("text"): 652 return self.func( 653 "TIMESTAMP", self.func("DATETIME", expression.this, expression.args.get("zone")) 654 ) 655 656 return super().attimezone_sql(expression) 657 658 def trycast_sql(self, expression: exp.TryCast) -> str: 659 return self.cast_sql(expression, safe_prefix="SAFE_") 660 661 def cte_sql(self, expression: exp.CTE) -> str: 662 if expression.alias_column_names: 663 self.unsupported("Column names in CTE definition are not supported.") 664 return super().cte_sql(expression) 665 666 def array_sql(self, expression: exp.Array) -> str: 667 first_arg = seq_get(expression.expressions, 0) 668 if isinstance(first_arg, exp.Subqueryable): 669 return f"ARRAY{self.wrap(self.sql(first_arg))}" 670 671 return inline_array_sql(self, expression) 672 673 def transaction_sql(self, *_) -> str: 674 return "BEGIN TRANSACTION" 675 676 def commit_sql(self, *_) -> str: 677 return "COMMIT TRANSACTION" 678 679 def rollback_sql(self, *_) -> str: 680 return "ROLLBACK TRANSACTION" 681 682 def in_unnest_op(self, expression: exp.Unnest) -> str: 683 return self.sql(expression) 684 685 def except_op(self, expression: exp.Except) -> str: 686 if not expression.args.get("distinct", False): 687 self.unsupported("EXCEPT without DISTINCT is not supported in BigQuery") 688 return f"EXCEPT{' DISTINCT' if expression.args.get('distinct') else ' ALL'}" 689 690 def intersect_op(self, expression: exp.Intersect) -> str: 691 if not expression.args.get("distinct", False): 692 self.unsupported("INTERSECT without DISTINCT is not supported in BigQuery") 693 return f"INTERSECT{' DISTINCT' if expression.args.get('distinct') else ' ALL'}" 694 695 def with_properties(self, properties: exp.Properties) -> str: 696 return self.properties(properties, prefix=self.seg("OPTIONS")) 697 698 def version_sql(self, expression: exp.Version) -> str: 699 if expression.name == "TIMESTAMP": 700 expression = expression.copy() 701 expression.set("this", "SYSTEM_TIME") 702 return super().version_sql(expression)
ESCAPE_SEQUENCES: Dict[str, str] =
{'\\a': '\x07', '\\b': '\x08', '\\f': '\x0c', '\\n': '\n', '\\r': '\r', '\\t': '\t', '\\v': '\x0b'}
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:
224 @classmethod 225 def normalize_identifier(cls, expression: E) -> E: 226 if isinstance(expression, exp.Identifier): 227 parent = expression.parent 228 while isinstance(parent, exp.Dot): 229 parent = parent.parent 230 231 # In BigQuery, CTEs aren't case-sensitive, but table names are (by default, at least). 232 # The following check is essentially a heuristic to detect tables based on whether or 233 # not they're qualified. It also avoids normalizing UDFs, because they're case-sensitive. 234 if ( 235 not isinstance(parent, exp.UserDefinedFunction) 236 and not (isinstance(parent, exp.Table) and parent.db) 237 and not expression.meta.get("is_table") 238 ): 239 expression.set("this", expression.this.lower()) 240 241 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 to lowercase regardless of being quoted or not.
tokenizer_class =
<class 'BigQuery.Tokenizer'>
parser_class =
<class 'BigQuery.Parser'>
generator_class =
<class '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}}}}
INVERSE_ESCAPE_SEQUENCES: Dict[str, str] =
{'\x07': '\\a', '\x08': '\\b', '\x0c': '\\f', '\n': '\\n', '\r': '\\r', '\t': '\\t', '\x0b': '\\v'}
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
243 class Tokenizer(tokens.Tokenizer): 244 QUOTES = ["'", '"', '"""', "'''"] 245 COMMENTS = ["--", "#", ("/*", "*/")] 246 IDENTIFIERS = ["`"] 247 STRING_ESCAPES = ["\\"] 248 249 HEX_STRINGS = [("0x", ""), ("0X", "")] 250 251 BYTE_STRINGS = [ 252 (prefix + q, q) for q in t.cast(t.List[str], QUOTES) for prefix in ("b", "B") 253 ] 254 255 RAW_STRINGS = [ 256 (prefix + q, q) for q in t.cast(t.List[str], QUOTES) for prefix in ("r", "R") 257 ] 258 259 KEYWORDS = { 260 **tokens.Tokenizer.KEYWORDS, 261 "ANY TYPE": TokenType.VARIANT, 262 "BEGIN": TokenType.COMMAND, 263 "BEGIN TRANSACTION": TokenType.BEGIN, 264 "BYTES": TokenType.BINARY, 265 "CURRENT_DATETIME": TokenType.CURRENT_DATETIME, 266 "DECLARE": TokenType.COMMAND, 267 "FLOAT64": TokenType.DOUBLE, 268 "FOR SYSTEM_TIME": TokenType.TIMESTAMP_SNAPSHOT, 269 "INT64": TokenType.BIGINT, 270 "MODEL": TokenType.MODEL, 271 "NOT DETERMINISTIC": TokenType.VOLATILE, 272 "RECORD": TokenType.STRUCT, 273 "TIMESTAMP": TokenType.TIMESTAMPTZ, 274 } 275 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'>, 'KILL': <TokenType.KILL: 'KILL'>, '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.UNKNOWN: 'UNKNOWN'>, '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'>, 'MEDIUMINT': <TokenType.MEDIUMINT: 'MEDIUMINT'>, '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'>, 'LONGTEXT': <TokenType.LONGTEXT: 'LONGTEXT'>, 'MEDIUMTEXT': <TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>, 'TINYTEXT': <TokenType.TINYTEXT: 'TINYTEXT'>, 'CLOB': <TokenType.TEXT: 'TEXT'>, 'LONGVARCHAR': <TokenType.TEXT: 'TEXT'>, 'BINARY': <TokenType.BINARY: 'BINARY'>, 'BLOB': <TokenType.VARBINARY: 'VARBINARY'>, 'LONGBLOB': <TokenType.LONGBLOB: 'LONGBLOB'>, 'MEDIUMBLOB': <TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>, 'TINYBLOB': <TokenType.TINYBLOB: 'TINYBLOB'>, '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'>, 'FOR VERSION': <TokenType.VERSION_SNAPSHOT: 'VERSION_SNAPSHOT'>, 'FOR TIMESTAMP': <TokenType.TIMESTAMP_SNAPSHOT: 'TIMESTAMP_SNAPSHOT'>, 'ANY TYPE': <TokenType.VARIANT: 'VARIANT'>, 'BEGIN TRANSACTION': <TokenType.BEGIN: 'BEGIN'>, 'BYTES': <TokenType.BINARY: 'BINARY'>, 'CURRENT_DATETIME': <TokenType.CURRENT_DATETIME: 'CURRENT_DATETIME'>, 'DECLARE': <TokenType.COMMAND: 'COMMAND'>, 'FLOAT64': <TokenType.DOUBLE: 'DOUBLE'>, 'FOR SYSTEM_TIME': <TokenType.TIMESTAMP_SNAPSHOT: 'TIMESTAMP_SNAPSHOT'>, 'INT64': <TokenType.BIGINT: 'BIGINT'>, 'MODEL': <TokenType.MODEL: 'MODEL'>, 'NOT DETERMINISTIC': <TokenType.VOLATILE: 'VOLATILE'>, 'RECORD': <TokenType.STRUCT: 'STRUCT'>}
277 class Parser(parser.Parser): 278 PREFIXED_PIVOT_COLUMNS = True 279 280 LOG_DEFAULTS_TO_LN = True 281 282 FUNCTIONS = { 283 **parser.Parser.FUNCTIONS, 284 "DATE": _parse_date, 285 "DATE_ADD": parse_date_delta_with_interval(exp.DateAdd), 286 "DATE_SUB": parse_date_delta_with_interval(exp.DateSub), 287 "DATE_TRUNC": lambda args: exp.DateTrunc( 288 unit=exp.Literal.string(str(seq_get(args, 1))), 289 this=seq_get(args, 0), 290 ), 291 "DATETIME_ADD": parse_date_delta_with_interval(exp.DatetimeAdd), 292 "DATETIME_SUB": parse_date_delta_with_interval(exp.DatetimeSub), 293 "DIV": binary_from_function(exp.IntDiv), 294 "GENERATE_ARRAY": exp.GenerateSeries.from_arg_list, 295 "MD5": exp.MD5Digest.from_arg_list, 296 "TO_HEX": _parse_to_hex, 297 "PARSE_DATE": lambda args: format_time_lambda(exp.StrToDate, "bigquery")( 298 [seq_get(args, 1), seq_get(args, 0)] 299 ), 300 "PARSE_TIMESTAMP": _parse_timestamp, 301 "REGEXP_CONTAINS": exp.RegexpLike.from_arg_list, 302 "REGEXP_EXTRACT": lambda args: exp.RegexpExtract( 303 this=seq_get(args, 0), 304 expression=seq_get(args, 1), 305 position=seq_get(args, 2), 306 occurrence=seq_get(args, 3), 307 group=exp.Literal.number(1) if re.compile(args[1].name).groups == 1 else None, 308 ), 309 "SHA256": lambda args: exp.SHA2(this=seq_get(args, 0), length=exp.Literal.number(256)), 310 "SHA512": lambda args: exp.SHA2(this=seq_get(args, 0), length=exp.Literal.number(512)), 311 "SPLIT": lambda args: exp.Split( 312 # https://cloud.google.com/bigquery/docs/reference/standard-sql/string_functions#split 313 this=seq_get(args, 0), 314 expression=seq_get(args, 1) or exp.Literal.string(","), 315 ), 316 "TIME_ADD": parse_date_delta_with_interval(exp.TimeAdd), 317 "TIME_SUB": parse_date_delta_with_interval(exp.TimeSub), 318 "TIMESTAMP_ADD": parse_date_delta_with_interval(exp.TimestampAdd), 319 "TIMESTAMP_SUB": parse_date_delta_with_interval(exp.TimestampSub), 320 "TO_JSON_STRING": exp.JSONFormat.from_arg_list, 321 } 322 323 FUNCTION_PARSERS = { 324 **parser.Parser.FUNCTION_PARSERS, 325 "ARRAY": lambda self: self.expression(exp.Array, expressions=[self._parse_statement()]), 326 } 327 FUNCTION_PARSERS.pop("TRIM") 328 329 NO_PAREN_FUNCTIONS = { 330 **parser.Parser.NO_PAREN_FUNCTIONS, 331 TokenType.CURRENT_DATETIME: exp.CurrentDatetime, 332 } 333 334 NESTED_TYPE_TOKENS = { 335 *parser.Parser.NESTED_TYPE_TOKENS, 336 TokenType.TABLE, 337 } 338 339 ID_VAR_TOKENS = { 340 *parser.Parser.ID_VAR_TOKENS, 341 TokenType.VALUES, 342 } 343 344 PROPERTY_PARSERS = { 345 **parser.Parser.PROPERTY_PARSERS, 346 "NOT DETERMINISTIC": lambda self: self.expression( 347 exp.StabilityProperty, this=exp.Literal.string("VOLATILE") 348 ), 349 "OPTIONS": lambda self: self._parse_with_property(), 350 } 351 352 CONSTRAINT_PARSERS = { 353 **parser.Parser.CONSTRAINT_PARSERS, 354 "OPTIONS": lambda self: exp.Properties(expressions=self._parse_with_property()), 355 } 356 357 RANGE_PARSERS = parser.Parser.RANGE_PARSERS.copy() 358 RANGE_PARSERS.pop(TokenType.OVERLAPS, None) 359 360 NULL_TOKENS = {TokenType.NULL, TokenType.UNKNOWN} 361 362 def _parse_table_part(self, schema: bool = False) -> t.Optional[exp.Expression]: 363 this = super()._parse_table_part(schema=schema) or self._parse_number() 364 365 # https://cloud.google.com/bigquery/docs/reference/standard-sql/lexical#table_names 366 if isinstance(this, exp.Identifier): 367 table_name = this.name 368 while self._match(TokenType.DASH, advance=False) and self._next: 369 self._advance(2) 370 table_name += f"-{self._prev.text}" 371 372 this = exp.Identifier(this=table_name, quoted=this.args.get("quoted")) 373 elif isinstance(this, exp.Literal): 374 table_name = this.name 375 376 if ( 377 self._curr 378 and self._prev.end == self._curr.start - 1 379 and self._parse_var(any_token=True) 380 ): 381 table_name += self._prev.text 382 383 this = exp.Identifier(this=table_name, quoted=True) 384 385 return this 386 387 def _parse_table_parts(self, schema: bool = False) -> exp.Table: 388 table = super()._parse_table_parts(schema=schema) 389 if isinstance(table.this, exp.Identifier) and "." in table.name: 390 catalog, db, this, *rest = ( 391 t.cast(t.Optional[exp.Expression], exp.to_identifier(x)) 392 for x in split_num_words(table.name, ".", 3) 393 ) 394 395 if rest and this: 396 this = exp.Dot.build(t.cast(t.List[exp.Expression], [this, *rest])) 397 398 table = exp.Table(this=this, db=db, catalog=catalog) 399 400 return table 401 402 def _parse_json_object(self) -> exp.JSONObject: 403 json_object = super()._parse_json_object() 404 array_kv_pair = seq_get(json_object.expressions, 0) 405 406 # Converts BQ's "signature 2" of JSON_OBJECT into SQLGlot's canonical representation 407 # https://cloud.google.com/bigquery/docs/reference/standard-sql/json_functions#json_object_signature2 408 if ( 409 array_kv_pair 410 and isinstance(array_kv_pair.this, exp.Array) 411 and isinstance(array_kv_pair.expression, exp.Array) 412 ): 413 keys = array_kv_pair.this.expressions 414 values = array_kv_pair.expression.expressions 415 416 json_object.set( 417 "expressions", 418 [exp.JSONKeyValue(this=k, expression=v) for k, v in zip(keys, values)], 419 ) 420 421 return json_object
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'>>, 'CHR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Chr'>>, 'CHAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Chr'>>, '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'>>, 'COLLATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Collate'>>, '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'>>, 'EXPLODE_OUTER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ExplodeOuter'>>, 'EXTRACT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Extract'>>, 'FIRST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.First'>>, 'FLATTEN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Flatten'>>, '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'>>, 'J_S_O_N_ARRAY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONArray'>>, 'J_S_O_N_ARRAY_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONArrayAgg'>>, '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'>>, 'J_S_O_N_TABLE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONTable'>>, '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'>>, 'PARSE_JSON': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ParseJSON'>>, 'JSON_PARSE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ParseJSON'>>, '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'>>, 'POSEXPLODE_OUTER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.PosexplodeOuter'>>, 'POWER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Pow'>>, 'POW': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Pow'>>, 'PREDICT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Predict'>>, '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': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Timestamp'>>, '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'>>, 'TO_DAYS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ToDays'>>, '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>>, 'CONCAT_WS': <function Parser.<lambda>>, 'CONVERT': <function Parser.<lambda>>, 'DECODE': <function Parser.<lambda>>, 'EXTRACT': <function Parser.<lambda>>, 'JSON_OBJECT': <function Parser.<lambda>>, 'JSON_TABLE': <function Parser.<lambda>>, 'LOG': <function Parser.<lambda>>, 'MATCH': <function Parser.<lambda>>, 'OPENJSON': <function Parser.<lambda>>, 'POSITION': <function Parser.<lambda>>, 'PREDICT': <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.STRUCT: 'STRUCT'>, <TokenType.ARRAY: 'ARRAY'>, <TokenType.NULLABLE: 'NULLABLE'>, <TokenType.MAP: 'MAP'>, <TokenType.TABLE: 'TABLE'>, <TokenType.LOWCARDINALITY: 'LOWCARDINALITY'>, <TokenType.NESTED: 'NESTED'>}
ID_VAR_TOKENS =
{<TokenType.DATEMULTIRANGE: 'DATEMULTIRANGE'>, <TokenType.PERCENT: 'PERCENT'>, <TokenType.UMEDIUMINT: 'UMEDIUMINT'>, <TokenType.DOUBLE: 'DOUBLE'>, <TokenType.PIVOT: 'PIVOT'>, <TokenType.TRUE: 'TRUE'>, <TokenType.TEXT: 'TEXT'>, <TokenType.EXECUTE: 'EXECUTE'>, <TokenType.DESC: 'DESC'>, <TokenType.CACHE: 'CACHE'>, <TokenType.FUNCTION: 'FUNCTION'>, <TokenType.DATE: 'DATE'>, <TokenType.BIT: 'BIT'>, <TokenType.SETTINGS: 'SETTINGS'>, <TokenType.TINYTEXT: 'TINYTEXT'>, <TokenType.ROWVERSION: 'ROWVERSION'>, <TokenType.CURRENT_USER: 'CURRENT_USER'>, <TokenType.GEOGRAPHY: 'GEOGRAPHY'>, <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, <TokenType.INT4MULTIRANGE: 'INT4MULTIRANGE'>, <TokenType.CASE: 'CASE'>, <TokenType.ANTI: 'ANTI'>, <TokenType.EXISTS: 'EXISTS'>, <TokenType.INDEX: 'INDEX'>, <TokenType.UUID: 'UUID'>, <TokenType.LOWCARDINALITY: 'LOWCARDINALITY'>, <TokenType.UNKNOWN: 'UNKNOWN'>, <TokenType.MEDIUMINT: 'MEDIUMINT'>, <TokenType.CURRENT_DATETIME: 'CURRENT_DATETIME'>, <TokenType.VOLATILE: 'VOLATILE'>, <TokenType.ALL: 'ALL'>, <TokenType.TINYBLOB: 'TINYBLOB'>, <TokenType.TSMULTIRANGE: 'TSMULTIRANGE'>, <TokenType.TIMETZ: 'TIMETZ'>, <TokenType.ENUM16: 'ENUM16'>, <TokenType.SHOW: 'SHOW'>, <TokenType.OVERLAPS: 'OVERLAPS'>, <TokenType.SMALLSERIAL: 'SMALLSERIAL'>, <TokenType.COLLATE: 'COLLATE'>, <TokenType.COMMENT: 'COMMENT'>, <TokenType.FILTER: 'FILTER'>, <TokenType.HLLSKETCH: 'HLLSKETCH'>, <TokenType.ROWS: 'ROWS'>, <TokenType.RIGHT: 'RIGHT'>, <TokenType.VARCHAR: 'VARCHAR'>, <TokenType.UPDATE: 'UPDATE'>, <TokenType.DICTIONARY: 'DICTIONARY'>, <TokenType.WINDOW: 'WINDOW'>, <TokenType.TABLE: 'TABLE'>, <TokenType.USERDEFINED: 'USERDEFINED'>, <TokenType.DIV: 'DIV'>, <TokenType.UNPIVOT: 'UNPIVOT'>, <TokenType.FIXEDSTRING: 'FIXEDSTRING'>, <TokenType.VARIANT: 'VARIANT'>, <TokenType.BIGINT: 'BIGINT'>, <TokenType.PARTITION: 'PARTITION'>, <TokenType.DATERANGE: 'DATERANGE'>, <TokenType.STRUCT: 'STRUCT'>, <TokenType.ASC: 'ASC'>, <TokenType.PRAGMA: 'PRAGMA'>, <TokenType.PROCEDURE: 'PROCEDURE'>, <TokenType.SEMI: 'SEMI'>, <TokenType.SOME: 'SOME'>, <TokenType.VARBINARY: 'VARBINARY'>, <TokenType.NUMRANGE: 'NUMRANGE'>, <TokenType.ESCAPE: 'ESCAPE'>, <TokenType.ANY: 'ANY'>, <TokenType.DELETE: 'DELETE'>, <TokenType.LONGTEXT: 'LONGTEXT'>, <TokenType.LOAD: 'LOAD'>, <TokenType.NEXT: 'NEXT'>, <TokenType.TOP: 'TOP'>, <TokenType.DEFAULT: 'DEFAULT'>, <TokenType.TIMESTAMP_MS: 'TIMESTAMP_MS'>, <TokenType.HSTORE: 'HSTORE'>, <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, <TokenType.OVERWRITE: 'OVERWRITE'>, <TokenType.IS: 'IS'>, <TokenType.NULL: 'NULL'>, <TokenType.TIMESTAMP_NS: 'TIMESTAMP_NS'>, <TokenType.VAR: 'VAR'>, <TokenType.UNIQUEIDENTIFIER: 'UNIQUEIDENTIFIER'>, <TokenType.IPADDRESS: 'IPADDRESS'>, <TokenType.TIME: 'TIME'>, <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>, <TokenType.TINYINT: 'TINYINT'>, <TokenType.UINT128: 'UINT128'>, <TokenType.UINT256: 'UINT256'>, <TokenType.NCHAR: 'NCHAR'>, <TokenType.COMMAND: 'COMMAND'>, <TokenType.BOOLEAN: 'BOOLEAN'>, <TokenType.SUPER: 'SUPER'>, <TokenType.CONSTRAINT: 'CONSTRAINT'>, <TokenType.UDECIMAL: 'UDECIMAL'>, <TokenType.REFERENCES: 'REFERENCES'>, <TokenType.CURRENT_TIMESTAMP: 'CURRENT_TIMESTAMP'>, <TokenType.INT4RANGE: 'INT4RANGE'>, <TokenType.VIEW: 'VIEW'>, <TokenType.BIGSERIAL: 'BIGSERIAL'>, <TokenType.MONEY: 'MONEY'>, <TokenType.LEFT: 'LEFT'>, <TokenType.COMMIT: 'COMMIT'>, <TokenType.LONGBLOB: 'LONGBLOB'>, <TokenType.INT8MULTIRANGE: 'INT8MULTIRANGE'>, <TokenType.DATETIME64: 'DATETIME64'>, <TokenType.IMAGE: 'IMAGE'>, <TokenType.UTINYINT: 'UTINYINT'>, <TokenType.MERGE: 'MERGE'>, <TokenType.INT128: 'INT128'>, <TokenType.ENUM8: 'ENUM8'>, <TokenType.DATABASE: 'DATABASE'>, <TokenType.SMALLMONEY: 'SMALLMONEY'>, <TokenType.CURRENT_DATE: 'CURRENT_DATE'>, <TokenType.TSRANGE: 'TSRANGE'>, <TokenType.TEMPORARY: 'TEMPORARY'>, <TokenType.SET: 'SET'>, <TokenType.INT256: 'INT256'>, <TokenType.DESCRIBE: 'DESCRIBE'>, <TokenType.FULL: 'FULL'>, <TokenType.FORMAT: 'FORMAT'>, <TokenType.MAP: 'MAP'>, <TokenType.CURRENT_TIME: 'CURRENT_TIME'>, <TokenType.END: 'END'>, <TokenType.UINT: 'UINT'>, <TokenType.CHAR: 'CHAR'>, <TokenType.NULLABLE: 'NULLABLE'>, <TokenType.ROW: 'ROW'>, <TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>, <TokenType.INT8RANGE: 'INT8RANGE'>, <TokenType.FLOAT: 'FLOAT'>, <TokenType.XML: 'XML'>, <TokenType.ORDINALITY: 'ORDINALITY'>, <TokenType.NESTED: 'NESTED'>, <TokenType.IPPREFIX: 'IPPREFIX'>, <TokenType.DECIMAL: 'DECIMAL'>, <TokenType.DATETIME: 'DATETIME'>, <TokenType.OBJECT_IDENTIFIER: 'OBJECT_IDENTIFIER'>, <TokenType.TIMESTAMP_S: 'TIMESTAMP_S'>, <TokenType.SERIAL: 'SERIAL'>, <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>, <TokenType.NATURAL: 'NATURAL'>, <TokenType.COLUMN: 'COLUMN'>, <TokenType.SCHEMA: 'SCHEMA'>, <TokenType.OBJECT: 'OBJECT'>, <TokenType.INET: 'INET'>, <TokenType.FIRST: 'FIRST'>, <TokenType.OFFSET: 'OFFSET'>, <TokenType.JSON: 'JSON'>, <TokenType.BINARY: 'BINARY'>, <TokenType.NVARCHAR: 'NVARCHAR'>, <TokenType.UNIQUE: 'UNIQUE'>, <TokenType.FALSE: 'FALSE'>, <TokenType.SMALLINT: 'SMALLINT'>, <TokenType.KEEP: 'KEEP'>, <TokenType.GEOMETRY: 'GEOMETRY'>, <TokenType.TIMESTAMP: 'TIMESTAMP'>, <TokenType.ARRAY: 'ARRAY'>, <TokenType.PSEUDO_TYPE: 'PSEUDO_TYPE'>, <TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>, <TokenType.USMALLINT: 'USMALLINT'>, <TokenType.TSTZRANGE: 'TSTZRANGE'>, <TokenType.RANGE: 'RANGE'>, <TokenType.TSTZMULTIRANGE: 'TSTZMULTIRANGE'>, <TokenType.YEAR: 'YEAR'>, <TokenType.ISNULL: 'ISNULL'>, <TokenType.UBIGINT: 'UBIGINT'>, <TokenType.NUMMULTIRANGE: 'NUMMULTIRANGE'>, <TokenType.INT: 'INT'>, <TokenType.JSONB: 'JSONB'>, <TokenType.VALUES: 'VALUES'>, <TokenType.APPLY: 'APPLY'>, <TokenType.INTERVAL: 'INTERVAL'>, <TokenType.MODEL: 'MODEL'>, <TokenType.BEGIN: 'BEGIN'>, <TokenType.KILL: 'KILL'>, <TokenType.ENUM: 'ENUM'>}
PROPERTY_PARSERS =
{'ALGORITHM': <function Parser.<lambda>>, 'AUTO_INCREMENT': <function Parser.<lambda>>, 'BLOCKCOMPRESSION': <function Parser.<lambda>>, 'CHARSET': <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>>, 'INPUT': <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>>, 'OUTPUT': <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>>, 'REMOTE': <function Parser.<lambda>>, 'RETURNS': <function Parser.<lambda>>, 'ROW': <function Parser.<lambda>>, 'ROW_FORMAT': <function Parser.<lambda>>, 'SAMPLE': <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>>, 'TRANSFORM': <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>>}
RANGE_PARSERS =
{<TokenType.BETWEEN: 'BETWEEN'>: <function Parser.<lambda>>, <TokenType.GLOB: 'GLOB'>: <function binary_range_parser.<locals>.<lambda>>, <TokenType.ILIKE: 'ILIKE'>: <function binary_range_parser.<locals>.<lambda>>, <TokenType.IN: 'IN'>: <function Parser.<lambda>>, <TokenType.IRLIKE: 'IRLIKE'>: <function binary_range_parser.<locals>.<lambda>>, <TokenType.IS: 'IS'>: <function Parser.<lambda>>, <TokenType.LIKE: 'LIKE'>: <function binary_range_parser.<locals>.<lambda>>, <TokenType.RLIKE: 'RLIKE'>: <function binary_range_parser.<locals>.<lambda>>, <TokenType.SIMILAR_TO: 'SIMILAR_TO'>: <function binary_range_parser.<locals>.<lambda>>, <TokenType.FOR: 'FOR'>: <function Parser.<lambda>>}
TABLE_ALIAS_TOKENS =
{<TokenType.DATEMULTIRANGE: 'DATEMULTIRANGE'>, <TokenType.PERCENT: 'PERCENT'>, <TokenType.UMEDIUMINT: 'UMEDIUMINT'>, <TokenType.DOUBLE: 'DOUBLE'>, <TokenType.PIVOT: 'PIVOT'>, <TokenType.TRUE: 'TRUE'>, <TokenType.TEXT: 'TEXT'>, <TokenType.EXECUTE: 'EXECUTE'>, <TokenType.DESC: 'DESC'>, <TokenType.CACHE: 'CACHE'>, <TokenType.FUNCTION: 'FUNCTION'>, <TokenType.DATE: 'DATE'>, <TokenType.BIT: 'BIT'>, <TokenType.SETTINGS: 'SETTINGS'>, <TokenType.TINYTEXT: 'TINYTEXT'>, <TokenType.ROWVERSION: 'ROWVERSION'>, <TokenType.CURRENT_USER: 'CURRENT_USER'>, <TokenType.GEOGRAPHY: 'GEOGRAPHY'>, <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, <TokenType.INT4MULTIRANGE: 'INT4MULTIRANGE'>, <TokenType.CASE: 'CASE'>, <TokenType.ANTI: 'ANTI'>, <TokenType.EXISTS: 'EXISTS'>, <TokenType.INDEX: 'INDEX'>, <TokenType.UUID: 'UUID'>, <TokenType.LOWCARDINALITY: 'LOWCARDINALITY'>, <TokenType.UNKNOWN: 'UNKNOWN'>, <TokenType.MEDIUMINT: 'MEDIUMINT'>, <TokenType.CURRENT_DATETIME: 'CURRENT_DATETIME'>, <TokenType.VOLATILE: 'VOLATILE'>, <TokenType.ALL: 'ALL'>, <TokenType.TINYBLOB: 'TINYBLOB'>, <TokenType.TSMULTIRANGE: 'TSMULTIRANGE'>, <TokenType.TIMETZ: 'TIMETZ'>, <TokenType.ENUM16: 'ENUM16'>, <TokenType.SHOW: 'SHOW'>, <TokenType.OVERLAPS: 'OVERLAPS'>, <TokenType.SMALLSERIAL: 'SMALLSERIAL'>, <TokenType.COLLATE: 'COLLATE'>, <TokenType.COMMENT: 'COMMENT'>, <TokenType.FILTER: 'FILTER'>, <TokenType.HLLSKETCH: 'HLLSKETCH'>, <TokenType.ROWS: 'ROWS'>, <TokenType.VARCHAR: 'VARCHAR'>, <TokenType.UPDATE: 'UPDATE'>, <TokenType.DICTIONARY: 'DICTIONARY'>, <TokenType.TABLE: 'TABLE'>, <TokenType.USERDEFINED: 'USERDEFINED'>, <TokenType.DIV: 'DIV'>, <TokenType.UNPIVOT: 'UNPIVOT'>, <TokenType.FIXEDSTRING: 'FIXEDSTRING'>, <TokenType.VARIANT: 'VARIANT'>, <TokenType.BIGINT: 'BIGINT'>, <TokenType.PARTITION: 'PARTITION'>, <TokenType.DATERANGE: 'DATERANGE'>, <TokenType.STRUCT: 'STRUCT'>, <TokenType.ASC: 'ASC'>, <TokenType.PRAGMA: 'PRAGMA'>, <TokenType.PROCEDURE: 'PROCEDURE'>, <TokenType.SEMI: 'SEMI'>, <TokenType.SOME: 'SOME'>, <TokenType.VARBINARY: 'VARBINARY'>, <TokenType.NUMRANGE: 'NUMRANGE'>, <TokenType.ESCAPE: 'ESCAPE'>, <TokenType.ANY: 'ANY'>, <TokenType.DELETE: 'DELETE'>, <TokenType.LONGTEXT: 'LONGTEXT'>, <TokenType.LOAD: 'LOAD'>, <TokenType.NEXT: 'NEXT'>, <TokenType.TOP: 'TOP'>, <TokenType.DEFAULT: 'DEFAULT'>, <TokenType.TIMESTAMP_MS: 'TIMESTAMP_MS'>, <TokenType.HSTORE: 'HSTORE'>, <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, <TokenType.OVERWRITE: 'OVERWRITE'>, <TokenType.IS: 'IS'>, <TokenType.NULL: 'NULL'>, <TokenType.TIMESTAMP_NS: 'TIMESTAMP_NS'>, <TokenType.VAR: 'VAR'>, <TokenType.UNIQUEIDENTIFIER: 'UNIQUEIDENTIFIER'>, <TokenType.IPADDRESS: 'IPADDRESS'>, <TokenType.TIME: 'TIME'>, <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>, <TokenType.TINYINT: 'TINYINT'>, <TokenType.UINT128: 'UINT128'>, <TokenType.UINT256: 'UINT256'>, <TokenType.NCHAR: 'NCHAR'>, <TokenType.COMMAND: 'COMMAND'>, <TokenType.BOOLEAN: 'BOOLEAN'>, <TokenType.SUPER: 'SUPER'>, <TokenType.CONSTRAINT: 'CONSTRAINT'>, <TokenType.UDECIMAL: 'UDECIMAL'>, <TokenType.REFERENCES: 'REFERENCES'>, <TokenType.CURRENT_TIMESTAMP: 'CURRENT_TIMESTAMP'>, <TokenType.INT4RANGE: 'INT4RANGE'>, <TokenType.VIEW: 'VIEW'>, <TokenType.BIGSERIAL: 'BIGSERIAL'>, <TokenType.MONEY: 'MONEY'>, <TokenType.COMMIT: 'COMMIT'>, <TokenType.LONGBLOB: 'LONGBLOB'>, <TokenType.INT8MULTIRANGE: 'INT8MULTIRANGE'>, <TokenType.DATETIME64: 'DATETIME64'>, <TokenType.IMAGE: 'IMAGE'>, <TokenType.UTINYINT: 'UTINYINT'>, <TokenType.MERGE: 'MERGE'>, <TokenType.INT128: 'INT128'>, <TokenType.ENUM8: 'ENUM8'>, <TokenType.DATABASE: 'DATABASE'>, <TokenType.SMALLMONEY: 'SMALLMONEY'>, <TokenType.CURRENT_DATE: 'CURRENT_DATE'>, <TokenType.TSRANGE: 'TSRANGE'>, <TokenType.TEMPORARY: 'TEMPORARY'>, <TokenType.SET: 'SET'>, <TokenType.INT256: 'INT256'>, <TokenType.DESCRIBE: 'DESCRIBE'>, <TokenType.MAP: 'MAP'>, <TokenType.FORMAT: 'FORMAT'>, <TokenType.CURRENT_TIME: 'CURRENT_TIME'>, <TokenType.END: 'END'>, <TokenType.UINT: 'UINT'>, <TokenType.CHAR: 'CHAR'>, <TokenType.NULLABLE: 'NULLABLE'>, <TokenType.ROW: 'ROW'>, <TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>, <TokenType.INT8RANGE: 'INT8RANGE'>, <TokenType.FLOAT: 'FLOAT'>, <TokenType.XML: 'XML'>, <TokenType.ORDINALITY: 'ORDINALITY'>, <TokenType.NESTED: 'NESTED'>, <TokenType.IPPREFIX: 'IPPREFIX'>, <TokenType.DECIMAL: 'DECIMAL'>, <TokenType.DATETIME: 'DATETIME'>, <TokenType.OBJECT_IDENTIFIER: 'OBJECT_IDENTIFIER'>, <TokenType.TIMESTAMP_S: 'TIMESTAMP_S'>, <TokenType.SERIAL: 'SERIAL'>, <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>, <TokenType.COLUMN: 'COLUMN'>, <TokenType.SCHEMA: 'SCHEMA'>, <TokenType.OBJECT: 'OBJECT'>, <TokenType.INET: 'INET'>, <TokenType.FIRST: 'FIRST'>, <TokenType.JSON: 'JSON'>, <TokenType.BINARY: 'BINARY'>, <TokenType.NVARCHAR: 'NVARCHAR'>, <TokenType.UNIQUE: 'UNIQUE'>, <TokenType.FALSE: 'FALSE'>, <TokenType.SMALLINT: 'SMALLINT'>, <TokenType.KEEP: 'KEEP'>, <TokenType.GEOMETRY: 'GEOMETRY'>, <TokenType.TIMESTAMP: 'TIMESTAMP'>, <TokenType.ARRAY: 'ARRAY'>, <TokenType.PSEUDO_TYPE: 'PSEUDO_TYPE'>, <TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>, <TokenType.USMALLINT: 'USMALLINT'>, <TokenType.TSTZRANGE: 'TSTZRANGE'>, <TokenType.RANGE: 'RANGE'>, <TokenType.TSTZMULTIRANGE: 'TSTZMULTIRANGE'>, <TokenType.YEAR: 'YEAR'>, <TokenType.ISNULL: 'ISNULL'>, <TokenType.UBIGINT: 'UBIGINT'>, <TokenType.NUMMULTIRANGE: 'NUMMULTIRANGE'>, <TokenType.INT: 'INT'>, <TokenType.JSONB: 'JSONB'>, <TokenType.MODEL: 'MODEL'>, <TokenType.INTERVAL: 'INTERVAL'>, <TokenType.BEGIN: 'BEGIN'>, <TokenType.KILL: 'KILL'>, <TokenType.ENUM: 'ENUM'>}
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
- SIGNED_TO_UNSIGNED_TYPE_TOKEN
- SUBQUERY_PREDICATES
- RESERVED_KEYWORDS
- DB_CREATABLES
- CREATABLES
- INTERVAL_VARS
- 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
- 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_KEYWORDS
- CLONE_KINDS
- OPCLASS_FOLLOW_KEYWORDS
- TABLE_INDEX_HINT_TOKENS
- WINDOW_ALIAS_TOKENS
- WINDOW_BEFORE_PAREN_TOKENS
- WINDOW_SIDES
- FETCH_TOKENS
- ADD_CONSTRAINT_TOKENS
- DISTINCT_TOKENS
- UNNEST_OFFSET_ALIAS_TOKENS
- STRICT_CAST
- CONCAT_NULL_OUTPUTS_STRING
- IDENTIFY_PIVOT_STRINGS
- ALTER_TABLE_ADD_COLUMN_KEYWORD
- TABLESAMPLE_CSV
- SET_REQUIRES_ASSIGNMENT_DELIMITER
- TRIM_PATTERN_FIRST
- 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
423 class Generator(generator.Generator): 424 EXPLICIT_UNION = True 425 INTERVAL_ALLOWS_PLURAL_FORM = False 426 JOIN_HINTS = False 427 QUERY_HINTS = False 428 TABLE_HINTS = False 429 LIMIT_FETCH = "LIMIT" 430 RENAME_TABLE_WITH_DB = False 431 NVL2_SUPPORTED = False 432 UNNEST_WITH_ORDINALITY = False 433 COLLATE_IS_FUNC = True 434 435 TRANSFORMS = { 436 **generator.Generator.TRANSFORMS, 437 exp.ApproxDistinct: rename_func("APPROX_COUNT_DISTINCT"), 438 exp.ArraySize: rename_func("ARRAY_LENGTH"), 439 exp.Cast: transforms.preprocess([transforms.remove_precision_parameterized_types]), 440 exp.CollateProperty: lambda self, e: f"DEFAULT COLLATE {self.sql(e, 'this')}" 441 if e.args.get("default") 442 else f"COLLATE {self.sql(e, 'this')}", 443 exp.Create: _create_sql, 444 exp.CTE: transforms.preprocess([_pushdown_cte_column_names]), 445 exp.DateAdd: date_add_interval_sql("DATE", "ADD"), 446 exp.DateDiff: lambda self, e: f"DATE_DIFF({self.sql(e, 'this')}, {self.sql(e, 'expression')}, {self.sql(e.args.get('unit', 'DAY'))})", 447 exp.DateFromParts: rename_func("DATE"), 448 exp.DateStrToDate: datestrtodate_sql, 449 exp.DateSub: date_add_interval_sql("DATE", "SUB"), 450 exp.DatetimeAdd: date_add_interval_sql("DATETIME", "ADD"), 451 exp.DatetimeSub: date_add_interval_sql("DATETIME", "SUB"), 452 exp.DateTrunc: lambda self, e: self.func("DATE_TRUNC", e.this, e.text("unit")), 453 exp.GenerateSeries: rename_func("GENERATE_ARRAY"), 454 exp.GroupConcat: rename_func("STRING_AGG"), 455 exp.Hex: rename_func("TO_HEX"), 456 exp.If: if_sql(false_value="NULL"), 457 exp.ILike: no_ilike_sql, 458 exp.IntDiv: rename_func("DIV"), 459 exp.JSONFormat: rename_func("TO_JSON_STRING"), 460 exp.JSONKeyValue: json_keyvalue_comma_sql, 461 exp.Max: max_or_greatest, 462 exp.MD5: lambda self, e: self.func("TO_HEX", self.func("MD5", e.this)), 463 exp.MD5Digest: rename_func("MD5"), 464 exp.Min: min_or_least, 465 exp.PartitionedByProperty: lambda self, e: f"PARTITION BY {self.sql(e, 'this')}", 466 exp.RegexpExtract: lambda self, e: self.func( 467 "REGEXP_EXTRACT", 468 e.this, 469 e.expression, 470 e.args.get("position"), 471 e.args.get("occurrence"), 472 ), 473 exp.RegexpReplace: regexp_replace_sql, 474 exp.RegexpLike: rename_func("REGEXP_CONTAINS"), 475 exp.ReturnsProperty: _returnsproperty_sql, 476 exp.Select: transforms.preprocess( 477 [ 478 transforms.explode_to_unnest(), 479 _unqualify_unnest, 480 transforms.eliminate_distinct_on, 481 _alias_ordered_group, 482 transforms.eliminate_semi_and_anti_joins, 483 ] 484 ), 485 exp.SHA2: lambda self, e: self.func( 486 f"SHA256" if e.text("length") == "256" else "SHA512", e.this 487 ), 488 exp.StabilityProperty: lambda self, e: f"DETERMINISTIC" 489 if e.name == "IMMUTABLE" 490 else "NOT DETERMINISTIC", 491 exp.StrToDate: lambda self, e: f"PARSE_DATE({self.format_time(e)}, {self.sql(e, 'this')})", 492 exp.StrToTime: lambda self, e: self.func( 493 "PARSE_TIMESTAMP", self.format_time(e), e.this, e.args.get("zone") 494 ), 495 exp.TimeAdd: date_add_interval_sql("TIME", "ADD"), 496 exp.TimeSub: date_add_interval_sql("TIME", "SUB"), 497 exp.TimestampAdd: date_add_interval_sql("TIMESTAMP", "ADD"), 498 exp.TimestampSub: date_add_interval_sql("TIMESTAMP", "SUB"), 499 exp.TimeStrToTime: timestrtotime_sql, 500 exp.Trim: lambda self, e: self.func(f"TRIM", e.this, e.expression), 501 exp.TsOrDsAdd: date_add_interval_sql("DATE", "ADD"), 502 exp.TsOrDsToDate: ts_or_ds_to_date_sql("bigquery"), 503 exp.Unhex: rename_func("FROM_HEX"), 504 exp.Values: _derived_table_values_to_unnest, 505 exp.VariancePop: rename_func("VAR_POP"), 506 } 507 508 TYPE_MAPPING = { 509 **generator.Generator.TYPE_MAPPING, 510 exp.DataType.Type.BIGDECIMAL: "BIGNUMERIC", 511 exp.DataType.Type.BIGINT: "INT64", 512 exp.DataType.Type.BINARY: "BYTES", 513 exp.DataType.Type.BOOLEAN: "BOOL", 514 exp.DataType.Type.CHAR: "STRING", 515 exp.DataType.Type.DECIMAL: "NUMERIC", 516 exp.DataType.Type.DOUBLE: "FLOAT64", 517 exp.DataType.Type.FLOAT: "FLOAT64", 518 exp.DataType.Type.INT: "INT64", 519 exp.DataType.Type.NCHAR: "STRING", 520 exp.DataType.Type.NVARCHAR: "STRING", 521 exp.DataType.Type.SMALLINT: "INT64", 522 exp.DataType.Type.TEXT: "STRING", 523 exp.DataType.Type.TIMESTAMP: "DATETIME", 524 exp.DataType.Type.TIMESTAMPTZ: "TIMESTAMP", 525 exp.DataType.Type.TIMESTAMPLTZ: "TIMESTAMP", 526 exp.DataType.Type.TINYINT: "INT64", 527 exp.DataType.Type.VARBINARY: "BYTES", 528 exp.DataType.Type.VARCHAR: "STRING", 529 exp.DataType.Type.VARIANT: "ANY TYPE", 530 } 531 532 PROPERTIES_LOCATION = { 533 **generator.Generator.PROPERTIES_LOCATION, 534 exp.PartitionedByProperty: exp.Properties.Location.POST_SCHEMA, 535 exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED, 536 } 537 538 # from: https://cloud.google.com/bigquery/docs/reference/standard-sql/lexical#reserved_keywords 539 RESERVED_KEYWORDS = { 540 *generator.Generator.RESERVED_KEYWORDS, 541 "all", 542 "and", 543 "any", 544 "array", 545 "as", 546 "asc", 547 "assert_rows_modified", 548 "at", 549 "between", 550 "by", 551 "case", 552 "cast", 553 "collate", 554 "contains", 555 "create", 556 "cross", 557 "cube", 558 "current", 559 "default", 560 "define", 561 "desc", 562 "distinct", 563 "else", 564 "end", 565 "enum", 566 "escape", 567 "except", 568 "exclude", 569 "exists", 570 "extract", 571 "false", 572 "fetch", 573 "following", 574 "for", 575 "from", 576 "full", 577 "group", 578 "grouping", 579 "groups", 580 "hash", 581 "having", 582 "if", 583 "ignore", 584 "in", 585 "inner", 586 "intersect", 587 "interval", 588 "into", 589 "is", 590 "join", 591 "lateral", 592 "left", 593 "like", 594 "limit", 595 "lookup", 596 "merge", 597 "natural", 598 "new", 599 "no", 600 "not", 601 "null", 602 "nulls", 603 "of", 604 "on", 605 "or", 606 "order", 607 "outer", 608 "over", 609 "partition", 610 "preceding", 611 "proto", 612 "qualify", 613 "range", 614 "recursive", 615 "respect", 616 "right", 617 "rollup", 618 "rows", 619 "select", 620 "set", 621 "some", 622 "struct", 623 "tablesample", 624 "then", 625 "to", 626 "treat", 627 "true", 628 "unbounded", 629 "union", 630 "unnest", 631 "using", 632 "when", 633 "where", 634 "window", 635 "with", 636 "within", 637 } 638 639 def eq_sql(self, expression: exp.EQ) -> str: 640 # Operands of = cannot be NULL in BigQuery 641 if isinstance(expression.left, exp.Null) or isinstance(expression.right, exp.Null): 642 return "NULL" 643 644 return self.binary(expression, "=") 645 646 def attimezone_sql(self, expression: exp.AtTimeZone) -> str: 647 parent = expression.parent 648 649 # BigQuery allows CAST(.. AS {STRING|TIMESTAMP} [FORMAT <fmt> [AT TIME ZONE <tz>]]). 650 # Only the TIMESTAMP one should use the below conversion, when AT TIME ZONE is included. 651 if not isinstance(parent, exp.Cast) or not parent.to.is_type("text"): 652 return self.func( 653 "TIMESTAMP", self.func("DATETIME", expression.this, expression.args.get("zone")) 654 ) 655 656 return super().attimezone_sql(expression) 657 658 def trycast_sql(self, expression: exp.TryCast) -> str: 659 return self.cast_sql(expression, safe_prefix="SAFE_") 660 661 def cte_sql(self, expression: exp.CTE) -> str: 662 if expression.alias_column_names: 663 self.unsupported("Column names in CTE definition are not supported.") 664 return super().cte_sql(expression) 665 666 def array_sql(self, expression: exp.Array) -> str: 667 first_arg = seq_get(expression.expressions, 0) 668 if isinstance(first_arg, exp.Subqueryable): 669 return f"ARRAY{self.wrap(self.sql(first_arg))}" 670 671 return inline_array_sql(self, expression) 672 673 def transaction_sql(self, *_) -> str: 674 return "BEGIN TRANSACTION" 675 676 def commit_sql(self, *_) -> str: 677 return "COMMIT TRANSACTION" 678 679 def rollback_sql(self, *_) -> str: 680 return "ROLLBACK TRANSACTION" 681 682 def in_unnest_op(self, expression: exp.Unnest) -> str: 683 return self.sql(expression) 684 685 def except_op(self, expression: exp.Except) -> str: 686 if not expression.args.get("distinct", False): 687 self.unsupported("EXCEPT without DISTINCT is not supported in BigQuery") 688 return f"EXCEPT{' DISTINCT' if expression.args.get('distinct') else ' ALL'}" 689 690 def intersect_op(self, expression: exp.Intersect) -> str: 691 if not expression.args.get("distinct", False): 692 self.unsupported("INTERSECT without DISTINCT is not supported in BigQuery") 693 return f"INTERSECT{' DISTINCT' if expression.args.get('distinct') else ' ALL'}" 694 695 def with_properties(self, properties: exp.Properties) -> str: 696 return self.properties(properties, prefix=self.seg("OPTIONS")) 697 698 def version_sql(self, expression: exp.Version) -> str: 699 if expression.name == "TIMESTAMP": 700 expression = expression.copy() 701 expression.set("this", "SYSTEM_TIME") 702 return super().version_sql(expression)
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_interval_sql.<locals>.func>, <class 'sqlglot.expressions.TsOrDsAdd'>: <function date_add_interval_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.InputModelProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.IntervalSpan'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.LanguageProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.LocationProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.LogProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.MaterializedProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.NoPrimaryIndexProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.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.OutputModelProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.PathColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.RemoteWithConnectionModelProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ReturnsProperty'>: <function _returnsproperty_sql>, <class 'sqlglot.expressions.SampleProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SetProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SettingsProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SqlSecurityProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.StabilityProperty'>: <function 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.TransformModelProperty'>: <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.CollateProperty'>: <function BigQuery.Generator.<lambda>>, <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_interval_sql.<locals>.func>, <class 'sqlglot.expressions.DatetimeAdd'>: <function date_add_interval_sql.<locals>.func>, <class 'sqlglot.expressions.DatetimeSub'>: <function date_add_interval_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.If'>: <function if_sql.<locals>._if_sql>, <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.JSONKeyValue'>: <function json_keyvalue_comma_sql>, <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_interval_sql.<locals>.func>, <class 'sqlglot.expressions.TimeSub'>: <function date_add_interval_sql.<locals>.func>, <class 'sqlglot.expressions.TimestampAdd'>: <function date_add_interval_sql.<locals>.func>, <class 'sqlglot.expressions.TimestampSub'>: <function date_add_interval_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.TINYTEXT: 'TINYTEXT'>: 'TEXT', <Type.MEDIUMBLOB: 'MEDIUMBLOB'>: 'BLOB', <Type.LONGBLOB: 'LONGBLOB'>: 'BLOB', <Type.TINYBLOB: 'TINYBLOB'>: '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.InputModelProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <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.OutputModelProperty'>: <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.RemoteWithConnectionModelProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <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.SampleProperty'>: <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.TransformModelProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <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 =
{'for', 'unbounded', 'partition', 'where', 'rollup', 'cast', 'enum', 'left', 'rows', 'all', 'grouping', 'fetch', 'collate', 'respect', 'into', 'union', 'inner', 'default', 'desc', 'full', 'define', 'intersect', 'true', 'by', 'of', 'treat', 'except', 'recursive', 'asc', 'using', 'like', 'range', 'case', 'create', 'groups', 'if', 'lateral', 'over', 'escape', 'following', 'select', 'when', 'exclude', 'window', 'or', 'order', 'unnest', 'null', 'assert_rows_modified', 'with', 'then', 'else', 'proto', 'and', 'natural', 'false', 'hash', 'contains', 'end', 'lookup', 'having', 'ignore', 'as', 'not', 'between', 'new', 'set', 'distinct', 'some', 'preceding', 'any', 'qualify', 'exists', 'tablesample', 'on', 'merge', 'within', 'extract', 'in', 'right', 'is', 'at', 'join', 'cross', 'struct', 'to', 'from', 'outer', 'no', 'array', 'nulls', 'interval', 'cube', 'current', 'limit', 'group'}
646 def attimezone_sql(self, expression: exp.AtTimeZone) -> str: 647 parent = expression.parent 648 649 # BigQuery allows CAST(.. AS {STRING|TIMESTAMP} [FORMAT <fmt> [AT TIME ZONE <tz>]]). 650 # Only the TIMESTAMP one should use the below conversion, when AT TIME ZONE is included. 651 if not isinstance(parent, exp.Cast) or not parent.to.is_type("text"): 652 return self.func( 653 "TIMESTAMP", self.func("DATETIME", expression.this, expression.args.get("zone")) 654 ) 655 656 return super().attimezone_sql(expression)
INVERSE_ESCAPE_SEQUENCES: Dict[str, str] =
{'\x07': '\\a', '\x08': '\\b', '\x0c': '\\f', '\n': '\\n', '\r': '\\r', '\t': '\\t', '\x0b': '\\v'}
@classmethod
def
can_identify(text: str, identify: str | bool = 'safe') -> bool:
279 @classmethod 280 def can_identify(cls, text: str, identify: str | bool = "safe") -> bool: 281 """Checks if text can be identified given an identify option. 282 283 Args: 284 text: The text to check. 285 identify: 286 "always" or `True`: Always returns true. 287 "safe": True if the identifier is case-insensitive. 288 289 Returns: 290 Whether or not the given text can be identified. 291 """ 292 if identify is True or identify == "always": 293 return True 294 295 if identify == "safe": 296 return not cls.case_sensitive(text) 297 298 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 '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
- LIMIT_ONLY_LITERALS
- 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
- ALTER_TABLE_ADD_COLUMN_KEYWORD
- AGGREGATE_FILTER_SUPPORTED
- SEMI_ANTI_JOIN_WITH_SIDE
- SUPPORTS_PARAMETERS
- COMPUTED_COLUMN_WITH_TYPE
- SUPPORTS_TABLE_COPY
- TABLESAMPLE_REQUIRES_PARENS
- DATA_TYPE_SPECIFIERS_ALLOWED
- STAR_MAPPING
- TIME_PART_SINGULARS
- TOKEN_MAPPING
- STRUCT_DELIMITER
- PARAMETER_TOKEN
- WITH_SEPARATED_COMMENTS
- EXCLUDE_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_name
- 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
- kill_sql
- pseudotype_sql
- objectidentifier_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
- formatjson_sql
- jsonobject_sql
- jsonarray_sql
- jsonarrayagg_sql
- jsoncolumndef_sql
- jsonschema_sql
- jsontable_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
- 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
- log_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
- columnprefix_sql
- opclass_sql
- predict_sql