sqlglot.tokens
1from __future__ import annotations 2 3import os 4import typing as t 5from enum import auto 6 7from sqlglot.errors import SqlglotError, TokenError 8from sqlglot.helper import AutoName 9from sqlglot.trie import TrieResult, in_trie, new_trie 10 11if t.TYPE_CHECKING: 12 from sqlglot.dialects.dialect import DialectType 13 14 15try: 16 from sqlglotrs import ( # type: ignore 17 Tokenizer as RsTokenizer, 18 TokenizerDialectSettings as RsTokenizerDialectSettings, 19 TokenizerSettings as RsTokenizerSettings, 20 TokenTypeSettings as RsTokenTypeSettings, 21 ) 22 23 USE_RS_TOKENIZER = os.environ.get("SQLGLOTRS_TOKENIZER", "1") == "1" 24except ImportError: 25 USE_RS_TOKENIZER = False 26 27 28class TokenType(AutoName): 29 L_PAREN = auto() 30 R_PAREN = auto() 31 L_BRACKET = auto() 32 R_BRACKET = auto() 33 L_BRACE = auto() 34 R_BRACE = auto() 35 COMMA = auto() 36 DOT = auto() 37 DASH = auto() 38 PLUS = auto() 39 COLON = auto() 40 DCOLON = auto() 41 DQMARK = auto() 42 SEMICOLON = auto() 43 STAR = auto() 44 BACKSLASH = auto() 45 SLASH = auto() 46 LT = auto() 47 LTE = auto() 48 GT = auto() 49 GTE = auto() 50 NOT = auto() 51 EQ = auto() 52 NEQ = auto() 53 NULLSAFE_EQ = auto() 54 COLON_EQ = auto() 55 AND = auto() 56 OR = auto() 57 AMP = auto() 58 DPIPE = auto() 59 PIPE = auto() 60 PIPE_SLASH = auto() 61 DPIPE_SLASH = auto() 62 CARET = auto() 63 TILDA = auto() 64 ARROW = auto() 65 DARROW = auto() 66 FARROW = auto() 67 HASH = auto() 68 HASH_ARROW = auto() 69 DHASH_ARROW = auto() 70 LR_ARROW = auto() 71 DAT = auto() 72 LT_AT = auto() 73 AT_GT = auto() 74 DOLLAR = auto() 75 PARAMETER = auto() 76 SESSION_PARAMETER = auto() 77 DAMP = auto() 78 XOR = auto() 79 DSTAR = auto() 80 81 BLOCK_START = auto() 82 BLOCK_END = auto() 83 84 SPACE = auto() 85 BREAK = auto() 86 87 STRING = auto() 88 NUMBER = auto() 89 IDENTIFIER = auto() 90 DATABASE = auto() 91 COLUMN = auto() 92 COLUMN_DEF = auto() 93 SCHEMA = auto() 94 TABLE = auto() 95 VAR = auto() 96 BIT_STRING = auto() 97 HEX_STRING = auto() 98 BYTE_STRING = auto() 99 NATIONAL_STRING = auto() 100 RAW_STRING = auto() 101 HEREDOC_STRING = auto() 102 UNICODE_STRING = auto() 103 104 # types 105 BIT = auto() 106 BOOLEAN = auto() 107 TINYINT = auto() 108 UTINYINT = auto() 109 SMALLINT = auto() 110 USMALLINT = auto() 111 MEDIUMINT = auto() 112 UMEDIUMINT = auto() 113 INT = auto() 114 UINT = auto() 115 BIGINT = auto() 116 UBIGINT = auto() 117 INT128 = auto() 118 UINT128 = auto() 119 INT256 = auto() 120 UINT256 = auto() 121 FLOAT = auto() 122 DOUBLE = auto() 123 DECIMAL = auto() 124 UDECIMAL = auto() 125 BIGDECIMAL = auto() 126 CHAR = auto() 127 NCHAR = auto() 128 VARCHAR = auto() 129 NVARCHAR = auto() 130 BPCHAR = auto() 131 TEXT = auto() 132 MEDIUMTEXT = auto() 133 LONGTEXT = auto() 134 MEDIUMBLOB = auto() 135 LONGBLOB = auto() 136 TINYBLOB = auto() 137 TINYTEXT = auto() 138 NAME = auto() 139 BINARY = auto() 140 VARBINARY = auto() 141 JSON = auto() 142 JSONB = auto() 143 TIME = auto() 144 TIMETZ = auto() 145 TIMESTAMP = auto() 146 TIMESTAMPTZ = auto() 147 TIMESTAMPLTZ = auto() 148 TIMESTAMP_S = auto() 149 TIMESTAMP_MS = auto() 150 TIMESTAMP_NS = auto() 151 DATETIME = auto() 152 DATETIME64 = auto() 153 DATE = auto() 154 DATE32 = auto() 155 INT4RANGE = auto() 156 INT4MULTIRANGE = auto() 157 INT8RANGE = auto() 158 INT8MULTIRANGE = auto() 159 NUMRANGE = auto() 160 NUMMULTIRANGE = auto() 161 TSRANGE = auto() 162 TSMULTIRANGE = auto() 163 TSTZRANGE = auto() 164 TSTZMULTIRANGE = auto() 165 DATERANGE = auto() 166 DATEMULTIRANGE = auto() 167 UUID = auto() 168 GEOGRAPHY = auto() 169 NULLABLE = auto() 170 GEOMETRY = auto() 171 HLLSKETCH = auto() 172 HSTORE = auto() 173 SUPER = auto() 174 SERIAL = auto() 175 SMALLSERIAL = auto() 176 BIGSERIAL = auto() 177 XML = auto() 178 YEAR = auto() 179 UNIQUEIDENTIFIER = auto() 180 USERDEFINED = auto() 181 MONEY = auto() 182 SMALLMONEY = auto() 183 ROWVERSION = auto() 184 IMAGE = auto() 185 VARIANT = auto() 186 OBJECT = auto() 187 INET = auto() 188 IPADDRESS = auto() 189 IPPREFIX = auto() 190 IPV4 = auto() 191 IPV6 = auto() 192 ENUM = auto() 193 ENUM8 = auto() 194 ENUM16 = auto() 195 FIXEDSTRING = auto() 196 LOWCARDINALITY = auto() 197 NESTED = auto() 198 AGGREGATEFUNCTION = auto() 199 SIMPLEAGGREGATEFUNCTION = auto() 200 UNKNOWN = auto() 201 202 # keywords 203 ALIAS = auto() 204 ALTER = auto() 205 ALWAYS = auto() 206 ALL = auto() 207 ANTI = auto() 208 ANY = auto() 209 APPLY = auto() 210 ARRAY = auto() 211 ASC = auto() 212 ASOF = auto() 213 AUTO_INCREMENT = auto() 214 BEGIN = auto() 215 BETWEEN = auto() 216 CACHE = auto() 217 CASE = auto() 218 CHARACTER_SET = auto() 219 CLUSTER_BY = auto() 220 COLLATE = auto() 221 COMMAND = auto() 222 COMMENT = auto() 223 COMMIT = auto() 224 CONNECT_BY = auto() 225 CONSTRAINT = auto() 226 CREATE = auto() 227 CROSS = auto() 228 CUBE = auto() 229 CURRENT_DATE = auto() 230 CURRENT_DATETIME = auto() 231 CURRENT_TIME = auto() 232 CURRENT_TIMESTAMP = auto() 233 CURRENT_USER = auto() 234 DEFAULT = auto() 235 DELETE = auto() 236 DESC = auto() 237 DESCRIBE = auto() 238 DICTIONARY = auto() 239 DISTINCT = auto() 240 DISTRIBUTE_BY = auto() 241 DIV = auto() 242 DROP = auto() 243 ELSE = auto() 244 END = auto() 245 ESCAPE = auto() 246 EXCEPT = auto() 247 EXECUTE = auto() 248 EXISTS = auto() 249 FALSE = auto() 250 FETCH = auto() 251 FILTER = auto() 252 FINAL = auto() 253 FIRST = auto() 254 FOR = auto() 255 FORCE = auto() 256 FOREIGN_KEY = auto() 257 FORMAT = auto() 258 FROM = auto() 259 FULL = auto() 260 FUNCTION = auto() 261 GLOB = auto() 262 GLOBAL = auto() 263 GROUP_BY = auto() 264 GROUPING_SETS = auto() 265 HAVING = auto() 266 HINT = auto() 267 IGNORE = auto() 268 ILIKE = auto() 269 ILIKE_ANY = auto() 270 IN = auto() 271 INDEX = auto() 272 INNER = auto() 273 INSERT = auto() 274 INTERSECT = auto() 275 INTERVAL = auto() 276 INTO = auto() 277 INTRODUCER = auto() 278 IRLIKE = auto() 279 IS = auto() 280 ISNULL = auto() 281 JOIN = auto() 282 JOIN_MARKER = auto() 283 KEEP = auto() 284 KILL = auto() 285 LANGUAGE = auto() 286 LATERAL = auto() 287 LEFT = auto() 288 LIKE = auto() 289 LIKE_ANY = auto() 290 LIMIT = auto() 291 LOAD = auto() 292 LOCK = auto() 293 MAP = auto() 294 MATCH_CONDITION = auto() 295 MATCH_RECOGNIZE = auto() 296 MEMBER_OF = auto() 297 MERGE = auto() 298 MOD = auto() 299 MODEL = auto() 300 NATURAL = auto() 301 NEXT = auto() 302 NOTNULL = auto() 303 NULL = auto() 304 OBJECT_IDENTIFIER = auto() 305 OFFSET = auto() 306 ON = auto() 307 ONLY = auto() 308 OPERATOR = auto() 309 ORDER_BY = auto() 310 ORDER_SIBLINGS_BY = auto() 311 ORDERED = auto() 312 ORDINALITY = auto() 313 OUTER = auto() 314 OVER = auto() 315 OVERLAPS = auto() 316 OVERWRITE = auto() 317 PARTITION = auto() 318 PARTITION_BY = auto() 319 PERCENT = auto() 320 PIVOT = auto() 321 PLACEHOLDER = auto() 322 POSITIONAL = auto() 323 PRAGMA = auto() 324 PREWHERE = auto() 325 PRIMARY_KEY = auto() 326 PROCEDURE = auto() 327 PROPERTIES = auto() 328 PSEUDO_TYPE = auto() 329 QUALIFY = auto() 330 QUOTE = auto() 331 RANGE = auto() 332 RECURSIVE = auto() 333 REFRESH = auto() 334 REPLACE = auto() 335 RETURNING = auto() 336 REFERENCES = auto() 337 RIGHT = auto() 338 RLIKE = auto() 339 ROLLBACK = auto() 340 ROLLUP = auto() 341 ROW = auto() 342 ROWS = auto() 343 SELECT = auto() 344 SEMI = auto() 345 SEPARATOR = auto() 346 SEQUENCE = auto() 347 SERDE_PROPERTIES = auto() 348 SET = auto() 349 SETTINGS = auto() 350 SHOW = auto() 351 SIMILAR_TO = auto() 352 SOME = auto() 353 SORT_BY = auto() 354 START_WITH = auto() 355 STORAGE_INTEGRATION = auto() 356 STRUCT = auto() 357 TABLE_SAMPLE = auto() 358 TEMPORARY = auto() 359 TOP = auto() 360 THEN = auto() 361 TRUE = auto() 362 TRUNCATE = auto() 363 UNCACHE = auto() 364 UNION = auto() 365 UNNEST = auto() 366 UNPIVOT = auto() 367 UPDATE = auto() 368 USE = auto() 369 USING = auto() 370 VALUES = auto() 371 VIEW = auto() 372 VOLATILE = auto() 373 WHEN = auto() 374 WHERE = auto() 375 WINDOW = auto() 376 WITH = auto() 377 UNIQUE = auto() 378 VERSION_SNAPSHOT = auto() 379 TIMESTAMP_SNAPSHOT = auto() 380 OPTION = auto() 381 382 383_ALL_TOKEN_TYPES = list(TokenType) 384_TOKEN_TYPE_TO_INDEX = {token_type: i for i, token_type in enumerate(_ALL_TOKEN_TYPES)} 385 386 387class Token: 388 __slots__ = ("token_type", "text", "line", "col", "start", "end", "comments") 389 390 @classmethod 391 def number(cls, number: int) -> Token: 392 """Returns a NUMBER token with `number` as its text.""" 393 return cls(TokenType.NUMBER, str(number)) 394 395 @classmethod 396 def string(cls, string: str) -> Token: 397 """Returns a STRING token with `string` as its text.""" 398 return cls(TokenType.STRING, string) 399 400 @classmethod 401 def identifier(cls, identifier: str) -> Token: 402 """Returns an IDENTIFIER token with `identifier` as its text.""" 403 return cls(TokenType.IDENTIFIER, identifier) 404 405 @classmethod 406 def var(cls, var: str) -> Token: 407 """Returns an VAR token with `var` as its text.""" 408 return cls(TokenType.VAR, var) 409 410 def __init__( 411 self, 412 token_type: TokenType, 413 text: str, 414 line: int = 1, 415 col: int = 1, 416 start: int = 0, 417 end: int = 0, 418 comments: t.Optional[t.List[str]] = None, 419 ) -> None: 420 """Token initializer. 421 422 Args: 423 token_type: The TokenType Enum. 424 text: The text of the token. 425 line: The line that the token ends on. 426 col: The column that the token ends on. 427 start: The start index of the token. 428 end: The ending index of the token. 429 comments: The comments to attach to the token. 430 """ 431 self.token_type = token_type 432 self.text = text 433 self.line = line 434 self.col = col 435 self.start = start 436 self.end = end 437 self.comments = [] if comments is None else comments 438 439 def __repr__(self) -> str: 440 attributes = ", ".join(f"{k}: {getattr(self, k)}" for k in self.__slots__) 441 return f"<Token {attributes}>" 442 443 444class _Tokenizer(type): 445 def __new__(cls, clsname, bases, attrs): 446 klass = super().__new__(cls, clsname, bases, attrs) 447 448 def _convert_quotes(arr: t.List[str | t.Tuple[str, str]]) -> t.Dict[str, str]: 449 return dict( 450 (item, item) if isinstance(item, str) else (item[0], item[1]) for item in arr 451 ) 452 453 def _quotes_to_format( 454 token_type: TokenType, arr: t.List[str | t.Tuple[str, str]] 455 ) -> t.Dict[str, t.Tuple[str, TokenType]]: 456 return {k: (v, token_type) for k, v in _convert_quotes(arr).items()} 457 458 klass._QUOTES = _convert_quotes(klass.QUOTES) 459 klass._IDENTIFIERS = _convert_quotes(klass.IDENTIFIERS) 460 461 klass._FORMAT_STRINGS = { 462 **{ 463 p + s: (e, TokenType.NATIONAL_STRING) 464 for s, e in klass._QUOTES.items() 465 for p in ("n", "N") 466 }, 467 **_quotes_to_format(TokenType.BIT_STRING, klass.BIT_STRINGS), 468 **_quotes_to_format(TokenType.BYTE_STRING, klass.BYTE_STRINGS), 469 **_quotes_to_format(TokenType.HEX_STRING, klass.HEX_STRINGS), 470 **_quotes_to_format(TokenType.RAW_STRING, klass.RAW_STRINGS), 471 **_quotes_to_format(TokenType.HEREDOC_STRING, klass.HEREDOC_STRINGS), 472 **_quotes_to_format(TokenType.UNICODE_STRING, klass.UNICODE_STRINGS), 473 } 474 475 klass._STRING_ESCAPES = set(klass.STRING_ESCAPES) 476 klass._IDENTIFIER_ESCAPES = set(klass.IDENTIFIER_ESCAPES) 477 klass._COMMENTS = { 478 **dict( 479 (comment, None) if isinstance(comment, str) else (comment[0], comment[1]) 480 for comment in klass.COMMENTS 481 ), 482 "{#": "#}", # Ensure Jinja comments are tokenized correctly in all dialects 483 } 484 485 klass._KEYWORD_TRIE = new_trie( 486 key.upper() 487 for key in ( 488 *klass.KEYWORDS, 489 *klass._COMMENTS, 490 *klass._QUOTES, 491 *klass._FORMAT_STRINGS, 492 ) 493 if " " in key or any(single in key for single in klass.SINGLE_TOKENS) 494 ) 495 496 if USE_RS_TOKENIZER: 497 settings = RsTokenizerSettings( 498 white_space={k: _TOKEN_TYPE_TO_INDEX[v] for k, v in klass.WHITE_SPACE.items()}, 499 single_tokens={k: _TOKEN_TYPE_TO_INDEX[v] for k, v in klass.SINGLE_TOKENS.items()}, 500 keywords={k: _TOKEN_TYPE_TO_INDEX[v] for k, v in klass.KEYWORDS.items()}, 501 numeric_literals=klass.NUMERIC_LITERALS, 502 identifiers=klass._IDENTIFIERS, 503 identifier_escapes=klass._IDENTIFIER_ESCAPES, 504 string_escapes=klass._STRING_ESCAPES, 505 quotes=klass._QUOTES, 506 format_strings={ 507 k: (v1, _TOKEN_TYPE_TO_INDEX[v2]) 508 for k, (v1, v2) in klass._FORMAT_STRINGS.items() 509 }, 510 has_bit_strings=bool(klass.BIT_STRINGS), 511 has_hex_strings=bool(klass.HEX_STRINGS), 512 comments=klass._COMMENTS, 513 var_single_tokens=klass.VAR_SINGLE_TOKENS, 514 commands={_TOKEN_TYPE_TO_INDEX[v] for v in klass.COMMANDS}, 515 command_prefix_tokens={ 516 _TOKEN_TYPE_TO_INDEX[v] for v in klass.COMMAND_PREFIX_TOKENS 517 }, 518 heredoc_tag_is_identifier=klass.HEREDOC_TAG_IS_IDENTIFIER, 519 ) 520 token_types = RsTokenTypeSettings( 521 bit_string=_TOKEN_TYPE_TO_INDEX[TokenType.BIT_STRING], 522 break_=_TOKEN_TYPE_TO_INDEX[TokenType.BREAK], 523 dcolon=_TOKEN_TYPE_TO_INDEX[TokenType.DCOLON], 524 heredoc_string=_TOKEN_TYPE_TO_INDEX[TokenType.HEREDOC_STRING], 525 raw_string=_TOKEN_TYPE_TO_INDEX[TokenType.RAW_STRING], 526 hex_string=_TOKEN_TYPE_TO_INDEX[TokenType.HEX_STRING], 527 identifier=_TOKEN_TYPE_TO_INDEX[TokenType.IDENTIFIER], 528 number=_TOKEN_TYPE_TO_INDEX[TokenType.NUMBER], 529 parameter=_TOKEN_TYPE_TO_INDEX[TokenType.PARAMETER], 530 semicolon=_TOKEN_TYPE_TO_INDEX[TokenType.SEMICOLON], 531 string=_TOKEN_TYPE_TO_INDEX[TokenType.STRING], 532 var=_TOKEN_TYPE_TO_INDEX[TokenType.VAR], 533 heredoc_string_alternative=_TOKEN_TYPE_TO_INDEX[klass.HEREDOC_STRING_ALTERNATIVE], 534 ) 535 klass._RS_TOKENIZER = RsTokenizer(settings, token_types) 536 else: 537 klass._RS_TOKENIZER = None 538 539 return klass 540 541 542class Tokenizer(metaclass=_Tokenizer): 543 SINGLE_TOKENS = { 544 "(": TokenType.L_PAREN, 545 ")": TokenType.R_PAREN, 546 "[": TokenType.L_BRACKET, 547 "]": TokenType.R_BRACKET, 548 "{": TokenType.L_BRACE, 549 "}": TokenType.R_BRACE, 550 "&": TokenType.AMP, 551 "^": TokenType.CARET, 552 ":": TokenType.COLON, 553 ",": TokenType.COMMA, 554 ".": TokenType.DOT, 555 "-": TokenType.DASH, 556 "=": TokenType.EQ, 557 ">": TokenType.GT, 558 "<": TokenType.LT, 559 "%": TokenType.MOD, 560 "!": TokenType.NOT, 561 "|": TokenType.PIPE, 562 "+": TokenType.PLUS, 563 ";": TokenType.SEMICOLON, 564 "/": TokenType.SLASH, 565 "\\": TokenType.BACKSLASH, 566 "*": TokenType.STAR, 567 "~": TokenType.TILDA, 568 "?": TokenType.PLACEHOLDER, 569 "@": TokenType.PARAMETER, 570 # Used for breaking a var like x'y' but nothing else the token type doesn't matter 571 "'": TokenType.QUOTE, 572 "`": TokenType.IDENTIFIER, 573 '"': TokenType.IDENTIFIER, 574 "#": TokenType.HASH, 575 } 576 577 BIT_STRINGS: t.List[str | t.Tuple[str, str]] = [] 578 BYTE_STRINGS: t.List[str | t.Tuple[str, str]] = [] 579 HEX_STRINGS: t.List[str | t.Tuple[str, str]] = [] 580 RAW_STRINGS: t.List[str | t.Tuple[str, str]] = [] 581 HEREDOC_STRINGS: t.List[str | t.Tuple[str, str]] = [] 582 UNICODE_STRINGS: t.List[str | t.Tuple[str, str]] = [] 583 IDENTIFIERS: t.List[str | t.Tuple[str, str]] = ['"'] 584 IDENTIFIER_ESCAPES = ['"'] 585 QUOTES: t.List[t.Tuple[str, str] | str] = ["'"] 586 STRING_ESCAPES = ["'"] 587 VAR_SINGLE_TOKENS: t.Set[str] = set() 588 589 # Whether the heredoc tags follow the same lexical rules as unquoted identifiers 590 HEREDOC_TAG_IS_IDENTIFIER = False 591 592 # Token that we'll generate as a fallback if the heredoc prefix doesn't correspond to a heredoc 593 HEREDOC_STRING_ALTERNATIVE = TokenType.VAR 594 595 # Autofilled 596 _COMMENTS: t.Dict[str, str] = {} 597 _FORMAT_STRINGS: t.Dict[str, t.Tuple[str, TokenType]] = {} 598 _IDENTIFIERS: t.Dict[str, str] = {} 599 _IDENTIFIER_ESCAPES: t.Set[str] = set() 600 _QUOTES: t.Dict[str, str] = {} 601 _STRING_ESCAPES: t.Set[str] = set() 602 _KEYWORD_TRIE: t.Dict = {} 603 _RS_TOKENIZER: t.Optional[t.Any] = None 604 605 KEYWORDS: t.Dict[str, TokenType] = { 606 **{f"{{%{postfix}": TokenType.BLOCK_START for postfix in ("", "+", "-")}, 607 **{f"{prefix}%}}": TokenType.BLOCK_END for prefix in ("", "+", "-")}, 608 **{f"{{{{{postfix}": TokenType.BLOCK_START for postfix in ("+", "-")}, 609 **{f"{prefix}}}}}": TokenType.BLOCK_END for prefix in ("+", "-")}, 610 "/*+": TokenType.HINT, 611 "==": TokenType.EQ, 612 "::": TokenType.DCOLON, 613 "||": TokenType.DPIPE, 614 ">=": TokenType.GTE, 615 "<=": TokenType.LTE, 616 "<>": TokenType.NEQ, 617 "!=": TokenType.NEQ, 618 ":=": TokenType.COLON_EQ, 619 "<=>": TokenType.NULLSAFE_EQ, 620 "->": TokenType.ARROW, 621 "->>": TokenType.DARROW, 622 "=>": TokenType.FARROW, 623 "#>": TokenType.HASH_ARROW, 624 "#>>": TokenType.DHASH_ARROW, 625 "<->": TokenType.LR_ARROW, 626 "&&": TokenType.DAMP, 627 "??": TokenType.DQMARK, 628 "ALL": TokenType.ALL, 629 "ALWAYS": TokenType.ALWAYS, 630 "AND": TokenType.AND, 631 "ANTI": TokenType.ANTI, 632 "ANY": TokenType.ANY, 633 "ASC": TokenType.ASC, 634 "AS": TokenType.ALIAS, 635 "ASOF": TokenType.ASOF, 636 "AUTOINCREMENT": TokenType.AUTO_INCREMENT, 637 "AUTO_INCREMENT": TokenType.AUTO_INCREMENT, 638 "BEGIN": TokenType.BEGIN, 639 "BETWEEN": TokenType.BETWEEN, 640 "CACHE": TokenType.CACHE, 641 "UNCACHE": TokenType.UNCACHE, 642 "CASE": TokenType.CASE, 643 "CHARACTER SET": TokenType.CHARACTER_SET, 644 "CLUSTER BY": TokenType.CLUSTER_BY, 645 "COLLATE": TokenType.COLLATE, 646 "COLUMN": TokenType.COLUMN, 647 "COMMIT": TokenType.COMMIT, 648 "CONNECT BY": TokenType.CONNECT_BY, 649 "CONSTRAINT": TokenType.CONSTRAINT, 650 "CREATE": TokenType.CREATE, 651 "CROSS": TokenType.CROSS, 652 "CUBE": TokenType.CUBE, 653 "CURRENT_DATE": TokenType.CURRENT_DATE, 654 "CURRENT_TIME": TokenType.CURRENT_TIME, 655 "CURRENT_TIMESTAMP": TokenType.CURRENT_TIMESTAMP, 656 "CURRENT_USER": TokenType.CURRENT_USER, 657 "DATABASE": TokenType.DATABASE, 658 "DEFAULT": TokenType.DEFAULT, 659 "DELETE": TokenType.DELETE, 660 "DESC": TokenType.DESC, 661 "DESCRIBE": TokenType.DESCRIBE, 662 "DISTINCT": TokenType.DISTINCT, 663 "DISTRIBUTE BY": TokenType.DISTRIBUTE_BY, 664 "DIV": TokenType.DIV, 665 "DROP": TokenType.DROP, 666 "ELSE": TokenType.ELSE, 667 "END": TokenType.END, 668 "ENUM": TokenType.ENUM, 669 "ESCAPE": TokenType.ESCAPE, 670 "EXCEPT": TokenType.EXCEPT, 671 "EXECUTE": TokenType.EXECUTE, 672 "EXISTS": TokenType.EXISTS, 673 "FALSE": TokenType.FALSE, 674 "FETCH": TokenType.FETCH, 675 "FILTER": TokenType.FILTER, 676 "FIRST": TokenType.FIRST, 677 "FULL": TokenType.FULL, 678 "FUNCTION": TokenType.FUNCTION, 679 "FOR": TokenType.FOR, 680 "FOREIGN KEY": TokenType.FOREIGN_KEY, 681 "FORMAT": TokenType.FORMAT, 682 "FROM": TokenType.FROM, 683 "GEOGRAPHY": TokenType.GEOGRAPHY, 684 "GEOMETRY": TokenType.GEOMETRY, 685 "GLOB": TokenType.GLOB, 686 "GROUP BY": TokenType.GROUP_BY, 687 "GROUPING SETS": TokenType.GROUPING_SETS, 688 "HAVING": TokenType.HAVING, 689 "ILIKE": TokenType.ILIKE, 690 "IN": TokenType.IN, 691 "INDEX": TokenType.INDEX, 692 "INET": TokenType.INET, 693 "INNER": TokenType.INNER, 694 "INSERT": TokenType.INSERT, 695 "INTERVAL": TokenType.INTERVAL, 696 "INTERSECT": TokenType.INTERSECT, 697 "INTO": TokenType.INTO, 698 "IS": TokenType.IS, 699 "ISNULL": TokenType.ISNULL, 700 "JOIN": TokenType.JOIN, 701 "KEEP": TokenType.KEEP, 702 "KILL": TokenType.KILL, 703 "LATERAL": TokenType.LATERAL, 704 "LEFT": TokenType.LEFT, 705 "LIKE": TokenType.LIKE, 706 "LIMIT": TokenType.LIMIT, 707 "LOAD": TokenType.LOAD, 708 "LOCK": TokenType.LOCK, 709 "MERGE": TokenType.MERGE, 710 "NATURAL": TokenType.NATURAL, 711 "NEXT": TokenType.NEXT, 712 "NOT": TokenType.NOT, 713 "NOTNULL": TokenType.NOTNULL, 714 "NULL": TokenType.NULL, 715 "OBJECT": TokenType.OBJECT, 716 "OFFSET": TokenType.OFFSET, 717 "ON": TokenType.ON, 718 "OR": TokenType.OR, 719 "XOR": TokenType.XOR, 720 "ORDER BY": TokenType.ORDER_BY, 721 "ORDINALITY": TokenType.ORDINALITY, 722 "OUTER": TokenType.OUTER, 723 "OVER": TokenType.OVER, 724 "OVERLAPS": TokenType.OVERLAPS, 725 "OVERWRITE": TokenType.OVERWRITE, 726 "PARTITION": TokenType.PARTITION, 727 "PARTITION BY": TokenType.PARTITION_BY, 728 "PARTITIONED BY": TokenType.PARTITION_BY, 729 "PARTITIONED_BY": TokenType.PARTITION_BY, 730 "PERCENT": TokenType.PERCENT, 731 "PIVOT": TokenType.PIVOT, 732 "PRAGMA": TokenType.PRAGMA, 733 "PRIMARY KEY": TokenType.PRIMARY_KEY, 734 "PROCEDURE": TokenType.PROCEDURE, 735 "QUALIFY": TokenType.QUALIFY, 736 "RANGE": TokenType.RANGE, 737 "RECURSIVE": TokenType.RECURSIVE, 738 "REGEXP": TokenType.RLIKE, 739 "REPLACE": TokenType.REPLACE, 740 "RETURNING": TokenType.RETURNING, 741 "REFERENCES": TokenType.REFERENCES, 742 "RIGHT": TokenType.RIGHT, 743 "RLIKE": TokenType.RLIKE, 744 "ROLLBACK": TokenType.ROLLBACK, 745 "ROLLUP": TokenType.ROLLUP, 746 "ROW": TokenType.ROW, 747 "ROWS": TokenType.ROWS, 748 "SCHEMA": TokenType.SCHEMA, 749 "SELECT": TokenType.SELECT, 750 "SEMI": TokenType.SEMI, 751 "SET": TokenType.SET, 752 "SETTINGS": TokenType.SETTINGS, 753 "SHOW": TokenType.SHOW, 754 "SIMILAR TO": TokenType.SIMILAR_TO, 755 "SOME": TokenType.SOME, 756 "SORT BY": TokenType.SORT_BY, 757 "START WITH": TokenType.START_WITH, 758 "TABLE": TokenType.TABLE, 759 "TABLESAMPLE": TokenType.TABLE_SAMPLE, 760 "TEMP": TokenType.TEMPORARY, 761 "TEMPORARY": TokenType.TEMPORARY, 762 "THEN": TokenType.THEN, 763 "TRUE": TokenType.TRUE, 764 "TRUNCATE": TokenType.TRUNCATE, 765 "UNION": TokenType.UNION, 766 "UNKNOWN": TokenType.UNKNOWN, 767 "UNNEST": TokenType.UNNEST, 768 "UNPIVOT": TokenType.UNPIVOT, 769 "UPDATE": TokenType.UPDATE, 770 "USE": TokenType.USE, 771 "USING": TokenType.USING, 772 "UUID": TokenType.UUID, 773 "VALUES": TokenType.VALUES, 774 "VIEW": TokenType.VIEW, 775 "VOLATILE": TokenType.VOLATILE, 776 "WHEN": TokenType.WHEN, 777 "WHERE": TokenType.WHERE, 778 "WINDOW": TokenType.WINDOW, 779 "WITH": TokenType.WITH, 780 "APPLY": TokenType.APPLY, 781 "ARRAY": TokenType.ARRAY, 782 "BIT": TokenType.BIT, 783 "BOOL": TokenType.BOOLEAN, 784 "BOOLEAN": TokenType.BOOLEAN, 785 "BYTE": TokenType.TINYINT, 786 "MEDIUMINT": TokenType.MEDIUMINT, 787 "INT1": TokenType.TINYINT, 788 "TINYINT": TokenType.TINYINT, 789 "INT16": TokenType.SMALLINT, 790 "SHORT": TokenType.SMALLINT, 791 "SMALLINT": TokenType.SMALLINT, 792 "INT128": TokenType.INT128, 793 "HUGEINT": TokenType.INT128, 794 "INT2": TokenType.SMALLINT, 795 "INTEGER": TokenType.INT, 796 "INT": TokenType.INT, 797 "INT4": TokenType.INT, 798 "INT32": TokenType.INT, 799 "INT64": TokenType.BIGINT, 800 "LONG": TokenType.BIGINT, 801 "BIGINT": TokenType.BIGINT, 802 "INT8": TokenType.TINYINT, 803 "UINT": TokenType.UINT, 804 "DEC": TokenType.DECIMAL, 805 "DECIMAL": TokenType.DECIMAL, 806 "BIGDECIMAL": TokenType.BIGDECIMAL, 807 "BIGNUMERIC": TokenType.BIGDECIMAL, 808 "MAP": TokenType.MAP, 809 "NULLABLE": TokenType.NULLABLE, 810 "NUMBER": TokenType.DECIMAL, 811 "NUMERIC": TokenType.DECIMAL, 812 "FIXED": TokenType.DECIMAL, 813 "REAL": TokenType.FLOAT, 814 "FLOAT": TokenType.FLOAT, 815 "FLOAT4": TokenType.FLOAT, 816 "FLOAT8": TokenType.DOUBLE, 817 "DOUBLE": TokenType.DOUBLE, 818 "DOUBLE PRECISION": TokenType.DOUBLE, 819 "JSON": TokenType.JSON, 820 "CHAR": TokenType.CHAR, 821 "CHARACTER": TokenType.CHAR, 822 "NCHAR": TokenType.NCHAR, 823 "VARCHAR": TokenType.VARCHAR, 824 "VARCHAR2": TokenType.VARCHAR, 825 "NVARCHAR": TokenType.NVARCHAR, 826 "NVARCHAR2": TokenType.NVARCHAR, 827 "BPCHAR": TokenType.BPCHAR, 828 "STR": TokenType.TEXT, 829 "STRING": TokenType.TEXT, 830 "TEXT": TokenType.TEXT, 831 "LONGTEXT": TokenType.LONGTEXT, 832 "MEDIUMTEXT": TokenType.MEDIUMTEXT, 833 "TINYTEXT": TokenType.TINYTEXT, 834 "CLOB": TokenType.TEXT, 835 "LONGVARCHAR": TokenType.TEXT, 836 "BINARY": TokenType.BINARY, 837 "BLOB": TokenType.VARBINARY, 838 "LONGBLOB": TokenType.LONGBLOB, 839 "MEDIUMBLOB": TokenType.MEDIUMBLOB, 840 "TINYBLOB": TokenType.TINYBLOB, 841 "BYTEA": TokenType.VARBINARY, 842 "VARBINARY": TokenType.VARBINARY, 843 "TIME": TokenType.TIME, 844 "TIMETZ": TokenType.TIMETZ, 845 "TIMESTAMP": TokenType.TIMESTAMP, 846 "TIMESTAMPTZ": TokenType.TIMESTAMPTZ, 847 "TIMESTAMPLTZ": TokenType.TIMESTAMPLTZ, 848 "DATE": TokenType.DATE, 849 "DATETIME": TokenType.DATETIME, 850 "INT4RANGE": TokenType.INT4RANGE, 851 "INT4MULTIRANGE": TokenType.INT4MULTIRANGE, 852 "INT8RANGE": TokenType.INT8RANGE, 853 "INT8MULTIRANGE": TokenType.INT8MULTIRANGE, 854 "NUMRANGE": TokenType.NUMRANGE, 855 "NUMMULTIRANGE": TokenType.NUMMULTIRANGE, 856 "TSRANGE": TokenType.TSRANGE, 857 "TSMULTIRANGE": TokenType.TSMULTIRANGE, 858 "TSTZRANGE": TokenType.TSTZRANGE, 859 "TSTZMULTIRANGE": TokenType.TSTZMULTIRANGE, 860 "DATERANGE": TokenType.DATERANGE, 861 "DATEMULTIRANGE": TokenType.DATEMULTIRANGE, 862 "UNIQUE": TokenType.UNIQUE, 863 "STRUCT": TokenType.STRUCT, 864 "SEQUENCE": TokenType.SEQUENCE, 865 "VARIANT": TokenType.VARIANT, 866 "ALTER": TokenType.ALTER, 867 "ANALYZE": TokenType.COMMAND, 868 "CALL": TokenType.COMMAND, 869 "COMMENT": TokenType.COMMENT, 870 "COPY": TokenType.COMMAND, 871 "EXPLAIN": TokenType.COMMAND, 872 "GRANT": TokenType.COMMAND, 873 "OPTIMIZE": TokenType.COMMAND, 874 "PREPARE": TokenType.COMMAND, 875 "VACUUM": TokenType.COMMAND, 876 "USER-DEFINED": TokenType.USERDEFINED, 877 "FOR VERSION": TokenType.VERSION_SNAPSHOT, 878 "FOR TIMESTAMP": TokenType.TIMESTAMP_SNAPSHOT, 879 } 880 881 WHITE_SPACE: t.Dict[t.Optional[str], TokenType] = { 882 " ": TokenType.SPACE, 883 "\t": TokenType.SPACE, 884 "\n": TokenType.BREAK, 885 "\r": TokenType.BREAK, 886 } 887 888 COMMANDS = { 889 TokenType.COMMAND, 890 TokenType.EXECUTE, 891 TokenType.FETCH, 892 TokenType.SHOW, 893 } 894 895 COMMAND_PREFIX_TOKENS = {TokenType.SEMICOLON, TokenType.BEGIN} 896 897 # Handle numeric literals like in hive (3L = BIGINT) 898 NUMERIC_LITERALS: t.Dict[str, str] = {} 899 900 COMMENTS = ["--", ("/*", "*/")] 901 902 __slots__ = ( 903 "sql", 904 "size", 905 "tokens", 906 "dialect", 907 "_start", 908 "_current", 909 "_line", 910 "_col", 911 "_comments", 912 "_char", 913 "_end", 914 "_peek", 915 "_prev_token_line", 916 "_rs_dialect_settings", 917 ) 918 919 def __init__(self, dialect: DialectType = None) -> None: 920 from sqlglot.dialects import Dialect 921 922 self.dialect = Dialect.get_or_raise(dialect) 923 924 if USE_RS_TOKENIZER: 925 self._rs_dialect_settings = RsTokenizerDialectSettings( 926 unescaped_sequences=self.dialect.UNESCAPED_SEQUENCES, 927 identifiers_can_start_with_digit=self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT, 928 ) 929 930 self.reset() 931 932 def reset(self) -> None: 933 self.sql = "" 934 self.size = 0 935 self.tokens: t.List[Token] = [] 936 self._start = 0 937 self._current = 0 938 self._line = 1 939 self._col = 0 940 self._comments: t.List[str] = [] 941 942 self._char = "" 943 self._end = False 944 self._peek = "" 945 self._prev_token_line = -1 946 947 def tokenize(self, sql: str) -> t.List[Token]: 948 """Returns a list of tokens corresponding to the SQL string `sql`.""" 949 if USE_RS_TOKENIZER: 950 return self.tokenize_rs(sql) 951 952 self.reset() 953 self.sql = sql 954 self.size = len(sql) 955 956 try: 957 self._scan() 958 except Exception as e: 959 start = max(self._current - 50, 0) 960 end = min(self._current + 50, self.size - 1) 961 context = self.sql[start:end] 962 raise TokenError(f"Error tokenizing '{context}'") from e 963 964 return self.tokens 965 966 def _scan(self, until: t.Optional[t.Callable] = None) -> None: 967 while self.size and not self._end: 968 current = self._current 969 970 # Skip spaces here rather than iteratively calling advance() for performance reasons 971 while current < self.size: 972 char = self.sql[current] 973 974 if char.isspace() and (char == " " or char == "\t"): 975 current += 1 976 else: 977 break 978 979 offset = current - self._current if current > self._current else 1 980 981 self._start = current 982 self._advance(offset) 983 984 if not self._char.isspace(): 985 if self._char.isdigit(): 986 self._scan_number() 987 elif self._char in self._IDENTIFIERS: 988 self._scan_identifier(self._IDENTIFIERS[self._char]) 989 else: 990 self._scan_keywords() 991 992 if until and until(): 993 break 994 995 if self.tokens and self._comments: 996 self.tokens[-1].comments.extend(self._comments) 997 998 def _chars(self, size: int) -> str: 999 if size == 1: 1000 return self._char 1001 1002 start = self._current - 1 1003 end = start + size 1004 1005 return self.sql[start:end] if end <= self.size else "" 1006 1007 def _advance(self, i: int = 1, alnum: bool = False) -> None: 1008 if self.WHITE_SPACE.get(self._char) is TokenType.BREAK: 1009 # Ensures we don't count an extra line if we get a \r\n line break sequence 1010 if not (self._char == "\r" and self._peek == "\n"): 1011 self._col = 1 1012 self._line += 1 1013 else: 1014 self._col += i 1015 1016 self._current += i 1017 self._end = self._current >= self.size 1018 self._char = self.sql[self._current - 1] 1019 self._peek = "" if self._end else self.sql[self._current] 1020 1021 if alnum and self._char.isalnum(): 1022 # Here we use local variables instead of attributes for better performance 1023 _col = self._col 1024 _current = self._current 1025 _end = self._end 1026 _peek = self._peek 1027 1028 while _peek.isalnum(): 1029 _col += 1 1030 _current += 1 1031 _end = _current >= self.size 1032 _peek = "" if _end else self.sql[_current] 1033 1034 self._col = _col 1035 self._current = _current 1036 self._end = _end 1037 self._peek = _peek 1038 self._char = self.sql[_current - 1] 1039 1040 @property 1041 def _text(self) -> str: 1042 return self.sql[self._start : self._current] 1043 1044 def _add(self, token_type: TokenType, text: t.Optional[str] = None) -> None: 1045 self._prev_token_line = self._line 1046 1047 if self._comments and token_type == TokenType.SEMICOLON and self.tokens: 1048 self.tokens[-1].comments.extend(self._comments) 1049 self._comments = [] 1050 1051 self.tokens.append( 1052 Token( 1053 token_type, 1054 text=self._text if text is None else text, 1055 line=self._line, 1056 col=self._col, 1057 start=self._start, 1058 end=self._current - 1, 1059 comments=self._comments, 1060 ) 1061 ) 1062 self._comments = [] 1063 1064 # If we have either a semicolon or a begin token before the command's token, we'll parse 1065 # whatever follows the command's token as a string 1066 if ( 1067 token_type in self.COMMANDS 1068 and self._peek != ";" 1069 and (len(self.tokens) == 1 or self.tokens[-2].token_type in self.COMMAND_PREFIX_TOKENS) 1070 ): 1071 start = self._current 1072 tokens = len(self.tokens) 1073 self._scan(lambda: self._peek == ";") 1074 self.tokens = self.tokens[:tokens] 1075 text = self.sql[start : self._current].strip() 1076 if text: 1077 self._add(TokenType.STRING, text) 1078 1079 def _scan_keywords(self) -> None: 1080 size = 0 1081 word = None 1082 chars = self._text 1083 char = chars 1084 prev_space = False 1085 skip = False 1086 trie = self._KEYWORD_TRIE 1087 single_token = char in self.SINGLE_TOKENS 1088 1089 while chars: 1090 if skip: 1091 result = TrieResult.PREFIX 1092 else: 1093 result, trie = in_trie(trie, char.upper()) 1094 1095 if result == TrieResult.FAILED: 1096 break 1097 if result == TrieResult.EXISTS: 1098 word = chars 1099 1100 end = self._current + size 1101 size += 1 1102 1103 if end < self.size: 1104 char = self.sql[end] 1105 single_token = single_token or char in self.SINGLE_TOKENS 1106 is_space = char.isspace() 1107 1108 if not is_space or not prev_space: 1109 if is_space: 1110 char = " " 1111 chars += char 1112 prev_space = is_space 1113 skip = False 1114 else: 1115 skip = True 1116 else: 1117 char = "" 1118 break 1119 1120 if word: 1121 if self._scan_string(word): 1122 return 1123 if self._scan_comment(word): 1124 return 1125 if prev_space or single_token or not char: 1126 self._advance(size - 1) 1127 word = word.upper() 1128 self._add(self.KEYWORDS[word], text=word) 1129 return 1130 1131 if self._char in self.SINGLE_TOKENS: 1132 self._add(self.SINGLE_TOKENS[self._char], text=self._char) 1133 return 1134 1135 self._scan_var() 1136 1137 def _scan_comment(self, comment_start: str) -> bool: 1138 if comment_start not in self._COMMENTS: 1139 return False 1140 1141 comment_start_line = self._line 1142 comment_start_size = len(comment_start) 1143 comment_end = self._COMMENTS[comment_start] 1144 1145 if comment_end: 1146 # Skip the comment's start delimiter 1147 self._advance(comment_start_size) 1148 1149 comment_end_size = len(comment_end) 1150 while not self._end and self._chars(comment_end_size) != comment_end: 1151 self._advance(alnum=True) 1152 1153 self._comments.append(self._text[comment_start_size : -comment_end_size + 1]) 1154 self._advance(comment_end_size - 1) 1155 else: 1156 while not self._end and self.WHITE_SPACE.get(self._peek) is not TokenType.BREAK: 1157 self._advance(alnum=True) 1158 self._comments.append(self._text[comment_start_size:]) 1159 1160 # Leading comment is attached to the succeeding token, whilst trailing comment to the preceding. 1161 # Multiple consecutive comments are preserved by appending them to the current comments list. 1162 if comment_start_line == self._prev_token_line: 1163 self.tokens[-1].comments.extend(self._comments) 1164 self._comments = [] 1165 self._prev_token_line = self._line 1166 1167 return True 1168 1169 def _scan_number(self) -> None: 1170 if self._char == "0": 1171 peek = self._peek.upper() 1172 if peek == "B": 1173 return self._scan_bits() if self.BIT_STRINGS else self._add(TokenType.NUMBER) 1174 elif peek == "X": 1175 return self._scan_hex() if self.HEX_STRINGS else self._add(TokenType.NUMBER) 1176 1177 decimal = False 1178 scientific = 0 1179 1180 while True: 1181 if self._peek.isdigit(): 1182 self._advance() 1183 elif self._peek == "." and not decimal: 1184 decimal = True 1185 self._advance() 1186 elif self._peek in ("-", "+") and scientific == 1: 1187 scientific += 1 1188 self._advance() 1189 elif self._peek.upper() == "E" and not scientific: 1190 scientific += 1 1191 self._advance() 1192 elif self._peek.isidentifier(): 1193 number_text = self._text 1194 literal = "" 1195 1196 while self._peek.strip() and self._peek not in self.SINGLE_TOKENS: 1197 literal += self._peek 1198 self._advance() 1199 1200 token_type = self.KEYWORDS.get(self.NUMERIC_LITERALS.get(literal.upper(), "")) 1201 1202 if token_type: 1203 self._add(TokenType.NUMBER, number_text) 1204 self._add(TokenType.DCOLON, "::") 1205 return self._add(token_type, literal) 1206 elif self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT: 1207 return self._add(TokenType.VAR) 1208 1209 self._advance(-len(literal)) 1210 return self._add(TokenType.NUMBER, number_text) 1211 else: 1212 return self._add(TokenType.NUMBER) 1213 1214 def _scan_bits(self) -> None: 1215 self._advance() 1216 value = self._extract_value() 1217 try: 1218 # If `value` can't be converted to a binary, fallback to tokenizing it as an identifier 1219 int(value, 2) 1220 self._add(TokenType.BIT_STRING, value[2:]) # Drop the 0b 1221 except ValueError: 1222 self._add(TokenType.IDENTIFIER) 1223 1224 def _scan_hex(self) -> None: 1225 self._advance() 1226 value = self._extract_value() 1227 try: 1228 # If `value` can't be converted to a hex, fallback to tokenizing it as an identifier 1229 int(value, 16) 1230 self._add(TokenType.HEX_STRING, value[2:]) # Drop the 0x 1231 except ValueError: 1232 self._add(TokenType.IDENTIFIER) 1233 1234 def _extract_value(self) -> str: 1235 while True: 1236 char = self._peek.strip() 1237 if char and char not in self.SINGLE_TOKENS: 1238 self._advance(alnum=True) 1239 else: 1240 break 1241 1242 return self._text 1243 1244 def _scan_string(self, start: str) -> bool: 1245 base = None 1246 token_type = TokenType.STRING 1247 1248 if start in self._QUOTES: 1249 end = self._QUOTES[start] 1250 elif start in self._FORMAT_STRINGS: 1251 end, token_type = self._FORMAT_STRINGS[start] 1252 1253 if token_type == TokenType.HEX_STRING: 1254 base = 16 1255 elif token_type == TokenType.BIT_STRING: 1256 base = 2 1257 elif token_type == TokenType.HEREDOC_STRING: 1258 if ( 1259 self.HEREDOC_TAG_IS_IDENTIFIER 1260 and not self._peek.isidentifier() 1261 and not self._peek == end 1262 ): 1263 if self.HEREDOC_STRING_ALTERNATIVE != token_type.VAR: 1264 self._add(self.HEREDOC_STRING_ALTERNATIVE) 1265 else: 1266 self._scan_var() 1267 1268 return True 1269 1270 self._advance() 1271 1272 if self._char == end: 1273 tag = "" 1274 else: 1275 tag = self._extract_string( 1276 end, 1277 unescape_sequences=False, 1278 raise_unmatched=not self.HEREDOC_TAG_IS_IDENTIFIER, 1279 ) 1280 1281 if self._end and tag and self.HEREDOC_TAG_IS_IDENTIFIER: 1282 self._advance(-len(tag)) 1283 self._add(self.HEREDOC_STRING_ALTERNATIVE) 1284 return True 1285 1286 end = f"{start}{tag}{end}" 1287 else: 1288 return False 1289 1290 self._advance(len(start)) 1291 text = self._extract_string(end, unescape_sequences=token_type != TokenType.RAW_STRING) 1292 1293 if base: 1294 try: 1295 int(text, base) 1296 except Exception: 1297 raise TokenError( 1298 f"Numeric string contains invalid characters from {self._line}:{self._start}" 1299 ) 1300 1301 self._add(token_type, text) 1302 return True 1303 1304 def _scan_identifier(self, identifier_end: str) -> None: 1305 self._advance() 1306 text = self._extract_string(identifier_end, escapes=self._IDENTIFIER_ESCAPES) 1307 self._add(TokenType.IDENTIFIER, text) 1308 1309 def _scan_var(self) -> None: 1310 while True: 1311 char = self._peek.strip() 1312 if char and (char in self.VAR_SINGLE_TOKENS or char not in self.SINGLE_TOKENS): 1313 self._advance(alnum=True) 1314 else: 1315 break 1316 1317 self._add( 1318 TokenType.VAR 1319 if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER 1320 else self.KEYWORDS.get(self._text.upper(), TokenType.VAR) 1321 ) 1322 1323 def _extract_string( 1324 self, 1325 delimiter: str, 1326 escapes: t.Optional[t.Set[str]] = None, 1327 unescape_sequences: bool = True, 1328 raise_unmatched: bool = True, 1329 ) -> str: 1330 text = "" 1331 delim_size = len(delimiter) 1332 escapes = self._STRING_ESCAPES if escapes is None else escapes 1333 1334 while True: 1335 if ( 1336 unescape_sequences 1337 and self.dialect.UNESCAPED_SEQUENCES 1338 and self._peek 1339 and self._char in self.STRING_ESCAPES 1340 ): 1341 unescaped_sequence = self.dialect.UNESCAPED_SEQUENCES.get(self._char + self._peek) 1342 if unescaped_sequence: 1343 self._advance(2) 1344 text += unescaped_sequence 1345 continue 1346 if ( 1347 self._char in escapes 1348 and (self._peek == delimiter or self._peek in escapes) 1349 and (self._char not in self._QUOTES or self._char == self._peek) 1350 ): 1351 if self._peek == delimiter: 1352 text += self._peek 1353 else: 1354 text += self._char + self._peek 1355 1356 if self._current + 1 < self.size: 1357 self._advance(2) 1358 else: 1359 raise TokenError(f"Missing {delimiter} from {self._line}:{self._current}") 1360 else: 1361 if self._chars(delim_size) == delimiter: 1362 if delim_size > 1: 1363 self._advance(delim_size - 1) 1364 break 1365 1366 if self._end: 1367 if not raise_unmatched: 1368 return text + self._char 1369 1370 raise TokenError(f"Missing {delimiter} from {self._line}:{self._start}") 1371 1372 current = self._current - 1 1373 self._advance(alnum=True) 1374 text += self.sql[current : self._current - 1] 1375 1376 return text 1377 1378 def tokenize_rs(self, sql: str) -> t.List[Token]: 1379 if not self._RS_TOKENIZER: 1380 raise SqlglotError("Rust tokenizer is not available") 1381 1382 try: 1383 tokens = self._RS_TOKENIZER.tokenize(sql, self._rs_dialect_settings) 1384 for token in tokens: 1385 token.token_type = _ALL_TOKEN_TYPES[token.token_type_index] 1386 return tokens 1387 except Exception as e: 1388 raise TokenError(str(e))
29class TokenType(AutoName): 30 L_PAREN = auto() 31 R_PAREN = auto() 32 L_BRACKET = auto() 33 R_BRACKET = auto() 34 L_BRACE = auto() 35 R_BRACE = auto() 36 COMMA = auto() 37 DOT = auto() 38 DASH = auto() 39 PLUS = auto() 40 COLON = auto() 41 DCOLON = auto() 42 DQMARK = auto() 43 SEMICOLON = auto() 44 STAR = auto() 45 BACKSLASH = auto() 46 SLASH = auto() 47 LT = auto() 48 LTE = auto() 49 GT = auto() 50 GTE = auto() 51 NOT = auto() 52 EQ = auto() 53 NEQ = auto() 54 NULLSAFE_EQ = auto() 55 COLON_EQ = auto() 56 AND = auto() 57 OR = auto() 58 AMP = auto() 59 DPIPE = auto() 60 PIPE = auto() 61 PIPE_SLASH = auto() 62 DPIPE_SLASH = auto() 63 CARET = auto() 64 TILDA = auto() 65 ARROW = auto() 66 DARROW = auto() 67 FARROW = auto() 68 HASH = auto() 69 HASH_ARROW = auto() 70 DHASH_ARROW = auto() 71 LR_ARROW = auto() 72 DAT = auto() 73 LT_AT = auto() 74 AT_GT = auto() 75 DOLLAR = auto() 76 PARAMETER = auto() 77 SESSION_PARAMETER = auto() 78 DAMP = auto() 79 XOR = auto() 80 DSTAR = auto() 81 82 BLOCK_START = auto() 83 BLOCK_END = auto() 84 85 SPACE = auto() 86 BREAK = auto() 87 88 STRING = auto() 89 NUMBER = auto() 90 IDENTIFIER = auto() 91 DATABASE = auto() 92 COLUMN = auto() 93 COLUMN_DEF = auto() 94 SCHEMA = auto() 95 TABLE = auto() 96 VAR = auto() 97 BIT_STRING = auto() 98 HEX_STRING = auto() 99 BYTE_STRING = auto() 100 NATIONAL_STRING = auto() 101 RAW_STRING = auto() 102 HEREDOC_STRING = auto() 103 UNICODE_STRING = auto() 104 105 # types 106 BIT = auto() 107 BOOLEAN = auto() 108 TINYINT = auto() 109 UTINYINT = auto() 110 SMALLINT = auto() 111 USMALLINT = auto() 112 MEDIUMINT = auto() 113 UMEDIUMINT = auto() 114 INT = auto() 115 UINT = auto() 116 BIGINT = auto() 117 UBIGINT = auto() 118 INT128 = auto() 119 UINT128 = auto() 120 INT256 = auto() 121 UINT256 = auto() 122 FLOAT = auto() 123 DOUBLE = auto() 124 DECIMAL = auto() 125 UDECIMAL = auto() 126 BIGDECIMAL = auto() 127 CHAR = auto() 128 NCHAR = auto() 129 VARCHAR = auto() 130 NVARCHAR = auto() 131 BPCHAR = auto() 132 TEXT = auto() 133 MEDIUMTEXT = auto() 134 LONGTEXT = auto() 135 MEDIUMBLOB = auto() 136 LONGBLOB = auto() 137 TINYBLOB = auto() 138 TINYTEXT = auto() 139 NAME = auto() 140 BINARY = auto() 141 VARBINARY = auto() 142 JSON = auto() 143 JSONB = auto() 144 TIME = auto() 145 TIMETZ = auto() 146 TIMESTAMP = auto() 147 TIMESTAMPTZ = auto() 148 TIMESTAMPLTZ = auto() 149 TIMESTAMP_S = auto() 150 TIMESTAMP_MS = auto() 151 TIMESTAMP_NS = auto() 152 DATETIME = auto() 153 DATETIME64 = auto() 154 DATE = auto() 155 DATE32 = auto() 156 INT4RANGE = auto() 157 INT4MULTIRANGE = auto() 158 INT8RANGE = auto() 159 INT8MULTIRANGE = auto() 160 NUMRANGE = auto() 161 NUMMULTIRANGE = auto() 162 TSRANGE = auto() 163 TSMULTIRANGE = auto() 164 TSTZRANGE = auto() 165 TSTZMULTIRANGE = auto() 166 DATERANGE = auto() 167 DATEMULTIRANGE = auto() 168 UUID = auto() 169 GEOGRAPHY = auto() 170 NULLABLE = auto() 171 GEOMETRY = auto() 172 HLLSKETCH = auto() 173 HSTORE = auto() 174 SUPER = auto() 175 SERIAL = auto() 176 SMALLSERIAL = auto() 177 BIGSERIAL = auto() 178 XML = auto() 179 YEAR = auto() 180 UNIQUEIDENTIFIER = auto() 181 USERDEFINED = auto() 182 MONEY = auto() 183 SMALLMONEY = auto() 184 ROWVERSION = auto() 185 IMAGE = auto() 186 VARIANT = auto() 187 OBJECT = auto() 188 INET = auto() 189 IPADDRESS = auto() 190 IPPREFIX = auto() 191 IPV4 = auto() 192 IPV6 = auto() 193 ENUM = auto() 194 ENUM8 = auto() 195 ENUM16 = auto() 196 FIXEDSTRING = auto() 197 LOWCARDINALITY = auto() 198 NESTED = auto() 199 AGGREGATEFUNCTION = auto() 200 SIMPLEAGGREGATEFUNCTION = auto() 201 UNKNOWN = auto() 202 203 # keywords 204 ALIAS = auto() 205 ALTER = auto() 206 ALWAYS = auto() 207 ALL = auto() 208 ANTI = auto() 209 ANY = auto() 210 APPLY = auto() 211 ARRAY = auto() 212 ASC = auto() 213 ASOF = auto() 214 AUTO_INCREMENT = auto() 215 BEGIN = auto() 216 BETWEEN = auto() 217 CACHE = auto() 218 CASE = auto() 219 CHARACTER_SET = auto() 220 CLUSTER_BY = auto() 221 COLLATE = auto() 222 COMMAND = auto() 223 COMMENT = auto() 224 COMMIT = auto() 225 CONNECT_BY = auto() 226 CONSTRAINT = auto() 227 CREATE = auto() 228 CROSS = auto() 229 CUBE = auto() 230 CURRENT_DATE = auto() 231 CURRENT_DATETIME = auto() 232 CURRENT_TIME = auto() 233 CURRENT_TIMESTAMP = auto() 234 CURRENT_USER = auto() 235 DEFAULT = auto() 236 DELETE = auto() 237 DESC = auto() 238 DESCRIBE = auto() 239 DICTIONARY = auto() 240 DISTINCT = auto() 241 DISTRIBUTE_BY = auto() 242 DIV = auto() 243 DROP = auto() 244 ELSE = auto() 245 END = auto() 246 ESCAPE = auto() 247 EXCEPT = auto() 248 EXECUTE = auto() 249 EXISTS = auto() 250 FALSE = auto() 251 FETCH = auto() 252 FILTER = auto() 253 FINAL = auto() 254 FIRST = auto() 255 FOR = auto() 256 FORCE = auto() 257 FOREIGN_KEY = auto() 258 FORMAT = auto() 259 FROM = auto() 260 FULL = auto() 261 FUNCTION = auto() 262 GLOB = auto() 263 GLOBAL = auto() 264 GROUP_BY = auto() 265 GROUPING_SETS = auto() 266 HAVING = auto() 267 HINT = auto() 268 IGNORE = auto() 269 ILIKE = auto() 270 ILIKE_ANY = auto() 271 IN = auto() 272 INDEX = auto() 273 INNER = auto() 274 INSERT = auto() 275 INTERSECT = auto() 276 INTERVAL = auto() 277 INTO = auto() 278 INTRODUCER = auto() 279 IRLIKE = auto() 280 IS = auto() 281 ISNULL = auto() 282 JOIN = auto() 283 JOIN_MARKER = auto() 284 KEEP = auto() 285 KILL = auto() 286 LANGUAGE = auto() 287 LATERAL = auto() 288 LEFT = auto() 289 LIKE = auto() 290 LIKE_ANY = auto() 291 LIMIT = auto() 292 LOAD = auto() 293 LOCK = auto() 294 MAP = auto() 295 MATCH_CONDITION = auto() 296 MATCH_RECOGNIZE = auto() 297 MEMBER_OF = auto() 298 MERGE = auto() 299 MOD = auto() 300 MODEL = auto() 301 NATURAL = auto() 302 NEXT = auto() 303 NOTNULL = auto() 304 NULL = auto() 305 OBJECT_IDENTIFIER = auto() 306 OFFSET = auto() 307 ON = auto() 308 ONLY = auto() 309 OPERATOR = auto() 310 ORDER_BY = auto() 311 ORDER_SIBLINGS_BY = auto() 312 ORDERED = auto() 313 ORDINALITY = auto() 314 OUTER = auto() 315 OVER = auto() 316 OVERLAPS = auto() 317 OVERWRITE = auto() 318 PARTITION = auto() 319 PARTITION_BY = auto() 320 PERCENT = auto() 321 PIVOT = auto() 322 PLACEHOLDER = auto() 323 POSITIONAL = auto() 324 PRAGMA = auto() 325 PREWHERE = auto() 326 PRIMARY_KEY = auto() 327 PROCEDURE = auto() 328 PROPERTIES = auto() 329 PSEUDO_TYPE = auto() 330 QUALIFY = auto() 331 QUOTE = auto() 332 RANGE = auto() 333 RECURSIVE = auto() 334 REFRESH = auto() 335 REPLACE = auto() 336 RETURNING = auto() 337 REFERENCES = auto() 338 RIGHT = auto() 339 RLIKE = auto() 340 ROLLBACK = auto() 341 ROLLUP = auto() 342 ROW = auto() 343 ROWS = auto() 344 SELECT = auto() 345 SEMI = auto() 346 SEPARATOR = auto() 347 SEQUENCE = auto() 348 SERDE_PROPERTIES = auto() 349 SET = auto() 350 SETTINGS = auto() 351 SHOW = auto() 352 SIMILAR_TO = auto() 353 SOME = auto() 354 SORT_BY = auto() 355 START_WITH = auto() 356 STORAGE_INTEGRATION = auto() 357 STRUCT = auto() 358 TABLE_SAMPLE = auto() 359 TEMPORARY = auto() 360 TOP = auto() 361 THEN = auto() 362 TRUE = auto() 363 TRUNCATE = auto() 364 UNCACHE = auto() 365 UNION = auto() 366 UNNEST = auto() 367 UNPIVOT = auto() 368 UPDATE = auto() 369 USE = auto() 370 USING = auto() 371 VALUES = auto() 372 VIEW = auto() 373 VOLATILE = auto() 374 WHEN = auto() 375 WHERE = auto() 376 WINDOW = auto() 377 WITH = auto() 378 UNIQUE = auto() 379 VERSION_SNAPSHOT = auto() 380 TIMESTAMP_SNAPSHOT = auto() 381 OPTION = auto()
An enumeration.
L_PAREN =
<TokenType.L_PAREN: 'L_PAREN'>
R_PAREN =
<TokenType.R_PAREN: 'R_PAREN'>
L_BRACKET =
<TokenType.L_BRACKET: 'L_BRACKET'>
R_BRACKET =
<TokenType.R_BRACKET: 'R_BRACKET'>
L_BRACE =
<TokenType.L_BRACE: 'L_BRACE'>
R_BRACE =
<TokenType.R_BRACE: 'R_BRACE'>
COMMA =
<TokenType.COMMA: 'COMMA'>
DOT =
<TokenType.DOT: 'DOT'>
DASH =
<TokenType.DASH: 'DASH'>
PLUS =
<TokenType.PLUS: 'PLUS'>
COLON =
<TokenType.COLON: 'COLON'>
DCOLON =
<TokenType.DCOLON: 'DCOLON'>
DQMARK =
<TokenType.DQMARK: 'DQMARK'>
SEMICOLON =
<TokenType.SEMICOLON: 'SEMICOLON'>
STAR =
<TokenType.STAR: 'STAR'>
BACKSLASH =
<TokenType.BACKSLASH: 'BACKSLASH'>
SLASH =
<TokenType.SLASH: 'SLASH'>
LT =
<TokenType.LT: 'LT'>
LTE =
<TokenType.LTE: 'LTE'>
GT =
<TokenType.GT: 'GT'>
GTE =
<TokenType.GTE: 'GTE'>
NOT =
<TokenType.NOT: 'NOT'>
EQ =
<TokenType.EQ: 'EQ'>
NEQ =
<TokenType.NEQ: 'NEQ'>
NULLSAFE_EQ =
<TokenType.NULLSAFE_EQ: 'NULLSAFE_EQ'>
COLON_EQ =
<TokenType.COLON_EQ: 'COLON_EQ'>
AND =
<TokenType.AND: 'AND'>
OR =
<TokenType.OR: 'OR'>
AMP =
<TokenType.AMP: 'AMP'>
DPIPE =
<TokenType.DPIPE: 'DPIPE'>
PIPE =
<TokenType.PIPE: 'PIPE'>
PIPE_SLASH =
<TokenType.PIPE_SLASH: 'PIPE_SLASH'>
DPIPE_SLASH =
<TokenType.DPIPE_SLASH: 'DPIPE_SLASH'>
CARET =
<TokenType.CARET: 'CARET'>
TILDA =
<TokenType.TILDA: 'TILDA'>
ARROW =
<TokenType.ARROW: 'ARROW'>
DARROW =
<TokenType.DARROW: 'DARROW'>
FARROW =
<TokenType.FARROW: 'FARROW'>
HASH =
<TokenType.HASH: 'HASH'>
HASH_ARROW =
<TokenType.HASH_ARROW: 'HASH_ARROW'>
DHASH_ARROW =
<TokenType.DHASH_ARROW: 'DHASH_ARROW'>
LR_ARROW =
<TokenType.LR_ARROW: 'LR_ARROW'>
DAT =
<TokenType.DAT: 'DAT'>
LT_AT =
<TokenType.LT_AT: 'LT_AT'>
AT_GT =
<TokenType.AT_GT: 'AT_GT'>
DOLLAR =
<TokenType.DOLLAR: 'DOLLAR'>
PARAMETER =
<TokenType.PARAMETER: 'PARAMETER'>
SESSION_PARAMETER =
<TokenType.SESSION_PARAMETER: 'SESSION_PARAMETER'>
DAMP =
<TokenType.DAMP: 'DAMP'>
XOR =
<TokenType.XOR: 'XOR'>
DSTAR =
<TokenType.DSTAR: 'DSTAR'>
BLOCK_START =
<TokenType.BLOCK_START: 'BLOCK_START'>
BLOCK_END =
<TokenType.BLOCK_END: 'BLOCK_END'>
SPACE =
<TokenType.SPACE: 'SPACE'>
BREAK =
<TokenType.BREAK: 'BREAK'>
STRING =
<TokenType.STRING: 'STRING'>
NUMBER =
<TokenType.NUMBER: 'NUMBER'>
IDENTIFIER =
<TokenType.IDENTIFIER: 'IDENTIFIER'>
DATABASE =
<TokenType.DATABASE: 'DATABASE'>
COLUMN =
<TokenType.COLUMN: 'COLUMN'>
COLUMN_DEF =
<TokenType.COLUMN_DEF: 'COLUMN_DEF'>
SCHEMA =
<TokenType.SCHEMA: 'SCHEMA'>
TABLE =
<TokenType.TABLE: 'TABLE'>
VAR =
<TokenType.VAR: 'VAR'>
BIT_STRING =
<TokenType.BIT_STRING: 'BIT_STRING'>
HEX_STRING =
<TokenType.HEX_STRING: 'HEX_STRING'>
BYTE_STRING =
<TokenType.BYTE_STRING: 'BYTE_STRING'>
NATIONAL_STRING =
<TokenType.NATIONAL_STRING: 'NATIONAL_STRING'>
RAW_STRING =
<TokenType.RAW_STRING: 'RAW_STRING'>
HEREDOC_STRING =
<TokenType.HEREDOC_STRING: 'HEREDOC_STRING'>
UNICODE_STRING =
<TokenType.UNICODE_STRING: 'UNICODE_STRING'>
BIT =
<TokenType.BIT: 'BIT'>
BOOLEAN =
<TokenType.BOOLEAN: 'BOOLEAN'>
TINYINT =
<TokenType.TINYINT: 'TINYINT'>
UTINYINT =
<TokenType.UTINYINT: 'UTINYINT'>
SMALLINT =
<TokenType.SMALLINT: 'SMALLINT'>
USMALLINT =
<TokenType.USMALLINT: 'USMALLINT'>
MEDIUMINT =
<TokenType.MEDIUMINT: 'MEDIUMINT'>
UMEDIUMINT =
<TokenType.UMEDIUMINT: 'UMEDIUMINT'>
INT =
<TokenType.INT: 'INT'>
UINT =
<TokenType.UINT: 'UINT'>
BIGINT =
<TokenType.BIGINT: 'BIGINT'>
UBIGINT =
<TokenType.UBIGINT: 'UBIGINT'>
INT128 =
<TokenType.INT128: 'INT128'>
UINT128 =
<TokenType.UINT128: 'UINT128'>
INT256 =
<TokenType.INT256: 'INT256'>
UINT256 =
<TokenType.UINT256: 'UINT256'>
FLOAT =
<TokenType.FLOAT: 'FLOAT'>
DOUBLE =
<TokenType.DOUBLE: 'DOUBLE'>
DECIMAL =
<TokenType.DECIMAL: 'DECIMAL'>
UDECIMAL =
<TokenType.UDECIMAL: 'UDECIMAL'>
BIGDECIMAL =
<TokenType.BIGDECIMAL: 'BIGDECIMAL'>
CHAR =
<TokenType.CHAR: 'CHAR'>
NCHAR =
<TokenType.NCHAR: 'NCHAR'>
VARCHAR =
<TokenType.VARCHAR: 'VARCHAR'>
NVARCHAR =
<TokenType.NVARCHAR: 'NVARCHAR'>
BPCHAR =
<TokenType.BPCHAR: 'BPCHAR'>
TEXT =
<TokenType.TEXT: 'TEXT'>
MEDIUMTEXT =
<TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>
LONGTEXT =
<TokenType.LONGTEXT: 'LONGTEXT'>
MEDIUMBLOB =
<TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>
LONGBLOB =
<TokenType.LONGBLOB: 'LONGBLOB'>
TINYBLOB =
<TokenType.TINYBLOB: 'TINYBLOB'>
TINYTEXT =
<TokenType.TINYTEXT: 'TINYTEXT'>
NAME =
<TokenType.NAME: 'NAME'>
BINARY =
<TokenType.BINARY: 'BINARY'>
VARBINARY =
<TokenType.VARBINARY: 'VARBINARY'>
JSON =
<TokenType.JSON: 'JSON'>
JSONB =
<TokenType.JSONB: 'JSONB'>
TIME =
<TokenType.TIME: 'TIME'>
TIMETZ =
<TokenType.TIMETZ: 'TIMETZ'>
TIMESTAMP =
<TokenType.TIMESTAMP: 'TIMESTAMP'>
TIMESTAMPTZ =
<TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>
TIMESTAMPLTZ =
<TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>
TIMESTAMP_S =
<TokenType.TIMESTAMP_S: 'TIMESTAMP_S'>
TIMESTAMP_MS =
<TokenType.TIMESTAMP_MS: 'TIMESTAMP_MS'>
TIMESTAMP_NS =
<TokenType.TIMESTAMP_NS: 'TIMESTAMP_NS'>
DATETIME =
<TokenType.DATETIME: 'DATETIME'>
DATETIME64 =
<TokenType.DATETIME64: 'DATETIME64'>
DATE =
<TokenType.DATE: 'DATE'>
DATE32 =
<TokenType.DATE32: 'DATE32'>
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'>
UUID =
<TokenType.UUID: 'UUID'>
GEOGRAPHY =
<TokenType.GEOGRAPHY: 'GEOGRAPHY'>
NULLABLE =
<TokenType.NULLABLE: 'NULLABLE'>
GEOMETRY =
<TokenType.GEOMETRY: 'GEOMETRY'>
HLLSKETCH =
<TokenType.HLLSKETCH: 'HLLSKETCH'>
HSTORE =
<TokenType.HSTORE: 'HSTORE'>
SUPER =
<TokenType.SUPER: 'SUPER'>
SERIAL =
<TokenType.SERIAL: 'SERIAL'>
SMALLSERIAL =
<TokenType.SMALLSERIAL: 'SMALLSERIAL'>
BIGSERIAL =
<TokenType.BIGSERIAL: 'BIGSERIAL'>
XML =
<TokenType.XML: 'XML'>
YEAR =
<TokenType.YEAR: 'YEAR'>
UNIQUEIDENTIFIER =
<TokenType.UNIQUEIDENTIFIER: 'UNIQUEIDENTIFIER'>
USERDEFINED =
<TokenType.USERDEFINED: 'USERDEFINED'>
MONEY =
<TokenType.MONEY: 'MONEY'>
SMALLMONEY =
<TokenType.SMALLMONEY: 'SMALLMONEY'>
ROWVERSION =
<TokenType.ROWVERSION: 'ROWVERSION'>
IMAGE =
<TokenType.IMAGE: 'IMAGE'>
VARIANT =
<TokenType.VARIANT: 'VARIANT'>
OBJECT =
<TokenType.OBJECT: 'OBJECT'>
INET =
<TokenType.INET: 'INET'>
IPADDRESS =
<TokenType.IPADDRESS: 'IPADDRESS'>
IPPREFIX =
<TokenType.IPPREFIX: 'IPPREFIX'>
IPV4 =
<TokenType.IPV4: 'IPV4'>
IPV6 =
<TokenType.IPV6: 'IPV6'>
ENUM =
<TokenType.ENUM: 'ENUM'>
ENUM8 =
<TokenType.ENUM8: 'ENUM8'>
ENUM16 =
<TokenType.ENUM16: 'ENUM16'>
FIXEDSTRING =
<TokenType.FIXEDSTRING: 'FIXEDSTRING'>
LOWCARDINALITY =
<TokenType.LOWCARDINALITY: 'LOWCARDINALITY'>
NESTED =
<TokenType.NESTED: 'NESTED'>
AGGREGATEFUNCTION =
<TokenType.AGGREGATEFUNCTION: 'AGGREGATEFUNCTION'>
SIMPLEAGGREGATEFUNCTION =
<TokenType.SIMPLEAGGREGATEFUNCTION: 'SIMPLEAGGREGATEFUNCTION'>
UNKNOWN =
<TokenType.UNKNOWN: 'UNKNOWN'>
ALIAS =
<TokenType.ALIAS: 'ALIAS'>
ALTER =
<TokenType.ALTER: 'ALTER'>
ALWAYS =
<TokenType.ALWAYS: 'ALWAYS'>
ALL =
<TokenType.ALL: 'ALL'>
ANTI =
<TokenType.ANTI: 'ANTI'>
ANY =
<TokenType.ANY: 'ANY'>
APPLY =
<TokenType.APPLY: 'APPLY'>
ARRAY =
<TokenType.ARRAY: 'ARRAY'>
ASC =
<TokenType.ASC: 'ASC'>
ASOF =
<TokenType.ASOF: 'ASOF'>
AUTO_INCREMENT =
<TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>
BEGIN =
<TokenType.BEGIN: 'BEGIN'>
BETWEEN =
<TokenType.BETWEEN: 'BETWEEN'>
CACHE =
<TokenType.CACHE: 'CACHE'>
CASE =
<TokenType.CASE: 'CASE'>
CHARACTER_SET =
<TokenType.CHARACTER_SET: 'CHARACTER_SET'>
CLUSTER_BY =
<TokenType.CLUSTER_BY: 'CLUSTER_BY'>
COLLATE =
<TokenType.COLLATE: 'COLLATE'>
COMMAND =
<TokenType.COMMAND: 'COMMAND'>
COMMENT =
<TokenType.COMMENT: 'COMMENT'>
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_DATETIME =
<TokenType.CURRENT_DATETIME: 'CURRENT_DATETIME'>
CURRENT_TIME =
<TokenType.CURRENT_TIME: 'CURRENT_TIME'>
CURRENT_TIMESTAMP =
<TokenType.CURRENT_TIMESTAMP: 'CURRENT_TIMESTAMP'>
CURRENT_USER =
<TokenType.CURRENT_USER: 'CURRENT_USER'>
DEFAULT =
<TokenType.DEFAULT: 'DEFAULT'>
DELETE =
<TokenType.DELETE: 'DELETE'>
DESC =
<TokenType.DESC: 'DESC'>
DESCRIBE =
<TokenType.DESCRIBE: 'DESCRIBE'>
DICTIONARY =
<TokenType.DICTIONARY: 'DICTIONARY'>
DISTINCT =
<TokenType.DISTINCT: 'DISTINCT'>
DISTRIBUTE_BY =
<TokenType.DISTRIBUTE_BY: 'DISTRIBUTE_BY'>
DIV =
<TokenType.DIV: 'DIV'>
DROP =
<TokenType.DROP: 'DROP'>
ELSE =
<TokenType.ELSE: 'ELSE'>
END =
<TokenType.END: 'END'>
ESCAPE =
<TokenType.ESCAPE: 'ESCAPE'>
EXCEPT =
<TokenType.EXCEPT: 'EXCEPT'>
EXECUTE =
<TokenType.EXECUTE: 'EXECUTE'>
EXISTS =
<TokenType.EXISTS: 'EXISTS'>
FALSE =
<TokenType.FALSE: 'FALSE'>
FETCH =
<TokenType.FETCH: 'FETCH'>
FILTER =
<TokenType.FILTER: 'FILTER'>
FINAL =
<TokenType.FINAL: 'FINAL'>
FIRST =
<TokenType.FIRST: 'FIRST'>
FOR =
<TokenType.FOR: 'FOR'>
FORCE =
<TokenType.FORCE: 'FORCE'>
FOREIGN_KEY =
<TokenType.FOREIGN_KEY: 'FOREIGN_KEY'>
FORMAT =
<TokenType.FORMAT: 'FORMAT'>
FROM =
<TokenType.FROM: 'FROM'>
FULL =
<TokenType.FULL: 'FULL'>
FUNCTION =
<TokenType.FUNCTION: 'FUNCTION'>
GLOB =
<TokenType.GLOB: 'GLOB'>
GLOBAL =
<TokenType.GLOBAL: 'GLOBAL'>
GROUP_BY =
<TokenType.GROUP_BY: 'GROUP_BY'>
GROUPING_SETS =
<TokenType.GROUPING_SETS: 'GROUPING_SETS'>
HAVING =
<TokenType.HAVING: 'HAVING'>
HINT =
<TokenType.HINT: 'HINT'>
IGNORE =
<TokenType.IGNORE: 'IGNORE'>
ILIKE =
<TokenType.ILIKE: 'ILIKE'>
ILIKE_ANY =
<TokenType.ILIKE_ANY: 'ILIKE_ANY'>
IN =
<TokenType.IN: 'IN'>
INDEX =
<TokenType.INDEX: 'INDEX'>
INNER =
<TokenType.INNER: 'INNER'>
INSERT =
<TokenType.INSERT: 'INSERT'>
INTERSECT =
<TokenType.INTERSECT: 'INTERSECT'>
INTERVAL =
<TokenType.INTERVAL: 'INTERVAL'>
INTO =
<TokenType.INTO: 'INTO'>
INTRODUCER =
<TokenType.INTRODUCER: 'INTRODUCER'>
IRLIKE =
<TokenType.IRLIKE: 'IRLIKE'>
IS =
<TokenType.IS: 'IS'>
ISNULL =
<TokenType.ISNULL: 'ISNULL'>
JOIN =
<TokenType.JOIN: 'JOIN'>
JOIN_MARKER =
<TokenType.JOIN_MARKER: 'JOIN_MARKER'>
KEEP =
<TokenType.KEEP: 'KEEP'>
KILL =
<TokenType.KILL: 'KILL'>
LANGUAGE =
<TokenType.LANGUAGE: 'LANGUAGE'>
LATERAL =
<TokenType.LATERAL: 'LATERAL'>
LEFT =
<TokenType.LEFT: 'LEFT'>
LIKE =
<TokenType.LIKE: 'LIKE'>
LIKE_ANY =
<TokenType.LIKE_ANY: 'LIKE_ANY'>
LIMIT =
<TokenType.LIMIT: 'LIMIT'>
LOAD =
<TokenType.LOAD: 'LOAD'>
LOCK =
<TokenType.LOCK: 'LOCK'>
MAP =
<TokenType.MAP: 'MAP'>
MATCH_CONDITION =
<TokenType.MATCH_CONDITION: 'MATCH_CONDITION'>
MATCH_RECOGNIZE =
<TokenType.MATCH_RECOGNIZE: 'MATCH_RECOGNIZE'>
MEMBER_OF =
<TokenType.MEMBER_OF: 'MEMBER_OF'>
MERGE =
<TokenType.MERGE: 'MERGE'>
MOD =
<TokenType.MOD: 'MOD'>
MODEL =
<TokenType.MODEL: 'MODEL'>
NATURAL =
<TokenType.NATURAL: 'NATURAL'>
NEXT =
<TokenType.NEXT: 'NEXT'>
NOTNULL =
<TokenType.NOTNULL: 'NOTNULL'>
NULL =
<TokenType.NULL: 'NULL'>
OBJECT_IDENTIFIER =
<TokenType.OBJECT_IDENTIFIER: 'OBJECT_IDENTIFIER'>
OFFSET =
<TokenType.OFFSET: 'OFFSET'>
ON =
<TokenType.ON: 'ON'>
ONLY =
<TokenType.ONLY: 'ONLY'>
OPERATOR =
<TokenType.OPERATOR: 'OPERATOR'>
ORDER_BY =
<TokenType.ORDER_BY: 'ORDER_BY'>
ORDER_SIBLINGS_BY =
<TokenType.ORDER_SIBLINGS_BY: 'ORDER_SIBLINGS_BY'>
ORDERED =
<TokenType.ORDERED: 'ORDERED'>
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'>
PERCENT =
<TokenType.PERCENT: 'PERCENT'>
PIVOT =
<TokenType.PIVOT: 'PIVOT'>
PLACEHOLDER =
<TokenType.PLACEHOLDER: 'PLACEHOLDER'>
POSITIONAL =
<TokenType.POSITIONAL: 'POSITIONAL'>
PRAGMA =
<TokenType.PRAGMA: 'PRAGMA'>
PREWHERE =
<TokenType.PREWHERE: 'PREWHERE'>
PRIMARY_KEY =
<TokenType.PRIMARY_KEY: 'PRIMARY_KEY'>
PROCEDURE =
<TokenType.PROCEDURE: 'PROCEDURE'>
PROPERTIES =
<TokenType.PROPERTIES: 'PROPERTIES'>
PSEUDO_TYPE =
<TokenType.PSEUDO_TYPE: 'PSEUDO_TYPE'>
QUALIFY =
<TokenType.QUALIFY: 'QUALIFY'>
QUOTE =
<TokenType.QUOTE: 'QUOTE'>
RANGE =
<TokenType.RANGE: 'RANGE'>
RECURSIVE =
<TokenType.RECURSIVE: 'RECURSIVE'>
REFRESH =
<TokenType.REFRESH: 'REFRESH'>
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'>
SELECT =
<TokenType.SELECT: 'SELECT'>
SEMI =
<TokenType.SEMI: 'SEMI'>
SEPARATOR =
<TokenType.SEPARATOR: 'SEPARATOR'>
SEQUENCE =
<TokenType.SEQUENCE: 'SEQUENCE'>
SERDE_PROPERTIES =
<TokenType.SERDE_PROPERTIES: 'SERDE_PROPERTIES'>
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'>
STORAGE_INTEGRATION =
<TokenType.STORAGE_INTEGRATION: 'STORAGE_INTEGRATION'>
STRUCT =
<TokenType.STRUCT: 'STRUCT'>
TABLE_SAMPLE =
<TokenType.TABLE_SAMPLE: 'TABLE_SAMPLE'>
TEMPORARY =
<TokenType.TEMPORARY: 'TEMPORARY'>
TOP =
<TokenType.TOP: 'TOP'>
THEN =
<TokenType.THEN: 'THEN'>
TRUE =
<TokenType.TRUE: 'TRUE'>
TRUNCATE =
<TokenType.TRUNCATE: 'TRUNCATE'>
UNCACHE =
<TokenType.UNCACHE: 'UNCACHE'>
UNION =
<TokenType.UNION: 'UNION'>
UNNEST =
<TokenType.UNNEST: 'UNNEST'>
UNPIVOT =
<TokenType.UNPIVOT: 'UNPIVOT'>
UPDATE =
<TokenType.UPDATE: 'UPDATE'>
USE =
<TokenType.USE: 'USE'>
USING =
<TokenType.USING: 'USING'>
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'>
UNIQUE =
<TokenType.UNIQUE: 'UNIQUE'>
VERSION_SNAPSHOT =
<TokenType.VERSION_SNAPSHOT: 'VERSION_SNAPSHOT'>
TIMESTAMP_SNAPSHOT =
<TokenType.TIMESTAMP_SNAPSHOT: 'TIMESTAMP_SNAPSHOT'>
OPTION =
<TokenType.OPTION: 'OPTION'>
Inherited Members
- enum.Enum
- name
- value
class
Token:
388class Token: 389 __slots__ = ("token_type", "text", "line", "col", "start", "end", "comments") 390 391 @classmethod 392 def number(cls, number: int) -> Token: 393 """Returns a NUMBER token with `number` as its text.""" 394 return cls(TokenType.NUMBER, str(number)) 395 396 @classmethod 397 def string(cls, string: str) -> Token: 398 """Returns a STRING token with `string` as its text.""" 399 return cls(TokenType.STRING, string) 400 401 @classmethod 402 def identifier(cls, identifier: str) -> Token: 403 """Returns an IDENTIFIER token with `identifier` as its text.""" 404 return cls(TokenType.IDENTIFIER, identifier) 405 406 @classmethod 407 def var(cls, var: str) -> Token: 408 """Returns an VAR token with `var` as its text.""" 409 return cls(TokenType.VAR, var) 410 411 def __init__( 412 self, 413 token_type: TokenType, 414 text: str, 415 line: int = 1, 416 col: int = 1, 417 start: int = 0, 418 end: int = 0, 419 comments: t.Optional[t.List[str]] = None, 420 ) -> None: 421 """Token initializer. 422 423 Args: 424 token_type: The TokenType Enum. 425 text: The text of the token. 426 line: The line that the token ends on. 427 col: The column that the token ends on. 428 start: The start index of the token. 429 end: The ending index of the token. 430 comments: The comments to attach to the token. 431 """ 432 self.token_type = token_type 433 self.text = text 434 self.line = line 435 self.col = col 436 self.start = start 437 self.end = end 438 self.comments = [] if comments is None else comments 439 440 def __repr__(self) -> str: 441 attributes = ", ".join(f"{k}: {getattr(self, k)}" for k in self.__slots__) 442 return f"<Token {attributes}>"
Token( token_type: TokenType, text: str, line: int = 1, col: int = 1, start: int = 0, end: int = 0, comments: Optional[List[str]] = None)
411 def __init__( 412 self, 413 token_type: TokenType, 414 text: str, 415 line: int = 1, 416 col: int = 1, 417 start: int = 0, 418 end: int = 0, 419 comments: t.Optional[t.List[str]] = None, 420 ) -> None: 421 """Token initializer. 422 423 Args: 424 token_type: The TokenType Enum. 425 text: The text of the token. 426 line: The line that the token ends on. 427 col: The column that the token ends on. 428 start: The start index of the token. 429 end: The ending index of the token. 430 comments: The comments to attach to the token. 431 """ 432 self.token_type = token_type 433 self.text = text 434 self.line = line 435 self.col = col 436 self.start = start 437 self.end = end 438 self.comments = [] if comments is None else comments
Token initializer.
Arguments:
- token_type: The TokenType Enum.
- text: The text of the token.
- line: The line that the token ends on.
- col: The column that the token ends on.
- start: The start index of the token.
- end: The ending index of the token.
- comments: The comments to attach to the token.
391 @classmethod 392 def number(cls, number: int) -> Token: 393 """Returns a NUMBER token with `number` as its text.""" 394 return cls(TokenType.NUMBER, str(number))
Returns a NUMBER token with number
as its text.
396 @classmethod 397 def string(cls, string: str) -> Token: 398 """Returns a STRING token with `string` as its text.""" 399 return cls(TokenType.STRING, string)
Returns a STRING token with string
as its text.
401 @classmethod 402 def identifier(cls, identifier: str) -> Token: 403 """Returns an IDENTIFIER token with `identifier` as its text.""" 404 return cls(TokenType.IDENTIFIER, identifier)
Returns an IDENTIFIER token with identifier
as its text.
class
Tokenizer:
543class Tokenizer(metaclass=_Tokenizer): 544 SINGLE_TOKENS = { 545 "(": TokenType.L_PAREN, 546 ")": TokenType.R_PAREN, 547 "[": TokenType.L_BRACKET, 548 "]": TokenType.R_BRACKET, 549 "{": TokenType.L_BRACE, 550 "}": TokenType.R_BRACE, 551 "&": TokenType.AMP, 552 "^": TokenType.CARET, 553 ":": TokenType.COLON, 554 ",": TokenType.COMMA, 555 ".": TokenType.DOT, 556 "-": TokenType.DASH, 557 "=": TokenType.EQ, 558 ">": TokenType.GT, 559 "<": TokenType.LT, 560 "%": TokenType.MOD, 561 "!": TokenType.NOT, 562 "|": TokenType.PIPE, 563 "+": TokenType.PLUS, 564 ";": TokenType.SEMICOLON, 565 "/": TokenType.SLASH, 566 "\\": TokenType.BACKSLASH, 567 "*": TokenType.STAR, 568 "~": TokenType.TILDA, 569 "?": TokenType.PLACEHOLDER, 570 "@": TokenType.PARAMETER, 571 # Used for breaking a var like x'y' but nothing else the token type doesn't matter 572 "'": TokenType.QUOTE, 573 "`": TokenType.IDENTIFIER, 574 '"': TokenType.IDENTIFIER, 575 "#": TokenType.HASH, 576 } 577 578 BIT_STRINGS: t.List[str | t.Tuple[str, str]] = [] 579 BYTE_STRINGS: t.List[str | t.Tuple[str, str]] = [] 580 HEX_STRINGS: t.List[str | t.Tuple[str, str]] = [] 581 RAW_STRINGS: t.List[str | t.Tuple[str, str]] = [] 582 HEREDOC_STRINGS: t.List[str | t.Tuple[str, str]] = [] 583 UNICODE_STRINGS: t.List[str | t.Tuple[str, str]] = [] 584 IDENTIFIERS: t.List[str | t.Tuple[str, str]] = ['"'] 585 IDENTIFIER_ESCAPES = ['"'] 586 QUOTES: t.List[t.Tuple[str, str] | str] = ["'"] 587 STRING_ESCAPES = ["'"] 588 VAR_SINGLE_TOKENS: t.Set[str] = set() 589 590 # Whether the heredoc tags follow the same lexical rules as unquoted identifiers 591 HEREDOC_TAG_IS_IDENTIFIER = False 592 593 # Token that we'll generate as a fallback if the heredoc prefix doesn't correspond to a heredoc 594 HEREDOC_STRING_ALTERNATIVE = TokenType.VAR 595 596 # Autofilled 597 _COMMENTS: t.Dict[str, str] = {} 598 _FORMAT_STRINGS: t.Dict[str, t.Tuple[str, TokenType]] = {} 599 _IDENTIFIERS: t.Dict[str, str] = {} 600 _IDENTIFIER_ESCAPES: t.Set[str] = set() 601 _QUOTES: t.Dict[str, str] = {} 602 _STRING_ESCAPES: t.Set[str] = set() 603 _KEYWORD_TRIE: t.Dict = {} 604 _RS_TOKENIZER: t.Optional[t.Any] = None 605 606 KEYWORDS: t.Dict[str, TokenType] = { 607 **{f"{{%{postfix}": TokenType.BLOCK_START for postfix in ("", "+", "-")}, 608 **{f"{prefix}%}}": TokenType.BLOCK_END for prefix in ("", "+", "-")}, 609 **{f"{{{{{postfix}": TokenType.BLOCK_START for postfix in ("+", "-")}, 610 **{f"{prefix}}}}}": TokenType.BLOCK_END for prefix in ("+", "-")}, 611 "/*+": TokenType.HINT, 612 "==": TokenType.EQ, 613 "::": TokenType.DCOLON, 614 "||": TokenType.DPIPE, 615 ">=": TokenType.GTE, 616 "<=": TokenType.LTE, 617 "<>": TokenType.NEQ, 618 "!=": TokenType.NEQ, 619 ":=": TokenType.COLON_EQ, 620 "<=>": TokenType.NULLSAFE_EQ, 621 "->": TokenType.ARROW, 622 "->>": TokenType.DARROW, 623 "=>": TokenType.FARROW, 624 "#>": TokenType.HASH_ARROW, 625 "#>>": TokenType.DHASH_ARROW, 626 "<->": TokenType.LR_ARROW, 627 "&&": TokenType.DAMP, 628 "??": TokenType.DQMARK, 629 "ALL": TokenType.ALL, 630 "ALWAYS": TokenType.ALWAYS, 631 "AND": TokenType.AND, 632 "ANTI": TokenType.ANTI, 633 "ANY": TokenType.ANY, 634 "ASC": TokenType.ASC, 635 "AS": TokenType.ALIAS, 636 "ASOF": TokenType.ASOF, 637 "AUTOINCREMENT": TokenType.AUTO_INCREMENT, 638 "AUTO_INCREMENT": TokenType.AUTO_INCREMENT, 639 "BEGIN": TokenType.BEGIN, 640 "BETWEEN": TokenType.BETWEEN, 641 "CACHE": TokenType.CACHE, 642 "UNCACHE": TokenType.UNCACHE, 643 "CASE": TokenType.CASE, 644 "CHARACTER SET": TokenType.CHARACTER_SET, 645 "CLUSTER BY": TokenType.CLUSTER_BY, 646 "COLLATE": TokenType.COLLATE, 647 "COLUMN": TokenType.COLUMN, 648 "COMMIT": TokenType.COMMIT, 649 "CONNECT BY": TokenType.CONNECT_BY, 650 "CONSTRAINT": TokenType.CONSTRAINT, 651 "CREATE": TokenType.CREATE, 652 "CROSS": TokenType.CROSS, 653 "CUBE": TokenType.CUBE, 654 "CURRENT_DATE": TokenType.CURRENT_DATE, 655 "CURRENT_TIME": TokenType.CURRENT_TIME, 656 "CURRENT_TIMESTAMP": TokenType.CURRENT_TIMESTAMP, 657 "CURRENT_USER": TokenType.CURRENT_USER, 658 "DATABASE": TokenType.DATABASE, 659 "DEFAULT": TokenType.DEFAULT, 660 "DELETE": TokenType.DELETE, 661 "DESC": TokenType.DESC, 662 "DESCRIBE": TokenType.DESCRIBE, 663 "DISTINCT": TokenType.DISTINCT, 664 "DISTRIBUTE BY": TokenType.DISTRIBUTE_BY, 665 "DIV": TokenType.DIV, 666 "DROP": TokenType.DROP, 667 "ELSE": TokenType.ELSE, 668 "END": TokenType.END, 669 "ENUM": TokenType.ENUM, 670 "ESCAPE": TokenType.ESCAPE, 671 "EXCEPT": TokenType.EXCEPT, 672 "EXECUTE": TokenType.EXECUTE, 673 "EXISTS": TokenType.EXISTS, 674 "FALSE": TokenType.FALSE, 675 "FETCH": TokenType.FETCH, 676 "FILTER": TokenType.FILTER, 677 "FIRST": TokenType.FIRST, 678 "FULL": TokenType.FULL, 679 "FUNCTION": TokenType.FUNCTION, 680 "FOR": TokenType.FOR, 681 "FOREIGN KEY": TokenType.FOREIGN_KEY, 682 "FORMAT": TokenType.FORMAT, 683 "FROM": TokenType.FROM, 684 "GEOGRAPHY": TokenType.GEOGRAPHY, 685 "GEOMETRY": TokenType.GEOMETRY, 686 "GLOB": TokenType.GLOB, 687 "GROUP BY": TokenType.GROUP_BY, 688 "GROUPING SETS": TokenType.GROUPING_SETS, 689 "HAVING": TokenType.HAVING, 690 "ILIKE": TokenType.ILIKE, 691 "IN": TokenType.IN, 692 "INDEX": TokenType.INDEX, 693 "INET": TokenType.INET, 694 "INNER": TokenType.INNER, 695 "INSERT": TokenType.INSERT, 696 "INTERVAL": TokenType.INTERVAL, 697 "INTERSECT": TokenType.INTERSECT, 698 "INTO": TokenType.INTO, 699 "IS": TokenType.IS, 700 "ISNULL": TokenType.ISNULL, 701 "JOIN": TokenType.JOIN, 702 "KEEP": TokenType.KEEP, 703 "KILL": TokenType.KILL, 704 "LATERAL": TokenType.LATERAL, 705 "LEFT": TokenType.LEFT, 706 "LIKE": TokenType.LIKE, 707 "LIMIT": TokenType.LIMIT, 708 "LOAD": TokenType.LOAD, 709 "LOCK": TokenType.LOCK, 710 "MERGE": TokenType.MERGE, 711 "NATURAL": TokenType.NATURAL, 712 "NEXT": TokenType.NEXT, 713 "NOT": TokenType.NOT, 714 "NOTNULL": TokenType.NOTNULL, 715 "NULL": TokenType.NULL, 716 "OBJECT": TokenType.OBJECT, 717 "OFFSET": TokenType.OFFSET, 718 "ON": TokenType.ON, 719 "OR": TokenType.OR, 720 "XOR": TokenType.XOR, 721 "ORDER BY": TokenType.ORDER_BY, 722 "ORDINALITY": TokenType.ORDINALITY, 723 "OUTER": TokenType.OUTER, 724 "OVER": TokenType.OVER, 725 "OVERLAPS": TokenType.OVERLAPS, 726 "OVERWRITE": TokenType.OVERWRITE, 727 "PARTITION": TokenType.PARTITION, 728 "PARTITION BY": TokenType.PARTITION_BY, 729 "PARTITIONED BY": TokenType.PARTITION_BY, 730 "PARTITIONED_BY": TokenType.PARTITION_BY, 731 "PERCENT": TokenType.PERCENT, 732 "PIVOT": TokenType.PIVOT, 733 "PRAGMA": TokenType.PRAGMA, 734 "PRIMARY KEY": TokenType.PRIMARY_KEY, 735 "PROCEDURE": TokenType.PROCEDURE, 736 "QUALIFY": TokenType.QUALIFY, 737 "RANGE": TokenType.RANGE, 738 "RECURSIVE": TokenType.RECURSIVE, 739 "REGEXP": TokenType.RLIKE, 740 "REPLACE": TokenType.REPLACE, 741 "RETURNING": TokenType.RETURNING, 742 "REFERENCES": TokenType.REFERENCES, 743 "RIGHT": TokenType.RIGHT, 744 "RLIKE": TokenType.RLIKE, 745 "ROLLBACK": TokenType.ROLLBACK, 746 "ROLLUP": TokenType.ROLLUP, 747 "ROW": TokenType.ROW, 748 "ROWS": TokenType.ROWS, 749 "SCHEMA": TokenType.SCHEMA, 750 "SELECT": TokenType.SELECT, 751 "SEMI": TokenType.SEMI, 752 "SET": TokenType.SET, 753 "SETTINGS": TokenType.SETTINGS, 754 "SHOW": TokenType.SHOW, 755 "SIMILAR TO": TokenType.SIMILAR_TO, 756 "SOME": TokenType.SOME, 757 "SORT BY": TokenType.SORT_BY, 758 "START WITH": TokenType.START_WITH, 759 "TABLE": TokenType.TABLE, 760 "TABLESAMPLE": TokenType.TABLE_SAMPLE, 761 "TEMP": TokenType.TEMPORARY, 762 "TEMPORARY": TokenType.TEMPORARY, 763 "THEN": TokenType.THEN, 764 "TRUE": TokenType.TRUE, 765 "TRUNCATE": TokenType.TRUNCATE, 766 "UNION": TokenType.UNION, 767 "UNKNOWN": TokenType.UNKNOWN, 768 "UNNEST": TokenType.UNNEST, 769 "UNPIVOT": TokenType.UNPIVOT, 770 "UPDATE": TokenType.UPDATE, 771 "USE": TokenType.USE, 772 "USING": TokenType.USING, 773 "UUID": TokenType.UUID, 774 "VALUES": TokenType.VALUES, 775 "VIEW": TokenType.VIEW, 776 "VOLATILE": TokenType.VOLATILE, 777 "WHEN": TokenType.WHEN, 778 "WHERE": TokenType.WHERE, 779 "WINDOW": TokenType.WINDOW, 780 "WITH": TokenType.WITH, 781 "APPLY": TokenType.APPLY, 782 "ARRAY": TokenType.ARRAY, 783 "BIT": TokenType.BIT, 784 "BOOL": TokenType.BOOLEAN, 785 "BOOLEAN": TokenType.BOOLEAN, 786 "BYTE": TokenType.TINYINT, 787 "MEDIUMINT": TokenType.MEDIUMINT, 788 "INT1": TokenType.TINYINT, 789 "TINYINT": TokenType.TINYINT, 790 "INT16": TokenType.SMALLINT, 791 "SHORT": TokenType.SMALLINT, 792 "SMALLINT": TokenType.SMALLINT, 793 "INT128": TokenType.INT128, 794 "HUGEINT": TokenType.INT128, 795 "INT2": TokenType.SMALLINT, 796 "INTEGER": TokenType.INT, 797 "INT": TokenType.INT, 798 "INT4": TokenType.INT, 799 "INT32": TokenType.INT, 800 "INT64": TokenType.BIGINT, 801 "LONG": TokenType.BIGINT, 802 "BIGINT": TokenType.BIGINT, 803 "INT8": TokenType.TINYINT, 804 "UINT": TokenType.UINT, 805 "DEC": TokenType.DECIMAL, 806 "DECIMAL": TokenType.DECIMAL, 807 "BIGDECIMAL": TokenType.BIGDECIMAL, 808 "BIGNUMERIC": TokenType.BIGDECIMAL, 809 "MAP": TokenType.MAP, 810 "NULLABLE": TokenType.NULLABLE, 811 "NUMBER": TokenType.DECIMAL, 812 "NUMERIC": TokenType.DECIMAL, 813 "FIXED": TokenType.DECIMAL, 814 "REAL": TokenType.FLOAT, 815 "FLOAT": TokenType.FLOAT, 816 "FLOAT4": TokenType.FLOAT, 817 "FLOAT8": TokenType.DOUBLE, 818 "DOUBLE": TokenType.DOUBLE, 819 "DOUBLE PRECISION": TokenType.DOUBLE, 820 "JSON": TokenType.JSON, 821 "CHAR": TokenType.CHAR, 822 "CHARACTER": TokenType.CHAR, 823 "NCHAR": TokenType.NCHAR, 824 "VARCHAR": TokenType.VARCHAR, 825 "VARCHAR2": TokenType.VARCHAR, 826 "NVARCHAR": TokenType.NVARCHAR, 827 "NVARCHAR2": TokenType.NVARCHAR, 828 "BPCHAR": TokenType.BPCHAR, 829 "STR": TokenType.TEXT, 830 "STRING": TokenType.TEXT, 831 "TEXT": TokenType.TEXT, 832 "LONGTEXT": TokenType.LONGTEXT, 833 "MEDIUMTEXT": TokenType.MEDIUMTEXT, 834 "TINYTEXT": TokenType.TINYTEXT, 835 "CLOB": TokenType.TEXT, 836 "LONGVARCHAR": TokenType.TEXT, 837 "BINARY": TokenType.BINARY, 838 "BLOB": TokenType.VARBINARY, 839 "LONGBLOB": TokenType.LONGBLOB, 840 "MEDIUMBLOB": TokenType.MEDIUMBLOB, 841 "TINYBLOB": TokenType.TINYBLOB, 842 "BYTEA": TokenType.VARBINARY, 843 "VARBINARY": TokenType.VARBINARY, 844 "TIME": TokenType.TIME, 845 "TIMETZ": TokenType.TIMETZ, 846 "TIMESTAMP": TokenType.TIMESTAMP, 847 "TIMESTAMPTZ": TokenType.TIMESTAMPTZ, 848 "TIMESTAMPLTZ": TokenType.TIMESTAMPLTZ, 849 "DATE": TokenType.DATE, 850 "DATETIME": TokenType.DATETIME, 851 "INT4RANGE": TokenType.INT4RANGE, 852 "INT4MULTIRANGE": TokenType.INT4MULTIRANGE, 853 "INT8RANGE": TokenType.INT8RANGE, 854 "INT8MULTIRANGE": TokenType.INT8MULTIRANGE, 855 "NUMRANGE": TokenType.NUMRANGE, 856 "NUMMULTIRANGE": TokenType.NUMMULTIRANGE, 857 "TSRANGE": TokenType.TSRANGE, 858 "TSMULTIRANGE": TokenType.TSMULTIRANGE, 859 "TSTZRANGE": TokenType.TSTZRANGE, 860 "TSTZMULTIRANGE": TokenType.TSTZMULTIRANGE, 861 "DATERANGE": TokenType.DATERANGE, 862 "DATEMULTIRANGE": TokenType.DATEMULTIRANGE, 863 "UNIQUE": TokenType.UNIQUE, 864 "STRUCT": TokenType.STRUCT, 865 "SEQUENCE": TokenType.SEQUENCE, 866 "VARIANT": TokenType.VARIANT, 867 "ALTER": TokenType.ALTER, 868 "ANALYZE": TokenType.COMMAND, 869 "CALL": TokenType.COMMAND, 870 "COMMENT": TokenType.COMMENT, 871 "COPY": TokenType.COMMAND, 872 "EXPLAIN": TokenType.COMMAND, 873 "GRANT": TokenType.COMMAND, 874 "OPTIMIZE": TokenType.COMMAND, 875 "PREPARE": TokenType.COMMAND, 876 "VACUUM": TokenType.COMMAND, 877 "USER-DEFINED": TokenType.USERDEFINED, 878 "FOR VERSION": TokenType.VERSION_SNAPSHOT, 879 "FOR TIMESTAMP": TokenType.TIMESTAMP_SNAPSHOT, 880 } 881 882 WHITE_SPACE: t.Dict[t.Optional[str], TokenType] = { 883 " ": TokenType.SPACE, 884 "\t": TokenType.SPACE, 885 "\n": TokenType.BREAK, 886 "\r": TokenType.BREAK, 887 } 888 889 COMMANDS = { 890 TokenType.COMMAND, 891 TokenType.EXECUTE, 892 TokenType.FETCH, 893 TokenType.SHOW, 894 } 895 896 COMMAND_PREFIX_TOKENS = {TokenType.SEMICOLON, TokenType.BEGIN} 897 898 # Handle numeric literals like in hive (3L = BIGINT) 899 NUMERIC_LITERALS: t.Dict[str, str] = {} 900 901 COMMENTS = ["--", ("/*", "*/")] 902 903 __slots__ = ( 904 "sql", 905 "size", 906 "tokens", 907 "dialect", 908 "_start", 909 "_current", 910 "_line", 911 "_col", 912 "_comments", 913 "_char", 914 "_end", 915 "_peek", 916 "_prev_token_line", 917 "_rs_dialect_settings", 918 ) 919 920 def __init__(self, dialect: DialectType = None) -> None: 921 from sqlglot.dialects import Dialect 922 923 self.dialect = Dialect.get_or_raise(dialect) 924 925 if USE_RS_TOKENIZER: 926 self._rs_dialect_settings = RsTokenizerDialectSettings( 927 unescaped_sequences=self.dialect.UNESCAPED_SEQUENCES, 928 identifiers_can_start_with_digit=self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT, 929 ) 930 931 self.reset() 932 933 def reset(self) -> None: 934 self.sql = "" 935 self.size = 0 936 self.tokens: t.List[Token] = [] 937 self._start = 0 938 self._current = 0 939 self._line = 1 940 self._col = 0 941 self._comments: t.List[str] = [] 942 943 self._char = "" 944 self._end = False 945 self._peek = "" 946 self._prev_token_line = -1 947 948 def tokenize(self, sql: str) -> t.List[Token]: 949 """Returns a list of tokens corresponding to the SQL string `sql`.""" 950 if USE_RS_TOKENIZER: 951 return self.tokenize_rs(sql) 952 953 self.reset() 954 self.sql = sql 955 self.size = len(sql) 956 957 try: 958 self._scan() 959 except Exception as e: 960 start = max(self._current - 50, 0) 961 end = min(self._current + 50, self.size - 1) 962 context = self.sql[start:end] 963 raise TokenError(f"Error tokenizing '{context}'") from e 964 965 return self.tokens 966 967 def _scan(self, until: t.Optional[t.Callable] = None) -> None: 968 while self.size and not self._end: 969 current = self._current 970 971 # Skip spaces here rather than iteratively calling advance() for performance reasons 972 while current < self.size: 973 char = self.sql[current] 974 975 if char.isspace() and (char == " " or char == "\t"): 976 current += 1 977 else: 978 break 979 980 offset = current - self._current if current > self._current else 1 981 982 self._start = current 983 self._advance(offset) 984 985 if not self._char.isspace(): 986 if self._char.isdigit(): 987 self._scan_number() 988 elif self._char in self._IDENTIFIERS: 989 self._scan_identifier(self._IDENTIFIERS[self._char]) 990 else: 991 self._scan_keywords() 992 993 if until and until(): 994 break 995 996 if self.tokens and self._comments: 997 self.tokens[-1].comments.extend(self._comments) 998 999 def _chars(self, size: int) -> str: 1000 if size == 1: 1001 return self._char 1002 1003 start = self._current - 1 1004 end = start + size 1005 1006 return self.sql[start:end] if end <= self.size else "" 1007 1008 def _advance(self, i: int = 1, alnum: bool = False) -> None: 1009 if self.WHITE_SPACE.get(self._char) is TokenType.BREAK: 1010 # Ensures we don't count an extra line if we get a \r\n line break sequence 1011 if not (self._char == "\r" and self._peek == "\n"): 1012 self._col = 1 1013 self._line += 1 1014 else: 1015 self._col += i 1016 1017 self._current += i 1018 self._end = self._current >= self.size 1019 self._char = self.sql[self._current - 1] 1020 self._peek = "" if self._end else self.sql[self._current] 1021 1022 if alnum and self._char.isalnum(): 1023 # Here we use local variables instead of attributes for better performance 1024 _col = self._col 1025 _current = self._current 1026 _end = self._end 1027 _peek = self._peek 1028 1029 while _peek.isalnum(): 1030 _col += 1 1031 _current += 1 1032 _end = _current >= self.size 1033 _peek = "" if _end else self.sql[_current] 1034 1035 self._col = _col 1036 self._current = _current 1037 self._end = _end 1038 self._peek = _peek 1039 self._char = self.sql[_current - 1] 1040 1041 @property 1042 def _text(self) -> str: 1043 return self.sql[self._start : self._current] 1044 1045 def _add(self, token_type: TokenType, text: t.Optional[str] = None) -> None: 1046 self._prev_token_line = self._line 1047 1048 if self._comments and token_type == TokenType.SEMICOLON and self.tokens: 1049 self.tokens[-1].comments.extend(self._comments) 1050 self._comments = [] 1051 1052 self.tokens.append( 1053 Token( 1054 token_type, 1055 text=self._text if text is None else text, 1056 line=self._line, 1057 col=self._col, 1058 start=self._start, 1059 end=self._current - 1, 1060 comments=self._comments, 1061 ) 1062 ) 1063 self._comments = [] 1064 1065 # If we have either a semicolon or a begin token before the command's token, we'll parse 1066 # whatever follows the command's token as a string 1067 if ( 1068 token_type in self.COMMANDS 1069 and self._peek != ";" 1070 and (len(self.tokens) == 1 or self.tokens[-2].token_type in self.COMMAND_PREFIX_TOKENS) 1071 ): 1072 start = self._current 1073 tokens = len(self.tokens) 1074 self._scan(lambda: self._peek == ";") 1075 self.tokens = self.tokens[:tokens] 1076 text = self.sql[start : self._current].strip() 1077 if text: 1078 self._add(TokenType.STRING, text) 1079 1080 def _scan_keywords(self) -> None: 1081 size = 0 1082 word = None 1083 chars = self._text 1084 char = chars 1085 prev_space = False 1086 skip = False 1087 trie = self._KEYWORD_TRIE 1088 single_token = char in self.SINGLE_TOKENS 1089 1090 while chars: 1091 if skip: 1092 result = TrieResult.PREFIX 1093 else: 1094 result, trie = in_trie(trie, char.upper()) 1095 1096 if result == TrieResult.FAILED: 1097 break 1098 if result == TrieResult.EXISTS: 1099 word = chars 1100 1101 end = self._current + size 1102 size += 1 1103 1104 if end < self.size: 1105 char = self.sql[end] 1106 single_token = single_token or char in self.SINGLE_TOKENS 1107 is_space = char.isspace() 1108 1109 if not is_space or not prev_space: 1110 if is_space: 1111 char = " " 1112 chars += char 1113 prev_space = is_space 1114 skip = False 1115 else: 1116 skip = True 1117 else: 1118 char = "" 1119 break 1120 1121 if word: 1122 if self._scan_string(word): 1123 return 1124 if self._scan_comment(word): 1125 return 1126 if prev_space or single_token or not char: 1127 self._advance(size - 1) 1128 word = word.upper() 1129 self._add(self.KEYWORDS[word], text=word) 1130 return 1131 1132 if self._char in self.SINGLE_TOKENS: 1133 self._add(self.SINGLE_TOKENS[self._char], text=self._char) 1134 return 1135 1136 self._scan_var() 1137 1138 def _scan_comment(self, comment_start: str) -> bool: 1139 if comment_start not in self._COMMENTS: 1140 return False 1141 1142 comment_start_line = self._line 1143 comment_start_size = len(comment_start) 1144 comment_end = self._COMMENTS[comment_start] 1145 1146 if comment_end: 1147 # Skip the comment's start delimiter 1148 self._advance(comment_start_size) 1149 1150 comment_end_size = len(comment_end) 1151 while not self._end and self._chars(comment_end_size) != comment_end: 1152 self._advance(alnum=True) 1153 1154 self._comments.append(self._text[comment_start_size : -comment_end_size + 1]) 1155 self._advance(comment_end_size - 1) 1156 else: 1157 while not self._end and self.WHITE_SPACE.get(self._peek) is not TokenType.BREAK: 1158 self._advance(alnum=True) 1159 self._comments.append(self._text[comment_start_size:]) 1160 1161 # Leading comment is attached to the succeeding token, whilst trailing comment to the preceding. 1162 # Multiple consecutive comments are preserved by appending them to the current comments list. 1163 if comment_start_line == self._prev_token_line: 1164 self.tokens[-1].comments.extend(self._comments) 1165 self._comments = [] 1166 self._prev_token_line = self._line 1167 1168 return True 1169 1170 def _scan_number(self) -> None: 1171 if self._char == "0": 1172 peek = self._peek.upper() 1173 if peek == "B": 1174 return self._scan_bits() if self.BIT_STRINGS else self._add(TokenType.NUMBER) 1175 elif peek == "X": 1176 return self._scan_hex() if self.HEX_STRINGS else self._add(TokenType.NUMBER) 1177 1178 decimal = False 1179 scientific = 0 1180 1181 while True: 1182 if self._peek.isdigit(): 1183 self._advance() 1184 elif self._peek == "." and not decimal: 1185 decimal = True 1186 self._advance() 1187 elif self._peek in ("-", "+") and scientific == 1: 1188 scientific += 1 1189 self._advance() 1190 elif self._peek.upper() == "E" and not scientific: 1191 scientific += 1 1192 self._advance() 1193 elif self._peek.isidentifier(): 1194 number_text = self._text 1195 literal = "" 1196 1197 while self._peek.strip() and self._peek not in self.SINGLE_TOKENS: 1198 literal += self._peek 1199 self._advance() 1200 1201 token_type = self.KEYWORDS.get(self.NUMERIC_LITERALS.get(literal.upper(), "")) 1202 1203 if token_type: 1204 self._add(TokenType.NUMBER, number_text) 1205 self._add(TokenType.DCOLON, "::") 1206 return self._add(token_type, literal) 1207 elif self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT: 1208 return self._add(TokenType.VAR) 1209 1210 self._advance(-len(literal)) 1211 return self._add(TokenType.NUMBER, number_text) 1212 else: 1213 return self._add(TokenType.NUMBER) 1214 1215 def _scan_bits(self) -> None: 1216 self._advance() 1217 value = self._extract_value() 1218 try: 1219 # If `value` can't be converted to a binary, fallback to tokenizing it as an identifier 1220 int(value, 2) 1221 self._add(TokenType.BIT_STRING, value[2:]) # Drop the 0b 1222 except ValueError: 1223 self._add(TokenType.IDENTIFIER) 1224 1225 def _scan_hex(self) -> None: 1226 self._advance() 1227 value = self._extract_value() 1228 try: 1229 # If `value` can't be converted to a hex, fallback to tokenizing it as an identifier 1230 int(value, 16) 1231 self._add(TokenType.HEX_STRING, value[2:]) # Drop the 0x 1232 except ValueError: 1233 self._add(TokenType.IDENTIFIER) 1234 1235 def _extract_value(self) -> str: 1236 while True: 1237 char = self._peek.strip() 1238 if char and char not in self.SINGLE_TOKENS: 1239 self._advance(alnum=True) 1240 else: 1241 break 1242 1243 return self._text 1244 1245 def _scan_string(self, start: str) -> bool: 1246 base = None 1247 token_type = TokenType.STRING 1248 1249 if start in self._QUOTES: 1250 end = self._QUOTES[start] 1251 elif start in self._FORMAT_STRINGS: 1252 end, token_type = self._FORMAT_STRINGS[start] 1253 1254 if token_type == TokenType.HEX_STRING: 1255 base = 16 1256 elif token_type == TokenType.BIT_STRING: 1257 base = 2 1258 elif token_type == TokenType.HEREDOC_STRING: 1259 if ( 1260 self.HEREDOC_TAG_IS_IDENTIFIER 1261 and not self._peek.isidentifier() 1262 and not self._peek == end 1263 ): 1264 if self.HEREDOC_STRING_ALTERNATIVE != token_type.VAR: 1265 self._add(self.HEREDOC_STRING_ALTERNATIVE) 1266 else: 1267 self._scan_var() 1268 1269 return True 1270 1271 self._advance() 1272 1273 if self._char == end: 1274 tag = "" 1275 else: 1276 tag = self._extract_string( 1277 end, 1278 unescape_sequences=False, 1279 raise_unmatched=not self.HEREDOC_TAG_IS_IDENTIFIER, 1280 ) 1281 1282 if self._end and tag and self.HEREDOC_TAG_IS_IDENTIFIER: 1283 self._advance(-len(tag)) 1284 self._add(self.HEREDOC_STRING_ALTERNATIVE) 1285 return True 1286 1287 end = f"{start}{tag}{end}" 1288 else: 1289 return False 1290 1291 self._advance(len(start)) 1292 text = self._extract_string(end, unescape_sequences=token_type != TokenType.RAW_STRING) 1293 1294 if base: 1295 try: 1296 int(text, base) 1297 except Exception: 1298 raise TokenError( 1299 f"Numeric string contains invalid characters from {self._line}:{self._start}" 1300 ) 1301 1302 self._add(token_type, text) 1303 return True 1304 1305 def _scan_identifier(self, identifier_end: str) -> None: 1306 self._advance() 1307 text = self._extract_string(identifier_end, escapes=self._IDENTIFIER_ESCAPES) 1308 self._add(TokenType.IDENTIFIER, text) 1309 1310 def _scan_var(self) -> None: 1311 while True: 1312 char = self._peek.strip() 1313 if char and (char in self.VAR_SINGLE_TOKENS or char not in self.SINGLE_TOKENS): 1314 self._advance(alnum=True) 1315 else: 1316 break 1317 1318 self._add( 1319 TokenType.VAR 1320 if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER 1321 else self.KEYWORDS.get(self._text.upper(), TokenType.VAR) 1322 ) 1323 1324 def _extract_string( 1325 self, 1326 delimiter: str, 1327 escapes: t.Optional[t.Set[str]] = None, 1328 unescape_sequences: bool = True, 1329 raise_unmatched: bool = True, 1330 ) -> str: 1331 text = "" 1332 delim_size = len(delimiter) 1333 escapes = self._STRING_ESCAPES if escapes is None else escapes 1334 1335 while True: 1336 if ( 1337 unescape_sequences 1338 and self.dialect.UNESCAPED_SEQUENCES 1339 and self._peek 1340 and self._char in self.STRING_ESCAPES 1341 ): 1342 unescaped_sequence = self.dialect.UNESCAPED_SEQUENCES.get(self._char + self._peek) 1343 if unescaped_sequence: 1344 self._advance(2) 1345 text += unescaped_sequence 1346 continue 1347 if ( 1348 self._char in escapes 1349 and (self._peek == delimiter or self._peek in escapes) 1350 and (self._char not in self._QUOTES or self._char == self._peek) 1351 ): 1352 if self._peek == delimiter: 1353 text += self._peek 1354 else: 1355 text += self._char + self._peek 1356 1357 if self._current + 1 < self.size: 1358 self._advance(2) 1359 else: 1360 raise TokenError(f"Missing {delimiter} from {self._line}:{self._current}") 1361 else: 1362 if self._chars(delim_size) == delimiter: 1363 if delim_size > 1: 1364 self._advance(delim_size - 1) 1365 break 1366 1367 if self._end: 1368 if not raise_unmatched: 1369 return text + self._char 1370 1371 raise TokenError(f"Missing {delimiter} from {self._line}:{self._start}") 1372 1373 current = self._current - 1 1374 self._advance(alnum=True) 1375 text += self.sql[current : self._current - 1] 1376 1377 return text 1378 1379 def tokenize_rs(self, sql: str) -> t.List[Token]: 1380 if not self._RS_TOKENIZER: 1381 raise SqlglotError("Rust tokenizer is not available") 1382 1383 try: 1384 tokens = self._RS_TOKENIZER.tokenize(sql, self._rs_dialect_settings) 1385 for token in tokens: 1386 token.token_type = _ALL_TOKEN_TYPES[token.token_type_index] 1387 return tokens 1388 except Exception as e: 1389 raise TokenError(str(e))
Tokenizer( dialect: Union[str, sqlglot.dialects.dialect.Dialect, Type[sqlglot.dialects.dialect.Dialect], NoneType] = None)
920 def __init__(self, dialect: DialectType = None) -> None: 921 from sqlglot.dialects import Dialect 922 923 self.dialect = Dialect.get_or_raise(dialect) 924 925 if USE_RS_TOKENIZER: 926 self._rs_dialect_settings = RsTokenizerDialectSettings( 927 unescaped_sequences=self.dialect.UNESCAPED_SEQUENCES, 928 identifiers_can_start_with_digit=self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT, 929 ) 930 931 self.reset()
SINGLE_TOKENS =
{'(': <TokenType.L_PAREN: 'L_PAREN'>, ')': <TokenType.R_PAREN: 'R_PAREN'>, '[': <TokenType.L_BRACKET: 'L_BRACKET'>, ']': <TokenType.R_BRACKET: 'R_BRACKET'>, '{': <TokenType.L_BRACE: 'L_BRACE'>, '}': <TokenType.R_BRACE: 'R_BRACE'>, '&': <TokenType.AMP: 'AMP'>, '^': <TokenType.CARET: 'CARET'>, ':': <TokenType.COLON: 'COLON'>, ',': <TokenType.COMMA: 'COMMA'>, '.': <TokenType.DOT: 'DOT'>, '-': <TokenType.DASH: 'DASH'>, '=': <TokenType.EQ: 'EQ'>, '>': <TokenType.GT: 'GT'>, '<': <TokenType.LT: 'LT'>, '%': <TokenType.MOD: 'MOD'>, '!': <TokenType.NOT: 'NOT'>, '|': <TokenType.PIPE: 'PIPE'>, '+': <TokenType.PLUS: 'PLUS'>, ';': <TokenType.SEMICOLON: 'SEMICOLON'>, '/': <TokenType.SLASH: 'SLASH'>, '\\': <TokenType.BACKSLASH: 'BACKSLASH'>, '*': <TokenType.STAR: 'STAR'>, '~': <TokenType.TILDA: 'TILDA'>, '?': <TokenType.PLACEHOLDER: 'PLACEHOLDER'>, '@': <TokenType.PARAMETER: 'PARAMETER'>, "'": <TokenType.QUOTE: 'QUOTE'>, '`': <TokenType.IDENTIFIER: 'IDENTIFIER'>, '"': <TokenType.IDENTIFIER: 'IDENTIFIER'>, '#': <TokenType.HASH: 'HASH'>}
HEREDOC_STRING_ALTERNATIVE =
<TokenType.VAR: 'VAR'>
KEYWORDS: Dict[str, TokenType] =
{'{%': <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.COLON_EQ: 'COLON_EQ'>, '<=>': <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.BEGIN: 'BEGIN'>, 'BETWEEN': <TokenType.BETWEEN: 'BETWEEN'>, 'CACHE': <TokenType.CACHE: 'CACHE'>, 'UNCACHE': <TokenType.UNCACHE: 'UNCACHE'>, 'CASE': <TokenType.CASE: 'CASE'>, 'CHARACTER SET': <TokenType.CHARACTER_SET: 'CHARACTER_SET'>, 'CLUSTER BY': <TokenType.CLUSTER_BY: 'CLUSTER_BY'>, 'COLLATE': <TokenType.COLLATE: 'COLLATE'>, 'COLUMN': <TokenType.COLUMN: 'COLUMN'>, 'COMMIT': <TokenType.COMMIT: 'COMMIT'>, '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'>, 'DIV': <TokenType.DIV: 'DIV'>, 'DROP': <TokenType.DROP: 'DROP'>, 'ELSE': <TokenType.ELSE: 'ELSE'>, 'END': <TokenType.END: 'END'>, 'ENUM': <TokenType.ENUM: 'ENUM'>, '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'>, 'TRUNCATE': <TokenType.TRUNCATE: 'TRUNCATE'>, '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'>, 'INT1': <TokenType.TINYINT: 'TINYINT'>, 'TINYINT': <TokenType.TINYINT: 'TINYINT'>, 'INT16': <TokenType.SMALLINT: 'SMALLINT'>, 'SHORT': <TokenType.SMALLINT: 'SMALLINT'>, 'SMALLINT': <TokenType.SMALLINT: 'SMALLINT'>, 'INT128': <TokenType.INT128: 'INT128'>, 'HUGEINT': <TokenType.INT128: 'INT128'>, 'INT2': <TokenType.SMALLINT: 'SMALLINT'>, 'INTEGER': <TokenType.INT: 'INT'>, 'INT': <TokenType.INT: 'INT'>, 'INT4': <TokenType.INT: 'INT'>, 'INT32': <TokenType.INT: 'INT'>, 'INT64': <TokenType.BIGINT: 'BIGINT'>, 'LONG': <TokenType.BIGINT: 'BIGINT'>, 'BIGINT': <TokenType.BIGINT: 'BIGINT'>, 'INT8': <TokenType.TINYINT: 'TINYINT'>, 'UINT': <TokenType.UINT: 'UINT'>, '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'>, 'BPCHAR': <TokenType.BPCHAR: 'BPCHAR'>, '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.TIMESTAMP: 'TIMESTAMP'>, 'TIMESTAMPTZ': <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>, 'TIMESTAMPLTZ': <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>, 'DATE': <TokenType.DATE: 'DATE'>, 'DATETIME': <TokenType.DATETIME: 'DATETIME'>, 'INT4RANGE': <TokenType.INT4RANGE: 'INT4RANGE'>, 'INT4MULTIRANGE': <TokenType.INT4MULTIRANGE: 'INT4MULTIRANGE'>, 'INT8RANGE': <TokenType.INT8RANGE: 'INT8RANGE'>, 'INT8MULTIRANGE': <TokenType.INT8MULTIRANGE: 'INT8MULTIRANGE'>, 'NUMRANGE': <TokenType.NUMRANGE: 'NUMRANGE'>, 'NUMMULTIRANGE': <TokenType.NUMMULTIRANGE: 'NUMMULTIRANGE'>, 'TSRANGE': <TokenType.TSRANGE: 'TSRANGE'>, 'TSMULTIRANGE': <TokenType.TSMULTIRANGE: 'TSMULTIRANGE'>, 'TSTZRANGE': <TokenType.TSTZRANGE: 'TSTZRANGE'>, 'TSTZMULTIRANGE': <TokenType.TSTZMULTIRANGE: 'TSTZMULTIRANGE'>, 'DATERANGE': <TokenType.DATERANGE: 'DATERANGE'>, 'DATEMULTIRANGE': <TokenType.DATEMULTIRANGE: 'DATEMULTIRANGE'>, 'UNIQUE': <TokenType.UNIQUE: 'UNIQUE'>, 'STRUCT': <TokenType.STRUCT: 'STRUCT'>, 'SEQUENCE': <TokenType.SEQUENCE: 'SEQUENCE'>, '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'>, 'VACUUM': <TokenType.COMMAND: 'COMMAND'>, 'USER-DEFINED': <TokenType.USERDEFINED: 'USERDEFINED'>, 'FOR VERSION': <TokenType.VERSION_SNAPSHOT: 'VERSION_SNAPSHOT'>, 'FOR TIMESTAMP': <TokenType.TIMESTAMP_SNAPSHOT: 'TIMESTAMP_SNAPSHOT'>}
WHITE_SPACE: Dict[Optional[str], TokenType] =
{' ': <TokenType.SPACE: 'SPACE'>, '\t': <TokenType.SPACE: 'SPACE'>, '\n': <TokenType.BREAK: 'BREAK'>, '\r': <TokenType.BREAK: 'BREAK'>}
COMMANDS =
{<TokenType.EXECUTE: 'EXECUTE'>, <TokenType.SHOW: 'SHOW'>, <TokenType.FETCH: 'FETCH'>, <TokenType.COMMAND: 'COMMAND'>}
COMMAND_PREFIX_TOKENS =
{<TokenType.SEMICOLON: 'SEMICOLON'>, <TokenType.BEGIN: 'BEGIN'>}
def
reset(self) -> None:
933 def reset(self) -> None: 934 self.sql = "" 935 self.size = 0 936 self.tokens: t.List[Token] = [] 937 self._start = 0 938 self._current = 0 939 self._line = 1 940 self._col = 0 941 self._comments: t.List[str] = [] 942 943 self._char = "" 944 self._end = False 945 self._peek = "" 946 self._prev_token_line = -1
948 def tokenize(self, sql: str) -> t.List[Token]: 949 """Returns a list of tokens corresponding to the SQL string `sql`.""" 950 if USE_RS_TOKENIZER: 951 return self.tokenize_rs(sql) 952 953 self.reset() 954 self.sql = sql 955 self.size = len(sql) 956 957 try: 958 self._scan() 959 except Exception as e: 960 start = max(self._current - 50, 0) 961 end = min(self._current + 50, self.size - 1) 962 context = self.sql[start:end] 963 raise TokenError(f"Error tokenizing '{context}'") from e 964 965 return self.tokens
Returns a list of tokens corresponding to the SQL string sql
.
1379 def tokenize_rs(self, sql: str) -> t.List[Token]: 1380 if not self._RS_TOKENIZER: 1381 raise SqlglotError("Rust tokenizer is not available") 1382 1383 try: 1384 tokens = self._RS_TOKENIZER.tokenize(sql, self._rs_dialect_settings) 1385 for token in tokens: 1386 token.token_type = _ALL_TOKEN_TYPES[token.token_type_index] 1387 return tokens 1388 except Exception as e: 1389 raise TokenError(str(e))