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