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