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