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