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