sqlglot.tokens
1from __future__ import annotations 2 3import typing as t 4from enum import auto 5 6from sqlglot.helper import AutoName 7from sqlglot.trie import in_trie, new_trie 8 9 10class TokenType(AutoName): 11 L_PAREN = auto() 12 R_PAREN = auto() 13 L_BRACKET = auto() 14 R_BRACKET = auto() 15 L_BRACE = auto() 16 R_BRACE = auto() 17 COMMA = auto() 18 DOT = auto() 19 DASH = auto() 20 PLUS = auto() 21 COLON = auto() 22 DCOLON = auto() 23 SEMICOLON = auto() 24 STAR = auto() 25 BACKSLASH = auto() 26 SLASH = auto() 27 LT = auto() 28 LTE = auto() 29 GT = auto() 30 GTE = auto() 31 NOT = auto() 32 EQ = auto() 33 NEQ = auto() 34 NULLSAFE_EQ = auto() 35 AND = auto() 36 OR = auto() 37 AMP = auto() 38 DPIPE = auto() 39 PIPE = auto() 40 CARET = auto() 41 TILDA = auto() 42 ARROW = auto() 43 DARROW = auto() 44 FARROW = auto() 45 HASH = auto() 46 HASH_ARROW = auto() 47 DHASH_ARROW = auto() 48 LR_ARROW = auto() 49 LT_AT = auto() 50 AT_GT = auto() 51 DOLLAR = auto() 52 PARAMETER = auto() 53 SESSION_PARAMETER = auto() 54 NATIONAL = auto() 55 DAMP = auto() 56 57 BLOCK_START = auto() 58 BLOCK_END = auto() 59 60 SPACE = auto() 61 BREAK = auto() 62 63 STRING = auto() 64 NUMBER = auto() 65 IDENTIFIER = auto() 66 DATABASE = auto() 67 COLUMN = auto() 68 COLUMN_DEF = auto() 69 SCHEMA = auto() 70 TABLE = auto() 71 VAR = auto() 72 BIT_STRING = auto() 73 HEX_STRING = auto() 74 BYTE_STRING = auto() 75 76 # types 77 BIT = auto() 78 BOOLEAN = auto() 79 TINYINT = auto() 80 UTINYINT = auto() 81 SMALLINT = auto() 82 USMALLINT = auto() 83 INT = auto() 84 UINT = auto() 85 BIGINT = auto() 86 UBIGINT = auto() 87 INT128 = auto() 88 UINT128 = auto() 89 INT256 = auto() 90 UINT256 = auto() 91 FLOAT = auto() 92 DOUBLE = auto() 93 DECIMAL = auto() 94 BIGDECIMAL = auto() 95 CHAR = auto() 96 NCHAR = auto() 97 VARCHAR = auto() 98 NVARCHAR = auto() 99 TEXT = auto() 100 MEDIUMTEXT = auto() 101 LONGTEXT = auto() 102 MEDIUMBLOB = auto() 103 LONGBLOB = auto() 104 BINARY = auto() 105 VARBINARY = auto() 106 JSON = auto() 107 JSONB = auto() 108 TIME = auto() 109 TIMESTAMP = auto() 110 TIMESTAMPTZ = auto() 111 TIMESTAMPLTZ = auto() 112 DATETIME = auto() 113 DATETIME64 = auto() 114 DATE = auto() 115 UUID = auto() 116 GEOGRAPHY = auto() 117 NULLABLE = auto() 118 GEOMETRY = auto() 119 HLLSKETCH = auto() 120 HSTORE = auto() 121 SUPER = auto() 122 SERIAL = auto() 123 SMALLSERIAL = auto() 124 BIGSERIAL = auto() 125 XML = auto() 126 UNIQUEIDENTIFIER = auto() 127 MONEY = auto() 128 SMALLMONEY = auto() 129 ROWVERSION = auto() 130 IMAGE = auto() 131 VARIANT = auto() 132 OBJECT = auto() 133 INET = auto() 134 135 # keywords 136 ALIAS = auto() 137 ALTER = auto() 138 ALWAYS = auto() 139 ALL = auto() 140 ANTI = auto() 141 ANY = auto() 142 APPLY = auto() 143 ARRAY = auto() 144 ASC = auto() 145 ASOF = auto() 146 AT_TIME_ZONE = auto() 147 AUTO_INCREMENT = auto() 148 BEGIN = auto() 149 BETWEEN = auto() 150 BOTH = auto() 151 BUCKET = auto() 152 BY_DEFAULT = auto() 153 CACHE = auto() 154 CASCADE = auto() 155 CASE = auto() 156 CHARACTER_SET = auto() 157 CLUSTER_BY = auto() 158 COLLATE = auto() 159 COMMAND = auto() 160 COMMENT = auto() 161 COMMIT = auto() 162 COMPOUND = auto() 163 CONSTRAINT = auto() 164 CREATE = auto() 165 CROSS = auto() 166 CUBE = auto() 167 CURRENT_DATE = auto() 168 CURRENT_DATETIME = auto() 169 CURRENT_ROW = auto() 170 CURRENT_TIME = auto() 171 CURRENT_TIMESTAMP = auto() 172 CURRENT_USER = auto() 173 DEFAULT = auto() 174 DELETE = auto() 175 DESC = auto() 176 DESCRIBE = auto() 177 DISTINCT = auto() 178 DISTINCT_FROM = auto() 179 DISTRIBUTE_BY = auto() 180 DIV = auto() 181 DROP = auto() 182 ELSE = auto() 183 END = auto() 184 ESCAPE = auto() 185 EXCEPT = auto() 186 EXECUTE = auto() 187 EXISTS = auto() 188 FALSE = auto() 189 FETCH = auto() 190 FILTER = auto() 191 FINAL = auto() 192 FIRST = auto() 193 FOLLOWING = auto() 194 FOR = auto() 195 FOREIGN_KEY = auto() 196 FORMAT = auto() 197 FROM = auto() 198 FULL = auto() 199 FUNCTION = auto() 200 GLOB = auto() 201 GLOBAL = auto() 202 GROUP_BY = auto() 203 GROUPING_SETS = auto() 204 HAVING = auto() 205 HINT = auto() 206 IF = auto() 207 IGNORE_NULLS = auto() 208 ILIKE = auto() 209 ILIKE_ANY = auto() 210 IN = auto() 211 INDEX = auto() 212 INNER = auto() 213 INSERT = auto() 214 INTERSECT = auto() 215 INTERVAL = auto() 216 INTO = auto() 217 INTRODUCER = auto() 218 IRLIKE = auto() 219 IS = auto() 220 ISNULL = auto() 221 JOIN = auto() 222 JOIN_MARKER = auto() 223 KEEP = auto() 224 LANGUAGE = auto() 225 LATERAL = auto() 226 LAZY = auto() 227 LEADING = auto() 228 LEFT = auto() 229 LIKE = auto() 230 LIKE_ANY = auto() 231 LIMIT = auto() 232 LOAD_DATA = auto() 233 LOCAL = auto() 234 LOCK = auto() 235 MAP = auto() 236 MATCH_RECOGNIZE = auto() 237 MATERIALIZED = auto() 238 MERGE = auto() 239 MOD = auto() 240 NATURAL = auto() 241 NEXT = auto() 242 NEXT_VALUE_FOR = auto() 243 NO_ACTION = auto() 244 NOTNULL = auto() 245 NULL = auto() 246 NULLS_FIRST = auto() 247 NULLS_LAST = auto() 248 OFFSET = auto() 249 ON = auto() 250 ONLY = auto() 251 OPTIONS = auto() 252 ORDER_BY = auto() 253 ORDERED = auto() 254 ORDINALITY = auto() 255 OUTER = auto() 256 OUT_OF = auto() 257 OVER = auto() 258 OVERLAPS = auto() 259 OVERWRITE = auto() 260 PARTITION = auto() 261 PARTITION_BY = auto() 262 PERCENT = auto() 263 PIVOT = auto() 264 PLACEHOLDER = auto() 265 PRAGMA = auto() 266 PRECEDING = auto() 267 PRIMARY_KEY = auto() 268 PROCEDURE = auto() 269 PROPERTIES = auto() 270 PSEUDO_TYPE = auto() 271 QUALIFY = auto() 272 QUOTE = auto() 273 RANGE = auto() 274 RECURSIVE = auto() 275 REPLACE = auto() 276 RESPECT_NULLS = auto() 277 RETURNING = auto() 278 REFERENCES = auto() 279 RIGHT = auto() 280 RLIKE = auto() 281 ROLLBACK = auto() 282 ROLLUP = auto() 283 ROW = auto() 284 ROWS = auto() 285 SEED = auto() 286 SELECT = auto() 287 SEMI = auto() 288 SEPARATOR = auto() 289 SERDE_PROPERTIES = auto() 290 SET = auto() 291 SETTINGS = auto() 292 SHOW = auto() 293 SIMILAR_TO = auto() 294 SOME = auto() 295 SORTKEY = auto() 296 SORT_BY = auto() 297 STRUCT = auto() 298 TABLE_SAMPLE = auto() 299 TEMPORARY = auto() 300 TOP = auto() 301 THEN = auto() 302 TRAILING = auto() 303 TRUE = auto() 304 UNBOUNDED = auto() 305 UNCACHE = auto() 306 UNION = auto() 307 UNLOGGED = auto() 308 UNNEST = auto() 309 UNPIVOT = auto() 310 UPDATE = auto() 311 USE = auto() 312 USING = auto() 313 VALUES = auto() 314 VIEW = auto() 315 VOLATILE = auto() 316 WHEN = auto() 317 WHERE = auto() 318 WINDOW = auto() 319 WITH = auto() 320 WITH_TIME_ZONE = auto() 321 WITH_LOCAL_TIME_ZONE = auto() 322 WITHIN_GROUP = auto() 323 WITHOUT_TIME_ZONE = auto() 324 UNIQUE = auto() 325 326 327class Token: 328 __slots__ = ("token_type", "text", "line", "col", "end", "comments") 329 330 @classmethod 331 def number(cls, number: int) -> Token: 332 """Returns a NUMBER token with `number` as its text.""" 333 return cls(TokenType.NUMBER, str(number)) 334 335 @classmethod 336 def string(cls, string: str) -> Token: 337 """Returns a STRING token with `string` as its text.""" 338 return cls(TokenType.STRING, string) 339 340 @classmethod 341 def identifier(cls, identifier: str) -> Token: 342 """Returns an IDENTIFIER token with `identifier` as its text.""" 343 return cls(TokenType.IDENTIFIER, identifier) 344 345 @classmethod 346 def var(cls, var: str) -> Token: 347 """Returns an VAR token with `var` as its text.""" 348 return cls(TokenType.VAR, var) 349 350 def __init__( 351 self, 352 token_type: TokenType, 353 text: str, 354 line: int = 1, 355 col: int = 1, 356 end: int = 0, 357 comments: t.List[str] = [], 358 ) -> None: 359 self.token_type = token_type 360 self.text = text 361 self.line = line 362 size = len(text) 363 self.col = col 364 self.end = end if end else size 365 self.comments = comments 366 367 @property 368 def start(self) -> int: 369 """Returns the start of the token.""" 370 return self.end - len(self.text) 371 372 def __repr__(self) -> str: 373 attributes = ", ".join(f"{k}: {getattr(self, k)}" for k in self.__slots__) 374 return f"<Token {attributes}>" 375 376 377class _Tokenizer(type): 378 def __new__(cls, clsname, bases, attrs): 379 klass = super().__new__(cls, clsname, bases, attrs) 380 381 klass._QUOTES = { 382 f"{prefix}{s}": e 383 for s, e in cls._delimeter_list_to_dict(klass.QUOTES).items() 384 for prefix in (("",) if s[0].isalpha() else ("", "n", "N")) 385 } 386 klass._BIT_STRINGS = cls._delimeter_list_to_dict(klass.BIT_STRINGS) 387 klass._HEX_STRINGS = cls._delimeter_list_to_dict(klass.HEX_STRINGS) 388 klass._BYTE_STRINGS = cls._delimeter_list_to_dict(klass.BYTE_STRINGS) 389 klass._IDENTIFIERS = cls._delimeter_list_to_dict(klass.IDENTIFIERS) 390 klass._STRING_ESCAPES = set(klass.STRING_ESCAPES) 391 klass._IDENTIFIER_ESCAPES = set(klass.IDENTIFIER_ESCAPES) 392 klass._COMMENTS = dict( 393 (comment, None) if isinstance(comment, str) else (comment[0], comment[1]) 394 for comment in klass.COMMENTS 395 ) 396 397 klass.KEYWORD_TRIE = new_trie( 398 key.upper() 399 for key in { 400 **klass.KEYWORDS, 401 **{comment: TokenType.COMMENT for comment in klass._COMMENTS}, 402 **{quote: TokenType.QUOTE for quote in klass._QUOTES}, 403 **{bit_string: TokenType.BIT_STRING for bit_string in klass._BIT_STRINGS}, 404 **{hex_string: TokenType.HEX_STRING for hex_string in klass._HEX_STRINGS}, 405 **{byte_string: TokenType.BYTE_STRING for byte_string in klass._BYTE_STRINGS}, 406 } 407 if " " in key or any(single in key for single in klass.SINGLE_TOKENS) 408 ) 409 410 return klass 411 412 @staticmethod 413 def _delimeter_list_to_dict(list: t.List[str | t.Tuple[str, str]]) -> t.Dict[str, str]: 414 return dict((item, item) if isinstance(item, str) else (item[0], item[1]) for item in list) 415 416 417class Tokenizer(metaclass=_Tokenizer): 418 SINGLE_TOKENS = { 419 "(": TokenType.L_PAREN, 420 ")": TokenType.R_PAREN, 421 "[": TokenType.L_BRACKET, 422 "]": TokenType.R_BRACKET, 423 "{": TokenType.L_BRACE, 424 "}": TokenType.R_BRACE, 425 "&": TokenType.AMP, 426 "^": TokenType.CARET, 427 ":": TokenType.COLON, 428 ",": TokenType.COMMA, 429 ".": TokenType.DOT, 430 "-": TokenType.DASH, 431 "=": TokenType.EQ, 432 ">": TokenType.GT, 433 "<": TokenType.LT, 434 "%": TokenType.MOD, 435 "!": TokenType.NOT, 436 "|": TokenType.PIPE, 437 "+": TokenType.PLUS, 438 ";": TokenType.SEMICOLON, 439 "/": TokenType.SLASH, 440 "\\": TokenType.BACKSLASH, 441 "*": TokenType.STAR, 442 "~": TokenType.TILDA, 443 "?": TokenType.PLACEHOLDER, 444 "@": TokenType.PARAMETER, 445 # used for breaking a var like x'y' but nothing else 446 # the token type doesn't matter 447 "'": TokenType.QUOTE, 448 "`": TokenType.IDENTIFIER, 449 '"': TokenType.IDENTIFIER, 450 "#": TokenType.HASH, 451 } 452 453 BIT_STRINGS: t.List[str | t.Tuple[str, str]] = [] 454 BYTE_STRINGS: t.List[str | t.Tuple[str, str]] = [] 455 HEX_STRINGS: t.List[str | t.Tuple[str, str]] = [] 456 IDENTIFIERS: t.List[str | t.Tuple[str, str]] = ['"'] 457 IDENTIFIER_ESCAPES = ['"'] 458 QUOTES: t.List[t.Tuple[str, str] | str] = ["'"] 459 STRING_ESCAPES = ["'"] 460 VAR_SINGLE_TOKENS: t.Set[str] = set() 461 462 _COMMENTS: t.Dict[str, str] = {} 463 _BIT_STRINGS: t.Dict[str, str] = {} 464 _BYTE_STRINGS: t.Dict[str, str] = {} 465 _HEX_STRINGS: t.Dict[str, str] = {} 466 _IDENTIFIERS: t.Dict[str, str] = {} 467 _IDENTIFIER_ESCAPES: t.Set[str] = set() 468 _QUOTES: t.Dict[str, str] = {} 469 _STRING_ESCAPES: t.Set[str] = set() 470 471 KEYWORDS: t.Dict[t.Optional[str], TokenType] = { 472 **{f"{{%{postfix}": TokenType.BLOCK_START for postfix in ("", "+", "-")}, 473 **{f"{prefix}%}}": TokenType.BLOCK_END for prefix in ("", "+", "-")}, 474 "{{+": TokenType.BLOCK_START, 475 "{{-": TokenType.BLOCK_START, 476 "+}}": TokenType.BLOCK_END, 477 "-}}": TokenType.BLOCK_END, 478 "/*+": TokenType.HINT, 479 "==": TokenType.EQ, 480 "::": TokenType.DCOLON, 481 "||": TokenType.DPIPE, 482 ">=": TokenType.GTE, 483 "<=": TokenType.LTE, 484 "<>": TokenType.NEQ, 485 "!=": TokenType.NEQ, 486 "<=>": TokenType.NULLSAFE_EQ, 487 "->": TokenType.ARROW, 488 "->>": TokenType.DARROW, 489 "=>": TokenType.FARROW, 490 "#>": TokenType.HASH_ARROW, 491 "#>>": TokenType.DHASH_ARROW, 492 "<->": TokenType.LR_ARROW, 493 "&&": TokenType.DAMP, 494 "ALL": TokenType.ALL, 495 "ALWAYS": TokenType.ALWAYS, 496 "AND": TokenType.AND, 497 "ANTI": TokenType.ANTI, 498 "ANY": TokenType.ANY, 499 "ASC": TokenType.ASC, 500 "AS": TokenType.ALIAS, 501 "AT TIME ZONE": TokenType.AT_TIME_ZONE, 502 "AUTOINCREMENT": TokenType.AUTO_INCREMENT, 503 "AUTO_INCREMENT": TokenType.AUTO_INCREMENT, 504 "BEGIN": TokenType.BEGIN, 505 "BETWEEN": TokenType.BETWEEN, 506 "BOTH": TokenType.BOTH, 507 "BUCKET": TokenType.BUCKET, 508 "BY DEFAULT": TokenType.BY_DEFAULT, 509 "CACHE": TokenType.CACHE, 510 "UNCACHE": TokenType.UNCACHE, 511 "CASE": TokenType.CASE, 512 "CASCADE": TokenType.CASCADE, 513 "CHARACTER SET": TokenType.CHARACTER_SET, 514 "CLUSTER BY": TokenType.CLUSTER_BY, 515 "COLLATE": TokenType.COLLATE, 516 "COLUMN": TokenType.COLUMN, 517 "COMMIT": TokenType.COMMIT, 518 "COMPOUND": TokenType.COMPOUND, 519 "CONSTRAINT": TokenType.CONSTRAINT, 520 "CREATE": TokenType.CREATE, 521 "CROSS": TokenType.CROSS, 522 "CUBE": TokenType.CUBE, 523 "CURRENT_DATE": TokenType.CURRENT_DATE, 524 "CURRENT ROW": TokenType.CURRENT_ROW, 525 "CURRENT_TIME": TokenType.CURRENT_TIME, 526 "CURRENT_TIMESTAMP": TokenType.CURRENT_TIMESTAMP, 527 "CURRENT_USER": TokenType.CURRENT_USER, 528 "DATABASE": TokenType.DATABASE, 529 "DEFAULT": TokenType.DEFAULT, 530 "DELETE": TokenType.DELETE, 531 "DESC": TokenType.DESC, 532 "DESCRIBE": TokenType.DESCRIBE, 533 "DISTINCT": TokenType.DISTINCT, 534 "DISTINCT FROM": TokenType.DISTINCT_FROM, 535 "DISTRIBUTE BY": TokenType.DISTRIBUTE_BY, 536 "DIV": TokenType.DIV, 537 "DROP": TokenType.DROP, 538 "ELSE": TokenType.ELSE, 539 "END": TokenType.END, 540 "ESCAPE": TokenType.ESCAPE, 541 "EXCEPT": TokenType.EXCEPT, 542 "EXECUTE": TokenType.EXECUTE, 543 "EXISTS": TokenType.EXISTS, 544 "FALSE": TokenType.FALSE, 545 "FETCH": TokenType.FETCH, 546 "FILTER": TokenType.FILTER, 547 "FIRST": TokenType.FIRST, 548 "FULL": TokenType.FULL, 549 "FUNCTION": TokenType.FUNCTION, 550 "FOLLOWING": TokenType.FOLLOWING, 551 "FOR": TokenType.FOR, 552 "FOREIGN KEY": TokenType.FOREIGN_KEY, 553 "FORMAT": TokenType.FORMAT, 554 "FROM": TokenType.FROM, 555 "GEOGRAPHY": TokenType.GEOGRAPHY, 556 "GEOMETRY": TokenType.GEOMETRY, 557 "GLOB": TokenType.GLOB, 558 "GROUP BY": TokenType.GROUP_BY, 559 "GROUPING SETS": TokenType.GROUPING_SETS, 560 "HAVING": TokenType.HAVING, 561 "IF": TokenType.IF, 562 "ILIKE": TokenType.ILIKE, 563 "IGNORE NULLS": TokenType.IGNORE_NULLS, 564 "IN": TokenType.IN, 565 "INDEX": TokenType.INDEX, 566 "INET": TokenType.INET, 567 "INNER": TokenType.INNER, 568 "INSERT": TokenType.INSERT, 569 "INTERVAL": TokenType.INTERVAL, 570 "INTERSECT": TokenType.INTERSECT, 571 "INTO": TokenType.INTO, 572 "IS": TokenType.IS, 573 "ISNULL": TokenType.ISNULL, 574 "JOIN": TokenType.JOIN, 575 "KEEP": TokenType.KEEP, 576 "LATERAL": TokenType.LATERAL, 577 "LAZY": TokenType.LAZY, 578 "LEADING": TokenType.LEADING, 579 "LEFT": TokenType.LEFT, 580 "LIKE": TokenType.LIKE, 581 "LIMIT": TokenType.LIMIT, 582 "LOAD DATA": TokenType.LOAD_DATA, 583 "LOCAL": TokenType.LOCAL, 584 "LOCK": TokenType.LOCK, 585 "MATERIALIZED": TokenType.MATERIALIZED, 586 "MERGE": TokenType.MERGE, 587 "NATURAL": TokenType.NATURAL, 588 "NEXT": TokenType.NEXT, 589 "NEXT VALUE FOR": TokenType.NEXT_VALUE_FOR, 590 "NO ACTION": TokenType.NO_ACTION, 591 "NOT": TokenType.NOT, 592 "NOTNULL": TokenType.NOTNULL, 593 "NULL": TokenType.NULL, 594 "NULLS FIRST": TokenType.NULLS_FIRST, 595 "NULLS LAST": TokenType.NULLS_LAST, 596 "OBJECT": TokenType.OBJECT, 597 "OFFSET": TokenType.OFFSET, 598 "ON": TokenType.ON, 599 "ONLY": TokenType.ONLY, 600 "OPTIONS": TokenType.OPTIONS, 601 "OR": TokenType.OR, 602 "ORDER BY": TokenType.ORDER_BY, 603 "ORDINALITY": TokenType.ORDINALITY, 604 "OUTER": TokenType.OUTER, 605 "OUT OF": TokenType.OUT_OF, 606 "OVER": TokenType.OVER, 607 "OVERLAPS": TokenType.OVERLAPS, 608 "OVERWRITE": TokenType.OVERWRITE, 609 "PARTITION": TokenType.PARTITION, 610 "PARTITION BY": TokenType.PARTITION_BY, 611 "PARTITIONED BY": TokenType.PARTITION_BY, 612 "PARTITIONED_BY": TokenType.PARTITION_BY, 613 "PERCENT": TokenType.PERCENT, 614 "PIVOT": TokenType.PIVOT, 615 "PRAGMA": TokenType.PRAGMA, 616 "PRECEDING": TokenType.PRECEDING, 617 "PRIMARY KEY": TokenType.PRIMARY_KEY, 618 "PROCEDURE": TokenType.PROCEDURE, 619 "QUALIFY": TokenType.QUALIFY, 620 "RANGE": TokenType.RANGE, 621 "RECURSIVE": TokenType.RECURSIVE, 622 "REGEXP": TokenType.RLIKE, 623 "REPLACE": TokenType.REPLACE, 624 "RESPECT NULLS": TokenType.RESPECT_NULLS, 625 "REFERENCES": TokenType.REFERENCES, 626 "RIGHT": TokenType.RIGHT, 627 "RLIKE": TokenType.RLIKE, 628 "ROLLBACK": TokenType.ROLLBACK, 629 "ROLLUP": TokenType.ROLLUP, 630 "ROW": TokenType.ROW, 631 "ROWS": TokenType.ROWS, 632 "SCHEMA": TokenType.SCHEMA, 633 "SEED": TokenType.SEED, 634 "SELECT": TokenType.SELECT, 635 "SEMI": TokenType.SEMI, 636 "SET": TokenType.SET, 637 "SETTINGS": TokenType.SETTINGS, 638 "SHOW": TokenType.SHOW, 639 "SIMILAR TO": TokenType.SIMILAR_TO, 640 "SOME": TokenType.SOME, 641 "SORTKEY": TokenType.SORTKEY, 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 "TRAILING": TokenType.TRAILING, 650 "UNBOUNDED": TokenType.UNBOUNDED, 651 "UNION": TokenType.UNION, 652 "UNLOGGED": TokenType.UNLOGGED, 653 "UNNEST": TokenType.UNNEST, 654 "UNPIVOT": TokenType.UNPIVOT, 655 "UPDATE": TokenType.UPDATE, 656 "USE": TokenType.USE, 657 "USING": TokenType.USING, 658 "UUID": TokenType.UUID, 659 "VALUES": TokenType.VALUES, 660 "VIEW": TokenType.VIEW, 661 "VOLATILE": TokenType.VOLATILE, 662 "WHEN": TokenType.WHEN, 663 "WHERE": TokenType.WHERE, 664 "WINDOW": TokenType.WINDOW, 665 "WITH": TokenType.WITH, 666 "WITH TIME ZONE": TokenType.WITH_TIME_ZONE, 667 "WITH LOCAL TIME ZONE": TokenType.WITH_LOCAL_TIME_ZONE, 668 "WITHIN GROUP": TokenType.WITHIN_GROUP, 669 "WITHOUT TIME ZONE": TokenType.WITHOUT_TIME_ZONE, 670 "APPLY": TokenType.APPLY, 671 "ARRAY": TokenType.ARRAY, 672 "BIT": TokenType.BIT, 673 "BOOL": TokenType.BOOLEAN, 674 "BOOLEAN": TokenType.BOOLEAN, 675 "BYTE": TokenType.TINYINT, 676 "TINYINT": TokenType.TINYINT, 677 "SHORT": TokenType.SMALLINT, 678 "SMALLINT": TokenType.SMALLINT, 679 "INT2": TokenType.SMALLINT, 680 "INTEGER": TokenType.INT, 681 "INT": TokenType.INT, 682 "INT4": TokenType.INT, 683 "LONG": TokenType.BIGINT, 684 "BIGINT": TokenType.BIGINT, 685 "INT8": TokenType.BIGINT, 686 "DEC": TokenType.DECIMAL, 687 "DECIMAL": TokenType.DECIMAL, 688 "BIGDECIMAL": TokenType.BIGDECIMAL, 689 "BIGNUMERIC": TokenType.BIGDECIMAL, 690 "MAP": TokenType.MAP, 691 "NULLABLE": TokenType.NULLABLE, 692 "NUMBER": TokenType.DECIMAL, 693 "NUMERIC": TokenType.DECIMAL, 694 "FIXED": TokenType.DECIMAL, 695 "REAL": TokenType.FLOAT, 696 "FLOAT": TokenType.FLOAT, 697 "FLOAT4": TokenType.FLOAT, 698 "FLOAT8": TokenType.DOUBLE, 699 "DOUBLE": TokenType.DOUBLE, 700 "DOUBLE PRECISION": TokenType.DOUBLE, 701 "JSON": TokenType.JSON, 702 "CHAR": TokenType.CHAR, 703 "CHARACTER": TokenType.CHAR, 704 "NCHAR": TokenType.NCHAR, 705 "VARCHAR": TokenType.VARCHAR, 706 "VARCHAR2": TokenType.VARCHAR, 707 "NVARCHAR": TokenType.NVARCHAR, 708 "NVARCHAR2": TokenType.NVARCHAR, 709 "STR": TokenType.TEXT, 710 "STRING": TokenType.TEXT, 711 "TEXT": TokenType.TEXT, 712 "CLOB": TokenType.TEXT, 713 "LONGVARCHAR": TokenType.TEXT, 714 "BINARY": TokenType.BINARY, 715 "BLOB": TokenType.VARBINARY, 716 "BYTEA": TokenType.VARBINARY, 717 "VARBINARY": TokenType.VARBINARY, 718 "TIME": TokenType.TIME, 719 "TIMESTAMP": TokenType.TIMESTAMP, 720 "TIMESTAMPTZ": TokenType.TIMESTAMPTZ, 721 "TIMESTAMPLTZ": TokenType.TIMESTAMPLTZ, 722 "DATE": TokenType.DATE, 723 "DATETIME": TokenType.DATETIME, 724 "UNIQUE": TokenType.UNIQUE, 725 "STRUCT": TokenType.STRUCT, 726 "VARIANT": TokenType.VARIANT, 727 "ALTER": TokenType.ALTER, 728 "ALTER AGGREGATE": TokenType.COMMAND, 729 "ALTER DEFAULT": TokenType.COMMAND, 730 "ALTER DOMAIN": TokenType.COMMAND, 731 "ALTER ROLE": TokenType.COMMAND, 732 "ALTER RULE": TokenType.COMMAND, 733 "ALTER SEQUENCE": TokenType.COMMAND, 734 "ALTER TYPE": TokenType.COMMAND, 735 "ALTER USER": TokenType.COMMAND, 736 "ALTER VIEW": TokenType.COMMAND, 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 } 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 KEYWORD_TRIE: t.Dict = {} # autofilled 772 773 IDENTIFIER_CAN_START_WITH_DIGIT = False 774 775 __slots__ = ( 776 "sql", 777 "size", 778 "tokens", 779 "_start", 780 "_current", 781 "_line", 782 "_col", 783 "_comments", 784 "_char", 785 "_end", 786 "_peek", 787 "_prev_token_line", 788 ) 789 790 def __init__(self) -> None: 791 self.reset() 792 793 def reset(self) -> None: 794 self.sql = "" 795 self.size = 0 796 self.tokens: t.List[Token] = [] 797 self._start = 0 798 self._current = 0 799 self._line = 1 800 self._col = 1 801 self._comments: t.List[str] = [] 802 803 self._char = "" 804 self._end = False 805 self._peek = "" 806 self._prev_token_line = -1 807 808 def tokenize(self, sql: str) -> t.List[Token]: 809 """Returns a list of tokens corresponding to the SQL string `sql`.""" 810 self.reset() 811 self.sql = sql 812 self.size = len(sql) 813 try: 814 self._scan() 815 except Exception as e: 816 start = self._current - 50 817 end = self._current + 50 818 start = start if start > 0 else 0 819 end = end if end < self.size else self.size - 1 820 context = self.sql[start:end] 821 raise ValueError(f"Error tokenizing '{context}'") from e 822 823 return self.tokens 824 825 def _scan(self, until: t.Optional[t.Callable] = None) -> None: 826 while self.size and not self._end: 827 self._start = self._current 828 self._advance() 829 830 if self._char is None: 831 break 832 833 if self._char not in self.WHITE_SPACE: 834 if self._char.isdigit(): 835 self._scan_number() 836 elif self._char in self._IDENTIFIERS: 837 self._scan_identifier(self._IDENTIFIERS[self._char]) 838 else: 839 self._scan_keywords() 840 841 if until and until(): 842 break 843 844 if self.tokens: 845 self.tokens[-1].comments.extend(self._comments) 846 847 def _chars(self, size: int) -> str: 848 if size == 1: 849 return self._char 850 start = self._current - 1 851 end = start + size 852 if end <= self.size: 853 return self.sql[start:end] 854 return "" 855 856 def _advance(self, i: int = 1, alnum: bool = False) -> None: 857 if self.WHITE_SPACE.get(self._char) is TokenType.BREAK: 858 self._col = 1 859 self._line += 1 860 else: 861 self._col += i 862 863 self._current += i 864 self._end = self._current >= self.size 865 self._char = self.sql[self._current - 1] 866 self._peek = "" if self._end else self.sql[self._current] 867 868 if alnum and self._char.isalnum(): 869 _col = self._col 870 _current = self._current 871 _end = self._end 872 _peek = self._peek 873 874 while _peek.isalnum(): 875 _col += 1 876 _current += 1 877 _end = _current >= self.size 878 _peek = "" if _end else self.sql[_current] 879 880 self._col = _col 881 self._current = _current 882 self._end = _end 883 self._peek = _peek 884 self._char = self.sql[_current - 1] 885 886 @property 887 def _text(self) -> str: 888 return self.sql[self._start : self._current] 889 890 def _add(self, token_type: TokenType, text: t.Optional[str] = None) -> None: 891 self._prev_token_line = self._line 892 self.tokens.append( 893 Token( 894 token_type, 895 self._text if text is None else text, 896 self._line, 897 self._col, 898 self._current, 899 self._comments, 900 ) 901 ) 902 self._comments = [] 903 904 # If we have either a semicolon or a begin token before the command's token, we'll parse 905 # whatever follows the command's token as a string 906 if ( 907 token_type in self.COMMANDS 908 and self._peek != ";" 909 and (len(self.tokens) == 1 or self.tokens[-2].token_type in self.COMMAND_PREFIX_TOKENS) 910 ): 911 start = self._current 912 tokens = len(self.tokens) 913 self._scan(lambda: self._peek == ";") 914 self.tokens = self.tokens[:tokens] 915 text = self.sql[start : self._current].strip() 916 if text: 917 self._add(TokenType.STRING, text) 918 919 def _scan_keywords(self) -> None: 920 size = 0 921 word = None 922 chars = self._text 923 char = chars 924 prev_space = False 925 skip = False 926 trie = self.KEYWORD_TRIE 927 single_token = char in self.SINGLE_TOKENS 928 929 while chars: 930 if skip: 931 result = 1 932 else: 933 result, trie = in_trie(trie, char.upper()) 934 935 if result == 0: 936 break 937 if result == 2: 938 word = chars 939 940 size += 1 941 end = self._current - 1 + size 942 943 if end < self.size: 944 char = self.sql[end] 945 single_token = single_token or char in self.SINGLE_TOKENS 946 is_space = char in self.WHITE_SPACE 947 948 if not is_space or not prev_space: 949 if is_space: 950 char = " " 951 chars += char 952 prev_space = is_space 953 skip = False 954 else: 955 skip = True 956 else: 957 char = "" 958 chars = " " 959 960 word = None if not single_token and chars[-1] not in self.WHITE_SPACE else word 961 962 if not word: 963 if self._char in self.SINGLE_TOKENS: 964 self._add(self.SINGLE_TOKENS[self._char], text=self._char) 965 return 966 self._scan_var() 967 return 968 969 if self._scan_string(word): 970 return 971 if self._scan_formatted_string(word): 972 return 973 if self._scan_comment(word): 974 return 975 976 self._advance(size - 1) 977 word = word.upper() 978 self._add(self.KEYWORDS[word], text=word) 979 980 def _scan_comment(self, comment_start: str) -> bool: 981 if comment_start not in self._COMMENTS: 982 return False 983 984 comment_start_line = self._line 985 comment_start_size = len(comment_start) 986 comment_end = self._COMMENTS[comment_start] 987 988 if comment_end: 989 # Skip the comment's start delimiter 990 self._advance(comment_start_size) 991 992 comment_end_size = len(comment_end) 993 while not self._end and self._chars(comment_end_size) != comment_end: 994 self._advance(alnum=True) 995 996 self._comments.append(self._text[comment_start_size : -comment_end_size + 1]) 997 self._advance(comment_end_size - 1) 998 else: 999 while not self._end and not self.WHITE_SPACE.get(self._peek) is TokenType.BREAK: 1000 self._advance(alnum=True) 1001 self._comments.append(self._text[comment_start_size:]) 1002 1003 # Leading comment is attached to the succeeding token, whilst trailing comment to the preceding. 1004 # Multiple consecutive comments are preserved by appending them to the current comments list. 1005 if comment_start_line == self._prev_token_line: 1006 self.tokens[-1].comments.extend(self._comments) 1007 self._comments = [] 1008 self._prev_token_line = self._line 1009 1010 return True 1011 1012 def _scan_number(self) -> None: 1013 if self._char == "0": 1014 peek = self._peek.upper() 1015 if peek == "B": 1016 return self._scan_bits() if self._BIT_STRINGS else self._add(TokenType.NUMBER) 1017 elif peek == "X": 1018 return self._scan_hex() if self._HEX_STRINGS else self._add(TokenType.NUMBER) 1019 1020 decimal = False 1021 scientific = 0 1022 1023 while True: 1024 if self._peek.isdigit(): 1025 self._advance() 1026 elif self._peek == "." and not decimal: 1027 decimal = True 1028 self._advance() 1029 elif self._peek in ("-", "+") and scientific == 1: 1030 scientific += 1 1031 self._advance() 1032 elif self._peek.upper() == "E" and not scientific: 1033 scientific += 1 1034 self._advance() 1035 elif self._peek.isidentifier(): 1036 number_text = self._text 1037 literal = "" 1038 1039 while self._peek.strip() and self._peek not in self.SINGLE_TOKENS: 1040 literal += self._peek.upper() 1041 self._advance() 1042 1043 token_type = self.KEYWORDS.get(self.NUMERIC_LITERALS.get(literal)) 1044 1045 if token_type: 1046 self._add(TokenType.NUMBER, number_text) 1047 self._add(TokenType.DCOLON, "::") 1048 return self._add(token_type, literal) 1049 elif self.IDENTIFIER_CAN_START_WITH_DIGIT: 1050 return self._add(TokenType.VAR) 1051 1052 self._add(TokenType.NUMBER, number_text) 1053 return self._advance(-len(literal)) 1054 else: 1055 return self._add(TokenType.NUMBER) 1056 1057 def _scan_bits(self) -> None: 1058 self._advance() 1059 value = self._extract_value() 1060 try: 1061 # If `value` can't be converted to a binary, fallback to tokenizing it as an identifier 1062 int(value, 2) 1063 self._add(TokenType.BIT_STRING, value[2:]) # Drop the 0b 1064 except ValueError: 1065 self._add(TokenType.IDENTIFIER) 1066 1067 def _scan_hex(self) -> None: 1068 self._advance() 1069 value = self._extract_value() 1070 try: 1071 # If `value` can't be converted to a hex, fallback to tokenizing it as an identifier 1072 int(value, 16) 1073 self._add(TokenType.HEX_STRING, value[2:]) # Drop the 0x 1074 except ValueError: 1075 self._add(TokenType.IDENTIFIER) 1076 1077 def _extract_value(self) -> str: 1078 while True: 1079 char = self._peek.strip() 1080 if char and char not in self.SINGLE_TOKENS: 1081 self._advance(alnum=True) 1082 else: 1083 break 1084 1085 return self._text 1086 1087 def _scan_string(self, quote: str) -> bool: 1088 quote_end = self._QUOTES.get(quote) 1089 if quote_end is None: 1090 return False 1091 1092 self._advance(len(quote)) 1093 text = self._extract_string(quote_end) 1094 text = text.encode(self.ENCODE).decode(self.ENCODE) if self.ENCODE else text 1095 self._add(TokenType.NATIONAL if quote[0].upper() == "N" else TokenType.STRING, text) 1096 return True 1097 1098 # X'1234', b'0110', E'\\\\\' etc. 1099 def _scan_formatted_string(self, string_start: str) -> bool: 1100 if string_start in self._HEX_STRINGS: 1101 delimiters = self._HEX_STRINGS 1102 token_type = TokenType.HEX_STRING 1103 base = 16 1104 elif string_start in self._BIT_STRINGS: 1105 delimiters = self._BIT_STRINGS 1106 token_type = TokenType.BIT_STRING 1107 base = 2 1108 elif string_start in self._BYTE_STRINGS: 1109 delimiters = self._BYTE_STRINGS 1110 token_type = TokenType.BYTE_STRING 1111 base = None 1112 else: 1113 return False 1114 1115 self._advance(len(string_start)) 1116 string_end = delimiters[string_start] 1117 text = self._extract_string(string_end) 1118 1119 if base: 1120 try: 1121 int(text, base) 1122 except: 1123 raise RuntimeError( 1124 f"Numeric string contains invalid characters from {self._line}:{self._start}" 1125 ) 1126 1127 self._add(token_type, text) 1128 return True 1129 1130 def _scan_identifier(self, identifier_end: str) -> None: 1131 self._advance() 1132 text = self._extract_string(identifier_end, self._IDENTIFIER_ESCAPES) 1133 self._add(TokenType.IDENTIFIER, text) 1134 1135 def _scan_var(self) -> None: 1136 while True: 1137 char = self._peek.strip() 1138 if char and (char in self.VAR_SINGLE_TOKENS or char not in self.SINGLE_TOKENS): 1139 self._advance(alnum=True) 1140 else: 1141 break 1142 1143 self._add( 1144 TokenType.VAR 1145 if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER 1146 else self.KEYWORDS.get(self._text.upper(), TokenType.VAR) 1147 ) 1148 1149 def _extract_string(self, delimiter: str, escapes=None) -> str: 1150 text = "" 1151 delim_size = len(delimiter) 1152 escapes = self._STRING_ESCAPES if escapes is None else escapes 1153 1154 while True: 1155 if self._char in escapes and (self._peek == delimiter or self._peek in escapes): 1156 if self._peek == delimiter: 1157 text += self._peek 1158 else: 1159 text += self._char + self._peek 1160 1161 if self._current + 1 < self.size: 1162 self._advance(2) 1163 else: 1164 raise RuntimeError(f"Missing {delimiter} from {self._line}:{self._current}") 1165 else: 1166 if self._chars(delim_size) == delimiter: 1167 if delim_size > 1: 1168 self._advance(delim_size - 1) 1169 break 1170 1171 if self._end: 1172 raise RuntimeError(f"Missing {delimiter} from {self._line}:{self._start}") 1173 1174 current = self._current - 1 1175 self._advance(alnum=True) 1176 text += self.sql[current : self._current - 1] 1177 1178 return text
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 SEMICOLON = auto() 25 STAR = auto() 26 BACKSLASH = auto() 27 SLASH = auto() 28 LT = auto() 29 LTE = auto() 30 GT = auto() 31 GTE = auto() 32 NOT = auto() 33 EQ = auto() 34 NEQ = auto() 35 NULLSAFE_EQ = auto() 36 AND = auto() 37 OR = auto() 38 AMP = auto() 39 DPIPE = auto() 40 PIPE = auto() 41 CARET = auto() 42 TILDA = auto() 43 ARROW = auto() 44 DARROW = auto() 45 FARROW = auto() 46 HASH = auto() 47 HASH_ARROW = auto() 48 DHASH_ARROW = auto() 49 LR_ARROW = auto() 50 LT_AT = auto() 51 AT_GT = auto() 52 DOLLAR = auto() 53 PARAMETER = auto() 54 SESSION_PARAMETER = auto() 55 NATIONAL = auto() 56 DAMP = auto() 57 58 BLOCK_START = auto() 59 BLOCK_END = auto() 60 61 SPACE = auto() 62 BREAK = auto() 63 64 STRING = auto() 65 NUMBER = auto() 66 IDENTIFIER = auto() 67 DATABASE = auto() 68 COLUMN = auto() 69 COLUMN_DEF = auto() 70 SCHEMA = auto() 71 TABLE = auto() 72 VAR = auto() 73 BIT_STRING = auto() 74 HEX_STRING = auto() 75 BYTE_STRING = auto() 76 77 # types 78 BIT = auto() 79 BOOLEAN = auto() 80 TINYINT = auto() 81 UTINYINT = auto() 82 SMALLINT = auto() 83 USMALLINT = auto() 84 INT = auto() 85 UINT = auto() 86 BIGINT = auto() 87 UBIGINT = auto() 88 INT128 = auto() 89 UINT128 = auto() 90 INT256 = auto() 91 UINT256 = auto() 92 FLOAT = auto() 93 DOUBLE = auto() 94 DECIMAL = auto() 95 BIGDECIMAL = auto() 96 CHAR = auto() 97 NCHAR = auto() 98 VARCHAR = auto() 99 NVARCHAR = auto() 100 TEXT = auto() 101 MEDIUMTEXT = auto() 102 LONGTEXT = auto() 103 MEDIUMBLOB = auto() 104 LONGBLOB = auto() 105 BINARY = auto() 106 VARBINARY = auto() 107 JSON = auto() 108 JSONB = auto() 109 TIME = auto() 110 TIMESTAMP = auto() 111 TIMESTAMPTZ = auto() 112 TIMESTAMPLTZ = auto() 113 DATETIME = auto() 114 DATETIME64 = auto() 115 DATE = auto() 116 UUID = auto() 117 GEOGRAPHY = auto() 118 NULLABLE = auto() 119 GEOMETRY = auto() 120 HLLSKETCH = auto() 121 HSTORE = auto() 122 SUPER = auto() 123 SERIAL = auto() 124 SMALLSERIAL = auto() 125 BIGSERIAL = auto() 126 XML = auto() 127 UNIQUEIDENTIFIER = auto() 128 MONEY = auto() 129 SMALLMONEY = auto() 130 ROWVERSION = auto() 131 IMAGE = auto() 132 VARIANT = auto() 133 OBJECT = auto() 134 INET = auto() 135 136 # keywords 137 ALIAS = auto() 138 ALTER = auto() 139 ALWAYS = auto() 140 ALL = auto() 141 ANTI = auto() 142 ANY = auto() 143 APPLY = auto() 144 ARRAY = auto() 145 ASC = auto() 146 ASOF = auto() 147 AT_TIME_ZONE = auto() 148 AUTO_INCREMENT = auto() 149 BEGIN = auto() 150 BETWEEN = auto() 151 BOTH = auto() 152 BUCKET = auto() 153 BY_DEFAULT = auto() 154 CACHE = auto() 155 CASCADE = auto() 156 CASE = auto() 157 CHARACTER_SET = auto() 158 CLUSTER_BY = auto() 159 COLLATE = auto() 160 COMMAND = auto() 161 COMMENT = auto() 162 COMMIT = auto() 163 COMPOUND = auto() 164 CONSTRAINT = auto() 165 CREATE = auto() 166 CROSS = auto() 167 CUBE = auto() 168 CURRENT_DATE = auto() 169 CURRENT_DATETIME = auto() 170 CURRENT_ROW = auto() 171 CURRENT_TIME = auto() 172 CURRENT_TIMESTAMP = auto() 173 CURRENT_USER = auto() 174 DEFAULT = auto() 175 DELETE = auto() 176 DESC = auto() 177 DESCRIBE = auto() 178 DISTINCT = auto() 179 DISTINCT_FROM = auto() 180 DISTRIBUTE_BY = auto() 181 DIV = auto() 182 DROP = auto() 183 ELSE = auto() 184 END = auto() 185 ESCAPE = auto() 186 EXCEPT = auto() 187 EXECUTE = auto() 188 EXISTS = auto() 189 FALSE = auto() 190 FETCH = auto() 191 FILTER = auto() 192 FINAL = auto() 193 FIRST = auto() 194 FOLLOWING = auto() 195 FOR = auto() 196 FOREIGN_KEY = auto() 197 FORMAT = auto() 198 FROM = auto() 199 FULL = auto() 200 FUNCTION = auto() 201 GLOB = auto() 202 GLOBAL = auto() 203 GROUP_BY = auto() 204 GROUPING_SETS = auto() 205 HAVING = auto() 206 HINT = auto() 207 IF = auto() 208 IGNORE_NULLS = auto() 209 ILIKE = auto() 210 ILIKE_ANY = auto() 211 IN = auto() 212 INDEX = auto() 213 INNER = auto() 214 INSERT = auto() 215 INTERSECT = auto() 216 INTERVAL = auto() 217 INTO = auto() 218 INTRODUCER = auto() 219 IRLIKE = auto() 220 IS = auto() 221 ISNULL = auto() 222 JOIN = auto() 223 JOIN_MARKER = auto() 224 KEEP = auto() 225 LANGUAGE = auto() 226 LATERAL = auto() 227 LAZY = auto() 228 LEADING = auto() 229 LEFT = auto() 230 LIKE = auto() 231 LIKE_ANY = auto() 232 LIMIT = auto() 233 LOAD_DATA = auto() 234 LOCAL = auto() 235 LOCK = auto() 236 MAP = auto() 237 MATCH_RECOGNIZE = auto() 238 MATERIALIZED = auto() 239 MERGE = auto() 240 MOD = auto() 241 NATURAL = auto() 242 NEXT = auto() 243 NEXT_VALUE_FOR = auto() 244 NO_ACTION = auto() 245 NOTNULL = auto() 246 NULL = auto() 247 NULLS_FIRST = auto() 248 NULLS_LAST = auto() 249 OFFSET = auto() 250 ON = auto() 251 ONLY = auto() 252 OPTIONS = auto() 253 ORDER_BY = auto() 254 ORDERED = auto() 255 ORDINALITY = auto() 256 OUTER = auto() 257 OUT_OF = auto() 258 OVER = auto() 259 OVERLAPS = auto() 260 OVERWRITE = auto() 261 PARTITION = auto() 262 PARTITION_BY = auto() 263 PERCENT = auto() 264 PIVOT = auto() 265 PLACEHOLDER = auto() 266 PRAGMA = auto() 267 PRECEDING = auto() 268 PRIMARY_KEY = auto() 269 PROCEDURE = auto() 270 PROPERTIES = auto() 271 PSEUDO_TYPE = auto() 272 QUALIFY = auto() 273 QUOTE = auto() 274 RANGE = auto() 275 RECURSIVE = auto() 276 REPLACE = auto() 277 RESPECT_NULLS = auto() 278 RETURNING = auto() 279 REFERENCES = auto() 280 RIGHT = auto() 281 RLIKE = auto() 282 ROLLBACK = auto() 283 ROLLUP = auto() 284 ROW = auto() 285 ROWS = auto() 286 SEED = auto() 287 SELECT = auto() 288 SEMI = auto() 289 SEPARATOR = auto() 290 SERDE_PROPERTIES = auto() 291 SET = auto() 292 SETTINGS = auto() 293 SHOW = auto() 294 SIMILAR_TO = auto() 295 SOME = auto() 296 SORTKEY = auto() 297 SORT_BY = auto() 298 STRUCT = auto() 299 TABLE_SAMPLE = auto() 300 TEMPORARY = auto() 301 TOP = auto() 302 THEN = auto() 303 TRAILING = auto() 304 TRUE = auto() 305 UNBOUNDED = auto() 306 UNCACHE = auto() 307 UNION = auto() 308 UNLOGGED = auto() 309 UNNEST = auto() 310 UNPIVOT = auto() 311 UPDATE = auto() 312 USE = auto() 313 USING = auto() 314 VALUES = auto() 315 VIEW = auto() 316 VOLATILE = auto() 317 WHEN = auto() 318 WHERE = auto() 319 WINDOW = auto() 320 WITH = auto() 321 WITH_TIME_ZONE = auto() 322 WITH_LOCAL_TIME_ZONE = auto() 323 WITHIN_GROUP = auto() 324 WITHOUT_TIME_ZONE = auto() 325 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'>
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'>
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'>
NATIONAL =
<TokenType.NATIONAL: 'NATIONAL'>
DAMP =
<TokenType.DAMP: 'DAMP'>
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'>
BIT =
<TokenType.BIT: 'BIT'>
BOOLEAN =
<TokenType.BOOLEAN: 'BOOLEAN'>
TINYINT =
<TokenType.TINYINT: 'TINYINT'>
UTINYINT =
<TokenType.UTINYINT: 'UTINYINT'>
SMALLINT =
<TokenType.SMALLINT: 'SMALLINT'>
USMALLINT =
<TokenType.USMALLINT: 'USMALLINT'>
INT =
<TokenType.INT: 'INT'>
UINT =
<TokenType.UINT: 'UINT'>
BIGINT =
<TokenType.BIGINT: 'BIGINT'>
UBIGINT =
<TokenType.UBIGINT: 'UBIGINT'>
INT128 =
<TokenType.INT128: 'INT128'>
UINT128 =
<TokenType.UINT128: 'UINT128'>
INT256 =
<TokenType.INT256: 'INT256'>
UINT256 =
<TokenType.UINT256: 'UINT256'>
FLOAT =
<TokenType.FLOAT: 'FLOAT'>
DOUBLE =
<TokenType.DOUBLE: 'DOUBLE'>
DECIMAL =
<TokenType.DECIMAL: 'DECIMAL'>
BIGDECIMAL =
<TokenType.BIGDECIMAL: 'BIGDECIMAL'>
CHAR =
<TokenType.CHAR: 'CHAR'>
NCHAR =
<TokenType.NCHAR: 'NCHAR'>
VARCHAR =
<TokenType.VARCHAR: 'VARCHAR'>
NVARCHAR =
<TokenType.NVARCHAR: 'NVARCHAR'>
TEXT =
<TokenType.TEXT: 'TEXT'>
MEDIUMTEXT =
<TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>
LONGTEXT =
<TokenType.LONGTEXT: 'LONGTEXT'>
MEDIUMBLOB =
<TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>
LONGBLOB =
<TokenType.LONGBLOB: 'LONGBLOB'>
BINARY =
<TokenType.BINARY: 'BINARY'>
VARBINARY =
<TokenType.VARBINARY: 'VARBINARY'>
JSON =
<TokenType.JSON: 'JSON'>
JSONB =
<TokenType.JSONB: 'JSONB'>
TIME =
<TokenType.TIME: 'TIME'>
TIMESTAMP =
<TokenType.TIMESTAMP: 'TIMESTAMP'>
TIMESTAMPTZ =
<TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>
TIMESTAMPLTZ =
<TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>
DATETIME =
<TokenType.DATETIME: 'DATETIME'>
DATETIME64 =
<TokenType.DATETIME64: 'DATETIME64'>
DATE =
<TokenType.DATE: 'DATE'>
UUID =
<TokenType.UUID: 'UUID'>
GEOGRAPHY =
<TokenType.GEOGRAPHY: 'GEOGRAPHY'>
NULLABLE =
<TokenType.NULLABLE: 'NULLABLE'>
GEOMETRY =
<TokenType.GEOMETRY: 'GEOMETRY'>
HLLSKETCH =
<TokenType.HLLSKETCH: 'HLLSKETCH'>
HSTORE =
<TokenType.HSTORE: 'HSTORE'>
SUPER =
<TokenType.SUPER: 'SUPER'>
SERIAL =
<TokenType.SERIAL: 'SERIAL'>
SMALLSERIAL =
<TokenType.SMALLSERIAL: 'SMALLSERIAL'>
BIGSERIAL =
<TokenType.BIGSERIAL: 'BIGSERIAL'>
XML =
<TokenType.XML: 'XML'>
UNIQUEIDENTIFIER =
<TokenType.UNIQUEIDENTIFIER: 'UNIQUEIDENTIFIER'>
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'>
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'>
AT_TIME_ZONE =
<TokenType.AT_TIME_ZONE: 'AT_TIME_ZONE'>
AUTO_INCREMENT =
<TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>
BEGIN =
<TokenType.BEGIN: 'BEGIN'>
BETWEEN =
<TokenType.BETWEEN: 'BETWEEN'>
BOTH =
<TokenType.BOTH: 'BOTH'>
BUCKET =
<TokenType.BUCKET: 'BUCKET'>
BY_DEFAULT =
<TokenType.BY_DEFAULT: 'BY_DEFAULT'>
CACHE =
<TokenType.CACHE: 'CACHE'>
CASCADE =
<TokenType.CASCADE: 'CASCADE'>
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'>
COMPOUND =
<TokenType.COMPOUND: 'COMPOUND'>
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_ROW =
<TokenType.CURRENT_ROW: 'CURRENT_ROW'>
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'>
DISTINCT =
<TokenType.DISTINCT: 'DISTINCT'>
DISTINCT_FROM =
<TokenType.DISTINCT_FROM: 'DISTINCT_FROM'>
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'>
FOLLOWING =
<TokenType.FOLLOWING: 'FOLLOWING'>
FOR =
<TokenType.FOR: 'FOR'>
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'>
IF =
<TokenType.IF: 'IF'>
IGNORE_NULLS =
<TokenType.IGNORE_NULLS: 'IGNORE_NULLS'>
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'>
LAZY =
<TokenType.LAZY: 'LAZY'>
LEADING =
<TokenType.LEADING: 'LEADING'>
LEFT =
<TokenType.LEFT: 'LEFT'>
LIKE =
<TokenType.LIKE: 'LIKE'>
LIKE_ANY =
<TokenType.LIKE_ANY: 'LIKE_ANY'>
LIMIT =
<TokenType.LIMIT: 'LIMIT'>
LOAD_DATA =
<TokenType.LOAD_DATA: 'LOAD_DATA'>
LOCAL =
<TokenType.LOCAL: 'LOCAL'>
LOCK =
<TokenType.LOCK: 'LOCK'>
MAP =
<TokenType.MAP: 'MAP'>
MATCH_RECOGNIZE =
<TokenType.MATCH_RECOGNIZE: 'MATCH_RECOGNIZE'>
MATERIALIZED =
<TokenType.MATERIALIZED: 'MATERIALIZED'>
MERGE =
<TokenType.MERGE: 'MERGE'>
MOD =
<TokenType.MOD: 'MOD'>
NATURAL =
<TokenType.NATURAL: 'NATURAL'>
NEXT =
<TokenType.NEXT: 'NEXT'>
NEXT_VALUE_FOR =
<TokenType.NEXT_VALUE_FOR: 'NEXT_VALUE_FOR'>
NO_ACTION =
<TokenType.NO_ACTION: 'NO_ACTION'>
NOTNULL =
<TokenType.NOTNULL: 'NOTNULL'>
NULL =
<TokenType.NULL: 'NULL'>
NULLS_FIRST =
<TokenType.NULLS_FIRST: 'NULLS_FIRST'>
NULLS_LAST =
<TokenType.NULLS_LAST: 'NULLS_LAST'>
OFFSET =
<TokenType.OFFSET: 'OFFSET'>
ON =
<TokenType.ON: 'ON'>
ONLY =
<TokenType.ONLY: 'ONLY'>
OPTIONS =
<TokenType.OPTIONS: 'OPTIONS'>
ORDER_BY =
<TokenType.ORDER_BY: 'ORDER_BY'>
ORDERED =
<TokenType.ORDERED: 'ORDERED'>
ORDINALITY =
<TokenType.ORDINALITY: 'ORDINALITY'>
OUTER =
<TokenType.OUTER: 'OUTER'>
OUT_OF =
<TokenType.OUT_OF: 'OUT_OF'>
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'>
PRECEDING =
<TokenType.PRECEDING: 'PRECEDING'>
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'>
RESPECT_NULLS =
<TokenType.RESPECT_NULLS: 'RESPECT_NULLS'>
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'>
SEED =
<TokenType.SEED: 'SEED'>
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'>
SORTKEY =
<TokenType.SORTKEY: 'SORTKEY'>
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'>
TRAILING =
<TokenType.TRAILING: 'TRAILING'>
TRUE =
<TokenType.TRUE: 'TRUE'>
UNBOUNDED =
<TokenType.UNBOUNDED: 'UNBOUNDED'>
UNCACHE =
<TokenType.UNCACHE: 'UNCACHE'>
UNION =
<TokenType.UNION: 'UNION'>
UNLOGGED =
<TokenType.UNLOGGED: 'UNLOGGED'>
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'>
WITH_TIME_ZONE =
<TokenType.WITH_TIME_ZONE: 'WITH_TIME_ZONE'>
WITH_LOCAL_TIME_ZONE =
<TokenType.WITH_LOCAL_TIME_ZONE: 'WITH_LOCAL_TIME_ZONE'>
WITHIN_GROUP =
<TokenType.WITHIN_GROUP: 'WITHIN_GROUP'>
WITHOUT_TIME_ZONE =
<TokenType.WITHOUT_TIME_ZONE: 'WITHOUT_TIME_ZONE'>
UNIQUE =
<TokenType.UNIQUE: 'UNIQUE'>
Inherited Members
- enum.Enum
- name
- value
class
Token:
328class Token: 329 __slots__ = ("token_type", "text", "line", "col", "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 end: int = 0, 358 comments: t.List[str] = [], 359 ) -> None: 360 self.token_type = token_type 361 self.text = text 362 self.line = line 363 size = len(text) 364 self.col = col 365 self.end = end if end else size 366 self.comments = comments 367 368 @property 369 def start(self) -> int: 370 """Returns the start of the token.""" 371 return self.end - len(self.text) 372 373 def __repr__(self) -> str: 374 attributes = ", ".join(f"{k}: {getattr(self, k)}" for k in self.__slots__) 375 return f"<Token {attributes}>"
Token( token_type: sqlglot.tokens.TokenType, text: str, line: int = 1, col: int = 1, end: int = 0, comments: List[str] = [])
351 def __init__( 352 self, 353 token_type: TokenType, 354 text: str, 355 line: int = 1, 356 col: int = 1, 357 end: int = 0, 358 comments: t.List[str] = [], 359 ) -> None: 360 self.token_type = token_type 361 self.text = text 362 self.line = line 363 size = len(text) 364 self.col = col 365 self.end = end if end else size 366 self.comments = comments
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))
Returns a NUMBER token with number
as its text.
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)
Returns a STRING token with string
as its text.
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)
Returns an IDENTIFIER token with identifier
as its text.
class
Tokenizer:
418class Tokenizer(metaclass=_Tokenizer): 419 SINGLE_TOKENS = { 420 "(": TokenType.L_PAREN, 421 ")": TokenType.R_PAREN, 422 "[": TokenType.L_BRACKET, 423 "]": TokenType.R_BRACKET, 424 "{": TokenType.L_BRACE, 425 "}": TokenType.R_BRACE, 426 "&": TokenType.AMP, 427 "^": TokenType.CARET, 428 ":": TokenType.COLON, 429 ",": TokenType.COMMA, 430 ".": TokenType.DOT, 431 "-": TokenType.DASH, 432 "=": TokenType.EQ, 433 ">": TokenType.GT, 434 "<": TokenType.LT, 435 "%": TokenType.MOD, 436 "!": TokenType.NOT, 437 "|": TokenType.PIPE, 438 "+": TokenType.PLUS, 439 ";": TokenType.SEMICOLON, 440 "/": TokenType.SLASH, 441 "\\": TokenType.BACKSLASH, 442 "*": TokenType.STAR, 443 "~": TokenType.TILDA, 444 "?": TokenType.PLACEHOLDER, 445 "@": TokenType.PARAMETER, 446 # used for breaking a var like x'y' but nothing else 447 # the token type doesn't matter 448 "'": TokenType.QUOTE, 449 "`": TokenType.IDENTIFIER, 450 '"': TokenType.IDENTIFIER, 451 "#": TokenType.HASH, 452 } 453 454 BIT_STRINGS: t.List[str | t.Tuple[str, str]] = [] 455 BYTE_STRINGS: t.List[str | t.Tuple[str, str]] = [] 456 HEX_STRINGS: t.List[str | t.Tuple[str, str]] = [] 457 IDENTIFIERS: t.List[str | t.Tuple[str, str]] = ['"'] 458 IDENTIFIER_ESCAPES = ['"'] 459 QUOTES: t.List[t.Tuple[str, str] | str] = ["'"] 460 STRING_ESCAPES = ["'"] 461 VAR_SINGLE_TOKENS: t.Set[str] = set() 462 463 _COMMENTS: t.Dict[str, str] = {} 464 _BIT_STRINGS: t.Dict[str, str] = {} 465 _BYTE_STRINGS: t.Dict[str, str] = {} 466 _HEX_STRINGS: t.Dict[str, str] = {} 467 _IDENTIFIERS: t.Dict[str, str] = {} 468 _IDENTIFIER_ESCAPES: t.Set[str] = set() 469 _QUOTES: t.Dict[str, str] = {} 470 _STRING_ESCAPES: t.Set[str] = set() 471 472 KEYWORDS: t.Dict[t.Optional[str], TokenType] = { 473 **{f"{{%{postfix}": TokenType.BLOCK_START for postfix in ("", "+", "-")}, 474 **{f"{prefix}%}}": TokenType.BLOCK_END for prefix in ("", "+", "-")}, 475 "{{+": TokenType.BLOCK_START, 476 "{{-": TokenType.BLOCK_START, 477 "+}}": TokenType.BLOCK_END, 478 "-}}": TokenType.BLOCK_END, 479 "/*+": TokenType.HINT, 480 "==": TokenType.EQ, 481 "::": TokenType.DCOLON, 482 "||": TokenType.DPIPE, 483 ">=": TokenType.GTE, 484 "<=": TokenType.LTE, 485 "<>": TokenType.NEQ, 486 "!=": TokenType.NEQ, 487 "<=>": TokenType.NULLSAFE_EQ, 488 "->": TokenType.ARROW, 489 "->>": TokenType.DARROW, 490 "=>": TokenType.FARROW, 491 "#>": TokenType.HASH_ARROW, 492 "#>>": TokenType.DHASH_ARROW, 493 "<->": TokenType.LR_ARROW, 494 "&&": TokenType.DAMP, 495 "ALL": TokenType.ALL, 496 "ALWAYS": TokenType.ALWAYS, 497 "AND": TokenType.AND, 498 "ANTI": TokenType.ANTI, 499 "ANY": TokenType.ANY, 500 "ASC": TokenType.ASC, 501 "AS": TokenType.ALIAS, 502 "AT TIME ZONE": TokenType.AT_TIME_ZONE, 503 "AUTOINCREMENT": TokenType.AUTO_INCREMENT, 504 "AUTO_INCREMENT": TokenType.AUTO_INCREMENT, 505 "BEGIN": TokenType.BEGIN, 506 "BETWEEN": TokenType.BETWEEN, 507 "BOTH": TokenType.BOTH, 508 "BUCKET": TokenType.BUCKET, 509 "BY DEFAULT": TokenType.BY_DEFAULT, 510 "CACHE": TokenType.CACHE, 511 "UNCACHE": TokenType.UNCACHE, 512 "CASE": TokenType.CASE, 513 "CASCADE": TokenType.CASCADE, 514 "CHARACTER SET": TokenType.CHARACTER_SET, 515 "CLUSTER BY": TokenType.CLUSTER_BY, 516 "COLLATE": TokenType.COLLATE, 517 "COLUMN": TokenType.COLUMN, 518 "COMMIT": TokenType.COMMIT, 519 "COMPOUND": TokenType.COMPOUND, 520 "CONSTRAINT": TokenType.CONSTRAINT, 521 "CREATE": TokenType.CREATE, 522 "CROSS": TokenType.CROSS, 523 "CUBE": TokenType.CUBE, 524 "CURRENT_DATE": TokenType.CURRENT_DATE, 525 "CURRENT ROW": TokenType.CURRENT_ROW, 526 "CURRENT_TIME": TokenType.CURRENT_TIME, 527 "CURRENT_TIMESTAMP": TokenType.CURRENT_TIMESTAMP, 528 "CURRENT_USER": TokenType.CURRENT_USER, 529 "DATABASE": TokenType.DATABASE, 530 "DEFAULT": TokenType.DEFAULT, 531 "DELETE": TokenType.DELETE, 532 "DESC": TokenType.DESC, 533 "DESCRIBE": TokenType.DESCRIBE, 534 "DISTINCT": TokenType.DISTINCT, 535 "DISTINCT FROM": TokenType.DISTINCT_FROM, 536 "DISTRIBUTE BY": TokenType.DISTRIBUTE_BY, 537 "DIV": TokenType.DIV, 538 "DROP": TokenType.DROP, 539 "ELSE": TokenType.ELSE, 540 "END": TokenType.END, 541 "ESCAPE": TokenType.ESCAPE, 542 "EXCEPT": TokenType.EXCEPT, 543 "EXECUTE": TokenType.EXECUTE, 544 "EXISTS": TokenType.EXISTS, 545 "FALSE": TokenType.FALSE, 546 "FETCH": TokenType.FETCH, 547 "FILTER": TokenType.FILTER, 548 "FIRST": TokenType.FIRST, 549 "FULL": TokenType.FULL, 550 "FUNCTION": TokenType.FUNCTION, 551 "FOLLOWING": TokenType.FOLLOWING, 552 "FOR": TokenType.FOR, 553 "FOREIGN KEY": TokenType.FOREIGN_KEY, 554 "FORMAT": TokenType.FORMAT, 555 "FROM": TokenType.FROM, 556 "GEOGRAPHY": TokenType.GEOGRAPHY, 557 "GEOMETRY": TokenType.GEOMETRY, 558 "GLOB": TokenType.GLOB, 559 "GROUP BY": TokenType.GROUP_BY, 560 "GROUPING SETS": TokenType.GROUPING_SETS, 561 "HAVING": TokenType.HAVING, 562 "IF": TokenType.IF, 563 "ILIKE": TokenType.ILIKE, 564 "IGNORE NULLS": TokenType.IGNORE_NULLS, 565 "IN": TokenType.IN, 566 "INDEX": TokenType.INDEX, 567 "INET": TokenType.INET, 568 "INNER": TokenType.INNER, 569 "INSERT": TokenType.INSERT, 570 "INTERVAL": TokenType.INTERVAL, 571 "INTERSECT": TokenType.INTERSECT, 572 "INTO": TokenType.INTO, 573 "IS": TokenType.IS, 574 "ISNULL": TokenType.ISNULL, 575 "JOIN": TokenType.JOIN, 576 "KEEP": TokenType.KEEP, 577 "LATERAL": TokenType.LATERAL, 578 "LAZY": TokenType.LAZY, 579 "LEADING": TokenType.LEADING, 580 "LEFT": TokenType.LEFT, 581 "LIKE": TokenType.LIKE, 582 "LIMIT": TokenType.LIMIT, 583 "LOAD DATA": TokenType.LOAD_DATA, 584 "LOCAL": TokenType.LOCAL, 585 "LOCK": TokenType.LOCK, 586 "MATERIALIZED": TokenType.MATERIALIZED, 587 "MERGE": TokenType.MERGE, 588 "NATURAL": TokenType.NATURAL, 589 "NEXT": TokenType.NEXT, 590 "NEXT VALUE FOR": TokenType.NEXT_VALUE_FOR, 591 "NO ACTION": TokenType.NO_ACTION, 592 "NOT": TokenType.NOT, 593 "NOTNULL": TokenType.NOTNULL, 594 "NULL": TokenType.NULL, 595 "NULLS FIRST": TokenType.NULLS_FIRST, 596 "NULLS LAST": TokenType.NULLS_LAST, 597 "OBJECT": TokenType.OBJECT, 598 "OFFSET": TokenType.OFFSET, 599 "ON": TokenType.ON, 600 "ONLY": TokenType.ONLY, 601 "OPTIONS": TokenType.OPTIONS, 602 "OR": TokenType.OR, 603 "ORDER BY": TokenType.ORDER_BY, 604 "ORDINALITY": TokenType.ORDINALITY, 605 "OUTER": TokenType.OUTER, 606 "OUT OF": TokenType.OUT_OF, 607 "OVER": TokenType.OVER, 608 "OVERLAPS": TokenType.OVERLAPS, 609 "OVERWRITE": TokenType.OVERWRITE, 610 "PARTITION": TokenType.PARTITION, 611 "PARTITION BY": TokenType.PARTITION_BY, 612 "PARTITIONED BY": TokenType.PARTITION_BY, 613 "PARTITIONED_BY": TokenType.PARTITION_BY, 614 "PERCENT": TokenType.PERCENT, 615 "PIVOT": TokenType.PIVOT, 616 "PRAGMA": TokenType.PRAGMA, 617 "PRECEDING": TokenType.PRECEDING, 618 "PRIMARY KEY": TokenType.PRIMARY_KEY, 619 "PROCEDURE": TokenType.PROCEDURE, 620 "QUALIFY": TokenType.QUALIFY, 621 "RANGE": TokenType.RANGE, 622 "RECURSIVE": TokenType.RECURSIVE, 623 "REGEXP": TokenType.RLIKE, 624 "REPLACE": TokenType.REPLACE, 625 "RESPECT NULLS": TokenType.RESPECT_NULLS, 626 "REFERENCES": TokenType.REFERENCES, 627 "RIGHT": TokenType.RIGHT, 628 "RLIKE": TokenType.RLIKE, 629 "ROLLBACK": TokenType.ROLLBACK, 630 "ROLLUP": TokenType.ROLLUP, 631 "ROW": TokenType.ROW, 632 "ROWS": TokenType.ROWS, 633 "SCHEMA": TokenType.SCHEMA, 634 "SEED": TokenType.SEED, 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 "SORTKEY": TokenType.SORTKEY, 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 "TRAILING": TokenType.TRAILING, 651 "UNBOUNDED": TokenType.UNBOUNDED, 652 "UNION": TokenType.UNION, 653 "UNLOGGED": TokenType.UNLOGGED, 654 "UNNEST": TokenType.UNNEST, 655 "UNPIVOT": TokenType.UNPIVOT, 656 "UPDATE": TokenType.UPDATE, 657 "USE": TokenType.USE, 658 "USING": TokenType.USING, 659 "UUID": TokenType.UUID, 660 "VALUES": TokenType.VALUES, 661 "VIEW": TokenType.VIEW, 662 "VOLATILE": TokenType.VOLATILE, 663 "WHEN": TokenType.WHEN, 664 "WHERE": TokenType.WHERE, 665 "WINDOW": TokenType.WINDOW, 666 "WITH": TokenType.WITH, 667 "WITH TIME ZONE": TokenType.WITH_TIME_ZONE, 668 "WITH LOCAL TIME ZONE": TokenType.WITH_LOCAL_TIME_ZONE, 669 "WITHIN GROUP": TokenType.WITHIN_GROUP, 670 "WITHOUT TIME ZONE": TokenType.WITHOUT_TIME_ZONE, 671 "APPLY": TokenType.APPLY, 672 "ARRAY": TokenType.ARRAY, 673 "BIT": TokenType.BIT, 674 "BOOL": TokenType.BOOLEAN, 675 "BOOLEAN": TokenType.BOOLEAN, 676 "BYTE": TokenType.TINYINT, 677 "TINYINT": TokenType.TINYINT, 678 "SHORT": TokenType.SMALLINT, 679 "SMALLINT": TokenType.SMALLINT, 680 "INT2": TokenType.SMALLINT, 681 "INTEGER": TokenType.INT, 682 "INT": TokenType.INT, 683 "INT4": TokenType.INT, 684 "LONG": TokenType.BIGINT, 685 "BIGINT": TokenType.BIGINT, 686 "INT8": TokenType.BIGINT, 687 "DEC": TokenType.DECIMAL, 688 "DECIMAL": TokenType.DECIMAL, 689 "BIGDECIMAL": TokenType.BIGDECIMAL, 690 "BIGNUMERIC": TokenType.BIGDECIMAL, 691 "MAP": TokenType.MAP, 692 "NULLABLE": TokenType.NULLABLE, 693 "NUMBER": TokenType.DECIMAL, 694 "NUMERIC": TokenType.DECIMAL, 695 "FIXED": TokenType.DECIMAL, 696 "REAL": TokenType.FLOAT, 697 "FLOAT": TokenType.FLOAT, 698 "FLOAT4": TokenType.FLOAT, 699 "FLOAT8": TokenType.DOUBLE, 700 "DOUBLE": TokenType.DOUBLE, 701 "DOUBLE PRECISION": TokenType.DOUBLE, 702 "JSON": TokenType.JSON, 703 "CHAR": TokenType.CHAR, 704 "CHARACTER": TokenType.CHAR, 705 "NCHAR": TokenType.NCHAR, 706 "VARCHAR": TokenType.VARCHAR, 707 "VARCHAR2": TokenType.VARCHAR, 708 "NVARCHAR": TokenType.NVARCHAR, 709 "NVARCHAR2": TokenType.NVARCHAR, 710 "STR": TokenType.TEXT, 711 "STRING": TokenType.TEXT, 712 "TEXT": TokenType.TEXT, 713 "CLOB": TokenType.TEXT, 714 "LONGVARCHAR": TokenType.TEXT, 715 "BINARY": TokenType.BINARY, 716 "BLOB": TokenType.VARBINARY, 717 "BYTEA": TokenType.VARBINARY, 718 "VARBINARY": TokenType.VARBINARY, 719 "TIME": TokenType.TIME, 720 "TIMESTAMP": TokenType.TIMESTAMP, 721 "TIMESTAMPTZ": TokenType.TIMESTAMPTZ, 722 "TIMESTAMPLTZ": TokenType.TIMESTAMPLTZ, 723 "DATE": TokenType.DATE, 724 "DATETIME": TokenType.DATETIME, 725 "UNIQUE": TokenType.UNIQUE, 726 "STRUCT": TokenType.STRUCT, 727 "VARIANT": TokenType.VARIANT, 728 "ALTER": TokenType.ALTER, 729 "ALTER AGGREGATE": TokenType.COMMAND, 730 "ALTER DEFAULT": TokenType.COMMAND, 731 "ALTER DOMAIN": TokenType.COMMAND, 732 "ALTER ROLE": TokenType.COMMAND, 733 "ALTER RULE": TokenType.COMMAND, 734 "ALTER SEQUENCE": TokenType.COMMAND, 735 "ALTER TYPE": TokenType.COMMAND, 736 "ALTER USER": TokenType.COMMAND, 737 "ALTER VIEW": TokenType.COMMAND, 738 "ANALYZE": TokenType.COMMAND, 739 "CALL": TokenType.COMMAND, 740 "COMMENT": TokenType.COMMENT, 741 "COPY": TokenType.COMMAND, 742 "EXPLAIN": TokenType.COMMAND, 743 "GRANT": TokenType.COMMAND, 744 "OPTIMIZE": TokenType.COMMAND, 745 "PREPARE": TokenType.COMMAND, 746 "TRUNCATE": TokenType.COMMAND, 747 "VACUUM": TokenType.COMMAND, 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 KEYWORD_TRIE: t.Dict = {} # autofilled 773 774 IDENTIFIER_CAN_START_WITH_DIGIT = False 775 776 __slots__ = ( 777 "sql", 778 "size", 779 "tokens", 780 "_start", 781 "_current", 782 "_line", 783 "_col", 784 "_comments", 785 "_char", 786 "_end", 787 "_peek", 788 "_prev_token_line", 789 ) 790 791 def __init__(self) -> None: 792 self.reset() 793 794 def reset(self) -> None: 795 self.sql = "" 796 self.size = 0 797 self.tokens: t.List[Token] = [] 798 self._start = 0 799 self._current = 0 800 self._line = 1 801 self._col = 1 802 self._comments: t.List[str] = [] 803 804 self._char = "" 805 self._end = False 806 self._peek = "" 807 self._prev_token_line = -1 808 809 def tokenize(self, sql: str) -> t.List[Token]: 810 """Returns a list of tokens corresponding to the SQL string `sql`.""" 811 self.reset() 812 self.sql = sql 813 self.size = len(sql) 814 try: 815 self._scan() 816 except Exception as e: 817 start = self._current - 50 818 end = self._current + 50 819 start = start if start > 0 else 0 820 end = end if end < self.size else self.size - 1 821 context = self.sql[start:end] 822 raise ValueError(f"Error tokenizing '{context}'") from e 823 824 return self.tokens 825 826 def _scan(self, until: t.Optional[t.Callable] = None) -> None: 827 while self.size and not self._end: 828 self._start = self._current 829 self._advance() 830 831 if self._char is None: 832 break 833 834 if self._char not in self.WHITE_SPACE: 835 if self._char.isdigit(): 836 self._scan_number() 837 elif self._char in self._IDENTIFIERS: 838 self._scan_identifier(self._IDENTIFIERS[self._char]) 839 else: 840 self._scan_keywords() 841 842 if until and until(): 843 break 844 845 if self.tokens: 846 self.tokens[-1].comments.extend(self._comments) 847 848 def _chars(self, size: int) -> str: 849 if size == 1: 850 return self._char 851 start = self._current - 1 852 end = start + size 853 if end <= self.size: 854 return self.sql[start:end] 855 return "" 856 857 def _advance(self, i: int = 1, alnum: bool = False) -> None: 858 if self.WHITE_SPACE.get(self._char) is TokenType.BREAK: 859 self._col = 1 860 self._line += 1 861 else: 862 self._col += i 863 864 self._current += i 865 self._end = self._current >= self.size 866 self._char = self.sql[self._current - 1] 867 self._peek = "" if self._end else self.sql[self._current] 868 869 if alnum and self._char.isalnum(): 870 _col = self._col 871 _current = self._current 872 _end = self._end 873 _peek = self._peek 874 875 while _peek.isalnum(): 876 _col += 1 877 _current += 1 878 _end = _current >= self.size 879 _peek = "" if _end else self.sql[_current] 880 881 self._col = _col 882 self._current = _current 883 self._end = _end 884 self._peek = _peek 885 self._char = self.sql[_current - 1] 886 887 @property 888 def _text(self) -> str: 889 return self.sql[self._start : self._current] 890 891 def _add(self, token_type: TokenType, text: t.Optional[str] = None) -> None: 892 self._prev_token_line = self._line 893 self.tokens.append( 894 Token( 895 token_type, 896 self._text if text is None else text, 897 self._line, 898 self._col, 899 self._current, 900 self._comments, 901 ) 902 ) 903 self._comments = [] 904 905 # If we have either a semicolon or a begin token before the command's token, we'll parse 906 # whatever follows the command's token as a string 907 if ( 908 token_type in self.COMMANDS 909 and self._peek != ";" 910 and (len(self.tokens) == 1 or self.tokens[-2].token_type in self.COMMAND_PREFIX_TOKENS) 911 ): 912 start = self._current 913 tokens = len(self.tokens) 914 self._scan(lambda: self._peek == ";") 915 self.tokens = self.tokens[:tokens] 916 text = self.sql[start : self._current].strip() 917 if text: 918 self._add(TokenType.STRING, text) 919 920 def _scan_keywords(self) -> None: 921 size = 0 922 word = None 923 chars = self._text 924 char = chars 925 prev_space = False 926 skip = False 927 trie = self.KEYWORD_TRIE 928 single_token = char in self.SINGLE_TOKENS 929 930 while chars: 931 if skip: 932 result = 1 933 else: 934 result, trie = in_trie(trie, char.upper()) 935 936 if result == 0: 937 break 938 if result == 2: 939 word = chars 940 941 size += 1 942 end = self._current - 1 + size 943 944 if end < self.size: 945 char = self.sql[end] 946 single_token = single_token or char in self.SINGLE_TOKENS 947 is_space = char in self.WHITE_SPACE 948 949 if not is_space or not prev_space: 950 if is_space: 951 char = " " 952 chars += char 953 prev_space = is_space 954 skip = False 955 else: 956 skip = True 957 else: 958 char = "" 959 chars = " " 960 961 word = None if not single_token and chars[-1] not in self.WHITE_SPACE else word 962 963 if not word: 964 if self._char in self.SINGLE_TOKENS: 965 self._add(self.SINGLE_TOKENS[self._char], text=self._char) 966 return 967 self._scan_var() 968 return 969 970 if self._scan_string(word): 971 return 972 if self._scan_formatted_string(word): 973 return 974 if self._scan_comment(word): 975 return 976 977 self._advance(size - 1) 978 word = word.upper() 979 self._add(self.KEYWORDS[word], text=word) 980 981 def _scan_comment(self, comment_start: str) -> bool: 982 if comment_start not in self._COMMENTS: 983 return False 984 985 comment_start_line = self._line 986 comment_start_size = len(comment_start) 987 comment_end = self._COMMENTS[comment_start] 988 989 if comment_end: 990 # Skip the comment's start delimiter 991 self._advance(comment_start_size) 992 993 comment_end_size = len(comment_end) 994 while not self._end and self._chars(comment_end_size) != comment_end: 995 self._advance(alnum=True) 996 997 self._comments.append(self._text[comment_start_size : -comment_end_size + 1]) 998 self._advance(comment_end_size - 1) 999 else: 1000 while not self._end and not self.WHITE_SPACE.get(self._peek) is TokenType.BREAK: 1001 self._advance(alnum=True) 1002 self._comments.append(self._text[comment_start_size:]) 1003 1004 # Leading comment is attached to the succeeding token, whilst trailing comment to the preceding. 1005 # Multiple consecutive comments are preserved by appending them to the current comments list. 1006 if comment_start_line == self._prev_token_line: 1007 self.tokens[-1].comments.extend(self._comments) 1008 self._comments = [] 1009 self._prev_token_line = self._line 1010 1011 return True 1012 1013 def _scan_number(self) -> None: 1014 if self._char == "0": 1015 peek = self._peek.upper() 1016 if peek == "B": 1017 return self._scan_bits() if self._BIT_STRINGS else self._add(TokenType.NUMBER) 1018 elif peek == "X": 1019 return self._scan_hex() if self._HEX_STRINGS else self._add(TokenType.NUMBER) 1020 1021 decimal = False 1022 scientific = 0 1023 1024 while True: 1025 if self._peek.isdigit(): 1026 self._advance() 1027 elif self._peek == "." and not decimal: 1028 decimal = True 1029 self._advance() 1030 elif self._peek in ("-", "+") and scientific == 1: 1031 scientific += 1 1032 self._advance() 1033 elif self._peek.upper() == "E" and not scientific: 1034 scientific += 1 1035 self._advance() 1036 elif self._peek.isidentifier(): 1037 number_text = self._text 1038 literal = "" 1039 1040 while self._peek.strip() and self._peek not in self.SINGLE_TOKENS: 1041 literal += self._peek.upper() 1042 self._advance() 1043 1044 token_type = self.KEYWORDS.get(self.NUMERIC_LITERALS.get(literal)) 1045 1046 if token_type: 1047 self._add(TokenType.NUMBER, number_text) 1048 self._add(TokenType.DCOLON, "::") 1049 return self._add(token_type, literal) 1050 elif self.IDENTIFIER_CAN_START_WITH_DIGIT: 1051 return self._add(TokenType.VAR) 1052 1053 self._add(TokenType.NUMBER, number_text) 1054 return self._advance(-len(literal)) 1055 else: 1056 return self._add(TokenType.NUMBER) 1057 1058 def _scan_bits(self) -> None: 1059 self._advance() 1060 value = self._extract_value() 1061 try: 1062 # If `value` can't be converted to a binary, fallback to tokenizing it as an identifier 1063 int(value, 2) 1064 self._add(TokenType.BIT_STRING, value[2:]) # Drop the 0b 1065 except ValueError: 1066 self._add(TokenType.IDENTIFIER) 1067 1068 def _scan_hex(self) -> None: 1069 self._advance() 1070 value = self._extract_value() 1071 try: 1072 # If `value` can't be converted to a hex, fallback to tokenizing it as an identifier 1073 int(value, 16) 1074 self._add(TokenType.HEX_STRING, value[2:]) # Drop the 0x 1075 except ValueError: 1076 self._add(TokenType.IDENTIFIER) 1077 1078 def _extract_value(self) -> str: 1079 while True: 1080 char = self._peek.strip() 1081 if char and char not in self.SINGLE_TOKENS: 1082 self._advance(alnum=True) 1083 else: 1084 break 1085 1086 return self._text 1087 1088 def _scan_string(self, quote: str) -> bool: 1089 quote_end = self._QUOTES.get(quote) 1090 if quote_end is None: 1091 return False 1092 1093 self._advance(len(quote)) 1094 text = self._extract_string(quote_end) 1095 text = text.encode(self.ENCODE).decode(self.ENCODE) if self.ENCODE else text 1096 self._add(TokenType.NATIONAL if quote[0].upper() == "N" else TokenType.STRING, text) 1097 return True 1098 1099 # X'1234', b'0110', E'\\\\\' etc. 1100 def _scan_formatted_string(self, string_start: str) -> bool: 1101 if string_start in self._HEX_STRINGS: 1102 delimiters = self._HEX_STRINGS 1103 token_type = TokenType.HEX_STRING 1104 base = 16 1105 elif string_start in self._BIT_STRINGS: 1106 delimiters = self._BIT_STRINGS 1107 token_type = TokenType.BIT_STRING 1108 base = 2 1109 elif string_start in self._BYTE_STRINGS: 1110 delimiters = self._BYTE_STRINGS 1111 token_type = TokenType.BYTE_STRING 1112 base = None 1113 else: 1114 return False 1115 1116 self._advance(len(string_start)) 1117 string_end = delimiters[string_start] 1118 text = self._extract_string(string_end) 1119 1120 if base: 1121 try: 1122 int(text, base) 1123 except: 1124 raise RuntimeError( 1125 f"Numeric string contains invalid characters from {self._line}:{self._start}" 1126 ) 1127 1128 self._add(token_type, text) 1129 return True 1130 1131 def _scan_identifier(self, identifier_end: str) -> None: 1132 self._advance() 1133 text = self._extract_string(identifier_end, self._IDENTIFIER_ESCAPES) 1134 self._add(TokenType.IDENTIFIER, text) 1135 1136 def _scan_var(self) -> None: 1137 while True: 1138 char = self._peek.strip() 1139 if char and (char in self.VAR_SINGLE_TOKENS or char not in self.SINGLE_TOKENS): 1140 self._advance(alnum=True) 1141 else: 1142 break 1143 1144 self._add( 1145 TokenType.VAR 1146 if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER 1147 else self.KEYWORDS.get(self._text.upper(), TokenType.VAR) 1148 ) 1149 1150 def _extract_string(self, delimiter: str, escapes=None) -> str: 1151 text = "" 1152 delim_size = len(delimiter) 1153 escapes = self._STRING_ESCAPES if escapes is None else escapes 1154 1155 while True: 1156 if self._char in escapes and (self._peek == delimiter or self._peek in escapes): 1157 if self._peek == delimiter: 1158 text += self._peek 1159 else: 1160 text += self._char + self._peek 1161 1162 if self._current + 1 < self.size: 1163 self._advance(2) 1164 else: 1165 raise RuntimeError(f"Missing {delimiter} from {self._line}:{self._current}") 1166 else: 1167 if self._chars(delim_size) == delimiter: 1168 if delim_size > 1: 1169 self._advance(delim_size - 1) 1170 break 1171 1172 if self._end: 1173 raise RuntimeError(f"Missing {delimiter} from {self._line}:{self._start}") 1174 1175 current = self._current - 1 1176 self._advance(alnum=True) 1177 text += self.sql[current : self._current - 1] 1178 1179 return text
def
reset(self) -> None:
794 def reset(self) -> None: 795 self.sql = "" 796 self.size = 0 797 self.tokens: t.List[Token] = [] 798 self._start = 0 799 self._current = 0 800 self._line = 1 801 self._col = 1 802 self._comments: t.List[str] = [] 803 804 self._char = "" 805 self._end = False 806 self._peek = "" 807 self._prev_token_line = -1
809 def tokenize(self, sql: str) -> t.List[Token]: 810 """Returns a list of tokens corresponding to the SQL string `sql`.""" 811 self.reset() 812 self.sql = sql 813 self.size = len(sql) 814 try: 815 self._scan() 816 except Exception as e: 817 start = self._current - 50 818 end = self._current + 50 819 start = start if start > 0 else 0 820 end = end if end < self.size else self.size - 1 821 context = self.sql[start:end] 822 raise ValueError(f"Error tokenizing '{context}'") from e 823 824 return self.tokens
Returns a list of tokens corresponding to the SQL string sql
.