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", "start", "end", "comments") 329 330 @classmethod 331 def number(cls, number: int) -> Token: 332 """Returns a NUMBER token with `number` as its text.""" 333 return cls(TokenType.NUMBER, str(number)) 334 335 @classmethod 336 def string(cls, string: str) -> Token: 337 """Returns a STRING token with `string` as its text.""" 338 return cls(TokenType.STRING, string) 339 340 @classmethod 341 def identifier(cls, identifier: str) -> Token: 342 """Returns an IDENTIFIER token with `identifier` as its text.""" 343 return cls(TokenType.IDENTIFIER, identifier) 344 345 @classmethod 346 def var(cls, var: str) -> Token: 347 """Returns an VAR token with `var` as its text.""" 348 return cls(TokenType.VAR, var) 349 350 def __init__( 351 self, 352 token_type: TokenType, 353 text: str, 354 line: int = 1, 355 col: int = 1, 356 start: int = 0, 357 end: int = 0, 358 comments: t.List[str] = [], 359 ) -> None: 360 """Token initializer. 361 362 Args: 363 token_type: The TokenType Enum. 364 text: The text of the token. 365 line: The line that the token ends on. 366 col: The column that the token ends on. 367 start: The start index of the token. 368 end: The ending index of the token. 369 """ 370 self.token_type = token_type 371 self.text = text 372 self.line = line 373 self.col = col 374 self.start = start 375 self.end = end 376 self.comments = comments 377 378 def __repr__(self) -> str: 379 attributes = ", ".join(f"{k}: {getattr(self, k)}" for k in self.__slots__) 380 return f"<Token {attributes}>" 381 382 383class _Tokenizer(type): 384 def __new__(cls, clsname, bases, attrs): 385 klass = super().__new__(cls, clsname, bases, attrs) 386 387 klass._QUOTES = { 388 f"{prefix}{s}": e 389 for s, e in cls._delimeter_list_to_dict(klass.QUOTES).items() 390 for prefix in (("",) if s[0].isalpha() else ("", "n", "N")) 391 } 392 klass._BIT_STRINGS = cls._delimeter_list_to_dict(klass.BIT_STRINGS) 393 klass._HEX_STRINGS = cls._delimeter_list_to_dict(klass.HEX_STRINGS) 394 klass._BYTE_STRINGS = cls._delimeter_list_to_dict(klass.BYTE_STRINGS) 395 klass._IDENTIFIERS = cls._delimeter_list_to_dict(klass.IDENTIFIERS) 396 klass._STRING_ESCAPES = set(klass.STRING_ESCAPES) 397 klass._IDENTIFIER_ESCAPES = set(klass.IDENTIFIER_ESCAPES) 398 klass._COMMENTS = dict( 399 (comment, None) if isinstance(comment, str) else (comment[0], comment[1]) 400 for comment in klass.COMMENTS 401 ) 402 403 klass.KEYWORD_TRIE = new_trie( 404 key.upper() 405 for key in { 406 **klass.KEYWORDS, 407 **{comment: TokenType.COMMENT for comment in klass._COMMENTS}, 408 **{quote: TokenType.QUOTE for quote in klass._QUOTES}, 409 **{bit_string: TokenType.BIT_STRING for bit_string in klass._BIT_STRINGS}, 410 **{hex_string: TokenType.HEX_STRING for hex_string in klass._HEX_STRINGS}, 411 **{byte_string: TokenType.BYTE_STRING for byte_string in klass._BYTE_STRINGS}, 412 } 413 if " " in key or any(single in key for single in klass.SINGLE_TOKENS) 414 ) 415 416 return klass 417 418 @staticmethod 419 def _delimeter_list_to_dict(list: t.List[str | t.Tuple[str, str]]) -> t.Dict[str, str]: 420 return dict((item, item) if isinstance(item, str) else (item[0], item[1]) for item in list) 421 422 423class Tokenizer(metaclass=_Tokenizer): 424 SINGLE_TOKENS = { 425 "(": TokenType.L_PAREN, 426 ")": TokenType.R_PAREN, 427 "[": TokenType.L_BRACKET, 428 "]": TokenType.R_BRACKET, 429 "{": TokenType.L_BRACE, 430 "}": TokenType.R_BRACE, 431 "&": TokenType.AMP, 432 "^": TokenType.CARET, 433 ":": TokenType.COLON, 434 ",": TokenType.COMMA, 435 ".": TokenType.DOT, 436 "-": TokenType.DASH, 437 "=": TokenType.EQ, 438 ">": TokenType.GT, 439 "<": TokenType.LT, 440 "%": TokenType.MOD, 441 "!": TokenType.NOT, 442 "|": TokenType.PIPE, 443 "+": TokenType.PLUS, 444 ";": TokenType.SEMICOLON, 445 "/": TokenType.SLASH, 446 "\\": TokenType.BACKSLASH, 447 "*": TokenType.STAR, 448 "~": TokenType.TILDA, 449 "?": TokenType.PLACEHOLDER, 450 "@": TokenType.PARAMETER, 451 # used for breaking a var like x'y' but nothing else 452 # the token type doesn't matter 453 "'": TokenType.QUOTE, 454 "`": TokenType.IDENTIFIER, 455 '"': TokenType.IDENTIFIER, 456 "#": TokenType.HASH, 457 } 458 459 BIT_STRINGS: t.List[str | t.Tuple[str, str]] = [] 460 BYTE_STRINGS: t.List[str | t.Tuple[str, str]] = [] 461 HEX_STRINGS: t.List[str | t.Tuple[str, str]] = [] 462 IDENTIFIERS: t.List[str | t.Tuple[str, str]] = ['"'] 463 IDENTIFIER_ESCAPES = ['"'] 464 QUOTES: t.List[t.Tuple[str, str] | str] = ["'"] 465 STRING_ESCAPES = ["'"] 466 VAR_SINGLE_TOKENS: t.Set[str] = set() 467 468 _COMMENTS: t.Dict[str, str] = {} 469 _BIT_STRINGS: t.Dict[str, str] = {} 470 _BYTE_STRINGS: t.Dict[str, str] = {} 471 _HEX_STRINGS: t.Dict[str, str] = {} 472 _IDENTIFIERS: t.Dict[str, str] = {} 473 _IDENTIFIER_ESCAPES: t.Set[str] = set() 474 _QUOTES: t.Dict[str, str] = {} 475 _STRING_ESCAPES: t.Set[str] = set() 476 477 KEYWORDS: t.Dict[t.Optional[str], TokenType] = { 478 **{f"{{%{postfix}": TokenType.BLOCK_START for postfix in ("", "+", "-")}, 479 **{f"{prefix}%}}": TokenType.BLOCK_END for prefix in ("", "+", "-")}, 480 "{{+": TokenType.BLOCK_START, 481 "{{-": TokenType.BLOCK_START, 482 "+}}": TokenType.BLOCK_END, 483 "-}}": TokenType.BLOCK_END, 484 "/*+": TokenType.HINT, 485 "==": TokenType.EQ, 486 "::": TokenType.DCOLON, 487 "||": TokenType.DPIPE, 488 ">=": TokenType.GTE, 489 "<=": TokenType.LTE, 490 "<>": TokenType.NEQ, 491 "!=": TokenType.NEQ, 492 "<=>": TokenType.NULLSAFE_EQ, 493 "->": TokenType.ARROW, 494 "->>": TokenType.DARROW, 495 "=>": TokenType.FARROW, 496 "#>": TokenType.HASH_ARROW, 497 "#>>": TokenType.DHASH_ARROW, 498 "<->": TokenType.LR_ARROW, 499 "&&": TokenType.DAMP, 500 "ALL": TokenType.ALL, 501 "ALWAYS": TokenType.ALWAYS, 502 "AND": TokenType.AND, 503 "ANTI": TokenType.ANTI, 504 "ANY": TokenType.ANY, 505 "ASC": TokenType.ASC, 506 "AS": TokenType.ALIAS, 507 "AT TIME ZONE": TokenType.AT_TIME_ZONE, 508 "AUTOINCREMENT": TokenType.AUTO_INCREMENT, 509 "AUTO_INCREMENT": TokenType.AUTO_INCREMENT, 510 "BEGIN": TokenType.BEGIN, 511 "BETWEEN": TokenType.BETWEEN, 512 "BOTH": TokenType.BOTH, 513 "BUCKET": TokenType.BUCKET, 514 "BY DEFAULT": TokenType.BY_DEFAULT, 515 "CACHE": TokenType.CACHE, 516 "UNCACHE": TokenType.UNCACHE, 517 "CASE": TokenType.CASE, 518 "CASCADE": TokenType.CASCADE, 519 "CHARACTER SET": TokenType.CHARACTER_SET, 520 "CLUSTER BY": TokenType.CLUSTER_BY, 521 "COLLATE": TokenType.COLLATE, 522 "COLUMN": TokenType.COLUMN, 523 "COMMIT": TokenType.COMMIT, 524 "COMPOUND": TokenType.COMPOUND, 525 "CONSTRAINT": TokenType.CONSTRAINT, 526 "CREATE": TokenType.CREATE, 527 "CROSS": TokenType.CROSS, 528 "CUBE": TokenType.CUBE, 529 "CURRENT_DATE": TokenType.CURRENT_DATE, 530 "CURRENT ROW": TokenType.CURRENT_ROW, 531 "CURRENT_TIME": TokenType.CURRENT_TIME, 532 "CURRENT_TIMESTAMP": TokenType.CURRENT_TIMESTAMP, 533 "CURRENT_USER": TokenType.CURRENT_USER, 534 "DATABASE": TokenType.DATABASE, 535 "DEFAULT": TokenType.DEFAULT, 536 "DELETE": TokenType.DELETE, 537 "DESC": TokenType.DESC, 538 "DESCRIBE": TokenType.DESCRIBE, 539 "DISTINCT": TokenType.DISTINCT, 540 "DISTINCT FROM": TokenType.DISTINCT_FROM, 541 "DISTRIBUTE BY": TokenType.DISTRIBUTE_BY, 542 "DIV": TokenType.DIV, 543 "DROP": TokenType.DROP, 544 "ELSE": TokenType.ELSE, 545 "END": TokenType.END, 546 "ESCAPE": TokenType.ESCAPE, 547 "EXCEPT": TokenType.EXCEPT, 548 "EXECUTE": TokenType.EXECUTE, 549 "EXISTS": TokenType.EXISTS, 550 "FALSE": TokenType.FALSE, 551 "FETCH": TokenType.FETCH, 552 "FILTER": TokenType.FILTER, 553 "FIRST": TokenType.FIRST, 554 "FULL": TokenType.FULL, 555 "FUNCTION": TokenType.FUNCTION, 556 "FOLLOWING": TokenType.FOLLOWING, 557 "FOR": TokenType.FOR, 558 "FOREIGN KEY": TokenType.FOREIGN_KEY, 559 "FORMAT": TokenType.FORMAT, 560 "FROM": TokenType.FROM, 561 "GEOGRAPHY": TokenType.GEOGRAPHY, 562 "GEOMETRY": TokenType.GEOMETRY, 563 "GLOB": TokenType.GLOB, 564 "GROUP BY": TokenType.GROUP_BY, 565 "GROUPING SETS": TokenType.GROUPING_SETS, 566 "HAVING": TokenType.HAVING, 567 "IF": TokenType.IF, 568 "ILIKE": TokenType.ILIKE, 569 "IGNORE NULLS": TokenType.IGNORE_NULLS, 570 "IN": TokenType.IN, 571 "INDEX": TokenType.INDEX, 572 "INET": TokenType.INET, 573 "INNER": TokenType.INNER, 574 "INSERT": TokenType.INSERT, 575 "INTERVAL": TokenType.INTERVAL, 576 "INTERSECT": TokenType.INTERSECT, 577 "INTO": TokenType.INTO, 578 "IS": TokenType.IS, 579 "ISNULL": TokenType.ISNULL, 580 "JOIN": TokenType.JOIN, 581 "KEEP": TokenType.KEEP, 582 "LATERAL": TokenType.LATERAL, 583 "LAZY": TokenType.LAZY, 584 "LEADING": TokenType.LEADING, 585 "LEFT": TokenType.LEFT, 586 "LIKE": TokenType.LIKE, 587 "LIMIT": TokenType.LIMIT, 588 "LOAD DATA": TokenType.LOAD_DATA, 589 "LOCAL": TokenType.LOCAL, 590 "LOCK": TokenType.LOCK, 591 "MATERIALIZED": TokenType.MATERIALIZED, 592 "MERGE": TokenType.MERGE, 593 "NATURAL": TokenType.NATURAL, 594 "NEXT": TokenType.NEXT, 595 "NEXT VALUE FOR": TokenType.NEXT_VALUE_FOR, 596 "NO ACTION": TokenType.NO_ACTION, 597 "NOT": TokenType.NOT, 598 "NOTNULL": TokenType.NOTNULL, 599 "NULL": TokenType.NULL, 600 "NULLS FIRST": TokenType.NULLS_FIRST, 601 "NULLS LAST": TokenType.NULLS_LAST, 602 "OBJECT": TokenType.OBJECT, 603 "OFFSET": TokenType.OFFSET, 604 "ON": TokenType.ON, 605 "ONLY": TokenType.ONLY, 606 "OPTIONS": TokenType.OPTIONS, 607 "OR": TokenType.OR, 608 "ORDER BY": TokenType.ORDER_BY, 609 "ORDINALITY": TokenType.ORDINALITY, 610 "OUTER": TokenType.OUTER, 611 "OUT OF": TokenType.OUT_OF, 612 "OVER": TokenType.OVER, 613 "OVERLAPS": TokenType.OVERLAPS, 614 "OVERWRITE": TokenType.OVERWRITE, 615 "PARTITION": TokenType.PARTITION, 616 "PARTITION BY": TokenType.PARTITION_BY, 617 "PARTITIONED BY": TokenType.PARTITION_BY, 618 "PARTITIONED_BY": TokenType.PARTITION_BY, 619 "PERCENT": TokenType.PERCENT, 620 "PIVOT": TokenType.PIVOT, 621 "PRAGMA": TokenType.PRAGMA, 622 "PRECEDING": TokenType.PRECEDING, 623 "PRIMARY KEY": TokenType.PRIMARY_KEY, 624 "PROCEDURE": TokenType.PROCEDURE, 625 "QUALIFY": TokenType.QUALIFY, 626 "RANGE": TokenType.RANGE, 627 "RECURSIVE": TokenType.RECURSIVE, 628 "REGEXP": TokenType.RLIKE, 629 "REPLACE": TokenType.REPLACE, 630 "RESPECT NULLS": TokenType.RESPECT_NULLS, 631 "REFERENCES": TokenType.REFERENCES, 632 "RIGHT": TokenType.RIGHT, 633 "RLIKE": TokenType.RLIKE, 634 "ROLLBACK": TokenType.ROLLBACK, 635 "ROLLUP": TokenType.ROLLUP, 636 "ROW": TokenType.ROW, 637 "ROWS": TokenType.ROWS, 638 "SCHEMA": TokenType.SCHEMA, 639 "SEED": TokenType.SEED, 640 "SELECT": TokenType.SELECT, 641 "SEMI": TokenType.SEMI, 642 "SET": TokenType.SET, 643 "SETTINGS": TokenType.SETTINGS, 644 "SHOW": TokenType.SHOW, 645 "SIMILAR TO": TokenType.SIMILAR_TO, 646 "SOME": TokenType.SOME, 647 "SORTKEY": TokenType.SORTKEY, 648 "SORT BY": TokenType.SORT_BY, 649 "TABLE": TokenType.TABLE, 650 "TABLESAMPLE": TokenType.TABLE_SAMPLE, 651 "TEMP": TokenType.TEMPORARY, 652 "TEMPORARY": TokenType.TEMPORARY, 653 "THEN": TokenType.THEN, 654 "TRUE": TokenType.TRUE, 655 "TRAILING": TokenType.TRAILING, 656 "UNBOUNDED": TokenType.UNBOUNDED, 657 "UNION": TokenType.UNION, 658 "UNLOGGED": TokenType.UNLOGGED, 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 "WITH TIME ZONE": TokenType.WITH_TIME_ZONE, 673 "WITH LOCAL TIME ZONE": TokenType.WITH_LOCAL_TIME_ZONE, 674 "WITHIN GROUP": TokenType.WITHIN_GROUP, 675 "WITHOUT TIME ZONE": TokenType.WITHOUT_TIME_ZONE, 676 "APPLY": TokenType.APPLY, 677 "ARRAY": TokenType.ARRAY, 678 "BIT": TokenType.BIT, 679 "BOOL": TokenType.BOOLEAN, 680 "BOOLEAN": TokenType.BOOLEAN, 681 "BYTE": TokenType.TINYINT, 682 "TINYINT": TokenType.TINYINT, 683 "SHORT": TokenType.SMALLINT, 684 "SMALLINT": TokenType.SMALLINT, 685 "INT2": TokenType.SMALLINT, 686 "INTEGER": TokenType.INT, 687 "INT": TokenType.INT, 688 "INT4": TokenType.INT, 689 "LONG": TokenType.BIGINT, 690 "BIGINT": TokenType.BIGINT, 691 "INT8": TokenType.BIGINT, 692 "DEC": TokenType.DECIMAL, 693 "DECIMAL": TokenType.DECIMAL, 694 "BIGDECIMAL": TokenType.BIGDECIMAL, 695 "BIGNUMERIC": TokenType.BIGDECIMAL, 696 "MAP": TokenType.MAP, 697 "NULLABLE": TokenType.NULLABLE, 698 "NUMBER": TokenType.DECIMAL, 699 "NUMERIC": TokenType.DECIMAL, 700 "FIXED": TokenType.DECIMAL, 701 "REAL": TokenType.FLOAT, 702 "FLOAT": TokenType.FLOAT, 703 "FLOAT4": TokenType.FLOAT, 704 "FLOAT8": TokenType.DOUBLE, 705 "DOUBLE": TokenType.DOUBLE, 706 "DOUBLE PRECISION": TokenType.DOUBLE, 707 "JSON": TokenType.JSON, 708 "CHAR": TokenType.CHAR, 709 "CHARACTER": TokenType.CHAR, 710 "NCHAR": TokenType.NCHAR, 711 "VARCHAR": TokenType.VARCHAR, 712 "VARCHAR2": TokenType.VARCHAR, 713 "NVARCHAR": TokenType.NVARCHAR, 714 "NVARCHAR2": TokenType.NVARCHAR, 715 "STR": TokenType.TEXT, 716 "STRING": TokenType.TEXT, 717 "TEXT": TokenType.TEXT, 718 "CLOB": TokenType.TEXT, 719 "LONGVARCHAR": TokenType.TEXT, 720 "BINARY": TokenType.BINARY, 721 "BLOB": TokenType.VARBINARY, 722 "BYTEA": TokenType.VARBINARY, 723 "VARBINARY": TokenType.VARBINARY, 724 "TIME": TokenType.TIME, 725 "TIMESTAMP": TokenType.TIMESTAMP, 726 "TIMESTAMPTZ": TokenType.TIMESTAMPTZ, 727 "TIMESTAMPLTZ": TokenType.TIMESTAMPLTZ, 728 "DATE": TokenType.DATE, 729 "DATETIME": TokenType.DATETIME, 730 "UNIQUE": TokenType.UNIQUE, 731 "STRUCT": TokenType.STRUCT, 732 "VARIANT": TokenType.VARIANT, 733 "ALTER": TokenType.ALTER, 734 "ALTER AGGREGATE": TokenType.COMMAND, 735 "ALTER DEFAULT": TokenType.COMMAND, 736 "ALTER DOMAIN": TokenType.COMMAND, 737 "ALTER ROLE": TokenType.COMMAND, 738 "ALTER RULE": TokenType.COMMAND, 739 "ALTER SEQUENCE": TokenType.COMMAND, 740 "ALTER TYPE": TokenType.COMMAND, 741 "ALTER USER": TokenType.COMMAND, 742 "ALTER VIEW": TokenType.COMMAND, 743 "ANALYZE": TokenType.COMMAND, 744 "CALL": TokenType.COMMAND, 745 "COMMENT": TokenType.COMMENT, 746 "COPY": TokenType.COMMAND, 747 "EXPLAIN": TokenType.COMMAND, 748 "GRANT": TokenType.COMMAND, 749 "OPTIMIZE": TokenType.COMMAND, 750 "PREPARE": TokenType.COMMAND, 751 "TRUNCATE": TokenType.COMMAND, 752 "VACUUM": TokenType.COMMAND, 753 } 754 755 WHITE_SPACE: t.Dict[t.Optional[str], TokenType] = { 756 " ": TokenType.SPACE, 757 "\t": TokenType.SPACE, 758 "\n": TokenType.BREAK, 759 "\r": TokenType.BREAK, 760 "\r\n": TokenType.BREAK, 761 } 762 763 COMMANDS = { 764 TokenType.COMMAND, 765 TokenType.EXECUTE, 766 TokenType.FETCH, 767 TokenType.SHOW, 768 } 769 770 COMMAND_PREFIX_TOKENS = {TokenType.SEMICOLON, TokenType.BEGIN} 771 772 # handle numeric literals like in hive (3L = BIGINT) 773 NUMERIC_LITERALS: t.Dict[str, str] = {} 774 ENCODE: t.Optional[str] = None 775 776 COMMENTS = ["--", ("/*", "*/"), ("{#", "#}")] 777 KEYWORD_TRIE: t.Dict = {} # autofilled 778 779 IDENTIFIER_CAN_START_WITH_DIGIT = False 780 781 __slots__ = ( 782 "sql", 783 "size", 784 "tokens", 785 "_start", 786 "_current", 787 "_line", 788 "_col", 789 "_comments", 790 "_char", 791 "_end", 792 "_peek", 793 "_prev_token_line", 794 ) 795 796 def __init__(self) -> None: 797 self.reset() 798 799 def reset(self) -> None: 800 self.sql = "" 801 self.size = 0 802 self.tokens: t.List[Token] = [] 803 self._start = 0 804 self._current = 0 805 self._line = 1 806 self._col = 0 807 self._comments: t.List[str] = [] 808 809 self._char = "" 810 self._end = False 811 self._peek = "" 812 self._prev_token_line = -1 813 814 def tokenize(self, sql: str) -> t.List[Token]: 815 """Returns a list of tokens corresponding to the SQL string `sql`.""" 816 self.reset() 817 self.sql = sql 818 self.size = len(sql) 819 820 try: 821 self._scan() 822 except Exception as e: 823 start = max(self._current - 50, 0) 824 end = min(self._current + 50, self.size - 1) 825 context = self.sql[start:end] 826 raise ValueError(f"Error tokenizing '{context}'") from e 827 828 return self.tokens 829 830 def _scan(self, until: t.Optional[t.Callable] = None) -> None: 831 while self.size and not self._end: 832 self._start = self._current 833 self._advance() 834 835 if self._char is None: 836 break 837 838 if self._char not in self.WHITE_SPACE: 839 if self._char.isdigit(): 840 self._scan_number() 841 elif self._char in self._IDENTIFIERS: 842 self._scan_identifier(self._IDENTIFIERS[self._char]) 843 else: 844 self._scan_keywords() 845 846 if until and until(): 847 break 848 849 if self.tokens and self._comments: 850 self.tokens[-1].comments.extend(self._comments) 851 852 def _chars(self, size: int) -> str: 853 if size == 1: 854 return self._char 855 856 start = self._current - 1 857 end = start + size 858 859 return self.sql[start:end] if end <= self.size else "" 860 861 def _advance(self, i: int = 1, alnum: bool = False) -> None: 862 if self.WHITE_SPACE.get(self._char) is TokenType.BREAK: 863 self._col = 1 864 self._line += 1 865 else: 866 self._col += i 867 868 self._current += i 869 self._end = self._current >= self.size 870 self._char = self.sql[self._current - 1] 871 self._peek = "" if self._end else self.sql[self._current] 872 873 if alnum and self._char.isalnum(): 874 # Here we use local variables instead of attributes for better performance 875 _col = self._col 876 _current = self._current 877 _end = self._end 878 _peek = self._peek 879 880 while _peek.isalnum(): 881 _col += 1 882 _current += 1 883 _end = _current >= self.size 884 _peek = "" if _end else self.sql[_current] 885 886 self._col = _col 887 self._current = _current 888 self._end = _end 889 self._peek = _peek 890 self._char = self.sql[_current - 1] 891 892 @property 893 def _text(self) -> str: 894 return self.sql[self._start : self._current] 895 896 def _add(self, token_type: TokenType, text: t.Optional[str] = None) -> None: 897 self._prev_token_line = self._line 898 self.tokens.append( 899 Token( 900 token_type, 901 text=self._text if text is None else text, 902 line=self._line, 903 col=self._col, 904 start=self._start, 905 end=self._current - 1, 906 comments=self._comments, 907 ) 908 ) 909 self._comments = [] 910 911 # If we have either a semicolon or a begin token before the command's token, we'll parse 912 # whatever follows the command's token as a string 913 if ( 914 token_type in self.COMMANDS 915 and self._peek != ";" 916 and (len(self.tokens) == 1 or self.tokens[-2].token_type in self.COMMAND_PREFIX_TOKENS) 917 ): 918 start = self._current 919 tokens = len(self.tokens) 920 self._scan(lambda: self._peek == ";") 921 self.tokens = self.tokens[:tokens] 922 text = self.sql[start : self._current].strip() 923 if text: 924 self._add(TokenType.STRING, text) 925 926 def _scan_keywords(self) -> None: 927 size = 0 928 word = None 929 chars = self._text 930 char = chars 931 prev_space = False 932 skip = False 933 trie = self.KEYWORD_TRIE 934 single_token = char in self.SINGLE_TOKENS 935 936 while chars: 937 if skip: 938 result = 1 939 else: 940 result, trie = in_trie(trie, char.upper()) 941 942 if result == 0: 943 break 944 if result == 2: 945 word = chars 946 947 size += 1 948 end = self._current - 1 + size 949 950 if end < self.size: 951 char = self.sql[end] 952 single_token = single_token or char in self.SINGLE_TOKENS 953 is_space = char in self.WHITE_SPACE 954 955 if not is_space or not prev_space: 956 if is_space: 957 char = " " 958 chars += char 959 prev_space = is_space 960 skip = False 961 else: 962 skip = True 963 else: 964 char = "" 965 chars = " " 966 967 word = None if not single_token and chars[-1] not in self.WHITE_SPACE else word 968 969 if not word: 970 if self._char in self.SINGLE_TOKENS: 971 self._add(self.SINGLE_TOKENS[self._char], text=self._char) 972 return 973 self._scan_var() 974 return 975 976 if self._scan_string(word): 977 return 978 if self._scan_formatted_string(word): 979 return 980 if self._scan_comment(word): 981 return 982 983 self._advance(size - 1) 984 word = word.upper() 985 self._add(self.KEYWORDS[word], text=word) 986 987 def _scan_comment(self, comment_start: str) -> bool: 988 if comment_start not in self._COMMENTS: 989 return False 990 991 comment_start_line = self._line 992 comment_start_size = len(comment_start) 993 comment_end = self._COMMENTS[comment_start] 994 995 if comment_end: 996 # Skip the comment's start delimiter 997 self._advance(comment_start_size) 998 999 comment_end_size = len(comment_end) 1000 while not self._end and self._chars(comment_end_size) != comment_end: 1001 self._advance(alnum=True) 1002 1003 self._comments.append(self._text[comment_start_size : -comment_end_size + 1]) 1004 self._advance(comment_end_size - 1) 1005 else: 1006 while not self._end and not self.WHITE_SPACE.get(self._peek) is TokenType.BREAK: 1007 self._advance(alnum=True) 1008 self._comments.append(self._text[comment_start_size:]) 1009 1010 # Leading comment is attached to the succeeding token, whilst trailing comment to the preceding. 1011 # Multiple consecutive comments are preserved by appending them to the current comments list. 1012 if comment_start_line == self._prev_token_line: 1013 self.tokens[-1].comments.extend(self._comments) 1014 self._comments = [] 1015 self._prev_token_line = self._line 1016 1017 return True 1018 1019 def _scan_number(self) -> None: 1020 if self._char == "0": 1021 peek = self._peek.upper() 1022 if peek == "B": 1023 return self._scan_bits() if self._BIT_STRINGS else self._add(TokenType.NUMBER) 1024 elif peek == "X": 1025 return self._scan_hex() if self._HEX_STRINGS else self._add(TokenType.NUMBER) 1026 1027 decimal = False 1028 scientific = 0 1029 1030 while True: 1031 if self._peek.isdigit(): 1032 self._advance() 1033 elif self._peek == "." and not decimal: 1034 decimal = True 1035 self._advance() 1036 elif self._peek in ("-", "+") and scientific == 1: 1037 scientific += 1 1038 self._advance() 1039 elif self._peek.upper() == "E" and not scientific: 1040 scientific += 1 1041 self._advance() 1042 elif self._peek.isidentifier(): 1043 number_text = self._text 1044 literal = "" 1045 1046 while self._peek.strip() and self._peek not in self.SINGLE_TOKENS: 1047 literal += self._peek.upper() 1048 self._advance() 1049 1050 token_type = self.KEYWORDS.get(self.NUMERIC_LITERALS.get(literal)) 1051 1052 if token_type: 1053 self._add(TokenType.NUMBER, number_text) 1054 self._add(TokenType.DCOLON, "::") 1055 return self._add(token_type, literal) 1056 elif self.IDENTIFIER_CAN_START_WITH_DIGIT: 1057 return self._add(TokenType.VAR) 1058 1059 self._add(TokenType.NUMBER, number_text) 1060 return self._advance(-len(literal)) 1061 else: 1062 return self._add(TokenType.NUMBER) 1063 1064 def _scan_bits(self) -> None: 1065 self._advance() 1066 value = self._extract_value() 1067 try: 1068 # If `value` can't be converted to a binary, fallback to tokenizing it as an identifier 1069 int(value, 2) 1070 self._add(TokenType.BIT_STRING, value[2:]) # Drop the 0b 1071 except ValueError: 1072 self._add(TokenType.IDENTIFIER) 1073 1074 def _scan_hex(self) -> None: 1075 self._advance() 1076 value = self._extract_value() 1077 try: 1078 # If `value` can't be converted to a hex, fallback to tokenizing it as an identifier 1079 int(value, 16) 1080 self._add(TokenType.HEX_STRING, value[2:]) # Drop the 0x 1081 except ValueError: 1082 self._add(TokenType.IDENTIFIER) 1083 1084 def _extract_value(self) -> str: 1085 while True: 1086 char = self._peek.strip() 1087 if char and char not in self.SINGLE_TOKENS: 1088 self._advance(alnum=True) 1089 else: 1090 break 1091 1092 return self._text 1093 1094 def _scan_string(self, quote: str) -> bool: 1095 quote_end = self._QUOTES.get(quote) 1096 if quote_end is None: 1097 return False 1098 1099 self._advance(len(quote)) 1100 text = self._extract_string(quote_end) 1101 text = text.encode(self.ENCODE).decode(self.ENCODE) if self.ENCODE else text 1102 self._add(TokenType.NATIONAL if quote[0].upper() == "N" else TokenType.STRING, text) 1103 return True 1104 1105 # X'1234', b'0110', E'\\\\\' etc. 1106 def _scan_formatted_string(self, string_start: str) -> bool: 1107 if string_start in self._HEX_STRINGS: 1108 delimiters = self._HEX_STRINGS 1109 token_type = TokenType.HEX_STRING 1110 base = 16 1111 elif string_start in self._BIT_STRINGS: 1112 delimiters = self._BIT_STRINGS 1113 token_type = TokenType.BIT_STRING 1114 base = 2 1115 elif string_start in self._BYTE_STRINGS: 1116 delimiters = self._BYTE_STRINGS 1117 token_type = TokenType.BYTE_STRING 1118 base = None 1119 else: 1120 return False 1121 1122 self._advance(len(string_start)) 1123 string_end = delimiters[string_start] 1124 text = self._extract_string(string_end) 1125 1126 if base: 1127 try: 1128 int(text, base) 1129 except: 1130 raise RuntimeError( 1131 f"Numeric string contains invalid characters from {self._line}:{self._start}" 1132 ) 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 RuntimeError(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 RuntimeError(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
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", "start", "end", "comments") 330 331 @classmethod 332 def number(cls, number: int) -> Token: 333 """Returns a NUMBER token with `number` as its text.""" 334 return cls(TokenType.NUMBER, str(number)) 335 336 @classmethod 337 def string(cls, string: str) -> Token: 338 """Returns a STRING token with `string` as its text.""" 339 return cls(TokenType.STRING, string) 340 341 @classmethod 342 def identifier(cls, identifier: str) -> Token: 343 """Returns an IDENTIFIER token with `identifier` as its text.""" 344 return cls(TokenType.IDENTIFIER, identifier) 345 346 @classmethod 347 def var(cls, var: str) -> Token: 348 """Returns an VAR token with `var` as its text.""" 349 return cls(TokenType.VAR, var) 350 351 def __init__( 352 self, 353 token_type: TokenType, 354 text: str, 355 line: int = 1, 356 col: int = 1, 357 start: int = 0, 358 end: int = 0, 359 comments: t.List[str] = [], 360 ) -> None: 361 """Token initializer. 362 363 Args: 364 token_type: The TokenType Enum. 365 text: The text of the token. 366 line: The line that the token ends on. 367 col: The column that the token ends on. 368 start: The start index of the token. 369 end: The ending index of the token. 370 """ 371 self.token_type = token_type 372 self.text = text 373 self.line = line 374 self.col = col 375 self.start = start 376 self.end = end 377 self.comments = comments 378 379 def __repr__(self) -> str: 380 attributes = ", ".join(f"{k}: {getattr(self, k)}" for k in self.__slots__) 381 return f"<Token {attributes}>"
Token( token_type: sqlglot.tokens.TokenType, text: str, line: int = 1, col: int = 1, start: int = 0, end: int = 0, comments: List[str] = [])
351 def __init__( 352 self, 353 token_type: TokenType, 354 text: str, 355 line: int = 1, 356 col: int = 1, 357 start: int = 0, 358 end: int = 0, 359 comments: t.List[str] = [], 360 ) -> None: 361 """Token initializer. 362 363 Args: 364 token_type: The TokenType Enum. 365 text: The text of the token. 366 line: The line that the token ends on. 367 col: The column that the token ends on. 368 start: The start index of the token. 369 end: The ending index of the token. 370 """ 371 self.token_type = token_type 372 self.text = text 373 self.line = line 374 self.col = col 375 self.start = start 376 self.end = end 377 self.comments = comments
Token initializer.
Arguments:
- token_type: The TokenType Enum.
- text: The text of the token.
- line: The line that the token ends on.
- col: The column that the token ends on.
- start: The start index of the token.
- end: The ending index of the token.
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:
424class Tokenizer(metaclass=_Tokenizer): 425 SINGLE_TOKENS = { 426 "(": TokenType.L_PAREN, 427 ")": TokenType.R_PAREN, 428 "[": TokenType.L_BRACKET, 429 "]": TokenType.R_BRACKET, 430 "{": TokenType.L_BRACE, 431 "}": TokenType.R_BRACE, 432 "&": TokenType.AMP, 433 "^": TokenType.CARET, 434 ":": TokenType.COLON, 435 ",": TokenType.COMMA, 436 ".": TokenType.DOT, 437 "-": TokenType.DASH, 438 "=": TokenType.EQ, 439 ">": TokenType.GT, 440 "<": TokenType.LT, 441 "%": TokenType.MOD, 442 "!": TokenType.NOT, 443 "|": TokenType.PIPE, 444 "+": TokenType.PLUS, 445 ";": TokenType.SEMICOLON, 446 "/": TokenType.SLASH, 447 "\\": TokenType.BACKSLASH, 448 "*": TokenType.STAR, 449 "~": TokenType.TILDA, 450 "?": TokenType.PLACEHOLDER, 451 "@": TokenType.PARAMETER, 452 # used for breaking a var like x'y' but nothing else 453 # the token type doesn't matter 454 "'": TokenType.QUOTE, 455 "`": TokenType.IDENTIFIER, 456 '"': TokenType.IDENTIFIER, 457 "#": TokenType.HASH, 458 } 459 460 BIT_STRINGS: t.List[str | t.Tuple[str, str]] = [] 461 BYTE_STRINGS: t.List[str | t.Tuple[str, str]] = [] 462 HEX_STRINGS: t.List[str | t.Tuple[str, str]] = [] 463 IDENTIFIERS: t.List[str | t.Tuple[str, str]] = ['"'] 464 IDENTIFIER_ESCAPES = ['"'] 465 QUOTES: t.List[t.Tuple[str, str] | str] = ["'"] 466 STRING_ESCAPES = ["'"] 467 VAR_SINGLE_TOKENS: t.Set[str] = set() 468 469 _COMMENTS: t.Dict[str, str] = {} 470 _BIT_STRINGS: t.Dict[str, str] = {} 471 _BYTE_STRINGS: t.Dict[str, str] = {} 472 _HEX_STRINGS: t.Dict[str, str] = {} 473 _IDENTIFIERS: t.Dict[str, str] = {} 474 _IDENTIFIER_ESCAPES: t.Set[str] = set() 475 _QUOTES: t.Dict[str, str] = {} 476 _STRING_ESCAPES: t.Set[str] = set() 477 478 KEYWORDS: t.Dict[t.Optional[str], TokenType] = { 479 **{f"{{%{postfix}": TokenType.BLOCK_START for postfix in ("", "+", "-")}, 480 **{f"{prefix}%}}": TokenType.BLOCK_END for prefix in ("", "+", "-")}, 481 "{{+": TokenType.BLOCK_START, 482 "{{-": TokenType.BLOCK_START, 483 "+}}": TokenType.BLOCK_END, 484 "-}}": TokenType.BLOCK_END, 485 "/*+": TokenType.HINT, 486 "==": TokenType.EQ, 487 "::": TokenType.DCOLON, 488 "||": TokenType.DPIPE, 489 ">=": TokenType.GTE, 490 "<=": TokenType.LTE, 491 "<>": TokenType.NEQ, 492 "!=": TokenType.NEQ, 493 "<=>": TokenType.NULLSAFE_EQ, 494 "->": TokenType.ARROW, 495 "->>": TokenType.DARROW, 496 "=>": TokenType.FARROW, 497 "#>": TokenType.HASH_ARROW, 498 "#>>": TokenType.DHASH_ARROW, 499 "<->": TokenType.LR_ARROW, 500 "&&": TokenType.DAMP, 501 "ALL": TokenType.ALL, 502 "ALWAYS": TokenType.ALWAYS, 503 "AND": TokenType.AND, 504 "ANTI": TokenType.ANTI, 505 "ANY": TokenType.ANY, 506 "ASC": TokenType.ASC, 507 "AS": TokenType.ALIAS, 508 "AT TIME ZONE": TokenType.AT_TIME_ZONE, 509 "AUTOINCREMENT": TokenType.AUTO_INCREMENT, 510 "AUTO_INCREMENT": TokenType.AUTO_INCREMENT, 511 "BEGIN": TokenType.BEGIN, 512 "BETWEEN": TokenType.BETWEEN, 513 "BOTH": TokenType.BOTH, 514 "BUCKET": TokenType.BUCKET, 515 "BY DEFAULT": TokenType.BY_DEFAULT, 516 "CACHE": TokenType.CACHE, 517 "UNCACHE": TokenType.UNCACHE, 518 "CASE": TokenType.CASE, 519 "CASCADE": TokenType.CASCADE, 520 "CHARACTER SET": TokenType.CHARACTER_SET, 521 "CLUSTER BY": TokenType.CLUSTER_BY, 522 "COLLATE": TokenType.COLLATE, 523 "COLUMN": TokenType.COLUMN, 524 "COMMIT": TokenType.COMMIT, 525 "COMPOUND": TokenType.COMPOUND, 526 "CONSTRAINT": TokenType.CONSTRAINT, 527 "CREATE": TokenType.CREATE, 528 "CROSS": TokenType.CROSS, 529 "CUBE": TokenType.CUBE, 530 "CURRENT_DATE": TokenType.CURRENT_DATE, 531 "CURRENT ROW": TokenType.CURRENT_ROW, 532 "CURRENT_TIME": TokenType.CURRENT_TIME, 533 "CURRENT_TIMESTAMP": TokenType.CURRENT_TIMESTAMP, 534 "CURRENT_USER": TokenType.CURRENT_USER, 535 "DATABASE": TokenType.DATABASE, 536 "DEFAULT": TokenType.DEFAULT, 537 "DELETE": TokenType.DELETE, 538 "DESC": TokenType.DESC, 539 "DESCRIBE": TokenType.DESCRIBE, 540 "DISTINCT": TokenType.DISTINCT, 541 "DISTINCT FROM": TokenType.DISTINCT_FROM, 542 "DISTRIBUTE BY": TokenType.DISTRIBUTE_BY, 543 "DIV": TokenType.DIV, 544 "DROP": TokenType.DROP, 545 "ELSE": TokenType.ELSE, 546 "END": TokenType.END, 547 "ESCAPE": TokenType.ESCAPE, 548 "EXCEPT": TokenType.EXCEPT, 549 "EXECUTE": TokenType.EXECUTE, 550 "EXISTS": TokenType.EXISTS, 551 "FALSE": TokenType.FALSE, 552 "FETCH": TokenType.FETCH, 553 "FILTER": TokenType.FILTER, 554 "FIRST": TokenType.FIRST, 555 "FULL": TokenType.FULL, 556 "FUNCTION": TokenType.FUNCTION, 557 "FOLLOWING": TokenType.FOLLOWING, 558 "FOR": TokenType.FOR, 559 "FOREIGN KEY": TokenType.FOREIGN_KEY, 560 "FORMAT": TokenType.FORMAT, 561 "FROM": TokenType.FROM, 562 "GEOGRAPHY": TokenType.GEOGRAPHY, 563 "GEOMETRY": TokenType.GEOMETRY, 564 "GLOB": TokenType.GLOB, 565 "GROUP BY": TokenType.GROUP_BY, 566 "GROUPING SETS": TokenType.GROUPING_SETS, 567 "HAVING": TokenType.HAVING, 568 "IF": TokenType.IF, 569 "ILIKE": TokenType.ILIKE, 570 "IGNORE NULLS": TokenType.IGNORE_NULLS, 571 "IN": TokenType.IN, 572 "INDEX": TokenType.INDEX, 573 "INET": TokenType.INET, 574 "INNER": TokenType.INNER, 575 "INSERT": TokenType.INSERT, 576 "INTERVAL": TokenType.INTERVAL, 577 "INTERSECT": TokenType.INTERSECT, 578 "INTO": TokenType.INTO, 579 "IS": TokenType.IS, 580 "ISNULL": TokenType.ISNULL, 581 "JOIN": TokenType.JOIN, 582 "KEEP": TokenType.KEEP, 583 "LATERAL": TokenType.LATERAL, 584 "LAZY": TokenType.LAZY, 585 "LEADING": TokenType.LEADING, 586 "LEFT": TokenType.LEFT, 587 "LIKE": TokenType.LIKE, 588 "LIMIT": TokenType.LIMIT, 589 "LOAD DATA": TokenType.LOAD_DATA, 590 "LOCAL": TokenType.LOCAL, 591 "LOCK": TokenType.LOCK, 592 "MATERIALIZED": TokenType.MATERIALIZED, 593 "MERGE": TokenType.MERGE, 594 "NATURAL": TokenType.NATURAL, 595 "NEXT": TokenType.NEXT, 596 "NEXT VALUE FOR": TokenType.NEXT_VALUE_FOR, 597 "NO ACTION": TokenType.NO_ACTION, 598 "NOT": TokenType.NOT, 599 "NOTNULL": TokenType.NOTNULL, 600 "NULL": TokenType.NULL, 601 "NULLS FIRST": TokenType.NULLS_FIRST, 602 "NULLS LAST": TokenType.NULLS_LAST, 603 "OBJECT": TokenType.OBJECT, 604 "OFFSET": TokenType.OFFSET, 605 "ON": TokenType.ON, 606 "ONLY": TokenType.ONLY, 607 "OPTIONS": TokenType.OPTIONS, 608 "OR": TokenType.OR, 609 "ORDER BY": TokenType.ORDER_BY, 610 "ORDINALITY": TokenType.ORDINALITY, 611 "OUTER": TokenType.OUTER, 612 "OUT OF": TokenType.OUT_OF, 613 "OVER": TokenType.OVER, 614 "OVERLAPS": TokenType.OVERLAPS, 615 "OVERWRITE": TokenType.OVERWRITE, 616 "PARTITION": TokenType.PARTITION, 617 "PARTITION BY": TokenType.PARTITION_BY, 618 "PARTITIONED BY": TokenType.PARTITION_BY, 619 "PARTITIONED_BY": TokenType.PARTITION_BY, 620 "PERCENT": TokenType.PERCENT, 621 "PIVOT": TokenType.PIVOT, 622 "PRAGMA": TokenType.PRAGMA, 623 "PRECEDING": TokenType.PRECEDING, 624 "PRIMARY KEY": TokenType.PRIMARY_KEY, 625 "PROCEDURE": TokenType.PROCEDURE, 626 "QUALIFY": TokenType.QUALIFY, 627 "RANGE": TokenType.RANGE, 628 "RECURSIVE": TokenType.RECURSIVE, 629 "REGEXP": TokenType.RLIKE, 630 "REPLACE": TokenType.REPLACE, 631 "RESPECT NULLS": TokenType.RESPECT_NULLS, 632 "REFERENCES": TokenType.REFERENCES, 633 "RIGHT": TokenType.RIGHT, 634 "RLIKE": TokenType.RLIKE, 635 "ROLLBACK": TokenType.ROLLBACK, 636 "ROLLUP": TokenType.ROLLUP, 637 "ROW": TokenType.ROW, 638 "ROWS": TokenType.ROWS, 639 "SCHEMA": TokenType.SCHEMA, 640 "SEED": TokenType.SEED, 641 "SELECT": TokenType.SELECT, 642 "SEMI": TokenType.SEMI, 643 "SET": TokenType.SET, 644 "SETTINGS": TokenType.SETTINGS, 645 "SHOW": TokenType.SHOW, 646 "SIMILAR TO": TokenType.SIMILAR_TO, 647 "SOME": TokenType.SOME, 648 "SORTKEY": TokenType.SORTKEY, 649 "SORT BY": TokenType.SORT_BY, 650 "TABLE": TokenType.TABLE, 651 "TABLESAMPLE": TokenType.TABLE_SAMPLE, 652 "TEMP": TokenType.TEMPORARY, 653 "TEMPORARY": TokenType.TEMPORARY, 654 "THEN": TokenType.THEN, 655 "TRUE": TokenType.TRUE, 656 "TRAILING": TokenType.TRAILING, 657 "UNBOUNDED": TokenType.UNBOUNDED, 658 "UNION": TokenType.UNION, 659 "UNLOGGED": TokenType.UNLOGGED, 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 "WITH TIME ZONE": TokenType.WITH_TIME_ZONE, 674 "WITH LOCAL TIME ZONE": TokenType.WITH_LOCAL_TIME_ZONE, 675 "WITHIN GROUP": TokenType.WITHIN_GROUP, 676 "WITHOUT TIME ZONE": TokenType.WITHOUT_TIME_ZONE, 677 "APPLY": TokenType.APPLY, 678 "ARRAY": TokenType.ARRAY, 679 "BIT": TokenType.BIT, 680 "BOOL": TokenType.BOOLEAN, 681 "BOOLEAN": TokenType.BOOLEAN, 682 "BYTE": TokenType.TINYINT, 683 "TINYINT": TokenType.TINYINT, 684 "SHORT": TokenType.SMALLINT, 685 "SMALLINT": TokenType.SMALLINT, 686 "INT2": TokenType.SMALLINT, 687 "INTEGER": TokenType.INT, 688 "INT": TokenType.INT, 689 "INT4": TokenType.INT, 690 "LONG": TokenType.BIGINT, 691 "BIGINT": TokenType.BIGINT, 692 "INT8": TokenType.BIGINT, 693 "DEC": TokenType.DECIMAL, 694 "DECIMAL": TokenType.DECIMAL, 695 "BIGDECIMAL": TokenType.BIGDECIMAL, 696 "BIGNUMERIC": TokenType.BIGDECIMAL, 697 "MAP": TokenType.MAP, 698 "NULLABLE": TokenType.NULLABLE, 699 "NUMBER": TokenType.DECIMAL, 700 "NUMERIC": TokenType.DECIMAL, 701 "FIXED": TokenType.DECIMAL, 702 "REAL": TokenType.FLOAT, 703 "FLOAT": TokenType.FLOAT, 704 "FLOAT4": TokenType.FLOAT, 705 "FLOAT8": TokenType.DOUBLE, 706 "DOUBLE": TokenType.DOUBLE, 707 "DOUBLE PRECISION": TokenType.DOUBLE, 708 "JSON": TokenType.JSON, 709 "CHAR": TokenType.CHAR, 710 "CHARACTER": TokenType.CHAR, 711 "NCHAR": TokenType.NCHAR, 712 "VARCHAR": TokenType.VARCHAR, 713 "VARCHAR2": TokenType.VARCHAR, 714 "NVARCHAR": TokenType.NVARCHAR, 715 "NVARCHAR2": TokenType.NVARCHAR, 716 "STR": TokenType.TEXT, 717 "STRING": TokenType.TEXT, 718 "TEXT": TokenType.TEXT, 719 "CLOB": TokenType.TEXT, 720 "LONGVARCHAR": TokenType.TEXT, 721 "BINARY": TokenType.BINARY, 722 "BLOB": TokenType.VARBINARY, 723 "BYTEA": TokenType.VARBINARY, 724 "VARBINARY": TokenType.VARBINARY, 725 "TIME": TokenType.TIME, 726 "TIMESTAMP": TokenType.TIMESTAMP, 727 "TIMESTAMPTZ": TokenType.TIMESTAMPTZ, 728 "TIMESTAMPLTZ": TokenType.TIMESTAMPLTZ, 729 "DATE": TokenType.DATE, 730 "DATETIME": TokenType.DATETIME, 731 "UNIQUE": TokenType.UNIQUE, 732 "STRUCT": TokenType.STRUCT, 733 "VARIANT": TokenType.VARIANT, 734 "ALTER": TokenType.ALTER, 735 "ALTER AGGREGATE": TokenType.COMMAND, 736 "ALTER DEFAULT": TokenType.COMMAND, 737 "ALTER DOMAIN": TokenType.COMMAND, 738 "ALTER ROLE": TokenType.COMMAND, 739 "ALTER RULE": TokenType.COMMAND, 740 "ALTER SEQUENCE": TokenType.COMMAND, 741 "ALTER TYPE": TokenType.COMMAND, 742 "ALTER USER": TokenType.COMMAND, 743 "ALTER VIEW": TokenType.COMMAND, 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 } 755 756 WHITE_SPACE: t.Dict[t.Optional[str], TokenType] = { 757 " ": TokenType.SPACE, 758 "\t": TokenType.SPACE, 759 "\n": TokenType.BREAK, 760 "\r": TokenType.BREAK, 761 "\r\n": TokenType.BREAK, 762 } 763 764 COMMANDS = { 765 TokenType.COMMAND, 766 TokenType.EXECUTE, 767 TokenType.FETCH, 768 TokenType.SHOW, 769 } 770 771 COMMAND_PREFIX_TOKENS = {TokenType.SEMICOLON, TokenType.BEGIN} 772 773 # handle numeric literals like in hive (3L = BIGINT) 774 NUMERIC_LITERALS: t.Dict[str, str] = {} 775 ENCODE: t.Optional[str] = None 776 777 COMMENTS = ["--", ("/*", "*/"), ("{#", "#}")] 778 KEYWORD_TRIE: t.Dict = {} # autofilled 779 780 IDENTIFIER_CAN_START_WITH_DIGIT = False 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 ValueError(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 _add(self, token_type: TokenType, text: t.Optional[str] = None) -> None: 898 self._prev_token_line = self._line 899 self.tokens.append( 900 Token( 901 token_type, 902 text=self._text if text is None else text, 903 line=self._line, 904 col=self._col, 905 start=self._start, 906 end=self._current - 1, 907 comments=self._comments, 908 ) 909 ) 910 self._comments = [] 911 912 # If we have either a semicolon or a begin token before the command's token, we'll parse 913 # whatever follows the command's token as a string 914 if ( 915 token_type in self.COMMANDS 916 and self._peek != ";" 917 and (len(self.tokens) == 1 or self.tokens[-2].token_type in self.COMMAND_PREFIX_TOKENS) 918 ): 919 start = self._current 920 tokens = len(self.tokens) 921 self._scan(lambda: self._peek == ";") 922 self.tokens = self.tokens[:tokens] 923 text = self.sql[start : self._current].strip() 924 if text: 925 self._add(TokenType.STRING, text) 926 927 def _scan_keywords(self) -> None: 928 size = 0 929 word = None 930 chars = self._text 931 char = chars 932 prev_space = False 933 skip = False 934 trie = self.KEYWORD_TRIE 935 single_token = char in self.SINGLE_TOKENS 936 937 while chars: 938 if skip: 939 result = 1 940 else: 941 result, trie = in_trie(trie, char.upper()) 942 943 if result == 0: 944 break 945 if result == 2: 946 word = chars 947 948 size += 1 949 end = self._current - 1 + size 950 951 if end < self.size: 952 char = self.sql[end] 953 single_token = single_token or char in self.SINGLE_TOKENS 954 is_space = char in self.WHITE_SPACE 955 956 if not is_space or not prev_space: 957 if is_space: 958 char = " " 959 chars += char 960 prev_space = is_space 961 skip = False 962 else: 963 skip = True 964 else: 965 char = "" 966 chars = " " 967 968 word = None if not single_token and chars[-1] not in self.WHITE_SPACE else word 969 970 if not word: 971 if self._char in self.SINGLE_TOKENS: 972 self._add(self.SINGLE_TOKENS[self._char], text=self._char) 973 return 974 self._scan_var() 975 return 976 977 if self._scan_string(word): 978 return 979 if self._scan_formatted_string(word): 980 return 981 if self._scan_comment(word): 982 return 983 984 self._advance(size - 1) 985 word = word.upper() 986 self._add(self.KEYWORDS[word], text=word) 987 988 def _scan_comment(self, comment_start: str) -> bool: 989 if comment_start not in self._COMMENTS: 990 return False 991 992 comment_start_line = self._line 993 comment_start_size = len(comment_start) 994 comment_end = self._COMMENTS[comment_start] 995 996 if comment_end: 997 # Skip the comment's start delimiter 998 self._advance(comment_start_size) 999 1000 comment_end_size = len(comment_end) 1001 while not self._end and self._chars(comment_end_size) != comment_end: 1002 self._advance(alnum=True) 1003 1004 self._comments.append(self._text[comment_start_size : -comment_end_size + 1]) 1005 self._advance(comment_end_size - 1) 1006 else: 1007 while not self._end and not self.WHITE_SPACE.get(self._peek) is TokenType.BREAK: 1008 self._advance(alnum=True) 1009 self._comments.append(self._text[comment_start_size:]) 1010 1011 # Leading comment is attached to the succeeding token, whilst trailing comment to the preceding. 1012 # Multiple consecutive comments are preserved by appending them to the current comments list. 1013 if comment_start_line == self._prev_token_line: 1014 self.tokens[-1].comments.extend(self._comments) 1015 self._comments = [] 1016 self._prev_token_line = self._line 1017 1018 return True 1019 1020 def _scan_number(self) -> None: 1021 if self._char == "0": 1022 peek = self._peek.upper() 1023 if peek == "B": 1024 return self._scan_bits() if self._BIT_STRINGS else self._add(TokenType.NUMBER) 1025 elif peek == "X": 1026 return self._scan_hex() if self._HEX_STRINGS else self._add(TokenType.NUMBER) 1027 1028 decimal = False 1029 scientific = 0 1030 1031 while True: 1032 if self._peek.isdigit(): 1033 self._advance() 1034 elif self._peek == "." and not decimal: 1035 decimal = True 1036 self._advance() 1037 elif self._peek in ("-", "+") and scientific == 1: 1038 scientific += 1 1039 self._advance() 1040 elif self._peek.upper() == "E" and not scientific: 1041 scientific += 1 1042 self._advance() 1043 elif self._peek.isidentifier(): 1044 number_text = self._text 1045 literal = "" 1046 1047 while self._peek.strip() and self._peek not in self.SINGLE_TOKENS: 1048 literal += self._peek.upper() 1049 self._advance() 1050 1051 token_type = self.KEYWORDS.get(self.NUMERIC_LITERALS.get(literal)) 1052 1053 if token_type: 1054 self._add(TokenType.NUMBER, number_text) 1055 self._add(TokenType.DCOLON, "::") 1056 return self._add(token_type, literal) 1057 elif self.IDENTIFIER_CAN_START_WITH_DIGIT: 1058 return self._add(TokenType.VAR) 1059 1060 self._add(TokenType.NUMBER, number_text) 1061 return self._advance(-len(literal)) 1062 else: 1063 return self._add(TokenType.NUMBER) 1064 1065 def _scan_bits(self) -> None: 1066 self._advance() 1067 value = self._extract_value() 1068 try: 1069 # If `value` can't be converted to a binary, fallback to tokenizing it as an identifier 1070 int(value, 2) 1071 self._add(TokenType.BIT_STRING, value[2:]) # Drop the 0b 1072 except ValueError: 1073 self._add(TokenType.IDENTIFIER) 1074 1075 def _scan_hex(self) -> None: 1076 self._advance() 1077 value = self._extract_value() 1078 try: 1079 # If `value` can't be converted to a hex, fallback to tokenizing it as an identifier 1080 int(value, 16) 1081 self._add(TokenType.HEX_STRING, value[2:]) # Drop the 0x 1082 except ValueError: 1083 self._add(TokenType.IDENTIFIER) 1084 1085 def _extract_value(self) -> str: 1086 while True: 1087 char = self._peek.strip() 1088 if char and char not in self.SINGLE_TOKENS: 1089 self._advance(alnum=True) 1090 else: 1091 break 1092 1093 return self._text 1094 1095 def _scan_string(self, quote: str) -> bool: 1096 quote_end = self._QUOTES.get(quote) 1097 if quote_end is None: 1098 return False 1099 1100 self._advance(len(quote)) 1101 text = self._extract_string(quote_end) 1102 text = text.encode(self.ENCODE).decode(self.ENCODE) if self.ENCODE else text 1103 self._add(TokenType.NATIONAL if quote[0].upper() == "N" else TokenType.STRING, text) 1104 return True 1105 1106 # X'1234', b'0110', E'\\\\\' etc. 1107 def _scan_formatted_string(self, string_start: str) -> bool: 1108 if string_start in self._HEX_STRINGS: 1109 delimiters = self._HEX_STRINGS 1110 token_type = TokenType.HEX_STRING 1111 base = 16 1112 elif string_start in self._BIT_STRINGS: 1113 delimiters = self._BIT_STRINGS 1114 token_type = TokenType.BIT_STRING 1115 base = 2 1116 elif string_start in self._BYTE_STRINGS: 1117 delimiters = self._BYTE_STRINGS 1118 token_type = TokenType.BYTE_STRING 1119 base = None 1120 else: 1121 return False 1122 1123 self._advance(len(string_start)) 1124 string_end = delimiters[string_start] 1125 text = self._extract_string(string_end) 1126 1127 if base: 1128 try: 1129 int(text, base) 1130 except: 1131 raise RuntimeError( 1132 f"Numeric string contains invalid characters from {self._line}:{self._start}" 1133 ) 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 RuntimeError(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 RuntimeError(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
def
reset(self) -> None:
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
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 ValueError(f"Error tokenizing '{context}'") from e 828 829 return self.tokens
Returns a list of tokens corresponding to the SQL string sql
.