sqlglot.tokens
1from __future__ import annotations 2 3import typing as t 4from enum import auto 5 6from sqlglot.errors import TokenError 7from sqlglot.helper import AutoName 8from sqlglot.trie import TrieResult, in_trie, new_trie 9 10if t.TYPE_CHECKING: 11 from sqlglot.dialects.dialect import DialectType 12 13 14class TokenType(AutoName): 15 L_PAREN = auto() 16 R_PAREN = auto() 17 L_BRACKET = auto() 18 R_BRACKET = auto() 19 L_BRACE = auto() 20 R_BRACE = auto() 21 COMMA = auto() 22 DOT = auto() 23 DASH = auto() 24 PLUS = auto() 25 COLON = auto() 26 DCOLON = auto() 27 DQMARK = auto() 28 SEMICOLON = auto() 29 STAR = auto() 30 BACKSLASH = auto() 31 SLASH = auto() 32 LT = auto() 33 LTE = auto() 34 GT = auto() 35 GTE = auto() 36 NOT = auto() 37 EQ = auto() 38 NEQ = auto() 39 NULLSAFE_EQ = auto() 40 COLON_EQ = auto() 41 AND = auto() 42 OR = auto() 43 AMP = auto() 44 DPIPE = auto() 45 PIPE = auto() 46 CARET = auto() 47 TILDA = auto() 48 ARROW = auto() 49 DARROW = auto() 50 FARROW = auto() 51 HASH = auto() 52 HASH_ARROW = auto() 53 DHASH_ARROW = auto() 54 LR_ARROW = auto() 55 DAT = auto() 56 LT_AT = auto() 57 AT_GT = auto() 58 DOLLAR = auto() 59 PARAMETER = auto() 60 SESSION_PARAMETER = auto() 61 DAMP = auto() 62 XOR = auto() 63 DSTAR = auto() 64 65 BLOCK_START = auto() 66 BLOCK_END = auto() 67 68 SPACE = auto() 69 BREAK = auto() 70 71 STRING = auto() 72 NUMBER = auto() 73 IDENTIFIER = auto() 74 DATABASE = auto() 75 COLUMN = auto() 76 COLUMN_DEF = auto() 77 SCHEMA = auto() 78 TABLE = auto() 79 VAR = auto() 80 BIT_STRING = auto() 81 HEX_STRING = auto() 82 BYTE_STRING = auto() 83 NATIONAL_STRING = auto() 84 RAW_STRING = auto() 85 HEREDOC_STRING = auto() 86 87 # types 88 BIT = auto() 89 BOOLEAN = auto() 90 TINYINT = auto() 91 UTINYINT = auto() 92 SMALLINT = auto() 93 USMALLINT = auto() 94 MEDIUMINT = auto() 95 UMEDIUMINT = auto() 96 INT = auto() 97 UINT = auto() 98 BIGINT = auto() 99 UBIGINT = auto() 100 INT128 = auto() 101 UINT128 = auto() 102 INT256 = auto() 103 UINT256 = auto() 104 FLOAT = auto() 105 DOUBLE = auto() 106 DECIMAL = auto() 107 UDECIMAL = auto() 108 BIGDECIMAL = auto() 109 CHAR = auto() 110 NCHAR = auto() 111 VARCHAR = auto() 112 NVARCHAR = auto() 113 TEXT = auto() 114 MEDIUMTEXT = auto() 115 LONGTEXT = auto() 116 MEDIUMBLOB = auto() 117 LONGBLOB = auto() 118 TINYBLOB = auto() 119 TINYTEXT = auto() 120 BINARY = auto() 121 VARBINARY = auto() 122 JSON = auto() 123 JSONB = auto() 124 TIME = auto() 125 TIMETZ = auto() 126 TIMESTAMP = auto() 127 TIMESTAMPTZ = auto() 128 TIMESTAMPLTZ = auto() 129 TIMESTAMP_S = auto() 130 TIMESTAMP_MS = auto() 131 TIMESTAMP_NS = auto() 132 DATETIME = auto() 133 DATETIME64 = auto() 134 DATE = auto() 135 INT4RANGE = auto() 136 INT4MULTIRANGE = auto() 137 INT8RANGE = auto() 138 INT8MULTIRANGE = auto() 139 NUMRANGE = auto() 140 NUMMULTIRANGE = auto() 141 TSRANGE = auto() 142 TSMULTIRANGE = auto() 143 TSTZRANGE = auto() 144 TSTZMULTIRANGE = auto() 145 DATERANGE = auto() 146 DATEMULTIRANGE = auto() 147 UUID = auto() 148 GEOGRAPHY = auto() 149 NULLABLE = auto() 150 GEOMETRY = auto() 151 HLLSKETCH = auto() 152 HSTORE = auto() 153 SUPER = auto() 154 SERIAL = auto() 155 SMALLSERIAL = auto() 156 BIGSERIAL = auto() 157 XML = auto() 158 YEAR = auto() 159 UNIQUEIDENTIFIER = auto() 160 USERDEFINED = auto() 161 MONEY = auto() 162 SMALLMONEY = auto() 163 ROWVERSION = auto() 164 IMAGE = auto() 165 VARIANT = auto() 166 OBJECT = auto() 167 INET = auto() 168 IPADDRESS = auto() 169 IPPREFIX = auto() 170 ENUM = auto() 171 ENUM8 = auto() 172 ENUM16 = auto() 173 FIXEDSTRING = auto() 174 LOWCARDINALITY = auto() 175 NESTED = auto() 176 UNKNOWN = auto() 177 178 # keywords 179 ALIAS = auto() 180 ALTER = auto() 181 ALWAYS = auto() 182 ALL = auto() 183 ANTI = auto() 184 ANY = auto() 185 APPLY = auto() 186 ARRAY = auto() 187 ASC = auto() 188 ASOF = auto() 189 AUTO_INCREMENT = auto() 190 BEGIN = auto() 191 BETWEEN = auto() 192 CACHE = auto() 193 CASE = auto() 194 CHARACTER_SET = auto() 195 CLUSTER_BY = auto() 196 COLLATE = auto() 197 COMMAND = auto() 198 COMMENT = auto() 199 COMMIT = auto() 200 CONNECT_BY = auto() 201 CONSTRAINT = auto() 202 CREATE = auto() 203 CROSS = auto() 204 CUBE = auto() 205 CURRENT_DATE = auto() 206 CURRENT_DATETIME = auto() 207 CURRENT_TIME = auto() 208 CURRENT_TIMESTAMP = auto() 209 CURRENT_USER = auto() 210 DEFAULT = auto() 211 DELETE = auto() 212 DESC = auto() 213 DESCRIBE = auto() 214 DICTIONARY = auto() 215 DISTINCT = auto() 216 DISTRIBUTE_BY = auto() 217 DIV = auto() 218 DROP = auto() 219 ELSE = auto() 220 END = auto() 221 ESCAPE = auto() 222 EXCEPT = auto() 223 EXECUTE = auto() 224 EXISTS = auto() 225 FALSE = auto() 226 FETCH = auto() 227 FILTER = auto() 228 FINAL = auto() 229 FIRST = auto() 230 FOR = auto() 231 FORCE = auto() 232 FOREIGN_KEY = auto() 233 FORMAT = auto() 234 FROM = auto() 235 FULL = auto() 236 FUNCTION = auto() 237 GLOB = auto() 238 GLOBAL = auto() 239 GROUP_BY = auto() 240 GROUPING_SETS = auto() 241 HAVING = auto() 242 HINT = auto() 243 IGNORE = auto() 244 ILIKE = auto() 245 ILIKE_ANY = auto() 246 IN = auto() 247 INDEX = auto() 248 INNER = auto() 249 INSERT = auto() 250 INTERSECT = auto() 251 INTERVAL = auto() 252 INTO = auto() 253 INTRODUCER = auto() 254 IRLIKE = auto() 255 IS = auto() 256 ISNULL = auto() 257 JOIN = auto() 258 JOIN_MARKER = auto() 259 KEEP = auto() 260 KILL = auto() 261 LANGUAGE = auto() 262 LATERAL = auto() 263 LEFT = auto() 264 LIKE = auto() 265 LIKE_ANY = auto() 266 LIMIT = auto() 267 LOAD = auto() 268 LOCK = auto() 269 MAP = auto() 270 MATCH_RECOGNIZE = auto() 271 MEMBER_OF = auto() 272 MERGE = auto() 273 MOD = auto() 274 MODEL = auto() 275 NATURAL = auto() 276 NEXT = auto() 277 NOTNULL = auto() 278 NULL = auto() 279 OBJECT_IDENTIFIER = auto() 280 OFFSET = auto() 281 ON = auto() 282 OPERATOR = auto() 283 ORDER_BY = auto() 284 ORDERED = auto() 285 ORDINALITY = auto() 286 OUTER = auto() 287 OVER = auto() 288 OVERLAPS = auto() 289 OVERWRITE = auto() 290 PARTITION = auto() 291 PARTITION_BY = auto() 292 PERCENT = auto() 293 PIVOT = auto() 294 PLACEHOLDER = auto() 295 PRAGMA = auto() 296 PRIMARY_KEY = auto() 297 PROCEDURE = auto() 298 PROPERTIES = auto() 299 PSEUDO_TYPE = auto() 300 QUALIFY = auto() 301 QUOTE = auto() 302 RANGE = auto() 303 RECURSIVE = auto() 304 REFRESH = auto() 305 REPLACE = auto() 306 RETURNING = auto() 307 REFERENCES = auto() 308 RIGHT = auto() 309 RLIKE = auto() 310 ROLLBACK = auto() 311 ROLLUP = auto() 312 ROW = auto() 313 ROWS = auto() 314 SELECT = auto() 315 SEMI = auto() 316 SEPARATOR = auto() 317 SERDE_PROPERTIES = auto() 318 SET = auto() 319 SETTINGS = auto() 320 SHOW = auto() 321 SIMILAR_TO = auto() 322 SOME = auto() 323 SORT_BY = auto() 324 START_WITH = auto() 325 STRUCT = auto() 326 TABLE_SAMPLE = auto() 327 TEMPORARY = auto() 328 TOP = auto() 329 THEN = auto() 330 TRUE = auto() 331 UNCACHE = auto() 332 UNION = auto() 333 UNNEST = auto() 334 UNPIVOT = auto() 335 UPDATE = auto() 336 USE = auto() 337 USING = auto() 338 VALUES = auto() 339 VIEW = auto() 340 VOLATILE = auto() 341 WHEN = auto() 342 WHERE = auto() 343 WINDOW = auto() 344 WITH = auto() 345 UNIQUE = auto() 346 VERSION_SNAPSHOT = auto() 347 TIMESTAMP_SNAPSHOT = auto() 348 349 350class Token: 351 __slots__ = ("token_type", "text", "line", "col", "start", "end", "comments") 352 353 @classmethod 354 def number(cls, number: int) -> Token: 355 """Returns a NUMBER token with `number` as its text.""" 356 return cls(TokenType.NUMBER, str(number)) 357 358 @classmethod 359 def string(cls, string: str) -> Token: 360 """Returns a STRING token with `string` as its text.""" 361 return cls(TokenType.STRING, string) 362 363 @classmethod 364 def identifier(cls, identifier: str) -> Token: 365 """Returns an IDENTIFIER token with `identifier` as its text.""" 366 return cls(TokenType.IDENTIFIER, identifier) 367 368 @classmethod 369 def var(cls, var: str) -> Token: 370 """Returns an VAR token with `var` as its text.""" 371 return cls(TokenType.VAR, var) 372 373 def __init__( 374 self, 375 token_type: TokenType, 376 text: str, 377 line: int = 1, 378 col: int = 1, 379 start: int = 0, 380 end: int = 0, 381 comments: t.Optional[t.List[str]] = None, 382 ) -> None: 383 """Token initializer. 384 385 Args: 386 token_type: The TokenType Enum. 387 text: The text of the token. 388 line: The line that the token ends on. 389 col: The column that the token ends on. 390 start: The start index of the token. 391 end: The ending index of the token. 392 comments: The comments to attach to the token. 393 """ 394 self.token_type = token_type 395 self.text = text 396 self.line = line 397 self.col = col 398 self.start = start 399 self.end = end 400 self.comments = [] if comments is None else comments 401 402 def __repr__(self) -> str: 403 attributes = ", ".join(f"{k}: {getattr(self, k)}" for k in self.__slots__) 404 return f"<Token {attributes}>" 405 406 407class _Tokenizer(type): 408 def __new__(cls, clsname, bases, attrs): 409 klass = super().__new__(cls, clsname, bases, attrs) 410 411 def _convert_quotes(arr: t.List[str | t.Tuple[str, str]]) -> t.Dict[str, str]: 412 return dict( 413 (item, item) if isinstance(item, str) else (item[0], item[1]) for item in arr 414 ) 415 416 def _quotes_to_format( 417 token_type: TokenType, arr: t.List[str | t.Tuple[str, str]] 418 ) -> t.Dict[str, t.Tuple[str, TokenType]]: 419 return {k: (v, token_type) for k, v in _convert_quotes(arr).items()} 420 421 klass._QUOTES = _convert_quotes(klass.QUOTES) 422 klass._IDENTIFIERS = _convert_quotes(klass.IDENTIFIERS) 423 424 klass._FORMAT_STRINGS = { 425 **{ 426 p + s: (e, TokenType.NATIONAL_STRING) 427 for s, e in klass._QUOTES.items() 428 for p in ("n", "N") 429 }, 430 **_quotes_to_format(TokenType.BIT_STRING, klass.BIT_STRINGS), 431 **_quotes_to_format(TokenType.BYTE_STRING, klass.BYTE_STRINGS), 432 **_quotes_to_format(TokenType.HEX_STRING, klass.HEX_STRINGS), 433 **_quotes_to_format(TokenType.RAW_STRING, klass.RAW_STRINGS), 434 **_quotes_to_format(TokenType.HEREDOC_STRING, klass.HEREDOC_STRINGS), 435 } 436 437 klass._STRING_ESCAPES = set(klass.STRING_ESCAPES) 438 klass._IDENTIFIER_ESCAPES = set(klass.IDENTIFIER_ESCAPES) 439 klass._COMMENTS = { 440 **dict( 441 (comment, None) if isinstance(comment, str) else (comment[0], comment[1]) 442 for comment in klass.COMMENTS 443 ), 444 "{#": "#}", # Ensure Jinja comments are tokenized correctly in all dialects 445 } 446 447 klass._KEYWORD_TRIE = new_trie( 448 key.upper() 449 for key in ( 450 *klass.KEYWORDS, 451 *klass._COMMENTS, 452 *klass._QUOTES, 453 *klass._FORMAT_STRINGS, 454 ) 455 if " " in key or any(single in key for single in klass.SINGLE_TOKENS) 456 ) 457 458 return klass 459 460 461class Tokenizer(metaclass=_Tokenizer): 462 SINGLE_TOKENS = { 463 "(": TokenType.L_PAREN, 464 ")": TokenType.R_PAREN, 465 "[": TokenType.L_BRACKET, 466 "]": TokenType.R_BRACKET, 467 "{": TokenType.L_BRACE, 468 "}": TokenType.R_BRACE, 469 "&": TokenType.AMP, 470 "^": TokenType.CARET, 471 ":": TokenType.COLON, 472 ",": TokenType.COMMA, 473 ".": TokenType.DOT, 474 "-": TokenType.DASH, 475 "=": TokenType.EQ, 476 ">": TokenType.GT, 477 "<": TokenType.LT, 478 "%": TokenType.MOD, 479 "!": TokenType.NOT, 480 "|": TokenType.PIPE, 481 "+": TokenType.PLUS, 482 ";": TokenType.SEMICOLON, 483 "/": TokenType.SLASH, 484 "\\": TokenType.BACKSLASH, 485 "*": TokenType.STAR, 486 "~": TokenType.TILDA, 487 "?": TokenType.PLACEHOLDER, 488 "@": TokenType.PARAMETER, 489 # used for breaking a var like x'y' but nothing else 490 # the token type doesn't matter 491 "'": TokenType.QUOTE, 492 "`": TokenType.IDENTIFIER, 493 '"': TokenType.IDENTIFIER, 494 "#": TokenType.HASH, 495 } 496 497 BIT_STRINGS: t.List[str | t.Tuple[str, str]] = [] 498 BYTE_STRINGS: t.List[str | t.Tuple[str, str]] = [] 499 HEX_STRINGS: t.List[str | t.Tuple[str, str]] = [] 500 RAW_STRINGS: t.List[str | t.Tuple[str, str]] = [] 501 HEREDOC_STRINGS: t.List[str | t.Tuple[str, str]] = [] 502 IDENTIFIERS: t.List[str | t.Tuple[str, str]] = ['"'] 503 IDENTIFIER_ESCAPES = ['"'] 504 QUOTES: t.List[t.Tuple[str, str] | str] = ["'"] 505 STRING_ESCAPES = ["'"] 506 VAR_SINGLE_TOKENS: t.Set[str] = set() 507 508 # Autofilled 509 _COMMENTS: t.Dict[str, str] = {} 510 _FORMAT_STRINGS: t.Dict[str, t.Tuple[str, TokenType]] = {} 511 _IDENTIFIERS: t.Dict[str, str] = {} 512 _IDENTIFIER_ESCAPES: t.Set[str] = set() 513 _QUOTES: t.Dict[str, str] = {} 514 _STRING_ESCAPES: t.Set[str] = set() 515 _KEYWORD_TRIE: t.Dict = {} 516 517 KEYWORDS: t.Dict[str, TokenType] = { 518 **{f"{{%{postfix}": TokenType.BLOCK_START for postfix in ("", "+", "-")}, 519 **{f"{prefix}%}}": TokenType.BLOCK_END for prefix in ("", "+", "-")}, 520 **{f"{{{{{postfix}": TokenType.BLOCK_START for postfix in ("+", "-")}, 521 **{f"{prefix}}}}}": TokenType.BLOCK_END for prefix in ("+", "-")}, 522 "/*+": TokenType.HINT, 523 "==": TokenType.EQ, 524 "::": TokenType.DCOLON, 525 "||": TokenType.DPIPE, 526 ">=": TokenType.GTE, 527 "<=": TokenType.LTE, 528 "<>": TokenType.NEQ, 529 "!=": TokenType.NEQ, 530 ":=": TokenType.COLON_EQ, 531 "<=>": TokenType.NULLSAFE_EQ, 532 "->": TokenType.ARROW, 533 "->>": TokenType.DARROW, 534 "=>": TokenType.FARROW, 535 "#>": TokenType.HASH_ARROW, 536 "#>>": TokenType.DHASH_ARROW, 537 "<->": TokenType.LR_ARROW, 538 "&&": TokenType.DAMP, 539 "??": TokenType.DQMARK, 540 "ALL": TokenType.ALL, 541 "ALWAYS": TokenType.ALWAYS, 542 "AND": TokenType.AND, 543 "ANTI": TokenType.ANTI, 544 "ANY": TokenType.ANY, 545 "ASC": TokenType.ASC, 546 "AS": TokenType.ALIAS, 547 "ASOF": TokenType.ASOF, 548 "AUTOINCREMENT": TokenType.AUTO_INCREMENT, 549 "AUTO_INCREMENT": TokenType.AUTO_INCREMENT, 550 "BEGIN": TokenType.BEGIN, 551 "BETWEEN": TokenType.BETWEEN, 552 "CACHE": TokenType.CACHE, 553 "UNCACHE": TokenType.UNCACHE, 554 "CASE": TokenType.CASE, 555 "CHARACTER SET": TokenType.CHARACTER_SET, 556 "CLUSTER BY": TokenType.CLUSTER_BY, 557 "COLLATE": TokenType.COLLATE, 558 "COLUMN": TokenType.COLUMN, 559 "COMMIT": TokenType.COMMIT, 560 "CONNECT BY": TokenType.CONNECT_BY, 561 "CONSTRAINT": TokenType.CONSTRAINT, 562 "CREATE": TokenType.CREATE, 563 "CROSS": TokenType.CROSS, 564 "CUBE": TokenType.CUBE, 565 "CURRENT_DATE": TokenType.CURRENT_DATE, 566 "CURRENT_TIME": TokenType.CURRENT_TIME, 567 "CURRENT_TIMESTAMP": TokenType.CURRENT_TIMESTAMP, 568 "CURRENT_USER": TokenType.CURRENT_USER, 569 "DATABASE": TokenType.DATABASE, 570 "DEFAULT": TokenType.DEFAULT, 571 "DELETE": TokenType.DELETE, 572 "DESC": TokenType.DESC, 573 "DESCRIBE": TokenType.DESCRIBE, 574 "DISTINCT": TokenType.DISTINCT, 575 "DISTRIBUTE BY": TokenType.DISTRIBUTE_BY, 576 "DIV": TokenType.DIV, 577 "DROP": TokenType.DROP, 578 "ELSE": TokenType.ELSE, 579 "END": TokenType.END, 580 "ESCAPE": TokenType.ESCAPE, 581 "EXCEPT": TokenType.EXCEPT, 582 "EXECUTE": TokenType.EXECUTE, 583 "EXISTS": TokenType.EXISTS, 584 "FALSE": TokenType.FALSE, 585 "FETCH": TokenType.FETCH, 586 "FILTER": TokenType.FILTER, 587 "FIRST": TokenType.FIRST, 588 "FULL": TokenType.FULL, 589 "FUNCTION": TokenType.FUNCTION, 590 "FOR": TokenType.FOR, 591 "FOREIGN KEY": TokenType.FOREIGN_KEY, 592 "FORMAT": TokenType.FORMAT, 593 "FROM": TokenType.FROM, 594 "GEOGRAPHY": TokenType.GEOGRAPHY, 595 "GEOMETRY": TokenType.GEOMETRY, 596 "GLOB": TokenType.GLOB, 597 "GROUP BY": TokenType.GROUP_BY, 598 "GROUPING SETS": TokenType.GROUPING_SETS, 599 "HAVING": TokenType.HAVING, 600 "ILIKE": TokenType.ILIKE, 601 "IN": TokenType.IN, 602 "INDEX": TokenType.INDEX, 603 "INET": TokenType.INET, 604 "INNER": TokenType.INNER, 605 "INSERT": TokenType.INSERT, 606 "INTERVAL": TokenType.INTERVAL, 607 "INTERSECT": TokenType.INTERSECT, 608 "INTO": TokenType.INTO, 609 "IS": TokenType.IS, 610 "ISNULL": TokenType.ISNULL, 611 "JOIN": TokenType.JOIN, 612 "KEEP": TokenType.KEEP, 613 "KILL": TokenType.KILL, 614 "LATERAL": TokenType.LATERAL, 615 "LEFT": TokenType.LEFT, 616 "LIKE": TokenType.LIKE, 617 "LIMIT": TokenType.LIMIT, 618 "LOAD": TokenType.LOAD, 619 "LOCK": TokenType.LOCK, 620 "MERGE": TokenType.MERGE, 621 "NATURAL": TokenType.NATURAL, 622 "NEXT": TokenType.NEXT, 623 "NOT": TokenType.NOT, 624 "NOTNULL": TokenType.NOTNULL, 625 "NULL": TokenType.NULL, 626 "OBJECT": TokenType.OBJECT, 627 "OFFSET": TokenType.OFFSET, 628 "ON": TokenType.ON, 629 "OR": TokenType.OR, 630 "XOR": TokenType.XOR, 631 "ORDER BY": TokenType.ORDER_BY, 632 "ORDINALITY": TokenType.ORDINALITY, 633 "OUTER": TokenType.OUTER, 634 "OVER": TokenType.OVER, 635 "OVERLAPS": TokenType.OVERLAPS, 636 "OVERWRITE": TokenType.OVERWRITE, 637 "PARTITION": TokenType.PARTITION, 638 "PARTITION BY": TokenType.PARTITION_BY, 639 "PARTITIONED BY": TokenType.PARTITION_BY, 640 "PARTITIONED_BY": TokenType.PARTITION_BY, 641 "PERCENT": TokenType.PERCENT, 642 "PIVOT": TokenType.PIVOT, 643 "PRAGMA": TokenType.PRAGMA, 644 "PRIMARY KEY": TokenType.PRIMARY_KEY, 645 "PROCEDURE": TokenType.PROCEDURE, 646 "QUALIFY": TokenType.QUALIFY, 647 "RANGE": TokenType.RANGE, 648 "RECURSIVE": TokenType.RECURSIVE, 649 "REGEXP": TokenType.RLIKE, 650 "REPLACE": TokenType.REPLACE, 651 "RETURNING": TokenType.RETURNING, 652 "REFERENCES": TokenType.REFERENCES, 653 "RIGHT": TokenType.RIGHT, 654 "RLIKE": TokenType.RLIKE, 655 "ROLLBACK": TokenType.ROLLBACK, 656 "ROLLUP": TokenType.ROLLUP, 657 "ROW": TokenType.ROW, 658 "ROWS": TokenType.ROWS, 659 "SCHEMA": TokenType.SCHEMA, 660 "SELECT": TokenType.SELECT, 661 "SEMI": TokenType.SEMI, 662 "SET": TokenType.SET, 663 "SETTINGS": TokenType.SETTINGS, 664 "SHOW": TokenType.SHOW, 665 "SIMILAR TO": TokenType.SIMILAR_TO, 666 "SOME": TokenType.SOME, 667 "SORT BY": TokenType.SORT_BY, 668 "START WITH": TokenType.START_WITH, 669 "TABLE": TokenType.TABLE, 670 "TABLESAMPLE": TokenType.TABLE_SAMPLE, 671 "TEMP": TokenType.TEMPORARY, 672 "TEMPORARY": TokenType.TEMPORARY, 673 "THEN": TokenType.THEN, 674 "TRUE": TokenType.TRUE, 675 "UNION": TokenType.UNION, 676 "UNKNOWN": TokenType.UNKNOWN, 677 "UNNEST": TokenType.UNNEST, 678 "UNPIVOT": TokenType.UNPIVOT, 679 "UPDATE": TokenType.UPDATE, 680 "USE": TokenType.USE, 681 "USING": TokenType.USING, 682 "UUID": TokenType.UUID, 683 "VALUES": TokenType.VALUES, 684 "VIEW": TokenType.VIEW, 685 "VOLATILE": TokenType.VOLATILE, 686 "WHEN": TokenType.WHEN, 687 "WHERE": TokenType.WHERE, 688 "WINDOW": TokenType.WINDOW, 689 "WITH": TokenType.WITH, 690 "APPLY": TokenType.APPLY, 691 "ARRAY": TokenType.ARRAY, 692 "BIT": TokenType.BIT, 693 "BOOL": TokenType.BOOLEAN, 694 "BOOLEAN": TokenType.BOOLEAN, 695 "BYTE": TokenType.TINYINT, 696 "MEDIUMINT": TokenType.MEDIUMINT, 697 "INT1": TokenType.TINYINT, 698 "TINYINT": TokenType.TINYINT, 699 "INT16": TokenType.SMALLINT, 700 "SHORT": TokenType.SMALLINT, 701 "SMALLINT": TokenType.SMALLINT, 702 "INT128": TokenType.INT128, 703 "HUGEINT": TokenType.INT128, 704 "INT2": TokenType.SMALLINT, 705 "INTEGER": TokenType.INT, 706 "INT": TokenType.INT, 707 "INT4": TokenType.INT, 708 "INT32": TokenType.INT, 709 "INT64": TokenType.BIGINT, 710 "LONG": TokenType.BIGINT, 711 "BIGINT": TokenType.BIGINT, 712 "INT8": TokenType.TINYINT, 713 "DEC": TokenType.DECIMAL, 714 "DECIMAL": TokenType.DECIMAL, 715 "BIGDECIMAL": TokenType.BIGDECIMAL, 716 "BIGNUMERIC": TokenType.BIGDECIMAL, 717 "MAP": TokenType.MAP, 718 "NULLABLE": TokenType.NULLABLE, 719 "NUMBER": TokenType.DECIMAL, 720 "NUMERIC": TokenType.DECIMAL, 721 "FIXED": TokenType.DECIMAL, 722 "REAL": TokenType.FLOAT, 723 "FLOAT": TokenType.FLOAT, 724 "FLOAT4": TokenType.FLOAT, 725 "FLOAT8": TokenType.DOUBLE, 726 "DOUBLE": TokenType.DOUBLE, 727 "DOUBLE PRECISION": TokenType.DOUBLE, 728 "JSON": TokenType.JSON, 729 "CHAR": TokenType.CHAR, 730 "CHARACTER": TokenType.CHAR, 731 "NCHAR": TokenType.NCHAR, 732 "VARCHAR": TokenType.VARCHAR, 733 "VARCHAR2": TokenType.VARCHAR, 734 "NVARCHAR": TokenType.NVARCHAR, 735 "NVARCHAR2": TokenType.NVARCHAR, 736 "STR": TokenType.TEXT, 737 "STRING": TokenType.TEXT, 738 "TEXT": TokenType.TEXT, 739 "LONGTEXT": TokenType.LONGTEXT, 740 "MEDIUMTEXT": TokenType.MEDIUMTEXT, 741 "TINYTEXT": TokenType.TINYTEXT, 742 "CLOB": TokenType.TEXT, 743 "LONGVARCHAR": TokenType.TEXT, 744 "BINARY": TokenType.BINARY, 745 "BLOB": TokenType.VARBINARY, 746 "LONGBLOB": TokenType.LONGBLOB, 747 "MEDIUMBLOB": TokenType.MEDIUMBLOB, 748 "TINYBLOB": TokenType.TINYBLOB, 749 "BYTEA": TokenType.VARBINARY, 750 "VARBINARY": TokenType.VARBINARY, 751 "TIME": TokenType.TIME, 752 "TIMETZ": TokenType.TIMETZ, 753 "TIMESTAMP": TokenType.TIMESTAMP, 754 "TIMESTAMPTZ": TokenType.TIMESTAMPTZ, 755 "TIMESTAMPLTZ": TokenType.TIMESTAMPLTZ, 756 "DATE": TokenType.DATE, 757 "DATETIME": TokenType.DATETIME, 758 "INT4RANGE": TokenType.INT4RANGE, 759 "INT4MULTIRANGE": TokenType.INT4MULTIRANGE, 760 "INT8RANGE": TokenType.INT8RANGE, 761 "INT8MULTIRANGE": TokenType.INT8MULTIRANGE, 762 "NUMRANGE": TokenType.NUMRANGE, 763 "NUMMULTIRANGE": TokenType.NUMMULTIRANGE, 764 "TSRANGE": TokenType.TSRANGE, 765 "TSMULTIRANGE": TokenType.TSMULTIRANGE, 766 "TSTZRANGE": TokenType.TSTZRANGE, 767 "TSTZMULTIRANGE": TokenType.TSTZMULTIRANGE, 768 "DATERANGE": TokenType.DATERANGE, 769 "DATEMULTIRANGE": TokenType.DATEMULTIRANGE, 770 "UNIQUE": TokenType.UNIQUE, 771 "STRUCT": TokenType.STRUCT, 772 "VARIANT": TokenType.VARIANT, 773 "ALTER": TokenType.ALTER, 774 "ANALYZE": TokenType.COMMAND, 775 "CALL": TokenType.COMMAND, 776 "COMMENT": TokenType.COMMENT, 777 "COPY": TokenType.COMMAND, 778 "EXPLAIN": TokenType.COMMAND, 779 "GRANT": TokenType.COMMAND, 780 "OPTIMIZE": TokenType.COMMAND, 781 "PREPARE": TokenType.COMMAND, 782 "TRUNCATE": TokenType.COMMAND, 783 "VACUUM": TokenType.COMMAND, 784 "USER-DEFINED": TokenType.USERDEFINED, 785 "FOR VERSION": TokenType.VERSION_SNAPSHOT, 786 "FOR TIMESTAMP": TokenType.TIMESTAMP_SNAPSHOT, 787 } 788 789 WHITE_SPACE: t.Dict[t.Optional[str], TokenType] = { 790 " ": TokenType.SPACE, 791 "\t": TokenType.SPACE, 792 "\n": TokenType.BREAK, 793 "\r": TokenType.BREAK, 794 } 795 796 COMMANDS = { 797 TokenType.COMMAND, 798 TokenType.EXECUTE, 799 TokenType.FETCH, 800 TokenType.SHOW, 801 } 802 803 COMMAND_PREFIX_TOKENS = {TokenType.SEMICOLON, TokenType.BEGIN} 804 805 # handle numeric literals like in hive (3L = BIGINT) 806 NUMERIC_LITERALS: t.Dict[str, str] = {} 807 ENCODE: t.Optional[str] = None 808 809 COMMENTS = ["--", ("/*", "*/")] 810 811 __slots__ = ( 812 "sql", 813 "size", 814 "tokens", 815 "dialect", 816 "_start", 817 "_current", 818 "_line", 819 "_col", 820 "_comments", 821 "_char", 822 "_end", 823 "_peek", 824 "_prev_token_line", 825 ) 826 827 def __init__(self, dialect: DialectType = None) -> None: 828 from sqlglot.dialects import Dialect 829 830 self.dialect = Dialect.get_or_raise(dialect) 831 self.reset() 832 833 def reset(self) -> None: 834 self.sql = "" 835 self.size = 0 836 self.tokens: t.List[Token] = [] 837 self._start = 0 838 self._current = 0 839 self._line = 1 840 self._col = 0 841 self._comments: t.List[str] = [] 842 843 self._char = "" 844 self._end = False 845 self._peek = "" 846 self._prev_token_line = -1 847 848 def tokenize(self, sql: str) -> t.List[Token]: 849 """Returns a list of tokens corresponding to the SQL string `sql`.""" 850 self.reset() 851 self.sql = sql 852 self.size = len(sql) 853 854 try: 855 self._scan() 856 except Exception as e: 857 start = max(self._current - 50, 0) 858 end = min(self._current + 50, self.size - 1) 859 context = self.sql[start:end] 860 raise TokenError(f"Error tokenizing '{context}'") from e 861 862 return self.tokens 863 864 def _scan(self, until: t.Optional[t.Callable] = None) -> None: 865 while self.size and not self._end: 866 current = self._current 867 868 # skip spaces inline rather than iteratively call advance() 869 # for performance reasons 870 while current < self.size: 871 char = self.sql[current] 872 873 if char.isspace() and (char == " " or char == "\t"): 874 current += 1 875 else: 876 break 877 878 n = current - self._current 879 self._start = current 880 self._advance(n if n > 1 else 1) 881 882 if self._char is None: 883 break 884 885 if not self._char.isspace(): 886 if self._char.isdigit(): 887 self._scan_number() 888 elif self._char in self._IDENTIFIERS: 889 self._scan_identifier(self._IDENTIFIERS[self._char]) 890 else: 891 self._scan_keywords() 892 893 if until and until(): 894 break 895 896 if self.tokens and self._comments: 897 self.tokens[-1].comments.extend(self._comments) 898 899 def _chars(self, size: int) -> str: 900 if size == 1: 901 return self._char 902 903 start = self._current - 1 904 end = start + size 905 906 return self.sql[start:end] if end <= self.size else "" 907 908 def _advance(self, i: int = 1, alnum: bool = False) -> None: 909 if self.WHITE_SPACE.get(self._char) is TokenType.BREAK: 910 # Ensures we don't count an extra line if we get a \r\n line break sequence 911 if self._char == "\r" and self._peek == "\n": 912 i = 2 913 914 self._col = 1 915 self._line += 1 916 else: 917 self._col += i 918 919 self._current += i 920 self._end = self._current >= self.size 921 self._char = self.sql[self._current - 1] 922 self._peek = "" if self._end else self.sql[self._current] 923 924 if alnum and self._char.isalnum(): 925 # Here we use local variables instead of attributes for better performance 926 _col = self._col 927 _current = self._current 928 _end = self._end 929 _peek = self._peek 930 931 while _peek.isalnum(): 932 _col += 1 933 _current += 1 934 _end = _current >= self.size 935 _peek = "" if _end else self.sql[_current] 936 937 self._col = _col 938 self._current = _current 939 self._end = _end 940 self._peek = _peek 941 self._char = self.sql[_current - 1] 942 943 @property 944 def _text(self) -> str: 945 return self.sql[self._start : self._current] 946 947 def peek(self, i: int = 0) -> str: 948 i = self._current + i 949 if i < self.size: 950 return self.sql[i] 951 return "" 952 953 def _add(self, token_type: TokenType, text: t.Optional[str] = None) -> None: 954 self._prev_token_line = self._line 955 956 if self._comments and token_type == TokenType.SEMICOLON and self.tokens: 957 self.tokens[-1].comments.extend(self._comments) 958 self._comments = [] 959 960 self.tokens.append( 961 Token( 962 token_type, 963 text=self._text if text is None else text, 964 line=self._line, 965 col=self._col, 966 start=self._start, 967 end=self._current - 1, 968 comments=self._comments, 969 ) 970 ) 971 self._comments = [] 972 973 # If we have either a semicolon or a begin token before the command's token, we'll parse 974 # whatever follows the command's token as a string 975 if ( 976 token_type in self.COMMANDS 977 and self._peek != ";" 978 and (len(self.tokens) == 1 or self.tokens[-2].token_type in self.COMMAND_PREFIX_TOKENS) 979 ): 980 start = self._current 981 tokens = len(self.tokens) 982 self._scan(lambda: self._peek == ";") 983 self.tokens = self.tokens[:tokens] 984 text = self.sql[start : self._current].strip() 985 if text: 986 self._add(TokenType.STRING, text) 987 988 def _scan_keywords(self) -> None: 989 size = 0 990 word = None 991 chars = self._text 992 char = chars 993 prev_space = False 994 skip = False 995 trie = self._KEYWORD_TRIE 996 single_token = char in self.SINGLE_TOKENS 997 998 while chars: 999 if skip: 1000 result = TrieResult.PREFIX 1001 else: 1002 result, trie = in_trie(trie, char.upper()) 1003 1004 if result == TrieResult.FAILED: 1005 break 1006 if result == TrieResult.EXISTS: 1007 word = chars 1008 1009 end = self._current + size 1010 size += 1 1011 1012 if end < self.size: 1013 char = self.sql[end] 1014 single_token = single_token or char in self.SINGLE_TOKENS 1015 is_space = char.isspace() 1016 1017 if not is_space or not prev_space: 1018 if is_space: 1019 char = " " 1020 chars += char 1021 prev_space = is_space 1022 skip = False 1023 else: 1024 skip = True 1025 else: 1026 char = "" 1027 break 1028 1029 if word: 1030 if self._scan_string(word): 1031 return 1032 if self._scan_comment(word): 1033 return 1034 if prev_space or single_token or not char: 1035 self._advance(size - 1) 1036 word = word.upper() 1037 self._add(self.KEYWORDS[word], text=word) 1038 return 1039 1040 if self._char in self.SINGLE_TOKENS: 1041 self._add(self.SINGLE_TOKENS[self._char], text=self._char) 1042 return 1043 1044 self._scan_var() 1045 1046 def _scan_comment(self, comment_start: str) -> bool: 1047 if comment_start not in self._COMMENTS: 1048 return False 1049 1050 comment_start_line = self._line 1051 comment_start_size = len(comment_start) 1052 comment_end = self._COMMENTS[comment_start] 1053 1054 if comment_end: 1055 # Skip the comment's start delimiter 1056 self._advance(comment_start_size) 1057 1058 comment_end_size = len(comment_end) 1059 while not self._end and self._chars(comment_end_size) != comment_end: 1060 self._advance(alnum=True) 1061 1062 self._comments.append(self._text[comment_start_size : -comment_end_size + 1]) 1063 self._advance(comment_end_size - 1) 1064 else: 1065 while not self._end and not self.WHITE_SPACE.get(self._peek) is TokenType.BREAK: 1066 self._advance(alnum=True) 1067 self._comments.append(self._text[comment_start_size:]) 1068 1069 # Leading comment is attached to the succeeding token, whilst trailing comment to the preceding. 1070 # Multiple consecutive comments are preserved by appending them to the current comments list. 1071 if comment_start_line == self._prev_token_line: 1072 self.tokens[-1].comments.extend(self._comments) 1073 self._comments = [] 1074 self._prev_token_line = self._line 1075 1076 return True 1077 1078 def _scan_number(self) -> None: 1079 if self._char == "0": 1080 peek = self._peek.upper() 1081 if peek == "B": 1082 return self._scan_bits() if self.BIT_STRINGS else self._add(TokenType.NUMBER) 1083 elif peek == "X": 1084 return self._scan_hex() if self.HEX_STRINGS else self._add(TokenType.NUMBER) 1085 1086 decimal = False 1087 scientific = 0 1088 1089 while True: 1090 if self._peek.isdigit(): 1091 self._advance() 1092 elif self._peek == "." and not decimal: 1093 after = self.peek(1) 1094 if after.isdigit() or not after.isalpha(): 1095 decimal = True 1096 self._advance() 1097 else: 1098 return self._add(TokenType.VAR) 1099 elif self._peek in ("-", "+") and scientific == 1: 1100 scientific += 1 1101 self._advance() 1102 elif self._peek.upper() == "E" and not scientific: 1103 scientific += 1 1104 self._advance() 1105 elif self._peek.isidentifier(): 1106 number_text = self._text 1107 literal = "" 1108 1109 while self._peek.strip() and self._peek not in self.SINGLE_TOKENS: 1110 literal += self._peek 1111 self._advance() 1112 1113 token_type = self.KEYWORDS.get(self.NUMERIC_LITERALS.get(literal.upper(), "")) 1114 1115 if token_type: 1116 self._add(TokenType.NUMBER, number_text) 1117 self._add(TokenType.DCOLON, "::") 1118 return self._add(token_type, literal) 1119 elif self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT: 1120 return self._add(TokenType.VAR) 1121 1122 self._advance(-len(literal)) 1123 return self._add(TokenType.NUMBER, number_text) 1124 else: 1125 return self._add(TokenType.NUMBER) 1126 1127 def _scan_bits(self) -> None: 1128 self._advance() 1129 value = self._extract_value() 1130 try: 1131 # If `value` can't be converted to a binary, fallback to tokenizing it as an identifier 1132 int(value, 2) 1133 self._add(TokenType.BIT_STRING, value[2:]) # Drop the 0b 1134 except ValueError: 1135 self._add(TokenType.IDENTIFIER) 1136 1137 def _scan_hex(self) -> None: 1138 self._advance() 1139 value = self._extract_value() 1140 try: 1141 # If `value` can't be converted to a hex, fallback to tokenizing it as an identifier 1142 int(value, 16) 1143 self._add(TokenType.HEX_STRING, value[2:]) # Drop the 0x 1144 except ValueError: 1145 self._add(TokenType.IDENTIFIER) 1146 1147 def _extract_value(self) -> str: 1148 while True: 1149 char = self._peek.strip() 1150 if char and char not in self.SINGLE_TOKENS: 1151 self._advance(alnum=True) 1152 else: 1153 break 1154 1155 return self._text 1156 1157 def _scan_string(self, start: str) -> bool: 1158 base = None 1159 token_type = TokenType.STRING 1160 1161 if start in self._QUOTES: 1162 end = self._QUOTES[start] 1163 elif start in self._FORMAT_STRINGS: 1164 end, token_type = self._FORMAT_STRINGS[start] 1165 1166 if token_type == TokenType.HEX_STRING: 1167 base = 16 1168 elif token_type == TokenType.BIT_STRING: 1169 base = 2 1170 elif token_type == TokenType.HEREDOC_STRING: 1171 self._advance() 1172 tag = "" if self._char == end else self._extract_string(end) 1173 end = f"{start}{tag}{end}" 1174 else: 1175 return False 1176 1177 self._advance(len(start)) 1178 text = self._extract_string(end) 1179 1180 if base: 1181 try: 1182 int(text, base) 1183 except: 1184 raise TokenError( 1185 f"Numeric string contains invalid characters from {self._line}:{self._start}" 1186 ) 1187 else: 1188 text = text.encode(self.ENCODE).decode(self.ENCODE) if self.ENCODE else text 1189 1190 self._add(token_type, text) 1191 return True 1192 1193 def _scan_identifier(self, identifier_end: str) -> None: 1194 self._advance() 1195 text = self._extract_string(identifier_end, self._IDENTIFIER_ESCAPES) 1196 self._add(TokenType.IDENTIFIER, text) 1197 1198 def _scan_var(self) -> None: 1199 while True: 1200 char = self._peek.strip() 1201 if char and (char in self.VAR_SINGLE_TOKENS or char not in self.SINGLE_TOKENS): 1202 self._advance(alnum=True) 1203 else: 1204 break 1205 1206 self._add( 1207 TokenType.VAR 1208 if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER 1209 else self.KEYWORDS.get(self._text.upper(), TokenType.VAR) 1210 ) 1211 1212 def _extract_string(self, delimiter: str, escapes=None) -> str: 1213 text = "" 1214 delim_size = len(delimiter) 1215 escapes = self._STRING_ESCAPES if escapes is None else escapes 1216 1217 while True: 1218 if ( 1219 self._char in escapes 1220 and (self._peek == delimiter or self._peek in escapes) 1221 and (self._char not in self._QUOTES or self._char == self._peek) 1222 ): 1223 if self._peek == delimiter: 1224 text += self._peek 1225 else: 1226 text += self._char + self._peek 1227 1228 if self._current + 1 < self.size: 1229 self._advance(2) 1230 else: 1231 raise TokenError(f"Missing {delimiter} from {self._line}:{self._current}") 1232 else: 1233 if self._chars(delim_size) == delimiter: 1234 if delim_size > 1: 1235 self._advance(delim_size - 1) 1236 break 1237 1238 if self._end: 1239 raise TokenError(f"Missing {delimiter} from {self._line}:{self._start}") 1240 1241 if ( 1242 self.dialect.ESCAPE_SEQUENCES 1243 and self._peek 1244 and self._char in self.STRING_ESCAPES 1245 ): 1246 escaped_sequence = self.dialect.ESCAPE_SEQUENCES.get(self._char + self._peek) 1247 if escaped_sequence: 1248 self._advance(2) 1249 text += escaped_sequence 1250 continue 1251 1252 current = self._current - 1 1253 self._advance(alnum=True) 1254 text += self.sql[current : self._current - 1] 1255 1256 return text
15class TokenType(AutoName): 16 L_PAREN = auto() 17 R_PAREN = auto() 18 L_BRACKET = auto() 19 R_BRACKET = auto() 20 L_BRACE = auto() 21 R_BRACE = auto() 22 COMMA = auto() 23 DOT = auto() 24 DASH = auto() 25 PLUS = auto() 26 COLON = auto() 27 DCOLON = auto() 28 DQMARK = auto() 29 SEMICOLON = auto() 30 STAR = auto() 31 BACKSLASH = auto() 32 SLASH = auto() 33 LT = auto() 34 LTE = auto() 35 GT = auto() 36 GTE = auto() 37 NOT = auto() 38 EQ = auto() 39 NEQ = auto() 40 NULLSAFE_EQ = auto() 41 COLON_EQ = auto() 42 AND = auto() 43 OR = auto() 44 AMP = auto() 45 DPIPE = auto() 46 PIPE = auto() 47 CARET = auto() 48 TILDA = auto() 49 ARROW = auto() 50 DARROW = auto() 51 FARROW = auto() 52 HASH = auto() 53 HASH_ARROW = auto() 54 DHASH_ARROW = auto() 55 LR_ARROW = auto() 56 DAT = auto() 57 LT_AT = auto() 58 AT_GT = auto() 59 DOLLAR = auto() 60 PARAMETER = auto() 61 SESSION_PARAMETER = auto() 62 DAMP = auto() 63 XOR = auto() 64 DSTAR = auto() 65 66 BLOCK_START = auto() 67 BLOCK_END = auto() 68 69 SPACE = auto() 70 BREAK = auto() 71 72 STRING = auto() 73 NUMBER = auto() 74 IDENTIFIER = auto() 75 DATABASE = auto() 76 COLUMN = auto() 77 COLUMN_DEF = auto() 78 SCHEMA = auto() 79 TABLE = auto() 80 VAR = auto() 81 BIT_STRING = auto() 82 HEX_STRING = auto() 83 BYTE_STRING = auto() 84 NATIONAL_STRING = auto() 85 RAW_STRING = auto() 86 HEREDOC_STRING = auto() 87 88 # types 89 BIT = auto() 90 BOOLEAN = auto() 91 TINYINT = auto() 92 UTINYINT = auto() 93 SMALLINT = auto() 94 USMALLINT = auto() 95 MEDIUMINT = auto() 96 UMEDIUMINT = auto() 97 INT = auto() 98 UINT = auto() 99 BIGINT = auto() 100 UBIGINT = auto() 101 INT128 = auto() 102 UINT128 = auto() 103 INT256 = auto() 104 UINT256 = auto() 105 FLOAT = auto() 106 DOUBLE = auto() 107 DECIMAL = auto() 108 UDECIMAL = auto() 109 BIGDECIMAL = auto() 110 CHAR = auto() 111 NCHAR = auto() 112 VARCHAR = auto() 113 NVARCHAR = auto() 114 TEXT = auto() 115 MEDIUMTEXT = auto() 116 LONGTEXT = auto() 117 MEDIUMBLOB = auto() 118 LONGBLOB = auto() 119 TINYBLOB = auto() 120 TINYTEXT = auto() 121 BINARY = auto() 122 VARBINARY = auto() 123 JSON = auto() 124 JSONB = auto() 125 TIME = auto() 126 TIMETZ = auto() 127 TIMESTAMP = auto() 128 TIMESTAMPTZ = auto() 129 TIMESTAMPLTZ = auto() 130 TIMESTAMP_S = auto() 131 TIMESTAMP_MS = auto() 132 TIMESTAMP_NS = auto() 133 DATETIME = auto() 134 DATETIME64 = auto() 135 DATE = auto() 136 INT4RANGE = auto() 137 INT4MULTIRANGE = auto() 138 INT8RANGE = auto() 139 INT8MULTIRANGE = auto() 140 NUMRANGE = auto() 141 NUMMULTIRANGE = auto() 142 TSRANGE = auto() 143 TSMULTIRANGE = auto() 144 TSTZRANGE = auto() 145 TSTZMULTIRANGE = auto() 146 DATERANGE = auto() 147 DATEMULTIRANGE = auto() 148 UUID = auto() 149 GEOGRAPHY = auto() 150 NULLABLE = auto() 151 GEOMETRY = auto() 152 HLLSKETCH = auto() 153 HSTORE = auto() 154 SUPER = auto() 155 SERIAL = auto() 156 SMALLSERIAL = auto() 157 BIGSERIAL = auto() 158 XML = auto() 159 YEAR = auto() 160 UNIQUEIDENTIFIER = auto() 161 USERDEFINED = auto() 162 MONEY = auto() 163 SMALLMONEY = auto() 164 ROWVERSION = auto() 165 IMAGE = auto() 166 VARIANT = auto() 167 OBJECT = auto() 168 INET = auto() 169 IPADDRESS = auto() 170 IPPREFIX = auto() 171 ENUM = auto() 172 ENUM8 = auto() 173 ENUM16 = auto() 174 FIXEDSTRING = auto() 175 LOWCARDINALITY = auto() 176 NESTED = auto() 177 UNKNOWN = auto() 178 179 # keywords 180 ALIAS = auto() 181 ALTER = auto() 182 ALWAYS = auto() 183 ALL = auto() 184 ANTI = auto() 185 ANY = auto() 186 APPLY = auto() 187 ARRAY = auto() 188 ASC = auto() 189 ASOF = auto() 190 AUTO_INCREMENT = auto() 191 BEGIN = auto() 192 BETWEEN = auto() 193 CACHE = auto() 194 CASE = auto() 195 CHARACTER_SET = auto() 196 CLUSTER_BY = auto() 197 COLLATE = auto() 198 COMMAND = auto() 199 COMMENT = auto() 200 COMMIT = auto() 201 CONNECT_BY = auto() 202 CONSTRAINT = auto() 203 CREATE = auto() 204 CROSS = auto() 205 CUBE = auto() 206 CURRENT_DATE = auto() 207 CURRENT_DATETIME = auto() 208 CURRENT_TIME = auto() 209 CURRENT_TIMESTAMP = auto() 210 CURRENT_USER = auto() 211 DEFAULT = auto() 212 DELETE = auto() 213 DESC = auto() 214 DESCRIBE = auto() 215 DICTIONARY = auto() 216 DISTINCT = auto() 217 DISTRIBUTE_BY = auto() 218 DIV = auto() 219 DROP = auto() 220 ELSE = auto() 221 END = auto() 222 ESCAPE = auto() 223 EXCEPT = auto() 224 EXECUTE = auto() 225 EXISTS = auto() 226 FALSE = auto() 227 FETCH = auto() 228 FILTER = auto() 229 FINAL = auto() 230 FIRST = auto() 231 FOR = auto() 232 FORCE = auto() 233 FOREIGN_KEY = auto() 234 FORMAT = auto() 235 FROM = auto() 236 FULL = auto() 237 FUNCTION = auto() 238 GLOB = auto() 239 GLOBAL = auto() 240 GROUP_BY = auto() 241 GROUPING_SETS = auto() 242 HAVING = auto() 243 HINT = auto() 244 IGNORE = auto() 245 ILIKE = auto() 246 ILIKE_ANY = auto() 247 IN = auto() 248 INDEX = auto() 249 INNER = auto() 250 INSERT = auto() 251 INTERSECT = auto() 252 INTERVAL = auto() 253 INTO = auto() 254 INTRODUCER = auto() 255 IRLIKE = auto() 256 IS = auto() 257 ISNULL = auto() 258 JOIN = auto() 259 JOIN_MARKER = auto() 260 KEEP = auto() 261 KILL = auto() 262 LANGUAGE = auto() 263 LATERAL = auto() 264 LEFT = auto() 265 LIKE = auto() 266 LIKE_ANY = auto() 267 LIMIT = auto() 268 LOAD = auto() 269 LOCK = auto() 270 MAP = auto() 271 MATCH_RECOGNIZE = auto() 272 MEMBER_OF = auto() 273 MERGE = auto() 274 MOD = auto() 275 MODEL = auto() 276 NATURAL = auto() 277 NEXT = auto() 278 NOTNULL = auto() 279 NULL = auto() 280 OBJECT_IDENTIFIER = auto() 281 OFFSET = auto() 282 ON = auto() 283 OPERATOR = auto() 284 ORDER_BY = auto() 285 ORDERED = auto() 286 ORDINALITY = auto() 287 OUTER = auto() 288 OVER = auto() 289 OVERLAPS = auto() 290 OVERWRITE = auto() 291 PARTITION = auto() 292 PARTITION_BY = auto() 293 PERCENT = auto() 294 PIVOT = auto() 295 PLACEHOLDER = auto() 296 PRAGMA = auto() 297 PRIMARY_KEY = auto() 298 PROCEDURE = auto() 299 PROPERTIES = auto() 300 PSEUDO_TYPE = auto() 301 QUALIFY = auto() 302 QUOTE = auto() 303 RANGE = auto() 304 RECURSIVE = auto() 305 REFRESH = auto() 306 REPLACE = auto() 307 RETURNING = auto() 308 REFERENCES = auto() 309 RIGHT = auto() 310 RLIKE = auto() 311 ROLLBACK = auto() 312 ROLLUP = auto() 313 ROW = auto() 314 ROWS = auto() 315 SELECT = auto() 316 SEMI = auto() 317 SEPARATOR = auto() 318 SERDE_PROPERTIES = auto() 319 SET = auto() 320 SETTINGS = auto() 321 SHOW = auto() 322 SIMILAR_TO = auto() 323 SOME = auto() 324 SORT_BY = auto() 325 START_WITH = auto() 326 STRUCT = auto() 327 TABLE_SAMPLE = auto() 328 TEMPORARY = auto() 329 TOP = auto() 330 THEN = auto() 331 TRUE = auto() 332 UNCACHE = auto() 333 UNION = auto() 334 UNNEST = auto() 335 UNPIVOT = auto() 336 UPDATE = auto() 337 USE = auto() 338 USING = auto() 339 VALUES = auto() 340 VIEW = auto() 341 VOLATILE = auto() 342 WHEN = auto() 343 WHERE = auto() 344 WINDOW = auto() 345 WITH = auto() 346 UNIQUE = auto() 347 VERSION_SNAPSHOT = auto() 348 TIMESTAMP_SNAPSHOT = auto()
An enumeration.
L_PAREN =
<TokenType.L_PAREN: 'L_PAREN'>
R_PAREN =
<TokenType.R_PAREN: 'R_PAREN'>
L_BRACKET =
<TokenType.L_BRACKET: 'L_BRACKET'>
R_BRACKET =
<TokenType.R_BRACKET: 'R_BRACKET'>
L_BRACE =
<TokenType.L_BRACE: 'L_BRACE'>
R_BRACE =
<TokenType.R_BRACE: 'R_BRACE'>
COMMA =
<TokenType.COMMA: 'COMMA'>
DOT =
<TokenType.DOT: 'DOT'>
DASH =
<TokenType.DASH: 'DASH'>
PLUS =
<TokenType.PLUS: 'PLUS'>
COLON =
<TokenType.COLON: 'COLON'>
DCOLON =
<TokenType.DCOLON: 'DCOLON'>
DQMARK =
<TokenType.DQMARK: 'DQMARK'>
SEMICOLON =
<TokenType.SEMICOLON: 'SEMICOLON'>
STAR =
<TokenType.STAR: 'STAR'>
BACKSLASH =
<TokenType.BACKSLASH: 'BACKSLASH'>
SLASH =
<TokenType.SLASH: 'SLASH'>
LT =
<TokenType.LT: 'LT'>
LTE =
<TokenType.LTE: 'LTE'>
GT =
<TokenType.GT: 'GT'>
GTE =
<TokenType.GTE: 'GTE'>
NOT =
<TokenType.NOT: 'NOT'>
EQ =
<TokenType.EQ: 'EQ'>
NEQ =
<TokenType.NEQ: 'NEQ'>
NULLSAFE_EQ =
<TokenType.NULLSAFE_EQ: 'NULLSAFE_EQ'>
COLON_EQ =
<TokenType.COLON_EQ: 'COLON_EQ'>
AND =
<TokenType.AND: 'AND'>
OR =
<TokenType.OR: 'OR'>
AMP =
<TokenType.AMP: 'AMP'>
DPIPE =
<TokenType.DPIPE: 'DPIPE'>
PIPE =
<TokenType.PIPE: 'PIPE'>
CARET =
<TokenType.CARET: 'CARET'>
TILDA =
<TokenType.TILDA: 'TILDA'>
ARROW =
<TokenType.ARROW: 'ARROW'>
DARROW =
<TokenType.DARROW: 'DARROW'>
FARROW =
<TokenType.FARROW: 'FARROW'>
HASH =
<TokenType.HASH: 'HASH'>
HASH_ARROW =
<TokenType.HASH_ARROW: 'HASH_ARROW'>
DHASH_ARROW =
<TokenType.DHASH_ARROW: 'DHASH_ARROW'>
LR_ARROW =
<TokenType.LR_ARROW: 'LR_ARROW'>
DAT =
<TokenType.DAT: 'DAT'>
LT_AT =
<TokenType.LT_AT: 'LT_AT'>
AT_GT =
<TokenType.AT_GT: 'AT_GT'>
DOLLAR =
<TokenType.DOLLAR: 'DOLLAR'>
PARAMETER =
<TokenType.PARAMETER: 'PARAMETER'>
SESSION_PARAMETER =
<TokenType.SESSION_PARAMETER: 'SESSION_PARAMETER'>
DAMP =
<TokenType.DAMP: 'DAMP'>
XOR =
<TokenType.XOR: 'XOR'>
DSTAR =
<TokenType.DSTAR: 'DSTAR'>
BLOCK_START =
<TokenType.BLOCK_START: 'BLOCK_START'>
BLOCK_END =
<TokenType.BLOCK_END: 'BLOCK_END'>
SPACE =
<TokenType.SPACE: 'SPACE'>
BREAK =
<TokenType.BREAK: 'BREAK'>
STRING =
<TokenType.STRING: 'STRING'>
NUMBER =
<TokenType.NUMBER: 'NUMBER'>
IDENTIFIER =
<TokenType.IDENTIFIER: 'IDENTIFIER'>
DATABASE =
<TokenType.DATABASE: 'DATABASE'>
COLUMN =
<TokenType.COLUMN: 'COLUMN'>
COLUMN_DEF =
<TokenType.COLUMN_DEF: 'COLUMN_DEF'>
SCHEMA =
<TokenType.SCHEMA: 'SCHEMA'>
TABLE =
<TokenType.TABLE: 'TABLE'>
VAR =
<TokenType.VAR: 'VAR'>
BIT_STRING =
<TokenType.BIT_STRING: 'BIT_STRING'>
HEX_STRING =
<TokenType.HEX_STRING: 'HEX_STRING'>
BYTE_STRING =
<TokenType.BYTE_STRING: 'BYTE_STRING'>
NATIONAL_STRING =
<TokenType.NATIONAL_STRING: 'NATIONAL_STRING'>
RAW_STRING =
<TokenType.RAW_STRING: 'RAW_STRING'>
HEREDOC_STRING =
<TokenType.HEREDOC_STRING: 'HEREDOC_STRING'>
BIT =
<TokenType.BIT: 'BIT'>
BOOLEAN =
<TokenType.BOOLEAN: 'BOOLEAN'>
TINYINT =
<TokenType.TINYINT: 'TINYINT'>
UTINYINT =
<TokenType.UTINYINT: 'UTINYINT'>
SMALLINT =
<TokenType.SMALLINT: 'SMALLINT'>
USMALLINT =
<TokenType.USMALLINT: 'USMALLINT'>
MEDIUMINT =
<TokenType.MEDIUMINT: 'MEDIUMINT'>
UMEDIUMINT =
<TokenType.UMEDIUMINT: 'UMEDIUMINT'>
INT =
<TokenType.INT: 'INT'>
UINT =
<TokenType.UINT: 'UINT'>
BIGINT =
<TokenType.BIGINT: 'BIGINT'>
UBIGINT =
<TokenType.UBIGINT: 'UBIGINT'>
INT128 =
<TokenType.INT128: 'INT128'>
UINT128 =
<TokenType.UINT128: 'UINT128'>
INT256 =
<TokenType.INT256: 'INT256'>
UINT256 =
<TokenType.UINT256: 'UINT256'>
FLOAT =
<TokenType.FLOAT: 'FLOAT'>
DOUBLE =
<TokenType.DOUBLE: 'DOUBLE'>
DECIMAL =
<TokenType.DECIMAL: 'DECIMAL'>
UDECIMAL =
<TokenType.UDECIMAL: 'UDECIMAL'>
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'>
TINYBLOB =
<TokenType.TINYBLOB: 'TINYBLOB'>
TINYTEXT =
<TokenType.TINYTEXT: 'TINYTEXT'>
BINARY =
<TokenType.BINARY: 'BINARY'>
VARBINARY =
<TokenType.VARBINARY: 'VARBINARY'>
JSON =
<TokenType.JSON: 'JSON'>
JSONB =
<TokenType.JSONB: 'JSONB'>
TIME =
<TokenType.TIME: 'TIME'>
TIMETZ =
<TokenType.TIMETZ: 'TIMETZ'>
TIMESTAMP =
<TokenType.TIMESTAMP: 'TIMESTAMP'>
TIMESTAMPTZ =
<TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>
TIMESTAMPLTZ =
<TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>
TIMESTAMP_S =
<TokenType.TIMESTAMP_S: 'TIMESTAMP_S'>
TIMESTAMP_MS =
<TokenType.TIMESTAMP_MS: 'TIMESTAMP_MS'>
TIMESTAMP_NS =
<TokenType.TIMESTAMP_NS: 'TIMESTAMP_NS'>
DATETIME =
<TokenType.DATETIME: 'DATETIME'>
DATETIME64 =
<TokenType.DATETIME64: 'DATETIME64'>
DATE =
<TokenType.DATE: 'DATE'>
INT4RANGE =
<TokenType.INT4RANGE: 'INT4RANGE'>
INT4MULTIRANGE =
<TokenType.INT4MULTIRANGE: 'INT4MULTIRANGE'>
INT8RANGE =
<TokenType.INT8RANGE: 'INT8RANGE'>
INT8MULTIRANGE =
<TokenType.INT8MULTIRANGE: 'INT8MULTIRANGE'>
NUMRANGE =
<TokenType.NUMRANGE: 'NUMRANGE'>
NUMMULTIRANGE =
<TokenType.NUMMULTIRANGE: 'NUMMULTIRANGE'>
TSRANGE =
<TokenType.TSRANGE: 'TSRANGE'>
TSMULTIRANGE =
<TokenType.TSMULTIRANGE: 'TSMULTIRANGE'>
TSTZRANGE =
<TokenType.TSTZRANGE: 'TSTZRANGE'>
TSTZMULTIRANGE =
<TokenType.TSTZMULTIRANGE: 'TSTZMULTIRANGE'>
DATERANGE =
<TokenType.DATERANGE: 'DATERANGE'>
DATEMULTIRANGE =
<TokenType.DATEMULTIRANGE: 'DATEMULTIRANGE'>
UUID =
<TokenType.UUID: 'UUID'>
GEOGRAPHY =
<TokenType.GEOGRAPHY: 'GEOGRAPHY'>
NULLABLE =
<TokenType.NULLABLE: 'NULLABLE'>
GEOMETRY =
<TokenType.GEOMETRY: 'GEOMETRY'>
HLLSKETCH =
<TokenType.HLLSKETCH: 'HLLSKETCH'>
HSTORE =
<TokenType.HSTORE: 'HSTORE'>
SUPER =
<TokenType.SUPER: 'SUPER'>
SERIAL =
<TokenType.SERIAL: 'SERIAL'>
SMALLSERIAL =
<TokenType.SMALLSERIAL: 'SMALLSERIAL'>
BIGSERIAL =
<TokenType.BIGSERIAL: 'BIGSERIAL'>
XML =
<TokenType.XML: 'XML'>
YEAR =
<TokenType.YEAR: 'YEAR'>
UNIQUEIDENTIFIER =
<TokenType.UNIQUEIDENTIFIER: 'UNIQUEIDENTIFIER'>
USERDEFINED =
<TokenType.USERDEFINED: 'USERDEFINED'>
MONEY =
<TokenType.MONEY: 'MONEY'>
SMALLMONEY =
<TokenType.SMALLMONEY: 'SMALLMONEY'>
ROWVERSION =
<TokenType.ROWVERSION: 'ROWVERSION'>
IMAGE =
<TokenType.IMAGE: 'IMAGE'>
VARIANT =
<TokenType.VARIANT: 'VARIANT'>
OBJECT =
<TokenType.OBJECT: 'OBJECT'>
INET =
<TokenType.INET: 'INET'>
IPADDRESS =
<TokenType.IPADDRESS: 'IPADDRESS'>
IPPREFIX =
<TokenType.IPPREFIX: 'IPPREFIX'>
ENUM =
<TokenType.ENUM: 'ENUM'>
ENUM8 =
<TokenType.ENUM8: 'ENUM8'>
ENUM16 =
<TokenType.ENUM16: 'ENUM16'>
FIXEDSTRING =
<TokenType.FIXEDSTRING: 'FIXEDSTRING'>
LOWCARDINALITY =
<TokenType.LOWCARDINALITY: 'LOWCARDINALITY'>
NESTED =
<TokenType.NESTED: 'NESTED'>
UNKNOWN =
<TokenType.UNKNOWN: 'UNKNOWN'>
ALIAS =
<TokenType.ALIAS: 'ALIAS'>
ALTER =
<TokenType.ALTER: 'ALTER'>
ALWAYS =
<TokenType.ALWAYS: 'ALWAYS'>
ALL =
<TokenType.ALL: 'ALL'>
ANTI =
<TokenType.ANTI: 'ANTI'>
ANY =
<TokenType.ANY: 'ANY'>
APPLY =
<TokenType.APPLY: 'APPLY'>
ARRAY =
<TokenType.ARRAY: 'ARRAY'>
ASC =
<TokenType.ASC: 'ASC'>
ASOF =
<TokenType.ASOF: 'ASOF'>
AUTO_INCREMENT =
<TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>
BEGIN =
<TokenType.BEGIN: 'BEGIN'>
BETWEEN =
<TokenType.BETWEEN: 'BETWEEN'>
CACHE =
<TokenType.CACHE: 'CACHE'>
CASE =
<TokenType.CASE: 'CASE'>
CHARACTER_SET =
<TokenType.CHARACTER_SET: 'CHARACTER_SET'>
CLUSTER_BY =
<TokenType.CLUSTER_BY: 'CLUSTER_BY'>
COLLATE =
<TokenType.COLLATE: 'COLLATE'>
COMMAND =
<TokenType.COMMAND: 'COMMAND'>
COMMENT =
<TokenType.COMMENT: 'COMMENT'>
COMMIT =
<TokenType.COMMIT: 'COMMIT'>
CONNECT_BY =
<TokenType.CONNECT_BY: 'CONNECT_BY'>
CONSTRAINT =
<TokenType.CONSTRAINT: 'CONSTRAINT'>
CREATE =
<TokenType.CREATE: 'CREATE'>
CROSS =
<TokenType.CROSS: 'CROSS'>
CUBE =
<TokenType.CUBE: 'CUBE'>
CURRENT_DATE =
<TokenType.CURRENT_DATE: 'CURRENT_DATE'>
CURRENT_DATETIME =
<TokenType.CURRENT_DATETIME: 'CURRENT_DATETIME'>
CURRENT_TIME =
<TokenType.CURRENT_TIME: 'CURRENT_TIME'>
CURRENT_TIMESTAMP =
<TokenType.CURRENT_TIMESTAMP: 'CURRENT_TIMESTAMP'>
CURRENT_USER =
<TokenType.CURRENT_USER: 'CURRENT_USER'>
DEFAULT =
<TokenType.DEFAULT: 'DEFAULT'>
DELETE =
<TokenType.DELETE: 'DELETE'>
DESC =
<TokenType.DESC: 'DESC'>
DESCRIBE =
<TokenType.DESCRIBE: 'DESCRIBE'>
DICTIONARY =
<TokenType.DICTIONARY: 'DICTIONARY'>
DISTINCT =
<TokenType.DISTINCT: 'DISTINCT'>
DISTRIBUTE_BY =
<TokenType.DISTRIBUTE_BY: 'DISTRIBUTE_BY'>
DIV =
<TokenType.DIV: 'DIV'>
DROP =
<TokenType.DROP: 'DROP'>
ELSE =
<TokenType.ELSE: 'ELSE'>
END =
<TokenType.END: 'END'>
ESCAPE =
<TokenType.ESCAPE: 'ESCAPE'>
EXCEPT =
<TokenType.EXCEPT: 'EXCEPT'>
EXECUTE =
<TokenType.EXECUTE: 'EXECUTE'>
EXISTS =
<TokenType.EXISTS: 'EXISTS'>
FALSE =
<TokenType.FALSE: 'FALSE'>
FETCH =
<TokenType.FETCH: 'FETCH'>
FILTER =
<TokenType.FILTER: 'FILTER'>
FINAL =
<TokenType.FINAL: 'FINAL'>
FIRST =
<TokenType.FIRST: 'FIRST'>
FOR =
<TokenType.FOR: 'FOR'>
FORCE =
<TokenType.FORCE: 'FORCE'>
FOREIGN_KEY =
<TokenType.FOREIGN_KEY: 'FOREIGN_KEY'>
FORMAT =
<TokenType.FORMAT: 'FORMAT'>
FROM =
<TokenType.FROM: 'FROM'>
FULL =
<TokenType.FULL: 'FULL'>
FUNCTION =
<TokenType.FUNCTION: 'FUNCTION'>
GLOB =
<TokenType.GLOB: 'GLOB'>
GLOBAL =
<TokenType.GLOBAL: 'GLOBAL'>
GROUP_BY =
<TokenType.GROUP_BY: 'GROUP_BY'>
GROUPING_SETS =
<TokenType.GROUPING_SETS: 'GROUPING_SETS'>
HAVING =
<TokenType.HAVING: 'HAVING'>
HINT =
<TokenType.HINT: 'HINT'>
IGNORE =
<TokenType.IGNORE: 'IGNORE'>
ILIKE =
<TokenType.ILIKE: 'ILIKE'>
ILIKE_ANY =
<TokenType.ILIKE_ANY: 'ILIKE_ANY'>
IN =
<TokenType.IN: 'IN'>
INDEX =
<TokenType.INDEX: 'INDEX'>
INNER =
<TokenType.INNER: 'INNER'>
INSERT =
<TokenType.INSERT: 'INSERT'>
INTERSECT =
<TokenType.INTERSECT: 'INTERSECT'>
INTERVAL =
<TokenType.INTERVAL: 'INTERVAL'>
INTO =
<TokenType.INTO: 'INTO'>
INTRODUCER =
<TokenType.INTRODUCER: 'INTRODUCER'>
IRLIKE =
<TokenType.IRLIKE: 'IRLIKE'>
IS =
<TokenType.IS: 'IS'>
ISNULL =
<TokenType.ISNULL: 'ISNULL'>
JOIN =
<TokenType.JOIN: 'JOIN'>
JOIN_MARKER =
<TokenType.JOIN_MARKER: 'JOIN_MARKER'>
KEEP =
<TokenType.KEEP: 'KEEP'>
KILL =
<TokenType.KILL: 'KILL'>
LANGUAGE =
<TokenType.LANGUAGE: 'LANGUAGE'>
LATERAL =
<TokenType.LATERAL: 'LATERAL'>
LEFT =
<TokenType.LEFT: 'LEFT'>
LIKE =
<TokenType.LIKE: 'LIKE'>
LIKE_ANY =
<TokenType.LIKE_ANY: 'LIKE_ANY'>
LIMIT =
<TokenType.LIMIT: 'LIMIT'>
LOAD =
<TokenType.LOAD: 'LOAD'>
LOCK =
<TokenType.LOCK: 'LOCK'>
MAP =
<TokenType.MAP: 'MAP'>
MATCH_RECOGNIZE =
<TokenType.MATCH_RECOGNIZE: 'MATCH_RECOGNIZE'>
MEMBER_OF =
<TokenType.MEMBER_OF: 'MEMBER_OF'>
MERGE =
<TokenType.MERGE: 'MERGE'>
MOD =
<TokenType.MOD: 'MOD'>
MODEL =
<TokenType.MODEL: 'MODEL'>
NATURAL =
<TokenType.NATURAL: 'NATURAL'>
NEXT =
<TokenType.NEXT: 'NEXT'>
NOTNULL =
<TokenType.NOTNULL: 'NOTNULL'>
NULL =
<TokenType.NULL: 'NULL'>
OBJECT_IDENTIFIER =
<TokenType.OBJECT_IDENTIFIER: 'OBJECT_IDENTIFIER'>
OFFSET =
<TokenType.OFFSET: 'OFFSET'>
ON =
<TokenType.ON: 'ON'>
OPERATOR =
<TokenType.OPERATOR: 'OPERATOR'>
ORDER_BY =
<TokenType.ORDER_BY: 'ORDER_BY'>
ORDERED =
<TokenType.ORDERED: 'ORDERED'>
ORDINALITY =
<TokenType.ORDINALITY: 'ORDINALITY'>
OUTER =
<TokenType.OUTER: 'OUTER'>
OVER =
<TokenType.OVER: 'OVER'>
OVERLAPS =
<TokenType.OVERLAPS: 'OVERLAPS'>
OVERWRITE =
<TokenType.OVERWRITE: 'OVERWRITE'>
PARTITION =
<TokenType.PARTITION: 'PARTITION'>
PARTITION_BY =
<TokenType.PARTITION_BY: 'PARTITION_BY'>
PERCENT =
<TokenType.PERCENT: 'PERCENT'>
PIVOT =
<TokenType.PIVOT: 'PIVOT'>
PLACEHOLDER =
<TokenType.PLACEHOLDER: 'PLACEHOLDER'>
PRAGMA =
<TokenType.PRAGMA: 'PRAGMA'>
PRIMARY_KEY =
<TokenType.PRIMARY_KEY: 'PRIMARY_KEY'>
PROCEDURE =
<TokenType.PROCEDURE: 'PROCEDURE'>
PROPERTIES =
<TokenType.PROPERTIES: 'PROPERTIES'>
PSEUDO_TYPE =
<TokenType.PSEUDO_TYPE: 'PSEUDO_TYPE'>
QUALIFY =
<TokenType.QUALIFY: 'QUALIFY'>
QUOTE =
<TokenType.QUOTE: 'QUOTE'>
RANGE =
<TokenType.RANGE: 'RANGE'>
RECURSIVE =
<TokenType.RECURSIVE: 'RECURSIVE'>
REFRESH =
<TokenType.REFRESH: 'REFRESH'>
REPLACE =
<TokenType.REPLACE: 'REPLACE'>
RETURNING =
<TokenType.RETURNING: 'RETURNING'>
REFERENCES =
<TokenType.REFERENCES: 'REFERENCES'>
RIGHT =
<TokenType.RIGHT: 'RIGHT'>
RLIKE =
<TokenType.RLIKE: 'RLIKE'>
ROLLBACK =
<TokenType.ROLLBACK: 'ROLLBACK'>
ROLLUP =
<TokenType.ROLLUP: 'ROLLUP'>
ROW =
<TokenType.ROW: 'ROW'>
ROWS =
<TokenType.ROWS: 'ROWS'>
SELECT =
<TokenType.SELECT: 'SELECT'>
SEMI =
<TokenType.SEMI: 'SEMI'>
SEPARATOR =
<TokenType.SEPARATOR: 'SEPARATOR'>
SERDE_PROPERTIES =
<TokenType.SERDE_PROPERTIES: 'SERDE_PROPERTIES'>
SET =
<TokenType.SET: 'SET'>
SETTINGS =
<TokenType.SETTINGS: 'SETTINGS'>
SHOW =
<TokenType.SHOW: 'SHOW'>
SIMILAR_TO =
<TokenType.SIMILAR_TO: 'SIMILAR_TO'>
SOME =
<TokenType.SOME: 'SOME'>
SORT_BY =
<TokenType.SORT_BY: 'SORT_BY'>
START_WITH =
<TokenType.START_WITH: 'START_WITH'>
STRUCT =
<TokenType.STRUCT: 'STRUCT'>
TABLE_SAMPLE =
<TokenType.TABLE_SAMPLE: 'TABLE_SAMPLE'>
TEMPORARY =
<TokenType.TEMPORARY: 'TEMPORARY'>
TOP =
<TokenType.TOP: 'TOP'>
THEN =
<TokenType.THEN: 'THEN'>
TRUE =
<TokenType.TRUE: 'TRUE'>
UNCACHE =
<TokenType.UNCACHE: 'UNCACHE'>
UNION =
<TokenType.UNION: 'UNION'>
UNNEST =
<TokenType.UNNEST: 'UNNEST'>
UNPIVOT =
<TokenType.UNPIVOT: 'UNPIVOT'>
UPDATE =
<TokenType.UPDATE: 'UPDATE'>
USE =
<TokenType.USE: 'USE'>
USING =
<TokenType.USING: 'USING'>
VALUES =
<TokenType.VALUES: 'VALUES'>
VIEW =
<TokenType.VIEW: 'VIEW'>
VOLATILE =
<TokenType.VOLATILE: 'VOLATILE'>
WHEN =
<TokenType.WHEN: 'WHEN'>
WHERE =
<TokenType.WHERE: 'WHERE'>
WINDOW =
<TokenType.WINDOW: 'WINDOW'>
WITH =
<TokenType.WITH: 'WITH'>
UNIQUE =
<TokenType.UNIQUE: 'UNIQUE'>
VERSION_SNAPSHOT =
<TokenType.VERSION_SNAPSHOT: 'VERSION_SNAPSHOT'>
TIMESTAMP_SNAPSHOT =
<TokenType.TIMESTAMP_SNAPSHOT: 'TIMESTAMP_SNAPSHOT'>
Inherited Members
- enum.Enum
- name
- value
class
Token:
351class Token: 352 __slots__ = ("token_type", "text", "line", "col", "start", "end", "comments") 353 354 @classmethod 355 def number(cls, number: int) -> Token: 356 """Returns a NUMBER token with `number` as its text.""" 357 return cls(TokenType.NUMBER, str(number)) 358 359 @classmethod 360 def string(cls, string: str) -> Token: 361 """Returns a STRING token with `string` as its text.""" 362 return cls(TokenType.STRING, string) 363 364 @classmethod 365 def identifier(cls, identifier: str) -> Token: 366 """Returns an IDENTIFIER token with `identifier` as its text.""" 367 return cls(TokenType.IDENTIFIER, identifier) 368 369 @classmethod 370 def var(cls, var: str) -> Token: 371 """Returns an VAR token with `var` as its text.""" 372 return cls(TokenType.VAR, var) 373 374 def __init__( 375 self, 376 token_type: TokenType, 377 text: str, 378 line: int = 1, 379 col: int = 1, 380 start: int = 0, 381 end: int = 0, 382 comments: t.Optional[t.List[str]] = None, 383 ) -> None: 384 """Token initializer. 385 386 Args: 387 token_type: The TokenType Enum. 388 text: The text of the token. 389 line: The line that the token ends on. 390 col: The column that the token ends on. 391 start: The start index of the token. 392 end: The ending index of the token. 393 comments: The comments to attach to the token. 394 """ 395 self.token_type = token_type 396 self.text = text 397 self.line = line 398 self.col = col 399 self.start = start 400 self.end = end 401 self.comments = [] if comments is None else comments 402 403 def __repr__(self) -> str: 404 attributes = ", ".join(f"{k}: {getattr(self, k)}" for k in self.__slots__) 405 return f"<Token {attributes}>"
Token( token_type: TokenType, text: str, line: int = 1, col: int = 1, start: int = 0, end: int = 0, comments: Optional[List[str]] = None)
374 def __init__( 375 self, 376 token_type: TokenType, 377 text: str, 378 line: int = 1, 379 col: int = 1, 380 start: int = 0, 381 end: int = 0, 382 comments: t.Optional[t.List[str]] = None, 383 ) -> None: 384 """Token initializer. 385 386 Args: 387 token_type: The TokenType Enum. 388 text: The text of the token. 389 line: The line that the token ends on. 390 col: The column that the token ends on. 391 start: The start index of the token. 392 end: The ending index of the token. 393 comments: The comments to attach to the token. 394 """ 395 self.token_type = token_type 396 self.text = text 397 self.line = line 398 self.col = col 399 self.start = start 400 self.end = end 401 self.comments = [] if comments is None else comments
Token initializer.
Arguments:
- token_type: The TokenType Enum.
- text: The text of the token.
- line: The line that the token ends on.
- col: The column that the token ends on.
- start: The start index of the token.
- end: The ending index of the token.
- comments: The comments to attach to the token.
354 @classmethod 355 def number(cls, number: int) -> Token: 356 """Returns a NUMBER token with `number` as its text.""" 357 return cls(TokenType.NUMBER, str(number))
Returns a NUMBER token with number
as its text.
359 @classmethod 360 def string(cls, string: str) -> Token: 361 """Returns a STRING token with `string` as its text.""" 362 return cls(TokenType.STRING, string)
Returns a STRING token with string
as its text.
364 @classmethod 365 def identifier(cls, identifier: str) -> Token: 366 """Returns an IDENTIFIER token with `identifier` as its text.""" 367 return cls(TokenType.IDENTIFIER, identifier)
Returns an IDENTIFIER token with identifier
as its text.
class
Tokenizer:
462class Tokenizer(metaclass=_Tokenizer): 463 SINGLE_TOKENS = { 464 "(": TokenType.L_PAREN, 465 ")": TokenType.R_PAREN, 466 "[": TokenType.L_BRACKET, 467 "]": TokenType.R_BRACKET, 468 "{": TokenType.L_BRACE, 469 "}": TokenType.R_BRACE, 470 "&": TokenType.AMP, 471 "^": TokenType.CARET, 472 ":": TokenType.COLON, 473 ",": TokenType.COMMA, 474 ".": TokenType.DOT, 475 "-": TokenType.DASH, 476 "=": TokenType.EQ, 477 ">": TokenType.GT, 478 "<": TokenType.LT, 479 "%": TokenType.MOD, 480 "!": TokenType.NOT, 481 "|": TokenType.PIPE, 482 "+": TokenType.PLUS, 483 ";": TokenType.SEMICOLON, 484 "/": TokenType.SLASH, 485 "\\": TokenType.BACKSLASH, 486 "*": TokenType.STAR, 487 "~": TokenType.TILDA, 488 "?": TokenType.PLACEHOLDER, 489 "@": TokenType.PARAMETER, 490 # used for breaking a var like x'y' but nothing else 491 # the token type doesn't matter 492 "'": TokenType.QUOTE, 493 "`": TokenType.IDENTIFIER, 494 '"': TokenType.IDENTIFIER, 495 "#": TokenType.HASH, 496 } 497 498 BIT_STRINGS: t.List[str | t.Tuple[str, str]] = [] 499 BYTE_STRINGS: t.List[str | t.Tuple[str, str]] = [] 500 HEX_STRINGS: t.List[str | t.Tuple[str, str]] = [] 501 RAW_STRINGS: t.List[str | t.Tuple[str, str]] = [] 502 HEREDOC_STRINGS: t.List[str | t.Tuple[str, str]] = [] 503 IDENTIFIERS: t.List[str | t.Tuple[str, str]] = ['"'] 504 IDENTIFIER_ESCAPES = ['"'] 505 QUOTES: t.List[t.Tuple[str, str] | str] = ["'"] 506 STRING_ESCAPES = ["'"] 507 VAR_SINGLE_TOKENS: t.Set[str] = set() 508 509 # Autofilled 510 _COMMENTS: t.Dict[str, str] = {} 511 _FORMAT_STRINGS: t.Dict[str, t.Tuple[str, TokenType]] = {} 512 _IDENTIFIERS: t.Dict[str, str] = {} 513 _IDENTIFIER_ESCAPES: t.Set[str] = set() 514 _QUOTES: t.Dict[str, str] = {} 515 _STRING_ESCAPES: t.Set[str] = set() 516 _KEYWORD_TRIE: t.Dict = {} 517 518 KEYWORDS: t.Dict[str, TokenType] = { 519 **{f"{{%{postfix}": TokenType.BLOCK_START for postfix in ("", "+", "-")}, 520 **{f"{prefix}%}}": TokenType.BLOCK_END for prefix in ("", "+", "-")}, 521 **{f"{{{{{postfix}": TokenType.BLOCK_START for postfix in ("+", "-")}, 522 **{f"{prefix}}}}}": TokenType.BLOCK_END for prefix in ("+", "-")}, 523 "/*+": TokenType.HINT, 524 "==": TokenType.EQ, 525 "::": TokenType.DCOLON, 526 "||": TokenType.DPIPE, 527 ">=": TokenType.GTE, 528 "<=": TokenType.LTE, 529 "<>": TokenType.NEQ, 530 "!=": TokenType.NEQ, 531 ":=": TokenType.COLON_EQ, 532 "<=>": TokenType.NULLSAFE_EQ, 533 "->": TokenType.ARROW, 534 "->>": TokenType.DARROW, 535 "=>": TokenType.FARROW, 536 "#>": TokenType.HASH_ARROW, 537 "#>>": TokenType.DHASH_ARROW, 538 "<->": TokenType.LR_ARROW, 539 "&&": TokenType.DAMP, 540 "??": TokenType.DQMARK, 541 "ALL": TokenType.ALL, 542 "ALWAYS": TokenType.ALWAYS, 543 "AND": TokenType.AND, 544 "ANTI": TokenType.ANTI, 545 "ANY": TokenType.ANY, 546 "ASC": TokenType.ASC, 547 "AS": TokenType.ALIAS, 548 "ASOF": TokenType.ASOF, 549 "AUTOINCREMENT": TokenType.AUTO_INCREMENT, 550 "AUTO_INCREMENT": TokenType.AUTO_INCREMENT, 551 "BEGIN": TokenType.BEGIN, 552 "BETWEEN": TokenType.BETWEEN, 553 "CACHE": TokenType.CACHE, 554 "UNCACHE": TokenType.UNCACHE, 555 "CASE": TokenType.CASE, 556 "CHARACTER SET": TokenType.CHARACTER_SET, 557 "CLUSTER BY": TokenType.CLUSTER_BY, 558 "COLLATE": TokenType.COLLATE, 559 "COLUMN": TokenType.COLUMN, 560 "COMMIT": TokenType.COMMIT, 561 "CONNECT BY": TokenType.CONNECT_BY, 562 "CONSTRAINT": TokenType.CONSTRAINT, 563 "CREATE": TokenType.CREATE, 564 "CROSS": TokenType.CROSS, 565 "CUBE": TokenType.CUBE, 566 "CURRENT_DATE": TokenType.CURRENT_DATE, 567 "CURRENT_TIME": TokenType.CURRENT_TIME, 568 "CURRENT_TIMESTAMP": TokenType.CURRENT_TIMESTAMP, 569 "CURRENT_USER": TokenType.CURRENT_USER, 570 "DATABASE": TokenType.DATABASE, 571 "DEFAULT": TokenType.DEFAULT, 572 "DELETE": TokenType.DELETE, 573 "DESC": TokenType.DESC, 574 "DESCRIBE": TokenType.DESCRIBE, 575 "DISTINCT": TokenType.DISTINCT, 576 "DISTRIBUTE BY": TokenType.DISTRIBUTE_BY, 577 "DIV": TokenType.DIV, 578 "DROP": TokenType.DROP, 579 "ELSE": TokenType.ELSE, 580 "END": TokenType.END, 581 "ESCAPE": TokenType.ESCAPE, 582 "EXCEPT": TokenType.EXCEPT, 583 "EXECUTE": TokenType.EXECUTE, 584 "EXISTS": TokenType.EXISTS, 585 "FALSE": TokenType.FALSE, 586 "FETCH": TokenType.FETCH, 587 "FILTER": TokenType.FILTER, 588 "FIRST": TokenType.FIRST, 589 "FULL": TokenType.FULL, 590 "FUNCTION": TokenType.FUNCTION, 591 "FOR": TokenType.FOR, 592 "FOREIGN KEY": TokenType.FOREIGN_KEY, 593 "FORMAT": TokenType.FORMAT, 594 "FROM": TokenType.FROM, 595 "GEOGRAPHY": TokenType.GEOGRAPHY, 596 "GEOMETRY": TokenType.GEOMETRY, 597 "GLOB": TokenType.GLOB, 598 "GROUP BY": TokenType.GROUP_BY, 599 "GROUPING SETS": TokenType.GROUPING_SETS, 600 "HAVING": TokenType.HAVING, 601 "ILIKE": TokenType.ILIKE, 602 "IN": TokenType.IN, 603 "INDEX": TokenType.INDEX, 604 "INET": TokenType.INET, 605 "INNER": TokenType.INNER, 606 "INSERT": TokenType.INSERT, 607 "INTERVAL": TokenType.INTERVAL, 608 "INTERSECT": TokenType.INTERSECT, 609 "INTO": TokenType.INTO, 610 "IS": TokenType.IS, 611 "ISNULL": TokenType.ISNULL, 612 "JOIN": TokenType.JOIN, 613 "KEEP": TokenType.KEEP, 614 "KILL": TokenType.KILL, 615 "LATERAL": TokenType.LATERAL, 616 "LEFT": TokenType.LEFT, 617 "LIKE": TokenType.LIKE, 618 "LIMIT": TokenType.LIMIT, 619 "LOAD": TokenType.LOAD, 620 "LOCK": TokenType.LOCK, 621 "MERGE": TokenType.MERGE, 622 "NATURAL": TokenType.NATURAL, 623 "NEXT": TokenType.NEXT, 624 "NOT": TokenType.NOT, 625 "NOTNULL": TokenType.NOTNULL, 626 "NULL": TokenType.NULL, 627 "OBJECT": TokenType.OBJECT, 628 "OFFSET": TokenType.OFFSET, 629 "ON": TokenType.ON, 630 "OR": TokenType.OR, 631 "XOR": TokenType.XOR, 632 "ORDER BY": TokenType.ORDER_BY, 633 "ORDINALITY": TokenType.ORDINALITY, 634 "OUTER": TokenType.OUTER, 635 "OVER": TokenType.OVER, 636 "OVERLAPS": TokenType.OVERLAPS, 637 "OVERWRITE": TokenType.OVERWRITE, 638 "PARTITION": TokenType.PARTITION, 639 "PARTITION BY": TokenType.PARTITION_BY, 640 "PARTITIONED BY": TokenType.PARTITION_BY, 641 "PARTITIONED_BY": TokenType.PARTITION_BY, 642 "PERCENT": TokenType.PERCENT, 643 "PIVOT": TokenType.PIVOT, 644 "PRAGMA": TokenType.PRAGMA, 645 "PRIMARY KEY": TokenType.PRIMARY_KEY, 646 "PROCEDURE": TokenType.PROCEDURE, 647 "QUALIFY": TokenType.QUALIFY, 648 "RANGE": TokenType.RANGE, 649 "RECURSIVE": TokenType.RECURSIVE, 650 "REGEXP": TokenType.RLIKE, 651 "REPLACE": TokenType.REPLACE, 652 "RETURNING": TokenType.RETURNING, 653 "REFERENCES": TokenType.REFERENCES, 654 "RIGHT": TokenType.RIGHT, 655 "RLIKE": TokenType.RLIKE, 656 "ROLLBACK": TokenType.ROLLBACK, 657 "ROLLUP": TokenType.ROLLUP, 658 "ROW": TokenType.ROW, 659 "ROWS": TokenType.ROWS, 660 "SCHEMA": TokenType.SCHEMA, 661 "SELECT": TokenType.SELECT, 662 "SEMI": TokenType.SEMI, 663 "SET": TokenType.SET, 664 "SETTINGS": TokenType.SETTINGS, 665 "SHOW": TokenType.SHOW, 666 "SIMILAR TO": TokenType.SIMILAR_TO, 667 "SOME": TokenType.SOME, 668 "SORT BY": TokenType.SORT_BY, 669 "START WITH": TokenType.START_WITH, 670 "TABLE": TokenType.TABLE, 671 "TABLESAMPLE": TokenType.TABLE_SAMPLE, 672 "TEMP": TokenType.TEMPORARY, 673 "TEMPORARY": TokenType.TEMPORARY, 674 "THEN": TokenType.THEN, 675 "TRUE": TokenType.TRUE, 676 "UNION": TokenType.UNION, 677 "UNKNOWN": TokenType.UNKNOWN, 678 "UNNEST": TokenType.UNNEST, 679 "UNPIVOT": TokenType.UNPIVOT, 680 "UPDATE": TokenType.UPDATE, 681 "USE": TokenType.USE, 682 "USING": TokenType.USING, 683 "UUID": TokenType.UUID, 684 "VALUES": TokenType.VALUES, 685 "VIEW": TokenType.VIEW, 686 "VOLATILE": TokenType.VOLATILE, 687 "WHEN": TokenType.WHEN, 688 "WHERE": TokenType.WHERE, 689 "WINDOW": TokenType.WINDOW, 690 "WITH": TokenType.WITH, 691 "APPLY": TokenType.APPLY, 692 "ARRAY": TokenType.ARRAY, 693 "BIT": TokenType.BIT, 694 "BOOL": TokenType.BOOLEAN, 695 "BOOLEAN": TokenType.BOOLEAN, 696 "BYTE": TokenType.TINYINT, 697 "MEDIUMINT": TokenType.MEDIUMINT, 698 "INT1": TokenType.TINYINT, 699 "TINYINT": TokenType.TINYINT, 700 "INT16": TokenType.SMALLINT, 701 "SHORT": TokenType.SMALLINT, 702 "SMALLINT": TokenType.SMALLINT, 703 "INT128": TokenType.INT128, 704 "HUGEINT": TokenType.INT128, 705 "INT2": TokenType.SMALLINT, 706 "INTEGER": TokenType.INT, 707 "INT": TokenType.INT, 708 "INT4": TokenType.INT, 709 "INT32": TokenType.INT, 710 "INT64": TokenType.BIGINT, 711 "LONG": TokenType.BIGINT, 712 "BIGINT": TokenType.BIGINT, 713 "INT8": TokenType.TINYINT, 714 "DEC": TokenType.DECIMAL, 715 "DECIMAL": TokenType.DECIMAL, 716 "BIGDECIMAL": TokenType.BIGDECIMAL, 717 "BIGNUMERIC": TokenType.BIGDECIMAL, 718 "MAP": TokenType.MAP, 719 "NULLABLE": TokenType.NULLABLE, 720 "NUMBER": TokenType.DECIMAL, 721 "NUMERIC": TokenType.DECIMAL, 722 "FIXED": TokenType.DECIMAL, 723 "REAL": TokenType.FLOAT, 724 "FLOAT": TokenType.FLOAT, 725 "FLOAT4": TokenType.FLOAT, 726 "FLOAT8": TokenType.DOUBLE, 727 "DOUBLE": TokenType.DOUBLE, 728 "DOUBLE PRECISION": TokenType.DOUBLE, 729 "JSON": TokenType.JSON, 730 "CHAR": TokenType.CHAR, 731 "CHARACTER": TokenType.CHAR, 732 "NCHAR": TokenType.NCHAR, 733 "VARCHAR": TokenType.VARCHAR, 734 "VARCHAR2": TokenType.VARCHAR, 735 "NVARCHAR": TokenType.NVARCHAR, 736 "NVARCHAR2": TokenType.NVARCHAR, 737 "STR": TokenType.TEXT, 738 "STRING": TokenType.TEXT, 739 "TEXT": TokenType.TEXT, 740 "LONGTEXT": TokenType.LONGTEXT, 741 "MEDIUMTEXT": TokenType.MEDIUMTEXT, 742 "TINYTEXT": TokenType.TINYTEXT, 743 "CLOB": TokenType.TEXT, 744 "LONGVARCHAR": TokenType.TEXT, 745 "BINARY": TokenType.BINARY, 746 "BLOB": TokenType.VARBINARY, 747 "LONGBLOB": TokenType.LONGBLOB, 748 "MEDIUMBLOB": TokenType.MEDIUMBLOB, 749 "TINYBLOB": TokenType.TINYBLOB, 750 "BYTEA": TokenType.VARBINARY, 751 "VARBINARY": TokenType.VARBINARY, 752 "TIME": TokenType.TIME, 753 "TIMETZ": TokenType.TIMETZ, 754 "TIMESTAMP": TokenType.TIMESTAMP, 755 "TIMESTAMPTZ": TokenType.TIMESTAMPTZ, 756 "TIMESTAMPLTZ": TokenType.TIMESTAMPLTZ, 757 "DATE": TokenType.DATE, 758 "DATETIME": TokenType.DATETIME, 759 "INT4RANGE": TokenType.INT4RANGE, 760 "INT4MULTIRANGE": TokenType.INT4MULTIRANGE, 761 "INT8RANGE": TokenType.INT8RANGE, 762 "INT8MULTIRANGE": TokenType.INT8MULTIRANGE, 763 "NUMRANGE": TokenType.NUMRANGE, 764 "NUMMULTIRANGE": TokenType.NUMMULTIRANGE, 765 "TSRANGE": TokenType.TSRANGE, 766 "TSMULTIRANGE": TokenType.TSMULTIRANGE, 767 "TSTZRANGE": TokenType.TSTZRANGE, 768 "TSTZMULTIRANGE": TokenType.TSTZMULTIRANGE, 769 "DATERANGE": TokenType.DATERANGE, 770 "DATEMULTIRANGE": TokenType.DATEMULTIRANGE, 771 "UNIQUE": TokenType.UNIQUE, 772 "STRUCT": TokenType.STRUCT, 773 "VARIANT": TokenType.VARIANT, 774 "ALTER": TokenType.ALTER, 775 "ANALYZE": TokenType.COMMAND, 776 "CALL": TokenType.COMMAND, 777 "COMMENT": TokenType.COMMENT, 778 "COPY": TokenType.COMMAND, 779 "EXPLAIN": TokenType.COMMAND, 780 "GRANT": TokenType.COMMAND, 781 "OPTIMIZE": TokenType.COMMAND, 782 "PREPARE": TokenType.COMMAND, 783 "TRUNCATE": TokenType.COMMAND, 784 "VACUUM": TokenType.COMMAND, 785 "USER-DEFINED": TokenType.USERDEFINED, 786 "FOR VERSION": TokenType.VERSION_SNAPSHOT, 787 "FOR TIMESTAMP": TokenType.TIMESTAMP_SNAPSHOT, 788 } 789 790 WHITE_SPACE: t.Dict[t.Optional[str], TokenType] = { 791 " ": TokenType.SPACE, 792 "\t": TokenType.SPACE, 793 "\n": TokenType.BREAK, 794 "\r": TokenType.BREAK, 795 } 796 797 COMMANDS = { 798 TokenType.COMMAND, 799 TokenType.EXECUTE, 800 TokenType.FETCH, 801 TokenType.SHOW, 802 } 803 804 COMMAND_PREFIX_TOKENS = {TokenType.SEMICOLON, TokenType.BEGIN} 805 806 # handle numeric literals like in hive (3L = BIGINT) 807 NUMERIC_LITERALS: t.Dict[str, str] = {} 808 ENCODE: t.Optional[str] = None 809 810 COMMENTS = ["--", ("/*", "*/")] 811 812 __slots__ = ( 813 "sql", 814 "size", 815 "tokens", 816 "dialect", 817 "_start", 818 "_current", 819 "_line", 820 "_col", 821 "_comments", 822 "_char", 823 "_end", 824 "_peek", 825 "_prev_token_line", 826 ) 827 828 def __init__(self, dialect: DialectType = None) -> None: 829 from sqlglot.dialects import Dialect 830 831 self.dialect = Dialect.get_or_raise(dialect) 832 self.reset() 833 834 def reset(self) -> None: 835 self.sql = "" 836 self.size = 0 837 self.tokens: t.List[Token] = [] 838 self._start = 0 839 self._current = 0 840 self._line = 1 841 self._col = 0 842 self._comments: t.List[str] = [] 843 844 self._char = "" 845 self._end = False 846 self._peek = "" 847 self._prev_token_line = -1 848 849 def tokenize(self, sql: str) -> t.List[Token]: 850 """Returns a list of tokens corresponding to the SQL string `sql`.""" 851 self.reset() 852 self.sql = sql 853 self.size = len(sql) 854 855 try: 856 self._scan() 857 except Exception as e: 858 start = max(self._current - 50, 0) 859 end = min(self._current + 50, self.size - 1) 860 context = self.sql[start:end] 861 raise TokenError(f"Error tokenizing '{context}'") from e 862 863 return self.tokens 864 865 def _scan(self, until: t.Optional[t.Callable] = None) -> None: 866 while self.size and not self._end: 867 current = self._current 868 869 # skip spaces inline rather than iteratively call advance() 870 # for performance reasons 871 while current < self.size: 872 char = self.sql[current] 873 874 if char.isspace() and (char == " " or char == "\t"): 875 current += 1 876 else: 877 break 878 879 n = current - self._current 880 self._start = current 881 self._advance(n if n > 1 else 1) 882 883 if self._char is None: 884 break 885 886 if not self._char.isspace(): 887 if self._char.isdigit(): 888 self._scan_number() 889 elif self._char in self._IDENTIFIERS: 890 self._scan_identifier(self._IDENTIFIERS[self._char]) 891 else: 892 self._scan_keywords() 893 894 if until and until(): 895 break 896 897 if self.tokens and self._comments: 898 self.tokens[-1].comments.extend(self._comments) 899 900 def _chars(self, size: int) -> str: 901 if size == 1: 902 return self._char 903 904 start = self._current - 1 905 end = start + size 906 907 return self.sql[start:end] if end <= self.size else "" 908 909 def _advance(self, i: int = 1, alnum: bool = False) -> None: 910 if self.WHITE_SPACE.get(self._char) is TokenType.BREAK: 911 # Ensures we don't count an extra line if we get a \r\n line break sequence 912 if self._char == "\r" and self._peek == "\n": 913 i = 2 914 915 self._col = 1 916 self._line += 1 917 else: 918 self._col += i 919 920 self._current += i 921 self._end = self._current >= self.size 922 self._char = self.sql[self._current - 1] 923 self._peek = "" if self._end else self.sql[self._current] 924 925 if alnum and self._char.isalnum(): 926 # Here we use local variables instead of attributes for better performance 927 _col = self._col 928 _current = self._current 929 _end = self._end 930 _peek = self._peek 931 932 while _peek.isalnum(): 933 _col += 1 934 _current += 1 935 _end = _current >= self.size 936 _peek = "" if _end else self.sql[_current] 937 938 self._col = _col 939 self._current = _current 940 self._end = _end 941 self._peek = _peek 942 self._char = self.sql[_current - 1] 943 944 @property 945 def _text(self) -> str: 946 return self.sql[self._start : self._current] 947 948 def peek(self, i: int = 0) -> str: 949 i = self._current + i 950 if i < self.size: 951 return self.sql[i] 952 return "" 953 954 def _add(self, token_type: TokenType, text: t.Optional[str] = None) -> None: 955 self._prev_token_line = self._line 956 957 if self._comments and token_type == TokenType.SEMICOLON and self.tokens: 958 self.tokens[-1].comments.extend(self._comments) 959 self._comments = [] 960 961 self.tokens.append( 962 Token( 963 token_type, 964 text=self._text if text is None else text, 965 line=self._line, 966 col=self._col, 967 start=self._start, 968 end=self._current - 1, 969 comments=self._comments, 970 ) 971 ) 972 self._comments = [] 973 974 # If we have either a semicolon or a begin token before the command's token, we'll parse 975 # whatever follows the command's token as a string 976 if ( 977 token_type in self.COMMANDS 978 and self._peek != ";" 979 and (len(self.tokens) == 1 or self.tokens[-2].token_type in self.COMMAND_PREFIX_TOKENS) 980 ): 981 start = self._current 982 tokens = len(self.tokens) 983 self._scan(lambda: self._peek == ";") 984 self.tokens = self.tokens[:tokens] 985 text = self.sql[start : self._current].strip() 986 if text: 987 self._add(TokenType.STRING, text) 988 989 def _scan_keywords(self) -> None: 990 size = 0 991 word = None 992 chars = self._text 993 char = chars 994 prev_space = False 995 skip = False 996 trie = self._KEYWORD_TRIE 997 single_token = char in self.SINGLE_TOKENS 998 999 while chars: 1000 if skip: 1001 result = TrieResult.PREFIX 1002 else: 1003 result, trie = in_trie(trie, char.upper()) 1004 1005 if result == TrieResult.FAILED: 1006 break 1007 if result == TrieResult.EXISTS: 1008 word = chars 1009 1010 end = self._current + size 1011 size += 1 1012 1013 if end < self.size: 1014 char = self.sql[end] 1015 single_token = single_token or char in self.SINGLE_TOKENS 1016 is_space = char.isspace() 1017 1018 if not is_space or not prev_space: 1019 if is_space: 1020 char = " " 1021 chars += char 1022 prev_space = is_space 1023 skip = False 1024 else: 1025 skip = True 1026 else: 1027 char = "" 1028 break 1029 1030 if word: 1031 if self._scan_string(word): 1032 return 1033 if self._scan_comment(word): 1034 return 1035 if prev_space or single_token or not char: 1036 self._advance(size - 1) 1037 word = word.upper() 1038 self._add(self.KEYWORDS[word], text=word) 1039 return 1040 1041 if self._char in self.SINGLE_TOKENS: 1042 self._add(self.SINGLE_TOKENS[self._char], text=self._char) 1043 return 1044 1045 self._scan_var() 1046 1047 def _scan_comment(self, comment_start: str) -> bool: 1048 if comment_start not in self._COMMENTS: 1049 return False 1050 1051 comment_start_line = self._line 1052 comment_start_size = len(comment_start) 1053 comment_end = self._COMMENTS[comment_start] 1054 1055 if comment_end: 1056 # Skip the comment's start delimiter 1057 self._advance(comment_start_size) 1058 1059 comment_end_size = len(comment_end) 1060 while not self._end and self._chars(comment_end_size) != comment_end: 1061 self._advance(alnum=True) 1062 1063 self._comments.append(self._text[comment_start_size : -comment_end_size + 1]) 1064 self._advance(comment_end_size - 1) 1065 else: 1066 while not self._end and not self.WHITE_SPACE.get(self._peek) is TokenType.BREAK: 1067 self._advance(alnum=True) 1068 self._comments.append(self._text[comment_start_size:]) 1069 1070 # Leading comment is attached to the succeeding token, whilst trailing comment to the preceding. 1071 # Multiple consecutive comments are preserved by appending them to the current comments list. 1072 if comment_start_line == self._prev_token_line: 1073 self.tokens[-1].comments.extend(self._comments) 1074 self._comments = [] 1075 self._prev_token_line = self._line 1076 1077 return True 1078 1079 def _scan_number(self) -> None: 1080 if self._char == "0": 1081 peek = self._peek.upper() 1082 if peek == "B": 1083 return self._scan_bits() if self.BIT_STRINGS else self._add(TokenType.NUMBER) 1084 elif peek == "X": 1085 return self._scan_hex() if self.HEX_STRINGS else self._add(TokenType.NUMBER) 1086 1087 decimal = False 1088 scientific = 0 1089 1090 while True: 1091 if self._peek.isdigit(): 1092 self._advance() 1093 elif self._peek == "." and not decimal: 1094 after = self.peek(1) 1095 if after.isdigit() or not after.isalpha(): 1096 decimal = True 1097 self._advance() 1098 else: 1099 return self._add(TokenType.VAR) 1100 elif self._peek in ("-", "+") and scientific == 1: 1101 scientific += 1 1102 self._advance() 1103 elif self._peek.upper() == "E" and not scientific: 1104 scientific += 1 1105 self._advance() 1106 elif self._peek.isidentifier(): 1107 number_text = self._text 1108 literal = "" 1109 1110 while self._peek.strip() and self._peek not in self.SINGLE_TOKENS: 1111 literal += self._peek 1112 self._advance() 1113 1114 token_type = self.KEYWORDS.get(self.NUMERIC_LITERALS.get(literal.upper(), "")) 1115 1116 if token_type: 1117 self._add(TokenType.NUMBER, number_text) 1118 self._add(TokenType.DCOLON, "::") 1119 return self._add(token_type, literal) 1120 elif self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT: 1121 return self._add(TokenType.VAR) 1122 1123 self._advance(-len(literal)) 1124 return self._add(TokenType.NUMBER, number_text) 1125 else: 1126 return self._add(TokenType.NUMBER) 1127 1128 def _scan_bits(self) -> None: 1129 self._advance() 1130 value = self._extract_value() 1131 try: 1132 # If `value` can't be converted to a binary, fallback to tokenizing it as an identifier 1133 int(value, 2) 1134 self._add(TokenType.BIT_STRING, value[2:]) # Drop the 0b 1135 except ValueError: 1136 self._add(TokenType.IDENTIFIER) 1137 1138 def _scan_hex(self) -> None: 1139 self._advance() 1140 value = self._extract_value() 1141 try: 1142 # If `value` can't be converted to a hex, fallback to tokenizing it as an identifier 1143 int(value, 16) 1144 self._add(TokenType.HEX_STRING, value[2:]) # Drop the 0x 1145 except ValueError: 1146 self._add(TokenType.IDENTIFIER) 1147 1148 def _extract_value(self) -> str: 1149 while True: 1150 char = self._peek.strip() 1151 if char and char not in self.SINGLE_TOKENS: 1152 self._advance(alnum=True) 1153 else: 1154 break 1155 1156 return self._text 1157 1158 def _scan_string(self, start: str) -> bool: 1159 base = None 1160 token_type = TokenType.STRING 1161 1162 if start in self._QUOTES: 1163 end = self._QUOTES[start] 1164 elif start in self._FORMAT_STRINGS: 1165 end, token_type = self._FORMAT_STRINGS[start] 1166 1167 if token_type == TokenType.HEX_STRING: 1168 base = 16 1169 elif token_type == TokenType.BIT_STRING: 1170 base = 2 1171 elif token_type == TokenType.HEREDOC_STRING: 1172 self._advance() 1173 tag = "" if self._char == end else self._extract_string(end) 1174 end = f"{start}{tag}{end}" 1175 else: 1176 return False 1177 1178 self._advance(len(start)) 1179 text = self._extract_string(end) 1180 1181 if base: 1182 try: 1183 int(text, base) 1184 except: 1185 raise TokenError( 1186 f"Numeric string contains invalid characters from {self._line}:{self._start}" 1187 ) 1188 else: 1189 text = text.encode(self.ENCODE).decode(self.ENCODE) if self.ENCODE else text 1190 1191 self._add(token_type, text) 1192 return True 1193 1194 def _scan_identifier(self, identifier_end: str) -> None: 1195 self._advance() 1196 text = self._extract_string(identifier_end, self._IDENTIFIER_ESCAPES) 1197 self._add(TokenType.IDENTIFIER, text) 1198 1199 def _scan_var(self) -> None: 1200 while True: 1201 char = self._peek.strip() 1202 if char and (char in self.VAR_SINGLE_TOKENS or char not in self.SINGLE_TOKENS): 1203 self._advance(alnum=True) 1204 else: 1205 break 1206 1207 self._add( 1208 TokenType.VAR 1209 if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER 1210 else self.KEYWORDS.get(self._text.upper(), TokenType.VAR) 1211 ) 1212 1213 def _extract_string(self, delimiter: str, escapes=None) -> str: 1214 text = "" 1215 delim_size = len(delimiter) 1216 escapes = self._STRING_ESCAPES if escapes is None else escapes 1217 1218 while True: 1219 if ( 1220 self._char in escapes 1221 and (self._peek == delimiter or self._peek in escapes) 1222 and (self._char not in self._QUOTES or self._char == self._peek) 1223 ): 1224 if self._peek == delimiter: 1225 text += self._peek 1226 else: 1227 text += self._char + self._peek 1228 1229 if self._current + 1 < self.size: 1230 self._advance(2) 1231 else: 1232 raise TokenError(f"Missing {delimiter} from {self._line}:{self._current}") 1233 else: 1234 if self._chars(delim_size) == delimiter: 1235 if delim_size > 1: 1236 self._advance(delim_size - 1) 1237 break 1238 1239 if self._end: 1240 raise TokenError(f"Missing {delimiter} from {self._line}:{self._start}") 1241 1242 if ( 1243 self.dialect.ESCAPE_SEQUENCES 1244 and self._peek 1245 and self._char in self.STRING_ESCAPES 1246 ): 1247 escaped_sequence = self.dialect.ESCAPE_SEQUENCES.get(self._char + self._peek) 1248 if escaped_sequence: 1249 self._advance(2) 1250 text += escaped_sequence 1251 continue 1252 1253 current = self._current - 1 1254 self._advance(alnum=True) 1255 text += self.sql[current : self._current - 1] 1256 1257 return text
Tokenizer( dialect: Union[str, sqlglot.dialects.dialect.Dialect, Type[sqlglot.dialects.dialect.Dialect], NoneType] = None)
SINGLE_TOKENS =
{'(': <TokenType.L_PAREN: 'L_PAREN'>, ')': <TokenType.R_PAREN: 'R_PAREN'>, '[': <TokenType.L_BRACKET: 'L_BRACKET'>, ']': <TokenType.R_BRACKET: 'R_BRACKET'>, '{': <TokenType.L_BRACE: 'L_BRACE'>, '}': <TokenType.R_BRACE: 'R_BRACE'>, '&': <TokenType.AMP: 'AMP'>, '^': <TokenType.CARET: 'CARET'>, ':': <TokenType.COLON: 'COLON'>, ',': <TokenType.COMMA: 'COMMA'>, '.': <TokenType.DOT: 'DOT'>, '-': <TokenType.DASH: 'DASH'>, '=': <TokenType.EQ: 'EQ'>, '>': <TokenType.GT: 'GT'>, '<': <TokenType.LT: 'LT'>, '%': <TokenType.MOD: 'MOD'>, '!': <TokenType.NOT: 'NOT'>, '|': <TokenType.PIPE: 'PIPE'>, '+': <TokenType.PLUS: 'PLUS'>, ';': <TokenType.SEMICOLON: 'SEMICOLON'>, '/': <TokenType.SLASH: 'SLASH'>, '\\': <TokenType.BACKSLASH: 'BACKSLASH'>, '*': <TokenType.STAR: 'STAR'>, '~': <TokenType.TILDA: 'TILDA'>, '?': <TokenType.PLACEHOLDER: 'PLACEHOLDER'>, '@': <TokenType.PARAMETER: 'PARAMETER'>, "'": <TokenType.QUOTE: 'QUOTE'>, '`': <TokenType.IDENTIFIER: 'IDENTIFIER'>, '"': <TokenType.IDENTIFIER: 'IDENTIFIER'>, '#': <TokenType.HASH: 'HASH'>}
KEYWORDS: Dict[str, TokenType] =
{'{%': <TokenType.BLOCK_START: 'BLOCK_START'>, '{%+': <TokenType.BLOCK_START: 'BLOCK_START'>, '{%-': <TokenType.BLOCK_START: 'BLOCK_START'>, '%}': <TokenType.BLOCK_END: 'BLOCK_END'>, '+%}': <TokenType.BLOCK_END: 'BLOCK_END'>, '-%}': <TokenType.BLOCK_END: 'BLOCK_END'>, '{{+': <TokenType.BLOCK_START: 'BLOCK_START'>, '{{-': <TokenType.BLOCK_START: 'BLOCK_START'>, '+}}': <TokenType.BLOCK_END: 'BLOCK_END'>, '-}}': <TokenType.BLOCK_END: 'BLOCK_END'>, '/*+': <TokenType.HINT: 'HINT'>, '==': <TokenType.EQ: 'EQ'>, '::': <TokenType.DCOLON: 'DCOLON'>, '||': <TokenType.DPIPE: 'DPIPE'>, '>=': <TokenType.GTE: 'GTE'>, '<=': <TokenType.LTE: 'LTE'>, '<>': <TokenType.NEQ: 'NEQ'>, '!=': <TokenType.NEQ: 'NEQ'>, ':=': <TokenType.COLON_EQ: 'COLON_EQ'>, '<=>': <TokenType.NULLSAFE_EQ: 'NULLSAFE_EQ'>, '->': <TokenType.ARROW: 'ARROW'>, '->>': <TokenType.DARROW: 'DARROW'>, '=>': <TokenType.FARROW: 'FARROW'>, '#>': <TokenType.HASH_ARROW: 'HASH_ARROW'>, '#>>': <TokenType.DHASH_ARROW: 'DHASH_ARROW'>, '<->': <TokenType.LR_ARROW: 'LR_ARROW'>, '&&': <TokenType.DAMP: 'DAMP'>, '??': <TokenType.DQMARK: 'DQMARK'>, 'ALL': <TokenType.ALL: 'ALL'>, 'ALWAYS': <TokenType.ALWAYS: 'ALWAYS'>, 'AND': <TokenType.AND: 'AND'>, 'ANTI': <TokenType.ANTI: 'ANTI'>, 'ANY': <TokenType.ANY: 'ANY'>, 'ASC': <TokenType.ASC: 'ASC'>, 'AS': <TokenType.ALIAS: 'ALIAS'>, 'ASOF': <TokenType.ASOF: 'ASOF'>, 'AUTOINCREMENT': <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, 'AUTO_INCREMENT': <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, 'BEGIN': <TokenType.BEGIN: 'BEGIN'>, 'BETWEEN': <TokenType.BETWEEN: 'BETWEEN'>, 'CACHE': <TokenType.CACHE: 'CACHE'>, 'UNCACHE': <TokenType.UNCACHE: 'UNCACHE'>, 'CASE': <TokenType.CASE: 'CASE'>, 'CHARACTER SET': <TokenType.CHARACTER_SET: 'CHARACTER_SET'>, 'CLUSTER BY': <TokenType.CLUSTER_BY: 'CLUSTER_BY'>, 'COLLATE': <TokenType.COLLATE: 'COLLATE'>, 'COLUMN': <TokenType.COLUMN: 'COLUMN'>, 'COMMIT': <TokenType.COMMIT: 'COMMIT'>, 'CONNECT BY': <TokenType.CONNECT_BY: 'CONNECT_BY'>, 'CONSTRAINT': <TokenType.CONSTRAINT: 'CONSTRAINT'>, 'CREATE': <TokenType.CREATE: 'CREATE'>, 'CROSS': <TokenType.CROSS: 'CROSS'>, 'CUBE': <TokenType.CUBE: 'CUBE'>, 'CURRENT_DATE': <TokenType.CURRENT_DATE: 'CURRENT_DATE'>, 'CURRENT_TIME': <TokenType.CURRENT_TIME: 'CURRENT_TIME'>, 'CURRENT_TIMESTAMP': <TokenType.CURRENT_TIMESTAMP: 'CURRENT_TIMESTAMP'>, 'CURRENT_USER': <TokenType.CURRENT_USER: 'CURRENT_USER'>, 'DATABASE': <TokenType.DATABASE: 'DATABASE'>, 'DEFAULT': <TokenType.DEFAULT: 'DEFAULT'>, 'DELETE': <TokenType.DELETE: 'DELETE'>, 'DESC': <TokenType.DESC: 'DESC'>, 'DESCRIBE': <TokenType.DESCRIBE: 'DESCRIBE'>, 'DISTINCT': <TokenType.DISTINCT: 'DISTINCT'>, 'DISTRIBUTE BY': <TokenType.DISTRIBUTE_BY: 'DISTRIBUTE_BY'>, 'DIV': <TokenType.DIV: 'DIV'>, 'DROP': <TokenType.DROP: 'DROP'>, 'ELSE': <TokenType.ELSE: 'ELSE'>, 'END': <TokenType.END: 'END'>, 'ESCAPE': <TokenType.ESCAPE: 'ESCAPE'>, 'EXCEPT': <TokenType.EXCEPT: 'EXCEPT'>, 'EXECUTE': <TokenType.EXECUTE: 'EXECUTE'>, 'EXISTS': <TokenType.EXISTS: 'EXISTS'>, 'FALSE': <TokenType.FALSE: 'FALSE'>, 'FETCH': <TokenType.FETCH: 'FETCH'>, 'FILTER': <TokenType.FILTER: 'FILTER'>, 'FIRST': <TokenType.FIRST: 'FIRST'>, 'FULL': <TokenType.FULL: 'FULL'>, 'FUNCTION': <TokenType.FUNCTION: 'FUNCTION'>, 'FOR': <TokenType.FOR: 'FOR'>, 'FOREIGN KEY': <TokenType.FOREIGN_KEY: 'FOREIGN_KEY'>, 'FORMAT': <TokenType.FORMAT: 'FORMAT'>, 'FROM': <TokenType.FROM: 'FROM'>, 'GEOGRAPHY': <TokenType.GEOGRAPHY: 'GEOGRAPHY'>, 'GEOMETRY': <TokenType.GEOMETRY: 'GEOMETRY'>, 'GLOB': <TokenType.GLOB: 'GLOB'>, 'GROUP BY': <TokenType.GROUP_BY: 'GROUP_BY'>, 'GROUPING SETS': <TokenType.GROUPING_SETS: 'GROUPING_SETS'>, 'HAVING': <TokenType.HAVING: 'HAVING'>, 'ILIKE': <TokenType.ILIKE: 'ILIKE'>, 'IN': <TokenType.IN: 'IN'>, 'INDEX': <TokenType.INDEX: 'INDEX'>, 'INET': <TokenType.INET: 'INET'>, 'INNER': <TokenType.INNER: 'INNER'>, 'INSERT': <TokenType.INSERT: 'INSERT'>, 'INTERVAL': <TokenType.INTERVAL: 'INTERVAL'>, 'INTERSECT': <TokenType.INTERSECT: 'INTERSECT'>, 'INTO': <TokenType.INTO: 'INTO'>, 'IS': <TokenType.IS: 'IS'>, 'ISNULL': <TokenType.ISNULL: 'ISNULL'>, 'JOIN': <TokenType.JOIN: 'JOIN'>, 'KEEP': <TokenType.KEEP: 'KEEP'>, 'KILL': <TokenType.KILL: 'KILL'>, 'LATERAL': <TokenType.LATERAL: 'LATERAL'>, 'LEFT': <TokenType.LEFT: 'LEFT'>, 'LIKE': <TokenType.LIKE: 'LIKE'>, 'LIMIT': <TokenType.LIMIT: 'LIMIT'>, 'LOAD': <TokenType.LOAD: 'LOAD'>, 'LOCK': <TokenType.LOCK: 'LOCK'>, 'MERGE': <TokenType.MERGE: 'MERGE'>, 'NATURAL': <TokenType.NATURAL: 'NATURAL'>, 'NEXT': <TokenType.NEXT: 'NEXT'>, 'NOT': <TokenType.NOT: 'NOT'>, 'NOTNULL': <TokenType.NOTNULL: 'NOTNULL'>, 'NULL': <TokenType.NULL: 'NULL'>, 'OBJECT': <TokenType.OBJECT: 'OBJECT'>, 'OFFSET': <TokenType.OFFSET: 'OFFSET'>, 'ON': <TokenType.ON: 'ON'>, 'OR': <TokenType.OR: 'OR'>, 'XOR': <TokenType.XOR: 'XOR'>, 'ORDER BY': <TokenType.ORDER_BY: 'ORDER_BY'>, 'ORDINALITY': <TokenType.ORDINALITY: 'ORDINALITY'>, 'OUTER': <TokenType.OUTER: 'OUTER'>, 'OVER': <TokenType.OVER: 'OVER'>, 'OVERLAPS': <TokenType.OVERLAPS: 'OVERLAPS'>, 'OVERWRITE': <TokenType.OVERWRITE: 'OVERWRITE'>, 'PARTITION': <TokenType.PARTITION: 'PARTITION'>, 'PARTITION BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PARTITIONED BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PARTITIONED_BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PERCENT': <TokenType.PERCENT: 'PERCENT'>, 'PIVOT': <TokenType.PIVOT: 'PIVOT'>, 'PRAGMA': <TokenType.PRAGMA: 'PRAGMA'>, 'PRIMARY KEY': <TokenType.PRIMARY_KEY: 'PRIMARY_KEY'>, 'PROCEDURE': <TokenType.PROCEDURE: 'PROCEDURE'>, 'QUALIFY': <TokenType.QUALIFY: 'QUALIFY'>, 'RANGE': <TokenType.RANGE: 'RANGE'>, 'RECURSIVE': <TokenType.RECURSIVE: 'RECURSIVE'>, 'REGEXP': <TokenType.RLIKE: 'RLIKE'>, 'REPLACE': <TokenType.REPLACE: 'REPLACE'>, 'RETURNING': <TokenType.RETURNING: 'RETURNING'>, 'REFERENCES': <TokenType.REFERENCES: 'REFERENCES'>, 'RIGHT': <TokenType.RIGHT: 'RIGHT'>, 'RLIKE': <TokenType.RLIKE: 'RLIKE'>, 'ROLLBACK': <TokenType.ROLLBACK: 'ROLLBACK'>, 'ROLLUP': <TokenType.ROLLUP: 'ROLLUP'>, 'ROW': <TokenType.ROW: 'ROW'>, 'ROWS': <TokenType.ROWS: 'ROWS'>, 'SCHEMA': <TokenType.SCHEMA: 'SCHEMA'>, 'SELECT': <TokenType.SELECT: 'SELECT'>, 'SEMI': <TokenType.SEMI: 'SEMI'>, 'SET': <TokenType.SET: 'SET'>, 'SETTINGS': <TokenType.SETTINGS: 'SETTINGS'>, 'SHOW': <TokenType.SHOW: 'SHOW'>, 'SIMILAR TO': <TokenType.SIMILAR_TO: 'SIMILAR_TO'>, 'SOME': <TokenType.SOME: 'SOME'>, 'SORT BY': <TokenType.SORT_BY: 'SORT_BY'>, 'START WITH': <TokenType.START_WITH: 'START_WITH'>, 'TABLE': <TokenType.TABLE: 'TABLE'>, 'TABLESAMPLE': <TokenType.TABLE_SAMPLE: 'TABLE_SAMPLE'>, 'TEMP': <TokenType.TEMPORARY: 'TEMPORARY'>, 'TEMPORARY': <TokenType.TEMPORARY: 'TEMPORARY'>, 'THEN': <TokenType.THEN: 'THEN'>, 'TRUE': <TokenType.TRUE: 'TRUE'>, 'UNION': <TokenType.UNION: 'UNION'>, 'UNKNOWN': <TokenType.UNKNOWN: 'UNKNOWN'>, 'UNNEST': <TokenType.UNNEST: 'UNNEST'>, 'UNPIVOT': <TokenType.UNPIVOT: 'UNPIVOT'>, 'UPDATE': <TokenType.UPDATE: 'UPDATE'>, 'USE': <TokenType.USE: 'USE'>, 'USING': <TokenType.USING: 'USING'>, 'UUID': <TokenType.UUID: 'UUID'>, 'VALUES': <TokenType.VALUES: 'VALUES'>, 'VIEW': <TokenType.VIEW: 'VIEW'>, 'VOLATILE': <TokenType.VOLATILE: 'VOLATILE'>, 'WHEN': <TokenType.WHEN: 'WHEN'>, 'WHERE': <TokenType.WHERE: 'WHERE'>, 'WINDOW': <TokenType.WINDOW: 'WINDOW'>, 'WITH': <TokenType.WITH: 'WITH'>, 'APPLY': <TokenType.APPLY: 'APPLY'>, 'ARRAY': <TokenType.ARRAY: 'ARRAY'>, 'BIT': <TokenType.BIT: 'BIT'>, 'BOOL': <TokenType.BOOLEAN: 'BOOLEAN'>, 'BOOLEAN': <TokenType.BOOLEAN: 'BOOLEAN'>, 'BYTE': <TokenType.TINYINT: 'TINYINT'>, 'MEDIUMINT': <TokenType.MEDIUMINT: 'MEDIUMINT'>, 'INT1': <TokenType.TINYINT: 'TINYINT'>, 'TINYINT': <TokenType.TINYINT: 'TINYINT'>, 'INT16': <TokenType.SMALLINT: 'SMALLINT'>, 'SHORT': <TokenType.SMALLINT: 'SMALLINT'>, 'SMALLINT': <TokenType.SMALLINT: 'SMALLINT'>, 'INT128': <TokenType.INT128: 'INT128'>, 'HUGEINT': <TokenType.INT128: 'INT128'>, 'INT2': <TokenType.SMALLINT: 'SMALLINT'>, 'INTEGER': <TokenType.INT: 'INT'>, 'INT': <TokenType.INT: 'INT'>, 'INT4': <TokenType.INT: 'INT'>, 'INT32': <TokenType.INT: 'INT'>, 'INT64': <TokenType.BIGINT: 'BIGINT'>, 'LONG': <TokenType.BIGINT: 'BIGINT'>, 'BIGINT': <TokenType.BIGINT: 'BIGINT'>, 'INT8': <TokenType.TINYINT: 'TINYINT'>, 'DEC': <TokenType.DECIMAL: 'DECIMAL'>, 'DECIMAL': <TokenType.DECIMAL: 'DECIMAL'>, 'BIGDECIMAL': <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, 'BIGNUMERIC': <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, 'MAP': <TokenType.MAP: 'MAP'>, 'NULLABLE': <TokenType.NULLABLE: 'NULLABLE'>, 'NUMBER': <TokenType.DECIMAL: 'DECIMAL'>, 'NUMERIC': <TokenType.DECIMAL: 'DECIMAL'>, 'FIXED': <TokenType.DECIMAL: 'DECIMAL'>, 'REAL': <TokenType.FLOAT: 'FLOAT'>, 'FLOAT': <TokenType.FLOAT: 'FLOAT'>, 'FLOAT4': <TokenType.FLOAT: 'FLOAT'>, 'FLOAT8': <TokenType.DOUBLE: 'DOUBLE'>, 'DOUBLE': <TokenType.DOUBLE: 'DOUBLE'>, 'DOUBLE PRECISION': <TokenType.DOUBLE: 'DOUBLE'>, 'JSON': <TokenType.JSON: 'JSON'>, 'CHAR': <TokenType.CHAR: 'CHAR'>, 'CHARACTER': <TokenType.CHAR: 'CHAR'>, 'NCHAR': <TokenType.NCHAR: 'NCHAR'>, 'VARCHAR': <TokenType.VARCHAR: 'VARCHAR'>, 'VARCHAR2': <TokenType.VARCHAR: 'VARCHAR'>, 'NVARCHAR': <TokenType.NVARCHAR: 'NVARCHAR'>, 'NVARCHAR2': <TokenType.NVARCHAR: 'NVARCHAR'>, 'STR': <TokenType.TEXT: 'TEXT'>, 'STRING': <TokenType.TEXT: 'TEXT'>, 'TEXT': <TokenType.TEXT: 'TEXT'>, 'LONGTEXT': <TokenType.LONGTEXT: 'LONGTEXT'>, 'MEDIUMTEXT': <TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>, 'TINYTEXT': <TokenType.TINYTEXT: 'TINYTEXT'>, 'CLOB': <TokenType.TEXT: 'TEXT'>, 'LONGVARCHAR': <TokenType.TEXT: 'TEXT'>, 'BINARY': <TokenType.BINARY: 'BINARY'>, 'BLOB': <TokenType.VARBINARY: 'VARBINARY'>, 'LONGBLOB': <TokenType.LONGBLOB: 'LONGBLOB'>, 'MEDIUMBLOB': <TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>, 'TINYBLOB': <TokenType.TINYBLOB: 'TINYBLOB'>, 'BYTEA': <TokenType.VARBINARY: 'VARBINARY'>, 'VARBINARY': <TokenType.VARBINARY: 'VARBINARY'>, 'TIME': <TokenType.TIME: 'TIME'>, 'TIMETZ': <TokenType.TIMETZ: 'TIMETZ'>, 'TIMESTAMP': <TokenType.TIMESTAMP: 'TIMESTAMP'>, 'TIMESTAMPTZ': <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>, 'TIMESTAMPLTZ': <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>, 'DATE': <TokenType.DATE: 'DATE'>, 'DATETIME': <TokenType.DATETIME: 'DATETIME'>, 'INT4RANGE': <TokenType.INT4RANGE: 'INT4RANGE'>, 'INT4MULTIRANGE': <TokenType.INT4MULTIRANGE: 'INT4MULTIRANGE'>, 'INT8RANGE': <TokenType.INT8RANGE: 'INT8RANGE'>, 'INT8MULTIRANGE': <TokenType.INT8MULTIRANGE: 'INT8MULTIRANGE'>, 'NUMRANGE': <TokenType.NUMRANGE: 'NUMRANGE'>, 'NUMMULTIRANGE': <TokenType.NUMMULTIRANGE: 'NUMMULTIRANGE'>, 'TSRANGE': <TokenType.TSRANGE: 'TSRANGE'>, 'TSMULTIRANGE': <TokenType.TSMULTIRANGE: 'TSMULTIRANGE'>, 'TSTZRANGE': <TokenType.TSTZRANGE: 'TSTZRANGE'>, 'TSTZMULTIRANGE': <TokenType.TSTZMULTIRANGE: 'TSTZMULTIRANGE'>, 'DATERANGE': <TokenType.DATERANGE: 'DATERANGE'>, 'DATEMULTIRANGE': <TokenType.DATEMULTIRANGE: 'DATEMULTIRANGE'>, 'UNIQUE': <TokenType.UNIQUE: 'UNIQUE'>, 'STRUCT': <TokenType.STRUCT: 'STRUCT'>, 'VARIANT': <TokenType.VARIANT: 'VARIANT'>, 'ALTER': <TokenType.ALTER: 'ALTER'>, 'ANALYZE': <TokenType.COMMAND: 'COMMAND'>, 'CALL': <TokenType.COMMAND: 'COMMAND'>, 'COMMENT': <TokenType.COMMENT: 'COMMENT'>, 'COPY': <TokenType.COMMAND: 'COMMAND'>, 'EXPLAIN': <TokenType.COMMAND: 'COMMAND'>, 'GRANT': <TokenType.COMMAND: 'COMMAND'>, 'OPTIMIZE': <TokenType.COMMAND: 'COMMAND'>, 'PREPARE': <TokenType.COMMAND: 'COMMAND'>, 'TRUNCATE': <TokenType.COMMAND: 'COMMAND'>, 'VACUUM': <TokenType.COMMAND: 'COMMAND'>, 'USER-DEFINED': <TokenType.USERDEFINED: 'USERDEFINED'>, 'FOR VERSION': <TokenType.VERSION_SNAPSHOT: 'VERSION_SNAPSHOT'>, 'FOR TIMESTAMP': <TokenType.TIMESTAMP_SNAPSHOT: 'TIMESTAMP_SNAPSHOT'>}
WHITE_SPACE: Dict[Optional[str], TokenType] =
{' ': <TokenType.SPACE: 'SPACE'>, '\t': <TokenType.SPACE: 'SPACE'>, '\n': <TokenType.BREAK: 'BREAK'>, '\r': <TokenType.BREAK: 'BREAK'>}
COMMANDS =
{<TokenType.SHOW: 'SHOW'>, <TokenType.FETCH: 'FETCH'>, <TokenType.EXECUTE: 'EXECUTE'>, <TokenType.COMMAND: 'COMMAND'>}
COMMAND_PREFIX_TOKENS =
{<TokenType.BEGIN: 'BEGIN'>, <TokenType.SEMICOLON: 'SEMICOLON'>}
def
reset(self) -> None:
834 def reset(self) -> None: 835 self.sql = "" 836 self.size = 0 837 self.tokens: t.List[Token] = [] 838 self._start = 0 839 self._current = 0 840 self._line = 1 841 self._col = 0 842 self._comments: t.List[str] = [] 843 844 self._char = "" 845 self._end = False 846 self._peek = "" 847 self._prev_token_line = -1
849 def tokenize(self, sql: str) -> t.List[Token]: 850 """Returns a list of tokens corresponding to the SQL string `sql`.""" 851 self.reset() 852 self.sql = sql 853 self.size = len(sql) 854 855 try: 856 self._scan() 857 except Exception as e: 858 start = max(self._current - 50, 0) 859 end = min(self._current + 50, self.size - 1) 860 context = self.sql[start:end] 861 raise TokenError(f"Error tokenizing '{context}'") from e 862 863 return self.tokens
Returns a list of tokens corresponding to the SQL string sql
.