sqlglot.tokens
1from __future__ import annotations 2 3import os 4import typing as t 5from enum import auto 6 7from sqlglot.errors import SqlglotError, TokenError 8from sqlglot.helper import AutoName 9from sqlglot.trie import TrieResult, in_trie, new_trie 10 11if t.TYPE_CHECKING: 12 from sqlglot.dialects.dialect import DialectType 13 14 15try: 16 from sqlglotrs import ( # type: ignore 17 Tokenizer as RsTokenizer, 18 TokenizerDialectSettings as RsTokenizerDialectSettings, 19 TokenizerSettings as RsTokenizerSettings, 20 TokenTypeSettings as RsTokenTypeSettings, 21 ) 22 23 USE_RS_TOKENIZER = os.environ.get("SQLGLOTRS_TOKENIZER", "1") == "1" 24except ImportError: 25 USE_RS_TOKENIZER = False 26 27 28class TokenType(AutoName): 29 L_PAREN = auto() 30 R_PAREN = auto() 31 L_BRACKET = auto() 32 R_BRACKET = auto() 33 L_BRACE = auto() 34 R_BRACE = auto() 35 COMMA = auto() 36 DOT = auto() 37 DASH = auto() 38 PLUS = auto() 39 COLON = auto() 40 DCOLON = auto() 41 DQMARK = auto() 42 SEMICOLON = auto() 43 STAR = auto() 44 BACKSLASH = auto() 45 SLASH = auto() 46 LT = auto() 47 LTE = auto() 48 GT = auto() 49 GTE = auto() 50 NOT = auto() 51 EQ = auto() 52 NEQ = auto() 53 NULLSAFE_EQ = auto() 54 COLON_EQ = auto() 55 AND = auto() 56 OR = auto() 57 AMP = auto() 58 DPIPE = auto() 59 PIPE = auto() 60 PIPE_SLASH = auto() 61 DPIPE_SLASH = auto() 62 CARET = auto() 63 CARET_AT = auto() 64 TILDA = auto() 65 ARROW = auto() 66 DARROW = auto() 67 FARROW = auto() 68 HASH = auto() 69 HASH_ARROW = auto() 70 DHASH_ARROW = auto() 71 LR_ARROW = auto() 72 DAT = auto() 73 LT_AT = auto() 74 AT_GT = auto() 75 DOLLAR = auto() 76 PARAMETER = auto() 77 SESSION_PARAMETER = auto() 78 DAMP = auto() 79 XOR = auto() 80 DSTAR = auto() 81 82 BLOCK_START = auto() 83 BLOCK_END = auto() 84 85 SPACE = auto() 86 BREAK = auto() 87 88 STRING = auto() 89 NUMBER = auto() 90 IDENTIFIER = auto() 91 DATABASE = auto() 92 COLUMN = auto() 93 COLUMN_DEF = auto() 94 SCHEMA = auto() 95 TABLE = auto() 96 WAREHOUSE = auto() 97 STREAMLIT = auto() 98 VAR = auto() 99 BIT_STRING = auto() 100 HEX_STRING = auto() 101 BYTE_STRING = auto() 102 NATIONAL_STRING = auto() 103 RAW_STRING = auto() 104 HEREDOC_STRING = auto() 105 UNICODE_STRING = auto() 106 107 # types 108 BIT = auto() 109 BOOLEAN = auto() 110 TINYINT = auto() 111 UTINYINT = auto() 112 SMALLINT = auto() 113 USMALLINT = auto() 114 MEDIUMINT = auto() 115 UMEDIUMINT = auto() 116 INT = auto() 117 UINT = auto() 118 BIGINT = auto() 119 UBIGINT = auto() 120 INT128 = auto() 121 UINT128 = auto() 122 INT256 = auto() 123 UINT256 = auto() 124 FLOAT = auto() 125 DOUBLE = auto() 126 DECIMAL = auto() 127 DECIMAL32 = auto() 128 DECIMAL64 = auto() 129 DECIMAL128 = auto() 130 UDECIMAL = auto() 131 BIGDECIMAL = auto() 132 CHAR = auto() 133 NCHAR = auto() 134 VARCHAR = auto() 135 NVARCHAR = auto() 136 BPCHAR = auto() 137 TEXT = auto() 138 MEDIUMTEXT = auto() 139 LONGTEXT = auto() 140 MEDIUMBLOB = auto() 141 LONGBLOB = auto() 142 TINYBLOB = auto() 143 TINYTEXT = auto() 144 NAME = auto() 145 BINARY = auto() 146 VARBINARY = auto() 147 JSON = auto() 148 JSONB = auto() 149 TIME = auto() 150 TIMETZ = auto() 151 TIMESTAMP = auto() 152 TIMESTAMPTZ = auto() 153 TIMESTAMPLTZ = auto() 154 TIMESTAMPNTZ = auto() 155 TIMESTAMP_S = auto() 156 TIMESTAMP_MS = auto() 157 TIMESTAMP_NS = auto() 158 DATETIME = auto() 159 DATETIME64 = auto() 160 DATE = auto() 161 DATE32 = auto() 162 INT4RANGE = auto() 163 INT4MULTIRANGE = auto() 164 INT8RANGE = auto() 165 INT8MULTIRANGE = auto() 166 NUMRANGE = auto() 167 NUMMULTIRANGE = auto() 168 TSRANGE = auto() 169 TSMULTIRANGE = auto() 170 TSTZRANGE = auto() 171 TSTZMULTIRANGE = auto() 172 DATERANGE = auto() 173 DATEMULTIRANGE = auto() 174 UUID = auto() 175 GEOGRAPHY = auto() 176 NULLABLE = auto() 177 GEOMETRY = auto() 178 HLLSKETCH = auto() 179 HSTORE = auto() 180 SUPER = auto() 181 SERIAL = auto() 182 SMALLSERIAL = auto() 183 BIGSERIAL = auto() 184 XML = auto() 185 YEAR = auto() 186 UNIQUEIDENTIFIER = auto() 187 USERDEFINED = auto() 188 MONEY = auto() 189 SMALLMONEY = auto() 190 ROWVERSION = auto() 191 IMAGE = auto() 192 VARIANT = auto() 193 OBJECT = auto() 194 INET = auto() 195 IPADDRESS = auto() 196 IPPREFIX = auto() 197 IPV4 = auto() 198 IPV6 = auto() 199 ENUM = auto() 200 ENUM8 = auto() 201 ENUM16 = auto() 202 FIXEDSTRING = auto() 203 LOWCARDINALITY = auto() 204 NESTED = auto() 205 AGGREGATEFUNCTION = auto() 206 SIMPLEAGGREGATEFUNCTION = auto() 207 TDIGEST = auto() 208 UNKNOWN = auto() 209 VECTOR = auto() 210 211 # keywords 212 ALIAS = auto() 213 ALTER = auto() 214 ALWAYS = auto() 215 ALL = auto() 216 ANTI = auto() 217 ANY = auto() 218 APPLY = auto() 219 ARRAY = auto() 220 ASC = auto() 221 ASOF = auto() 222 AUTO_INCREMENT = auto() 223 BEGIN = auto() 224 BETWEEN = auto() 225 BULK_COLLECT_INTO = auto() 226 CACHE = auto() 227 CASE = auto() 228 CHARACTER_SET = auto() 229 CLUSTER_BY = auto() 230 COLLATE = auto() 231 COMMAND = auto() 232 COMMENT = auto() 233 COMMIT = auto() 234 CONNECT_BY = auto() 235 CONSTRAINT = auto() 236 COPY = auto() 237 CREATE = auto() 238 CROSS = auto() 239 CUBE = auto() 240 CURRENT_DATE = auto() 241 CURRENT_DATETIME = auto() 242 CURRENT_TIME = auto() 243 CURRENT_TIMESTAMP = auto() 244 CURRENT_USER = auto() 245 DECLARE = auto() 246 DEFAULT = auto() 247 DELETE = auto() 248 DESC = auto() 249 DESCRIBE = auto() 250 DICTIONARY = auto() 251 DISTINCT = auto() 252 DISTRIBUTE_BY = auto() 253 DIV = auto() 254 DROP = auto() 255 ELSE = auto() 256 END = auto() 257 ESCAPE = auto() 258 EXCEPT = auto() 259 EXECUTE = auto() 260 EXISTS = auto() 261 FALSE = auto() 262 FETCH = auto() 263 FILTER = auto() 264 FINAL = auto() 265 FIRST = auto() 266 FOR = auto() 267 FORCE = auto() 268 FOREIGN_KEY = auto() 269 FORMAT = auto() 270 FROM = auto() 271 FULL = auto() 272 FUNCTION = auto() 273 GLOB = auto() 274 GLOBAL = auto() 275 GRANT = auto() 276 GROUP_BY = auto() 277 GROUPING_SETS = auto() 278 HAVING = auto() 279 HINT = auto() 280 IGNORE = auto() 281 ILIKE = auto() 282 ILIKE_ANY = auto() 283 IN = auto() 284 INDEX = auto() 285 INNER = auto() 286 INSERT = auto() 287 INTERSECT = auto() 288 INTERVAL = auto() 289 INTO = auto() 290 INTRODUCER = auto() 291 IRLIKE = auto() 292 IS = auto() 293 ISNULL = auto() 294 JOIN = auto() 295 JOIN_MARKER = auto() 296 KEEP = auto() 297 KEY = auto() 298 KILL = auto() 299 LANGUAGE = auto() 300 LATERAL = auto() 301 LEFT = auto() 302 LIKE = auto() 303 LIKE_ANY = auto() 304 LIMIT = auto() 305 LIST = auto() 306 LOAD = auto() 307 LOCK = auto() 308 MAP = auto() 309 MATCH_CONDITION = auto() 310 MATCH_RECOGNIZE = auto() 311 MEMBER_OF = auto() 312 MERGE = auto() 313 MOD = auto() 314 MODEL = auto() 315 NATURAL = auto() 316 NEXT = auto() 317 NOTNULL = auto() 318 NULL = auto() 319 OBJECT_IDENTIFIER = auto() 320 OFFSET = auto() 321 ON = auto() 322 ONLY = auto() 323 OPERATOR = auto() 324 ORDER_BY = auto() 325 ORDER_SIBLINGS_BY = auto() 326 ORDERED = auto() 327 ORDINALITY = auto() 328 OUTER = auto() 329 OVER = auto() 330 OVERLAPS = auto() 331 OVERWRITE = auto() 332 PARTITION = auto() 333 PARTITION_BY = auto() 334 PERCENT = auto() 335 PIVOT = auto() 336 PLACEHOLDER = auto() 337 POSITIONAL = auto() 338 PRAGMA = auto() 339 PREWHERE = auto() 340 PRIMARY_KEY = auto() 341 PROCEDURE = auto() 342 PROPERTIES = auto() 343 PSEUDO_TYPE = auto() 344 QUALIFY = auto() 345 QUOTE = auto() 346 RANGE = auto() 347 RECURSIVE = auto() 348 REFRESH = auto() 349 RENAME = auto() 350 REPLACE = auto() 351 RETURNING = auto() 352 REFERENCES = auto() 353 RIGHT = auto() 354 RLIKE = auto() 355 ROLLBACK = auto() 356 ROLLUP = auto() 357 ROW = auto() 358 ROWS = auto() 359 SELECT = auto() 360 SEMI = auto() 361 SEPARATOR = auto() 362 SEQUENCE = auto() 363 SERDE_PROPERTIES = auto() 364 SET = auto() 365 SETTINGS = auto() 366 SHOW = auto() 367 SIMILAR_TO = auto() 368 SOME = auto() 369 SORT_BY = auto() 370 START_WITH = auto() 371 STORAGE_INTEGRATION = auto() 372 STRAIGHT_JOIN = auto() 373 STRUCT = auto() 374 SUMMARIZE = auto() 375 TABLE_SAMPLE = auto() 376 TAG = auto() 377 TEMPORARY = auto() 378 TOP = auto() 379 THEN = auto() 380 TRUE = auto() 381 TRUNCATE = auto() 382 UNCACHE = auto() 383 UNION = auto() 384 UNNEST = auto() 385 UNPIVOT = auto() 386 UPDATE = auto() 387 USE = auto() 388 USING = auto() 389 VALUES = auto() 390 VIEW = auto() 391 VOLATILE = auto() 392 WHEN = auto() 393 WHERE = auto() 394 WINDOW = auto() 395 WITH = auto() 396 UNIQUE = auto() 397 VERSION_SNAPSHOT = auto() 398 TIMESTAMP_SNAPSHOT = auto() 399 OPTION = auto() 400 401 402_ALL_TOKEN_TYPES = list(TokenType) 403_TOKEN_TYPE_TO_INDEX = {token_type: i for i, token_type in enumerate(_ALL_TOKEN_TYPES)} 404 405 406class Token: 407 __slots__ = ("token_type", "text", "line", "col", "start", "end", "comments") 408 409 @classmethod 410 def number(cls, number: int) -> Token: 411 """Returns a NUMBER token with `number` as its text.""" 412 return cls(TokenType.NUMBER, str(number)) 413 414 @classmethod 415 def string(cls, string: str) -> Token: 416 """Returns a STRING token with `string` as its text.""" 417 return cls(TokenType.STRING, string) 418 419 @classmethod 420 def identifier(cls, identifier: str) -> Token: 421 """Returns an IDENTIFIER token with `identifier` as its text.""" 422 return cls(TokenType.IDENTIFIER, identifier) 423 424 @classmethod 425 def var(cls, var: str) -> Token: 426 """Returns an VAR token with `var` as its text.""" 427 return cls(TokenType.VAR, var) 428 429 def __init__( 430 self, 431 token_type: TokenType, 432 text: str, 433 line: int = 1, 434 col: int = 1, 435 start: int = 0, 436 end: int = 0, 437 comments: t.Optional[t.List[str]] = None, 438 ) -> None: 439 """Token initializer. 440 441 Args: 442 token_type: The TokenType Enum. 443 text: The text of the token. 444 line: The line that the token ends on. 445 col: The column that the token ends on. 446 start: The start index of the token. 447 end: The ending index of the token. 448 comments: The comments to attach to the token. 449 """ 450 self.token_type = token_type 451 self.text = text 452 self.line = line 453 self.col = col 454 self.start = start 455 self.end = end 456 self.comments = [] if comments is None else comments 457 458 def __repr__(self) -> str: 459 attributes = ", ".join(f"{k}: {getattr(self, k)}" for k in self.__slots__) 460 return f"<Token {attributes}>" 461 462 463class _Tokenizer(type): 464 def __new__(cls, clsname, bases, attrs): 465 klass = super().__new__(cls, clsname, bases, attrs) 466 467 def _convert_quotes(arr: t.List[str | t.Tuple[str, str]]) -> t.Dict[str, str]: 468 return dict( 469 (item, item) if isinstance(item, str) else (item[0], item[1]) for item in arr 470 ) 471 472 def _quotes_to_format( 473 token_type: TokenType, arr: t.List[str | t.Tuple[str, str]] 474 ) -> t.Dict[str, t.Tuple[str, TokenType]]: 475 return {k: (v, token_type) for k, v in _convert_quotes(arr).items()} 476 477 klass._QUOTES = _convert_quotes(klass.QUOTES) 478 klass._IDENTIFIERS = _convert_quotes(klass.IDENTIFIERS) 479 480 klass._FORMAT_STRINGS = { 481 **{ 482 p + s: (e, TokenType.NATIONAL_STRING) 483 for s, e in klass._QUOTES.items() 484 for p in ("n", "N") 485 }, 486 **_quotes_to_format(TokenType.BIT_STRING, klass.BIT_STRINGS), 487 **_quotes_to_format(TokenType.BYTE_STRING, klass.BYTE_STRINGS), 488 **_quotes_to_format(TokenType.HEX_STRING, klass.HEX_STRINGS), 489 **_quotes_to_format(TokenType.RAW_STRING, klass.RAW_STRINGS), 490 **_quotes_to_format(TokenType.HEREDOC_STRING, klass.HEREDOC_STRINGS), 491 **_quotes_to_format(TokenType.UNICODE_STRING, klass.UNICODE_STRINGS), 492 } 493 494 klass._STRING_ESCAPES = set(klass.STRING_ESCAPES) 495 klass._IDENTIFIER_ESCAPES = set(klass.IDENTIFIER_ESCAPES) 496 klass._COMMENTS = { 497 **dict( 498 (comment, None) if isinstance(comment, str) else (comment[0], comment[1]) 499 for comment in klass.COMMENTS 500 ), 501 "{#": "#}", # Ensure Jinja comments are tokenized correctly in all dialects 502 } 503 504 klass._KEYWORD_TRIE = new_trie( 505 key.upper() 506 for key in ( 507 *klass.KEYWORDS, 508 *klass._COMMENTS, 509 *klass._QUOTES, 510 *klass._FORMAT_STRINGS, 511 ) 512 if " " in key or any(single in key for single in klass.SINGLE_TOKENS) 513 ) 514 515 if USE_RS_TOKENIZER: 516 settings = RsTokenizerSettings( 517 white_space={k: _TOKEN_TYPE_TO_INDEX[v] for k, v in klass.WHITE_SPACE.items()}, 518 single_tokens={k: _TOKEN_TYPE_TO_INDEX[v] for k, v in klass.SINGLE_TOKENS.items()}, 519 keywords={k: _TOKEN_TYPE_TO_INDEX[v] for k, v in klass.KEYWORDS.items()}, 520 numeric_literals=klass.NUMERIC_LITERALS, 521 identifiers=klass._IDENTIFIERS, 522 identifier_escapes=klass._IDENTIFIER_ESCAPES, 523 string_escapes=klass._STRING_ESCAPES, 524 quotes=klass._QUOTES, 525 format_strings={ 526 k: (v1, _TOKEN_TYPE_TO_INDEX[v2]) 527 for k, (v1, v2) in klass._FORMAT_STRINGS.items() 528 }, 529 has_bit_strings=bool(klass.BIT_STRINGS), 530 has_hex_strings=bool(klass.HEX_STRINGS), 531 comments=klass._COMMENTS, 532 var_single_tokens=klass.VAR_SINGLE_TOKENS, 533 commands={_TOKEN_TYPE_TO_INDEX[v] for v in klass.COMMANDS}, 534 command_prefix_tokens={ 535 _TOKEN_TYPE_TO_INDEX[v] for v in klass.COMMAND_PREFIX_TOKENS 536 }, 537 heredoc_tag_is_identifier=klass.HEREDOC_TAG_IS_IDENTIFIER, 538 string_escapes_allowed_in_raw_strings=klass.STRING_ESCAPES_ALLOWED_IN_RAW_STRINGS, 539 nested_comments=klass.NESTED_COMMENTS, 540 ) 541 token_types = RsTokenTypeSettings( 542 bit_string=_TOKEN_TYPE_TO_INDEX[TokenType.BIT_STRING], 543 break_=_TOKEN_TYPE_TO_INDEX[TokenType.BREAK], 544 dcolon=_TOKEN_TYPE_TO_INDEX[TokenType.DCOLON], 545 heredoc_string=_TOKEN_TYPE_TO_INDEX[TokenType.HEREDOC_STRING], 546 raw_string=_TOKEN_TYPE_TO_INDEX[TokenType.RAW_STRING], 547 hex_string=_TOKEN_TYPE_TO_INDEX[TokenType.HEX_STRING], 548 identifier=_TOKEN_TYPE_TO_INDEX[TokenType.IDENTIFIER], 549 number=_TOKEN_TYPE_TO_INDEX[TokenType.NUMBER], 550 parameter=_TOKEN_TYPE_TO_INDEX[TokenType.PARAMETER], 551 semicolon=_TOKEN_TYPE_TO_INDEX[TokenType.SEMICOLON], 552 string=_TOKEN_TYPE_TO_INDEX[TokenType.STRING], 553 var=_TOKEN_TYPE_TO_INDEX[TokenType.VAR], 554 heredoc_string_alternative=_TOKEN_TYPE_TO_INDEX[klass.HEREDOC_STRING_ALTERNATIVE], 555 ) 556 klass._RS_TOKENIZER = RsTokenizer(settings, token_types) 557 else: 558 klass._RS_TOKENIZER = None 559 560 return klass 561 562 563class Tokenizer(metaclass=_Tokenizer): 564 SINGLE_TOKENS = { 565 "(": TokenType.L_PAREN, 566 ")": TokenType.R_PAREN, 567 "[": TokenType.L_BRACKET, 568 "]": TokenType.R_BRACKET, 569 "{": TokenType.L_BRACE, 570 "}": TokenType.R_BRACE, 571 "&": TokenType.AMP, 572 "^": TokenType.CARET, 573 ":": TokenType.COLON, 574 ",": TokenType.COMMA, 575 ".": TokenType.DOT, 576 "-": TokenType.DASH, 577 "=": TokenType.EQ, 578 ">": TokenType.GT, 579 "<": TokenType.LT, 580 "%": TokenType.MOD, 581 "!": TokenType.NOT, 582 "|": TokenType.PIPE, 583 "+": TokenType.PLUS, 584 ";": TokenType.SEMICOLON, 585 "/": TokenType.SLASH, 586 "\\": TokenType.BACKSLASH, 587 "*": TokenType.STAR, 588 "~": TokenType.TILDA, 589 "?": TokenType.PLACEHOLDER, 590 "@": TokenType.PARAMETER, 591 "#": TokenType.HASH, 592 # Used for breaking a var like x'y' but nothing else the token type doesn't matter 593 "'": TokenType.UNKNOWN, 594 "`": TokenType.UNKNOWN, 595 '"': TokenType.UNKNOWN, 596 } 597 598 BIT_STRINGS: t.List[str | t.Tuple[str, str]] = [] 599 BYTE_STRINGS: t.List[str | t.Tuple[str, str]] = [] 600 HEX_STRINGS: t.List[str | t.Tuple[str, str]] = [] 601 RAW_STRINGS: t.List[str | t.Tuple[str, str]] = [] 602 HEREDOC_STRINGS: t.List[str | t.Tuple[str, str]] = [] 603 UNICODE_STRINGS: t.List[str | t.Tuple[str, str]] = [] 604 IDENTIFIERS: t.List[str | t.Tuple[str, str]] = ['"'] 605 IDENTIFIER_ESCAPES = ['"'] 606 QUOTES: t.List[t.Tuple[str, str] | str] = ["'"] 607 STRING_ESCAPES = ["'"] 608 VAR_SINGLE_TOKENS: t.Set[str] = set() 609 610 # Whether the heredoc tags follow the same lexical rules as unquoted identifiers 611 HEREDOC_TAG_IS_IDENTIFIER = False 612 613 # Token that we'll generate as a fallback if the heredoc prefix doesn't correspond to a heredoc 614 HEREDOC_STRING_ALTERNATIVE = TokenType.VAR 615 616 # Whether string escape characters function as such when placed within raw strings 617 STRING_ESCAPES_ALLOWED_IN_RAW_STRINGS = True 618 619 NESTED_COMMENTS = True 620 621 # Autofilled 622 _COMMENTS: t.Dict[str, str] = {} 623 _FORMAT_STRINGS: t.Dict[str, t.Tuple[str, TokenType]] = {} 624 _IDENTIFIERS: t.Dict[str, str] = {} 625 _IDENTIFIER_ESCAPES: t.Set[str] = set() 626 _QUOTES: t.Dict[str, str] = {} 627 _STRING_ESCAPES: t.Set[str] = set() 628 _KEYWORD_TRIE: t.Dict = {} 629 _RS_TOKENIZER: t.Optional[t.Any] = None 630 631 KEYWORDS: t.Dict[str, TokenType] = { 632 **{f"{{%{postfix}": TokenType.BLOCK_START for postfix in ("", "+", "-")}, 633 **{f"{prefix}%}}": TokenType.BLOCK_END for prefix in ("", "+", "-")}, 634 **{f"{{{{{postfix}": TokenType.BLOCK_START for postfix in ("+", "-")}, 635 **{f"{prefix}}}}}": TokenType.BLOCK_END for prefix in ("+", "-")}, 636 "/*+": TokenType.HINT, 637 "==": TokenType.EQ, 638 "::": TokenType.DCOLON, 639 "||": TokenType.DPIPE, 640 ">=": TokenType.GTE, 641 "<=": TokenType.LTE, 642 "<>": TokenType.NEQ, 643 "!=": TokenType.NEQ, 644 ":=": TokenType.COLON_EQ, 645 "<=>": TokenType.NULLSAFE_EQ, 646 "->": TokenType.ARROW, 647 "->>": TokenType.DARROW, 648 "=>": TokenType.FARROW, 649 "#>": TokenType.HASH_ARROW, 650 "#>>": TokenType.DHASH_ARROW, 651 "<->": TokenType.LR_ARROW, 652 "&&": TokenType.DAMP, 653 "??": TokenType.DQMARK, 654 "~~~": TokenType.GLOB, 655 "~~": TokenType.LIKE, 656 "~~*": TokenType.ILIKE, 657 "~*": TokenType.IRLIKE, 658 "ALL": TokenType.ALL, 659 "ALWAYS": TokenType.ALWAYS, 660 "AND": TokenType.AND, 661 "ANTI": TokenType.ANTI, 662 "ANY": TokenType.ANY, 663 "ASC": TokenType.ASC, 664 "AS": TokenType.ALIAS, 665 "ASOF": TokenType.ASOF, 666 "AUTOINCREMENT": TokenType.AUTO_INCREMENT, 667 "AUTO_INCREMENT": TokenType.AUTO_INCREMENT, 668 "BEGIN": TokenType.BEGIN, 669 "BETWEEN": TokenType.BETWEEN, 670 "CACHE": TokenType.CACHE, 671 "UNCACHE": TokenType.UNCACHE, 672 "CASE": TokenType.CASE, 673 "CHARACTER SET": TokenType.CHARACTER_SET, 674 "CLUSTER BY": TokenType.CLUSTER_BY, 675 "COLLATE": TokenType.COLLATE, 676 "COLUMN": TokenType.COLUMN, 677 "COMMIT": TokenType.COMMIT, 678 "CONNECT BY": TokenType.CONNECT_BY, 679 "CONSTRAINT": TokenType.CONSTRAINT, 680 "COPY": TokenType.COPY, 681 "CREATE": TokenType.CREATE, 682 "CROSS": TokenType.CROSS, 683 "CUBE": TokenType.CUBE, 684 "CURRENT_DATE": TokenType.CURRENT_DATE, 685 "CURRENT_TIME": TokenType.CURRENT_TIME, 686 "CURRENT_TIMESTAMP": TokenType.CURRENT_TIMESTAMP, 687 "CURRENT_USER": TokenType.CURRENT_USER, 688 "DATABASE": TokenType.DATABASE, 689 "DEFAULT": TokenType.DEFAULT, 690 "DELETE": TokenType.DELETE, 691 "DESC": TokenType.DESC, 692 "DESCRIBE": TokenType.DESCRIBE, 693 "DISTINCT": TokenType.DISTINCT, 694 "DISTRIBUTE BY": TokenType.DISTRIBUTE_BY, 695 "DIV": TokenType.DIV, 696 "DROP": TokenType.DROP, 697 "ELSE": TokenType.ELSE, 698 "END": TokenType.END, 699 "ENUM": TokenType.ENUM, 700 "ESCAPE": TokenType.ESCAPE, 701 "EXCEPT": TokenType.EXCEPT, 702 "EXECUTE": TokenType.EXECUTE, 703 "EXISTS": TokenType.EXISTS, 704 "FALSE": TokenType.FALSE, 705 "FETCH": TokenType.FETCH, 706 "FILTER": TokenType.FILTER, 707 "FIRST": TokenType.FIRST, 708 "FULL": TokenType.FULL, 709 "FUNCTION": TokenType.FUNCTION, 710 "FOR": TokenType.FOR, 711 "FOREIGN KEY": TokenType.FOREIGN_KEY, 712 "FORMAT": TokenType.FORMAT, 713 "FROM": TokenType.FROM, 714 "GEOGRAPHY": TokenType.GEOGRAPHY, 715 "GEOMETRY": TokenType.GEOMETRY, 716 "GLOB": TokenType.GLOB, 717 "GROUP BY": TokenType.GROUP_BY, 718 "GROUPING SETS": TokenType.GROUPING_SETS, 719 "HAVING": TokenType.HAVING, 720 "ILIKE": TokenType.ILIKE, 721 "IN": TokenType.IN, 722 "INDEX": TokenType.INDEX, 723 "INET": TokenType.INET, 724 "INNER": TokenType.INNER, 725 "INSERT": TokenType.INSERT, 726 "INTERVAL": TokenType.INTERVAL, 727 "INTERSECT": TokenType.INTERSECT, 728 "INTO": TokenType.INTO, 729 "IS": TokenType.IS, 730 "ISNULL": TokenType.ISNULL, 731 "JOIN": TokenType.JOIN, 732 "KEEP": TokenType.KEEP, 733 "KILL": TokenType.KILL, 734 "LATERAL": TokenType.LATERAL, 735 "LEFT": TokenType.LEFT, 736 "LIKE": TokenType.LIKE, 737 "LIMIT": TokenType.LIMIT, 738 "LOAD": TokenType.LOAD, 739 "LOCK": TokenType.LOCK, 740 "MERGE": TokenType.MERGE, 741 "NATURAL": TokenType.NATURAL, 742 "NEXT": TokenType.NEXT, 743 "NOT": TokenType.NOT, 744 "NOTNULL": TokenType.NOTNULL, 745 "NULL": TokenType.NULL, 746 "OBJECT": TokenType.OBJECT, 747 "OFFSET": TokenType.OFFSET, 748 "ON": TokenType.ON, 749 "OR": TokenType.OR, 750 "XOR": TokenType.XOR, 751 "ORDER BY": TokenType.ORDER_BY, 752 "ORDINALITY": TokenType.ORDINALITY, 753 "OUTER": TokenType.OUTER, 754 "OVER": TokenType.OVER, 755 "OVERLAPS": TokenType.OVERLAPS, 756 "OVERWRITE": TokenType.OVERWRITE, 757 "PARTITION": TokenType.PARTITION, 758 "PARTITION BY": TokenType.PARTITION_BY, 759 "PARTITIONED BY": TokenType.PARTITION_BY, 760 "PARTITIONED_BY": TokenType.PARTITION_BY, 761 "PERCENT": TokenType.PERCENT, 762 "PIVOT": TokenType.PIVOT, 763 "PRAGMA": TokenType.PRAGMA, 764 "PRIMARY KEY": TokenType.PRIMARY_KEY, 765 "PROCEDURE": TokenType.PROCEDURE, 766 "QUALIFY": TokenType.QUALIFY, 767 "RANGE": TokenType.RANGE, 768 "RECURSIVE": TokenType.RECURSIVE, 769 "REGEXP": TokenType.RLIKE, 770 "RENAME": TokenType.RENAME, 771 "REPLACE": TokenType.REPLACE, 772 "RETURNING": TokenType.RETURNING, 773 "REFERENCES": TokenType.REFERENCES, 774 "RIGHT": TokenType.RIGHT, 775 "RLIKE": TokenType.RLIKE, 776 "ROLLBACK": TokenType.ROLLBACK, 777 "ROLLUP": TokenType.ROLLUP, 778 "ROW": TokenType.ROW, 779 "ROWS": TokenType.ROWS, 780 "SCHEMA": TokenType.SCHEMA, 781 "SELECT": TokenType.SELECT, 782 "SEMI": TokenType.SEMI, 783 "SET": TokenType.SET, 784 "SETTINGS": TokenType.SETTINGS, 785 "SHOW": TokenType.SHOW, 786 "SIMILAR TO": TokenType.SIMILAR_TO, 787 "SOME": TokenType.SOME, 788 "SORT BY": TokenType.SORT_BY, 789 "START WITH": TokenType.START_WITH, 790 "STRAIGHT_JOIN": TokenType.STRAIGHT_JOIN, 791 "TABLE": TokenType.TABLE, 792 "TABLESAMPLE": TokenType.TABLE_SAMPLE, 793 "TEMP": TokenType.TEMPORARY, 794 "TEMPORARY": TokenType.TEMPORARY, 795 "THEN": TokenType.THEN, 796 "TRUE": TokenType.TRUE, 797 "TRUNCATE": TokenType.TRUNCATE, 798 "UNION": TokenType.UNION, 799 "UNKNOWN": TokenType.UNKNOWN, 800 "UNNEST": TokenType.UNNEST, 801 "UNPIVOT": TokenType.UNPIVOT, 802 "UPDATE": TokenType.UPDATE, 803 "USE": TokenType.USE, 804 "USING": TokenType.USING, 805 "UUID": TokenType.UUID, 806 "VALUES": TokenType.VALUES, 807 "VIEW": TokenType.VIEW, 808 "VOLATILE": TokenType.VOLATILE, 809 "WHEN": TokenType.WHEN, 810 "WHERE": TokenType.WHERE, 811 "WINDOW": TokenType.WINDOW, 812 "WITH": TokenType.WITH, 813 "APPLY": TokenType.APPLY, 814 "ARRAY": TokenType.ARRAY, 815 "BIT": TokenType.BIT, 816 "BOOL": TokenType.BOOLEAN, 817 "BOOLEAN": TokenType.BOOLEAN, 818 "BYTE": TokenType.TINYINT, 819 "MEDIUMINT": TokenType.MEDIUMINT, 820 "INT1": TokenType.TINYINT, 821 "TINYINT": TokenType.TINYINT, 822 "INT16": TokenType.SMALLINT, 823 "SHORT": TokenType.SMALLINT, 824 "SMALLINT": TokenType.SMALLINT, 825 "INT128": TokenType.INT128, 826 "HUGEINT": TokenType.INT128, 827 "UHUGEINT": TokenType.UINT128, 828 "INT2": TokenType.SMALLINT, 829 "INTEGER": TokenType.INT, 830 "INT": TokenType.INT, 831 "INT4": TokenType.INT, 832 "INT32": TokenType.INT, 833 "INT64": TokenType.BIGINT, 834 "LONG": TokenType.BIGINT, 835 "BIGINT": TokenType.BIGINT, 836 "INT8": TokenType.TINYINT, 837 "UINT": TokenType.UINT, 838 "DEC": TokenType.DECIMAL, 839 "DECIMAL": TokenType.DECIMAL, 840 "DECIMAL32": TokenType.DECIMAL32, 841 "DECIMAL64": TokenType.DECIMAL64, 842 "DECIMAL128": TokenType.DECIMAL128, 843 "BIGDECIMAL": TokenType.BIGDECIMAL, 844 "BIGNUMERIC": TokenType.BIGDECIMAL, 845 "LIST": TokenType.LIST, 846 "MAP": TokenType.MAP, 847 "NULLABLE": TokenType.NULLABLE, 848 "NUMBER": TokenType.DECIMAL, 849 "NUMERIC": TokenType.DECIMAL, 850 "FIXED": TokenType.DECIMAL, 851 "REAL": TokenType.FLOAT, 852 "FLOAT": TokenType.FLOAT, 853 "FLOAT4": TokenType.FLOAT, 854 "FLOAT8": TokenType.DOUBLE, 855 "DOUBLE": TokenType.DOUBLE, 856 "DOUBLE PRECISION": TokenType.DOUBLE, 857 "JSON": TokenType.JSON, 858 "JSONB": TokenType.JSONB, 859 "CHAR": TokenType.CHAR, 860 "CHARACTER": TokenType.CHAR, 861 "NCHAR": TokenType.NCHAR, 862 "VARCHAR": TokenType.VARCHAR, 863 "VARCHAR2": TokenType.VARCHAR, 864 "NVARCHAR": TokenType.NVARCHAR, 865 "NVARCHAR2": TokenType.NVARCHAR, 866 "BPCHAR": TokenType.BPCHAR, 867 "STR": TokenType.TEXT, 868 "STRING": TokenType.TEXT, 869 "TEXT": TokenType.TEXT, 870 "LONGTEXT": TokenType.LONGTEXT, 871 "MEDIUMTEXT": TokenType.MEDIUMTEXT, 872 "TINYTEXT": TokenType.TINYTEXT, 873 "CLOB": TokenType.TEXT, 874 "LONGVARCHAR": TokenType.TEXT, 875 "BINARY": TokenType.BINARY, 876 "BLOB": TokenType.VARBINARY, 877 "LONGBLOB": TokenType.LONGBLOB, 878 "MEDIUMBLOB": TokenType.MEDIUMBLOB, 879 "TINYBLOB": TokenType.TINYBLOB, 880 "BYTEA": TokenType.VARBINARY, 881 "VARBINARY": TokenType.VARBINARY, 882 "TIME": TokenType.TIME, 883 "TIMETZ": TokenType.TIMETZ, 884 "TIMESTAMP": TokenType.TIMESTAMP, 885 "TIMESTAMPTZ": TokenType.TIMESTAMPTZ, 886 "TIMESTAMPLTZ": TokenType.TIMESTAMPLTZ, 887 "TIMESTAMP_LTZ": TokenType.TIMESTAMPLTZ, 888 "TIMESTAMPNTZ": TokenType.TIMESTAMPNTZ, 889 "TIMESTAMP_NTZ": TokenType.TIMESTAMPNTZ, 890 "DATE": TokenType.DATE, 891 "DATETIME": TokenType.DATETIME, 892 "INT4RANGE": TokenType.INT4RANGE, 893 "INT4MULTIRANGE": TokenType.INT4MULTIRANGE, 894 "INT8RANGE": TokenType.INT8RANGE, 895 "INT8MULTIRANGE": TokenType.INT8MULTIRANGE, 896 "NUMRANGE": TokenType.NUMRANGE, 897 "NUMMULTIRANGE": TokenType.NUMMULTIRANGE, 898 "TSRANGE": TokenType.TSRANGE, 899 "TSMULTIRANGE": TokenType.TSMULTIRANGE, 900 "TSTZRANGE": TokenType.TSTZRANGE, 901 "TSTZMULTIRANGE": TokenType.TSTZMULTIRANGE, 902 "DATERANGE": TokenType.DATERANGE, 903 "DATEMULTIRANGE": TokenType.DATEMULTIRANGE, 904 "UNIQUE": TokenType.UNIQUE, 905 "VECTOR": TokenType.VECTOR, 906 "STRUCT": TokenType.STRUCT, 907 "SEQUENCE": TokenType.SEQUENCE, 908 "VARIANT": TokenType.VARIANT, 909 "ALTER": TokenType.ALTER, 910 "ANALYZE": TokenType.COMMAND, 911 "CALL": TokenType.COMMAND, 912 "COMMENT": TokenType.COMMENT, 913 "EXPLAIN": TokenType.COMMAND, 914 "GRANT": TokenType.GRANT, 915 "OPTIMIZE": TokenType.COMMAND, 916 "PREPARE": TokenType.COMMAND, 917 "VACUUM": TokenType.COMMAND, 918 "USER-DEFINED": TokenType.USERDEFINED, 919 "FOR VERSION": TokenType.VERSION_SNAPSHOT, 920 "FOR TIMESTAMP": TokenType.TIMESTAMP_SNAPSHOT, 921 } 922 923 WHITE_SPACE: t.Dict[t.Optional[str], TokenType] = { 924 " ": TokenType.SPACE, 925 "\t": TokenType.SPACE, 926 "\n": TokenType.BREAK, 927 "\r": TokenType.BREAK, 928 } 929 930 COMMANDS = { 931 TokenType.COMMAND, 932 TokenType.EXECUTE, 933 TokenType.FETCH, 934 TokenType.SHOW, 935 TokenType.RENAME, 936 } 937 938 COMMAND_PREFIX_TOKENS = {TokenType.SEMICOLON, TokenType.BEGIN} 939 940 # Handle numeric literals like in hive (3L = BIGINT) 941 NUMERIC_LITERALS: t.Dict[str, str] = {} 942 943 COMMENTS = ["--", ("/*", "*/")] 944 945 __slots__ = ( 946 "sql", 947 "size", 948 "tokens", 949 "dialect", 950 "_start", 951 "_current", 952 "_line", 953 "_col", 954 "_comments", 955 "_char", 956 "_end", 957 "_peek", 958 "_prev_token_line", 959 "_rs_dialect_settings", 960 ) 961 962 def __init__(self, dialect: DialectType = None) -> None: 963 from sqlglot.dialects import Dialect 964 965 self.dialect = Dialect.get_or_raise(dialect) 966 967 if USE_RS_TOKENIZER: 968 self._rs_dialect_settings = RsTokenizerDialectSettings( 969 unescaped_sequences=self.dialect.UNESCAPED_SEQUENCES, 970 identifiers_can_start_with_digit=self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT, 971 ) 972 973 self.reset() 974 975 def reset(self) -> None: 976 self.sql = "" 977 self.size = 0 978 self.tokens: t.List[Token] = [] 979 self._start = 0 980 self._current = 0 981 self._line = 1 982 self._col = 0 983 self._comments: t.List[str] = [] 984 985 self._char = "" 986 self._end = False 987 self._peek = "" 988 self._prev_token_line = -1 989 990 def tokenize(self, sql: str) -> t.List[Token]: 991 """Returns a list of tokens corresponding to the SQL string `sql`.""" 992 if USE_RS_TOKENIZER: 993 return self.tokenize_rs(sql) 994 995 self.reset() 996 self.sql = sql 997 self.size = len(sql) 998 999 try: 1000 self._scan() 1001 except Exception as e: 1002 start = max(self._current - 50, 0) 1003 end = min(self._current + 50, self.size - 1) 1004 context = self.sql[start:end] 1005 raise TokenError(f"Error tokenizing '{context}'") from e 1006 1007 return self.tokens 1008 1009 def _scan(self, until: t.Optional[t.Callable] = None) -> None: 1010 while self.size and not self._end: 1011 current = self._current 1012 1013 # Skip spaces here rather than iteratively calling advance() for performance reasons 1014 while current < self.size: 1015 char = self.sql[current] 1016 1017 if char.isspace() and (char == " " or char == "\t"): 1018 current += 1 1019 else: 1020 break 1021 1022 offset = current - self._current if current > self._current else 1 1023 1024 self._start = current 1025 self._advance(offset) 1026 1027 if not self._char.isspace(): 1028 if self._char.isdigit(): 1029 self._scan_number() 1030 elif self._char in self._IDENTIFIERS: 1031 self._scan_identifier(self._IDENTIFIERS[self._char]) 1032 else: 1033 self._scan_keywords() 1034 1035 if until and until(): 1036 break 1037 1038 if self.tokens and self._comments: 1039 self.tokens[-1].comments.extend(self._comments) 1040 1041 def _chars(self, size: int) -> str: 1042 if size == 1: 1043 return self._char 1044 1045 start = self._current - 1 1046 end = start + size 1047 1048 return self.sql[start:end] if end <= self.size else "" 1049 1050 def _advance(self, i: int = 1, alnum: bool = False) -> None: 1051 if self.WHITE_SPACE.get(self._char) is TokenType.BREAK: 1052 # Ensures we don't count an extra line if we get a \r\n line break sequence 1053 if not (self._char == "\r" and self._peek == "\n"): 1054 self._col = 1 1055 self._line += 1 1056 else: 1057 self._col += i 1058 1059 self._current += i 1060 self._end = self._current >= self.size 1061 self._char = self.sql[self._current - 1] 1062 self._peek = "" if self._end else self.sql[self._current] 1063 1064 if alnum and self._char.isalnum(): 1065 # Here we use local variables instead of attributes for better performance 1066 _col = self._col 1067 _current = self._current 1068 _end = self._end 1069 _peek = self._peek 1070 1071 while _peek.isalnum(): 1072 _col += 1 1073 _current += 1 1074 _end = _current >= self.size 1075 _peek = "" if _end else self.sql[_current] 1076 1077 self._col = _col 1078 self._current = _current 1079 self._end = _end 1080 self._peek = _peek 1081 self._char = self.sql[_current - 1] 1082 1083 @property 1084 def _text(self) -> str: 1085 return self.sql[self._start : self._current] 1086 1087 def _add(self, token_type: TokenType, text: t.Optional[str] = None) -> None: 1088 self._prev_token_line = self._line 1089 1090 if self._comments and token_type == TokenType.SEMICOLON and self.tokens: 1091 self.tokens[-1].comments.extend(self._comments) 1092 self._comments = [] 1093 1094 self.tokens.append( 1095 Token( 1096 token_type, 1097 text=self._text if text is None else text, 1098 line=self._line, 1099 col=self._col, 1100 start=self._start, 1101 end=self._current - 1, 1102 comments=self._comments, 1103 ) 1104 ) 1105 self._comments = [] 1106 1107 # If we have either a semicolon or a begin token before the command's token, we'll parse 1108 # whatever follows the command's token as a string 1109 if ( 1110 token_type in self.COMMANDS 1111 and self._peek != ";" 1112 and (len(self.tokens) == 1 or self.tokens[-2].token_type in self.COMMAND_PREFIX_TOKENS) 1113 ): 1114 start = self._current 1115 tokens = len(self.tokens) 1116 self._scan(lambda: self._peek == ";") 1117 self.tokens = self.tokens[:tokens] 1118 text = self.sql[start : self._current].strip() 1119 if text: 1120 self._add(TokenType.STRING, text) 1121 1122 def _scan_keywords(self) -> None: 1123 size = 0 1124 word = None 1125 chars = self._text 1126 char = chars 1127 prev_space = False 1128 skip = False 1129 trie = self._KEYWORD_TRIE 1130 single_token = char in self.SINGLE_TOKENS 1131 1132 while chars: 1133 if skip: 1134 result = TrieResult.PREFIX 1135 else: 1136 result, trie = in_trie(trie, char.upper()) 1137 1138 if result == TrieResult.FAILED: 1139 break 1140 if result == TrieResult.EXISTS: 1141 word = chars 1142 1143 end = self._current + size 1144 size += 1 1145 1146 if end < self.size: 1147 char = self.sql[end] 1148 single_token = single_token or char in self.SINGLE_TOKENS 1149 is_space = char.isspace() 1150 1151 if not is_space or not prev_space: 1152 if is_space: 1153 char = " " 1154 chars += char 1155 prev_space = is_space 1156 skip = False 1157 else: 1158 skip = True 1159 else: 1160 char = "" 1161 break 1162 1163 if word: 1164 if self._scan_string(word): 1165 return 1166 if self._scan_comment(word): 1167 return 1168 if prev_space or single_token or not char: 1169 self._advance(size - 1) 1170 word = word.upper() 1171 self._add(self.KEYWORDS[word], text=word) 1172 return 1173 1174 if self._char in self.SINGLE_TOKENS: 1175 self._add(self.SINGLE_TOKENS[self._char], text=self._char) 1176 return 1177 1178 self._scan_var() 1179 1180 def _scan_comment(self, comment_start: str) -> bool: 1181 if comment_start not in self._COMMENTS: 1182 return False 1183 1184 comment_start_line = self._line 1185 comment_start_size = len(comment_start) 1186 comment_end = self._COMMENTS[comment_start] 1187 1188 if comment_end: 1189 # Skip the comment's start delimiter 1190 self._advance(comment_start_size) 1191 1192 comment_count = 1 1193 comment_end_size = len(comment_end) 1194 1195 while not self._end: 1196 if self._chars(comment_end_size) == comment_end: 1197 comment_count -= 1 1198 if not comment_count: 1199 break 1200 1201 self._advance(alnum=True) 1202 1203 # Nested comments are allowed by some dialects, e.g. databricks, duckdb, postgres 1204 if ( 1205 self.NESTED_COMMENTS 1206 and not self._end 1207 and self._chars(comment_end_size) == comment_start 1208 ): 1209 self._advance(comment_start_size) 1210 comment_count += 1 1211 1212 self._comments.append(self._text[comment_start_size : -comment_end_size + 1]) 1213 self._advance(comment_end_size - 1) 1214 else: 1215 while not self._end and self.WHITE_SPACE.get(self._peek) is not TokenType.BREAK: 1216 self._advance(alnum=True) 1217 self._comments.append(self._text[comment_start_size:]) 1218 1219 # Leading comment is attached to the succeeding token, whilst trailing comment to the preceding. 1220 # Multiple consecutive comments are preserved by appending them to the current comments list. 1221 if comment_start_line == self._prev_token_line: 1222 self.tokens[-1].comments.extend(self._comments) 1223 self._comments = [] 1224 self._prev_token_line = self._line 1225 1226 return True 1227 1228 def _scan_number(self) -> None: 1229 if self._char == "0": 1230 peek = self._peek.upper() 1231 if peek == "B": 1232 return self._scan_bits() if self.BIT_STRINGS else self._add(TokenType.NUMBER) 1233 elif peek == "X": 1234 return self._scan_hex() if self.HEX_STRINGS else self._add(TokenType.NUMBER) 1235 1236 decimal = False 1237 scientific = 0 1238 1239 while True: 1240 if self._peek.isdigit(): 1241 self._advance() 1242 elif self._peek == "." and not decimal: 1243 if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER: 1244 return self._add(TokenType.NUMBER) 1245 decimal = True 1246 self._advance() 1247 elif self._peek in ("-", "+") and scientific == 1: 1248 scientific += 1 1249 self._advance() 1250 elif self._peek.upper() == "E" and not scientific: 1251 scientific += 1 1252 self._advance() 1253 elif self._peek.isidentifier(): 1254 number_text = self._text 1255 literal = "" 1256 1257 while self._peek.strip() and self._peek not in self.SINGLE_TOKENS: 1258 literal += self._peek 1259 self._advance() 1260 1261 token_type = self.KEYWORDS.get(self.NUMERIC_LITERALS.get(literal.upper(), "")) 1262 1263 if token_type: 1264 self._add(TokenType.NUMBER, number_text) 1265 self._add(TokenType.DCOLON, "::") 1266 return self._add(token_type, literal) 1267 elif self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT: 1268 return self._add(TokenType.VAR) 1269 1270 self._advance(-len(literal)) 1271 return self._add(TokenType.NUMBER, number_text) 1272 else: 1273 return self._add(TokenType.NUMBER) 1274 1275 def _scan_bits(self) -> None: 1276 self._advance() 1277 value = self._extract_value() 1278 try: 1279 # If `value` can't be converted to a binary, fallback to tokenizing it as an identifier 1280 int(value, 2) 1281 self._add(TokenType.BIT_STRING, value[2:]) # Drop the 0b 1282 except ValueError: 1283 self._add(TokenType.IDENTIFIER) 1284 1285 def _scan_hex(self) -> None: 1286 self._advance() 1287 value = self._extract_value() 1288 try: 1289 # If `value` can't be converted to a hex, fallback to tokenizing it as an identifier 1290 int(value, 16) 1291 self._add(TokenType.HEX_STRING, value[2:]) # Drop the 0x 1292 except ValueError: 1293 self._add(TokenType.IDENTIFIER) 1294 1295 def _extract_value(self) -> str: 1296 while True: 1297 char = self._peek.strip() 1298 if char and char not in self.SINGLE_TOKENS: 1299 self._advance(alnum=True) 1300 else: 1301 break 1302 1303 return self._text 1304 1305 def _scan_string(self, start: str) -> bool: 1306 base = None 1307 token_type = TokenType.STRING 1308 1309 if start in self._QUOTES: 1310 end = self._QUOTES[start] 1311 elif start in self._FORMAT_STRINGS: 1312 end, token_type = self._FORMAT_STRINGS[start] 1313 1314 if token_type == TokenType.HEX_STRING: 1315 base = 16 1316 elif token_type == TokenType.BIT_STRING: 1317 base = 2 1318 elif token_type == TokenType.HEREDOC_STRING: 1319 self._advance() 1320 1321 if self._char == end: 1322 tag = "" 1323 else: 1324 tag = self._extract_string( 1325 end, 1326 raw_string=True, 1327 raise_unmatched=not self.HEREDOC_TAG_IS_IDENTIFIER, 1328 ) 1329 1330 if tag and self.HEREDOC_TAG_IS_IDENTIFIER and (self._end or not tag.isidentifier()): 1331 if not self._end: 1332 self._advance(-1) 1333 1334 self._advance(-len(tag)) 1335 self._add(self.HEREDOC_STRING_ALTERNATIVE) 1336 return True 1337 1338 end = f"{start}{tag}{end}" 1339 else: 1340 return False 1341 1342 self._advance(len(start)) 1343 text = self._extract_string(end, raw_string=token_type == TokenType.RAW_STRING) 1344 1345 if base: 1346 try: 1347 int(text, base) 1348 except Exception: 1349 raise TokenError( 1350 f"Numeric string contains invalid characters from {self._line}:{self._start}" 1351 ) 1352 1353 self._add(token_type, text) 1354 return True 1355 1356 def _scan_identifier(self, identifier_end: str) -> None: 1357 self._advance() 1358 text = self._extract_string(identifier_end, escapes=self._IDENTIFIER_ESCAPES) 1359 self._add(TokenType.IDENTIFIER, text) 1360 1361 def _scan_var(self) -> None: 1362 while True: 1363 char = self._peek.strip() 1364 if char and (char in self.VAR_SINGLE_TOKENS or char not in self.SINGLE_TOKENS): 1365 self._advance(alnum=True) 1366 else: 1367 break 1368 1369 self._add( 1370 TokenType.VAR 1371 if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER 1372 else self.KEYWORDS.get(self._text.upper(), TokenType.VAR) 1373 ) 1374 1375 def _extract_string( 1376 self, 1377 delimiter: str, 1378 escapes: t.Optional[t.Set[str]] = None, 1379 raw_string: bool = False, 1380 raise_unmatched: bool = True, 1381 ) -> str: 1382 text = "" 1383 delim_size = len(delimiter) 1384 escapes = self._STRING_ESCAPES if escapes is None else escapes 1385 1386 while True: 1387 if ( 1388 not raw_string 1389 and self.dialect.UNESCAPED_SEQUENCES 1390 and self._peek 1391 and self._char in self.STRING_ESCAPES 1392 ): 1393 unescaped_sequence = self.dialect.UNESCAPED_SEQUENCES.get(self._char + self._peek) 1394 if unescaped_sequence: 1395 self._advance(2) 1396 text += unescaped_sequence 1397 continue 1398 if ( 1399 (self.STRING_ESCAPES_ALLOWED_IN_RAW_STRINGS or not raw_string) 1400 and self._char in escapes 1401 and (self._peek == delimiter or self._peek in escapes) 1402 and (self._char not in self._QUOTES or self._char == self._peek) 1403 ): 1404 if self._peek == delimiter: 1405 text += self._peek 1406 else: 1407 text += self._char + self._peek 1408 1409 if self._current + 1 < self.size: 1410 self._advance(2) 1411 else: 1412 raise TokenError(f"Missing {delimiter} from {self._line}:{self._current}") 1413 else: 1414 if self._chars(delim_size) == delimiter: 1415 if delim_size > 1: 1416 self._advance(delim_size - 1) 1417 break 1418 1419 if self._end: 1420 if not raise_unmatched: 1421 return text + self._char 1422 1423 raise TokenError(f"Missing {delimiter} from {self._line}:{self._start}") 1424 1425 current = self._current - 1 1426 self._advance(alnum=True) 1427 text += self.sql[current : self._current - 1] 1428 1429 return text 1430 1431 def tokenize_rs(self, sql: str) -> t.List[Token]: 1432 if not self._RS_TOKENIZER: 1433 raise SqlglotError("Rust tokenizer is not available") 1434 1435 try: 1436 tokens = self._RS_TOKENIZER.tokenize(sql, self._rs_dialect_settings) 1437 for token in tokens: 1438 token.token_type = _ALL_TOKEN_TYPES[token.token_type_index] 1439 return tokens 1440 except Exception as e: 1441 raise TokenError(str(e))
29class TokenType(AutoName): 30 L_PAREN = auto() 31 R_PAREN = auto() 32 L_BRACKET = auto() 33 R_BRACKET = auto() 34 L_BRACE = auto() 35 R_BRACE = auto() 36 COMMA = auto() 37 DOT = auto() 38 DASH = auto() 39 PLUS = auto() 40 COLON = auto() 41 DCOLON = auto() 42 DQMARK = auto() 43 SEMICOLON = auto() 44 STAR = auto() 45 BACKSLASH = auto() 46 SLASH = auto() 47 LT = auto() 48 LTE = auto() 49 GT = auto() 50 GTE = auto() 51 NOT = auto() 52 EQ = auto() 53 NEQ = auto() 54 NULLSAFE_EQ = auto() 55 COLON_EQ = auto() 56 AND = auto() 57 OR = auto() 58 AMP = auto() 59 DPIPE = auto() 60 PIPE = auto() 61 PIPE_SLASH = auto() 62 DPIPE_SLASH = auto() 63 CARET = auto() 64 CARET_AT = auto() 65 TILDA = auto() 66 ARROW = auto() 67 DARROW = auto() 68 FARROW = auto() 69 HASH = auto() 70 HASH_ARROW = auto() 71 DHASH_ARROW = auto() 72 LR_ARROW = auto() 73 DAT = auto() 74 LT_AT = auto() 75 AT_GT = auto() 76 DOLLAR = auto() 77 PARAMETER = auto() 78 SESSION_PARAMETER = auto() 79 DAMP = auto() 80 XOR = auto() 81 DSTAR = auto() 82 83 BLOCK_START = auto() 84 BLOCK_END = auto() 85 86 SPACE = auto() 87 BREAK = auto() 88 89 STRING = auto() 90 NUMBER = auto() 91 IDENTIFIER = auto() 92 DATABASE = auto() 93 COLUMN = auto() 94 COLUMN_DEF = auto() 95 SCHEMA = auto() 96 TABLE = auto() 97 WAREHOUSE = auto() 98 STREAMLIT = auto() 99 VAR = auto() 100 BIT_STRING = auto() 101 HEX_STRING = auto() 102 BYTE_STRING = auto() 103 NATIONAL_STRING = auto() 104 RAW_STRING = auto() 105 HEREDOC_STRING = auto() 106 UNICODE_STRING = auto() 107 108 # types 109 BIT = auto() 110 BOOLEAN = auto() 111 TINYINT = auto() 112 UTINYINT = auto() 113 SMALLINT = auto() 114 USMALLINT = auto() 115 MEDIUMINT = auto() 116 UMEDIUMINT = auto() 117 INT = auto() 118 UINT = auto() 119 BIGINT = auto() 120 UBIGINT = auto() 121 INT128 = auto() 122 UINT128 = auto() 123 INT256 = auto() 124 UINT256 = auto() 125 FLOAT = auto() 126 DOUBLE = auto() 127 DECIMAL = auto() 128 DECIMAL32 = auto() 129 DECIMAL64 = auto() 130 DECIMAL128 = auto() 131 UDECIMAL = auto() 132 BIGDECIMAL = auto() 133 CHAR = auto() 134 NCHAR = auto() 135 VARCHAR = auto() 136 NVARCHAR = auto() 137 BPCHAR = auto() 138 TEXT = auto() 139 MEDIUMTEXT = auto() 140 LONGTEXT = auto() 141 MEDIUMBLOB = auto() 142 LONGBLOB = auto() 143 TINYBLOB = auto() 144 TINYTEXT = auto() 145 NAME = auto() 146 BINARY = auto() 147 VARBINARY = auto() 148 JSON = auto() 149 JSONB = auto() 150 TIME = auto() 151 TIMETZ = auto() 152 TIMESTAMP = auto() 153 TIMESTAMPTZ = auto() 154 TIMESTAMPLTZ = auto() 155 TIMESTAMPNTZ = auto() 156 TIMESTAMP_S = auto() 157 TIMESTAMP_MS = auto() 158 TIMESTAMP_NS = auto() 159 DATETIME = auto() 160 DATETIME64 = auto() 161 DATE = auto() 162 DATE32 = auto() 163 INT4RANGE = auto() 164 INT4MULTIRANGE = auto() 165 INT8RANGE = auto() 166 INT8MULTIRANGE = auto() 167 NUMRANGE = auto() 168 NUMMULTIRANGE = auto() 169 TSRANGE = auto() 170 TSMULTIRANGE = auto() 171 TSTZRANGE = auto() 172 TSTZMULTIRANGE = auto() 173 DATERANGE = auto() 174 DATEMULTIRANGE = auto() 175 UUID = auto() 176 GEOGRAPHY = auto() 177 NULLABLE = auto() 178 GEOMETRY = auto() 179 HLLSKETCH = auto() 180 HSTORE = auto() 181 SUPER = auto() 182 SERIAL = auto() 183 SMALLSERIAL = auto() 184 BIGSERIAL = auto() 185 XML = auto() 186 YEAR = auto() 187 UNIQUEIDENTIFIER = auto() 188 USERDEFINED = auto() 189 MONEY = auto() 190 SMALLMONEY = auto() 191 ROWVERSION = auto() 192 IMAGE = auto() 193 VARIANT = auto() 194 OBJECT = auto() 195 INET = auto() 196 IPADDRESS = auto() 197 IPPREFIX = auto() 198 IPV4 = auto() 199 IPV6 = auto() 200 ENUM = auto() 201 ENUM8 = auto() 202 ENUM16 = auto() 203 FIXEDSTRING = auto() 204 LOWCARDINALITY = auto() 205 NESTED = auto() 206 AGGREGATEFUNCTION = auto() 207 SIMPLEAGGREGATEFUNCTION = auto() 208 TDIGEST = auto() 209 UNKNOWN = auto() 210 VECTOR = auto() 211 212 # keywords 213 ALIAS = auto() 214 ALTER = auto() 215 ALWAYS = auto() 216 ALL = auto() 217 ANTI = auto() 218 ANY = auto() 219 APPLY = auto() 220 ARRAY = auto() 221 ASC = auto() 222 ASOF = auto() 223 AUTO_INCREMENT = auto() 224 BEGIN = auto() 225 BETWEEN = auto() 226 BULK_COLLECT_INTO = auto() 227 CACHE = auto() 228 CASE = auto() 229 CHARACTER_SET = auto() 230 CLUSTER_BY = auto() 231 COLLATE = auto() 232 COMMAND = auto() 233 COMMENT = auto() 234 COMMIT = auto() 235 CONNECT_BY = auto() 236 CONSTRAINT = auto() 237 COPY = auto() 238 CREATE = auto() 239 CROSS = auto() 240 CUBE = auto() 241 CURRENT_DATE = auto() 242 CURRENT_DATETIME = auto() 243 CURRENT_TIME = auto() 244 CURRENT_TIMESTAMP = auto() 245 CURRENT_USER = auto() 246 DECLARE = auto() 247 DEFAULT = auto() 248 DELETE = auto() 249 DESC = auto() 250 DESCRIBE = auto() 251 DICTIONARY = auto() 252 DISTINCT = auto() 253 DISTRIBUTE_BY = auto() 254 DIV = auto() 255 DROP = auto() 256 ELSE = auto() 257 END = auto() 258 ESCAPE = auto() 259 EXCEPT = auto() 260 EXECUTE = auto() 261 EXISTS = auto() 262 FALSE = auto() 263 FETCH = auto() 264 FILTER = auto() 265 FINAL = auto() 266 FIRST = auto() 267 FOR = auto() 268 FORCE = auto() 269 FOREIGN_KEY = auto() 270 FORMAT = auto() 271 FROM = auto() 272 FULL = auto() 273 FUNCTION = auto() 274 GLOB = auto() 275 GLOBAL = auto() 276 GRANT = auto() 277 GROUP_BY = auto() 278 GROUPING_SETS = auto() 279 HAVING = auto() 280 HINT = auto() 281 IGNORE = auto() 282 ILIKE = auto() 283 ILIKE_ANY = auto() 284 IN = auto() 285 INDEX = auto() 286 INNER = auto() 287 INSERT = auto() 288 INTERSECT = auto() 289 INTERVAL = auto() 290 INTO = auto() 291 INTRODUCER = auto() 292 IRLIKE = auto() 293 IS = auto() 294 ISNULL = auto() 295 JOIN = auto() 296 JOIN_MARKER = auto() 297 KEEP = auto() 298 KEY = auto() 299 KILL = auto() 300 LANGUAGE = auto() 301 LATERAL = auto() 302 LEFT = auto() 303 LIKE = auto() 304 LIKE_ANY = auto() 305 LIMIT = auto() 306 LIST = auto() 307 LOAD = auto() 308 LOCK = auto() 309 MAP = auto() 310 MATCH_CONDITION = auto() 311 MATCH_RECOGNIZE = auto() 312 MEMBER_OF = auto() 313 MERGE = auto() 314 MOD = auto() 315 MODEL = auto() 316 NATURAL = auto() 317 NEXT = auto() 318 NOTNULL = auto() 319 NULL = auto() 320 OBJECT_IDENTIFIER = auto() 321 OFFSET = auto() 322 ON = auto() 323 ONLY = auto() 324 OPERATOR = auto() 325 ORDER_BY = auto() 326 ORDER_SIBLINGS_BY = auto() 327 ORDERED = auto() 328 ORDINALITY = auto() 329 OUTER = auto() 330 OVER = auto() 331 OVERLAPS = auto() 332 OVERWRITE = auto() 333 PARTITION = auto() 334 PARTITION_BY = auto() 335 PERCENT = auto() 336 PIVOT = auto() 337 PLACEHOLDER = auto() 338 POSITIONAL = auto() 339 PRAGMA = auto() 340 PREWHERE = auto() 341 PRIMARY_KEY = auto() 342 PROCEDURE = auto() 343 PROPERTIES = auto() 344 PSEUDO_TYPE = auto() 345 QUALIFY = auto() 346 QUOTE = auto() 347 RANGE = auto() 348 RECURSIVE = auto() 349 REFRESH = auto() 350 RENAME = auto() 351 REPLACE = auto() 352 RETURNING = auto() 353 REFERENCES = auto() 354 RIGHT = auto() 355 RLIKE = auto() 356 ROLLBACK = auto() 357 ROLLUP = auto() 358 ROW = auto() 359 ROWS = auto() 360 SELECT = auto() 361 SEMI = auto() 362 SEPARATOR = auto() 363 SEQUENCE = auto() 364 SERDE_PROPERTIES = auto() 365 SET = auto() 366 SETTINGS = auto() 367 SHOW = auto() 368 SIMILAR_TO = auto() 369 SOME = auto() 370 SORT_BY = auto() 371 START_WITH = auto() 372 STORAGE_INTEGRATION = auto() 373 STRAIGHT_JOIN = auto() 374 STRUCT = auto() 375 SUMMARIZE = auto() 376 TABLE_SAMPLE = auto() 377 TAG = auto() 378 TEMPORARY = auto() 379 TOP = auto() 380 THEN = auto() 381 TRUE = auto() 382 TRUNCATE = auto() 383 UNCACHE = auto() 384 UNION = auto() 385 UNNEST = auto() 386 UNPIVOT = auto() 387 UPDATE = auto() 388 USE = auto() 389 USING = auto() 390 VALUES = auto() 391 VIEW = auto() 392 VOLATILE = auto() 393 WHEN = auto() 394 WHERE = auto() 395 WINDOW = auto() 396 WITH = auto() 397 UNIQUE = auto() 398 VERSION_SNAPSHOT = auto() 399 TIMESTAMP_SNAPSHOT = auto() 400 OPTION = 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'>
PIPE_SLASH =
<TokenType.PIPE_SLASH: 'PIPE_SLASH'>
DPIPE_SLASH =
<TokenType.DPIPE_SLASH: 'DPIPE_SLASH'>
CARET =
<TokenType.CARET: 'CARET'>
CARET_AT =
<TokenType.CARET_AT: 'CARET_AT'>
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'>
WAREHOUSE =
<TokenType.WAREHOUSE: 'WAREHOUSE'>
STREAMLIT =
<TokenType.STREAMLIT: 'STREAMLIT'>
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'>
UNICODE_STRING =
<TokenType.UNICODE_STRING: 'UNICODE_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'>
DECIMAL32 =
<TokenType.DECIMAL32: 'DECIMAL32'>
DECIMAL64 =
<TokenType.DECIMAL64: 'DECIMAL64'>
DECIMAL128 =
<TokenType.DECIMAL128: 'DECIMAL128'>
UDECIMAL =
<TokenType.UDECIMAL: 'UDECIMAL'>
BIGDECIMAL =
<TokenType.BIGDECIMAL: 'BIGDECIMAL'>
CHAR =
<TokenType.CHAR: 'CHAR'>
NCHAR =
<TokenType.NCHAR: 'NCHAR'>
VARCHAR =
<TokenType.VARCHAR: 'VARCHAR'>
NVARCHAR =
<TokenType.NVARCHAR: 'NVARCHAR'>
BPCHAR =
<TokenType.BPCHAR: 'BPCHAR'>
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'>
NAME =
<TokenType.NAME: 'NAME'>
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'>
TIMESTAMPNTZ =
<TokenType.TIMESTAMPNTZ: 'TIMESTAMPNTZ'>
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'>
DATE32 =
<TokenType.DATE32: 'DATE32'>
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'>
IPV4 =
<TokenType.IPV4: 'IPV4'>
IPV6 =
<TokenType.IPV6: 'IPV6'>
ENUM =
<TokenType.ENUM: 'ENUM'>
ENUM8 =
<TokenType.ENUM8: 'ENUM8'>
ENUM16 =
<TokenType.ENUM16: 'ENUM16'>
FIXEDSTRING =
<TokenType.FIXEDSTRING: 'FIXEDSTRING'>
LOWCARDINALITY =
<TokenType.LOWCARDINALITY: 'LOWCARDINALITY'>
NESTED =
<TokenType.NESTED: 'NESTED'>
AGGREGATEFUNCTION =
<TokenType.AGGREGATEFUNCTION: 'AGGREGATEFUNCTION'>
SIMPLEAGGREGATEFUNCTION =
<TokenType.SIMPLEAGGREGATEFUNCTION: 'SIMPLEAGGREGATEFUNCTION'>
TDIGEST =
<TokenType.TDIGEST: 'TDIGEST'>
UNKNOWN =
<TokenType.UNKNOWN: 'UNKNOWN'>
VECTOR =
<TokenType.VECTOR: 'VECTOR'>
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'>
BULK_COLLECT_INTO =
<TokenType.BULK_COLLECT_INTO: 'BULK_COLLECT_INTO'>
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'>
COPY =
<TokenType.COPY: 'COPY'>
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'>
DECLARE =
<TokenType.DECLARE: 'DECLARE'>
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'>
GRANT =
<TokenType.GRANT: 'GRANT'>
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'>
KEY =
<TokenType.KEY: 'KEY'>
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'>
LIST =
<TokenType.LIST: 'LIST'>
LOAD =
<TokenType.LOAD: 'LOAD'>
LOCK =
<TokenType.LOCK: 'LOCK'>
MAP =
<TokenType.MAP: 'MAP'>
MATCH_CONDITION =
<TokenType.MATCH_CONDITION: 'MATCH_CONDITION'>
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'>
ONLY =
<TokenType.ONLY: 'ONLY'>
OPERATOR =
<TokenType.OPERATOR: 'OPERATOR'>
ORDER_BY =
<TokenType.ORDER_BY: 'ORDER_BY'>
ORDER_SIBLINGS_BY =
<TokenType.ORDER_SIBLINGS_BY: 'ORDER_SIBLINGS_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'>
POSITIONAL =
<TokenType.POSITIONAL: 'POSITIONAL'>
PRAGMA =
<TokenType.PRAGMA: 'PRAGMA'>
PREWHERE =
<TokenType.PREWHERE: 'PREWHERE'>
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'>
RENAME =
<TokenType.RENAME: 'RENAME'>
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'>
SEQUENCE =
<TokenType.SEQUENCE: 'SEQUENCE'>
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'>
STORAGE_INTEGRATION =
<TokenType.STORAGE_INTEGRATION: 'STORAGE_INTEGRATION'>
STRAIGHT_JOIN =
<TokenType.STRAIGHT_JOIN: 'STRAIGHT_JOIN'>
STRUCT =
<TokenType.STRUCT: 'STRUCT'>
SUMMARIZE =
<TokenType.SUMMARIZE: 'SUMMARIZE'>
TABLE_SAMPLE =
<TokenType.TABLE_SAMPLE: 'TABLE_SAMPLE'>
TAG =
<TokenType.TAG: 'TAG'>
TEMPORARY =
<TokenType.TEMPORARY: 'TEMPORARY'>
TOP =
<TokenType.TOP: 'TOP'>
THEN =
<TokenType.THEN: 'THEN'>
TRUE =
<TokenType.TRUE: 'TRUE'>
TRUNCATE =
<TokenType.TRUNCATE: 'TRUNCATE'>
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'>
OPTION =
<TokenType.OPTION: 'OPTION'>
Inherited Members
- enum.Enum
- name
- value
class
Token:
407class Token: 408 __slots__ = ("token_type", "text", "line", "col", "start", "end", "comments") 409 410 @classmethod 411 def number(cls, number: int) -> Token: 412 """Returns a NUMBER token with `number` as its text.""" 413 return cls(TokenType.NUMBER, str(number)) 414 415 @classmethod 416 def string(cls, string: str) -> Token: 417 """Returns a STRING token with `string` as its text.""" 418 return cls(TokenType.STRING, string) 419 420 @classmethod 421 def identifier(cls, identifier: str) -> Token: 422 """Returns an IDENTIFIER token with `identifier` as its text.""" 423 return cls(TokenType.IDENTIFIER, identifier) 424 425 @classmethod 426 def var(cls, var: str) -> Token: 427 """Returns an VAR token with `var` as its text.""" 428 return cls(TokenType.VAR, var) 429 430 def __init__( 431 self, 432 token_type: TokenType, 433 text: str, 434 line: int = 1, 435 col: int = 1, 436 start: int = 0, 437 end: int = 0, 438 comments: t.Optional[t.List[str]] = None, 439 ) -> None: 440 """Token initializer. 441 442 Args: 443 token_type: The TokenType Enum. 444 text: The text of the token. 445 line: The line that the token ends on. 446 col: The column that the token ends on. 447 start: The start index of the token. 448 end: The ending index of the token. 449 comments: The comments to attach to the token. 450 """ 451 self.token_type = token_type 452 self.text = text 453 self.line = line 454 self.col = col 455 self.start = start 456 self.end = end 457 self.comments = [] if comments is None else comments 458 459 def __repr__(self) -> str: 460 attributes = ", ".join(f"{k}: {getattr(self, k)}" for k in self.__slots__) 461 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)
430 def __init__( 431 self, 432 token_type: TokenType, 433 text: str, 434 line: int = 1, 435 col: int = 1, 436 start: int = 0, 437 end: int = 0, 438 comments: t.Optional[t.List[str]] = None, 439 ) -> None: 440 """Token initializer. 441 442 Args: 443 token_type: The TokenType Enum. 444 text: The text of the token. 445 line: The line that the token ends on. 446 col: The column that the token ends on. 447 start: The start index of the token. 448 end: The ending index of the token. 449 comments: The comments to attach to the token. 450 """ 451 self.token_type = token_type 452 self.text = text 453 self.line = line 454 self.col = col 455 self.start = start 456 self.end = end 457 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.
410 @classmethod 411 def number(cls, number: int) -> Token: 412 """Returns a NUMBER token with `number` as its text.""" 413 return cls(TokenType.NUMBER, str(number))
Returns a NUMBER token with number
as its text.
415 @classmethod 416 def string(cls, string: str) -> Token: 417 """Returns a STRING token with `string` as its text.""" 418 return cls(TokenType.STRING, string)
Returns a STRING token with string
as its text.
420 @classmethod 421 def identifier(cls, identifier: str) -> Token: 422 """Returns an IDENTIFIER token with `identifier` as its text.""" 423 return cls(TokenType.IDENTIFIER, identifier)
Returns an IDENTIFIER token with identifier
as its text.
class
Tokenizer:
564class Tokenizer(metaclass=_Tokenizer): 565 SINGLE_TOKENS = { 566 "(": TokenType.L_PAREN, 567 ")": TokenType.R_PAREN, 568 "[": TokenType.L_BRACKET, 569 "]": TokenType.R_BRACKET, 570 "{": TokenType.L_BRACE, 571 "}": TokenType.R_BRACE, 572 "&": TokenType.AMP, 573 "^": TokenType.CARET, 574 ":": TokenType.COLON, 575 ",": TokenType.COMMA, 576 ".": TokenType.DOT, 577 "-": TokenType.DASH, 578 "=": TokenType.EQ, 579 ">": TokenType.GT, 580 "<": TokenType.LT, 581 "%": TokenType.MOD, 582 "!": TokenType.NOT, 583 "|": TokenType.PIPE, 584 "+": TokenType.PLUS, 585 ";": TokenType.SEMICOLON, 586 "/": TokenType.SLASH, 587 "\\": TokenType.BACKSLASH, 588 "*": TokenType.STAR, 589 "~": TokenType.TILDA, 590 "?": TokenType.PLACEHOLDER, 591 "@": TokenType.PARAMETER, 592 "#": TokenType.HASH, 593 # Used for breaking a var like x'y' but nothing else the token type doesn't matter 594 "'": TokenType.UNKNOWN, 595 "`": TokenType.UNKNOWN, 596 '"': TokenType.UNKNOWN, 597 } 598 599 BIT_STRINGS: t.List[str | t.Tuple[str, str]] = [] 600 BYTE_STRINGS: t.List[str | t.Tuple[str, str]] = [] 601 HEX_STRINGS: t.List[str | t.Tuple[str, str]] = [] 602 RAW_STRINGS: t.List[str | t.Tuple[str, str]] = [] 603 HEREDOC_STRINGS: t.List[str | t.Tuple[str, str]] = [] 604 UNICODE_STRINGS: t.List[str | t.Tuple[str, str]] = [] 605 IDENTIFIERS: t.List[str | t.Tuple[str, str]] = ['"'] 606 IDENTIFIER_ESCAPES = ['"'] 607 QUOTES: t.List[t.Tuple[str, str] | str] = ["'"] 608 STRING_ESCAPES = ["'"] 609 VAR_SINGLE_TOKENS: t.Set[str] = set() 610 611 # Whether the heredoc tags follow the same lexical rules as unquoted identifiers 612 HEREDOC_TAG_IS_IDENTIFIER = False 613 614 # Token that we'll generate as a fallback if the heredoc prefix doesn't correspond to a heredoc 615 HEREDOC_STRING_ALTERNATIVE = TokenType.VAR 616 617 # Whether string escape characters function as such when placed within raw strings 618 STRING_ESCAPES_ALLOWED_IN_RAW_STRINGS = True 619 620 NESTED_COMMENTS = True 621 622 # Autofilled 623 _COMMENTS: t.Dict[str, str] = {} 624 _FORMAT_STRINGS: t.Dict[str, t.Tuple[str, TokenType]] = {} 625 _IDENTIFIERS: t.Dict[str, str] = {} 626 _IDENTIFIER_ESCAPES: t.Set[str] = set() 627 _QUOTES: t.Dict[str, str] = {} 628 _STRING_ESCAPES: t.Set[str] = set() 629 _KEYWORD_TRIE: t.Dict = {} 630 _RS_TOKENIZER: t.Optional[t.Any] = None 631 632 KEYWORDS: t.Dict[str, TokenType] = { 633 **{f"{{%{postfix}": TokenType.BLOCK_START for postfix in ("", "+", "-")}, 634 **{f"{prefix}%}}": TokenType.BLOCK_END for prefix in ("", "+", "-")}, 635 **{f"{{{{{postfix}": TokenType.BLOCK_START for postfix in ("+", "-")}, 636 **{f"{prefix}}}}}": TokenType.BLOCK_END for prefix in ("+", "-")}, 637 "/*+": TokenType.HINT, 638 "==": TokenType.EQ, 639 "::": TokenType.DCOLON, 640 "||": TokenType.DPIPE, 641 ">=": TokenType.GTE, 642 "<=": TokenType.LTE, 643 "<>": TokenType.NEQ, 644 "!=": TokenType.NEQ, 645 ":=": TokenType.COLON_EQ, 646 "<=>": TokenType.NULLSAFE_EQ, 647 "->": TokenType.ARROW, 648 "->>": TokenType.DARROW, 649 "=>": TokenType.FARROW, 650 "#>": TokenType.HASH_ARROW, 651 "#>>": TokenType.DHASH_ARROW, 652 "<->": TokenType.LR_ARROW, 653 "&&": TokenType.DAMP, 654 "??": TokenType.DQMARK, 655 "~~~": TokenType.GLOB, 656 "~~": TokenType.LIKE, 657 "~~*": TokenType.ILIKE, 658 "~*": TokenType.IRLIKE, 659 "ALL": TokenType.ALL, 660 "ALWAYS": TokenType.ALWAYS, 661 "AND": TokenType.AND, 662 "ANTI": TokenType.ANTI, 663 "ANY": TokenType.ANY, 664 "ASC": TokenType.ASC, 665 "AS": TokenType.ALIAS, 666 "ASOF": TokenType.ASOF, 667 "AUTOINCREMENT": TokenType.AUTO_INCREMENT, 668 "AUTO_INCREMENT": TokenType.AUTO_INCREMENT, 669 "BEGIN": TokenType.BEGIN, 670 "BETWEEN": TokenType.BETWEEN, 671 "CACHE": TokenType.CACHE, 672 "UNCACHE": TokenType.UNCACHE, 673 "CASE": TokenType.CASE, 674 "CHARACTER SET": TokenType.CHARACTER_SET, 675 "CLUSTER BY": TokenType.CLUSTER_BY, 676 "COLLATE": TokenType.COLLATE, 677 "COLUMN": TokenType.COLUMN, 678 "COMMIT": TokenType.COMMIT, 679 "CONNECT BY": TokenType.CONNECT_BY, 680 "CONSTRAINT": TokenType.CONSTRAINT, 681 "COPY": TokenType.COPY, 682 "CREATE": TokenType.CREATE, 683 "CROSS": TokenType.CROSS, 684 "CUBE": TokenType.CUBE, 685 "CURRENT_DATE": TokenType.CURRENT_DATE, 686 "CURRENT_TIME": TokenType.CURRENT_TIME, 687 "CURRENT_TIMESTAMP": TokenType.CURRENT_TIMESTAMP, 688 "CURRENT_USER": TokenType.CURRENT_USER, 689 "DATABASE": TokenType.DATABASE, 690 "DEFAULT": TokenType.DEFAULT, 691 "DELETE": TokenType.DELETE, 692 "DESC": TokenType.DESC, 693 "DESCRIBE": TokenType.DESCRIBE, 694 "DISTINCT": TokenType.DISTINCT, 695 "DISTRIBUTE BY": TokenType.DISTRIBUTE_BY, 696 "DIV": TokenType.DIV, 697 "DROP": TokenType.DROP, 698 "ELSE": TokenType.ELSE, 699 "END": TokenType.END, 700 "ENUM": TokenType.ENUM, 701 "ESCAPE": TokenType.ESCAPE, 702 "EXCEPT": TokenType.EXCEPT, 703 "EXECUTE": TokenType.EXECUTE, 704 "EXISTS": TokenType.EXISTS, 705 "FALSE": TokenType.FALSE, 706 "FETCH": TokenType.FETCH, 707 "FILTER": TokenType.FILTER, 708 "FIRST": TokenType.FIRST, 709 "FULL": TokenType.FULL, 710 "FUNCTION": TokenType.FUNCTION, 711 "FOR": TokenType.FOR, 712 "FOREIGN KEY": TokenType.FOREIGN_KEY, 713 "FORMAT": TokenType.FORMAT, 714 "FROM": TokenType.FROM, 715 "GEOGRAPHY": TokenType.GEOGRAPHY, 716 "GEOMETRY": TokenType.GEOMETRY, 717 "GLOB": TokenType.GLOB, 718 "GROUP BY": TokenType.GROUP_BY, 719 "GROUPING SETS": TokenType.GROUPING_SETS, 720 "HAVING": TokenType.HAVING, 721 "ILIKE": TokenType.ILIKE, 722 "IN": TokenType.IN, 723 "INDEX": TokenType.INDEX, 724 "INET": TokenType.INET, 725 "INNER": TokenType.INNER, 726 "INSERT": TokenType.INSERT, 727 "INTERVAL": TokenType.INTERVAL, 728 "INTERSECT": TokenType.INTERSECT, 729 "INTO": TokenType.INTO, 730 "IS": TokenType.IS, 731 "ISNULL": TokenType.ISNULL, 732 "JOIN": TokenType.JOIN, 733 "KEEP": TokenType.KEEP, 734 "KILL": TokenType.KILL, 735 "LATERAL": TokenType.LATERAL, 736 "LEFT": TokenType.LEFT, 737 "LIKE": TokenType.LIKE, 738 "LIMIT": TokenType.LIMIT, 739 "LOAD": TokenType.LOAD, 740 "LOCK": TokenType.LOCK, 741 "MERGE": TokenType.MERGE, 742 "NATURAL": TokenType.NATURAL, 743 "NEXT": TokenType.NEXT, 744 "NOT": TokenType.NOT, 745 "NOTNULL": TokenType.NOTNULL, 746 "NULL": TokenType.NULL, 747 "OBJECT": TokenType.OBJECT, 748 "OFFSET": TokenType.OFFSET, 749 "ON": TokenType.ON, 750 "OR": TokenType.OR, 751 "XOR": TokenType.XOR, 752 "ORDER BY": TokenType.ORDER_BY, 753 "ORDINALITY": TokenType.ORDINALITY, 754 "OUTER": TokenType.OUTER, 755 "OVER": TokenType.OVER, 756 "OVERLAPS": TokenType.OVERLAPS, 757 "OVERWRITE": TokenType.OVERWRITE, 758 "PARTITION": TokenType.PARTITION, 759 "PARTITION BY": TokenType.PARTITION_BY, 760 "PARTITIONED BY": TokenType.PARTITION_BY, 761 "PARTITIONED_BY": TokenType.PARTITION_BY, 762 "PERCENT": TokenType.PERCENT, 763 "PIVOT": TokenType.PIVOT, 764 "PRAGMA": TokenType.PRAGMA, 765 "PRIMARY KEY": TokenType.PRIMARY_KEY, 766 "PROCEDURE": TokenType.PROCEDURE, 767 "QUALIFY": TokenType.QUALIFY, 768 "RANGE": TokenType.RANGE, 769 "RECURSIVE": TokenType.RECURSIVE, 770 "REGEXP": TokenType.RLIKE, 771 "RENAME": TokenType.RENAME, 772 "REPLACE": TokenType.REPLACE, 773 "RETURNING": TokenType.RETURNING, 774 "REFERENCES": TokenType.REFERENCES, 775 "RIGHT": TokenType.RIGHT, 776 "RLIKE": TokenType.RLIKE, 777 "ROLLBACK": TokenType.ROLLBACK, 778 "ROLLUP": TokenType.ROLLUP, 779 "ROW": TokenType.ROW, 780 "ROWS": TokenType.ROWS, 781 "SCHEMA": TokenType.SCHEMA, 782 "SELECT": TokenType.SELECT, 783 "SEMI": TokenType.SEMI, 784 "SET": TokenType.SET, 785 "SETTINGS": TokenType.SETTINGS, 786 "SHOW": TokenType.SHOW, 787 "SIMILAR TO": TokenType.SIMILAR_TO, 788 "SOME": TokenType.SOME, 789 "SORT BY": TokenType.SORT_BY, 790 "START WITH": TokenType.START_WITH, 791 "STRAIGHT_JOIN": TokenType.STRAIGHT_JOIN, 792 "TABLE": TokenType.TABLE, 793 "TABLESAMPLE": TokenType.TABLE_SAMPLE, 794 "TEMP": TokenType.TEMPORARY, 795 "TEMPORARY": TokenType.TEMPORARY, 796 "THEN": TokenType.THEN, 797 "TRUE": TokenType.TRUE, 798 "TRUNCATE": TokenType.TRUNCATE, 799 "UNION": TokenType.UNION, 800 "UNKNOWN": TokenType.UNKNOWN, 801 "UNNEST": TokenType.UNNEST, 802 "UNPIVOT": TokenType.UNPIVOT, 803 "UPDATE": TokenType.UPDATE, 804 "USE": TokenType.USE, 805 "USING": TokenType.USING, 806 "UUID": TokenType.UUID, 807 "VALUES": TokenType.VALUES, 808 "VIEW": TokenType.VIEW, 809 "VOLATILE": TokenType.VOLATILE, 810 "WHEN": TokenType.WHEN, 811 "WHERE": TokenType.WHERE, 812 "WINDOW": TokenType.WINDOW, 813 "WITH": TokenType.WITH, 814 "APPLY": TokenType.APPLY, 815 "ARRAY": TokenType.ARRAY, 816 "BIT": TokenType.BIT, 817 "BOOL": TokenType.BOOLEAN, 818 "BOOLEAN": TokenType.BOOLEAN, 819 "BYTE": TokenType.TINYINT, 820 "MEDIUMINT": TokenType.MEDIUMINT, 821 "INT1": TokenType.TINYINT, 822 "TINYINT": TokenType.TINYINT, 823 "INT16": TokenType.SMALLINT, 824 "SHORT": TokenType.SMALLINT, 825 "SMALLINT": TokenType.SMALLINT, 826 "INT128": TokenType.INT128, 827 "HUGEINT": TokenType.INT128, 828 "UHUGEINT": TokenType.UINT128, 829 "INT2": TokenType.SMALLINT, 830 "INTEGER": TokenType.INT, 831 "INT": TokenType.INT, 832 "INT4": TokenType.INT, 833 "INT32": TokenType.INT, 834 "INT64": TokenType.BIGINT, 835 "LONG": TokenType.BIGINT, 836 "BIGINT": TokenType.BIGINT, 837 "INT8": TokenType.TINYINT, 838 "UINT": TokenType.UINT, 839 "DEC": TokenType.DECIMAL, 840 "DECIMAL": TokenType.DECIMAL, 841 "DECIMAL32": TokenType.DECIMAL32, 842 "DECIMAL64": TokenType.DECIMAL64, 843 "DECIMAL128": TokenType.DECIMAL128, 844 "BIGDECIMAL": TokenType.BIGDECIMAL, 845 "BIGNUMERIC": TokenType.BIGDECIMAL, 846 "LIST": TokenType.LIST, 847 "MAP": TokenType.MAP, 848 "NULLABLE": TokenType.NULLABLE, 849 "NUMBER": TokenType.DECIMAL, 850 "NUMERIC": TokenType.DECIMAL, 851 "FIXED": TokenType.DECIMAL, 852 "REAL": TokenType.FLOAT, 853 "FLOAT": TokenType.FLOAT, 854 "FLOAT4": TokenType.FLOAT, 855 "FLOAT8": TokenType.DOUBLE, 856 "DOUBLE": TokenType.DOUBLE, 857 "DOUBLE PRECISION": TokenType.DOUBLE, 858 "JSON": TokenType.JSON, 859 "JSONB": TokenType.JSONB, 860 "CHAR": TokenType.CHAR, 861 "CHARACTER": TokenType.CHAR, 862 "NCHAR": TokenType.NCHAR, 863 "VARCHAR": TokenType.VARCHAR, 864 "VARCHAR2": TokenType.VARCHAR, 865 "NVARCHAR": TokenType.NVARCHAR, 866 "NVARCHAR2": TokenType.NVARCHAR, 867 "BPCHAR": TokenType.BPCHAR, 868 "STR": TokenType.TEXT, 869 "STRING": TokenType.TEXT, 870 "TEXT": TokenType.TEXT, 871 "LONGTEXT": TokenType.LONGTEXT, 872 "MEDIUMTEXT": TokenType.MEDIUMTEXT, 873 "TINYTEXT": TokenType.TINYTEXT, 874 "CLOB": TokenType.TEXT, 875 "LONGVARCHAR": TokenType.TEXT, 876 "BINARY": TokenType.BINARY, 877 "BLOB": TokenType.VARBINARY, 878 "LONGBLOB": TokenType.LONGBLOB, 879 "MEDIUMBLOB": TokenType.MEDIUMBLOB, 880 "TINYBLOB": TokenType.TINYBLOB, 881 "BYTEA": TokenType.VARBINARY, 882 "VARBINARY": TokenType.VARBINARY, 883 "TIME": TokenType.TIME, 884 "TIMETZ": TokenType.TIMETZ, 885 "TIMESTAMP": TokenType.TIMESTAMP, 886 "TIMESTAMPTZ": TokenType.TIMESTAMPTZ, 887 "TIMESTAMPLTZ": TokenType.TIMESTAMPLTZ, 888 "TIMESTAMP_LTZ": TokenType.TIMESTAMPLTZ, 889 "TIMESTAMPNTZ": TokenType.TIMESTAMPNTZ, 890 "TIMESTAMP_NTZ": TokenType.TIMESTAMPNTZ, 891 "DATE": TokenType.DATE, 892 "DATETIME": TokenType.DATETIME, 893 "INT4RANGE": TokenType.INT4RANGE, 894 "INT4MULTIRANGE": TokenType.INT4MULTIRANGE, 895 "INT8RANGE": TokenType.INT8RANGE, 896 "INT8MULTIRANGE": TokenType.INT8MULTIRANGE, 897 "NUMRANGE": TokenType.NUMRANGE, 898 "NUMMULTIRANGE": TokenType.NUMMULTIRANGE, 899 "TSRANGE": TokenType.TSRANGE, 900 "TSMULTIRANGE": TokenType.TSMULTIRANGE, 901 "TSTZRANGE": TokenType.TSTZRANGE, 902 "TSTZMULTIRANGE": TokenType.TSTZMULTIRANGE, 903 "DATERANGE": TokenType.DATERANGE, 904 "DATEMULTIRANGE": TokenType.DATEMULTIRANGE, 905 "UNIQUE": TokenType.UNIQUE, 906 "VECTOR": TokenType.VECTOR, 907 "STRUCT": TokenType.STRUCT, 908 "SEQUENCE": TokenType.SEQUENCE, 909 "VARIANT": TokenType.VARIANT, 910 "ALTER": TokenType.ALTER, 911 "ANALYZE": TokenType.COMMAND, 912 "CALL": TokenType.COMMAND, 913 "COMMENT": TokenType.COMMENT, 914 "EXPLAIN": TokenType.COMMAND, 915 "GRANT": TokenType.GRANT, 916 "OPTIMIZE": TokenType.COMMAND, 917 "PREPARE": TokenType.COMMAND, 918 "VACUUM": TokenType.COMMAND, 919 "USER-DEFINED": TokenType.USERDEFINED, 920 "FOR VERSION": TokenType.VERSION_SNAPSHOT, 921 "FOR TIMESTAMP": TokenType.TIMESTAMP_SNAPSHOT, 922 } 923 924 WHITE_SPACE: t.Dict[t.Optional[str], TokenType] = { 925 " ": TokenType.SPACE, 926 "\t": TokenType.SPACE, 927 "\n": TokenType.BREAK, 928 "\r": TokenType.BREAK, 929 } 930 931 COMMANDS = { 932 TokenType.COMMAND, 933 TokenType.EXECUTE, 934 TokenType.FETCH, 935 TokenType.SHOW, 936 TokenType.RENAME, 937 } 938 939 COMMAND_PREFIX_TOKENS = {TokenType.SEMICOLON, TokenType.BEGIN} 940 941 # Handle numeric literals like in hive (3L = BIGINT) 942 NUMERIC_LITERALS: t.Dict[str, str] = {} 943 944 COMMENTS = ["--", ("/*", "*/")] 945 946 __slots__ = ( 947 "sql", 948 "size", 949 "tokens", 950 "dialect", 951 "_start", 952 "_current", 953 "_line", 954 "_col", 955 "_comments", 956 "_char", 957 "_end", 958 "_peek", 959 "_prev_token_line", 960 "_rs_dialect_settings", 961 ) 962 963 def __init__(self, dialect: DialectType = None) -> None: 964 from sqlglot.dialects import Dialect 965 966 self.dialect = Dialect.get_or_raise(dialect) 967 968 if USE_RS_TOKENIZER: 969 self._rs_dialect_settings = RsTokenizerDialectSettings( 970 unescaped_sequences=self.dialect.UNESCAPED_SEQUENCES, 971 identifiers_can_start_with_digit=self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT, 972 ) 973 974 self.reset() 975 976 def reset(self) -> None: 977 self.sql = "" 978 self.size = 0 979 self.tokens: t.List[Token] = [] 980 self._start = 0 981 self._current = 0 982 self._line = 1 983 self._col = 0 984 self._comments: t.List[str] = [] 985 986 self._char = "" 987 self._end = False 988 self._peek = "" 989 self._prev_token_line = -1 990 991 def tokenize(self, sql: str) -> t.List[Token]: 992 """Returns a list of tokens corresponding to the SQL string `sql`.""" 993 if USE_RS_TOKENIZER: 994 return self.tokenize_rs(sql) 995 996 self.reset() 997 self.sql = sql 998 self.size = len(sql) 999 1000 try: 1001 self._scan() 1002 except Exception as e: 1003 start = max(self._current - 50, 0) 1004 end = min(self._current + 50, self.size - 1) 1005 context = self.sql[start:end] 1006 raise TokenError(f"Error tokenizing '{context}'") from e 1007 1008 return self.tokens 1009 1010 def _scan(self, until: t.Optional[t.Callable] = None) -> None: 1011 while self.size and not self._end: 1012 current = self._current 1013 1014 # Skip spaces here rather than iteratively calling advance() for performance reasons 1015 while current < self.size: 1016 char = self.sql[current] 1017 1018 if char.isspace() and (char == " " or char == "\t"): 1019 current += 1 1020 else: 1021 break 1022 1023 offset = current - self._current if current > self._current else 1 1024 1025 self._start = current 1026 self._advance(offset) 1027 1028 if not self._char.isspace(): 1029 if self._char.isdigit(): 1030 self._scan_number() 1031 elif self._char in self._IDENTIFIERS: 1032 self._scan_identifier(self._IDENTIFIERS[self._char]) 1033 else: 1034 self._scan_keywords() 1035 1036 if until and until(): 1037 break 1038 1039 if self.tokens and self._comments: 1040 self.tokens[-1].comments.extend(self._comments) 1041 1042 def _chars(self, size: int) -> str: 1043 if size == 1: 1044 return self._char 1045 1046 start = self._current - 1 1047 end = start + size 1048 1049 return self.sql[start:end] if end <= self.size else "" 1050 1051 def _advance(self, i: int = 1, alnum: bool = False) -> None: 1052 if self.WHITE_SPACE.get(self._char) is TokenType.BREAK: 1053 # Ensures we don't count an extra line if we get a \r\n line break sequence 1054 if not (self._char == "\r" and self._peek == "\n"): 1055 self._col = 1 1056 self._line += 1 1057 else: 1058 self._col += i 1059 1060 self._current += i 1061 self._end = self._current >= self.size 1062 self._char = self.sql[self._current - 1] 1063 self._peek = "" if self._end else self.sql[self._current] 1064 1065 if alnum and self._char.isalnum(): 1066 # Here we use local variables instead of attributes for better performance 1067 _col = self._col 1068 _current = self._current 1069 _end = self._end 1070 _peek = self._peek 1071 1072 while _peek.isalnum(): 1073 _col += 1 1074 _current += 1 1075 _end = _current >= self.size 1076 _peek = "" if _end else self.sql[_current] 1077 1078 self._col = _col 1079 self._current = _current 1080 self._end = _end 1081 self._peek = _peek 1082 self._char = self.sql[_current - 1] 1083 1084 @property 1085 def _text(self) -> str: 1086 return self.sql[self._start : self._current] 1087 1088 def _add(self, token_type: TokenType, text: t.Optional[str] = None) -> None: 1089 self._prev_token_line = self._line 1090 1091 if self._comments and token_type == TokenType.SEMICOLON and self.tokens: 1092 self.tokens[-1].comments.extend(self._comments) 1093 self._comments = [] 1094 1095 self.tokens.append( 1096 Token( 1097 token_type, 1098 text=self._text if text is None else text, 1099 line=self._line, 1100 col=self._col, 1101 start=self._start, 1102 end=self._current - 1, 1103 comments=self._comments, 1104 ) 1105 ) 1106 self._comments = [] 1107 1108 # If we have either a semicolon or a begin token before the command's token, we'll parse 1109 # whatever follows the command's token as a string 1110 if ( 1111 token_type in self.COMMANDS 1112 and self._peek != ";" 1113 and (len(self.tokens) == 1 or self.tokens[-2].token_type in self.COMMAND_PREFIX_TOKENS) 1114 ): 1115 start = self._current 1116 tokens = len(self.tokens) 1117 self._scan(lambda: self._peek == ";") 1118 self.tokens = self.tokens[:tokens] 1119 text = self.sql[start : self._current].strip() 1120 if text: 1121 self._add(TokenType.STRING, text) 1122 1123 def _scan_keywords(self) -> None: 1124 size = 0 1125 word = None 1126 chars = self._text 1127 char = chars 1128 prev_space = False 1129 skip = False 1130 trie = self._KEYWORD_TRIE 1131 single_token = char in self.SINGLE_TOKENS 1132 1133 while chars: 1134 if skip: 1135 result = TrieResult.PREFIX 1136 else: 1137 result, trie = in_trie(trie, char.upper()) 1138 1139 if result == TrieResult.FAILED: 1140 break 1141 if result == TrieResult.EXISTS: 1142 word = chars 1143 1144 end = self._current + size 1145 size += 1 1146 1147 if end < self.size: 1148 char = self.sql[end] 1149 single_token = single_token or char in self.SINGLE_TOKENS 1150 is_space = char.isspace() 1151 1152 if not is_space or not prev_space: 1153 if is_space: 1154 char = " " 1155 chars += char 1156 prev_space = is_space 1157 skip = False 1158 else: 1159 skip = True 1160 else: 1161 char = "" 1162 break 1163 1164 if word: 1165 if self._scan_string(word): 1166 return 1167 if self._scan_comment(word): 1168 return 1169 if prev_space or single_token or not char: 1170 self._advance(size - 1) 1171 word = word.upper() 1172 self._add(self.KEYWORDS[word], text=word) 1173 return 1174 1175 if self._char in self.SINGLE_TOKENS: 1176 self._add(self.SINGLE_TOKENS[self._char], text=self._char) 1177 return 1178 1179 self._scan_var() 1180 1181 def _scan_comment(self, comment_start: str) -> bool: 1182 if comment_start not in self._COMMENTS: 1183 return False 1184 1185 comment_start_line = self._line 1186 comment_start_size = len(comment_start) 1187 comment_end = self._COMMENTS[comment_start] 1188 1189 if comment_end: 1190 # Skip the comment's start delimiter 1191 self._advance(comment_start_size) 1192 1193 comment_count = 1 1194 comment_end_size = len(comment_end) 1195 1196 while not self._end: 1197 if self._chars(comment_end_size) == comment_end: 1198 comment_count -= 1 1199 if not comment_count: 1200 break 1201 1202 self._advance(alnum=True) 1203 1204 # Nested comments are allowed by some dialects, e.g. databricks, duckdb, postgres 1205 if ( 1206 self.NESTED_COMMENTS 1207 and not self._end 1208 and self._chars(comment_end_size) == comment_start 1209 ): 1210 self._advance(comment_start_size) 1211 comment_count += 1 1212 1213 self._comments.append(self._text[comment_start_size : -comment_end_size + 1]) 1214 self._advance(comment_end_size - 1) 1215 else: 1216 while not self._end and self.WHITE_SPACE.get(self._peek) is not TokenType.BREAK: 1217 self._advance(alnum=True) 1218 self._comments.append(self._text[comment_start_size:]) 1219 1220 # Leading comment is attached to the succeeding token, whilst trailing comment to the preceding. 1221 # Multiple consecutive comments are preserved by appending them to the current comments list. 1222 if comment_start_line == self._prev_token_line: 1223 self.tokens[-1].comments.extend(self._comments) 1224 self._comments = [] 1225 self._prev_token_line = self._line 1226 1227 return True 1228 1229 def _scan_number(self) -> None: 1230 if self._char == "0": 1231 peek = self._peek.upper() 1232 if peek == "B": 1233 return self._scan_bits() if self.BIT_STRINGS else self._add(TokenType.NUMBER) 1234 elif peek == "X": 1235 return self._scan_hex() if self.HEX_STRINGS else self._add(TokenType.NUMBER) 1236 1237 decimal = False 1238 scientific = 0 1239 1240 while True: 1241 if self._peek.isdigit(): 1242 self._advance() 1243 elif self._peek == "." and not decimal: 1244 if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER: 1245 return self._add(TokenType.NUMBER) 1246 decimal = True 1247 self._advance() 1248 elif self._peek in ("-", "+") and scientific == 1: 1249 scientific += 1 1250 self._advance() 1251 elif self._peek.upper() == "E" and not scientific: 1252 scientific += 1 1253 self._advance() 1254 elif self._peek.isidentifier(): 1255 number_text = self._text 1256 literal = "" 1257 1258 while self._peek.strip() and self._peek not in self.SINGLE_TOKENS: 1259 literal += self._peek 1260 self._advance() 1261 1262 token_type = self.KEYWORDS.get(self.NUMERIC_LITERALS.get(literal.upper(), "")) 1263 1264 if token_type: 1265 self._add(TokenType.NUMBER, number_text) 1266 self._add(TokenType.DCOLON, "::") 1267 return self._add(token_type, literal) 1268 elif self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT: 1269 return self._add(TokenType.VAR) 1270 1271 self._advance(-len(literal)) 1272 return self._add(TokenType.NUMBER, number_text) 1273 else: 1274 return self._add(TokenType.NUMBER) 1275 1276 def _scan_bits(self) -> None: 1277 self._advance() 1278 value = self._extract_value() 1279 try: 1280 # If `value` can't be converted to a binary, fallback to tokenizing it as an identifier 1281 int(value, 2) 1282 self._add(TokenType.BIT_STRING, value[2:]) # Drop the 0b 1283 except ValueError: 1284 self._add(TokenType.IDENTIFIER) 1285 1286 def _scan_hex(self) -> None: 1287 self._advance() 1288 value = self._extract_value() 1289 try: 1290 # If `value` can't be converted to a hex, fallback to tokenizing it as an identifier 1291 int(value, 16) 1292 self._add(TokenType.HEX_STRING, value[2:]) # Drop the 0x 1293 except ValueError: 1294 self._add(TokenType.IDENTIFIER) 1295 1296 def _extract_value(self) -> str: 1297 while True: 1298 char = self._peek.strip() 1299 if char and char not in self.SINGLE_TOKENS: 1300 self._advance(alnum=True) 1301 else: 1302 break 1303 1304 return self._text 1305 1306 def _scan_string(self, start: str) -> bool: 1307 base = None 1308 token_type = TokenType.STRING 1309 1310 if start in self._QUOTES: 1311 end = self._QUOTES[start] 1312 elif start in self._FORMAT_STRINGS: 1313 end, token_type = self._FORMAT_STRINGS[start] 1314 1315 if token_type == TokenType.HEX_STRING: 1316 base = 16 1317 elif token_type == TokenType.BIT_STRING: 1318 base = 2 1319 elif token_type == TokenType.HEREDOC_STRING: 1320 self._advance() 1321 1322 if self._char == end: 1323 tag = "" 1324 else: 1325 tag = self._extract_string( 1326 end, 1327 raw_string=True, 1328 raise_unmatched=not self.HEREDOC_TAG_IS_IDENTIFIER, 1329 ) 1330 1331 if tag and self.HEREDOC_TAG_IS_IDENTIFIER and (self._end or not tag.isidentifier()): 1332 if not self._end: 1333 self._advance(-1) 1334 1335 self._advance(-len(tag)) 1336 self._add(self.HEREDOC_STRING_ALTERNATIVE) 1337 return True 1338 1339 end = f"{start}{tag}{end}" 1340 else: 1341 return False 1342 1343 self._advance(len(start)) 1344 text = self._extract_string(end, raw_string=token_type == TokenType.RAW_STRING) 1345 1346 if base: 1347 try: 1348 int(text, base) 1349 except Exception: 1350 raise TokenError( 1351 f"Numeric string contains invalid characters from {self._line}:{self._start}" 1352 ) 1353 1354 self._add(token_type, text) 1355 return True 1356 1357 def _scan_identifier(self, identifier_end: str) -> None: 1358 self._advance() 1359 text = self._extract_string(identifier_end, escapes=self._IDENTIFIER_ESCAPES) 1360 self._add(TokenType.IDENTIFIER, text) 1361 1362 def _scan_var(self) -> None: 1363 while True: 1364 char = self._peek.strip() 1365 if char and (char in self.VAR_SINGLE_TOKENS or char not in self.SINGLE_TOKENS): 1366 self._advance(alnum=True) 1367 else: 1368 break 1369 1370 self._add( 1371 TokenType.VAR 1372 if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER 1373 else self.KEYWORDS.get(self._text.upper(), TokenType.VAR) 1374 ) 1375 1376 def _extract_string( 1377 self, 1378 delimiter: str, 1379 escapes: t.Optional[t.Set[str]] = None, 1380 raw_string: bool = False, 1381 raise_unmatched: bool = True, 1382 ) -> str: 1383 text = "" 1384 delim_size = len(delimiter) 1385 escapes = self._STRING_ESCAPES if escapes is None else escapes 1386 1387 while True: 1388 if ( 1389 not raw_string 1390 and self.dialect.UNESCAPED_SEQUENCES 1391 and self._peek 1392 and self._char in self.STRING_ESCAPES 1393 ): 1394 unescaped_sequence = self.dialect.UNESCAPED_SEQUENCES.get(self._char + self._peek) 1395 if unescaped_sequence: 1396 self._advance(2) 1397 text += unescaped_sequence 1398 continue 1399 if ( 1400 (self.STRING_ESCAPES_ALLOWED_IN_RAW_STRINGS or not raw_string) 1401 and self._char in escapes 1402 and (self._peek == delimiter or self._peek in escapes) 1403 and (self._char not in self._QUOTES or self._char == self._peek) 1404 ): 1405 if self._peek == delimiter: 1406 text += self._peek 1407 else: 1408 text += self._char + self._peek 1409 1410 if self._current + 1 < self.size: 1411 self._advance(2) 1412 else: 1413 raise TokenError(f"Missing {delimiter} from {self._line}:{self._current}") 1414 else: 1415 if self._chars(delim_size) == delimiter: 1416 if delim_size > 1: 1417 self._advance(delim_size - 1) 1418 break 1419 1420 if self._end: 1421 if not raise_unmatched: 1422 return text + self._char 1423 1424 raise TokenError(f"Missing {delimiter} from {self._line}:{self._start}") 1425 1426 current = self._current - 1 1427 self._advance(alnum=True) 1428 text += self.sql[current : self._current - 1] 1429 1430 return text 1431 1432 def tokenize_rs(self, sql: str) -> t.List[Token]: 1433 if not self._RS_TOKENIZER: 1434 raise SqlglotError("Rust tokenizer is not available") 1435 1436 try: 1437 tokens = self._RS_TOKENIZER.tokenize(sql, self._rs_dialect_settings) 1438 for token in tokens: 1439 token.token_type = _ALL_TOKEN_TYPES[token.token_type_index] 1440 return tokens 1441 except Exception as e: 1442 raise TokenError(str(e))
Tokenizer( dialect: Union[str, sqlglot.dialects.dialect.Dialect, Type[sqlglot.dialects.dialect.Dialect], NoneType] = None)
963 def __init__(self, dialect: DialectType = None) -> None: 964 from sqlglot.dialects import Dialect 965 966 self.dialect = Dialect.get_or_raise(dialect) 967 968 if USE_RS_TOKENIZER: 969 self._rs_dialect_settings = RsTokenizerDialectSettings( 970 unescaped_sequences=self.dialect.UNESCAPED_SEQUENCES, 971 identifiers_can_start_with_digit=self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT, 972 ) 973 974 self.reset()
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.HASH: 'HASH'>, "'": <TokenType.UNKNOWN: 'UNKNOWN'>, '`': <TokenType.UNKNOWN: 'UNKNOWN'>, '"': <TokenType.UNKNOWN: 'UNKNOWN'>}
HEREDOC_STRING_ALTERNATIVE =
<TokenType.VAR: 'VAR'>
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'>, '~~~': <TokenType.GLOB: 'GLOB'>, '~~': <TokenType.LIKE: 'LIKE'>, '~~*': <TokenType.ILIKE: 'ILIKE'>, '~*': <TokenType.IRLIKE: 'IRLIKE'>, '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'>, 'COPY': <TokenType.COPY: 'COPY'>, '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'>, 'ENUM': <TokenType.ENUM: 'ENUM'>, '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'>, 'RENAME': <TokenType.RENAME: 'RENAME'>, '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'>, 'STRAIGHT_JOIN': <TokenType.STRAIGHT_JOIN: 'STRAIGHT_JOIN'>, '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'>, 'TRUNCATE': <TokenType.TRUNCATE: 'TRUNCATE'>, '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'>, 'UHUGEINT': <TokenType.UINT128: 'UINT128'>, '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'>, 'UINT': <TokenType.UINT: 'UINT'>, 'DEC': <TokenType.DECIMAL: 'DECIMAL'>, 'DECIMAL': <TokenType.DECIMAL: 'DECIMAL'>, 'DECIMAL32': <TokenType.DECIMAL32: 'DECIMAL32'>, 'DECIMAL64': <TokenType.DECIMAL64: 'DECIMAL64'>, 'DECIMAL128': <TokenType.DECIMAL128: 'DECIMAL128'>, 'BIGDECIMAL': <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, 'BIGNUMERIC': <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, 'LIST': <TokenType.LIST: 'LIST'>, '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'>, 'JSONB': <TokenType.JSONB: 'JSONB'>, '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'>, 'BPCHAR': <TokenType.BPCHAR: 'BPCHAR'>, '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'>, 'TIMESTAMP_LTZ': <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>, 'TIMESTAMPNTZ': <TokenType.TIMESTAMPNTZ: 'TIMESTAMPNTZ'>, 'TIMESTAMP_NTZ': <TokenType.TIMESTAMPNTZ: 'TIMESTAMPNTZ'>, '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'>, 'VECTOR': <TokenType.VECTOR: 'VECTOR'>, 'STRUCT': <TokenType.STRUCT: 'STRUCT'>, 'SEQUENCE': <TokenType.SEQUENCE: 'SEQUENCE'>, 'VARIANT': <TokenType.VARIANT: 'VARIANT'>, 'ALTER': <TokenType.ALTER: 'ALTER'>, 'ANALYZE': <TokenType.COMMAND: 'COMMAND'>, 'CALL': <TokenType.COMMAND: 'COMMAND'>, 'COMMENT': <TokenType.COMMENT: 'COMMENT'>, 'EXPLAIN': <TokenType.COMMAND: 'COMMAND'>, 'GRANT': <TokenType.GRANT: 'GRANT'>, 'OPTIMIZE': <TokenType.COMMAND: 'COMMAND'>, 'PREPARE': <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.COMMAND: 'COMMAND'>, <TokenType.EXECUTE: 'EXECUTE'>, <TokenType.RENAME: 'RENAME'>, <TokenType.FETCH: 'FETCH'>}
COMMAND_PREFIX_TOKENS =
{<TokenType.BEGIN: 'BEGIN'>, <TokenType.SEMICOLON: 'SEMICOLON'>}
def
reset(self) -> None:
976 def reset(self) -> None: 977 self.sql = "" 978 self.size = 0 979 self.tokens: t.List[Token] = [] 980 self._start = 0 981 self._current = 0 982 self._line = 1 983 self._col = 0 984 self._comments: t.List[str] = [] 985 986 self._char = "" 987 self._end = False 988 self._peek = "" 989 self._prev_token_line = -1
991 def tokenize(self, sql: str) -> t.List[Token]: 992 """Returns a list of tokens corresponding to the SQL string `sql`.""" 993 if USE_RS_TOKENIZER: 994 return self.tokenize_rs(sql) 995 996 self.reset() 997 self.sql = sql 998 self.size = len(sql) 999 1000 try: 1001 self._scan() 1002 except Exception as e: 1003 start = max(self._current - 50, 0) 1004 end = min(self._current + 50, self.size - 1) 1005 context = self.sql[start:end] 1006 raise TokenError(f"Error tokenizing '{context}'") from e 1007 1008 return self.tokens
Returns a list of tokens corresponding to the SQL string sql
.
1432 def tokenize_rs(self, sql: str) -> t.List[Token]: 1433 if not self._RS_TOKENIZER: 1434 raise SqlglotError("Rust tokenizer is not available") 1435 1436 try: 1437 tokens = self._RS_TOKENIZER.tokenize(sql, self._rs_dialect_settings) 1438 for token in tokens: 1439 token.token_type = _ALL_TOKEN_TYPES[token.token_type_index] 1440 return tokens 1441 except Exception as e: 1442 raise TokenError(str(e))