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