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