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 OPERATOR = auto() 306 ORDER_BY = auto() 307 ORDER_SIBLINGS_BY = auto() 308 ORDERED = auto() 309 ORDINALITY = auto() 310 OUTER = auto() 311 OVER = auto() 312 OVERLAPS = auto() 313 OVERWRITE = auto() 314 PARTITION = auto() 315 PARTITION_BY = auto() 316 PERCENT = auto() 317 PIVOT = auto() 318 PLACEHOLDER = auto() 319 PRAGMA = auto() 320 PRIMARY_KEY = auto() 321 PROCEDURE = auto() 322 PROPERTIES = auto() 323 PSEUDO_TYPE = auto() 324 QUALIFY = auto() 325 QUOTE = auto() 326 RANGE = auto() 327 RECURSIVE = auto() 328 REFRESH = auto() 329 REPLACE = auto() 330 RETURNING = auto() 331 REFERENCES = auto() 332 RIGHT = auto() 333 RLIKE = auto() 334 ROLLBACK = auto() 335 ROLLUP = auto() 336 ROW = auto() 337 ROWS = auto() 338 SELECT = auto() 339 SEMI = auto() 340 SEPARATOR = auto() 341 SERDE_PROPERTIES = auto() 342 SET = auto() 343 SETTINGS = auto() 344 SHOW = auto() 345 SIMILAR_TO = auto() 346 SOME = auto() 347 SORT_BY = auto() 348 START_WITH = auto() 349 STORAGE_INTEGRATION = auto() 350 STRUCT = auto() 351 TABLE_SAMPLE = auto() 352 TEMPORARY = auto() 353 TOP = auto() 354 THEN = auto() 355 TRUE = auto() 356 UNCACHE = auto() 357 UNION = auto() 358 UNNEST = auto() 359 UNPIVOT = auto() 360 UPDATE = auto() 361 USE = auto() 362 USING = auto() 363 VALUES = auto() 364 VIEW = auto() 365 VOLATILE = auto() 366 WHEN = auto() 367 WHERE = auto() 368 WINDOW = auto() 369 WITH = auto() 370 UNIQUE = auto() 371 VERSION_SNAPSHOT = auto() 372 TIMESTAMP_SNAPSHOT = auto() 373 374 375_ALL_TOKEN_TYPES = list(TokenType) 376_TOKEN_TYPE_TO_INDEX = {token_type: i for i, token_type in enumerate(_ALL_TOKEN_TYPES)} 377 378 379class Token: 380 __slots__ = ("token_type", "text", "line", "col", "start", "end", "comments") 381 382 @classmethod 383 def number(cls, number: int) -> Token: 384 """Returns a NUMBER token with `number` as its text.""" 385 return cls(TokenType.NUMBER, str(number)) 386 387 @classmethod 388 def string(cls, string: str) -> Token: 389 """Returns a STRING token with `string` as its text.""" 390 return cls(TokenType.STRING, string) 391 392 @classmethod 393 def identifier(cls, identifier: str) -> Token: 394 """Returns an IDENTIFIER token with `identifier` as its text.""" 395 return cls(TokenType.IDENTIFIER, identifier) 396 397 @classmethod 398 def var(cls, var: str) -> Token: 399 """Returns an VAR token with `var` as its text.""" 400 return cls(TokenType.VAR, var) 401 402 def __init__( 403 self, 404 token_type: TokenType, 405 text: str, 406 line: int = 1, 407 col: int = 1, 408 start: int = 0, 409 end: int = 0, 410 comments: t.Optional[t.List[str]] = None, 411 ) -> None: 412 """Token initializer. 413 414 Args: 415 token_type: The TokenType Enum. 416 text: The text of the token. 417 line: The line that the token ends on. 418 col: The column that the token ends on. 419 start: The start index of the token. 420 end: The ending index of the token. 421 comments: The comments to attach to the token. 422 """ 423 self.token_type = token_type 424 self.text = text 425 self.line = line 426 self.col = col 427 self.start = start 428 self.end = end 429 self.comments = [] if comments is None else comments 430 431 def __repr__(self) -> str: 432 attributes = ", ".join(f"{k}: {getattr(self, k)}" for k in self.__slots__) 433 return f"<Token {attributes}>" 434 435 436class _Tokenizer(type): 437 def __new__(cls, clsname, bases, attrs): 438 klass = super().__new__(cls, clsname, bases, attrs) 439 440 def _convert_quotes(arr: t.List[str | t.Tuple[str, str]]) -> t.Dict[str, str]: 441 return dict( 442 (item, item) if isinstance(item, str) else (item[0], item[1]) for item in arr 443 ) 444 445 def _quotes_to_format( 446 token_type: TokenType, arr: t.List[str | t.Tuple[str, str]] 447 ) -> t.Dict[str, t.Tuple[str, TokenType]]: 448 return {k: (v, token_type) for k, v in _convert_quotes(arr).items()} 449 450 klass._QUOTES = _convert_quotes(klass.QUOTES) 451 klass._IDENTIFIERS = _convert_quotes(klass.IDENTIFIERS) 452 453 klass._FORMAT_STRINGS = { 454 **{ 455 p + s: (e, TokenType.NATIONAL_STRING) 456 for s, e in klass._QUOTES.items() 457 for p in ("n", "N") 458 }, 459 **_quotes_to_format(TokenType.BIT_STRING, klass.BIT_STRINGS), 460 **_quotes_to_format(TokenType.BYTE_STRING, klass.BYTE_STRINGS), 461 **_quotes_to_format(TokenType.HEX_STRING, klass.HEX_STRINGS), 462 **_quotes_to_format(TokenType.RAW_STRING, klass.RAW_STRINGS), 463 **_quotes_to_format(TokenType.HEREDOC_STRING, klass.HEREDOC_STRINGS), 464 **_quotes_to_format(TokenType.UNICODE_STRING, klass.UNICODE_STRINGS), 465 } 466 467 klass._STRING_ESCAPES = set(klass.STRING_ESCAPES) 468 klass._IDENTIFIER_ESCAPES = set(klass.IDENTIFIER_ESCAPES) 469 klass._COMMENTS = { 470 **dict( 471 (comment, None) if isinstance(comment, str) else (comment[0], comment[1]) 472 for comment in klass.COMMENTS 473 ), 474 "{#": "#}", # Ensure Jinja comments are tokenized correctly in all dialects 475 } 476 477 klass._KEYWORD_TRIE = new_trie( 478 key.upper() 479 for key in ( 480 *klass.KEYWORDS, 481 *klass._COMMENTS, 482 *klass._QUOTES, 483 *klass._FORMAT_STRINGS, 484 ) 485 if " " in key or any(single in key for single in klass.SINGLE_TOKENS) 486 ) 487 488 if USE_RS_TOKENIZER: 489 settings = RsTokenizerSettings( 490 white_space={k: _TOKEN_TYPE_TO_INDEX[v] for k, v in klass.WHITE_SPACE.items()}, 491 single_tokens={k: _TOKEN_TYPE_TO_INDEX[v] for k, v in klass.SINGLE_TOKENS.items()}, 492 keywords={k: _TOKEN_TYPE_TO_INDEX[v] for k, v in klass.KEYWORDS.items()}, 493 numeric_literals=klass.NUMERIC_LITERALS, 494 identifiers=klass._IDENTIFIERS, 495 identifier_escapes=klass._IDENTIFIER_ESCAPES, 496 string_escapes=klass._STRING_ESCAPES, 497 quotes=klass._QUOTES, 498 format_strings={ 499 k: (v1, _TOKEN_TYPE_TO_INDEX[v2]) 500 for k, (v1, v2) in klass._FORMAT_STRINGS.items() 501 }, 502 has_bit_strings=bool(klass.BIT_STRINGS), 503 has_hex_strings=bool(klass.HEX_STRINGS), 504 comments=klass._COMMENTS, 505 var_single_tokens=klass.VAR_SINGLE_TOKENS, 506 commands={_TOKEN_TYPE_TO_INDEX[v] for v in klass.COMMANDS}, 507 command_prefix_tokens={ 508 _TOKEN_TYPE_TO_INDEX[v] for v in klass.COMMAND_PREFIX_TOKENS 509 }, 510 heredoc_tag_is_identifier=klass.HEREDOC_TAG_IS_IDENTIFIER, 511 ) 512 token_types = RsTokenTypeSettings( 513 bit_string=_TOKEN_TYPE_TO_INDEX[TokenType.BIT_STRING], 514 break_=_TOKEN_TYPE_TO_INDEX[TokenType.BREAK], 515 dcolon=_TOKEN_TYPE_TO_INDEX[TokenType.DCOLON], 516 heredoc_string=_TOKEN_TYPE_TO_INDEX[TokenType.HEREDOC_STRING], 517 hex_string=_TOKEN_TYPE_TO_INDEX[TokenType.HEX_STRING], 518 identifier=_TOKEN_TYPE_TO_INDEX[TokenType.IDENTIFIER], 519 number=_TOKEN_TYPE_TO_INDEX[TokenType.NUMBER], 520 parameter=_TOKEN_TYPE_TO_INDEX[TokenType.PARAMETER], 521 semicolon=_TOKEN_TYPE_TO_INDEX[TokenType.SEMICOLON], 522 string=_TOKEN_TYPE_TO_INDEX[TokenType.STRING], 523 var=_TOKEN_TYPE_TO_INDEX[TokenType.VAR], 524 heredoc_string_alternative=_TOKEN_TYPE_TO_INDEX[klass.HEREDOC_STRING_ALTERNATIVE], 525 ) 526 klass._RS_TOKENIZER = RsTokenizer(settings, token_types) 527 else: 528 klass._RS_TOKENIZER = None 529 530 return klass 531 532 533class Tokenizer(metaclass=_Tokenizer): 534 SINGLE_TOKENS = { 535 "(": TokenType.L_PAREN, 536 ")": TokenType.R_PAREN, 537 "[": TokenType.L_BRACKET, 538 "]": TokenType.R_BRACKET, 539 "{": TokenType.L_BRACE, 540 "}": TokenType.R_BRACE, 541 "&": TokenType.AMP, 542 "^": TokenType.CARET, 543 ":": TokenType.COLON, 544 ",": TokenType.COMMA, 545 ".": TokenType.DOT, 546 "-": TokenType.DASH, 547 "=": TokenType.EQ, 548 ">": TokenType.GT, 549 "<": TokenType.LT, 550 "%": TokenType.MOD, 551 "!": TokenType.NOT, 552 "|": TokenType.PIPE, 553 "+": TokenType.PLUS, 554 ";": TokenType.SEMICOLON, 555 "/": TokenType.SLASH, 556 "\\": TokenType.BACKSLASH, 557 "*": TokenType.STAR, 558 "~": TokenType.TILDA, 559 "?": TokenType.PLACEHOLDER, 560 "@": TokenType.PARAMETER, 561 # used for breaking a var like x'y' but nothing else 562 # the token type doesn't matter 563 "'": TokenType.QUOTE, 564 "`": TokenType.IDENTIFIER, 565 '"': TokenType.IDENTIFIER, 566 "#": TokenType.HASH, 567 } 568 569 BIT_STRINGS: t.List[str | t.Tuple[str, str]] = [] 570 BYTE_STRINGS: t.List[str | t.Tuple[str, str]] = [] 571 HEX_STRINGS: t.List[str | t.Tuple[str, str]] = [] 572 RAW_STRINGS: t.List[str | t.Tuple[str, str]] = [] 573 HEREDOC_STRINGS: t.List[str | t.Tuple[str, str]] = [] 574 UNICODE_STRINGS: t.List[str | t.Tuple[str, str]] = [] 575 IDENTIFIERS: t.List[str | t.Tuple[str, str]] = ['"'] 576 IDENTIFIER_ESCAPES = ['"'] 577 QUOTES: t.List[t.Tuple[str, str] | str] = ["'"] 578 STRING_ESCAPES = ["'"] 579 VAR_SINGLE_TOKENS: t.Set[str] = set() 580 581 # Whether the heredoc tags follow the same lexical rules as unquoted identifiers 582 HEREDOC_TAG_IS_IDENTIFIER = False 583 584 # Token that we'll generate as a fallback if the heredoc prefix doesn't correspond to a heredoc 585 HEREDOC_STRING_ALTERNATIVE = TokenType.VAR 586 587 # Autofilled 588 _COMMENTS: t.Dict[str, str] = {} 589 _FORMAT_STRINGS: t.Dict[str, t.Tuple[str, TokenType]] = {} 590 _IDENTIFIERS: t.Dict[str, str] = {} 591 _IDENTIFIER_ESCAPES: t.Set[str] = set() 592 _QUOTES: t.Dict[str, str] = {} 593 _STRING_ESCAPES: t.Set[str] = set() 594 _KEYWORD_TRIE: t.Dict = {} 595 _RS_TOKENIZER: t.Optional[t.Any] = None 596 597 KEYWORDS: t.Dict[str, TokenType] = { 598 **{f"{{%{postfix}": TokenType.BLOCK_START for postfix in ("", "+", "-")}, 599 **{f"{prefix}%}}": TokenType.BLOCK_END for prefix in ("", "+", "-")}, 600 **{f"{{{{{postfix}": TokenType.BLOCK_START for postfix in ("+", "-")}, 601 **{f"{prefix}}}}}": TokenType.BLOCK_END for prefix in ("+", "-")}, 602 "/*+": TokenType.HINT, 603 "==": TokenType.EQ, 604 "::": TokenType.DCOLON, 605 "||": TokenType.DPIPE, 606 ">=": TokenType.GTE, 607 "<=": TokenType.LTE, 608 "<>": TokenType.NEQ, 609 "!=": TokenType.NEQ, 610 ":=": TokenType.COLON_EQ, 611 "<=>": TokenType.NULLSAFE_EQ, 612 "->": TokenType.ARROW, 613 "->>": TokenType.DARROW, 614 "=>": TokenType.FARROW, 615 "#>": TokenType.HASH_ARROW, 616 "#>>": TokenType.DHASH_ARROW, 617 "<->": TokenType.LR_ARROW, 618 "&&": TokenType.DAMP, 619 "??": TokenType.DQMARK, 620 "ALL": TokenType.ALL, 621 "ALWAYS": TokenType.ALWAYS, 622 "AND": TokenType.AND, 623 "ANTI": TokenType.ANTI, 624 "ANY": TokenType.ANY, 625 "ASC": TokenType.ASC, 626 "AS": TokenType.ALIAS, 627 "ASOF": TokenType.ASOF, 628 "AUTOINCREMENT": TokenType.AUTO_INCREMENT, 629 "AUTO_INCREMENT": TokenType.AUTO_INCREMENT, 630 "BEGIN": TokenType.BEGIN, 631 "BETWEEN": TokenType.BETWEEN, 632 "CACHE": TokenType.CACHE, 633 "UNCACHE": TokenType.UNCACHE, 634 "CASE": TokenType.CASE, 635 "CHARACTER SET": TokenType.CHARACTER_SET, 636 "CLUSTER BY": TokenType.CLUSTER_BY, 637 "COLLATE": TokenType.COLLATE, 638 "COLUMN": TokenType.COLUMN, 639 "COMMIT": TokenType.COMMIT, 640 "CONNECT BY": TokenType.CONNECT_BY, 641 "CONSTRAINT": TokenType.CONSTRAINT, 642 "CREATE": TokenType.CREATE, 643 "CROSS": TokenType.CROSS, 644 "CUBE": TokenType.CUBE, 645 "CURRENT_DATE": TokenType.CURRENT_DATE, 646 "CURRENT_TIME": TokenType.CURRENT_TIME, 647 "CURRENT_TIMESTAMP": TokenType.CURRENT_TIMESTAMP, 648 "CURRENT_USER": TokenType.CURRENT_USER, 649 "DATABASE": TokenType.DATABASE, 650 "DEFAULT": TokenType.DEFAULT, 651 "DELETE": TokenType.DELETE, 652 "DESC": TokenType.DESC, 653 "DESCRIBE": TokenType.DESCRIBE, 654 "DISTINCT": TokenType.DISTINCT, 655 "DISTRIBUTE BY": TokenType.DISTRIBUTE_BY, 656 "DIV": TokenType.DIV, 657 "DROP": TokenType.DROP, 658 "ELSE": TokenType.ELSE, 659 "END": TokenType.END, 660 "ESCAPE": TokenType.ESCAPE, 661 "EXCEPT": TokenType.EXCEPT, 662 "EXECUTE": TokenType.EXECUTE, 663 "EXISTS": TokenType.EXISTS, 664 "FALSE": TokenType.FALSE, 665 "FETCH": TokenType.FETCH, 666 "FILTER": TokenType.FILTER, 667 "FIRST": TokenType.FIRST, 668 "FULL": TokenType.FULL, 669 "FUNCTION": TokenType.FUNCTION, 670 "FOR": TokenType.FOR, 671 "FOREIGN KEY": TokenType.FOREIGN_KEY, 672 "FORMAT": TokenType.FORMAT, 673 "FROM": TokenType.FROM, 674 "GEOGRAPHY": TokenType.GEOGRAPHY, 675 "GEOMETRY": TokenType.GEOMETRY, 676 "GLOB": TokenType.GLOB, 677 "GROUP BY": TokenType.GROUP_BY, 678 "GROUPING SETS": TokenType.GROUPING_SETS, 679 "HAVING": TokenType.HAVING, 680 "ILIKE": TokenType.ILIKE, 681 "IN": TokenType.IN, 682 "INDEX": TokenType.INDEX, 683 "INET": TokenType.INET, 684 "INNER": TokenType.INNER, 685 "INSERT": TokenType.INSERT, 686 "INTERVAL": TokenType.INTERVAL, 687 "INTERSECT": TokenType.INTERSECT, 688 "INTO": TokenType.INTO, 689 "IS": TokenType.IS, 690 "ISNULL": TokenType.ISNULL, 691 "JOIN": TokenType.JOIN, 692 "KEEP": TokenType.KEEP, 693 "KILL": TokenType.KILL, 694 "LATERAL": TokenType.LATERAL, 695 "LEFT": TokenType.LEFT, 696 "LIKE": TokenType.LIKE, 697 "LIMIT": TokenType.LIMIT, 698 "LOAD": TokenType.LOAD, 699 "LOCK": TokenType.LOCK, 700 "MERGE": TokenType.MERGE, 701 "NATURAL": TokenType.NATURAL, 702 "NEXT": TokenType.NEXT, 703 "NOT": TokenType.NOT, 704 "NOTNULL": TokenType.NOTNULL, 705 "NULL": TokenType.NULL, 706 "OBJECT": TokenType.OBJECT, 707 "OFFSET": TokenType.OFFSET, 708 "ON": TokenType.ON, 709 "OR": TokenType.OR, 710 "XOR": TokenType.XOR, 711 "ORDER BY": TokenType.ORDER_BY, 712 "ORDINALITY": TokenType.ORDINALITY, 713 "OUTER": TokenType.OUTER, 714 "OVER": TokenType.OVER, 715 "OVERLAPS": TokenType.OVERLAPS, 716 "OVERWRITE": TokenType.OVERWRITE, 717 "PARTITION": TokenType.PARTITION, 718 "PARTITION BY": TokenType.PARTITION_BY, 719 "PARTITIONED BY": TokenType.PARTITION_BY, 720 "PARTITIONED_BY": TokenType.PARTITION_BY, 721 "PERCENT": TokenType.PERCENT, 722 "PIVOT": TokenType.PIVOT, 723 "PRAGMA": TokenType.PRAGMA, 724 "PRIMARY KEY": TokenType.PRIMARY_KEY, 725 "PROCEDURE": TokenType.PROCEDURE, 726 "QUALIFY": TokenType.QUALIFY, 727 "RANGE": TokenType.RANGE, 728 "RECURSIVE": TokenType.RECURSIVE, 729 "REGEXP": TokenType.RLIKE, 730 "REPLACE": TokenType.REPLACE, 731 "RETURNING": TokenType.RETURNING, 732 "REFERENCES": TokenType.REFERENCES, 733 "RIGHT": TokenType.RIGHT, 734 "RLIKE": TokenType.RLIKE, 735 "ROLLBACK": TokenType.ROLLBACK, 736 "ROLLUP": TokenType.ROLLUP, 737 "ROW": TokenType.ROW, 738 "ROWS": TokenType.ROWS, 739 "SCHEMA": TokenType.SCHEMA, 740 "SELECT": TokenType.SELECT, 741 "SEMI": TokenType.SEMI, 742 "SET": TokenType.SET, 743 "SETTINGS": TokenType.SETTINGS, 744 "SHOW": TokenType.SHOW, 745 "SIMILAR TO": TokenType.SIMILAR_TO, 746 "SOME": TokenType.SOME, 747 "SORT BY": TokenType.SORT_BY, 748 "START WITH": TokenType.START_WITH, 749 "TABLE": TokenType.TABLE, 750 "TABLESAMPLE": TokenType.TABLE_SAMPLE, 751 "TEMP": TokenType.TEMPORARY, 752 "TEMPORARY": TokenType.TEMPORARY, 753 "THEN": TokenType.THEN, 754 "TRUE": TokenType.TRUE, 755 "UNION": TokenType.UNION, 756 "UNKNOWN": TokenType.UNKNOWN, 757 "UNNEST": TokenType.UNNEST, 758 "UNPIVOT": TokenType.UNPIVOT, 759 "UPDATE": TokenType.UPDATE, 760 "USE": TokenType.USE, 761 "USING": TokenType.USING, 762 "UUID": TokenType.UUID, 763 "VALUES": TokenType.VALUES, 764 "VIEW": TokenType.VIEW, 765 "VOLATILE": TokenType.VOLATILE, 766 "WHEN": TokenType.WHEN, 767 "WHERE": TokenType.WHERE, 768 "WINDOW": TokenType.WINDOW, 769 "WITH": TokenType.WITH, 770 "APPLY": TokenType.APPLY, 771 "ARRAY": TokenType.ARRAY, 772 "BIT": TokenType.BIT, 773 "BOOL": TokenType.BOOLEAN, 774 "BOOLEAN": TokenType.BOOLEAN, 775 "BYTE": TokenType.TINYINT, 776 "MEDIUMINT": TokenType.MEDIUMINT, 777 "INT1": TokenType.TINYINT, 778 "TINYINT": TokenType.TINYINT, 779 "INT16": TokenType.SMALLINT, 780 "SHORT": TokenType.SMALLINT, 781 "SMALLINT": TokenType.SMALLINT, 782 "INT128": TokenType.INT128, 783 "HUGEINT": TokenType.INT128, 784 "INT2": TokenType.SMALLINT, 785 "INTEGER": TokenType.INT, 786 "INT": TokenType.INT, 787 "INT4": TokenType.INT, 788 "INT32": TokenType.INT, 789 "INT64": TokenType.BIGINT, 790 "LONG": TokenType.BIGINT, 791 "BIGINT": TokenType.BIGINT, 792 "INT8": TokenType.TINYINT, 793 "DEC": TokenType.DECIMAL, 794 "DECIMAL": TokenType.DECIMAL, 795 "BIGDECIMAL": TokenType.BIGDECIMAL, 796 "BIGNUMERIC": TokenType.BIGDECIMAL, 797 "MAP": TokenType.MAP, 798 "NULLABLE": TokenType.NULLABLE, 799 "NUMBER": TokenType.DECIMAL, 800 "NUMERIC": TokenType.DECIMAL, 801 "FIXED": TokenType.DECIMAL, 802 "REAL": TokenType.FLOAT, 803 "FLOAT": TokenType.FLOAT, 804 "FLOAT4": TokenType.FLOAT, 805 "FLOAT8": TokenType.DOUBLE, 806 "DOUBLE": TokenType.DOUBLE, 807 "DOUBLE PRECISION": TokenType.DOUBLE, 808 "JSON": TokenType.JSON, 809 "CHAR": TokenType.CHAR, 810 "CHARACTER": TokenType.CHAR, 811 "NCHAR": TokenType.NCHAR, 812 "VARCHAR": TokenType.VARCHAR, 813 "VARCHAR2": TokenType.VARCHAR, 814 "NVARCHAR": TokenType.NVARCHAR, 815 "NVARCHAR2": TokenType.NVARCHAR, 816 "BPCHAR": TokenType.BPCHAR, 817 "STR": TokenType.TEXT, 818 "STRING": TokenType.TEXT, 819 "TEXT": TokenType.TEXT, 820 "LONGTEXT": TokenType.LONGTEXT, 821 "MEDIUMTEXT": TokenType.MEDIUMTEXT, 822 "TINYTEXT": TokenType.TINYTEXT, 823 "CLOB": TokenType.TEXT, 824 "LONGVARCHAR": TokenType.TEXT, 825 "BINARY": TokenType.BINARY, 826 "BLOB": TokenType.VARBINARY, 827 "LONGBLOB": TokenType.LONGBLOB, 828 "MEDIUMBLOB": TokenType.MEDIUMBLOB, 829 "TINYBLOB": TokenType.TINYBLOB, 830 "BYTEA": TokenType.VARBINARY, 831 "VARBINARY": TokenType.VARBINARY, 832 "TIME": TokenType.TIME, 833 "TIMETZ": TokenType.TIMETZ, 834 "TIMESTAMP": TokenType.TIMESTAMP, 835 "TIMESTAMPTZ": TokenType.TIMESTAMPTZ, 836 "TIMESTAMPLTZ": TokenType.TIMESTAMPLTZ, 837 "DATE": TokenType.DATE, 838 "DATETIME": TokenType.DATETIME, 839 "INT4RANGE": TokenType.INT4RANGE, 840 "INT4MULTIRANGE": TokenType.INT4MULTIRANGE, 841 "INT8RANGE": TokenType.INT8RANGE, 842 "INT8MULTIRANGE": TokenType.INT8MULTIRANGE, 843 "NUMRANGE": TokenType.NUMRANGE, 844 "NUMMULTIRANGE": TokenType.NUMMULTIRANGE, 845 "TSRANGE": TokenType.TSRANGE, 846 "TSMULTIRANGE": TokenType.TSMULTIRANGE, 847 "TSTZRANGE": TokenType.TSTZRANGE, 848 "TSTZMULTIRANGE": TokenType.TSTZMULTIRANGE, 849 "DATERANGE": TokenType.DATERANGE, 850 "DATEMULTIRANGE": TokenType.DATEMULTIRANGE, 851 "UNIQUE": TokenType.UNIQUE, 852 "STRUCT": TokenType.STRUCT, 853 "VARIANT": TokenType.VARIANT, 854 "ALTER": TokenType.ALTER, 855 "ANALYZE": TokenType.COMMAND, 856 "CALL": TokenType.COMMAND, 857 "COMMENT": TokenType.COMMENT, 858 "COPY": TokenType.COMMAND, 859 "EXPLAIN": TokenType.COMMAND, 860 "GRANT": TokenType.COMMAND, 861 "OPTIMIZE": TokenType.COMMAND, 862 "PREPARE": TokenType.COMMAND, 863 "TRUNCATE": TokenType.COMMAND, 864 "VACUUM": TokenType.COMMAND, 865 "USER-DEFINED": TokenType.USERDEFINED, 866 "FOR VERSION": TokenType.VERSION_SNAPSHOT, 867 "FOR TIMESTAMP": TokenType.TIMESTAMP_SNAPSHOT, 868 } 869 870 WHITE_SPACE: t.Dict[t.Optional[str], TokenType] = { 871 " ": TokenType.SPACE, 872 "\t": TokenType.SPACE, 873 "\n": TokenType.BREAK, 874 "\r": TokenType.BREAK, 875 } 876 877 COMMANDS = { 878 TokenType.COMMAND, 879 TokenType.EXECUTE, 880 TokenType.FETCH, 881 TokenType.SHOW, 882 } 883 884 COMMAND_PREFIX_TOKENS = {TokenType.SEMICOLON, TokenType.BEGIN} 885 886 # handle numeric literals like in hive (3L = BIGINT) 887 NUMERIC_LITERALS: t.Dict[str, str] = {} 888 889 COMMENTS = ["--", ("/*", "*/")] 890 891 __slots__ = ( 892 "sql", 893 "size", 894 "tokens", 895 "dialect", 896 "_start", 897 "_current", 898 "_line", 899 "_col", 900 "_comments", 901 "_char", 902 "_end", 903 "_peek", 904 "_prev_token_line", 905 "_rs_dialect_settings", 906 ) 907 908 def __init__(self, dialect: DialectType = None) -> None: 909 from sqlglot.dialects import Dialect 910 911 self.dialect = Dialect.get_or_raise(dialect) 912 913 if USE_RS_TOKENIZER: 914 self._rs_dialect_settings = RsTokenizerDialectSettings( 915 escape_sequences=self.dialect.ESCAPE_SEQUENCES, 916 identifiers_can_start_with_digit=self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT, 917 ) 918 919 self.reset() 920 921 def reset(self) -> None: 922 self.sql = "" 923 self.size = 0 924 self.tokens: t.List[Token] = [] 925 self._start = 0 926 self._current = 0 927 self._line = 1 928 self._col = 0 929 self._comments: t.List[str] = [] 930 931 self._char = "" 932 self._end = False 933 self._peek = "" 934 self._prev_token_line = -1 935 936 def tokenize(self, sql: str) -> t.List[Token]: 937 """Returns a list of tokens corresponding to the SQL string `sql`.""" 938 if USE_RS_TOKENIZER: 939 return self.tokenize_rs(sql) 940 941 self.reset() 942 self.sql = sql 943 self.size = len(sql) 944 945 try: 946 self._scan() 947 except Exception as e: 948 start = max(self._current - 50, 0) 949 end = min(self._current + 50, self.size - 1) 950 context = self.sql[start:end] 951 raise TokenError(f"Error tokenizing '{context}'") from e 952 953 return self.tokens 954 955 def _scan(self, until: t.Optional[t.Callable] = None) -> None: 956 while self.size and not self._end: 957 current = self._current 958 959 # skip spaces inline rather than iteratively call advance() 960 # for performance reasons 961 while current < self.size: 962 char = self.sql[current] 963 964 if char.isspace() and (char == " " or char == "\t"): 965 current += 1 966 else: 967 break 968 969 n = current - self._current 970 self._start = current 971 self._advance(n if n > 1 else 1) 972 973 if self._char is None: 974 break 975 976 if not self._char.isspace(): 977 if self._char.isdigit(): 978 self._scan_number() 979 elif self._char in self._IDENTIFIERS: 980 self._scan_identifier(self._IDENTIFIERS[self._char]) 981 else: 982 self._scan_keywords() 983 984 if until and until(): 985 break 986 987 if self.tokens and self._comments: 988 self.tokens[-1].comments.extend(self._comments) 989 990 def _chars(self, size: int) -> str: 991 if size == 1: 992 return self._char 993 994 start = self._current - 1 995 end = start + size 996 997 return self.sql[start:end] if end <= self.size else "" 998 999 def _advance(self, i: int = 1, alnum: bool = False) -> None: 1000 if self.WHITE_SPACE.get(self._char) is TokenType.BREAK: 1001 # Ensures we don't count an extra line if we get a \r\n line break sequence 1002 if self._char == "\r" and self._peek == "\n": 1003 i = 2 1004 self._start += 1 1005 1006 self._col = 1 1007 self._line += 1 1008 else: 1009 self._col += i 1010 1011 self._current += i 1012 self._end = self._current >= self.size 1013 self._char = self.sql[self._current - 1] 1014 self._peek = "" if self._end else self.sql[self._current] 1015 1016 if alnum and self._char.isalnum(): 1017 # Here we use local variables instead of attributes for better performance 1018 _col = self._col 1019 _current = self._current 1020 _end = self._end 1021 _peek = self._peek 1022 1023 while _peek.isalnum(): 1024 _col += 1 1025 _current += 1 1026 _end = _current >= self.size 1027 _peek = "" if _end else self.sql[_current] 1028 1029 self._col = _col 1030 self._current = _current 1031 self._end = _end 1032 self._peek = _peek 1033 self._char = self.sql[_current - 1] 1034 1035 @property 1036 def _text(self) -> str: 1037 return self.sql[self._start : self._current] 1038 1039 def peek(self, i: int = 0) -> str: 1040 i = self._current + i 1041 if i < self.size: 1042 return self.sql[i] 1043 return "" 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 after = self.peek(1) 1186 if after.isdigit() or not after.isalpha(): 1187 decimal = True 1188 self._advance() 1189 else: 1190 return self._add(TokenType.VAR) 1191 elif self._peek in ("-", "+") and scientific == 1: 1192 scientific += 1 1193 self._advance() 1194 elif self._peek.upper() == "E" and not scientific: 1195 scientific += 1 1196 self._advance() 1197 elif self._peek.isidentifier(): 1198 number_text = self._text 1199 literal = "" 1200 1201 while self._peek.strip() and self._peek not in self.SINGLE_TOKENS: 1202 literal += self._peek 1203 self._advance() 1204 1205 token_type = self.KEYWORDS.get(self.NUMERIC_LITERALS.get(literal.upper(), "")) 1206 1207 if token_type: 1208 self._add(TokenType.NUMBER, number_text) 1209 self._add(TokenType.DCOLON, "::") 1210 return self._add(token_type, literal) 1211 elif self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT: 1212 return self._add(TokenType.VAR) 1213 1214 self._advance(-len(literal)) 1215 return self._add(TokenType.NUMBER, number_text) 1216 else: 1217 return self._add(TokenType.NUMBER) 1218 1219 def _scan_bits(self) -> None: 1220 self._advance() 1221 value = self._extract_value() 1222 try: 1223 # If `value` can't be converted to a binary, fallback to tokenizing it as an identifier 1224 int(value, 2) 1225 self._add(TokenType.BIT_STRING, value[2:]) # Drop the 0b 1226 except ValueError: 1227 self._add(TokenType.IDENTIFIER) 1228 1229 def _scan_hex(self) -> None: 1230 self._advance() 1231 value = self._extract_value() 1232 try: 1233 # If `value` can't be converted to a hex, fallback to tokenizing it as an identifier 1234 int(value, 16) 1235 self._add(TokenType.HEX_STRING, value[2:]) # Drop the 0x 1236 except ValueError: 1237 self._add(TokenType.IDENTIFIER) 1238 1239 def _extract_value(self) -> str: 1240 while True: 1241 char = self._peek.strip() 1242 if char and char not in self.SINGLE_TOKENS: 1243 self._advance(alnum=True) 1244 else: 1245 break 1246 1247 return self._text 1248 1249 def _scan_string(self, start: str) -> bool: 1250 base = None 1251 token_type = TokenType.STRING 1252 1253 if start in self._QUOTES: 1254 end = self._QUOTES[start] 1255 elif start in self._FORMAT_STRINGS: 1256 end, token_type = self._FORMAT_STRINGS[start] 1257 1258 if token_type == TokenType.HEX_STRING: 1259 base = 16 1260 elif token_type == TokenType.BIT_STRING: 1261 base = 2 1262 elif token_type == TokenType.HEREDOC_STRING: 1263 if ( 1264 self.HEREDOC_TAG_IS_IDENTIFIER 1265 and not self._peek.isidentifier() 1266 and not self._peek == end 1267 ): 1268 if self.HEREDOC_STRING_ALTERNATIVE != token_type.VAR: 1269 self._add(self.HEREDOC_STRING_ALTERNATIVE) 1270 else: 1271 self._scan_var() 1272 1273 return True 1274 1275 self._advance() 1276 tag = "" if self._char == end else self._extract_string(end) 1277 end = f"{start}{tag}{end}" 1278 else: 1279 return False 1280 1281 self._advance(len(start)) 1282 text = self._extract_string(end) 1283 1284 if base: 1285 try: 1286 int(text, base) 1287 except Exception: 1288 raise TokenError( 1289 f"Numeric string contains invalid characters from {self._line}:{self._start}" 1290 ) 1291 1292 self._add(token_type, text) 1293 return True 1294 1295 def _scan_identifier(self, identifier_end: str) -> None: 1296 self._advance() 1297 text = self._extract_string(identifier_end, self._IDENTIFIER_ESCAPES) 1298 self._add(TokenType.IDENTIFIER, text) 1299 1300 def _scan_var(self) -> None: 1301 while True: 1302 char = self._peek.strip() 1303 if char and (char in self.VAR_SINGLE_TOKENS or char not in self.SINGLE_TOKENS): 1304 self._advance(alnum=True) 1305 else: 1306 break 1307 1308 self._add( 1309 TokenType.VAR 1310 if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER 1311 else self.KEYWORDS.get(self._text.upper(), TokenType.VAR) 1312 ) 1313 1314 def _extract_string(self, delimiter: str, escapes=None) -> str: 1315 text = "" 1316 delim_size = len(delimiter) 1317 escapes = self._STRING_ESCAPES if escapes is None else escapes 1318 1319 while True: 1320 if ( 1321 self._char in escapes 1322 and (self._peek == delimiter or self._peek in escapes) 1323 and (self._char not in self._QUOTES or self._char == self._peek) 1324 ): 1325 if self._peek == delimiter: 1326 text += self._peek 1327 else: 1328 text += self._char + self._peek 1329 1330 if self._current + 1 < self.size: 1331 self._advance(2) 1332 else: 1333 raise TokenError(f"Missing {delimiter} from {self._line}:{self._current}") 1334 else: 1335 if self._chars(delim_size) == delimiter: 1336 if delim_size > 1: 1337 self._advance(delim_size - 1) 1338 break 1339 1340 if self._end: 1341 raise TokenError(f"Missing {delimiter} from {self._line}:{self._start}") 1342 1343 if ( 1344 self.dialect.ESCAPE_SEQUENCES 1345 and self._peek 1346 and self._char in self.STRING_ESCAPES 1347 ): 1348 escaped_sequence = self.dialect.ESCAPE_SEQUENCES.get(self._char + self._peek) 1349 if escaped_sequence: 1350 self._advance(2) 1351 text += escaped_sequence 1352 continue 1353 1354 current = self._current - 1 1355 self._advance(alnum=True) 1356 text += self.sql[current : self._current - 1] 1357 1358 return text 1359 1360 def tokenize_rs(self, sql: str) -> t.List[Token]: 1361 if not self._RS_TOKENIZER: 1362 raise SqlglotError("Rust tokenizer is not available") 1363 1364 try: 1365 tokens = self._RS_TOKENIZER.tokenize(sql, self._rs_dialect_settings) 1366 for token in tokens: 1367 token.token_type = _ALL_TOKEN_TYPES[token.token_type_index] 1368 return tokens 1369 except Exception as e: 1370 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 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 PRIMARY_KEY = auto() 322 PROCEDURE = auto() 323 PROPERTIES = auto() 324 PSEUDO_TYPE = auto() 325 QUALIFY = auto() 326 QUOTE = auto() 327 RANGE = auto() 328 RECURSIVE = auto() 329 REFRESH = auto() 330 REPLACE = auto() 331 RETURNING = auto() 332 REFERENCES = auto() 333 RIGHT = auto() 334 RLIKE = auto() 335 ROLLBACK = auto() 336 ROLLUP = auto() 337 ROW = auto() 338 ROWS = auto() 339 SELECT = auto() 340 SEMI = auto() 341 SEPARATOR = auto() 342 SERDE_PROPERTIES = auto() 343 SET = auto() 344 SETTINGS = auto() 345 SHOW = auto() 346 SIMILAR_TO = auto() 347 SOME = auto() 348 SORT_BY = auto() 349 START_WITH = auto() 350 STORAGE_INTEGRATION = auto() 351 STRUCT = auto() 352 TABLE_SAMPLE = auto() 353 TEMPORARY = auto() 354 TOP = auto() 355 THEN = auto() 356 TRUE = auto() 357 UNCACHE = auto() 358 UNION = auto() 359 UNNEST = auto() 360 UNPIVOT = auto() 361 UPDATE = auto() 362 USE = auto() 363 USING = auto() 364 VALUES = auto() 365 VIEW = auto() 366 VOLATILE = auto() 367 WHEN = auto() 368 WHERE = auto() 369 WINDOW = auto() 370 WITH = auto() 371 UNIQUE = auto() 372 VERSION_SNAPSHOT = auto() 373 TIMESTAMP_SNAPSHOT = auto()
An enumeration.
L_PAREN =
<TokenType.L_PAREN: 'L_PAREN'>
R_PAREN =
<TokenType.R_PAREN: 'R_PAREN'>
L_BRACKET =
<TokenType.L_BRACKET: 'L_BRACKET'>
R_BRACKET =
<TokenType.R_BRACKET: 'R_BRACKET'>
L_BRACE =
<TokenType.L_BRACE: 'L_BRACE'>
R_BRACE =
<TokenType.R_BRACE: 'R_BRACE'>
COMMA =
<TokenType.COMMA: 'COMMA'>
DOT =
<TokenType.DOT: 'DOT'>
DASH =
<TokenType.DASH: 'DASH'>
PLUS =
<TokenType.PLUS: 'PLUS'>
COLON =
<TokenType.COLON: 'COLON'>
DCOLON =
<TokenType.DCOLON: 'DCOLON'>
DQMARK =
<TokenType.DQMARK: 'DQMARK'>
SEMICOLON =
<TokenType.SEMICOLON: 'SEMICOLON'>
STAR =
<TokenType.STAR: 'STAR'>
BACKSLASH =
<TokenType.BACKSLASH: 'BACKSLASH'>
SLASH =
<TokenType.SLASH: 'SLASH'>
LT =
<TokenType.LT: 'LT'>
LTE =
<TokenType.LTE: 'LTE'>
GT =
<TokenType.GT: 'GT'>
GTE =
<TokenType.GTE: 'GTE'>
NOT =
<TokenType.NOT: 'NOT'>
EQ =
<TokenType.EQ: 'EQ'>
NEQ =
<TokenType.NEQ: 'NEQ'>
NULLSAFE_EQ =
<TokenType.NULLSAFE_EQ: 'NULLSAFE_EQ'>
COLON_EQ =
<TokenType.COLON_EQ: 'COLON_EQ'>
AND =
<TokenType.AND: 'AND'>
OR =
<TokenType.OR: 'OR'>
AMP =
<TokenType.AMP: 'AMP'>
DPIPE =
<TokenType.DPIPE: 'DPIPE'>
PIPE =
<TokenType.PIPE: 'PIPE'>
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'>
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'>
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'>
UNCACHE =
<TokenType.UNCACHE: 'UNCACHE'>
UNION =
<TokenType.UNION: 'UNION'>
UNNEST =
<TokenType.UNNEST: 'UNNEST'>
UNPIVOT =
<TokenType.UNPIVOT: 'UNPIVOT'>
UPDATE =
<TokenType.UPDATE: 'UPDATE'>
USE =
<TokenType.USE: 'USE'>
USING =
<TokenType.USING: 'USING'>
VALUES =
<TokenType.VALUES: 'VALUES'>
VIEW =
<TokenType.VIEW: 'VIEW'>
VOLATILE =
<TokenType.VOLATILE: 'VOLATILE'>
WHEN =
<TokenType.WHEN: 'WHEN'>
WHERE =
<TokenType.WHERE: 'WHERE'>
WINDOW =
<TokenType.WINDOW: 'WINDOW'>
WITH =
<TokenType.WITH: 'WITH'>
UNIQUE =
<TokenType.UNIQUE: 'UNIQUE'>
VERSION_SNAPSHOT =
<TokenType.VERSION_SNAPSHOT: 'VERSION_SNAPSHOT'>
TIMESTAMP_SNAPSHOT =
<TokenType.TIMESTAMP_SNAPSHOT: 'TIMESTAMP_SNAPSHOT'>
Inherited Members
- enum.Enum
- name
- value
class
Token:
380class Token: 381 __slots__ = ("token_type", "text", "line", "col", "start", "end", "comments") 382 383 @classmethod 384 def number(cls, number: int) -> Token: 385 """Returns a NUMBER token with `number` as its text.""" 386 return cls(TokenType.NUMBER, str(number)) 387 388 @classmethod 389 def string(cls, string: str) -> Token: 390 """Returns a STRING token with `string` as its text.""" 391 return cls(TokenType.STRING, string) 392 393 @classmethod 394 def identifier(cls, identifier: str) -> Token: 395 """Returns an IDENTIFIER token with `identifier` as its text.""" 396 return cls(TokenType.IDENTIFIER, identifier) 397 398 @classmethod 399 def var(cls, var: str) -> Token: 400 """Returns an VAR token with `var` as its text.""" 401 return cls(TokenType.VAR, var) 402 403 def __init__( 404 self, 405 token_type: TokenType, 406 text: str, 407 line: int = 1, 408 col: int = 1, 409 start: int = 0, 410 end: int = 0, 411 comments: t.Optional[t.List[str]] = None, 412 ) -> None: 413 """Token initializer. 414 415 Args: 416 token_type: The TokenType Enum. 417 text: The text of the token. 418 line: The line that the token ends on. 419 col: The column that the token ends on. 420 start: The start index of the token. 421 end: The ending index of the token. 422 comments: The comments to attach to the token. 423 """ 424 self.token_type = token_type 425 self.text = text 426 self.line = line 427 self.col = col 428 self.start = start 429 self.end = end 430 self.comments = [] if comments is None else comments 431 432 def __repr__(self) -> str: 433 attributes = ", ".join(f"{k}: {getattr(self, k)}" for k in self.__slots__) 434 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)
403 def __init__( 404 self, 405 token_type: TokenType, 406 text: str, 407 line: int = 1, 408 col: int = 1, 409 start: int = 0, 410 end: int = 0, 411 comments: t.Optional[t.List[str]] = None, 412 ) -> None: 413 """Token initializer. 414 415 Args: 416 token_type: The TokenType Enum. 417 text: The text of the token. 418 line: The line that the token ends on. 419 col: The column that the token ends on. 420 start: The start index of the token. 421 end: The ending index of the token. 422 comments: The comments to attach to the token. 423 """ 424 self.token_type = token_type 425 self.text = text 426 self.line = line 427 self.col = col 428 self.start = start 429 self.end = end 430 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.
383 @classmethod 384 def number(cls, number: int) -> Token: 385 """Returns a NUMBER token with `number` as its text.""" 386 return cls(TokenType.NUMBER, str(number))
Returns a NUMBER token with number
as its text.
388 @classmethod 389 def string(cls, string: str) -> Token: 390 """Returns a STRING token with `string` as its text.""" 391 return cls(TokenType.STRING, string)
Returns a STRING token with string
as its text.
393 @classmethod 394 def identifier(cls, identifier: str) -> Token: 395 """Returns an IDENTIFIER token with `identifier` as its text.""" 396 return cls(TokenType.IDENTIFIER, identifier)
Returns an IDENTIFIER token with identifier
as its text.
class
Tokenizer:
534class Tokenizer(metaclass=_Tokenizer): 535 SINGLE_TOKENS = { 536 "(": TokenType.L_PAREN, 537 ")": TokenType.R_PAREN, 538 "[": TokenType.L_BRACKET, 539 "]": TokenType.R_BRACKET, 540 "{": TokenType.L_BRACE, 541 "}": TokenType.R_BRACE, 542 "&": TokenType.AMP, 543 "^": TokenType.CARET, 544 ":": TokenType.COLON, 545 ",": TokenType.COMMA, 546 ".": TokenType.DOT, 547 "-": TokenType.DASH, 548 "=": TokenType.EQ, 549 ">": TokenType.GT, 550 "<": TokenType.LT, 551 "%": TokenType.MOD, 552 "!": TokenType.NOT, 553 "|": TokenType.PIPE, 554 "+": TokenType.PLUS, 555 ";": TokenType.SEMICOLON, 556 "/": TokenType.SLASH, 557 "\\": TokenType.BACKSLASH, 558 "*": TokenType.STAR, 559 "~": TokenType.TILDA, 560 "?": TokenType.PLACEHOLDER, 561 "@": TokenType.PARAMETER, 562 # used for breaking a var like x'y' but nothing else 563 # the token type doesn't matter 564 "'": TokenType.QUOTE, 565 "`": TokenType.IDENTIFIER, 566 '"': TokenType.IDENTIFIER, 567 "#": TokenType.HASH, 568 } 569 570 BIT_STRINGS: t.List[str | t.Tuple[str, str]] = [] 571 BYTE_STRINGS: t.List[str | t.Tuple[str, str]] = [] 572 HEX_STRINGS: t.List[str | t.Tuple[str, str]] = [] 573 RAW_STRINGS: t.List[str | t.Tuple[str, str]] = [] 574 HEREDOC_STRINGS: t.List[str | t.Tuple[str, str]] = [] 575 UNICODE_STRINGS: t.List[str | t.Tuple[str, str]] = [] 576 IDENTIFIERS: t.List[str | t.Tuple[str, str]] = ['"'] 577 IDENTIFIER_ESCAPES = ['"'] 578 QUOTES: t.List[t.Tuple[str, str] | str] = ["'"] 579 STRING_ESCAPES = ["'"] 580 VAR_SINGLE_TOKENS: t.Set[str] = set() 581 582 # Whether the heredoc tags follow the same lexical rules as unquoted identifiers 583 HEREDOC_TAG_IS_IDENTIFIER = False 584 585 # Token that we'll generate as a fallback if the heredoc prefix doesn't correspond to a heredoc 586 HEREDOC_STRING_ALTERNATIVE = TokenType.VAR 587 588 # Autofilled 589 _COMMENTS: t.Dict[str, str] = {} 590 _FORMAT_STRINGS: t.Dict[str, t.Tuple[str, TokenType]] = {} 591 _IDENTIFIERS: t.Dict[str, str] = {} 592 _IDENTIFIER_ESCAPES: t.Set[str] = set() 593 _QUOTES: t.Dict[str, str] = {} 594 _STRING_ESCAPES: t.Set[str] = set() 595 _KEYWORD_TRIE: t.Dict = {} 596 _RS_TOKENIZER: t.Optional[t.Any] = None 597 598 KEYWORDS: t.Dict[str, TokenType] = { 599 **{f"{{%{postfix}": TokenType.BLOCK_START for postfix in ("", "+", "-")}, 600 **{f"{prefix}%}}": TokenType.BLOCK_END for prefix in ("", "+", "-")}, 601 **{f"{{{{{postfix}": TokenType.BLOCK_START for postfix in ("+", "-")}, 602 **{f"{prefix}}}}}": TokenType.BLOCK_END for prefix in ("+", "-")}, 603 "/*+": TokenType.HINT, 604 "==": TokenType.EQ, 605 "::": TokenType.DCOLON, 606 "||": TokenType.DPIPE, 607 ">=": TokenType.GTE, 608 "<=": TokenType.LTE, 609 "<>": TokenType.NEQ, 610 "!=": TokenType.NEQ, 611 ":=": TokenType.COLON_EQ, 612 "<=>": TokenType.NULLSAFE_EQ, 613 "->": TokenType.ARROW, 614 "->>": TokenType.DARROW, 615 "=>": TokenType.FARROW, 616 "#>": TokenType.HASH_ARROW, 617 "#>>": TokenType.DHASH_ARROW, 618 "<->": TokenType.LR_ARROW, 619 "&&": TokenType.DAMP, 620 "??": TokenType.DQMARK, 621 "ALL": TokenType.ALL, 622 "ALWAYS": TokenType.ALWAYS, 623 "AND": TokenType.AND, 624 "ANTI": TokenType.ANTI, 625 "ANY": TokenType.ANY, 626 "ASC": TokenType.ASC, 627 "AS": TokenType.ALIAS, 628 "ASOF": TokenType.ASOF, 629 "AUTOINCREMENT": TokenType.AUTO_INCREMENT, 630 "AUTO_INCREMENT": TokenType.AUTO_INCREMENT, 631 "BEGIN": TokenType.BEGIN, 632 "BETWEEN": TokenType.BETWEEN, 633 "CACHE": TokenType.CACHE, 634 "UNCACHE": TokenType.UNCACHE, 635 "CASE": TokenType.CASE, 636 "CHARACTER SET": TokenType.CHARACTER_SET, 637 "CLUSTER BY": TokenType.CLUSTER_BY, 638 "COLLATE": TokenType.COLLATE, 639 "COLUMN": TokenType.COLUMN, 640 "COMMIT": TokenType.COMMIT, 641 "CONNECT BY": TokenType.CONNECT_BY, 642 "CONSTRAINT": TokenType.CONSTRAINT, 643 "CREATE": TokenType.CREATE, 644 "CROSS": TokenType.CROSS, 645 "CUBE": TokenType.CUBE, 646 "CURRENT_DATE": TokenType.CURRENT_DATE, 647 "CURRENT_TIME": TokenType.CURRENT_TIME, 648 "CURRENT_TIMESTAMP": TokenType.CURRENT_TIMESTAMP, 649 "CURRENT_USER": TokenType.CURRENT_USER, 650 "DATABASE": TokenType.DATABASE, 651 "DEFAULT": TokenType.DEFAULT, 652 "DELETE": TokenType.DELETE, 653 "DESC": TokenType.DESC, 654 "DESCRIBE": TokenType.DESCRIBE, 655 "DISTINCT": TokenType.DISTINCT, 656 "DISTRIBUTE BY": TokenType.DISTRIBUTE_BY, 657 "DIV": TokenType.DIV, 658 "DROP": TokenType.DROP, 659 "ELSE": TokenType.ELSE, 660 "END": TokenType.END, 661 "ESCAPE": TokenType.ESCAPE, 662 "EXCEPT": TokenType.EXCEPT, 663 "EXECUTE": TokenType.EXECUTE, 664 "EXISTS": TokenType.EXISTS, 665 "FALSE": TokenType.FALSE, 666 "FETCH": TokenType.FETCH, 667 "FILTER": TokenType.FILTER, 668 "FIRST": TokenType.FIRST, 669 "FULL": TokenType.FULL, 670 "FUNCTION": TokenType.FUNCTION, 671 "FOR": TokenType.FOR, 672 "FOREIGN KEY": TokenType.FOREIGN_KEY, 673 "FORMAT": TokenType.FORMAT, 674 "FROM": TokenType.FROM, 675 "GEOGRAPHY": TokenType.GEOGRAPHY, 676 "GEOMETRY": TokenType.GEOMETRY, 677 "GLOB": TokenType.GLOB, 678 "GROUP BY": TokenType.GROUP_BY, 679 "GROUPING SETS": TokenType.GROUPING_SETS, 680 "HAVING": TokenType.HAVING, 681 "ILIKE": TokenType.ILIKE, 682 "IN": TokenType.IN, 683 "INDEX": TokenType.INDEX, 684 "INET": TokenType.INET, 685 "INNER": TokenType.INNER, 686 "INSERT": TokenType.INSERT, 687 "INTERVAL": TokenType.INTERVAL, 688 "INTERSECT": TokenType.INTERSECT, 689 "INTO": TokenType.INTO, 690 "IS": TokenType.IS, 691 "ISNULL": TokenType.ISNULL, 692 "JOIN": TokenType.JOIN, 693 "KEEP": TokenType.KEEP, 694 "KILL": TokenType.KILL, 695 "LATERAL": TokenType.LATERAL, 696 "LEFT": TokenType.LEFT, 697 "LIKE": TokenType.LIKE, 698 "LIMIT": TokenType.LIMIT, 699 "LOAD": TokenType.LOAD, 700 "LOCK": TokenType.LOCK, 701 "MERGE": TokenType.MERGE, 702 "NATURAL": TokenType.NATURAL, 703 "NEXT": TokenType.NEXT, 704 "NOT": TokenType.NOT, 705 "NOTNULL": TokenType.NOTNULL, 706 "NULL": TokenType.NULL, 707 "OBJECT": TokenType.OBJECT, 708 "OFFSET": TokenType.OFFSET, 709 "ON": TokenType.ON, 710 "OR": TokenType.OR, 711 "XOR": TokenType.XOR, 712 "ORDER BY": TokenType.ORDER_BY, 713 "ORDINALITY": TokenType.ORDINALITY, 714 "OUTER": TokenType.OUTER, 715 "OVER": TokenType.OVER, 716 "OVERLAPS": TokenType.OVERLAPS, 717 "OVERWRITE": TokenType.OVERWRITE, 718 "PARTITION": TokenType.PARTITION, 719 "PARTITION BY": TokenType.PARTITION_BY, 720 "PARTITIONED BY": TokenType.PARTITION_BY, 721 "PARTITIONED_BY": TokenType.PARTITION_BY, 722 "PERCENT": TokenType.PERCENT, 723 "PIVOT": TokenType.PIVOT, 724 "PRAGMA": TokenType.PRAGMA, 725 "PRIMARY KEY": TokenType.PRIMARY_KEY, 726 "PROCEDURE": TokenType.PROCEDURE, 727 "QUALIFY": TokenType.QUALIFY, 728 "RANGE": TokenType.RANGE, 729 "RECURSIVE": TokenType.RECURSIVE, 730 "REGEXP": TokenType.RLIKE, 731 "REPLACE": TokenType.REPLACE, 732 "RETURNING": TokenType.RETURNING, 733 "REFERENCES": TokenType.REFERENCES, 734 "RIGHT": TokenType.RIGHT, 735 "RLIKE": TokenType.RLIKE, 736 "ROLLBACK": TokenType.ROLLBACK, 737 "ROLLUP": TokenType.ROLLUP, 738 "ROW": TokenType.ROW, 739 "ROWS": TokenType.ROWS, 740 "SCHEMA": TokenType.SCHEMA, 741 "SELECT": TokenType.SELECT, 742 "SEMI": TokenType.SEMI, 743 "SET": TokenType.SET, 744 "SETTINGS": TokenType.SETTINGS, 745 "SHOW": TokenType.SHOW, 746 "SIMILAR TO": TokenType.SIMILAR_TO, 747 "SOME": TokenType.SOME, 748 "SORT BY": TokenType.SORT_BY, 749 "START WITH": TokenType.START_WITH, 750 "TABLE": TokenType.TABLE, 751 "TABLESAMPLE": TokenType.TABLE_SAMPLE, 752 "TEMP": TokenType.TEMPORARY, 753 "TEMPORARY": TokenType.TEMPORARY, 754 "THEN": TokenType.THEN, 755 "TRUE": TokenType.TRUE, 756 "UNION": TokenType.UNION, 757 "UNKNOWN": TokenType.UNKNOWN, 758 "UNNEST": TokenType.UNNEST, 759 "UNPIVOT": TokenType.UNPIVOT, 760 "UPDATE": TokenType.UPDATE, 761 "USE": TokenType.USE, 762 "USING": TokenType.USING, 763 "UUID": TokenType.UUID, 764 "VALUES": TokenType.VALUES, 765 "VIEW": TokenType.VIEW, 766 "VOLATILE": TokenType.VOLATILE, 767 "WHEN": TokenType.WHEN, 768 "WHERE": TokenType.WHERE, 769 "WINDOW": TokenType.WINDOW, 770 "WITH": TokenType.WITH, 771 "APPLY": TokenType.APPLY, 772 "ARRAY": TokenType.ARRAY, 773 "BIT": TokenType.BIT, 774 "BOOL": TokenType.BOOLEAN, 775 "BOOLEAN": TokenType.BOOLEAN, 776 "BYTE": TokenType.TINYINT, 777 "MEDIUMINT": TokenType.MEDIUMINT, 778 "INT1": TokenType.TINYINT, 779 "TINYINT": TokenType.TINYINT, 780 "INT16": TokenType.SMALLINT, 781 "SHORT": TokenType.SMALLINT, 782 "SMALLINT": TokenType.SMALLINT, 783 "INT128": TokenType.INT128, 784 "HUGEINT": TokenType.INT128, 785 "INT2": TokenType.SMALLINT, 786 "INTEGER": TokenType.INT, 787 "INT": TokenType.INT, 788 "INT4": TokenType.INT, 789 "INT32": TokenType.INT, 790 "INT64": TokenType.BIGINT, 791 "LONG": TokenType.BIGINT, 792 "BIGINT": TokenType.BIGINT, 793 "INT8": TokenType.TINYINT, 794 "DEC": TokenType.DECIMAL, 795 "DECIMAL": TokenType.DECIMAL, 796 "BIGDECIMAL": TokenType.BIGDECIMAL, 797 "BIGNUMERIC": TokenType.BIGDECIMAL, 798 "MAP": TokenType.MAP, 799 "NULLABLE": TokenType.NULLABLE, 800 "NUMBER": TokenType.DECIMAL, 801 "NUMERIC": TokenType.DECIMAL, 802 "FIXED": TokenType.DECIMAL, 803 "REAL": TokenType.FLOAT, 804 "FLOAT": TokenType.FLOAT, 805 "FLOAT4": TokenType.FLOAT, 806 "FLOAT8": TokenType.DOUBLE, 807 "DOUBLE": TokenType.DOUBLE, 808 "DOUBLE PRECISION": TokenType.DOUBLE, 809 "JSON": TokenType.JSON, 810 "CHAR": TokenType.CHAR, 811 "CHARACTER": TokenType.CHAR, 812 "NCHAR": TokenType.NCHAR, 813 "VARCHAR": TokenType.VARCHAR, 814 "VARCHAR2": TokenType.VARCHAR, 815 "NVARCHAR": TokenType.NVARCHAR, 816 "NVARCHAR2": TokenType.NVARCHAR, 817 "BPCHAR": TokenType.BPCHAR, 818 "STR": TokenType.TEXT, 819 "STRING": TokenType.TEXT, 820 "TEXT": TokenType.TEXT, 821 "LONGTEXT": TokenType.LONGTEXT, 822 "MEDIUMTEXT": TokenType.MEDIUMTEXT, 823 "TINYTEXT": TokenType.TINYTEXT, 824 "CLOB": TokenType.TEXT, 825 "LONGVARCHAR": TokenType.TEXT, 826 "BINARY": TokenType.BINARY, 827 "BLOB": TokenType.VARBINARY, 828 "LONGBLOB": TokenType.LONGBLOB, 829 "MEDIUMBLOB": TokenType.MEDIUMBLOB, 830 "TINYBLOB": TokenType.TINYBLOB, 831 "BYTEA": TokenType.VARBINARY, 832 "VARBINARY": TokenType.VARBINARY, 833 "TIME": TokenType.TIME, 834 "TIMETZ": TokenType.TIMETZ, 835 "TIMESTAMP": TokenType.TIMESTAMP, 836 "TIMESTAMPTZ": TokenType.TIMESTAMPTZ, 837 "TIMESTAMPLTZ": TokenType.TIMESTAMPLTZ, 838 "DATE": TokenType.DATE, 839 "DATETIME": TokenType.DATETIME, 840 "INT4RANGE": TokenType.INT4RANGE, 841 "INT4MULTIRANGE": TokenType.INT4MULTIRANGE, 842 "INT8RANGE": TokenType.INT8RANGE, 843 "INT8MULTIRANGE": TokenType.INT8MULTIRANGE, 844 "NUMRANGE": TokenType.NUMRANGE, 845 "NUMMULTIRANGE": TokenType.NUMMULTIRANGE, 846 "TSRANGE": TokenType.TSRANGE, 847 "TSMULTIRANGE": TokenType.TSMULTIRANGE, 848 "TSTZRANGE": TokenType.TSTZRANGE, 849 "TSTZMULTIRANGE": TokenType.TSTZMULTIRANGE, 850 "DATERANGE": TokenType.DATERANGE, 851 "DATEMULTIRANGE": TokenType.DATEMULTIRANGE, 852 "UNIQUE": TokenType.UNIQUE, 853 "STRUCT": TokenType.STRUCT, 854 "VARIANT": TokenType.VARIANT, 855 "ALTER": TokenType.ALTER, 856 "ANALYZE": TokenType.COMMAND, 857 "CALL": TokenType.COMMAND, 858 "COMMENT": TokenType.COMMENT, 859 "COPY": TokenType.COMMAND, 860 "EXPLAIN": TokenType.COMMAND, 861 "GRANT": TokenType.COMMAND, 862 "OPTIMIZE": TokenType.COMMAND, 863 "PREPARE": TokenType.COMMAND, 864 "TRUNCATE": TokenType.COMMAND, 865 "VACUUM": TokenType.COMMAND, 866 "USER-DEFINED": TokenType.USERDEFINED, 867 "FOR VERSION": TokenType.VERSION_SNAPSHOT, 868 "FOR TIMESTAMP": TokenType.TIMESTAMP_SNAPSHOT, 869 } 870 871 WHITE_SPACE: t.Dict[t.Optional[str], TokenType] = { 872 " ": TokenType.SPACE, 873 "\t": TokenType.SPACE, 874 "\n": TokenType.BREAK, 875 "\r": TokenType.BREAK, 876 } 877 878 COMMANDS = { 879 TokenType.COMMAND, 880 TokenType.EXECUTE, 881 TokenType.FETCH, 882 TokenType.SHOW, 883 } 884 885 COMMAND_PREFIX_TOKENS = {TokenType.SEMICOLON, TokenType.BEGIN} 886 887 # handle numeric literals like in hive (3L = BIGINT) 888 NUMERIC_LITERALS: t.Dict[str, str] = {} 889 890 COMMENTS = ["--", ("/*", "*/")] 891 892 __slots__ = ( 893 "sql", 894 "size", 895 "tokens", 896 "dialect", 897 "_start", 898 "_current", 899 "_line", 900 "_col", 901 "_comments", 902 "_char", 903 "_end", 904 "_peek", 905 "_prev_token_line", 906 "_rs_dialect_settings", 907 ) 908 909 def __init__(self, dialect: DialectType = None) -> None: 910 from sqlglot.dialects import Dialect 911 912 self.dialect = Dialect.get_or_raise(dialect) 913 914 if USE_RS_TOKENIZER: 915 self._rs_dialect_settings = RsTokenizerDialectSettings( 916 escape_sequences=self.dialect.ESCAPE_SEQUENCES, 917 identifiers_can_start_with_digit=self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT, 918 ) 919 920 self.reset() 921 922 def reset(self) -> None: 923 self.sql = "" 924 self.size = 0 925 self.tokens: t.List[Token] = [] 926 self._start = 0 927 self._current = 0 928 self._line = 1 929 self._col = 0 930 self._comments: t.List[str] = [] 931 932 self._char = "" 933 self._end = False 934 self._peek = "" 935 self._prev_token_line = -1 936 937 def tokenize(self, sql: str) -> t.List[Token]: 938 """Returns a list of tokens corresponding to the SQL string `sql`.""" 939 if USE_RS_TOKENIZER: 940 return self.tokenize_rs(sql) 941 942 self.reset() 943 self.sql = sql 944 self.size = len(sql) 945 946 try: 947 self._scan() 948 except Exception as e: 949 start = max(self._current - 50, 0) 950 end = min(self._current + 50, self.size - 1) 951 context = self.sql[start:end] 952 raise TokenError(f"Error tokenizing '{context}'") from e 953 954 return self.tokens 955 956 def _scan(self, until: t.Optional[t.Callable] = None) -> None: 957 while self.size and not self._end: 958 current = self._current 959 960 # skip spaces inline rather than iteratively call advance() 961 # for performance reasons 962 while current < self.size: 963 char = self.sql[current] 964 965 if char.isspace() and (char == " " or char == "\t"): 966 current += 1 967 else: 968 break 969 970 n = current - self._current 971 self._start = current 972 self._advance(n if n > 1 else 1) 973 974 if self._char is None: 975 break 976 977 if not self._char.isspace(): 978 if self._char.isdigit(): 979 self._scan_number() 980 elif self._char in self._IDENTIFIERS: 981 self._scan_identifier(self._IDENTIFIERS[self._char]) 982 else: 983 self._scan_keywords() 984 985 if until and until(): 986 break 987 988 if self.tokens and self._comments: 989 self.tokens[-1].comments.extend(self._comments) 990 991 def _chars(self, size: int) -> str: 992 if size == 1: 993 return self._char 994 995 start = self._current - 1 996 end = start + size 997 998 return self.sql[start:end] if end <= self.size else "" 999 1000 def _advance(self, i: int = 1, alnum: bool = False) -> None: 1001 if self.WHITE_SPACE.get(self._char) is TokenType.BREAK: 1002 # Ensures we don't count an extra line if we get a \r\n line break sequence 1003 if self._char == "\r" and self._peek == "\n": 1004 i = 2 1005 self._start += 1 1006 1007 self._col = 1 1008 self._line += 1 1009 else: 1010 self._col += i 1011 1012 self._current += i 1013 self._end = self._current >= self.size 1014 self._char = self.sql[self._current - 1] 1015 self._peek = "" if self._end else self.sql[self._current] 1016 1017 if alnum and self._char.isalnum(): 1018 # Here we use local variables instead of attributes for better performance 1019 _col = self._col 1020 _current = self._current 1021 _end = self._end 1022 _peek = self._peek 1023 1024 while _peek.isalnum(): 1025 _col += 1 1026 _current += 1 1027 _end = _current >= self.size 1028 _peek = "" if _end else self.sql[_current] 1029 1030 self._col = _col 1031 self._current = _current 1032 self._end = _end 1033 self._peek = _peek 1034 self._char = self.sql[_current - 1] 1035 1036 @property 1037 def _text(self) -> str: 1038 return self.sql[self._start : self._current] 1039 1040 def peek(self, i: int = 0) -> str: 1041 i = self._current + i 1042 if i < self.size: 1043 return self.sql[i] 1044 return "" 1045 1046 def _add(self, token_type: TokenType, text: t.Optional[str] = None) -> None: 1047 self._prev_token_line = self._line 1048 1049 if self._comments and token_type == TokenType.SEMICOLON and self.tokens: 1050 self.tokens[-1].comments.extend(self._comments) 1051 self._comments = [] 1052 1053 self.tokens.append( 1054 Token( 1055 token_type, 1056 text=self._text if text is None else text, 1057 line=self._line, 1058 col=self._col, 1059 start=self._start, 1060 end=self._current - 1, 1061 comments=self._comments, 1062 ) 1063 ) 1064 self._comments = [] 1065 1066 # If we have either a semicolon or a begin token before the command's token, we'll parse 1067 # whatever follows the command's token as a string 1068 if ( 1069 token_type in self.COMMANDS 1070 and self._peek != ";" 1071 and (len(self.tokens) == 1 or self.tokens[-2].token_type in self.COMMAND_PREFIX_TOKENS) 1072 ): 1073 start = self._current 1074 tokens = len(self.tokens) 1075 self._scan(lambda: self._peek == ";") 1076 self.tokens = self.tokens[:tokens] 1077 text = self.sql[start : self._current].strip() 1078 if text: 1079 self._add(TokenType.STRING, text) 1080 1081 def _scan_keywords(self) -> None: 1082 size = 0 1083 word = None 1084 chars = self._text 1085 char = chars 1086 prev_space = False 1087 skip = False 1088 trie = self._KEYWORD_TRIE 1089 single_token = char in self.SINGLE_TOKENS 1090 1091 while chars: 1092 if skip: 1093 result = TrieResult.PREFIX 1094 else: 1095 result, trie = in_trie(trie, char.upper()) 1096 1097 if result == TrieResult.FAILED: 1098 break 1099 if result == TrieResult.EXISTS: 1100 word = chars 1101 1102 end = self._current + size 1103 size += 1 1104 1105 if end < self.size: 1106 char = self.sql[end] 1107 single_token = single_token or char in self.SINGLE_TOKENS 1108 is_space = char.isspace() 1109 1110 if not is_space or not prev_space: 1111 if is_space: 1112 char = " " 1113 chars += char 1114 prev_space = is_space 1115 skip = False 1116 else: 1117 skip = True 1118 else: 1119 char = "" 1120 break 1121 1122 if word: 1123 if self._scan_string(word): 1124 return 1125 if self._scan_comment(word): 1126 return 1127 if prev_space or single_token or not char: 1128 self._advance(size - 1) 1129 word = word.upper() 1130 self._add(self.KEYWORDS[word], text=word) 1131 return 1132 1133 if self._char in self.SINGLE_TOKENS: 1134 self._add(self.SINGLE_TOKENS[self._char], text=self._char) 1135 return 1136 1137 self._scan_var() 1138 1139 def _scan_comment(self, comment_start: str) -> bool: 1140 if comment_start not in self._COMMENTS: 1141 return False 1142 1143 comment_start_line = self._line 1144 comment_start_size = len(comment_start) 1145 comment_end = self._COMMENTS[comment_start] 1146 1147 if comment_end: 1148 # Skip the comment's start delimiter 1149 self._advance(comment_start_size) 1150 1151 comment_end_size = len(comment_end) 1152 while not self._end and self._chars(comment_end_size) != comment_end: 1153 self._advance(alnum=True) 1154 1155 self._comments.append(self._text[comment_start_size : -comment_end_size + 1]) 1156 self._advance(comment_end_size - 1) 1157 else: 1158 while not self._end and self.WHITE_SPACE.get(self._peek) is not TokenType.BREAK: 1159 self._advance(alnum=True) 1160 self._comments.append(self._text[comment_start_size:]) 1161 1162 # Leading comment is attached to the succeeding token, whilst trailing comment to the preceding. 1163 # Multiple consecutive comments are preserved by appending them to the current comments list. 1164 if comment_start_line == self._prev_token_line: 1165 self.tokens[-1].comments.extend(self._comments) 1166 self._comments = [] 1167 self._prev_token_line = self._line 1168 1169 return True 1170 1171 def _scan_number(self) -> None: 1172 if self._char == "0": 1173 peek = self._peek.upper() 1174 if peek == "B": 1175 return self._scan_bits() if self.BIT_STRINGS else self._add(TokenType.NUMBER) 1176 elif peek == "X": 1177 return self._scan_hex() if self.HEX_STRINGS else self._add(TokenType.NUMBER) 1178 1179 decimal = False 1180 scientific = 0 1181 1182 while True: 1183 if self._peek.isdigit(): 1184 self._advance() 1185 elif self._peek == "." and not decimal: 1186 after = self.peek(1) 1187 if after.isdigit() or not after.isalpha(): 1188 decimal = True 1189 self._advance() 1190 else: 1191 return self._add(TokenType.VAR) 1192 elif self._peek in ("-", "+") and scientific == 1: 1193 scientific += 1 1194 self._advance() 1195 elif self._peek.upper() == "E" and not scientific: 1196 scientific += 1 1197 self._advance() 1198 elif self._peek.isidentifier(): 1199 number_text = self._text 1200 literal = "" 1201 1202 while self._peek.strip() and self._peek not in self.SINGLE_TOKENS: 1203 literal += self._peek 1204 self._advance() 1205 1206 token_type = self.KEYWORDS.get(self.NUMERIC_LITERALS.get(literal.upper(), "")) 1207 1208 if token_type: 1209 self._add(TokenType.NUMBER, number_text) 1210 self._add(TokenType.DCOLON, "::") 1211 return self._add(token_type, literal) 1212 elif self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT: 1213 return self._add(TokenType.VAR) 1214 1215 self._advance(-len(literal)) 1216 return self._add(TokenType.NUMBER, number_text) 1217 else: 1218 return self._add(TokenType.NUMBER) 1219 1220 def _scan_bits(self) -> None: 1221 self._advance() 1222 value = self._extract_value() 1223 try: 1224 # If `value` can't be converted to a binary, fallback to tokenizing it as an identifier 1225 int(value, 2) 1226 self._add(TokenType.BIT_STRING, value[2:]) # Drop the 0b 1227 except ValueError: 1228 self._add(TokenType.IDENTIFIER) 1229 1230 def _scan_hex(self) -> None: 1231 self._advance() 1232 value = self._extract_value() 1233 try: 1234 # If `value` can't be converted to a hex, fallback to tokenizing it as an identifier 1235 int(value, 16) 1236 self._add(TokenType.HEX_STRING, value[2:]) # Drop the 0x 1237 except ValueError: 1238 self._add(TokenType.IDENTIFIER) 1239 1240 def _extract_value(self) -> str: 1241 while True: 1242 char = self._peek.strip() 1243 if char and char not in self.SINGLE_TOKENS: 1244 self._advance(alnum=True) 1245 else: 1246 break 1247 1248 return self._text 1249 1250 def _scan_string(self, start: str) -> bool: 1251 base = None 1252 token_type = TokenType.STRING 1253 1254 if start in self._QUOTES: 1255 end = self._QUOTES[start] 1256 elif start in self._FORMAT_STRINGS: 1257 end, token_type = self._FORMAT_STRINGS[start] 1258 1259 if token_type == TokenType.HEX_STRING: 1260 base = 16 1261 elif token_type == TokenType.BIT_STRING: 1262 base = 2 1263 elif token_type == TokenType.HEREDOC_STRING: 1264 if ( 1265 self.HEREDOC_TAG_IS_IDENTIFIER 1266 and not self._peek.isidentifier() 1267 and not self._peek == end 1268 ): 1269 if self.HEREDOC_STRING_ALTERNATIVE != token_type.VAR: 1270 self._add(self.HEREDOC_STRING_ALTERNATIVE) 1271 else: 1272 self._scan_var() 1273 1274 return True 1275 1276 self._advance() 1277 tag = "" if self._char == end else self._extract_string(end) 1278 end = f"{start}{tag}{end}" 1279 else: 1280 return False 1281 1282 self._advance(len(start)) 1283 text = self._extract_string(end) 1284 1285 if base: 1286 try: 1287 int(text, base) 1288 except Exception: 1289 raise TokenError( 1290 f"Numeric string contains invalid characters from {self._line}:{self._start}" 1291 ) 1292 1293 self._add(token_type, text) 1294 return True 1295 1296 def _scan_identifier(self, identifier_end: str) -> None: 1297 self._advance() 1298 text = self._extract_string(identifier_end, self._IDENTIFIER_ESCAPES) 1299 self._add(TokenType.IDENTIFIER, text) 1300 1301 def _scan_var(self) -> None: 1302 while True: 1303 char = self._peek.strip() 1304 if char and (char in self.VAR_SINGLE_TOKENS or char not in self.SINGLE_TOKENS): 1305 self._advance(alnum=True) 1306 else: 1307 break 1308 1309 self._add( 1310 TokenType.VAR 1311 if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER 1312 else self.KEYWORDS.get(self._text.upper(), TokenType.VAR) 1313 ) 1314 1315 def _extract_string(self, delimiter: str, escapes=None) -> str: 1316 text = "" 1317 delim_size = len(delimiter) 1318 escapes = self._STRING_ESCAPES if escapes is None else escapes 1319 1320 while True: 1321 if ( 1322 self._char in escapes 1323 and (self._peek == delimiter or self._peek in escapes) 1324 and (self._char not in self._QUOTES or self._char == self._peek) 1325 ): 1326 if self._peek == delimiter: 1327 text += self._peek 1328 else: 1329 text += self._char + self._peek 1330 1331 if self._current + 1 < self.size: 1332 self._advance(2) 1333 else: 1334 raise TokenError(f"Missing {delimiter} from {self._line}:{self._current}") 1335 else: 1336 if self._chars(delim_size) == delimiter: 1337 if delim_size > 1: 1338 self._advance(delim_size - 1) 1339 break 1340 1341 if self._end: 1342 raise TokenError(f"Missing {delimiter} from {self._line}:{self._start}") 1343 1344 if ( 1345 self.dialect.ESCAPE_SEQUENCES 1346 and self._peek 1347 and self._char in self.STRING_ESCAPES 1348 ): 1349 escaped_sequence = self.dialect.ESCAPE_SEQUENCES.get(self._char + self._peek) 1350 if escaped_sequence: 1351 self._advance(2) 1352 text += escaped_sequence 1353 continue 1354 1355 current = self._current - 1 1356 self._advance(alnum=True) 1357 text += self.sql[current : self._current - 1] 1358 1359 return text 1360 1361 def tokenize_rs(self, sql: str) -> t.List[Token]: 1362 if not self._RS_TOKENIZER: 1363 raise SqlglotError("Rust tokenizer is not available") 1364 1365 try: 1366 tokens = self._RS_TOKENIZER.tokenize(sql, self._rs_dialect_settings) 1367 for token in tokens: 1368 token.token_type = _ALL_TOKEN_TYPES[token.token_type_index] 1369 return tokens 1370 except Exception as e: 1371 raise TokenError(str(e))
Tokenizer( dialect: Union[str, sqlglot.dialects.dialect.Dialect, Type[sqlglot.dialects.dialect.Dialect], NoneType] = None)
909 def __init__(self, dialect: DialectType = None) -> None: 910 from sqlglot.dialects import Dialect 911 912 self.dialect = Dialect.get_or_raise(dialect) 913 914 if USE_RS_TOKENIZER: 915 self._rs_dialect_settings = RsTokenizerDialectSettings( 916 escape_sequences=self.dialect.ESCAPE_SEQUENCES, 917 identifiers_can_start_with_digit=self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT, 918 ) 919 920 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'>, 'ESCAPE': <TokenType.ESCAPE: 'ESCAPE'>, 'EXCEPT': <TokenType.EXCEPT: 'EXCEPT'>, 'EXECUTE': <TokenType.EXECUTE: 'EXECUTE'>, 'EXISTS': <TokenType.EXISTS: 'EXISTS'>, 'FALSE': <TokenType.FALSE: 'FALSE'>, 'FETCH': <TokenType.FETCH: 'FETCH'>, 'FILTER': <TokenType.FILTER: 'FILTER'>, 'FIRST': <TokenType.FIRST: 'FIRST'>, 'FULL': <TokenType.FULL: 'FULL'>, 'FUNCTION': <TokenType.FUNCTION: 'FUNCTION'>, 'FOR': <TokenType.FOR: 'FOR'>, 'FOREIGN KEY': <TokenType.FOREIGN_KEY: 'FOREIGN_KEY'>, 'FORMAT': <TokenType.FORMAT: 'FORMAT'>, 'FROM': <TokenType.FROM: 'FROM'>, 'GEOGRAPHY': <TokenType.GEOGRAPHY: 'GEOGRAPHY'>, 'GEOMETRY': <TokenType.GEOMETRY: 'GEOMETRY'>, 'GLOB': <TokenType.GLOB: 'GLOB'>, 'GROUP BY': <TokenType.GROUP_BY: 'GROUP_BY'>, 'GROUPING SETS': <TokenType.GROUPING_SETS: 'GROUPING_SETS'>, 'HAVING': <TokenType.HAVING: 'HAVING'>, 'ILIKE': <TokenType.ILIKE: 'ILIKE'>, 'IN': <TokenType.IN: 'IN'>, 'INDEX': <TokenType.INDEX: 'INDEX'>, 'INET': <TokenType.INET: 'INET'>, 'INNER': <TokenType.INNER: 'INNER'>, 'INSERT': <TokenType.INSERT: 'INSERT'>, 'INTERVAL': <TokenType.INTERVAL: 'INTERVAL'>, 'INTERSECT': <TokenType.INTERSECT: 'INTERSECT'>, 'INTO': <TokenType.INTO: 'INTO'>, 'IS': <TokenType.IS: 'IS'>, 'ISNULL': <TokenType.ISNULL: 'ISNULL'>, 'JOIN': <TokenType.JOIN: 'JOIN'>, 'KEEP': <TokenType.KEEP: 'KEEP'>, 'KILL': <TokenType.KILL: 'KILL'>, 'LATERAL': <TokenType.LATERAL: 'LATERAL'>, 'LEFT': <TokenType.LEFT: 'LEFT'>, 'LIKE': <TokenType.LIKE: 'LIKE'>, 'LIMIT': <TokenType.LIMIT: 'LIMIT'>, 'LOAD': <TokenType.LOAD: 'LOAD'>, 'LOCK': <TokenType.LOCK: 'LOCK'>, 'MERGE': <TokenType.MERGE: 'MERGE'>, 'NATURAL': <TokenType.NATURAL: 'NATURAL'>, 'NEXT': <TokenType.NEXT: 'NEXT'>, 'NOT': <TokenType.NOT: 'NOT'>, 'NOTNULL': <TokenType.NOTNULL: 'NOTNULL'>, 'NULL': <TokenType.NULL: 'NULL'>, 'OBJECT': <TokenType.OBJECT: 'OBJECT'>, 'OFFSET': <TokenType.OFFSET: 'OFFSET'>, 'ON': <TokenType.ON: 'ON'>, 'OR': <TokenType.OR: 'OR'>, 'XOR': <TokenType.XOR: 'XOR'>, 'ORDER BY': <TokenType.ORDER_BY: 'ORDER_BY'>, 'ORDINALITY': <TokenType.ORDINALITY: 'ORDINALITY'>, 'OUTER': <TokenType.OUTER: 'OUTER'>, 'OVER': <TokenType.OVER: 'OVER'>, 'OVERLAPS': <TokenType.OVERLAPS: 'OVERLAPS'>, 'OVERWRITE': <TokenType.OVERWRITE: 'OVERWRITE'>, 'PARTITION': <TokenType.PARTITION: 'PARTITION'>, 'PARTITION BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PARTITIONED BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PARTITIONED_BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PERCENT': <TokenType.PERCENT: 'PERCENT'>, 'PIVOT': <TokenType.PIVOT: 'PIVOT'>, 'PRAGMA': <TokenType.PRAGMA: 'PRAGMA'>, 'PRIMARY KEY': <TokenType.PRIMARY_KEY: 'PRIMARY_KEY'>, 'PROCEDURE': <TokenType.PROCEDURE: 'PROCEDURE'>, 'QUALIFY': <TokenType.QUALIFY: 'QUALIFY'>, 'RANGE': <TokenType.RANGE: 'RANGE'>, 'RECURSIVE': <TokenType.RECURSIVE: 'RECURSIVE'>, 'REGEXP': <TokenType.RLIKE: 'RLIKE'>, 'REPLACE': <TokenType.REPLACE: 'REPLACE'>, 'RETURNING': <TokenType.RETURNING: 'RETURNING'>, 'REFERENCES': <TokenType.REFERENCES: 'REFERENCES'>, 'RIGHT': <TokenType.RIGHT: 'RIGHT'>, 'RLIKE': <TokenType.RLIKE: 'RLIKE'>, 'ROLLBACK': <TokenType.ROLLBACK: 'ROLLBACK'>, 'ROLLUP': <TokenType.ROLLUP: 'ROLLUP'>, 'ROW': <TokenType.ROW: 'ROW'>, 'ROWS': <TokenType.ROWS: 'ROWS'>, 'SCHEMA': <TokenType.SCHEMA: 'SCHEMA'>, 'SELECT': <TokenType.SELECT: 'SELECT'>, 'SEMI': <TokenType.SEMI: 'SEMI'>, 'SET': <TokenType.SET: 'SET'>, 'SETTINGS': <TokenType.SETTINGS: 'SETTINGS'>, 'SHOW': <TokenType.SHOW: 'SHOW'>, 'SIMILAR TO': <TokenType.SIMILAR_TO: 'SIMILAR_TO'>, 'SOME': <TokenType.SOME: 'SOME'>, 'SORT BY': <TokenType.SORT_BY: 'SORT_BY'>, 'START WITH': <TokenType.START_WITH: 'START_WITH'>, 'TABLE': <TokenType.TABLE: 'TABLE'>, 'TABLESAMPLE': <TokenType.TABLE_SAMPLE: 'TABLE_SAMPLE'>, 'TEMP': <TokenType.TEMPORARY: 'TEMPORARY'>, 'TEMPORARY': <TokenType.TEMPORARY: 'TEMPORARY'>, 'THEN': <TokenType.THEN: 'THEN'>, 'TRUE': <TokenType.TRUE: 'TRUE'>, 'UNION': <TokenType.UNION: 'UNION'>, 'UNKNOWN': <TokenType.UNKNOWN: 'UNKNOWN'>, 'UNNEST': <TokenType.UNNEST: 'UNNEST'>, 'UNPIVOT': <TokenType.UNPIVOT: 'UNPIVOT'>, 'UPDATE': <TokenType.UPDATE: 'UPDATE'>, 'USE': <TokenType.USE: 'USE'>, 'USING': <TokenType.USING: 'USING'>, 'UUID': <TokenType.UUID: 'UUID'>, 'VALUES': <TokenType.VALUES: 'VALUES'>, 'VIEW': <TokenType.VIEW: 'VIEW'>, 'VOLATILE': <TokenType.VOLATILE: 'VOLATILE'>, 'WHEN': <TokenType.WHEN: 'WHEN'>, 'WHERE': <TokenType.WHERE: 'WHERE'>, 'WINDOW': <TokenType.WINDOW: 'WINDOW'>, 'WITH': <TokenType.WITH: 'WITH'>, 'APPLY': <TokenType.APPLY: 'APPLY'>, 'ARRAY': <TokenType.ARRAY: 'ARRAY'>, 'BIT': <TokenType.BIT: 'BIT'>, 'BOOL': <TokenType.BOOLEAN: 'BOOLEAN'>, 'BOOLEAN': <TokenType.BOOLEAN: 'BOOLEAN'>, 'BYTE': <TokenType.TINYINT: 'TINYINT'>, 'MEDIUMINT': <TokenType.MEDIUMINT: 'MEDIUMINT'>, 'INT1': <TokenType.TINYINT: 'TINYINT'>, 'TINYINT': <TokenType.TINYINT: 'TINYINT'>, 'INT16': <TokenType.SMALLINT: 'SMALLINT'>, 'SHORT': <TokenType.SMALLINT: 'SMALLINT'>, 'SMALLINT': <TokenType.SMALLINT: 'SMALLINT'>, 'INT128': <TokenType.INT128: 'INT128'>, 'HUGEINT': <TokenType.INT128: 'INT128'>, 'INT2': <TokenType.SMALLINT: 'SMALLINT'>, 'INTEGER': <TokenType.INT: 'INT'>, 'INT': <TokenType.INT: 'INT'>, 'INT4': <TokenType.INT: 'INT'>, 'INT32': <TokenType.INT: 'INT'>, 'INT64': <TokenType.BIGINT: 'BIGINT'>, 'LONG': <TokenType.BIGINT: 'BIGINT'>, 'BIGINT': <TokenType.BIGINT: 'BIGINT'>, 'INT8': <TokenType.TINYINT: 'TINYINT'>, 'DEC': <TokenType.DECIMAL: 'DECIMAL'>, 'DECIMAL': <TokenType.DECIMAL: 'DECIMAL'>, 'BIGDECIMAL': <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, 'BIGNUMERIC': <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, 'MAP': <TokenType.MAP: 'MAP'>, 'NULLABLE': <TokenType.NULLABLE: 'NULLABLE'>, 'NUMBER': <TokenType.DECIMAL: 'DECIMAL'>, 'NUMERIC': <TokenType.DECIMAL: 'DECIMAL'>, 'FIXED': <TokenType.DECIMAL: 'DECIMAL'>, 'REAL': <TokenType.FLOAT: 'FLOAT'>, 'FLOAT': <TokenType.FLOAT: 'FLOAT'>, 'FLOAT4': <TokenType.FLOAT: 'FLOAT'>, 'FLOAT8': <TokenType.DOUBLE: 'DOUBLE'>, 'DOUBLE': <TokenType.DOUBLE: 'DOUBLE'>, 'DOUBLE PRECISION': <TokenType.DOUBLE: 'DOUBLE'>, 'JSON': <TokenType.JSON: 'JSON'>, 'CHAR': <TokenType.CHAR: 'CHAR'>, 'CHARACTER': <TokenType.CHAR: 'CHAR'>, 'NCHAR': <TokenType.NCHAR: 'NCHAR'>, 'VARCHAR': <TokenType.VARCHAR: 'VARCHAR'>, 'VARCHAR2': <TokenType.VARCHAR: 'VARCHAR'>, 'NVARCHAR': <TokenType.NVARCHAR: 'NVARCHAR'>, 'NVARCHAR2': <TokenType.NVARCHAR: 'NVARCHAR'>, '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'>, 'TRUNCATE': <TokenType.COMMAND: 'COMMAND'>, 'VACUUM': <TokenType.COMMAND: 'COMMAND'>, 'USER-DEFINED': <TokenType.USERDEFINED: 'USERDEFINED'>, 'FOR VERSION': <TokenType.VERSION_SNAPSHOT: 'VERSION_SNAPSHOT'>, 'FOR TIMESTAMP': <TokenType.TIMESTAMP_SNAPSHOT: 'TIMESTAMP_SNAPSHOT'>}
WHITE_SPACE: Dict[Optional[str], TokenType] =
{' ': <TokenType.SPACE: 'SPACE'>, '\t': <TokenType.SPACE: 'SPACE'>, '\n': <TokenType.BREAK: 'BREAK'>, '\r': <TokenType.BREAK: 'BREAK'>}
COMMANDS =
{<TokenType.COMMAND: 'COMMAND'>, <TokenType.FETCH: 'FETCH'>, <TokenType.SHOW: 'SHOW'>, <TokenType.EXECUTE: 'EXECUTE'>}
COMMAND_PREFIX_TOKENS =
{<TokenType.SEMICOLON: 'SEMICOLON'>, <TokenType.BEGIN: 'BEGIN'>}
def
reset(self) -> None:
922 def reset(self) -> None: 923 self.sql = "" 924 self.size = 0 925 self.tokens: t.List[Token] = [] 926 self._start = 0 927 self._current = 0 928 self._line = 1 929 self._col = 0 930 self._comments: t.List[str] = [] 931 932 self._char = "" 933 self._end = False 934 self._peek = "" 935 self._prev_token_line = -1
937 def tokenize(self, sql: str) -> t.List[Token]: 938 """Returns a list of tokens corresponding to the SQL string `sql`.""" 939 if USE_RS_TOKENIZER: 940 return self.tokenize_rs(sql) 941 942 self.reset() 943 self.sql = sql 944 self.size = len(sql) 945 946 try: 947 self._scan() 948 except Exception as e: 949 start = max(self._current - 50, 0) 950 end = min(self._current + 50, self.size - 1) 951 context = self.sql[start:end] 952 raise TokenError(f"Error tokenizing '{context}'") from e 953 954 return self.tokens
Returns a list of tokens corresponding to the SQL string sql
.
1361 def tokenize_rs(self, sql: str) -> t.List[Token]: 1362 if not self._RS_TOKENIZER: 1363 raise SqlglotError("Rust tokenizer is not available") 1364 1365 try: 1366 tokens = self._RS_TOKENIZER.tokenize(sql, self._rs_dialect_settings) 1367 for token in tokens: 1368 token.token_type = _ALL_TOKEN_TYPES[token.token_type_index] 1369 return tokens 1370 except Exception as e: 1371 raise TokenError(str(e))