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