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 DOTCOLON = auto() 41 DCOLON = auto() 42 DQMARK = auto() 43 SEMICOLON = auto() 44 STAR = auto() 45 BACKSLASH = auto() 46 SLASH = auto() 47 LT = auto() 48 LTE = auto() 49 GT = auto() 50 GTE = auto() 51 NOT = auto() 52 EQ = auto() 53 NEQ = auto() 54 NULLSAFE_EQ = auto() 55 COLON_EQ = auto() 56 AND = auto() 57 OR = auto() 58 AMP = auto() 59 DPIPE = auto() 60 PIPE = auto() 61 PIPE_SLASH = auto() 62 DPIPE_SLASH = auto() 63 CARET = auto() 64 CARET_AT = auto() 65 TILDA = auto() 66 ARROW = auto() 67 DARROW = auto() 68 FARROW = auto() 69 HASH = auto() 70 HASH_ARROW = auto() 71 DHASH_ARROW = auto() 72 LR_ARROW = auto() 73 DAT = auto() 74 LT_AT = auto() 75 AT_GT = auto() 76 DOLLAR = auto() 77 PARAMETER = auto() 78 SESSION_PARAMETER = auto() 79 DAMP = auto() 80 XOR = auto() 81 DSTAR = auto() 82 83 URI_START = auto() 84 85 BLOCK_START = auto() 86 BLOCK_END = auto() 87 88 SPACE = auto() 89 BREAK = auto() 90 91 STRING = auto() 92 NUMBER = auto() 93 IDENTIFIER = auto() 94 DATABASE = auto() 95 COLUMN = auto() 96 COLUMN_DEF = auto() 97 SCHEMA = auto() 98 TABLE = auto() 99 WAREHOUSE = auto() 100 STREAMLIT = auto() 101 VAR = auto() 102 BIT_STRING = auto() 103 HEX_STRING = auto() 104 BYTE_STRING = auto() 105 NATIONAL_STRING = auto() 106 RAW_STRING = auto() 107 HEREDOC_STRING = auto() 108 UNICODE_STRING = auto() 109 110 # types 111 BIT = auto() 112 BOOLEAN = auto() 113 TINYINT = auto() 114 UTINYINT = auto() 115 SMALLINT = auto() 116 USMALLINT = auto() 117 MEDIUMINT = auto() 118 UMEDIUMINT = auto() 119 INT = auto() 120 UINT = auto() 121 BIGINT = auto() 122 UBIGINT = auto() 123 INT128 = auto() 124 UINT128 = auto() 125 INT256 = auto() 126 UINT256 = auto() 127 FLOAT = auto() 128 DOUBLE = auto() 129 UDOUBLE = auto() 130 DECIMAL = auto() 131 DECIMAL32 = auto() 132 DECIMAL64 = auto() 133 DECIMAL128 = auto() 134 DECIMAL256 = auto() 135 UDECIMAL = auto() 136 BIGDECIMAL = auto() 137 CHAR = auto() 138 NCHAR = auto() 139 VARCHAR = auto() 140 NVARCHAR = auto() 141 BPCHAR = auto() 142 TEXT = auto() 143 MEDIUMTEXT = auto() 144 LONGTEXT = auto() 145 BLOB = auto() 146 MEDIUMBLOB = auto() 147 LONGBLOB = auto() 148 TINYBLOB = auto() 149 TINYTEXT = auto() 150 NAME = auto() 151 BINARY = auto() 152 VARBINARY = auto() 153 JSON = auto() 154 JSONB = auto() 155 TIME = auto() 156 TIMETZ = auto() 157 TIMESTAMP = auto() 158 TIMESTAMPTZ = auto() 159 TIMESTAMPLTZ = auto() 160 TIMESTAMPNTZ = auto() 161 TIMESTAMP_S = auto() 162 TIMESTAMP_MS = auto() 163 TIMESTAMP_NS = auto() 164 DATETIME = auto() 165 DATETIME2 = auto() 166 DATETIME64 = auto() 167 SMALLDATETIME = auto() 168 DATE = auto() 169 DATE32 = auto() 170 INT4RANGE = auto() 171 INT4MULTIRANGE = auto() 172 INT8RANGE = auto() 173 INT8MULTIRANGE = auto() 174 NUMRANGE = auto() 175 NUMMULTIRANGE = auto() 176 TSRANGE = auto() 177 TSMULTIRANGE = auto() 178 TSTZRANGE = auto() 179 TSTZMULTIRANGE = auto() 180 DATERANGE = auto() 181 DATEMULTIRANGE = auto() 182 UUID = auto() 183 GEOGRAPHY = auto() 184 NULLABLE = auto() 185 GEOMETRY = auto() 186 POINT = auto() 187 RING = auto() 188 LINESTRING = auto() 189 MULTILINESTRING = auto() 190 POLYGON = auto() 191 MULTIPOLYGON = auto() 192 HLLSKETCH = auto() 193 HSTORE = auto() 194 SUPER = auto() 195 SERIAL = auto() 196 SMALLSERIAL = auto() 197 BIGSERIAL = auto() 198 XML = auto() 199 YEAR = auto() 200 USERDEFINED = auto() 201 MONEY = auto() 202 SMALLMONEY = auto() 203 ROWVERSION = auto() 204 IMAGE = auto() 205 VARIANT = auto() 206 OBJECT = auto() 207 INET = auto() 208 IPADDRESS = auto() 209 IPPREFIX = auto() 210 IPV4 = auto() 211 IPV6 = auto() 212 ENUM = auto() 213 ENUM8 = auto() 214 ENUM16 = auto() 215 FIXEDSTRING = auto() 216 LOWCARDINALITY = auto() 217 NESTED = auto() 218 AGGREGATEFUNCTION = auto() 219 SIMPLEAGGREGATEFUNCTION = auto() 220 TDIGEST = auto() 221 UNKNOWN = auto() 222 VECTOR = auto() 223 DYNAMIC = auto() 224 225 # keywords 226 ALIAS = auto() 227 ALTER = auto() 228 ALWAYS = auto() 229 ALL = auto() 230 ANTI = auto() 231 ANY = auto() 232 APPLY = auto() 233 ARRAY = auto() 234 ASC = auto() 235 ASOF = auto() 236 ATTACH = auto() 237 AUTO_INCREMENT = auto() 238 BEGIN = auto() 239 BETWEEN = auto() 240 BULK_COLLECT_INTO = auto() 241 CACHE = auto() 242 CASE = auto() 243 CHARACTER_SET = auto() 244 CLUSTER_BY = auto() 245 COLLATE = auto() 246 COMMAND = auto() 247 COMMENT = auto() 248 COMMIT = auto() 249 CONNECT_BY = auto() 250 CONSTRAINT = auto() 251 COPY = auto() 252 CREATE = auto() 253 CROSS = auto() 254 CUBE = auto() 255 CURRENT_DATE = auto() 256 CURRENT_DATETIME = auto() 257 CURRENT_SCHEMA = auto() 258 CURRENT_TIME = auto() 259 CURRENT_TIMESTAMP = auto() 260 CURRENT_USER = auto() 261 DECLARE = auto() 262 DEFAULT = auto() 263 DELETE = auto() 264 DESC = auto() 265 DESCRIBE = auto() 266 DETACH = auto() 267 DICTIONARY = auto() 268 DISTINCT = auto() 269 DISTRIBUTE_BY = auto() 270 DIV = auto() 271 DROP = auto() 272 ELSE = auto() 273 END = auto() 274 ESCAPE = auto() 275 EXCEPT = auto() 276 EXECUTE = auto() 277 EXISTS = auto() 278 FALSE = auto() 279 FETCH = auto() 280 FILTER = auto() 281 FINAL = auto() 282 FIRST = auto() 283 FOR = auto() 284 FORCE = auto() 285 FOREIGN_KEY = auto() 286 FORMAT = auto() 287 FROM = auto() 288 FULL = auto() 289 FUNCTION = auto() 290 GLOB = auto() 291 GLOBAL = auto() 292 GRANT = auto() 293 GROUP_BY = auto() 294 GROUPING_SETS = auto() 295 HAVING = auto() 296 HINT = auto() 297 IGNORE = auto() 298 ILIKE = auto() 299 ILIKE_ANY = auto() 300 IN = auto() 301 INDEX = auto() 302 INNER = auto() 303 INSERT = auto() 304 INTERSECT = auto() 305 INTERVAL = auto() 306 INTO = auto() 307 INTRODUCER = auto() 308 IRLIKE = auto() 309 IS = auto() 310 ISNULL = auto() 311 JOIN = auto() 312 JOIN_MARKER = auto() 313 KEEP = auto() 314 KEY = auto() 315 KILL = auto() 316 LANGUAGE = auto() 317 LATERAL = auto() 318 LEFT = auto() 319 LIKE = auto() 320 LIKE_ANY = auto() 321 LIMIT = auto() 322 LIST = auto() 323 LOAD = auto() 324 LOCK = auto() 325 MAP = auto() 326 MATCH_CONDITION = auto() 327 MATCH_RECOGNIZE = auto() 328 MEMBER_OF = auto() 329 MERGE = auto() 330 MOD = auto() 331 MODEL = auto() 332 NATURAL = auto() 333 NEXT = auto() 334 NOTNULL = auto() 335 NULL = auto() 336 OBJECT_IDENTIFIER = auto() 337 OFFSET = auto() 338 ON = auto() 339 ONLY = auto() 340 OPERATOR = auto() 341 ORDER_BY = auto() 342 ORDER_SIBLINGS_BY = auto() 343 ORDERED = auto() 344 ORDINALITY = auto() 345 OUTER = auto() 346 OVER = auto() 347 OVERLAPS = auto() 348 OVERWRITE = auto() 349 PARTITION = auto() 350 PARTITION_BY = auto() 351 PERCENT = auto() 352 PIVOT = auto() 353 PLACEHOLDER = auto() 354 POSITIONAL = auto() 355 PRAGMA = auto() 356 PREWHERE = auto() 357 PRIMARY_KEY = auto() 358 PROCEDURE = auto() 359 PROPERTIES = auto() 360 PSEUDO_TYPE = auto() 361 PUT = auto() 362 QUALIFY = auto() 363 QUOTE = auto() 364 RANGE = auto() 365 RECURSIVE = auto() 366 REFRESH = auto() 367 RENAME = auto() 368 REPLACE = auto() 369 RETURNING = auto() 370 REFERENCES = auto() 371 RIGHT = auto() 372 RLIKE = auto() 373 ROLLBACK = auto() 374 ROLLUP = auto() 375 ROW = auto() 376 ROWS = auto() 377 SELECT = auto() 378 SEMI = auto() 379 SEPARATOR = auto() 380 SEQUENCE = auto() 381 SERDE_PROPERTIES = auto() 382 SET = auto() 383 SETTINGS = auto() 384 SHOW = auto() 385 SIMILAR_TO = auto() 386 SOME = auto() 387 SORT_BY = auto() 388 START_WITH = auto() 389 STORAGE_INTEGRATION = auto() 390 STRAIGHT_JOIN = auto() 391 STRUCT = auto() 392 SUMMARIZE = auto() 393 TABLE_SAMPLE = auto() 394 TAG = auto() 395 TEMPORARY = auto() 396 TOP = auto() 397 THEN = auto() 398 TRUE = auto() 399 TRUNCATE = auto() 400 UNCACHE = auto() 401 UNION = auto() 402 UNNEST = auto() 403 UNPIVOT = auto() 404 UPDATE = auto() 405 USE = auto() 406 USING = auto() 407 VALUES = auto() 408 VIEW = auto() 409 VOLATILE = auto() 410 WHEN = auto() 411 WHERE = auto() 412 WINDOW = auto() 413 WITH = auto() 414 UNIQUE = auto() 415 VERSION_SNAPSHOT = auto() 416 TIMESTAMP_SNAPSHOT = auto() 417 OPTION = auto() 418 SINK = auto() 419 SOURCE = auto() 420 ANALYZE = auto() 421 NAMESPACE = auto() 422 EXPORT = auto() 423 424 425_ALL_TOKEN_TYPES = list(TokenType) 426_TOKEN_TYPE_TO_INDEX = {token_type: i for i, token_type in enumerate(_ALL_TOKEN_TYPES)} 427 428 429class Token: 430 __slots__ = ("token_type", "text", "line", "col", "start", "end", "comments") 431 432 @classmethod 433 def number(cls, number: int) -> Token: 434 """Returns a NUMBER token with `number` as its text.""" 435 return cls(TokenType.NUMBER, str(number)) 436 437 @classmethod 438 def string(cls, string: str) -> Token: 439 """Returns a STRING token with `string` as its text.""" 440 return cls(TokenType.STRING, string) 441 442 @classmethod 443 def identifier(cls, identifier: str) -> Token: 444 """Returns an IDENTIFIER token with `identifier` as its text.""" 445 return cls(TokenType.IDENTIFIER, identifier) 446 447 @classmethod 448 def var(cls, var: str) -> Token: 449 """Returns an VAR token with `var` as its text.""" 450 return cls(TokenType.VAR, var) 451 452 def __init__( 453 self, 454 token_type: TokenType, 455 text: str, 456 line: int = 1, 457 col: int = 1, 458 start: int = 0, 459 end: int = 0, 460 comments: t.Optional[t.List[str]] = None, 461 ) -> None: 462 """Token initializer. 463 464 Args: 465 token_type: The TokenType Enum. 466 text: The text of the token. 467 line: The line that the token ends on. 468 col: The column that the token ends on. 469 start: The start index of the token. 470 end: The ending index of the token. 471 comments: The comments to attach to the token. 472 """ 473 self.token_type = token_type 474 self.text = text 475 self.line = line 476 self.col = col 477 self.start = start 478 self.end = end 479 self.comments = [] if comments is None else comments 480 481 def __repr__(self) -> str: 482 attributes = ", ".join(f"{k}: {getattr(self, k)}" for k in self.__slots__) 483 return f"<Token {attributes}>" 484 485 486class _Tokenizer(type): 487 def __new__(cls, clsname, bases, attrs): 488 klass = super().__new__(cls, clsname, bases, attrs) 489 490 def _convert_quotes(arr: t.List[str | t.Tuple[str, str]]) -> t.Dict[str, str]: 491 return dict( 492 (item, item) if isinstance(item, str) else (item[0], item[1]) for item in arr 493 ) 494 495 def _quotes_to_format( 496 token_type: TokenType, arr: t.List[str | t.Tuple[str, str]] 497 ) -> t.Dict[str, t.Tuple[str, TokenType]]: 498 return {k: (v, token_type) for k, v in _convert_quotes(arr).items()} 499 500 klass._QUOTES = _convert_quotes(klass.QUOTES) 501 klass._IDENTIFIERS = _convert_quotes(klass.IDENTIFIERS) 502 503 klass._FORMAT_STRINGS = { 504 **{ 505 p + s: (e, TokenType.NATIONAL_STRING) 506 for s, e in klass._QUOTES.items() 507 for p in ("n", "N") 508 }, 509 **_quotes_to_format(TokenType.BIT_STRING, klass.BIT_STRINGS), 510 **_quotes_to_format(TokenType.BYTE_STRING, klass.BYTE_STRINGS), 511 **_quotes_to_format(TokenType.HEX_STRING, klass.HEX_STRINGS), 512 **_quotes_to_format(TokenType.RAW_STRING, klass.RAW_STRINGS), 513 **_quotes_to_format(TokenType.HEREDOC_STRING, klass.HEREDOC_STRINGS), 514 **_quotes_to_format(TokenType.UNICODE_STRING, klass.UNICODE_STRINGS), 515 } 516 517 klass._STRING_ESCAPES = set(klass.STRING_ESCAPES) 518 klass._IDENTIFIER_ESCAPES = set(klass.IDENTIFIER_ESCAPES) 519 klass._COMMENTS = { 520 **dict( 521 (comment, None) if isinstance(comment, str) else (comment[0], comment[1]) 522 for comment in klass.COMMENTS 523 ), 524 "{#": "#}", # Ensure Jinja comments are tokenized correctly in all dialects 525 } 526 if klass.HINT_START in klass.KEYWORDS: 527 klass._COMMENTS[klass.HINT_START] = "*/" 528 529 klass._KEYWORD_TRIE = new_trie( 530 key.upper() 531 for key in ( 532 *klass.KEYWORDS, 533 *klass._COMMENTS, 534 *klass._QUOTES, 535 *klass._FORMAT_STRINGS, 536 ) 537 if " " in key or any(single in key for single in klass.SINGLE_TOKENS) 538 ) 539 540 if USE_RS_TOKENIZER: 541 settings = RsTokenizerSettings( 542 white_space={k: _TOKEN_TYPE_TO_INDEX[v] for k, v in klass.WHITE_SPACE.items()}, 543 single_tokens={k: _TOKEN_TYPE_TO_INDEX[v] for k, v in klass.SINGLE_TOKENS.items()}, 544 keywords={k: _TOKEN_TYPE_TO_INDEX[v] for k, v in klass.KEYWORDS.items()}, 545 numeric_literals=klass.NUMERIC_LITERALS, 546 identifiers=klass._IDENTIFIERS, 547 identifier_escapes=klass._IDENTIFIER_ESCAPES, 548 string_escapes=klass._STRING_ESCAPES, 549 quotes=klass._QUOTES, 550 format_strings={ 551 k: (v1, _TOKEN_TYPE_TO_INDEX[v2]) 552 for k, (v1, v2) in klass._FORMAT_STRINGS.items() 553 }, 554 has_bit_strings=bool(klass.BIT_STRINGS), 555 has_hex_strings=bool(klass.HEX_STRINGS), 556 comments=klass._COMMENTS, 557 var_single_tokens=klass.VAR_SINGLE_TOKENS, 558 commands={_TOKEN_TYPE_TO_INDEX[v] for v in klass.COMMANDS}, 559 command_prefix_tokens={ 560 _TOKEN_TYPE_TO_INDEX[v] for v in klass.COMMAND_PREFIX_TOKENS 561 }, 562 heredoc_tag_is_identifier=klass.HEREDOC_TAG_IS_IDENTIFIER, 563 string_escapes_allowed_in_raw_strings=klass.STRING_ESCAPES_ALLOWED_IN_RAW_STRINGS, 564 nested_comments=klass.NESTED_COMMENTS, 565 hint_start=klass.HINT_START, 566 tokens_preceding_hint={ 567 _TOKEN_TYPE_TO_INDEX[v] for v in klass.TOKENS_PRECEDING_HINT 568 }, 569 ) 570 token_types = RsTokenTypeSettings( 571 bit_string=_TOKEN_TYPE_TO_INDEX[TokenType.BIT_STRING], 572 break_=_TOKEN_TYPE_TO_INDEX[TokenType.BREAK], 573 dcolon=_TOKEN_TYPE_TO_INDEX[TokenType.DCOLON], 574 heredoc_string=_TOKEN_TYPE_TO_INDEX[TokenType.HEREDOC_STRING], 575 raw_string=_TOKEN_TYPE_TO_INDEX[TokenType.RAW_STRING], 576 hex_string=_TOKEN_TYPE_TO_INDEX[TokenType.HEX_STRING], 577 identifier=_TOKEN_TYPE_TO_INDEX[TokenType.IDENTIFIER], 578 number=_TOKEN_TYPE_TO_INDEX[TokenType.NUMBER], 579 parameter=_TOKEN_TYPE_TO_INDEX[TokenType.PARAMETER], 580 semicolon=_TOKEN_TYPE_TO_INDEX[TokenType.SEMICOLON], 581 string=_TOKEN_TYPE_TO_INDEX[TokenType.STRING], 582 var=_TOKEN_TYPE_TO_INDEX[TokenType.VAR], 583 heredoc_string_alternative=_TOKEN_TYPE_TO_INDEX[klass.HEREDOC_STRING_ALTERNATIVE], 584 hint=_TOKEN_TYPE_TO_INDEX[TokenType.HINT], 585 ) 586 klass._RS_TOKENIZER = RsTokenizer(settings, token_types) 587 else: 588 klass._RS_TOKENIZER = None 589 590 return klass 591 592 593class Tokenizer(metaclass=_Tokenizer): 594 SINGLE_TOKENS = { 595 "(": TokenType.L_PAREN, 596 ")": TokenType.R_PAREN, 597 "[": TokenType.L_BRACKET, 598 "]": TokenType.R_BRACKET, 599 "{": TokenType.L_BRACE, 600 "}": TokenType.R_BRACE, 601 "&": TokenType.AMP, 602 "^": TokenType.CARET, 603 ":": TokenType.COLON, 604 ",": TokenType.COMMA, 605 ".": TokenType.DOT, 606 "-": TokenType.DASH, 607 "=": TokenType.EQ, 608 ">": TokenType.GT, 609 "<": TokenType.LT, 610 "%": TokenType.MOD, 611 "!": TokenType.NOT, 612 "|": TokenType.PIPE, 613 "+": TokenType.PLUS, 614 ";": TokenType.SEMICOLON, 615 "/": TokenType.SLASH, 616 "\\": TokenType.BACKSLASH, 617 "*": TokenType.STAR, 618 "~": TokenType.TILDA, 619 "?": TokenType.PLACEHOLDER, 620 "@": TokenType.PARAMETER, 621 "#": TokenType.HASH, 622 # Used for breaking a var like x'y' but nothing else the token type doesn't matter 623 "'": TokenType.UNKNOWN, 624 "`": TokenType.UNKNOWN, 625 '"': TokenType.UNKNOWN, 626 } 627 628 BIT_STRINGS: t.List[str | t.Tuple[str, str]] = [] 629 BYTE_STRINGS: t.List[str | t.Tuple[str, str]] = [] 630 HEX_STRINGS: t.List[str | t.Tuple[str, str]] = [] 631 RAW_STRINGS: t.List[str | t.Tuple[str, str]] = [] 632 HEREDOC_STRINGS: t.List[str | t.Tuple[str, str]] = [] 633 UNICODE_STRINGS: t.List[str | t.Tuple[str, str]] = [] 634 IDENTIFIERS: t.List[str | t.Tuple[str, str]] = ['"'] 635 QUOTES: t.List[t.Tuple[str, str] | str] = ["'"] 636 STRING_ESCAPES = ["'"] 637 VAR_SINGLE_TOKENS: t.Set[str] = set() 638 639 # The strings in this list can always be used as escapes, regardless of the surrounding 640 # identifier delimiters. By default, the closing delimiter is assumed to also act as an 641 # identifier escape, e.g. if we use double-quotes, then they also act as escapes: "x""" 642 IDENTIFIER_ESCAPES: t.List[str] = [] 643 644 # Whether the heredoc tags follow the same lexical rules as unquoted identifiers 645 HEREDOC_TAG_IS_IDENTIFIER = False 646 647 # Token that we'll generate as a fallback if the heredoc prefix doesn't correspond to a heredoc 648 HEREDOC_STRING_ALTERNATIVE = TokenType.VAR 649 650 # Whether string escape characters function as such when placed within raw strings 651 STRING_ESCAPES_ALLOWED_IN_RAW_STRINGS = True 652 653 NESTED_COMMENTS = True 654 655 HINT_START = "/*+" 656 657 TOKENS_PRECEDING_HINT = {TokenType.SELECT, TokenType.INSERT, TokenType.UPDATE, TokenType.DELETE} 658 659 # Autofilled 660 _COMMENTS: t.Dict[str, str] = {} 661 _FORMAT_STRINGS: t.Dict[str, t.Tuple[str, TokenType]] = {} 662 _IDENTIFIERS: t.Dict[str, str] = {} 663 _IDENTIFIER_ESCAPES: t.Set[str] = set() 664 _QUOTES: t.Dict[str, str] = {} 665 _STRING_ESCAPES: t.Set[str] = set() 666 _KEYWORD_TRIE: t.Dict = {} 667 _RS_TOKENIZER: t.Optional[t.Any] = None 668 669 KEYWORDS: t.Dict[str, TokenType] = { 670 **{f"{{%{postfix}": TokenType.BLOCK_START for postfix in ("", "+", "-")}, 671 **{f"{prefix}%}}": TokenType.BLOCK_END for prefix in ("", "+", "-")}, 672 **{f"{{{{{postfix}": TokenType.BLOCK_START for postfix in ("+", "-")}, 673 **{f"{prefix}}}}}": TokenType.BLOCK_END for prefix in ("+", "-")}, 674 HINT_START: TokenType.HINT, 675 "==": TokenType.EQ, 676 "::": TokenType.DCOLON, 677 "||": TokenType.DPIPE, 678 ">=": TokenType.GTE, 679 "<=": TokenType.LTE, 680 "<>": TokenType.NEQ, 681 "!=": TokenType.NEQ, 682 ":=": TokenType.COLON_EQ, 683 "<=>": TokenType.NULLSAFE_EQ, 684 "->": TokenType.ARROW, 685 "->>": TokenType.DARROW, 686 "=>": TokenType.FARROW, 687 "#>": TokenType.HASH_ARROW, 688 "#>>": TokenType.DHASH_ARROW, 689 "<->": TokenType.LR_ARROW, 690 "&&": TokenType.DAMP, 691 "??": TokenType.DQMARK, 692 "~~~": TokenType.GLOB, 693 "~~": TokenType.LIKE, 694 "~~*": TokenType.ILIKE, 695 "~*": TokenType.IRLIKE, 696 "ALL": TokenType.ALL, 697 "ALWAYS": TokenType.ALWAYS, 698 "AND": TokenType.AND, 699 "ANTI": TokenType.ANTI, 700 "ANY": TokenType.ANY, 701 "ASC": TokenType.ASC, 702 "AS": TokenType.ALIAS, 703 "ASOF": TokenType.ASOF, 704 "AUTOINCREMENT": TokenType.AUTO_INCREMENT, 705 "AUTO_INCREMENT": TokenType.AUTO_INCREMENT, 706 "BEGIN": TokenType.BEGIN, 707 "BETWEEN": TokenType.BETWEEN, 708 "CACHE": TokenType.CACHE, 709 "UNCACHE": TokenType.UNCACHE, 710 "CASE": TokenType.CASE, 711 "CHARACTER SET": TokenType.CHARACTER_SET, 712 "CLUSTER BY": TokenType.CLUSTER_BY, 713 "COLLATE": TokenType.COLLATE, 714 "COLUMN": TokenType.COLUMN, 715 "COMMIT": TokenType.COMMIT, 716 "CONNECT BY": TokenType.CONNECT_BY, 717 "CONSTRAINT": TokenType.CONSTRAINT, 718 "COPY": TokenType.COPY, 719 "CREATE": TokenType.CREATE, 720 "CROSS": TokenType.CROSS, 721 "CUBE": TokenType.CUBE, 722 "CURRENT_DATE": TokenType.CURRENT_DATE, 723 "CURRENT_SCHEMA": TokenType.CURRENT_SCHEMA, 724 "CURRENT_TIME": TokenType.CURRENT_TIME, 725 "CURRENT_TIMESTAMP": TokenType.CURRENT_TIMESTAMP, 726 "CURRENT_USER": TokenType.CURRENT_USER, 727 "DATABASE": TokenType.DATABASE, 728 "DEFAULT": TokenType.DEFAULT, 729 "DELETE": TokenType.DELETE, 730 "DESC": TokenType.DESC, 731 "DESCRIBE": TokenType.DESCRIBE, 732 "DISTINCT": TokenType.DISTINCT, 733 "DISTRIBUTE BY": TokenType.DISTRIBUTE_BY, 734 "DIV": TokenType.DIV, 735 "DROP": TokenType.DROP, 736 "ELSE": TokenType.ELSE, 737 "END": TokenType.END, 738 "ENUM": TokenType.ENUM, 739 "ESCAPE": TokenType.ESCAPE, 740 "EXCEPT": TokenType.EXCEPT, 741 "EXECUTE": TokenType.EXECUTE, 742 "EXISTS": TokenType.EXISTS, 743 "FALSE": TokenType.FALSE, 744 "FETCH": TokenType.FETCH, 745 "FILTER": TokenType.FILTER, 746 "FIRST": TokenType.FIRST, 747 "FULL": TokenType.FULL, 748 "FUNCTION": TokenType.FUNCTION, 749 "FOR": TokenType.FOR, 750 "FOREIGN KEY": TokenType.FOREIGN_KEY, 751 "FORMAT": TokenType.FORMAT, 752 "FROM": TokenType.FROM, 753 "GEOGRAPHY": TokenType.GEOGRAPHY, 754 "GEOMETRY": TokenType.GEOMETRY, 755 "GLOB": TokenType.GLOB, 756 "GROUP BY": TokenType.GROUP_BY, 757 "GROUPING SETS": TokenType.GROUPING_SETS, 758 "HAVING": TokenType.HAVING, 759 "ILIKE": TokenType.ILIKE, 760 "IN": TokenType.IN, 761 "INDEX": TokenType.INDEX, 762 "INET": TokenType.INET, 763 "INNER": TokenType.INNER, 764 "INSERT": TokenType.INSERT, 765 "INTERVAL": TokenType.INTERVAL, 766 "INTERSECT": TokenType.INTERSECT, 767 "INTO": TokenType.INTO, 768 "IS": TokenType.IS, 769 "ISNULL": TokenType.ISNULL, 770 "JOIN": TokenType.JOIN, 771 "KEEP": TokenType.KEEP, 772 "KILL": TokenType.KILL, 773 "LATERAL": TokenType.LATERAL, 774 "LEFT": TokenType.LEFT, 775 "LIKE": TokenType.LIKE, 776 "LIMIT": TokenType.LIMIT, 777 "LOAD": TokenType.LOAD, 778 "LOCK": TokenType.LOCK, 779 "MERGE": TokenType.MERGE, 780 "NAMESPACE": TokenType.NAMESPACE, 781 "NATURAL": TokenType.NATURAL, 782 "NEXT": TokenType.NEXT, 783 "NOT": TokenType.NOT, 784 "NOTNULL": TokenType.NOTNULL, 785 "NULL": TokenType.NULL, 786 "OBJECT": TokenType.OBJECT, 787 "OFFSET": TokenType.OFFSET, 788 "ON": TokenType.ON, 789 "OR": TokenType.OR, 790 "XOR": TokenType.XOR, 791 "ORDER BY": TokenType.ORDER_BY, 792 "ORDINALITY": TokenType.ORDINALITY, 793 "OUTER": TokenType.OUTER, 794 "OVER": TokenType.OVER, 795 "OVERLAPS": TokenType.OVERLAPS, 796 "OVERWRITE": TokenType.OVERWRITE, 797 "PARTITION": TokenType.PARTITION, 798 "PARTITION BY": TokenType.PARTITION_BY, 799 "PARTITIONED BY": TokenType.PARTITION_BY, 800 "PARTITIONED_BY": TokenType.PARTITION_BY, 801 "PERCENT": TokenType.PERCENT, 802 "PIVOT": TokenType.PIVOT, 803 "PRAGMA": TokenType.PRAGMA, 804 "PRIMARY KEY": TokenType.PRIMARY_KEY, 805 "PROCEDURE": TokenType.PROCEDURE, 806 "QUALIFY": TokenType.QUALIFY, 807 "RANGE": TokenType.RANGE, 808 "RECURSIVE": TokenType.RECURSIVE, 809 "REGEXP": TokenType.RLIKE, 810 "RENAME": TokenType.RENAME, 811 "REPLACE": TokenType.REPLACE, 812 "RETURNING": TokenType.RETURNING, 813 "REFERENCES": TokenType.REFERENCES, 814 "RIGHT": TokenType.RIGHT, 815 "RLIKE": TokenType.RLIKE, 816 "ROLLBACK": TokenType.ROLLBACK, 817 "ROLLUP": TokenType.ROLLUP, 818 "ROW": TokenType.ROW, 819 "ROWS": TokenType.ROWS, 820 "SCHEMA": TokenType.SCHEMA, 821 "SELECT": TokenType.SELECT, 822 "SEMI": TokenType.SEMI, 823 "SET": TokenType.SET, 824 "SETTINGS": TokenType.SETTINGS, 825 "SHOW": TokenType.SHOW, 826 "SIMILAR TO": TokenType.SIMILAR_TO, 827 "SOME": TokenType.SOME, 828 "SORT BY": TokenType.SORT_BY, 829 "START WITH": TokenType.START_WITH, 830 "STRAIGHT_JOIN": TokenType.STRAIGHT_JOIN, 831 "TABLE": TokenType.TABLE, 832 "TABLESAMPLE": TokenType.TABLE_SAMPLE, 833 "TEMP": TokenType.TEMPORARY, 834 "TEMPORARY": TokenType.TEMPORARY, 835 "THEN": TokenType.THEN, 836 "TRUE": TokenType.TRUE, 837 "TRUNCATE": TokenType.TRUNCATE, 838 "UNION": TokenType.UNION, 839 "UNKNOWN": TokenType.UNKNOWN, 840 "UNNEST": TokenType.UNNEST, 841 "UNPIVOT": TokenType.UNPIVOT, 842 "UPDATE": TokenType.UPDATE, 843 "USE": TokenType.USE, 844 "USING": TokenType.USING, 845 "UUID": TokenType.UUID, 846 "VALUES": TokenType.VALUES, 847 "VIEW": TokenType.VIEW, 848 "VOLATILE": TokenType.VOLATILE, 849 "WHEN": TokenType.WHEN, 850 "WHERE": TokenType.WHERE, 851 "WINDOW": TokenType.WINDOW, 852 "WITH": TokenType.WITH, 853 "APPLY": TokenType.APPLY, 854 "ARRAY": TokenType.ARRAY, 855 "BIT": TokenType.BIT, 856 "BOOL": TokenType.BOOLEAN, 857 "BOOLEAN": TokenType.BOOLEAN, 858 "BYTE": TokenType.TINYINT, 859 "MEDIUMINT": TokenType.MEDIUMINT, 860 "INT1": TokenType.TINYINT, 861 "TINYINT": TokenType.TINYINT, 862 "INT16": TokenType.SMALLINT, 863 "SHORT": TokenType.SMALLINT, 864 "SMALLINT": TokenType.SMALLINT, 865 "HUGEINT": TokenType.INT128, 866 "UHUGEINT": TokenType.UINT128, 867 "INT2": TokenType.SMALLINT, 868 "INTEGER": TokenType.INT, 869 "INT": TokenType.INT, 870 "INT4": TokenType.INT, 871 "INT32": TokenType.INT, 872 "INT64": TokenType.BIGINT, 873 "INT128": TokenType.INT128, 874 "INT256": TokenType.INT256, 875 "LONG": TokenType.BIGINT, 876 "BIGINT": TokenType.BIGINT, 877 "INT8": TokenType.TINYINT, 878 "UINT": TokenType.UINT, 879 "UINT128": TokenType.UINT128, 880 "UINT256": TokenType.UINT256, 881 "DEC": TokenType.DECIMAL, 882 "DECIMAL": TokenType.DECIMAL, 883 "DECIMAL32": TokenType.DECIMAL32, 884 "DECIMAL64": TokenType.DECIMAL64, 885 "DECIMAL128": TokenType.DECIMAL128, 886 "DECIMAL256": TokenType.DECIMAL256, 887 "BIGDECIMAL": TokenType.BIGDECIMAL, 888 "BIGNUMERIC": TokenType.BIGDECIMAL, 889 "LIST": TokenType.LIST, 890 "MAP": TokenType.MAP, 891 "NULLABLE": TokenType.NULLABLE, 892 "NUMBER": TokenType.DECIMAL, 893 "NUMERIC": TokenType.DECIMAL, 894 "FIXED": TokenType.DECIMAL, 895 "REAL": TokenType.FLOAT, 896 "FLOAT": TokenType.FLOAT, 897 "FLOAT4": TokenType.FLOAT, 898 "FLOAT8": TokenType.DOUBLE, 899 "DOUBLE": TokenType.DOUBLE, 900 "DOUBLE PRECISION": TokenType.DOUBLE, 901 "JSON": TokenType.JSON, 902 "JSONB": TokenType.JSONB, 903 "CHAR": TokenType.CHAR, 904 "CHARACTER": TokenType.CHAR, 905 "NCHAR": TokenType.NCHAR, 906 "VARCHAR": TokenType.VARCHAR, 907 "VARCHAR2": TokenType.VARCHAR, 908 "NVARCHAR": TokenType.NVARCHAR, 909 "NVARCHAR2": TokenType.NVARCHAR, 910 "BPCHAR": TokenType.BPCHAR, 911 "STR": TokenType.TEXT, 912 "STRING": TokenType.TEXT, 913 "TEXT": TokenType.TEXT, 914 "LONGTEXT": TokenType.LONGTEXT, 915 "MEDIUMTEXT": TokenType.MEDIUMTEXT, 916 "TINYTEXT": TokenType.TINYTEXT, 917 "CLOB": TokenType.TEXT, 918 "LONGVARCHAR": TokenType.TEXT, 919 "BINARY": TokenType.BINARY, 920 "BLOB": TokenType.VARBINARY, 921 "LONGBLOB": TokenType.LONGBLOB, 922 "MEDIUMBLOB": TokenType.MEDIUMBLOB, 923 "TINYBLOB": TokenType.TINYBLOB, 924 "BYTEA": TokenType.VARBINARY, 925 "VARBINARY": TokenType.VARBINARY, 926 "TIME": TokenType.TIME, 927 "TIMETZ": TokenType.TIMETZ, 928 "TIMESTAMP": TokenType.TIMESTAMP, 929 "TIMESTAMPTZ": TokenType.TIMESTAMPTZ, 930 "TIMESTAMPLTZ": TokenType.TIMESTAMPLTZ, 931 "TIMESTAMP_LTZ": TokenType.TIMESTAMPLTZ, 932 "TIMESTAMPNTZ": TokenType.TIMESTAMPNTZ, 933 "TIMESTAMP_NTZ": TokenType.TIMESTAMPNTZ, 934 "DATE": TokenType.DATE, 935 "DATETIME": TokenType.DATETIME, 936 "INT4RANGE": TokenType.INT4RANGE, 937 "INT4MULTIRANGE": TokenType.INT4MULTIRANGE, 938 "INT8RANGE": TokenType.INT8RANGE, 939 "INT8MULTIRANGE": TokenType.INT8MULTIRANGE, 940 "NUMRANGE": TokenType.NUMRANGE, 941 "NUMMULTIRANGE": TokenType.NUMMULTIRANGE, 942 "TSRANGE": TokenType.TSRANGE, 943 "TSMULTIRANGE": TokenType.TSMULTIRANGE, 944 "TSTZRANGE": TokenType.TSTZRANGE, 945 "TSTZMULTIRANGE": TokenType.TSTZMULTIRANGE, 946 "DATERANGE": TokenType.DATERANGE, 947 "DATEMULTIRANGE": TokenType.DATEMULTIRANGE, 948 "UNIQUE": TokenType.UNIQUE, 949 "VECTOR": TokenType.VECTOR, 950 "STRUCT": TokenType.STRUCT, 951 "SEQUENCE": TokenType.SEQUENCE, 952 "VARIANT": TokenType.VARIANT, 953 "ALTER": TokenType.ALTER, 954 "ANALYZE": TokenType.ANALYZE, 955 "CALL": TokenType.COMMAND, 956 "COMMENT": TokenType.COMMENT, 957 "EXPLAIN": TokenType.COMMAND, 958 "GRANT": TokenType.GRANT, 959 "OPTIMIZE": TokenType.COMMAND, 960 "PREPARE": TokenType.COMMAND, 961 "VACUUM": TokenType.COMMAND, 962 "USER-DEFINED": TokenType.USERDEFINED, 963 "FOR VERSION": TokenType.VERSION_SNAPSHOT, 964 "FOR TIMESTAMP": TokenType.TIMESTAMP_SNAPSHOT, 965 } 966 967 WHITE_SPACE: t.Dict[t.Optional[str], TokenType] = { 968 " ": TokenType.SPACE, 969 "\t": TokenType.SPACE, 970 "\n": TokenType.BREAK, 971 "\r": TokenType.BREAK, 972 } 973 974 COMMANDS = { 975 TokenType.COMMAND, 976 TokenType.EXECUTE, 977 TokenType.FETCH, 978 TokenType.SHOW, 979 TokenType.RENAME, 980 } 981 982 COMMAND_PREFIX_TOKENS = {TokenType.SEMICOLON, TokenType.BEGIN} 983 984 # Handle numeric literals like in hive (3L = BIGINT) 985 NUMERIC_LITERALS: t.Dict[str, str] = {} 986 987 COMMENTS = ["--", ("/*", "*/")] 988 989 __slots__ = ( 990 "sql", 991 "size", 992 "tokens", 993 "dialect", 994 "use_rs_tokenizer", 995 "_start", 996 "_current", 997 "_line", 998 "_col", 999 "_comments", 1000 "_char", 1001 "_end", 1002 "_peek", 1003 "_prev_token_line", 1004 "_rs_dialect_settings", 1005 ) 1006 1007 def __init__( 1008 self, dialect: DialectType = None, use_rs_tokenizer: t.Optional[bool] = None 1009 ) -> None: 1010 from sqlglot.dialects import Dialect 1011 1012 self.dialect = Dialect.get_or_raise(dialect) 1013 1014 # initialize `use_rs_tokenizer`, and allow it to be overwritten per Tokenizer instance 1015 self.use_rs_tokenizer = ( 1016 use_rs_tokenizer if use_rs_tokenizer is not None else USE_RS_TOKENIZER 1017 ) 1018 1019 if self.use_rs_tokenizer: 1020 self._rs_dialect_settings = RsTokenizerDialectSettings( 1021 unescaped_sequences=self.dialect.UNESCAPED_SEQUENCES, 1022 identifiers_can_start_with_digit=self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT, 1023 numbers_can_be_underscore_separated=self.dialect.NUMBERS_CAN_BE_UNDERSCORE_SEPARATED, 1024 ) 1025 1026 self.reset() 1027 1028 def reset(self) -> None: 1029 self.sql = "" 1030 self.size = 0 1031 self.tokens: t.List[Token] = [] 1032 self._start = 0 1033 self._current = 0 1034 self._line = 1 1035 self._col = 0 1036 self._comments: t.List[str] = [] 1037 1038 self._char = "" 1039 self._end = False 1040 self._peek = "" 1041 self._prev_token_line = -1 1042 1043 def tokenize(self, sql: str) -> t.List[Token]: 1044 """Returns a list of tokens corresponding to the SQL string `sql`.""" 1045 if self.use_rs_tokenizer: 1046 return self.tokenize_rs(sql) 1047 1048 self.reset() 1049 self.sql = sql 1050 self.size = len(sql) 1051 1052 try: 1053 self._scan() 1054 except Exception as e: 1055 start = max(self._current - 50, 0) 1056 end = min(self._current + 50, self.size - 1) 1057 context = self.sql[start:end] 1058 raise TokenError(f"Error tokenizing '{context}'") from e 1059 1060 return self.tokens 1061 1062 def _scan(self, until: t.Optional[t.Callable] = None) -> None: 1063 while self.size and not self._end: 1064 current = self._current 1065 1066 # Skip spaces here rather than iteratively calling advance() for performance reasons 1067 while current < self.size: 1068 char = self.sql[current] 1069 1070 if char.isspace() and (char == " " or char == "\t"): 1071 current += 1 1072 else: 1073 break 1074 1075 offset = current - self._current if current > self._current else 1 1076 1077 self._start = current 1078 self._advance(offset) 1079 1080 if not self._char.isspace(): 1081 if self._char.isdigit(): 1082 self._scan_number() 1083 elif self._char in self._IDENTIFIERS: 1084 self._scan_identifier(self._IDENTIFIERS[self._char]) 1085 else: 1086 self._scan_keywords() 1087 1088 if until and until(): 1089 break 1090 1091 if self.tokens and self._comments: 1092 self.tokens[-1].comments.extend(self._comments) 1093 1094 def _chars(self, size: int) -> str: 1095 if size == 1: 1096 return self._char 1097 1098 start = self._current - 1 1099 end = start + size 1100 1101 return self.sql[start:end] if end <= self.size else "" 1102 1103 def _advance(self, i: int = 1, alnum: bool = False) -> None: 1104 if self.WHITE_SPACE.get(self._char) is TokenType.BREAK: 1105 # Ensures we don't count an extra line if we get a \r\n line break sequence 1106 if not (self._char == "\r" and self._peek == "\n"): 1107 self._col = 1 1108 self._line += 1 1109 else: 1110 self._col += i 1111 1112 self._current += i 1113 self._end = self._current >= self.size 1114 self._char = self.sql[self._current - 1] 1115 self._peek = "" if self._end else self.sql[self._current] 1116 1117 if alnum and self._char.isalnum(): 1118 # Here we use local variables instead of attributes for better performance 1119 _col = self._col 1120 _current = self._current 1121 _end = self._end 1122 _peek = self._peek 1123 1124 while _peek.isalnum(): 1125 _col += 1 1126 _current += 1 1127 _end = _current >= self.size 1128 _peek = "" if _end else self.sql[_current] 1129 1130 self._col = _col 1131 self._current = _current 1132 self._end = _end 1133 self._peek = _peek 1134 self._char = self.sql[_current - 1] 1135 1136 @property 1137 def _text(self) -> str: 1138 return self.sql[self._start : self._current] 1139 1140 def _add(self, token_type: TokenType, text: t.Optional[str] = None) -> None: 1141 self._prev_token_line = self._line 1142 1143 if self._comments and token_type == TokenType.SEMICOLON and self.tokens: 1144 self.tokens[-1].comments.extend(self._comments) 1145 self._comments = [] 1146 1147 self.tokens.append( 1148 Token( 1149 token_type, 1150 text=self._text if text is None else text, 1151 line=self._line, 1152 col=self._col, 1153 start=self._start, 1154 end=self._current - 1, 1155 comments=self._comments, 1156 ) 1157 ) 1158 self._comments = [] 1159 1160 # If we have either a semicolon or a begin token before the command's token, we'll parse 1161 # whatever follows the command's token as a string 1162 if ( 1163 token_type in self.COMMANDS 1164 and self._peek != ";" 1165 and (len(self.tokens) == 1 or self.tokens[-2].token_type in self.COMMAND_PREFIX_TOKENS) 1166 ): 1167 start = self._current 1168 tokens = len(self.tokens) 1169 self._scan(lambda: self._peek == ";") 1170 self.tokens = self.tokens[:tokens] 1171 text = self.sql[start : self._current].strip() 1172 if text: 1173 self._add(TokenType.STRING, text) 1174 1175 def _scan_keywords(self) -> None: 1176 size = 0 1177 word = None 1178 chars = self._text 1179 char = chars 1180 prev_space = False 1181 skip = False 1182 trie = self._KEYWORD_TRIE 1183 single_token = char in self.SINGLE_TOKENS 1184 1185 while chars: 1186 if skip: 1187 result = TrieResult.PREFIX 1188 else: 1189 result, trie = in_trie(trie, char.upper()) 1190 1191 if result == TrieResult.FAILED: 1192 break 1193 if result == TrieResult.EXISTS: 1194 word = chars 1195 1196 end = self._current + size 1197 size += 1 1198 1199 if end < self.size: 1200 char = self.sql[end] 1201 single_token = single_token or char in self.SINGLE_TOKENS 1202 is_space = char.isspace() 1203 1204 if not is_space or not prev_space: 1205 if is_space: 1206 char = " " 1207 chars += char 1208 prev_space = is_space 1209 skip = False 1210 else: 1211 skip = True 1212 else: 1213 char = "" 1214 break 1215 1216 if word: 1217 if self._scan_string(word): 1218 return 1219 if self._scan_comment(word): 1220 return 1221 if prev_space or single_token or not char: 1222 self._advance(size - 1) 1223 word = word.upper() 1224 self._add(self.KEYWORDS[word], text=word) 1225 return 1226 1227 if self._char in self.SINGLE_TOKENS: 1228 self._add(self.SINGLE_TOKENS[self._char], text=self._char) 1229 return 1230 1231 self._scan_var() 1232 1233 def _scan_comment(self, comment_start: str) -> bool: 1234 if comment_start not in self._COMMENTS: 1235 return False 1236 1237 comment_start_line = self._line 1238 comment_start_size = len(comment_start) 1239 comment_end = self._COMMENTS[comment_start] 1240 1241 if comment_end: 1242 # Skip the comment's start delimiter 1243 self._advance(comment_start_size) 1244 1245 comment_count = 1 1246 comment_end_size = len(comment_end) 1247 1248 while not self._end: 1249 if self._chars(comment_end_size) == comment_end: 1250 comment_count -= 1 1251 if not comment_count: 1252 break 1253 1254 self._advance(alnum=True) 1255 1256 # Nested comments are allowed by some dialects, e.g. databricks, duckdb, postgres 1257 if ( 1258 self.NESTED_COMMENTS 1259 and not self._end 1260 and self._chars(comment_end_size) == comment_start 1261 ): 1262 self._advance(comment_start_size) 1263 comment_count += 1 1264 1265 self._comments.append(self._text[comment_start_size : -comment_end_size + 1]) 1266 self._advance(comment_end_size - 1) 1267 else: 1268 while not self._end and self.WHITE_SPACE.get(self._peek) is not TokenType.BREAK: 1269 self._advance(alnum=True) 1270 self._comments.append(self._text[comment_start_size:]) 1271 1272 if ( 1273 comment_start == self.HINT_START 1274 and self.tokens 1275 and self.tokens[-1].token_type in self.TOKENS_PRECEDING_HINT 1276 ): 1277 self._add(TokenType.HINT) 1278 1279 # Leading comment is attached to the succeeding token, whilst trailing comment to the preceding. 1280 # Multiple consecutive comments are preserved by appending them to the current comments list. 1281 if comment_start_line == self._prev_token_line: 1282 self.tokens[-1].comments.extend(self._comments) 1283 self._comments = [] 1284 self._prev_token_line = self._line 1285 1286 return True 1287 1288 def _scan_number(self) -> None: 1289 if self._char == "0": 1290 peek = self._peek.upper() 1291 if peek == "B": 1292 return self._scan_bits() if self.BIT_STRINGS else self._add(TokenType.NUMBER) 1293 elif peek == "X": 1294 return self._scan_hex() if self.HEX_STRINGS else self._add(TokenType.NUMBER) 1295 1296 decimal = False 1297 scientific = 0 1298 1299 while True: 1300 if self._peek.isdigit(): 1301 self._advance() 1302 elif self._peek == "." and not decimal: 1303 if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER: 1304 return self._add(TokenType.NUMBER) 1305 decimal = True 1306 self._advance() 1307 elif self._peek in ("-", "+") and scientific == 1: 1308 scientific += 1 1309 self._advance() 1310 elif self._peek.upper() == "E" and not scientific: 1311 scientific += 1 1312 self._advance() 1313 elif self._peek.isidentifier(): 1314 number_text = self._text 1315 literal = "" 1316 1317 while self._peek.strip() and self._peek not in self.SINGLE_TOKENS: 1318 literal += self._peek 1319 self._advance() 1320 1321 token_type = self.KEYWORDS.get(self.NUMERIC_LITERALS.get(literal.upper(), "")) 1322 1323 if token_type: 1324 self._add(TokenType.NUMBER, number_text) 1325 self._add(TokenType.DCOLON, "::") 1326 return self._add(token_type, literal) 1327 else: 1328 replaced = literal.replace("_", "") 1329 if self.dialect.NUMBERS_CAN_BE_UNDERSCORE_SEPARATED and replaced.isdigit(): 1330 return self._add(TokenType.NUMBER, number_text + replaced) 1331 if self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT: 1332 return self._add(TokenType.VAR) 1333 1334 self._advance(-len(literal)) 1335 return self._add(TokenType.NUMBER, number_text) 1336 else: 1337 return self._add(TokenType.NUMBER) 1338 1339 def _scan_bits(self) -> None: 1340 self._advance() 1341 value = self._extract_value() 1342 try: 1343 # If `value` can't be converted to a binary, fallback to tokenizing it as an identifier 1344 int(value, 2) 1345 self._add(TokenType.BIT_STRING, value[2:]) # Drop the 0b 1346 except ValueError: 1347 self._add(TokenType.IDENTIFIER) 1348 1349 def _scan_hex(self) -> None: 1350 self._advance() 1351 value = self._extract_value() 1352 try: 1353 # If `value` can't be converted to a hex, fallback to tokenizing it as an identifier 1354 int(value, 16) 1355 self._add(TokenType.HEX_STRING, value[2:]) # Drop the 0x 1356 except ValueError: 1357 self._add(TokenType.IDENTIFIER) 1358 1359 def _extract_value(self) -> str: 1360 while True: 1361 char = self._peek.strip() 1362 if char and char not in self.SINGLE_TOKENS: 1363 self._advance(alnum=True) 1364 else: 1365 break 1366 1367 return self._text 1368 1369 def _scan_string(self, start: str) -> bool: 1370 base = None 1371 token_type = TokenType.STRING 1372 1373 if start in self._QUOTES: 1374 end = self._QUOTES[start] 1375 elif start in self._FORMAT_STRINGS: 1376 end, token_type = self._FORMAT_STRINGS[start] 1377 1378 if token_type == TokenType.HEX_STRING: 1379 base = 16 1380 elif token_type == TokenType.BIT_STRING: 1381 base = 2 1382 elif token_type == TokenType.HEREDOC_STRING: 1383 self._advance() 1384 1385 if self._char == end: 1386 tag = "" 1387 else: 1388 tag = self._extract_string( 1389 end, 1390 raw_string=True, 1391 raise_unmatched=not self.HEREDOC_TAG_IS_IDENTIFIER, 1392 ) 1393 1394 if tag and self.HEREDOC_TAG_IS_IDENTIFIER and (self._end or not tag.isidentifier()): 1395 if not self._end: 1396 self._advance(-1) 1397 1398 self._advance(-len(tag)) 1399 self._add(self.HEREDOC_STRING_ALTERNATIVE) 1400 return True 1401 1402 end = f"{start}{tag}{end}" 1403 else: 1404 return False 1405 1406 self._advance(len(start)) 1407 text = self._extract_string(end, raw_string=token_type == TokenType.RAW_STRING) 1408 1409 if base: 1410 try: 1411 int(text, base) 1412 except Exception: 1413 raise TokenError( 1414 f"Numeric string contains invalid characters from {self._line}:{self._start}" 1415 ) 1416 1417 self._add(token_type, text) 1418 return True 1419 1420 def _scan_identifier(self, identifier_end: str) -> None: 1421 self._advance() 1422 text = self._extract_string( 1423 identifier_end, escapes=self._IDENTIFIER_ESCAPES | {identifier_end} 1424 ) 1425 self._add(TokenType.IDENTIFIER, text) 1426 1427 def _scan_var(self) -> None: 1428 while True: 1429 char = self._peek.strip() 1430 if char and (char in self.VAR_SINGLE_TOKENS or char not in self.SINGLE_TOKENS): 1431 self._advance(alnum=True) 1432 else: 1433 break 1434 1435 self._add( 1436 TokenType.VAR 1437 if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER 1438 else self.KEYWORDS.get(self._text.upper(), TokenType.VAR) 1439 ) 1440 1441 def _extract_string( 1442 self, 1443 delimiter: str, 1444 escapes: t.Optional[t.Set[str]] = None, 1445 raw_string: bool = False, 1446 raise_unmatched: bool = True, 1447 ) -> str: 1448 text = "" 1449 delim_size = len(delimiter) 1450 escapes = self._STRING_ESCAPES if escapes is None else escapes 1451 1452 while True: 1453 if ( 1454 not raw_string 1455 and self.dialect.UNESCAPED_SEQUENCES 1456 and self._peek 1457 and self._char in self.STRING_ESCAPES 1458 ): 1459 unescaped_sequence = self.dialect.UNESCAPED_SEQUENCES.get(self._char + self._peek) 1460 if unescaped_sequence: 1461 self._advance(2) 1462 text += unescaped_sequence 1463 continue 1464 if ( 1465 (self.STRING_ESCAPES_ALLOWED_IN_RAW_STRINGS or not raw_string) 1466 and self._char in escapes 1467 and (self._peek == delimiter or self._peek in escapes) 1468 and (self._char not in self._QUOTES or self._char == self._peek) 1469 ): 1470 if self._peek == delimiter: 1471 text += self._peek 1472 else: 1473 text += self._char + self._peek 1474 1475 if self._current + 1 < self.size: 1476 self._advance(2) 1477 else: 1478 raise TokenError(f"Missing {delimiter} from {self._line}:{self._current}") 1479 else: 1480 if self._chars(delim_size) == delimiter: 1481 if delim_size > 1: 1482 self._advance(delim_size - 1) 1483 break 1484 1485 if self._end: 1486 if not raise_unmatched: 1487 return text + self._char 1488 1489 raise TokenError(f"Missing {delimiter} from {self._line}:{self._start}") 1490 1491 current = self._current - 1 1492 self._advance(alnum=True) 1493 text += self.sql[current : self._current - 1] 1494 1495 return text 1496 1497 def tokenize_rs(self, sql: str) -> t.List[Token]: 1498 if not self._RS_TOKENIZER: 1499 raise SqlglotError("Rust tokenizer is not available") 1500 1501 try: 1502 tokens = self._RS_TOKENIZER.tokenize(sql, self._rs_dialect_settings) 1503 for token in tokens: 1504 token.token_type = _ALL_TOKEN_TYPES[token.token_type_index] 1505 return tokens 1506 except Exception as e: 1507 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 DOTCOLON = auto() 42 DCOLON = auto() 43 DQMARK = auto() 44 SEMICOLON = auto() 45 STAR = auto() 46 BACKSLASH = auto() 47 SLASH = auto() 48 LT = auto() 49 LTE = auto() 50 GT = auto() 51 GTE = auto() 52 NOT = auto() 53 EQ = auto() 54 NEQ = auto() 55 NULLSAFE_EQ = auto() 56 COLON_EQ = auto() 57 AND = auto() 58 OR = auto() 59 AMP = auto() 60 DPIPE = auto() 61 PIPE = auto() 62 PIPE_SLASH = auto() 63 DPIPE_SLASH = auto() 64 CARET = auto() 65 CARET_AT = auto() 66 TILDA = auto() 67 ARROW = auto() 68 DARROW = auto() 69 FARROW = auto() 70 HASH = auto() 71 HASH_ARROW = auto() 72 DHASH_ARROW = auto() 73 LR_ARROW = auto() 74 DAT = auto() 75 LT_AT = auto() 76 AT_GT = auto() 77 DOLLAR = auto() 78 PARAMETER = auto() 79 SESSION_PARAMETER = auto() 80 DAMP = auto() 81 XOR = auto() 82 DSTAR = auto() 83 84 URI_START = auto() 85 86 BLOCK_START = auto() 87 BLOCK_END = auto() 88 89 SPACE = auto() 90 BREAK = auto() 91 92 STRING = auto() 93 NUMBER = auto() 94 IDENTIFIER = auto() 95 DATABASE = auto() 96 COLUMN = auto() 97 COLUMN_DEF = auto() 98 SCHEMA = auto() 99 TABLE = auto() 100 WAREHOUSE = auto() 101 STREAMLIT = auto() 102 VAR = auto() 103 BIT_STRING = auto() 104 HEX_STRING = auto() 105 BYTE_STRING = auto() 106 NATIONAL_STRING = auto() 107 RAW_STRING = auto() 108 HEREDOC_STRING = auto() 109 UNICODE_STRING = auto() 110 111 # types 112 BIT = auto() 113 BOOLEAN = auto() 114 TINYINT = auto() 115 UTINYINT = auto() 116 SMALLINT = auto() 117 USMALLINT = auto() 118 MEDIUMINT = auto() 119 UMEDIUMINT = auto() 120 INT = auto() 121 UINT = auto() 122 BIGINT = auto() 123 UBIGINT = auto() 124 INT128 = auto() 125 UINT128 = auto() 126 INT256 = auto() 127 UINT256 = auto() 128 FLOAT = auto() 129 DOUBLE = auto() 130 UDOUBLE = auto() 131 DECIMAL = auto() 132 DECIMAL32 = auto() 133 DECIMAL64 = auto() 134 DECIMAL128 = auto() 135 DECIMAL256 = auto() 136 UDECIMAL = auto() 137 BIGDECIMAL = auto() 138 CHAR = auto() 139 NCHAR = auto() 140 VARCHAR = auto() 141 NVARCHAR = auto() 142 BPCHAR = auto() 143 TEXT = auto() 144 MEDIUMTEXT = auto() 145 LONGTEXT = auto() 146 BLOB = auto() 147 MEDIUMBLOB = auto() 148 LONGBLOB = auto() 149 TINYBLOB = auto() 150 TINYTEXT = auto() 151 NAME = auto() 152 BINARY = auto() 153 VARBINARY = auto() 154 JSON = auto() 155 JSONB = auto() 156 TIME = auto() 157 TIMETZ = auto() 158 TIMESTAMP = auto() 159 TIMESTAMPTZ = auto() 160 TIMESTAMPLTZ = auto() 161 TIMESTAMPNTZ = auto() 162 TIMESTAMP_S = auto() 163 TIMESTAMP_MS = auto() 164 TIMESTAMP_NS = auto() 165 DATETIME = auto() 166 DATETIME2 = auto() 167 DATETIME64 = auto() 168 SMALLDATETIME = auto() 169 DATE = auto() 170 DATE32 = auto() 171 INT4RANGE = auto() 172 INT4MULTIRANGE = auto() 173 INT8RANGE = auto() 174 INT8MULTIRANGE = auto() 175 NUMRANGE = auto() 176 NUMMULTIRANGE = auto() 177 TSRANGE = auto() 178 TSMULTIRANGE = auto() 179 TSTZRANGE = auto() 180 TSTZMULTIRANGE = auto() 181 DATERANGE = auto() 182 DATEMULTIRANGE = auto() 183 UUID = auto() 184 GEOGRAPHY = auto() 185 NULLABLE = auto() 186 GEOMETRY = auto() 187 POINT = auto() 188 RING = auto() 189 LINESTRING = auto() 190 MULTILINESTRING = auto() 191 POLYGON = auto() 192 MULTIPOLYGON = auto() 193 HLLSKETCH = auto() 194 HSTORE = auto() 195 SUPER = auto() 196 SERIAL = auto() 197 SMALLSERIAL = auto() 198 BIGSERIAL = auto() 199 XML = auto() 200 YEAR = auto() 201 USERDEFINED = auto() 202 MONEY = auto() 203 SMALLMONEY = auto() 204 ROWVERSION = auto() 205 IMAGE = auto() 206 VARIANT = auto() 207 OBJECT = auto() 208 INET = auto() 209 IPADDRESS = auto() 210 IPPREFIX = auto() 211 IPV4 = auto() 212 IPV6 = auto() 213 ENUM = auto() 214 ENUM8 = auto() 215 ENUM16 = auto() 216 FIXEDSTRING = auto() 217 LOWCARDINALITY = auto() 218 NESTED = auto() 219 AGGREGATEFUNCTION = auto() 220 SIMPLEAGGREGATEFUNCTION = auto() 221 TDIGEST = auto() 222 UNKNOWN = auto() 223 VECTOR = auto() 224 DYNAMIC = auto() 225 226 # keywords 227 ALIAS = auto() 228 ALTER = auto() 229 ALWAYS = auto() 230 ALL = auto() 231 ANTI = auto() 232 ANY = auto() 233 APPLY = auto() 234 ARRAY = auto() 235 ASC = auto() 236 ASOF = auto() 237 ATTACH = auto() 238 AUTO_INCREMENT = auto() 239 BEGIN = auto() 240 BETWEEN = auto() 241 BULK_COLLECT_INTO = auto() 242 CACHE = auto() 243 CASE = auto() 244 CHARACTER_SET = auto() 245 CLUSTER_BY = auto() 246 COLLATE = auto() 247 COMMAND = auto() 248 COMMENT = auto() 249 COMMIT = auto() 250 CONNECT_BY = auto() 251 CONSTRAINT = auto() 252 COPY = auto() 253 CREATE = auto() 254 CROSS = auto() 255 CUBE = auto() 256 CURRENT_DATE = auto() 257 CURRENT_DATETIME = auto() 258 CURRENT_SCHEMA = auto() 259 CURRENT_TIME = auto() 260 CURRENT_TIMESTAMP = auto() 261 CURRENT_USER = auto() 262 DECLARE = auto() 263 DEFAULT = auto() 264 DELETE = auto() 265 DESC = auto() 266 DESCRIBE = auto() 267 DETACH = auto() 268 DICTIONARY = auto() 269 DISTINCT = auto() 270 DISTRIBUTE_BY = auto() 271 DIV = auto() 272 DROP = auto() 273 ELSE = auto() 274 END = auto() 275 ESCAPE = auto() 276 EXCEPT = auto() 277 EXECUTE = auto() 278 EXISTS = auto() 279 FALSE = auto() 280 FETCH = auto() 281 FILTER = auto() 282 FINAL = auto() 283 FIRST = auto() 284 FOR = auto() 285 FORCE = auto() 286 FOREIGN_KEY = auto() 287 FORMAT = auto() 288 FROM = auto() 289 FULL = auto() 290 FUNCTION = auto() 291 GLOB = auto() 292 GLOBAL = auto() 293 GRANT = auto() 294 GROUP_BY = auto() 295 GROUPING_SETS = auto() 296 HAVING = auto() 297 HINT = auto() 298 IGNORE = auto() 299 ILIKE = auto() 300 ILIKE_ANY = auto() 301 IN = auto() 302 INDEX = auto() 303 INNER = auto() 304 INSERT = auto() 305 INTERSECT = auto() 306 INTERVAL = auto() 307 INTO = auto() 308 INTRODUCER = auto() 309 IRLIKE = auto() 310 IS = auto() 311 ISNULL = auto() 312 JOIN = auto() 313 JOIN_MARKER = auto() 314 KEEP = auto() 315 KEY = auto() 316 KILL = auto() 317 LANGUAGE = auto() 318 LATERAL = auto() 319 LEFT = auto() 320 LIKE = auto() 321 LIKE_ANY = auto() 322 LIMIT = auto() 323 LIST = auto() 324 LOAD = auto() 325 LOCK = auto() 326 MAP = auto() 327 MATCH_CONDITION = auto() 328 MATCH_RECOGNIZE = auto() 329 MEMBER_OF = auto() 330 MERGE = auto() 331 MOD = auto() 332 MODEL = auto() 333 NATURAL = auto() 334 NEXT = auto() 335 NOTNULL = auto() 336 NULL = auto() 337 OBJECT_IDENTIFIER = auto() 338 OFFSET = auto() 339 ON = auto() 340 ONLY = auto() 341 OPERATOR = auto() 342 ORDER_BY = auto() 343 ORDER_SIBLINGS_BY = auto() 344 ORDERED = auto() 345 ORDINALITY = auto() 346 OUTER = auto() 347 OVER = auto() 348 OVERLAPS = auto() 349 OVERWRITE = auto() 350 PARTITION = auto() 351 PARTITION_BY = auto() 352 PERCENT = auto() 353 PIVOT = auto() 354 PLACEHOLDER = auto() 355 POSITIONAL = auto() 356 PRAGMA = auto() 357 PREWHERE = auto() 358 PRIMARY_KEY = auto() 359 PROCEDURE = auto() 360 PROPERTIES = auto() 361 PSEUDO_TYPE = auto() 362 PUT = auto() 363 QUALIFY = auto() 364 QUOTE = auto() 365 RANGE = auto() 366 RECURSIVE = auto() 367 REFRESH = auto() 368 RENAME = auto() 369 REPLACE = auto() 370 RETURNING = auto() 371 REFERENCES = auto() 372 RIGHT = auto() 373 RLIKE = auto() 374 ROLLBACK = auto() 375 ROLLUP = auto() 376 ROW = auto() 377 ROWS = auto() 378 SELECT = auto() 379 SEMI = auto() 380 SEPARATOR = auto() 381 SEQUENCE = auto() 382 SERDE_PROPERTIES = auto() 383 SET = auto() 384 SETTINGS = auto() 385 SHOW = auto() 386 SIMILAR_TO = auto() 387 SOME = auto() 388 SORT_BY = auto() 389 START_WITH = auto() 390 STORAGE_INTEGRATION = auto() 391 STRAIGHT_JOIN = auto() 392 STRUCT = auto() 393 SUMMARIZE = auto() 394 TABLE_SAMPLE = auto() 395 TAG = auto() 396 TEMPORARY = auto() 397 TOP = auto() 398 THEN = auto() 399 TRUE = auto() 400 TRUNCATE = auto() 401 UNCACHE = auto() 402 UNION = auto() 403 UNNEST = auto() 404 UNPIVOT = auto() 405 UPDATE = auto() 406 USE = auto() 407 USING = auto() 408 VALUES = auto() 409 VIEW = auto() 410 VOLATILE = auto() 411 WHEN = auto() 412 WHERE = auto() 413 WINDOW = auto() 414 WITH = auto() 415 UNIQUE = auto() 416 VERSION_SNAPSHOT = auto() 417 TIMESTAMP_SNAPSHOT = auto() 418 OPTION = auto() 419 SINK = auto() 420 SOURCE = auto() 421 ANALYZE = auto() 422 NAMESPACE = auto() 423 EXPORT = 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'>
DOTCOLON =
<TokenType.DOTCOLON: 'DOTCOLON'>
DCOLON =
<TokenType.DCOLON: 'DCOLON'>
DQMARK =
<TokenType.DQMARK: 'DQMARK'>
SEMICOLON =
<TokenType.SEMICOLON: 'SEMICOLON'>
STAR =
<TokenType.STAR: 'STAR'>
BACKSLASH =
<TokenType.BACKSLASH: 'BACKSLASH'>
SLASH =
<TokenType.SLASH: 'SLASH'>
LT =
<TokenType.LT: 'LT'>
LTE =
<TokenType.LTE: 'LTE'>
GT =
<TokenType.GT: 'GT'>
GTE =
<TokenType.GTE: 'GTE'>
NOT =
<TokenType.NOT: 'NOT'>
EQ =
<TokenType.EQ: 'EQ'>
NEQ =
<TokenType.NEQ: 'NEQ'>
NULLSAFE_EQ =
<TokenType.NULLSAFE_EQ: 'NULLSAFE_EQ'>
COLON_EQ =
<TokenType.COLON_EQ: 'COLON_EQ'>
AND =
<TokenType.AND: 'AND'>
OR =
<TokenType.OR: 'OR'>
AMP =
<TokenType.AMP: 'AMP'>
DPIPE =
<TokenType.DPIPE: 'DPIPE'>
PIPE =
<TokenType.PIPE: 'PIPE'>
PIPE_SLASH =
<TokenType.PIPE_SLASH: 'PIPE_SLASH'>
DPIPE_SLASH =
<TokenType.DPIPE_SLASH: 'DPIPE_SLASH'>
CARET =
<TokenType.CARET: 'CARET'>
CARET_AT =
<TokenType.CARET_AT: 'CARET_AT'>
TILDA =
<TokenType.TILDA: 'TILDA'>
ARROW =
<TokenType.ARROW: 'ARROW'>
DARROW =
<TokenType.DARROW: 'DARROW'>
FARROW =
<TokenType.FARROW: 'FARROW'>
HASH =
<TokenType.HASH: 'HASH'>
HASH_ARROW =
<TokenType.HASH_ARROW: 'HASH_ARROW'>
DHASH_ARROW =
<TokenType.DHASH_ARROW: 'DHASH_ARROW'>
LR_ARROW =
<TokenType.LR_ARROW: 'LR_ARROW'>
DAT =
<TokenType.DAT: 'DAT'>
LT_AT =
<TokenType.LT_AT: 'LT_AT'>
AT_GT =
<TokenType.AT_GT: 'AT_GT'>
DOLLAR =
<TokenType.DOLLAR: 'DOLLAR'>
PARAMETER =
<TokenType.PARAMETER: 'PARAMETER'>
SESSION_PARAMETER =
<TokenType.SESSION_PARAMETER: 'SESSION_PARAMETER'>
DAMP =
<TokenType.DAMP: 'DAMP'>
XOR =
<TokenType.XOR: 'XOR'>
DSTAR =
<TokenType.DSTAR: 'DSTAR'>
URI_START =
<TokenType.URI_START: 'URI_START'>
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'>
UDOUBLE =
<TokenType.UDOUBLE: 'UDOUBLE'>
DECIMAL =
<TokenType.DECIMAL: 'DECIMAL'>
DECIMAL32 =
<TokenType.DECIMAL32: 'DECIMAL32'>
DECIMAL64 =
<TokenType.DECIMAL64: 'DECIMAL64'>
DECIMAL128 =
<TokenType.DECIMAL128: 'DECIMAL128'>
DECIMAL256 =
<TokenType.DECIMAL256: 'DECIMAL256'>
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'>
BLOB =
<TokenType.BLOB: 'BLOB'>
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'>
DATETIME2 =
<TokenType.DATETIME2: 'DATETIME2'>
DATETIME64 =
<TokenType.DATETIME64: 'DATETIME64'>
SMALLDATETIME =
<TokenType.SMALLDATETIME: 'SMALLDATETIME'>
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'>
POINT =
<TokenType.POINT: 'POINT'>
RING =
<TokenType.RING: 'RING'>
LINESTRING =
<TokenType.LINESTRING: 'LINESTRING'>
MULTILINESTRING =
<TokenType.MULTILINESTRING: 'MULTILINESTRING'>
POLYGON =
<TokenType.POLYGON: 'POLYGON'>
MULTIPOLYGON =
<TokenType.MULTIPOLYGON: 'MULTIPOLYGON'>
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'>
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'>
DYNAMIC =
<TokenType.DYNAMIC: 'DYNAMIC'>
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'>
ATTACH =
<TokenType.ATTACH: 'ATTACH'>
AUTO_INCREMENT =
<TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>
BEGIN =
<TokenType.BEGIN: 'BEGIN'>
BETWEEN =
<TokenType.BETWEEN: 'BETWEEN'>
BULK_COLLECT_INTO =
<TokenType.BULK_COLLECT_INTO: 'BULK_COLLECT_INTO'>
CACHE =
<TokenType.CACHE: 'CACHE'>
CASE =
<TokenType.CASE: 'CASE'>
CHARACTER_SET =
<TokenType.CHARACTER_SET: 'CHARACTER_SET'>
CLUSTER_BY =
<TokenType.CLUSTER_BY: 'CLUSTER_BY'>
COLLATE =
<TokenType.COLLATE: 'COLLATE'>
COMMAND =
<TokenType.COMMAND: 'COMMAND'>
COMMENT =
<TokenType.COMMENT: 'COMMENT'>
COMMIT =
<TokenType.COMMIT: 'COMMIT'>
CONNECT_BY =
<TokenType.CONNECT_BY: 'CONNECT_BY'>
CONSTRAINT =
<TokenType.CONSTRAINT: 'CONSTRAINT'>
COPY =
<TokenType.COPY: 'COPY'>
CREATE =
<TokenType.CREATE: 'CREATE'>
CROSS =
<TokenType.CROSS: 'CROSS'>
CUBE =
<TokenType.CUBE: 'CUBE'>
CURRENT_DATE =
<TokenType.CURRENT_DATE: 'CURRENT_DATE'>
CURRENT_DATETIME =
<TokenType.CURRENT_DATETIME: 'CURRENT_DATETIME'>
CURRENT_SCHEMA =
<TokenType.CURRENT_SCHEMA: 'CURRENT_SCHEMA'>
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'>
DETACH =
<TokenType.DETACH: 'DETACH'>
DICTIONARY =
<TokenType.DICTIONARY: 'DICTIONARY'>
DISTINCT =
<TokenType.DISTINCT: 'DISTINCT'>
DISTRIBUTE_BY =
<TokenType.DISTRIBUTE_BY: 'DISTRIBUTE_BY'>
DIV =
<TokenType.DIV: 'DIV'>
DROP =
<TokenType.DROP: 'DROP'>
ELSE =
<TokenType.ELSE: 'ELSE'>
END =
<TokenType.END: 'END'>
ESCAPE =
<TokenType.ESCAPE: 'ESCAPE'>
EXCEPT =
<TokenType.EXCEPT: 'EXCEPT'>
EXECUTE =
<TokenType.EXECUTE: 'EXECUTE'>
EXISTS =
<TokenType.EXISTS: 'EXISTS'>
FALSE =
<TokenType.FALSE: 'FALSE'>
FETCH =
<TokenType.FETCH: 'FETCH'>
FILTER =
<TokenType.FILTER: 'FILTER'>
FINAL =
<TokenType.FINAL: 'FINAL'>
FIRST =
<TokenType.FIRST: 'FIRST'>
FOR =
<TokenType.FOR: 'FOR'>
FORCE =
<TokenType.FORCE: 'FORCE'>
FOREIGN_KEY =
<TokenType.FOREIGN_KEY: 'FOREIGN_KEY'>
FORMAT =
<TokenType.FORMAT: 'FORMAT'>
FROM =
<TokenType.FROM: 'FROM'>
FULL =
<TokenType.FULL: 'FULL'>
FUNCTION =
<TokenType.FUNCTION: 'FUNCTION'>
GLOB =
<TokenType.GLOB: 'GLOB'>
GLOBAL =
<TokenType.GLOBAL: 'GLOBAL'>
GRANT =
<TokenType.GRANT: 'GRANT'>
GROUP_BY =
<TokenType.GROUP_BY: 'GROUP_BY'>
GROUPING_SETS =
<TokenType.GROUPING_SETS: 'GROUPING_SETS'>
HAVING =
<TokenType.HAVING: 'HAVING'>
HINT =
<TokenType.HINT: 'HINT'>
IGNORE =
<TokenType.IGNORE: 'IGNORE'>
ILIKE =
<TokenType.ILIKE: 'ILIKE'>
ILIKE_ANY =
<TokenType.ILIKE_ANY: 'ILIKE_ANY'>
IN =
<TokenType.IN: 'IN'>
INDEX =
<TokenType.INDEX: 'INDEX'>
INNER =
<TokenType.INNER: 'INNER'>
INSERT =
<TokenType.INSERT: 'INSERT'>
INTERSECT =
<TokenType.INTERSECT: 'INTERSECT'>
INTERVAL =
<TokenType.INTERVAL: 'INTERVAL'>
INTO =
<TokenType.INTO: 'INTO'>
INTRODUCER =
<TokenType.INTRODUCER: 'INTRODUCER'>
IRLIKE =
<TokenType.IRLIKE: 'IRLIKE'>
IS =
<TokenType.IS: 'IS'>
ISNULL =
<TokenType.ISNULL: 'ISNULL'>
JOIN =
<TokenType.JOIN: 'JOIN'>
JOIN_MARKER =
<TokenType.JOIN_MARKER: 'JOIN_MARKER'>
KEEP =
<TokenType.KEEP: 'KEEP'>
KEY =
<TokenType.KEY: 'KEY'>
KILL =
<TokenType.KILL: 'KILL'>
LANGUAGE =
<TokenType.LANGUAGE: 'LANGUAGE'>
LATERAL =
<TokenType.LATERAL: 'LATERAL'>
LEFT =
<TokenType.LEFT: 'LEFT'>
LIKE =
<TokenType.LIKE: 'LIKE'>
LIKE_ANY =
<TokenType.LIKE_ANY: 'LIKE_ANY'>
LIMIT =
<TokenType.LIMIT: 'LIMIT'>
LIST =
<TokenType.LIST: 'LIST'>
LOAD =
<TokenType.LOAD: 'LOAD'>
LOCK =
<TokenType.LOCK: 'LOCK'>
MAP =
<TokenType.MAP: 'MAP'>
MATCH_CONDITION =
<TokenType.MATCH_CONDITION: 'MATCH_CONDITION'>
MATCH_RECOGNIZE =
<TokenType.MATCH_RECOGNIZE: 'MATCH_RECOGNIZE'>
MEMBER_OF =
<TokenType.MEMBER_OF: 'MEMBER_OF'>
MERGE =
<TokenType.MERGE: 'MERGE'>
MOD =
<TokenType.MOD: 'MOD'>
MODEL =
<TokenType.MODEL: 'MODEL'>
NATURAL =
<TokenType.NATURAL: 'NATURAL'>
NEXT =
<TokenType.NEXT: 'NEXT'>
NOTNULL =
<TokenType.NOTNULL: 'NOTNULL'>
NULL =
<TokenType.NULL: 'NULL'>
OBJECT_IDENTIFIER =
<TokenType.OBJECT_IDENTIFIER: 'OBJECT_IDENTIFIER'>
OFFSET =
<TokenType.OFFSET: 'OFFSET'>
ON =
<TokenType.ON: 'ON'>
ONLY =
<TokenType.ONLY: 'ONLY'>
OPERATOR =
<TokenType.OPERATOR: 'OPERATOR'>
ORDER_BY =
<TokenType.ORDER_BY: 'ORDER_BY'>
ORDER_SIBLINGS_BY =
<TokenType.ORDER_SIBLINGS_BY: 'ORDER_SIBLINGS_BY'>
ORDERED =
<TokenType.ORDERED: 'ORDERED'>
ORDINALITY =
<TokenType.ORDINALITY: 'ORDINALITY'>
OUTER =
<TokenType.OUTER: 'OUTER'>
OVER =
<TokenType.OVER: 'OVER'>
OVERLAPS =
<TokenType.OVERLAPS: 'OVERLAPS'>
OVERWRITE =
<TokenType.OVERWRITE: 'OVERWRITE'>
PARTITION =
<TokenType.PARTITION: 'PARTITION'>
PARTITION_BY =
<TokenType.PARTITION_BY: 'PARTITION_BY'>
PERCENT =
<TokenType.PERCENT: 'PERCENT'>
PIVOT =
<TokenType.PIVOT: 'PIVOT'>
PLACEHOLDER =
<TokenType.PLACEHOLDER: 'PLACEHOLDER'>
POSITIONAL =
<TokenType.POSITIONAL: 'POSITIONAL'>
PRAGMA =
<TokenType.PRAGMA: 'PRAGMA'>
PREWHERE =
<TokenType.PREWHERE: 'PREWHERE'>
PRIMARY_KEY =
<TokenType.PRIMARY_KEY: 'PRIMARY_KEY'>
PROCEDURE =
<TokenType.PROCEDURE: 'PROCEDURE'>
PROPERTIES =
<TokenType.PROPERTIES: 'PROPERTIES'>
PSEUDO_TYPE =
<TokenType.PSEUDO_TYPE: 'PSEUDO_TYPE'>
PUT =
<TokenType.PUT: 'PUT'>
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'>
SINK =
<TokenType.SINK: 'SINK'>
SOURCE =
<TokenType.SOURCE: 'SOURCE'>
ANALYZE =
<TokenType.ANALYZE: 'ANALYZE'>
NAMESPACE =
<TokenType.NAMESPACE: 'NAMESPACE'>
EXPORT =
<TokenType.EXPORT: 'EXPORT'>
class
Token:
430class Token: 431 __slots__ = ("token_type", "text", "line", "col", "start", "end", "comments") 432 433 @classmethod 434 def number(cls, number: int) -> Token: 435 """Returns a NUMBER token with `number` as its text.""" 436 return cls(TokenType.NUMBER, str(number)) 437 438 @classmethod 439 def string(cls, string: str) -> Token: 440 """Returns a STRING token with `string` as its text.""" 441 return cls(TokenType.STRING, string) 442 443 @classmethod 444 def identifier(cls, identifier: str) -> Token: 445 """Returns an IDENTIFIER token with `identifier` as its text.""" 446 return cls(TokenType.IDENTIFIER, identifier) 447 448 @classmethod 449 def var(cls, var: str) -> Token: 450 """Returns an VAR token with `var` as its text.""" 451 return cls(TokenType.VAR, var) 452 453 def __init__( 454 self, 455 token_type: TokenType, 456 text: str, 457 line: int = 1, 458 col: int = 1, 459 start: int = 0, 460 end: int = 0, 461 comments: t.Optional[t.List[str]] = None, 462 ) -> None: 463 """Token initializer. 464 465 Args: 466 token_type: The TokenType Enum. 467 text: The text of the token. 468 line: The line that the token ends on. 469 col: The column that the token ends on. 470 start: The start index of the token. 471 end: The ending index of the token. 472 comments: The comments to attach to the token. 473 """ 474 self.token_type = token_type 475 self.text = text 476 self.line = line 477 self.col = col 478 self.start = start 479 self.end = end 480 self.comments = [] if comments is None else comments 481 482 def __repr__(self) -> str: 483 attributes = ", ".join(f"{k}: {getattr(self, k)}" for k in self.__slots__) 484 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)
453 def __init__( 454 self, 455 token_type: TokenType, 456 text: str, 457 line: int = 1, 458 col: int = 1, 459 start: int = 0, 460 end: int = 0, 461 comments: t.Optional[t.List[str]] = None, 462 ) -> None: 463 """Token initializer. 464 465 Args: 466 token_type: The TokenType Enum. 467 text: The text of the token. 468 line: The line that the token ends on. 469 col: The column that the token ends on. 470 start: The start index of the token. 471 end: The ending index of the token. 472 comments: The comments to attach to the token. 473 """ 474 self.token_type = token_type 475 self.text = text 476 self.line = line 477 self.col = col 478 self.start = start 479 self.end = end 480 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.
433 @classmethod 434 def number(cls, number: int) -> Token: 435 """Returns a NUMBER token with `number` as its text.""" 436 return cls(TokenType.NUMBER, str(number))
Returns a NUMBER token with number
as its text.
438 @classmethod 439 def string(cls, string: str) -> Token: 440 """Returns a STRING token with `string` as its text.""" 441 return cls(TokenType.STRING, string)
Returns a STRING token with string
as its text.
443 @classmethod 444 def identifier(cls, identifier: str) -> Token: 445 """Returns an IDENTIFIER token with `identifier` as its text.""" 446 return cls(TokenType.IDENTIFIER, identifier)
Returns an IDENTIFIER token with identifier
as its text.
class
Tokenizer:
594class Tokenizer(metaclass=_Tokenizer): 595 SINGLE_TOKENS = { 596 "(": TokenType.L_PAREN, 597 ")": TokenType.R_PAREN, 598 "[": TokenType.L_BRACKET, 599 "]": TokenType.R_BRACKET, 600 "{": TokenType.L_BRACE, 601 "}": TokenType.R_BRACE, 602 "&": TokenType.AMP, 603 "^": TokenType.CARET, 604 ":": TokenType.COLON, 605 ",": TokenType.COMMA, 606 ".": TokenType.DOT, 607 "-": TokenType.DASH, 608 "=": TokenType.EQ, 609 ">": TokenType.GT, 610 "<": TokenType.LT, 611 "%": TokenType.MOD, 612 "!": TokenType.NOT, 613 "|": TokenType.PIPE, 614 "+": TokenType.PLUS, 615 ";": TokenType.SEMICOLON, 616 "/": TokenType.SLASH, 617 "\\": TokenType.BACKSLASH, 618 "*": TokenType.STAR, 619 "~": TokenType.TILDA, 620 "?": TokenType.PLACEHOLDER, 621 "@": TokenType.PARAMETER, 622 "#": TokenType.HASH, 623 # Used for breaking a var like x'y' but nothing else the token type doesn't matter 624 "'": TokenType.UNKNOWN, 625 "`": TokenType.UNKNOWN, 626 '"': TokenType.UNKNOWN, 627 } 628 629 BIT_STRINGS: t.List[str | t.Tuple[str, str]] = [] 630 BYTE_STRINGS: t.List[str | t.Tuple[str, str]] = [] 631 HEX_STRINGS: t.List[str | t.Tuple[str, str]] = [] 632 RAW_STRINGS: t.List[str | t.Tuple[str, str]] = [] 633 HEREDOC_STRINGS: t.List[str | t.Tuple[str, str]] = [] 634 UNICODE_STRINGS: t.List[str | t.Tuple[str, str]] = [] 635 IDENTIFIERS: t.List[str | t.Tuple[str, str]] = ['"'] 636 QUOTES: t.List[t.Tuple[str, str] | str] = ["'"] 637 STRING_ESCAPES = ["'"] 638 VAR_SINGLE_TOKENS: t.Set[str] = set() 639 640 # The strings in this list can always be used as escapes, regardless of the surrounding 641 # identifier delimiters. By default, the closing delimiter is assumed to also act as an 642 # identifier escape, e.g. if we use double-quotes, then they also act as escapes: "x""" 643 IDENTIFIER_ESCAPES: t.List[str] = [] 644 645 # Whether the heredoc tags follow the same lexical rules as unquoted identifiers 646 HEREDOC_TAG_IS_IDENTIFIER = False 647 648 # Token that we'll generate as a fallback if the heredoc prefix doesn't correspond to a heredoc 649 HEREDOC_STRING_ALTERNATIVE = TokenType.VAR 650 651 # Whether string escape characters function as such when placed within raw strings 652 STRING_ESCAPES_ALLOWED_IN_RAW_STRINGS = True 653 654 NESTED_COMMENTS = True 655 656 HINT_START = "/*+" 657 658 TOKENS_PRECEDING_HINT = {TokenType.SELECT, TokenType.INSERT, TokenType.UPDATE, TokenType.DELETE} 659 660 # Autofilled 661 _COMMENTS: t.Dict[str, str] = {} 662 _FORMAT_STRINGS: t.Dict[str, t.Tuple[str, TokenType]] = {} 663 _IDENTIFIERS: t.Dict[str, str] = {} 664 _IDENTIFIER_ESCAPES: t.Set[str] = set() 665 _QUOTES: t.Dict[str, str] = {} 666 _STRING_ESCAPES: t.Set[str] = set() 667 _KEYWORD_TRIE: t.Dict = {} 668 _RS_TOKENIZER: t.Optional[t.Any] = None 669 670 KEYWORDS: t.Dict[str, TokenType] = { 671 **{f"{{%{postfix}": TokenType.BLOCK_START for postfix in ("", "+", "-")}, 672 **{f"{prefix}%}}": TokenType.BLOCK_END for prefix in ("", "+", "-")}, 673 **{f"{{{{{postfix}": TokenType.BLOCK_START for postfix in ("+", "-")}, 674 **{f"{prefix}}}}}": TokenType.BLOCK_END for prefix in ("+", "-")}, 675 HINT_START: TokenType.HINT, 676 "==": TokenType.EQ, 677 "::": TokenType.DCOLON, 678 "||": TokenType.DPIPE, 679 ">=": TokenType.GTE, 680 "<=": TokenType.LTE, 681 "<>": TokenType.NEQ, 682 "!=": TokenType.NEQ, 683 ":=": TokenType.COLON_EQ, 684 "<=>": TokenType.NULLSAFE_EQ, 685 "->": TokenType.ARROW, 686 "->>": TokenType.DARROW, 687 "=>": TokenType.FARROW, 688 "#>": TokenType.HASH_ARROW, 689 "#>>": TokenType.DHASH_ARROW, 690 "<->": TokenType.LR_ARROW, 691 "&&": TokenType.DAMP, 692 "??": TokenType.DQMARK, 693 "~~~": TokenType.GLOB, 694 "~~": TokenType.LIKE, 695 "~~*": TokenType.ILIKE, 696 "~*": TokenType.IRLIKE, 697 "ALL": TokenType.ALL, 698 "ALWAYS": TokenType.ALWAYS, 699 "AND": TokenType.AND, 700 "ANTI": TokenType.ANTI, 701 "ANY": TokenType.ANY, 702 "ASC": TokenType.ASC, 703 "AS": TokenType.ALIAS, 704 "ASOF": TokenType.ASOF, 705 "AUTOINCREMENT": TokenType.AUTO_INCREMENT, 706 "AUTO_INCREMENT": TokenType.AUTO_INCREMENT, 707 "BEGIN": TokenType.BEGIN, 708 "BETWEEN": TokenType.BETWEEN, 709 "CACHE": TokenType.CACHE, 710 "UNCACHE": TokenType.UNCACHE, 711 "CASE": TokenType.CASE, 712 "CHARACTER SET": TokenType.CHARACTER_SET, 713 "CLUSTER BY": TokenType.CLUSTER_BY, 714 "COLLATE": TokenType.COLLATE, 715 "COLUMN": TokenType.COLUMN, 716 "COMMIT": TokenType.COMMIT, 717 "CONNECT BY": TokenType.CONNECT_BY, 718 "CONSTRAINT": TokenType.CONSTRAINT, 719 "COPY": TokenType.COPY, 720 "CREATE": TokenType.CREATE, 721 "CROSS": TokenType.CROSS, 722 "CUBE": TokenType.CUBE, 723 "CURRENT_DATE": TokenType.CURRENT_DATE, 724 "CURRENT_SCHEMA": TokenType.CURRENT_SCHEMA, 725 "CURRENT_TIME": TokenType.CURRENT_TIME, 726 "CURRENT_TIMESTAMP": TokenType.CURRENT_TIMESTAMP, 727 "CURRENT_USER": TokenType.CURRENT_USER, 728 "DATABASE": TokenType.DATABASE, 729 "DEFAULT": TokenType.DEFAULT, 730 "DELETE": TokenType.DELETE, 731 "DESC": TokenType.DESC, 732 "DESCRIBE": TokenType.DESCRIBE, 733 "DISTINCT": TokenType.DISTINCT, 734 "DISTRIBUTE BY": TokenType.DISTRIBUTE_BY, 735 "DIV": TokenType.DIV, 736 "DROP": TokenType.DROP, 737 "ELSE": TokenType.ELSE, 738 "END": TokenType.END, 739 "ENUM": TokenType.ENUM, 740 "ESCAPE": TokenType.ESCAPE, 741 "EXCEPT": TokenType.EXCEPT, 742 "EXECUTE": TokenType.EXECUTE, 743 "EXISTS": TokenType.EXISTS, 744 "FALSE": TokenType.FALSE, 745 "FETCH": TokenType.FETCH, 746 "FILTER": TokenType.FILTER, 747 "FIRST": TokenType.FIRST, 748 "FULL": TokenType.FULL, 749 "FUNCTION": TokenType.FUNCTION, 750 "FOR": TokenType.FOR, 751 "FOREIGN KEY": TokenType.FOREIGN_KEY, 752 "FORMAT": TokenType.FORMAT, 753 "FROM": TokenType.FROM, 754 "GEOGRAPHY": TokenType.GEOGRAPHY, 755 "GEOMETRY": TokenType.GEOMETRY, 756 "GLOB": TokenType.GLOB, 757 "GROUP BY": TokenType.GROUP_BY, 758 "GROUPING SETS": TokenType.GROUPING_SETS, 759 "HAVING": TokenType.HAVING, 760 "ILIKE": TokenType.ILIKE, 761 "IN": TokenType.IN, 762 "INDEX": TokenType.INDEX, 763 "INET": TokenType.INET, 764 "INNER": TokenType.INNER, 765 "INSERT": TokenType.INSERT, 766 "INTERVAL": TokenType.INTERVAL, 767 "INTERSECT": TokenType.INTERSECT, 768 "INTO": TokenType.INTO, 769 "IS": TokenType.IS, 770 "ISNULL": TokenType.ISNULL, 771 "JOIN": TokenType.JOIN, 772 "KEEP": TokenType.KEEP, 773 "KILL": TokenType.KILL, 774 "LATERAL": TokenType.LATERAL, 775 "LEFT": TokenType.LEFT, 776 "LIKE": TokenType.LIKE, 777 "LIMIT": TokenType.LIMIT, 778 "LOAD": TokenType.LOAD, 779 "LOCK": TokenType.LOCK, 780 "MERGE": TokenType.MERGE, 781 "NAMESPACE": TokenType.NAMESPACE, 782 "NATURAL": TokenType.NATURAL, 783 "NEXT": TokenType.NEXT, 784 "NOT": TokenType.NOT, 785 "NOTNULL": TokenType.NOTNULL, 786 "NULL": TokenType.NULL, 787 "OBJECT": TokenType.OBJECT, 788 "OFFSET": TokenType.OFFSET, 789 "ON": TokenType.ON, 790 "OR": TokenType.OR, 791 "XOR": TokenType.XOR, 792 "ORDER BY": TokenType.ORDER_BY, 793 "ORDINALITY": TokenType.ORDINALITY, 794 "OUTER": TokenType.OUTER, 795 "OVER": TokenType.OVER, 796 "OVERLAPS": TokenType.OVERLAPS, 797 "OVERWRITE": TokenType.OVERWRITE, 798 "PARTITION": TokenType.PARTITION, 799 "PARTITION BY": TokenType.PARTITION_BY, 800 "PARTITIONED BY": TokenType.PARTITION_BY, 801 "PARTITIONED_BY": TokenType.PARTITION_BY, 802 "PERCENT": TokenType.PERCENT, 803 "PIVOT": TokenType.PIVOT, 804 "PRAGMA": TokenType.PRAGMA, 805 "PRIMARY KEY": TokenType.PRIMARY_KEY, 806 "PROCEDURE": TokenType.PROCEDURE, 807 "QUALIFY": TokenType.QUALIFY, 808 "RANGE": TokenType.RANGE, 809 "RECURSIVE": TokenType.RECURSIVE, 810 "REGEXP": TokenType.RLIKE, 811 "RENAME": TokenType.RENAME, 812 "REPLACE": TokenType.REPLACE, 813 "RETURNING": TokenType.RETURNING, 814 "REFERENCES": TokenType.REFERENCES, 815 "RIGHT": TokenType.RIGHT, 816 "RLIKE": TokenType.RLIKE, 817 "ROLLBACK": TokenType.ROLLBACK, 818 "ROLLUP": TokenType.ROLLUP, 819 "ROW": TokenType.ROW, 820 "ROWS": TokenType.ROWS, 821 "SCHEMA": TokenType.SCHEMA, 822 "SELECT": TokenType.SELECT, 823 "SEMI": TokenType.SEMI, 824 "SET": TokenType.SET, 825 "SETTINGS": TokenType.SETTINGS, 826 "SHOW": TokenType.SHOW, 827 "SIMILAR TO": TokenType.SIMILAR_TO, 828 "SOME": TokenType.SOME, 829 "SORT BY": TokenType.SORT_BY, 830 "START WITH": TokenType.START_WITH, 831 "STRAIGHT_JOIN": TokenType.STRAIGHT_JOIN, 832 "TABLE": TokenType.TABLE, 833 "TABLESAMPLE": TokenType.TABLE_SAMPLE, 834 "TEMP": TokenType.TEMPORARY, 835 "TEMPORARY": TokenType.TEMPORARY, 836 "THEN": TokenType.THEN, 837 "TRUE": TokenType.TRUE, 838 "TRUNCATE": TokenType.TRUNCATE, 839 "UNION": TokenType.UNION, 840 "UNKNOWN": TokenType.UNKNOWN, 841 "UNNEST": TokenType.UNNEST, 842 "UNPIVOT": TokenType.UNPIVOT, 843 "UPDATE": TokenType.UPDATE, 844 "USE": TokenType.USE, 845 "USING": TokenType.USING, 846 "UUID": TokenType.UUID, 847 "VALUES": TokenType.VALUES, 848 "VIEW": TokenType.VIEW, 849 "VOLATILE": TokenType.VOLATILE, 850 "WHEN": TokenType.WHEN, 851 "WHERE": TokenType.WHERE, 852 "WINDOW": TokenType.WINDOW, 853 "WITH": TokenType.WITH, 854 "APPLY": TokenType.APPLY, 855 "ARRAY": TokenType.ARRAY, 856 "BIT": TokenType.BIT, 857 "BOOL": TokenType.BOOLEAN, 858 "BOOLEAN": TokenType.BOOLEAN, 859 "BYTE": TokenType.TINYINT, 860 "MEDIUMINT": TokenType.MEDIUMINT, 861 "INT1": TokenType.TINYINT, 862 "TINYINT": TokenType.TINYINT, 863 "INT16": TokenType.SMALLINT, 864 "SHORT": TokenType.SMALLINT, 865 "SMALLINT": TokenType.SMALLINT, 866 "HUGEINT": TokenType.INT128, 867 "UHUGEINT": TokenType.UINT128, 868 "INT2": TokenType.SMALLINT, 869 "INTEGER": TokenType.INT, 870 "INT": TokenType.INT, 871 "INT4": TokenType.INT, 872 "INT32": TokenType.INT, 873 "INT64": TokenType.BIGINT, 874 "INT128": TokenType.INT128, 875 "INT256": TokenType.INT256, 876 "LONG": TokenType.BIGINT, 877 "BIGINT": TokenType.BIGINT, 878 "INT8": TokenType.TINYINT, 879 "UINT": TokenType.UINT, 880 "UINT128": TokenType.UINT128, 881 "UINT256": TokenType.UINT256, 882 "DEC": TokenType.DECIMAL, 883 "DECIMAL": TokenType.DECIMAL, 884 "DECIMAL32": TokenType.DECIMAL32, 885 "DECIMAL64": TokenType.DECIMAL64, 886 "DECIMAL128": TokenType.DECIMAL128, 887 "DECIMAL256": TokenType.DECIMAL256, 888 "BIGDECIMAL": TokenType.BIGDECIMAL, 889 "BIGNUMERIC": TokenType.BIGDECIMAL, 890 "LIST": TokenType.LIST, 891 "MAP": TokenType.MAP, 892 "NULLABLE": TokenType.NULLABLE, 893 "NUMBER": TokenType.DECIMAL, 894 "NUMERIC": TokenType.DECIMAL, 895 "FIXED": TokenType.DECIMAL, 896 "REAL": TokenType.FLOAT, 897 "FLOAT": TokenType.FLOAT, 898 "FLOAT4": TokenType.FLOAT, 899 "FLOAT8": TokenType.DOUBLE, 900 "DOUBLE": TokenType.DOUBLE, 901 "DOUBLE PRECISION": TokenType.DOUBLE, 902 "JSON": TokenType.JSON, 903 "JSONB": TokenType.JSONB, 904 "CHAR": TokenType.CHAR, 905 "CHARACTER": TokenType.CHAR, 906 "NCHAR": TokenType.NCHAR, 907 "VARCHAR": TokenType.VARCHAR, 908 "VARCHAR2": TokenType.VARCHAR, 909 "NVARCHAR": TokenType.NVARCHAR, 910 "NVARCHAR2": TokenType.NVARCHAR, 911 "BPCHAR": TokenType.BPCHAR, 912 "STR": TokenType.TEXT, 913 "STRING": TokenType.TEXT, 914 "TEXT": TokenType.TEXT, 915 "LONGTEXT": TokenType.LONGTEXT, 916 "MEDIUMTEXT": TokenType.MEDIUMTEXT, 917 "TINYTEXT": TokenType.TINYTEXT, 918 "CLOB": TokenType.TEXT, 919 "LONGVARCHAR": TokenType.TEXT, 920 "BINARY": TokenType.BINARY, 921 "BLOB": TokenType.VARBINARY, 922 "LONGBLOB": TokenType.LONGBLOB, 923 "MEDIUMBLOB": TokenType.MEDIUMBLOB, 924 "TINYBLOB": TokenType.TINYBLOB, 925 "BYTEA": TokenType.VARBINARY, 926 "VARBINARY": TokenType.VARBINARY, 927 "TIME": TokenType.TIME, 928 "TIMETZ": TokenType.TIMETZ, 929 "TIMESTAMP": TokenType.TIMESTAMP, 930 "TIMESTAMPTZ": TokenType.TIMESTAMPTZ, 931 "TIMESTAMPLTZ": TokenType.TIMESTAMPLTZ, 932 "TIMESTAMP_LTZ": TokenType.TIMESTAMPLTZ, 933 "TIMESTAMPNTZ": TokenType.TIMESTAMPNTZ, 934 "TIMESTAMP_NTZ": TokenType.TIMESTAMPNTZ, 935 "DATE": TokenType.DATE, 936 "DATETIME": TokenType.DATETIME, 937 "INT4RANGE": TokenType.INT4RANGE, 938 "INT4MULTIRANGE": TokenType.INT4MULTIRANGE, 939 "INT8RANGE": TokenType.INT8RANGE, 940 "INT8MULTIRANGE": TokenType.INT8MULTIRANGE, 941 "NUMRANGE": TokenType.NUMRANGE, 942 "NUMMULTIRANGE": TokenType.NUMMULTIRANGE, 943 "TSRANGE": TokenType.TSRANGE, 944 "TSMULTIRANGE": TokenType.TSMULTIRANGE, 945 "TSTZRANGE": TokenType.TSTZRANGE, 946 "TSTZMULTIRANGE": TokenType.TSTZMULTIRANGE, 947 "DATERANGE": TokenType.DATERANGE, 948 "DATEMULTIRANGE": TokenType.DATEMULTIRANGE, 949 "UNIQUE": TokenType.UNIQUE, 950 "VECTOR": TokenType.VECTOR, 951 "STRUCT": TokenType.STRUCT, 952 "SEQUENCE": TokenType.SEQUENCE, 953 "VARIANT": TokenType.VARIANT, 954 "ALTER": TokenType.ALTER, 955 "ANALYZE": TokenType.ANALYZE, 956 "CALL": TokenType.COMMAND, 957 "COMMENT": TokenType.COMMENT, 958 "EXPLAIN": TokenType.COMMAND, 959 "GRANT": TokenType.GRANT, 960 "OPTIMIZE": TokenType.COMMAND, 961 "PREPARE": TokenType.COMMAND, 962 "VACUUM": TokenType.COMMAND, 963 "USER-DEFINED": TokenType.USERDEFINED, 964 "FOR VERSION": TokenType.VERSION_SNAPSHOT, 965 "FOR TIMESTAMP": TokenType.TIMESTAMP_SNAPSHOT, 966 } 967 968 WHITE_SPACE: t.Dict[t.Optional[str], TokenType] = { 969 " ": TokenType.SPACE, 970 "\t": TokenType.SPACE, 971 "\n": TokenType.BREAK, 972 "\r": TokenType.BREAK, 973 } 974 975 COMMANDS = { 976 TokenType.COMMAND, 977 TokenType.EXECUTE, 978 TokenType.FETCH, 979 TokenType.SHOW, 980 TokenType.RENAME, 981 } 982 983 COMMAND_PREFIX_TOKENS = {TokenType.SEMICOLON, TokenType.BEGIN} 984 985 # Handle numeric literals like in hive (3L = BIGINT) 986 NUMERIC_LITERALS: t.Dict[str, str] = {} 987 988 COMMENTS = ["--", ("/*", "*/")] 989 990 __slots__ = ( 991 "sql", 992 "size", 993 "tokens", 994 "dialect", 995 "use_rs_tokenizer", 996 "_start", 997 "_current", 998 "_line", 999 "_col", 1000 "_comments", 1001 "_char", 1002 "_end", 1003 "_peek", 1004 "_prev_token_line", 1005 "_rs_dialect_settings", 1006 ) 1007 1008 def __init__( 1009 self, dialect: DialectType = None, use_rs_tokenizer: t.Optional[bool] = None 1010 ) -> None: 1011 from sqlglot.dialects import Dialect 1012 1013 self.dialect = Dialect.get_or_raise(dialect) 1014 1015 # initialize `use_rs_tokenizer`, and allow it to be overwritten per Tokenizer instance 1016 self.use_rs_tokenizer = ( 1017 use_rs_tokenizer if use_rs_tokenizer is not None else USE_RS_TOKENIZER 1018 ) 1019 1020 if self.use_rs_tokenizer: 1021 self._rs_dialect_settings = RsTokenizerDialectSettings( 1022 unescaped_sequences=self.dialect.UNESCAPED_SEQUENCES, 1023 identifiers_can_start_with_digit=self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT, 1024 numbers_can_be_underscore_separated=self.dialect.NUMBERS_CAN_BE_UNDERSCORE_SEPARATED, 1025 ) 1026 1027 self.reset() 1028 1029 def reset(self) -> None: 1030 self.sql = "" 1031 self.size = 0 1032 self.tokens: t.List[Token] = [] 1033 self._start = 0 1034 self._current = 0 1035 self._line = 1 1036 self._col = 0 1037 self._comments: t.List[str] = [] 1038 1039 self._char = "" 1040 self._end = False 1041 self._peek = "" 1042 self._prev_token_line = -1 1043 1044 def tokenize(self, sql: str) -> t.List[Token]: 1045 """Returns a list of tokens corresponding to the SQL string `sql`.""" 1046 if self.use_rs_tokenizer: 1047 return self.tokenize_rs(sql) 1048 1049 self.reset() 1050 self.sql = sql 1051 self.size = len(sql) 1052 1053 try: 1054 self._scan() 1055 except Exception as e: 1056 start = max(self._current - 50, 0) 1057 end = min(self._current + 50, self.size - 1) 1058 context = self.sql[start:end] 1059 raise TokenError(f"Error tokenizing '{context}'") from e 1060 1061 return self.tokens 1062 1063 def _scan(self, until: t.Optional[t.Callable] = None) -> None: 1064 while self.size and not self._end: 1065 current = self._current 1066 1067 # Skip spaces here rather than iteratively calling advance() for performance reasons 1068 while current < self.size: 1069 char = self.sql[current] 1070 1071 if char.isspace() and (char == " " or char == "\t"): 1072 current += 1 1073 else: 1074 break 1075 1076 offset = current - self._current if current > self._current else 1 1077 1078 self._start = current 1079 self._advance(offset) 1080 1081 if not self._char.isspace(): 1082 if self._char.isdigit(): 1083 self._scan_number() 1084 elif self._char in self._IDENTIFIERS: 1085 self._scan_identifier(self._IDENTIFIERS[self._char]) 1086 else: 1087 self._scan_keywords() 1088 1089 if until and until(): 1090 break 1091 1092 if self.tokens and self._comments: 1093 self.tokens[-1].comments.extend(self._comments) 1094 1095 def _chars(self, size: int) -> str: 1096 if size == 1: 1097 return self._char 1098 1099 start = self._current - 1 1100 end = start + size 1101 1102 return self.sql[start:end] if end <= self.size else "" 1103 1104 def _advance(self, i: int = 1, alnum: bool = False) -> None: 1105 if self.WHITE_SPACE.get(self._char) is TokenType.BREAK: 1106 # Ensures we don't count an extra line if we get a \r\n line break sequence 1107 if not (self._char == "\r" and self._peek == "\n"): 1108 self._col = 1 1109 self._line += 1 1110 else: 1111 self._col += i 1112 1113 self._current += i 1114 self._end = self._current >= self.size 1115 self._char = self.sql[self._current - 1] 1116 self._peek = "" if self._end else self.sql[self._current] 1117 1118 if alnum and self._char.isalnum(): 1119 # Here we use local variables instead of attributes for better performance 1120 _col = self._col 1121 _current = self._current 1122 _end = self._end 1123 _peek = self._peek 1124 1125 while _peek.isalnum(): 1126 _col += 1 1127 _current += 1 1128 _end = _current >= self.size 1129 _peek = "" if _end else self.sql[_current] 1130 1131 self._col = _col 1132 self._current = _current 1133 self._end = _end 1134 self._peek = _peek 1135 self._char = self.sql[_current - 1] 1136 1137 @property 1138 def _text(self) -> str: 1139 return self.sql[self._start : self._current] 1140 1141 def _add(self, token_type: TokenType, text: t.Optional[str] = None) -> None: 1142 self._prev_token_line = self._line 1143 1144 if self._comments and token_type == TokenType.SEMICOLON and self.tokens: 1145 self.tokens[-1].comments.extend(self._comments) 1146 self._comments = [] 1147 1148 self.tokens.append( 1149 Token( 1150 token_type, 1151 text=self._text if text is None else text, 1152 line=self._line, 1153 col=self._col, 1154 start=self._start, 1155 end=self._current - 1, 1156 comments=self._comments, 1157 ) 1158 ) 1159 self._comments = [] 1160 1161 # If we have either a semicolon or a begin token before the command's token, we'll parse 1162 # whatever follows the command's token as a string 1163 if ( 1164 token_type in self.COMMANDS 1165 and self._peek != ";" 1166 and (len(self.tokens) == 1 or self.tokens[-2].token_type in self.COMMAND_PREFIX_TOKENS) 1167 ): 1168 start = self._current 1169 tokens = len(self.tokens) 1170 self._scan(lambda: self._peek == ";") 1171 self.tokens = self.tokens[:tokens] 1172 text = self.sql[start : self._current].strip() 1173 if text: 1174 self._add(TokenType.STRING, text) 1175 1176 def _scan_keywords(self) -> None: 1177 size = 0 1178 word = None 1179 chars = self._text 1180 char = chars 1181 prev_space = False 1182 skip = False 1183 trie = self._KEYWORD_TRIE 1184 single_token = char in self.SINGLE_TOKENS 1185 1186 while chars: 1187 if skip: 1188 result = TrieResult.PREFIX 1189 else: 1190 result, trie = in_trie(trie, char.upper()) 1191 1192 if result == TrieResult.FAILED: 1193 break 1194 if result == TrieResult.EXISTS: 1195 word = chars 1196 1197 end = self._current + size 1198 size += 1 1199 1200 if end < self.size: 1201 char = self.sql[end] 1202 single_token = single_token or char in self.SINGLE_TOKENS 1203 is_space = char.isspace() 1204 1205 if not is_space or not prev_space: 1206 if is_space: 1207 char = " " 1208 chars += char 1209 prev_space = is_space 1210 skip = False 1211 else: 1212 skip = True 1213 else: 1214 char = "" 1215 break 1216 1217 if word: 1218 if self._scan_string(word): 1219 return 1220 if self._scan_comment(word): 1221 return 1222 if prev_space or single_token or not char: 1223 self._advance(size - 1) 1224 word = word.upper() 1225 self._add(self.KEYWORDS[word], text=word) 1226 return 1227 1228 if self._char in self.SINGLE_TOKENS: 1229 self._add(self.SINGLE_TOKENS[self._char], text=self._char) 1230 return 1231 1232 self._scan_var() 1233 1234 def _scan_comment(self, comment_start: str) -> bool: 1235 if comment_start not in self._COMMENTS: 1236 return False 1237 1238 comment_start_line = self._line 1239 comment_start_size = len(comment_start) 1240 comment_end = self._COMMENTS[comment_start] 1241 1242 if comment_end: 1243 # Skip the comment's start delimiter 1244 self._advance(comment_start_size) 1245 1246 comment_count = 1 1247 comment_end_size = len(comment_end) 1248 1249 while not self._end: 1250 if self._chars(comment_end_size) == comment_end: 1251 comment_count -= 1 1252 if not comment_count: 1253 break 1254 1255 self._advance(alnum=True) 1256 1257 # Nested comments are allowed by some dialects, e.g. databricks, duckdb, postgres 1258 if ( 1259 self.NESTED_COMMENTS 1260 and not self._end 1261 and self._chars(comment_end_size) == comment_start 1262 ): 1263 self._advance(comment_start_size) 1264 comment_count += 1 1265 1266 self._comments.append(self._text[comment_start_size : -comment_end_size + 1]) 1267 self._advance(comment_end_size - 1) 1268 else: 1269 while not self._end and self.WHITE_SPACE.get(self._peek) is not TokenType.BREAK: 1270 self._advance(alnum=True) 1271 self._comments.append(self._text[comment_start_size:]) 1272 1273 if ( 1274 comment_start == self.HINT_START 1275 and self.tokens 1276 and self.tokens[-1].token_type in self.TOKENS_PRECEDING_HINT 1277 ): 1278 self._add(TokenType.HINT) 1279 1280 # Leading comment is attached to the succeeding token, whilst trailing comment to the preceding. 1281 # Multiple consecutive comments are preserved by appending them to the current comments list. 1282 if comment_start_line == self._prev_token_line: 1283 self.tokens[-1].comments.extend(self._comments) 1284 self._comments = [] 1285 self._prev_token_line = self._line 1286 1287 return True 1288 1289 def _scan_number(self) -> None: 1290 if self._char == "0": 1291 peek = self._peek.upper() 1292 if peek == "B": 1293 return self._scan_bits() if self.BIT_STRINGS else self._add(TokenType.NUMBER) 1294 elif peek == "X": 1295 return self._scan_hex() if self.HEX_STRINGS else self._add(TokenType.NUMBER) 1296 1297 decimal = False 1298 scientific = 0 1299 1300 while True: 1301 if self._peek.isdigit(): 1302 self._advance() 1303 elif self._peek == "." and not decimal: 1304 if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER: 1305 return self._add(TokenType.NUMBER) 1306 decimal = True 1307 self._advance() 1308 elif self._peek in ("-", "+") and scientific == 1: 1309 scientific += 1 1310 self._advance() 1311 elif self._peek.upper() == "E" and not scientific: 1312 scientific += 1 1313 self._advance() 1314 elif self._peek.isidentifier(): 1315 number_text = self._text 1316 literal = "" 1317 1318 while self._peek.strip() and self._peek not in self.SINGLE_TOKENS: 1319 literal += self._peek 1320 self._advance() 1321 1322 token_type = self.KEYWORDS.get(self.NUMERIC_LITERALS.get(literal.upper(), "")) 1323 1324 if token_type: 1325 self._add(TokenType.NUMBER, number_text) 1326 self._add(TokenType.DCOLON, "::") 1327 return self._add(token_type, literal) 1328 else: 1329 replaced = literal.replace("_", "") 1330 if self.dialect.NUMBERS_CAN_BE_UNDERSCORE_SEPARATED and replaced.isdigit(): 1331 return self._add(TokenType.NUMBER, number_text + replaced) 1332 if self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT: 1333 return self._add(TokenType.VAR) 1334 1335 self._advance(-len(literal)) 1336 return self._add(TokenType.NUMBER, number_text) 1337 else: 1338 return self._add(TokenType.NUMBER) 1339 1340 def _scan_bits(self) -> None: 1341 self._advance() 1342 value = self._extract_value() 1343 try: 1344 # If `value` can't be converted to a binary, fallback to tokenizing it as an identifier 1345 int(value, 2) 1346 self._add(TokenType.BIT_STRING, value[2:]) # Drop the 0b 1347 except ValueError: 1348 self._add(TokenType.IDENTIFIER) 1349 1350 def _scan_hex(self) -> None: 1351 self._advance() 1352 value = self._extract_value() 1353 try: 1354 # If `value` can't be converted to a hex, fallback to tokenizing it as an identifier 1355 int(value, 16) 1356 self._add(TokenType.HEX_STRING, value[2:]) # Drop the 0x 1357 except ValueError: 1358 self._add(TokenType.IDENTIFIER) 1359 1360 def _extract_value(self) -> str: 1361 while True: 1362 char = self._peek.strip() 1363 if char and char not in self.SINGLE_TOKENS: 1364 self._advance(alnum=True) 1365 else: 1366 break 1367 1368 return self._text 1369 1370 def _scan_string(self, start: str) -> bool: 1371 base = None 1372 token_type = TokenType.STRING 1373 1374 if start in self._QUOTES: 1375 end = self._QUOTES[start] 1376 elif start in self._FORMAT_STRINGS: 1377 end, token_type = self._FORMAT_STRINGS[start] 1378 1379 if token_type == TokenType.HEX_STRING: 1380 base = 16 1381 elif token_type == TokenType.BIT_STRING: 1382 base = 2 1383 elif token_type == TokenType.HEREDOC_STRING: 1384 self._advance() 1385 1386 if self._char == end: 1387 tag = "" 1388 else: 1389 tag = self._extract_string( 1390 end, 1391 raw_string=True, 1392 raise_unmatched=not self.HEREDOC_TAG_IS_IDENTIFIER, 1393 ) 1394 1395 if tag and self.HEREDOC_TAG_IS_IDENTIFIER and (self._end or not tag.isidentifier()): 1396 if not self._end: 1397 self._advance(-1) 1398 1399 self._advance(-len(tag)) 1400 self._add(self.HEREDOC_STRING_ALTERNATIVE) 1401 return True 1402 1403 end = f"{start}{tag}{end}" 1404 else: 1405 return False 1406 1407 self._advance(len(start)) 1408 text = self._extract_string(end, raw_string=token_type == TokenType.RAW_STRING) 1409 1410 if base: 1411 try: 1412 int(text, base) 1413 except Exception: 1414 raise TokenError( 1415 f"Numeric string contains invalid characters from {self._line}:{self._start}" 1416 ) 1417 1418 self._add(token_type, text) 1419 return True 1420 1421 def _scan_identifier(self, identifier_end: str) -> None: 1422 self._advance() 1423 text = self._extract_string( 1424 identifier_end, escapes=self._IDENTIFIER_ESCAPES | {identifier_end} 1425 ) 1426 self._add(TokenType.IDENTIFIER, text) 1427 1428 def _scan_var(self) -> None: 1429 while True: 1430 char = self._peek.strip() 1431 if char and (char in self.VAR_SINGLE_TOKENS or char not in self.SINGLE_TOKENS): 1432 self._advance(alnum=True) 1433 else: 1434 break 1435 1436 self._add( 1437 TokenType.VAR 1438 if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER 1439 else self.KEYWORDS.get(self._text.upper(), TokenType.VAR) 1440 ) 1441 1442 def _extract_string( 1443 self, 1444 delimiter: str, 1445 escapes: t.Optional[t.Set[str]] = None, 1446 raw_string: bool = False, 1447 raise_unmatched: bool = True, 1448 ) -> str: 1449 text = "" 1450 delim_size = len(delimiter) 1451 escapes = self._STRING_ESCAPES if escapes is None else escapes 1452 1453 while True: 1454 if ( 1455 not raw_string 1456 and self.dialect.UNESCAPED_SEQUENCES 1457 and self._peek 1458 and self._char in self.STRING_ESCAPES 1459 ): 1460 unescaped_sequence = self.dialect.UNESCAPED_SEQUENCES.get(self._char + self._peek) 1461 if unescaped_sequence: 1462 self._advance(2) 1463 text += unescaped_sequence 1464 continue 1465 if ( 1466 (self.STRING_ESCAPES_ALLOWED_IN_RAW_STRINGS or not raw_string) 1467 and self._char in escapes 1468 and (self._peek == delimiter or self._peek in escapes) 1469 and (self._char not in self._QUOTES or self._char == self._peek) 1470 ): 1471 if self._peek == delimiter: 1472 text += self._peek 1473 else: 1474 text += self._char + self._peek 1475 1476 if self._current + 1 < self.size: 1477 self._advance(2) 1478 else: 1479 raise TokenError(f"Missing {delimiter} from {self._line}:{self._current}") 1480 else: 1481 if self._chars(delim_size) == delimiter: 1482 if delim_size > 1: 1483 self._advance(delim_size - 1) 1484 break 1485 1486 if self._end: 1487 if not raise_unmatched: 1488 return text + self._char 1489 1490 raise TokenError(f"Missing {delimiter} from {self._line}:{self._start}") 1491 1492 current = self._current - 1 1493 self._advance(alnum=True) 1494 text += self.sql[current : self._current - 1] 1495 1496 return text 1497 1498 def tokenize_rs(self, sql: str) -> t.List[Token]: 1499 if not self._RS_TOKENIZER: 1500 raise SqlglotError("Rust tokenizer is not available") 1501 1502 try: 1503 tokens = self._RS_TOKENIZER.tokenize(sql, self._rs_dialect_settings) 1504 for token in tokens: 1505 token.token_type = _ALL_TOKEN_TYPES[token.token_type_index] 1506 return tokens 1507 except Exception as e: 1508 raise TokenError(str(e))
Tokenizer( dialect: Union[str, sqlglot.dialects.Dialect, Type[sqlglot.dialects.Dialect], NoneType] = None, use_rs_tokenizer: Optional[bool] = None)
1008 def __init__( 1009 self, dialect: DialectType = None, use_rs_tokenizer: t.Optional[bool] = None 1010 ) -> None: 1011 from sqlglot.dialects import Dialect 1012 1013 self.dialect = Dialect.get_or_raise(dialect) 1014 1015 # initialize `use_rs_tokenizer`, and allow it to be overwritten per Tokenizer instance 1016 self.use_rs_tokenizer = ( 1017 use_rs_tokenizer if use_rs_tokenizer is not None else USE_RS_TOKENIZER 1018 ) 1019 1020 if self.use_rs_tokenizer: 1021 self._rs_dialect_settings = RsTokenizerDialectSettings( 1022 unescaped_sequences=self.dialect.UNESCAPED_SEQUENCES, 1023 identifiers_can_start_with_digit=self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT, 1024 numbers_can_be_underscore_separated=self.dialect.NUMBERS_CAN_BE_UNDERSCORE_SEPARATED, 1025 ) 1026 1027 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'>
TOKENS_PRECEDING_HINT =
{<TokenType.UPDATE: 'UPDATE'>, <TokenType.INSERT: 'INSERT'>, <TokenType.DELETE: 'DELETE'>, <TokenType.SELECT: 'SELECT'>}
KEYWORDS: Dict[str, TokenType] =
{'{%': <TokenType.BLOCK_START: 'BLOCK_START'>, '{%+': <TokenType.BLOCK_START: 'BLOCK_START'>, '{%-': <TokenType.BLOCK_START: 'BLOCK_START'>, '%}': <TokenType.BLOCK_END: 'BLOCK_END'>, '+%}': <TokenType.BLOCK_END: 'BLOCK_END'>, '-%}': <TokenType.BLOCK_END: 'BLOCK_END'>, '{{+': <TokenType.BLOCK_START: 'BLOCK_START'>, '{{-': <TokenType.BLOCK_START: 'BLOCK_START'>, '+}}': <TokenType.BLOCK_END: 'BLOCK_END'>, '-}}': <TokenType.BLOCK_END: 'BLOCK_END'>, '/*+': <TokenType.HINT: 'HINT'>, '==': <TokenType.EQ: 'EQ'>, '::': <TokenType.DCOLON: 'DCOLON'>, '||': <TokenType.DPIPE: 'DPIPE'>, '>=': <TokenType.GTE: 'GTE'>, '<=': <TokenType.LTE: 'LTE'>, '<>': <TokenType.NEQ: 'NEQ'>, '!=': <TokenType.NEQ: 'NEQ'>, ':=': <TokenType.COLON_EQ: 'COLON_EQ'>, '<=>': <TokenType.NULLSAFE_EQ: 'NULLSAFE_EQ'>, '->': <TokenType.ARROW: 'ARROW'>, '->>': <TokenType.DARROW: 'DARROW'>, '=>': <TokenType.FARROW: 'FARROW'>, '#>': <TokenType.HASH_ARROW: 'HASH_ARROW'>, '#>>': <TokenType.DHASH_ARROW: 'DHASH_ARROW'>, '<->': <TokenType.LR_ARROW: 'LR_ARROW'>, '&&': <TokenType.DAMP: 'DAMP'>, '??': <TokenType.DQMARK: 'DQMARK'>, '~~~': <TokenType.GLOB: 'GLOB'>, '~~': <TokenType.LIKE: 'LIKE'>, '~~*': <TokenType.ILIKE: 'ILIKE'>, '~*': <TokenType.IRLIKE: 'IRLIKE'>, 'ALL': <TokenType.ALL: 'ALL'>, 'ALWAYS': <TokenType.ALWAYS: 'ALWAYS'>, 'AND': <TokenType.AND: 'AND'>, 'ANTI': <TokenType.ANTI: 'ANTI'>, 'ANY': <TokenType.ANY: 'ANY'>, 'ASC': <TokenType.ASC: 'ASC'>, 'AS': <TokenType.ALIAS: 'ALIAS'>, 'ASOF': <TokenType.ASOF: 'ASOF'>, 'AUTOINCREMENT': <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, 'AUTO_INCREMENT': <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, 'BEGIN': <TokenType.BEGIN: 'BEGIN'>, 'BETWEEN': <TokenType.BETWEEN: 'BETWEEN'>, 'CACHE': <TokenType.CACHE: 'CACHE'>, 'UNCACHE': <TokenType.UNCACHE: 'UNCACHE'>, 'CASE': <TokenType.CASE: 'CASE'>, 'CHARACTER SET': <TokenType.CHARACTER_SET: 'CHARACTER_SET'>, 'CLUSTER BY': <TokenType.CLUSTER_BY: 'CLUSTER_BY'>, 'COLLATE': <TokenType.COLLATE: 'COLLATE'>, 'COLUMN': <TokenType.COLUMN: 'COLUMN'>, 'COMMIT': <TokenType.COMMIT: 'COMMIT'>, 'CONNECT BY': <TokenType.CONNECT_BY: 'CONNECT_BY'>, 'CONSTRAINT': <TokenType.CONSTRAINT: 'CONSTRAINT'>, 'COPY': <TokenType.COPY: 'COPY'>, 'CREATE': <TokenType.CREATE: 'CREATE'>, 'CROSS': <TokenType.CROSS: 'CROSS'>, 'CUBE': <TokenType.CUBE: 'CUBE'>, 'CURRENT_DATE': <TokenType.CURRENT_DATE: 'CURRENT_DATE'>, 'CURRENT_SCHEMA': <TokenType.CURRENT_SCHEMA: 'CURRENT_SCHEMA'>, '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'>, 'NAMESPACE': <TokenType.NAMESPACE: 'NAMESPACE'>, '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'>, 'HUGEINT': <TokenType.INT128: 'INT128'>, 'UHUGEINT': <TokenType.UINT128: 'UINT128'>, 'INT2': <TokenType.SMALLINT: 'SMALLINT'>, 'INTEGER': <TokenType.INT: 'INT'>, 'INT': <TokenType.INT: 'INT'>, 'INT4': <TokenType.INT: 'INT'>, 'INT32': <TokenType.INT: 'INT'>, 'INT64': <TokenType.BIGINT: 'BIGINT'>, 'INT128': <TokenType.INT128: 'INT128'>, 'INT256': <TokenType.INT256: 'INT256'>, 'LONG': <TokenType.BIGINT: 'BIGINT'>, 'BIGINT': <TokenType.BIGINT: 'BIGINT'>, 'INT8': <TokenType.TINYINT: 'TINYINT'>, 'UINT': <TokenType.UINT: 'UINT'>, 'UINT128': <TokenType.UINT128: 'UINT128'>, 'UINT256': <TokenType.UINT256: 'UINT256'>, 'DEC': <TokenType.DECIMAL: 'DECIMAL'>, 'DECIMAL': <TokenType.DECIMAL: 'DECIMAL'>, 'DECIMAL32': <TokenType.DECIMAL32: 'DECIMAL32'>, 'DECIMAL64': <TokenType.DECIMAL64: 'DECIMAL64'>, 'DECIMAL128': <TokenType.DECIMAL128: 'DECIMAL128'>, 'DECIMAL256': <TokenType.DECIMAL256: 'DECIMAL256'>, '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.ANALYZE: 'ANALYZE'>, 'CALL': <TokenType.COMMAND: 'COMMAND'>, 'COMMENT': <TokenType.COMMENT: 'COMMENT'>, 'EXPLAIN': <TokenType.COMMAND: 'COMMAND'>, 'GRANT': <TokenType.GRANT: 'GRANT'>, 'OPTIMIZE': <TokenType.COMMAND: 'COMMAND'>, 'PREPARE': <TokenType.COMMAND: 'COMMAND'>, 'VACUUM': <TokenType.COMMAND: 'COMMAND'>, 'USER-DEFINED': <TokenType.USERDEFINED: 'USERDEFINED'>, 'FOR VERSION': <TokenType.VERSION_SNAPSHOT: 'VERSION_SNAPSHOT'>, 'FOR TIMESTAMP': <TokenType.TIMESTAMP_SNAPSHOT: 'TIMESTAMP_SNAPSHOT'>}
WHITE_SPACE: Dict[Optional[str], TokenType] =
{' ': <TokenType.SPACE: 'SPACE'>, '\t': <TokenType.SPACE: 'SPACE'>, '\n': <TokenType.BREAK: 'BREAK'>, '\r': <TokenType.BREAK: 'BREAK'>}
COMMANDS =
{<TokenType.EXECUTE: 'EXECUTE'>, <TokenType.SHOW: 'SHOW'>, <TokenType.FETCH: 'FETCH'>, <TokenType.RENAME: 'RENAME'>, <TokenType.COMMAND: 'COMMAND'>}
COMMAND_PREFIX_TOKENS =
{<TokenType.BEGIN: 'BEGIN'>, <TokenType.SEMICOLON: 'SEMICOLON'>}
def
reset(self) -> None:
1029 def reset(self) -> None: 1030 self.sql = "" 1031 self.size = 0 1032 self.tokens: t.List[Token] = [] 1033 self._start = 0 1034 self._current = 0 1035 self._line = 1 1036 self._col = 0 1037 self._comments: t.List[str] = [] 1038 1039 self._char = "" 1040 self._end = False 1041 self._peek = "" 1042 self._prev_token_line = -1
1044 def tokenize(self, sql: str) -> t.List[Token]: 1045 """Returns a list of tokens corresponding to the SQL string `sql`.""" 1046 if self.use_rs_tokenizer: 1047 return self.tokenize_rs(sql) 1048 1049 self.reset() 1050 self.sql = sql 1051 self.size = len(sql) 1052 1053 try: 1054 self._scan() 1055 except Exception as e: 1056 start = max(self._current - 50, 0) 1057 end = min(self._current + 50, self.size - 1) 1058 context = self.sql[start:end] 1059 raise TokenError(f"Error tokenizing '{context}'") from e 1060 1061 return self.tokens
Returns a list of tokens corresponding to the SQL string sql
.
1498 def tokenize_rs(self, sql: str) -> t.List[Token]: 1499 if not self._RS_TOKENIZER: 1500 raise SqlglotError("Rust tokenizer is not available") 1501 1502 try: 1503 tokens = self._RS_TOKENIZER.tokenize(sql, self._rs_dialect_settings) 1504 for token in tokens: 1505 token.token_type = _ALL_TOKEN_TYPES[token.token_type_index] 1506 return tokens 1507 except Exception as e: 1508 raise TokenError(str(e))