Edit on GitHub

sqlglot.tokens

   1from __future__ import annotations
   2
   3import os
   4import typing as t
   5from enum import auto
   6
   7from sqlglot.errors import SqlglotError, TokenError
   8from sqlglot.helper import AutoName
   9from sqlglot.trie import TrieResult, in_trie, new_trie
  10
  11if t.TYPE_CHECKING:
  12    from sqlglot.dialects.dialect import DialectType
  13
  14
  15try:
  16    from sqlglotrs import (  # type: ignore
  17        Tokenizer as RsTokenizer,
  18        TokenizerDialectSettings as RsTokenizerDialectSettings,
  19        TokenizerSettings as RsTokenizerSettings,
  20        TokenTypeSettings as RsTokenTypeSettings,
  21    )
  22
  23    USE_RS_TOKENIZER = os.environ.get("SQLGLOTRS_TOKENIZER", "1") == "1"
  24except ImportError:
  25    USE_RS_TOKENIZER = False
  26
  27
  28class TokenType(AutoName):
  29    L_PAREN = auto()
  30    R_PAREN = auto()
  31    L_BRACKET = auto()
  32    R_BRACKET = auto()
  33    L_BRACE = auto()
  34    R_BRACE = auto()
  35    COMMA = auto()
  36    DOT = auto()
  37    DASH = auto()
  38    PLUS = auto()
  39    COLON = auto()
  40    DCOLON = auto()
  41    DQMARK = auto()
  42    SEMICOLON = auto()
  43    STAR = auto()
  44    BACKSLASH = auto()
  45    SLASH = auto()
  46    LT = auto()
  47    LTE = auto()
  48    GT = auto()
  49    GTE = auto()
  50    NOT = auto()
  51    EQ = auto()
  52    NEQ = auto()
  53    NULLSAFE_EQ = auto()
  54    COLON_EQ = auto()
  55    AND = auto()
  56    OR = auto()
  57    AMP = auto()
  58    DPIPE = auto()
  59    PIPE = auto()
  60    CARET = auto()
  61    TILDA = auto()
  62    ARROW = auto()
  63    DARROW = auto()
  64    FARROW = auto()
  65    HASH = auto()
  66    HASH_ARROW = auto()
  67    DHASH_ARROW = auto()
  68    LR_ARROW = auto()
  69    DAT = auto()
  70    LT_AT = auto()
  71    AT_GT = auto()
  72    DOLLAR = auto()
  73    PARAMETER = auto()
  74    SESSION_PARAMETER = auto()
  75    DAMP = auto()
  76    XOR = auto()
  77    DSTAR = auto()
  78
  79    BLOCK_START = auto()
  80    BLOCK_END = auto()
  81
  82    SPACE = auto()
  83    BREAK = auto()
  84
  85    STRING = auto()
  86    NUMBER = auto()
  87    IDENTIFIER = auto()
  88    DATABASE = auto()
  89    COLUMN = auto()
  90    COLUMN_DEF = auto()
  91    SCHEMA = auto()
  92    TABLE = auto()
  93    VAR = auto()
  94    BIT_STRING = auto()
  95    HEX_STRING = auto()
  96    BYTE_STRING = auto()
  97    NATIONAL_STRING = auto()
  98    RAW_STRING = auto()
  99    HEREDOC_STRING = auto()
 100    UNICODE_STRING = auto()
 101
 102    # types
 103    BIT = auto()
 104    BOOLEAN = auto()
 105    TINYINT = auto()
 106    UTINYINT = auto()
 107    SMALLINT = auto()
 108    USMALLINT = auto()
 109    MEDIUMINT = auto()
 110    UMEDIUMINT = auto()
 111    INT = auto()
 112    UINT = auto()
 113    BIGINT = auto()
 114    UBIGINT = auto()
 115    INT128 = auto()
 116    UINT128 = auto()
 117    INT256 = auto()
 118    UINT256 = auto()
 119    FLOAT = auto()
 120    DOUBLE = auto()
 121    DECIMAL = auto()
 122    UDECIMAL = auto()
 123    BIGDECIMAL = auto()
 124    CHAR = auto()
 125    NCHAR = auto()
 126    VARCHAR = auto()
 127    NVARCHAR = auto()
 128    TEXT = auto()
 129    MEDIUMTEXT = auto()
 130    LONGTEXT = auto()
 131    MEDIUMBLOB = auto()
 132    LONGBLOB = auto()
 133    TINYBLOB = auto()
 134    TINYTEXT = auto()
 135    BINARY = auto()
 136    VARBINARY = auto()
 137    JSON = auto()
 138    JSONB = auto()
 139    TIME = auto()
 140    TIMETZ = auto()
 141    TIMESTAMP = auto()
 142    TIMESTAMPTZ = auto()
 143    TIMESTAMPLTZ = auto()
 144    TIMESTAMP_S = auto()
 145    TIMESTAMP_MS = auto()
 146    TIMESTAMP_NS = auto()
 147    DATETIME = auto()
 148    DATETIME64 = auto()
 149    DATE = auto()
 150    DATE32 = auto()
 151    INT4RANGE = auto()
 152    INT4MULTIRANGE = auto()
 153    INT8RANGE = auto()
 154    INT8MULTIRANGE = auto()
 155    NUMRANGE = auto()
 156    NUMMULTIRANGE = auto()
 157    TSRANGE = auto()
 158    TSMULTIRANGE = auto()
 159    TSTZRANGE = auto()
 160    TSTZMULTIRANGE = auto()
 161    DATERANGE = auto()
 162    DATEMULTIRANGE = auto()
 163    UUID = auto()
 164    GEOGRAPHY = auto()
 165    NULLABLE = auto()
 166    GEOMETRY = auto()
 167    HLLSKETCH = auto()
 168    HSTORE = auto()
 169    SUPER = auto()
 170    SERIAL = auto()
 171    SMALLSERIAL = auto()
 172    BIGSERIAL = auto()
 173    XML = auto()
 174    YEAR = auto()
 175    UNIQUEIDENTIFIER = auto()
 176    USERDEFINED = auto()
 177    MONEY = auto()
 178    SMALLMONEY = auto()
 179    ROWVERSION = auto()
 180    IMAGE = auto()
 181    VARIANT = auto()
 182    OBJECT = auto()
 183    INET = auto()
 184    IPADDRESS = auto()
 185    IPPREFIX = auto()
 186    IPV4 = auto()
 187    IPV6 = auto()
 188    ENUM = auto()
 189    ENUM8 = auto()
 190    ENUM16 = auto()
 191    FIXEDSTRING = auto()
 192    LOWCARDINALITY = auto()
 193    NESTED = auto()
 194    AGGREGATEFUNCTION = auto()
 195    SIMPLEAGGREGATEFUNCTION = auto()
 196    UNKNOWN = auto()
 197
 198    # keywords
 199    ALIAS = auto()
 200    ALTER = auto()
 201    ALWAYS = auto()
 202    ALL = auto()
 203    ANTI = auto()
 204    ANY = auto()
 205    APPLY = auto()
 206    ARRAY = auto()
 207    ASC = auto()
 208    ASOF = auto()
 209    AUTO_INCREMENT = auto()
 210    BEGIN = auto()
 211    BETWEEN = auto()
 212    CACHE = auto()
 213    CASE = auto()
 214    CHARACTER_SET = auto()
 215    CLUSTER_BY = auto()
 216    COLLATE = auto()
 217    COMMAND = auto()
 218    COMMENT = auto()
 219    COMMIT = auto()
 220    CONNECT_BY = auto()
 221    CONSTRAINT = auto()
 222    CREATE = auto()
 223    CROSS = auto()
 224    CUBE = auto()
 225    CURRENT_DATE = auto()
 226    CURRENT_DATETIME = auto()
 227    CURRENT_TIME = auto()
 228    CURRENT_TIMESTAMP = auto()
 229    CURRENT_USER = auto()
 230    DEFAULT = auto()
 231    DELETE = auto()
 232    DESC = auto()
 233    DESCRIBE = auto()
 234    DICTIONARY = auto()
 235    DISTINCT = auto()
 236    DISTRIBUTE_BY = auto()
 237    DIV = auto()
 238    DROP = auto()
 239    ELSE = auto()
 240    END = auto()
 241    ESCAPE = auto()
 242    EXCEPT = auto()
 243    EXECUTE = auto()
 244    EXISTS = auto()
 245    FALSE = auto()
 246    FETCH = auto()
 247    FILTER = auto()
 248    FINAL = auto()
 249    FIRST = auto()
 250    FOR = auto()
 251    FORCE = auto()
 252    FOREIGN_KEY = auto()
 253    FORMAT = auto()
 254    FROM = auto()
 255    FULL = auto()
 256    FUNCTION = auto()
 257    GLOB = auto()
 258    GLOBAL = auto()
 259    GROUP_BY = auto()
 260    GROUPING_SETS = auto()
 261    HAVING = auto()
 262    HINT = auto()
 263    IGNORE = auto()
 264    ILIKE = auto()
 265    ILIKE_ANY = auto()
 266    IN = auto()
 267    INDEX = auto()
 268    INNER = auto()
 269    INSERT = auto()
 270    INTERSECT = auto()
 271    INTERVAL = auto()
 272    INTO = auto()
 273    INTRODUCER = auto()
 274    IRLIKE = auto()
 275    IS = auto()
 276    ISNULL = auto()
 277    JOIN = auto()
 278    JOIN_MARKER = auto()
 279    KEEP = auto()
 280    KILL = auto()
 281    LANGUAGE = auto()
 282    LATERAL = auto()
 283    LEFT = auto()
 284    LIKE = auto()
 285    LIKE_ANY = auto()
 286    LIMIT = auto()
 287    LOAD = auto()
 288    LOCK = auto()
 289    MAP = auto()
 290    MATCH_RECOGNIZE = auto()
 291    MEMBER_OF = auto()
 292    MERGE = auto()
 293    MOD = auto()
 294    MODEL = auto()
 295    NATURAL = auto()
 296    NEXT = auto()
 297    NOTNULL = auto()
 298    NULL = auto()
 299    OBJECT_IDENTIFIER = auto()
 300    OFFSET = auto()
 301    ON = auto()
 302    OPERATOR = auto()
 303    ORDER_BY = auto()
 304    ORDER_SIBLINGS_BY = auto()
 305    ORDERED = auto()
 306    ORDINALITY = auto()
 307    OUTER = auto()
 308    OVER = auto()
 309    OVERLAPS = auto()
 310    OVERWRITE = auto()
 311    PARTITION = auto()
 312    PARTITION_BY = auto()
 313    PERCENT = auto()
 314    PIVOT = auto()
 315    PLACEHOLDER = auto()
 316    PRAGMA = auto()
 317    PRIMARY_KEY = auto()
 318    PROCEDURE = auto()
 319    PROPERTIES = auto()
 320    PSEUDO_TYPE = auto()
 321    QUALIFY = auto()
 322    QUOTE = auto()
 323    RANGE = auto()
 324    RECURSIVE = auto()
 325    REFRESH = auto()
 326    REPLACE = auto()
 327    RETURNING = auto()
 328    REFERENCES = auto()
 329    RIGHT = auto()
 330    RLIKE = auto()
 331    ROLLBACK = auto()
 332    ROLLUP = auto()
 333    ROW = auto()
 334    ROWS = auto()
 335    SELECT = auto()
 336    SEMI = auto()
 337    SEPARATOR = auto()
 338    SERDE_PROPERTIES = auto()
 339    SET = auto()
 340    SETTINGS = auto()
 341    SHOW = auto()
 342    SIMILAR_TO = auto()
 343    SOME = auto()
 344    SORT_BY = auto()
 345    START_WITH = auto()
 346    STRUCT = auto()
 347    TABLE_SAMPLE = auto()
 348    TEMPORARY = auto()
 349    TOP = auto()
 350    THEN = auto()
 351    TRUE = auto()
 352    UNCACHE = auto()
 353    UNION = auto()
 354    UNNEST = auto()
 355    UNPIVOT = auto()
 356    UPDATE = auto()
 357    USE = auto()
 358    USING = auto()
 359    VALUES = auto()
 360    VIEW = auto()
 361    VOLATILE = auto()
 362    WHEN = auto()
 363    WHERE = auto()
 364    WINDOW = auto()
 365    WITH = auto()
 366    UNIQUE = auto()
 367    VERSION_SNAPSHOT = auto()
 368    TIMESTAMP_SNAPSHOT = auto()
 369
 370
 371_ALL_TOKEN_TYPES = list(TokenType)
 372_TOKEN_TYPE_TO_INDEX = {token_type: i for i, token_type in enumerate(_ALL_TOKEN_TYPES)}
 373
 374
 375class Token:
 376    __slots__ = ("token_type", "text", "line", "col", "start", "end", "comments")
 377
 378    @classmethod
 379    def number(cls, number: int) -> Token:
 380        """Returns a NUMBER token with `number` as its text."""
 381        return cls(TokenType.NUMBER, str(number))
 382
 383    @classmethod
 384    def string(cls, string: str) -> Token:
 385        """Returns a STRING token with `string` as its text."""
 386        return cls(TokenType.STRING, string)
 387
 388    @classmethod
 389    def identifier(cls, identifier: str) -> Token:
 390        """Returns an IDENTIFIER token with `identifier` as its text."""
 391        return cls(TokenType.IDENTIFIER, identifier)
 392
 393    @classmethod
 394    def var(cls, var: str) -> Token:
 395        """Returns an VAR token with `var` as its text."""
 396        return cls(TokenType.VAR, var)
 397
 398    def __init__(
 399        self,
 400        token_type: TokenType,
 401        text: str,
 402        line: int = 1,
 403        col: int = 1,
 404        start: int = 0,
 405        end: int = 0,
 406        comments: t.Optional[t.List[str]] = None,
 407    ) -> None:
 408        """Token initializer.
 409
 410        Args:
 411            token_type: The TokenType Enum.
 412            text: The text of the token.
 413            line: The line that the token ends on.
 414            col: The column that the token ends on.
 415            start: The start index of the token.
 416            end: The ending index of the token.
 417            comments: The comments to attach to the token.
 418        """
 419        self.token_type = token_type
 420        self.text = text
 421        self.line = line
 422        self.col = col
 423        self.start = start
 424        self.end = end
 425        self.comments = [] if comments is None else comments
 426
 427    def __repr__(self) -> str:
 428        attributes = ", ".join(f"{k}: {getattr(self, k)}" for k in self.__slots__)
 429        return f"<Token {attributes}>"
 430
 431
 432class _Tokenizer(type):
 433    def __new__(cls, clsname, bases, attrs):
 434        klass = super().__new__(cls, clsname, bases, attrs)
 435
 436        def _convert_quotes(arr: t.List[str | t.Tuple[str, str]]) -> t.Dict[str, str]:
 437            return dict(
 438                (item, item) if isinstance(item, str) else (item[0], item[1]) for item in arr
 439            )
 440
 441        def _quotes_to_format(
 442            token_type: TokenType, arr: t.List[str | t.Tuple[str, str]]
 443        ) -> t.Dict[str, t.Tuple[str, TokenType]]:
 444            return {k: (v, token_type) for k, v in _convert_quotes(arr).items()}
 445
 446        klass._QUOTES = _convert_quotes(klass.QUOTES)
 447        klass._IDENTIFIERS = _convert_quotes(klass.IDENTIFIERS)
 448
 449        klass._FORMAT_STRINGS = {
 450            **{
 451                p + s: (e, TokenType.NATIONAL_STRING)
 452                for s, e in klass._QUOTES.items()
 453                for p in ("n", "N")
 454            },
 455            **_quotes_to_format(TokenType.BIT_STRING, klass.BIT_STRINGS),
 456            **_quotes_to_format(TokenType.BYTE_STRING, klass.BYTE_STRINGS),
 457            **_quotes_to_format(TokenType.HEX_STRING, klass.HEX_STRINGS),
 458            **_quotes_to_format(TokenType.RAW_STRING, klass.RAW_STRINGS),
 459            **_quotes_to_format(TokenType.HEREDOC_STRING, klass.HEREDOC_STRINGS),
 460            **_quotes_to_format(TokenType.UNICODE_STRING, klass.UNICODE_STRINGS),
 461        }
 462
 463        klass._STRING_ESCAPES = set(klass.STRING_ESCAPES)
 464        klass._IDENTIFIER_ESCAPES = set(klass.IDENTIFIER_ESCAPES)
 465        klass._COMMENTS = {
 466            **dict(
 467                (comment, None) if isinstance(comment, str) else (comment[0], comment[1])
 468                for comment in klass.COMMENTS
 469            ),
 470            "{#": "#}",  # Ensure Jinja comments are tokenized correctly in all dialects
 471        }
 472
 473        klass._KEYWORD_TRIE = new_trie(
 474            key.upper()
 475            for key in (
 476                *klass.KEYWORDS,
 477                *klass._COMMENTS,
 478                *klass._QUOTES,
 479                *klass._FORMAT_STRINGS,
 480            )
 481            if " " in key or any(single in key for single in klass.SINGLE_TOKENS)
 482        )
 483
 484        if USE_RS_TOKENIZER:
 485            settings = RsTokenizerSettings(
 486                white_space={k: _TOKEN_TYPE_TO_INDEX[v] for k, v in klass.WHITE_SPACE.items()},
 487                single_tokens={k: _TOKEN_TYPE_TO_INDEX[v] for k, v in klass.SINGLE_TOKENS.items()},
 488                keywords={k: _TOKEN_TYPE_TO_INDEX[v] for k, v in klass.KEYWORDS.items()},
 489                numeric_literals=klass.NUMERIC_LITERALS,
 490                identifiers=klass._IDENTIFIERS,
 491                identifier_escapes=klass._IDENTIFIER_ESCAPES,
 492                string_escapes=klass._STRING_ESCAPES,
 493                quotes=klass._QUOTES,
 494                format_strings={
 495                    k: (v1, _TOKEN_TYPE_TO_INDEX[v2])
 496                    for k, (v1, v2) in klass._FORMAT_STRINGS.items()
 497                },
 498                has_bit_strings=bool(klass.BIT_STRINGS),
 499                has_hex_strings=bool(klass.HEX_STRINGS),
 500                comments=klass._COMMENTS,
 501                var_single_tokens=klass.VAR_SINGLE_TOKENS,
 502                commands={_TOKEN_TYPE_TO_INDEX[v] for v in klass.COMMANDS},
 503                command_prefix_tokens={
 504                    _TOKEN_TYPE_TO_INDEX[v] for v in klass.COMMAND_PREFIX_TOKENS
 505                },
 506            )
 507            token_types = RsTokenTypeSettings(
 508                bit_string=_TOKEN_TYPE_TO_INDEX[TokenType.BIT_STRING],
 509                break_=_TOKEN_TYPE_TO_INDEX[TokenType.BREAK],
 510                dcolon=_TOKEN_TYPE_TO_INDEX[TokenType.DCOLON],
 511                heredoc_string=_TOKEN_TYPE_TO_INDEX[TokenType.HEREDOC_STRING],
 512                hex_string=_TOKEN_TYPE_TO_INDEX[TokenType.HEX_STRING],
 513                identifier=_TOKEN_TYPE_TO_INDEX[TokenType.IDENTIFIER],
 514                number=_TOKEN_TYPE_TO_INDEX[TokenType.NUMBER],
 515                parameter=_TOKEN_TYPE_TO_INDEX[TokenType.PARAMETER],
 516                semicolon=_TOKEN_TYPE_TO_INDEX[TokenType.SEMICOLON],
 517                string=_TOKEN_TYPE_TO_INDEX[TokenType.STRING],
 518                var=_TOKEN_TYPE_TO_INDEX[TokenType.VAR],
 519            )
 520            klass._RS_TOKENIZER = RsTokenizer(settings, token_types)
 521        else:
 522            klass._RS_TOKENIZER = None
 523
 524        return klass
 525
 526
 527class Tokenizer(metaclass=_Tokenizer):
 528    SINGLE_TOKENS = {
 529        "(": TokenType.L_PAREN,
 530        ")": TokenType.R_PAREN,
 531        "[": TokenType.L_BRACKET,
 532        "]": TokenType.R_BRACKET,
 533        "{": TokenType.L_BRACE,
 534        "}": TokenType.R_BRACE,
 535        "&": TokenType.AMP,
 536        "^": TokenType.CARET,
 537        ":": TokenType.COLON,
 538        ",": TokenType.COMMA,
 539        ".": TokenType.DOT,
 540        "-": TokenType.DASH,
 541        "=": TokenType.EQ,
 542        ">": TokenType.GT,
 543        "<": TokenType.LT,
 544        "%": TokenType.MOD,
 545        "!": TokenType.NOT,
 546        "|": TokenType.PIPE,
 547        "+": TokenType.PLUS,
 548        ";": TokenType.SEMICOLON,
 549        "/": TokenType.SLASH,
 550        "\\": TokenType.BACKSLASH,
 551        "*": TokenType.STAR,
 552        "~": TokenType.TILDA,
 553        "?": TokenType.PLACEHOLDER,
 554        "@": TokenType.PARAMETER,
 555        # used for breaking a var like x'y' but nothing else
 556        # the token type doesn't matter
 557        "'": TokenType.QUOTE,
 558        "`": TokenType.IDENTIFIER,
 559        '"': TokenType.IDENTIFIER,
 560        "#": TokenType.HASH,
 561    }
 562
 563    BIT_STRINGS: t.List[str | t.Tuple[str, str]] = []
 564    BYTE_STRINGS: t.List[str | t.Tuple[str, str]] = []
 565    HEX_STRINGS: t.List[str | t.Tuple[str, str]] = []
 566    RAW_STRINGS: t.List[str | t.Tuple[str, str]] = []
 567    HEREDOC_STRINGS: t.List[str | t.Tuple[str, str]] = []
 568    UNICODE_STRINGS: t.List[str | t.Tuple[str, str]] = []
 569    IDENTIFIERS: t.List[str | t.Tuple[str, str]] = ['"']
 570    IDENTIFIER_ESCAPES = ['"']
 571    QUOTES: t.List[t.Tuple[str, str] | str] = ["'"]
 572    STRING_ESCAPES = ["'"]
 573    VAR_SINGLE_TOKENS: t.Set[str] = set()
 574
 575    # Autofilled
 576    _COMMENTS: t.Dict[str, str] = {}
 577    _FORMAT_STRINGS: t.Dict[str, t.Tuple[str, TokenType]] = {}
 578    _IDENTIFIERS: t.Dict[str, str] = {}
 579    _IDENTIFIER_ESCAPES: t.Set[str] = set()
 580    _QUOTES: t.Dict[str, str] = {}
 581    _STRING_ESCAPES: t.Set[str] = set()
 582    _KEYWORD_TRIE: t.Dict = {}
 583    _RS_TOKENIZER: t.Optional[t.Any] = None
 584
 585    KEYWORDS: t.Dict[str, TokenType] = {
 586        **{f"{{%{postfix}": TokenType.BLOCK_START for postfix in ("", "+", "-")},
 587        **{f"{prefix}%}}": TokenType.BLOCK_END for prefix in ("", "+", "-")},
 588        **{f"{{{{{postfix}": TokenType.BLOCK_START for postfix in ("+", "-")},
 589        **{f"{prefix}}}}}": TokenType.BLOCK_END for prefix in ("+", "-")},
 590        "/*+": TokenType.HINT,
 591        "==": TokenType.EQ,
 592        "::": TokenType.DCOLON,
 593        "||": TokenType.DPIPE,
 594        ">=": TokenType.GTE,
 595        "<=": TokenType.LTE,
 596        "<>": TokenType.NEQ,
 597        "!=": TokenType.NEQ,
 598        ":=": TokenType.COLON_EQ,
 599        "<=>": TokenType.NULLSAFE_EQ,
 600        "->": TokenType.ARROW,
 601        "->>": TokenType.DARROW,
 602        "=>": TokenType.FARROW,
 603        "#>": TokenType.HASH_ARROW,
 604        "#>>": TokenType.DHASH_ARROW,
 605        "<->": TokenType.LR_ARROW,
 606        "&&": TokenType.DAMP,
 607        "??": TokenType.DQMARK,
 608        "ALL": TokenType.ALL,
 609        "ALWAYS": TokenType.ALWAYS,
 610        "AND": TokenType.AND,
 611        "ANTI": TokenType.ANTI,
 612        "ANY": TokenType.ANY,
 613        "ASC": TokenType.ASC,
 614        "AS": TokenType.ALIAS,
 615        "ASOF": TokenType.ASOF,
 616        "AUTOINCREMENT": TokenType.AUTO_INCREMENT,
 617        "AUTO_INCREMENT": TokenType.AUTO_INCREMENT,
 618        "BEGIN": TokenType.BEGIN,
 619        "BETWEEN": TokenType.BETWEEN,
 620        "CACHE": TokenType.CACHE,
 621        "UNCACHE": TokenType.UNCACHE,
 622        "CASE": TokenType.CASE,
 623        "CHARACTER SET": TokenType.CHARACTER_SET,
 624        "CLUSTER BY": TokenType.CLUSTER_BY,
 625        "COLLATE": TokenType.COLLATE,
 626        "COLUMN": TokenType.COLUMN,
 627        "COMMIT": TokenType.COMMIT,
 628        "CONNECT BY": TokenType.CONNECT_BY,
 629        "CONSTRAINT": TokenType.CONSTRAINT,
 630        "CREATE": TokenType.CREATE,
 631        "CROSS": TokenType.CROSS,
 632        "CUBE": TokenType.CUBE,
 633        "CURRENT_DATE": TokenType.CURRENT_DATE,
 634        "CURRENT_TIME": TokenType.CURRENT_TIME,
 635        "CURRENT_TIMESTAMP": TokenType.CURRENT_TIMESTAMP,
 636        "CURRENT_USER": TokenType.CURRENT_USER,
 637        "DATABASE": TokenType.DATABASE,
 638        "DEFAULT": TokenType.DEFAULT,
 639        "DELETE": TokenType.DELETE,
 640        "DESC": TokenType.DESC,
 641        "DESCRIBE": TokenType.DESCRIBE,
 642        "DISTINCT": TokenType.DISTINCT,
 643        "DISTRIBUTE BY": TokenType.DISTRIBUTE_BY,
 644        "DIV": TokenType.DIV,
 645        "DROP": TokenType.DROP,
 646        "ELSE": TokenType.ELSE,
 647        "END": TokenType.END,
 648        "ESCAPE": TokenType.ESCAPE,
 649        "EXCEPT": TokenType.EXCEPT,
 650        "EXECUTE": TokenType.EXECUTE,
 651        "EXISTS": TokenType.EXISTS,
 652        "FALSE": TokenType.FALSE,
 653        "FETCH": TokenType.FETCH,
 654        "FILTER": TokenType.FILTER,
 655        "FIRST": TokenType.FIRST,
 656        "FULL": TokenType.FULL,
 657        "FUNCTION": TokenType.FUNCTION,
 658        "FOR": TokenType.FOR,
 659        "FOREIGN KEY": TokenType.FOREIGN_KEY,
 660        "FORMAT": TokenType.FORMAT,
 661        "FROM": TokenType.FROM,
 662        "GEOGRAPHY": TokenType.GEOGRAPHY,
 663        "GEOMETRY": TokenType.GEOMETRY,
 664        "GLOB": TokenType.GLOB,
 665        "GROUP BY": TokenType.GROUP_BY,
 666        "GROUPING SETS": TokenType.GROUPING_SETS,
 667        "HAVING": TokenType.HAVING,
 668        "ILIKE": TokenType.ILIKE,
 669        "IN": TokenType.IN,
 670        "INDEX": TokenType.INDEX,
 671        "INET": TokenType.INET,
 672        "INNER": TokenType.INNER,
 673        "INSERT": TokenType.INSERT,
 674        "INTERVAL": TokenType.INTERVAL,
 675        "INTERSECT": TokenType.INTERSECT,
 676        "INTO": TokenType.INTO,
 677        "IS": TokenType.IS,
 678        "ISNULL": TokenType.ISNULL,
 679        "JOIN": TokenType.JOIN,
 680        "KEEP": TokenType.KEEP,
 681        "KILL": TokenType.KILL,
 682        "LATERAL": TokenType.LATERAL,
 683        "LEFT": TokenType.LEFT,
 684        "LIKE": TokenType.LIKE,
 685        "LIMIT": TokenType.LIMIT,
 686        "LOAD": TokenType.LOAD,
 687        "LOCK": TokenType.LOCK,
 688        "MERGE": TokenType.MERGE,
 689        "NATURAL": TokenType.NATURAL,
 690        "NEXT": TokenType.NEXT,
 691        "NOT": TokenType.NOT,
 692        "NOTNULL": TokenType.NOTNULL,
 693        "NULL": TokenType.NULL,
 694        "OBJECT": TokenType.OBJECT,
 695        "OFFSET": TokenType.OFFSET,
 696        "ON": TokenType.ON,
 697        "OR": TokenType.OR,
 698        "XOR": TokenType.XOR,
 699        "ORDER BY": TokenType.ORDER_BY,
 700        "ORDINALITY": TokenType.ORDINALITY,
 701        "OUTER": TokenType.OUTER,
 702        "OVER": TokenType.OVER,
 703        "OVERLAPS": TokenType.OVERLAPS,
 704        "OVERWRITE": TokenType.OVERWRITE,
 705        "PARTITION": TokenType.PARTITION,
 706        "PARTITION BY": TokenType.PARTITION_BY,
 707        "PARTITIONED BY": TokenType.PARTITION_BY,
 708        "PARTITIONED_BY": TokenType.PARTITION_BY,
 709        "PERCENT": TokenType.PERCENT,
 710        "PIVOT": TokenType.PIVOT,
 711        "PRAGMA": TokenType.PRAGMA,
 712        "PRIMARY KEY": TokenType.PRIMARY_KEY,
 713        "PROCEDURE": TokenType.PROCEDURE,
 714        "QUALIFY": TokenType.QUALIFY,
 715        "RANGE": TokenType.RANGE,
 716        "RECURSIVE": TokenType.RECURSIVE,
 717        "REGEXP": TokenType.RLIKE,
 718        "REPLACE": TokenType.REPLACE,
 719        "RETURNING": TokenType.RETURNING,
 720        "REFERENCES": TokenType.REFERENCES,
 721        "RIGHT": TokenType.RIGHT,
 722        "RLIKE": TokenType.RLIKE,
 723        "ROLLBACK": TokenType.ROLLBACK,
 724        "ROLLUP": TokenType.ROLLUP,
 725        "ROW": TokenType.ROW,
 726        "ROWS": TokenType.ROWS,
 727        "SCHEMA": TokenType.SCHEMA,
 728        "SELECT": TokenType.SELECT,
 729        "SEMI": TokenType.SEMI,
 730        "SET": TokenType.SET,
 731        "SETTINGS": TokenType.SETTINGS,
 732        "SHOW": TokenType.SHOW,
 733        "SIMILAR TO": TokenType.SIMILAR_TO,
 734        "SOME": TokenType.SOME,
 735        "SORT BY": TokenType.SORT_BY,
 736        "START WITH": TokenType.START_WITH,
 737        "TABLE": TokenType.TABLE,
 738        "TABLESAMPLE": TokenType.TABLE_SAMPLE,
 739        "TEMP": TokenType.TEMPORARY,
 740        "TEMPORARY": TokenType.TEMPORARY,
 741        "THEN": TokenType.THEN,
 742        "TRUE": TokenType.TRUE,
 743        "UNION": TokenType.UNION,
 744        "UNKNOWN": TokenType.UNKNOWN,
 745        "UNNEST": TokenType.UNNEST,
 746        "UNPIVOT": TokenType.UNPIVOT,
 747        "UPDATE": TokenType.UPDATE,
 748        "USE": TokenType.USE,
 749        "USING": TokenType.USING,
 750        "UUID": TokenType.UUID,
 751        "VALUES": TokenType.VALUES,
 752        "VIEW": TokenType.VIEW,
 753        "VOLATILE": TokenType.VOLATILE,
 754        "WHEN": TokenType.WHEN,
 755        "WHERE": TokenType.WHERE,
 756        "WINDOW": TokenType.WINDOW,
 757        "WITH": TokenType.WITH,
 758        "APPLY": TokenType.APPLY,
 759        "ARRAY": TokenType.ARRAY,
 760        "BIT": TokenType.BIT,
 761        "BOOL": TokenType.BOOLEAN,
 762        "BOOLEAN": TokenType.BOOLEAN,
 763        "BYTE": TokenType.TINYINT,
 764        "MEDIUMINT": TokenType.MEDIUMINT,
 765        "INT1": TokenType.TINYINT,
 766        "TINYINT": TokenType.TINYINT,
 767        "INT16": TokenType.SMALLINT,
 768        "SHORT": TokenType.SMALLINT,
 769        "SMALLINT": TokenType.SMALLINT,
 770        "INT128": TokenType.INT128,
 771        "HUGEINT": TokenType.INT128,
 772        "INT2": TokenType.SMALLINT,
 773        "INTEGER": TokenType.INT,
 774        "INT": TokenType.INT,
 775        "INT4": TokenType.INT,
 776        "INT32": TokenType.INT,
 777        "INT64": TokenType.BIGINT,
 778        "LONG": TokenType.BIGINT,
 779        "BIGINT": TokenType.BIGINT,
 780        "INT8": TokenType.TINYINT,
 781        "DEC": TokenType.DECIMAL,
 782        "DECIMAL": TokenType.DECIMAL,
 783        "BIGDECIMAL": TokenType.BIGDECIMAL,
 784        "BIGNUMERIC": TokenType.BIGDECIMAL,
 785        "MAP": TokenType.MAP,
 786        "NULLABLE": TokenType.NULLABLE,
 787        "NUMBER": TokenType.DECIMAL,
 788        "NUMERIC": TokenType.DECIMAL,
 789        "FIXED": TokenType.DECIMAL,
 790        "REAL": TokenType.FLOAT,
 791        "FLOAT": TokenType.FLOAT,
 792        "FLOAT4": TokenType.FLOAT,
 793        "FLOAT8": TokenType.DOUBLE,
 794        "DOUBLE": TokenType.DOUBLE,
 795        "DOUBLE PRECISION": TokenType.DOUBLE,
 796        "JSON": TokenType.JSON,
 797        "CHAR": TokenType.CHAR,
 798        "CHARACTER": TokenType.CHAR,
 799        "NCHAR": TokenType.NCHAR,
 800        "VARCHAR": TokenType.VARCHAR,
 801        "VARCHAR2": TokenType.VARCHAR,
 802        "NVARCHAR": TokenType.NVARCHAR,
 803        "NVARCHAR2": TokenType.NVARCHAR,
 804        "STR": TokenType.TEXT,
 805        "STRING": TokenType.TEXT,
 806        "TEXT": TokenType.TEXT,
 807        "LONGTEXT": TokenType.LONGTEXT,
 808        "MEDIUMTEXT": TokenType.MEDIUMTEXT,
 809        "TINYTEXT": TokenType.TINYTEXT,
 810        "CLOB": TokenType.TEXT,
 811        "LONGVARCHAR": TokenType.TEXT,
 812        "BINARY": TokenType.BINARY,
 813        "BLOB": TokenType.VARBINARY,
 814        "LONGBLOB": TokenType.LONGBLOB,
 815        "MEDIUMBLOB": TokenType.MEDIUMBLOB,
 816        "TINYBLOB": TokenType.TINYBLOB,
 817        "BYTEA": TokenType.VARBINARY,
 818        "VARBINARY": TokenType.VARBINARY,
 819        "TIME": TokenType.TIME,
 820        "TIMETZ": TokenType.TIMETZ,
 821        "TIMESTAMP": TokenType.TIMESTAMP,
 822        "TIMESTAMPTZ": TokenType.TIMESTAMPTZ,
 823        "TIMESTAMPLTZ": TokenType.TIMESTAMPLTZ,
 824        "DATE": TokenType.DATE,
 825        "DATETIME": TokenType.DATETIME,
 826        "INT4RANGE": TokenType.INT4RANGE,
 827        "INT4MULTIRANGE": TokenType.INT4MULTIRANGE,
 828        "INT8RANGE": TokenType.INT8RANGE,
 829        "INT8MULTIRANGE": TokenType.INT8MULTIRANGE,
 830        "NUMRANGE": TokenType.NUMRANGE,
 831        "NUMMULTIRANGE": TokenType.NUMMULTIRANGE,
 832        "TSRANGE": TokenType.TSRANGE,
 833        "TSMULTIRANGE": TokenType.TSMULTIRANGE,
 834        "TSTZRANGE": TokenType.TSTZRANGE,
 835        "TSTZMULTIRANGE": TokenType.TSTZMULTIRANGE,
 836        "DATERANGE": TokenType.DATERANGE,
 837        "DATEMULTIRANGE": TokenType.DATEMULTIRANGE,
 838        "UNIQUE": TokenType.UNIQUE,
 839        "STRUCT": TokenType.STRUCT,
 840        "VARIANT": TokenType.VARIANT,
 841        "ALTER": TokenType.ALTER,
 842        "ANALYZE": TokenType.COMMAND,
 843        "CALL": TokenType.COMMAND,
 844        "COMMENT": TokenType.COMMENT,
 845        "COPY": TokenType.COMMAND,
 846        "EXPLAIN": TokenType.COMMAND,
 847        "GRANT": TokenType.COMMAND,
 848        "OPTIMIZE": TokenType.COMMAND,
 849        "PREPARE": TokenType.COMMAND,
 850        "TRUNCATE": TokenType.COMMAND,
 851        "VACUUM": TokenType.COMMAND,
 852        "USER-DEFINED": TokenType.USERDEFINED,
 853        "FOR VERSION": TokenType.VERSION_SNAPSHOT,
 854        "FOR TIMESTAMP": TokenType.TIMESTAMP_SNAPSHOT,
 855    }
 856
 857    WHITE_SPACE: t.Dict[t.Optional[str], TokenType] = {
 858        " ": TokenType.SPACE,
 859        "\t": TokenType.SPACE,
 860        "\n": TokenType.BREAK,
 861        "\r": TokenType.BREAK,
 862    }
 863
 864    COMMANDS = {
 865        TokenType.COMMAND,
 866        TokenType.EXECUTE,
 867        TokenType.FETCH,
 868        TokenType.SHOW,
 869    }
 870
 871    COMMAND_PREFIX_TOKENS = {TokenType.SEMICOLON, TokenType.BEGIN}
 872
 873    # handle numeric literals like in hive (3L = BIGINT)
 874    NUMERIC_LITERALS: t.Dict[str, str] = {}
 875
 876    COMMENTS = ["--", ("/*", "*/")]
 877
 878    __slots__ = (
 879        "sql",
 880        "size",
 881        "tokens",
 882        "dialect",
 883        "_start",
 884        "_current",
 885        "_line",
 886        "_col",
 887        "_comments",
 888        "_char",
 889        "_end",
 890        "_peek",
 891        "_prev_token_line",
 892        "_rs_dialect_settings",
 893    )
 894
 895    def __init__(self, dialect: DialectType = None) -> None:
 896        from sqlglot.dialects import Dialect
 897
 898        self.dialect = Dialect.get_or_raise(dialect)
 899
 900        if USE_RS_TOKENIZER:
 901            self._rs_dialect_settings = RsTokenizerDialectSettings(
 902                escape_sequences=self.dialect.ESCAPE_SEQUENCES,
 903                identifiers_can_start_with_digit=self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT,
 904            )
 905
 906        self.reset()
 907
 908    def reset(self) -> None:
 909        self.sql = ""
 910        self.size = 0
 911        self.tokens: t.List[Token] = []
 912        self._start = 0
 913        self._current = 0
 914        self._line = 1
 915        self._col = 0
 916        self._comments: t.List[str] = []
 917
 918        self._char = ""
 919        self._end = False
 920        self._peek = ""
 921        self._prev_token_line = -1
 922
 923    def tokenize(self, sql: str) -> t.List[Token]:
 924        """Returns a list of tokens corresponding to the SQL string `sql`."""
 925        if USE_RS_TOKENIZER:
 926            return self.tokenize_rs(sql)
 927
 928        self.reset()
 929        self.sql = sql
 930        self.size = len(sql)
 931
 932        try:
 933            self._scan()
 934        except Exception as e:
 935            start = max(self._current - 50, 0)
 936            end = min(self._current + 50, self.size - 1)
 937            context = self.sql[start:end]
 938            raise TokenError(f"Error tokenizing '{context}'") from e
 939
 940        return self.tokens
 941
 942    def _scan(self, until: t.Optional[t.Callable] = None) -> None:
 943        while self.size and not self._end:
 944            current = self._current
 945
 946            # skip spaces inline rather than iteratively call advance()
 947            # for performance reasons
 948            while current < self.size:
 949                char = self.sql[current]
 950
 951                if char.isspace() and (char == " " or char == "\t"):
 952                    current += 1
 953                else:
 954                    break
 955
 956            n = current - self._current
 957            self._start = current
 958            self._advance(n if n > 1 else 1)
 959
 960            if self._char is None:
 961                break
 962
 963            if not self._char.isspace():
 964                if self._char.isdigit():
 965                    self._scan_number()
 966                elif self._char in self._IDENTIFIERS:
 967                    self._scan_identifier(self._IDENTIFIERS[self._char])
 968                else:
 969                    self._scan_keywords()
 970
 971            if until and until():
 972                break
 973
 974        if self.tokens and self._comments:
 975            self.tokens[-1].comments.extend(self._comments)
 976
 977    def _chars(self, size: int) -> str:
 978        if size == 1:
 979            return self._char
 980
 981        start = self._current - 1
 982        end = start + size
 983
 984        return self.sql[start:end] if end <= self.size else ""
 985
 986    def _advance(self, i: int = 1, alnum: bool = False) -> None:
 987        if self.WHITE_SPACE.get(self._char) is TokenType.BREAK:
 988            # Ensures we don't count an extra line if we get a \r\n line break sequence
 989            if self._char == "\r" and self._peek == "\n":
 990                i = 2
 991                self._start += 1
 992
 993            self._col = 1
 994            self._line += 1
 995        else:
 996            self._col += i
 997
 998        self._current += i
 999        self._end = self._current >= self.size
1000        self._char = self.sql[self._current - 1]
1001        self._peek = "" if self._end else self.sql[self._current]
1002
1003        if alnum and self._char.isalnum():
1004            # Here we use local variables instead of attributes for better performance
1005            _col = self._col
1006            _current = self._current
1007            _end = self._end
1008            _peek = self._peek
1009
1010            while _peek.isalnum():
1011                _col += 1
1012                _current += 1
1013                _end = _current >= self.size
1014                _peek = "" if _end else self.sql[_current]
1015
1016            self._col = _col
1017            self._current = _current
1018            self._end = _end
1019            self._peek = _peek
1020            self._char = self.sql[_current - 1]
1021
1022    @property
1023    def _text(self) -> str:
1024        return self.sql[self._start : self._current]
1025
1026    def peek(self, i: int = 0) -> str:
1027        i = self._current + i
1028        if i < self.size:
1029            return self.sql[i]
1030        return ""
1031
1032    def _add(self, token_type: TokenType, text: t.Optional[str] = None) -> None:
1033        self._prev_token_line = self._line
1034
1035        if self._comments and token_type == TokenType.SEMICOLON and self.tokens:
1036            self.tokens[-1].comments.extend(self._comments)
1037            self._comments = []
1038
1039        self.tokens.append(
1040            Token(
1041                token_type,
1042                text=self._text if text is None else text,
1043                line=self._line,
1044                col=self._col,
1045                start=self._start,
1046                end=self._current - 1,
1047                comments=self._comments,
1048            )
1049        )
1050        self._comments = []
1051
1052        # If we have either a semicolon or a begin token before the command's token, we'll parse
1053        # whatever follows the command's token as a string
1054        if (
1055            token_type in self.COMMANDS
1056            and self._peek != ";"
1057            and (len(self.tokens) == 1 or self.tokens[-2].token_type in self.COMMAND_PREFIX_TOKENS)
1058        ):
1059            start = self._current
1060            tokens = len(self.tokens)
1061            self._scan(lambda: self._peek == ";")
1062            self.tokens = self.tokens[:tokens]
1063            text = self.sql[start : self._current].strip()
1064            if text:
1065                self._add(TokenType.STRING, text)
1066
1067    def _scan_keywords(self) -> None:
1068        size = 0
1069        word = None
1070        chars = self._text
1071        char = chars
1072        prev_space = False
1073        skip = False
1074        trie = self._KEYWORD_TRIE
1075        single_token = char in self.SINGLE_TOKENS
1076
1077        while chars:
1078            if skip:
1079                result = TrieResult.PREFIX
1080            else:
1081                result, trie = in_trie(trie, char.upper())
1082
1083            if result == TrieResult.FAILED:
1084                break
1085            if result == TrieResult.EXISTS:
1086                word = chars
1087
1088            end = self._current + size
1089            size += 1
1090
1091            if end < self.size:
1092                char = self.sql[end]
1093                single_token = single_token or char in self.SINGLE_TOKENS
1094                is_space = char.isspace()
1095
1096                if not is_space or not prev_space:
1097                    if is_space:
1098                        char = " "
1099                    chars += char
1100                    prev_space = is_space
1101                    skip = False
1102                else:
1103                    skip = True
1104            else:
1105                char = ""
1106                break
1107
1108        if word:
1109            if self._scan_string(word):
1110                return
1111            if self._scan_comment(word):
1112                return
1113            if prev_space or single_token or not char:
1114                self._advance(size - 1)
1115                word = word.upper()
1116                self._add(self.KEYWORDS[word], text=word)
1117                return
1118
1119        if self._char in self.SINGLE_TOKENS:
1120            self._add(self.SINGLE_TOKENS[self._char], text=self._char)
1121            return
1122
1123        self._scan_var()
1124
1125    def _scan_comment(self, comment_start: str) -> bool:
1126        if comment_start not in self._COMMENTS:
1127            return False
1128
1129        comment_start_line = self._line
1130        comment_start_size = len(comment_start)
1131        comment_end = self._COMMENTS[comment_start]
1132
1133        if comment_end:
1134            # Skip the comment's start delimiter
1135            self._advance(comment_start_size)
1136
1137            comment_end_size = len(comment_end)
1138            while not self._end and self._chars(comment_end_size) != comment_end:
1139                self._advance(alnum=True)
1140
1141            self._comments.append(self._text[comment_start_size : -comment_end_size + 1])
1142            self._advance(comment_end_size - 1)
1143        else:
1144            while not self._end and not self.WHITE_SPACE.get(self._peek) is TokenType.BREAK:
1145                self._advance(alnum=True)
1146            self._comments.append(self._text[comment_start_size:])
1147
1148        # Leading comment is attached to the succeeding token, whilst trailing comment to the preceding.
1149        # Multiple consecutive comments are preserved by appending them to the current comments list.
1150        if comment_start_line == self._prev_token_line:
1151            self.tokens[-1].comments.extend(self._comments)
1152            self._comments = []
1153            self._prev_token_line = self._line
1154
1155        return True
1156
1157    def _scan_number(self) -> None:
1158        if self._char == "0":
1159            peek = self._peek.upper()
1160            if peek == "B":
1161                return self._scan_bits() if self.BIT_STRINGS else self._add(TokenType.NUMBER)
1162            elif peek == "X":
1163                return self._scan_hex() if self.HEX_STRINGS else self._add(TokenType.NUMBER)
1164
1165        decimal = False
1166        scientific = 0
1167
1168        while True:
1169            if self._peek.isdigit():
1170                self._advance()
1171            elif self._peek == "." and not decimal:
1172                after = self.peek(1)
1173                if after.isdigit() or not after.isalpha():
1174                    decimal = True
1175                    self._advance()
1176                else:
1177                    return self._add(TokenType.VAR)
1178            elif self._peek in ("-", "+") and scientific == 1:
1179                scientific += 1
1180                self._advance()
1181            elif self._peek.upper() == "E" and not scientific:
1182                scientific += 1
1183                self._advance()
1184            elif self._peek.isidentifier():
1185                number_text = self._text
1186                literal = ""
1187
1188                while self._peek.strip() and self._peek not in self.SINGLE_TOKENS:
1189                    literal += self._peek
1190                    self._advance()
1191
1192                token_type = self.KEYWORDS.get(self.NUMERIC_LITERALS.get(literal.upper(), ""))
1193
1194                if token_type:
1195                    self._add(TokenType.NUMBER, number_text)
1196                    self._add(TokenType.DCOLON, "::")
1197                    return self._add(token_type, literal)
1198                elif self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT:
1199                    return self._add(TokenType.VAR)
1200
1201                self._advance(-len(literal))
1202                return self._add(TokenType.NUMBER, number_text)
1203            else:
1204                return self._add(TokenType.NUMBER)
1205
1206    def _scan_bits(self) -> None:
1207        self._advance()
1208        value = self._extract_value()
1209        try:
1210            # If `value` can't be converted to a binary, fallback to tokenizing it as an identifier
1211            int(value, 2)
1212            self._add(TokenType.BIT_STRING, value[2:])  # Drop the 0b
1213        except ValueError:
1214            self._add(TokenType.IDENTIFIER)
1215
1216    def _scan_hex(self) -> None:
1217        self._advance()
1218        value = self._extract_value()
1219        try:
1220            # If `value` can't be converted to a hex, fallback to tokenizing it as an identifier
1221            int(value, 16)
1222            self._add(TokenType.HEX_STRING, value[2:])  # Drop the 0x
1223        except ValueError:
1224            self._add(TokenType.IDENTIFIER)
1225
1226    def _extract_value(self) -> str:
1227        while True:
1228            char = self._peek.strip()
1229            if char and char not in self.SINGLE_TOKENS:
1230                self._advance(alnum=True)
1231            else:
1232                break
1233
1234        return self._text
1235
1236    def _scan_string(self, start: str) -> bool:
1237        base = None
1238        token_type = TokenType.STRING
1239
1240        if start in self._QUOTES:
1241            end = self._QUOTES[start]
1242        elif start in self._FORMAT_STRINGS:
1243            end, token_type = self._FORMAT_STRINGS[start]
1244
1245            if token_type == TokenType.HEX_STRING:
1246                base = 16
1247            elif token_type == TokenType.BIT_STRING:
1248                base = 2
1249            elif token_type == TokenType.HEREDOC_STRING:
1250                self._advance()
1251                tag = "" if self._char == end else self._extract_string(end)
1252                end = f"{start}{tag}{end}"
1253        else:
1254            return False
1255
1256        self._advance(len(start))
1257        text = self._extract_string(end)
1258
1259        if base:
1260            try:
1261                int(text, base)
1262            except:
1263                raise TokenError(
1264                    f"Numeric string contains invalid characters from {self._line}:{self._start}"
1265                )
1266
1267        self._add(token_type, text)
1268        return True
1269
1270    def _scan_identifier(self, identifier_end: str) -> None:
1271        self._advance()
1272        text = self._extract_string(identifier_end, self._IDENTIFIER_ESCAPES)
1273        self._add(TokenType.IDENTIFIER, text)
1274
1275    def _scan_var(self) -> None:
1276        while True:
1277            char = self._peek.strip()
1278            if char and (char in self.VAR_SINGLE_TOKENS or char not in self.SINGLE_TOKENS):
1279                self._advance(alnum=True)
1280            else:
1281                break
1282
1283        self._add(
1284            TokenType.VAR
1285            if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER
1286            else self.KEYWORDS.get(self._text.upper(), TokenType.VAR)
1287        )
1288
1289    def _extract_string(self, delimiter: str, escapes=None) -> str:
1290        text = ""
1291        delim_size = len(delimiter)
1292        escapes = self._STRING_ESCAPES if escapes is None else escapes
1293
1294        while True:
1295            if (
1296                self._char in escapes
1297                and (self._peek == delimiter or self._peek in escapes)
1298                and (self._char not in self._QUOTES or self._char == self._peek)
1299            ):
1300                if self._peek == delimiter:
1301                    text += self._peek
1302                else:
1303                    text += self._char + self._peek
1304
1305                if self._current + 1 < self.size:
1306                    self._advance(2)
1307                else:
1308                    raise TokenError(f"Missing {delimiter} from {self._line}:{self._current}")
1309            else:
1310                if self._chars(delim_size) == delimiter:
1311                    if delim_size > 1:
1312                        self._advance(delim_size - 1)
1313                    break
1314
1315                if self._end:
1316                    raise TokenError(f"Missing {delimiter} from {self._line}:{self._start}")
1317
1318                if (
1319                    self.dialect.ESCAPE_SEQUENCES
1320                    and self._peek
1321                    and self._char in self.STRING_ESCAPES
1322                ):
1323                    escaped_sequence = self.dialect.ESCAPE_SEQUENCES.get(self._char + self._peek)
1324                    if escaped_sequence:
1325                        self._advance(2)
1326                        text += escaped_sequence
1327                        continue
1328
1329                current = self._current - 1
1330                self._advance(alnum=True)
1331                text += self.sql[current : self._current - 1]
1332
1333        return text
1334
1335    def tokenize_rs(self, sql: str) -> t.List[Token]:
1336        if not self._RS_TOKENIZER:
1337            raise SqlglotError("Rust tokenizer is not available")
1338
1339        try:
1340            tokens = self._RS_TOKENIZER.tokenize(sql, self._rs_dialect_settings)
1341            for token in tokens:
1342                token.token_type = _ALL_TOKEN_TYPES[token.token_type_index]
1343            return tokens
1344        except Exception as e:
1345            raise TokenError(str(e))
class TokenType(sqlglot.helper.AutoName):
 29class TokenType(AutoName):
 30    L_PAREN = auto()
 31    R_PAREN = auto()
 32    L_BRACKET = auto()
 33    R_BRACKET = auto()
 34    L_BRACE = auto()
 35    R_BRACE = auto()
 36    COMMA = auto()
 37    DOT = auto()
 38    DASH = auto()
 39    PLUS = auto()
 40    COLON = auto()
 41    DCOLON = auto()
 42    DQMARK = auto()
 43    SEMICOLON = auto()
 44    STAR = auto()
 45    BACKSLASH = auto()
 46    SLASH = auto()
 47    LT = auto()
 48    LTE = auto()
 49    GT = auto()
 50    GTE = auto()
 51    NOT = auto()
 52    EQ = auto()
 53    NEQ = auto()
 54    NULLSAFE_EQ = auto()
 55    COLON_EQ = auto()
 56    AND = auto()
 57    OR = auto()
 58    AMP = auto()
 59    DPIPE = auto()
 60    PIPE = auto()
 61    CARET = auto()
 62    TILDA = auto()
 63    ARROW = auto()
 64    DARROW = auto()
 65    FARROW = auto()
 66    HASH = auto()
 67    HASH_ARROW = auto()
 68    DHASH_ARROW = auto()
 69    LR_ARROW = auto()
 70    DAT = auto()
 71    LT_AT = auto()
 72    AT_GT = auto()
 73    DOLLAR = auto()
 74    PARAMETER = auto()
 75    SESSION_PARAMETER = auto()
 76    DAMP = auto()
 77    XOR = auto()
 78    DSTAR = auto()
 79
 80    BLOCK_START = auto()
 81    BLOCK_END = auto()
 82
 83    SPACE = auto()
 84    BREAK = auto()
 85
 86    STRING = auto()
 87    NUMBER = auto()
 88    IDENTIFIER = auto()
 89    DATABASE = auto()
 90    COLUMN = auto()
 91    COLUMN_DEF = auto()
 92    SCHEMA = auto()
 93    TABLE = auto()
 94    VAR = auto()
 95    BIT_STRING = auto()
 96    HEX_STRING = auto()
 97    BYTE_STRING = auto()
 98    NATIONAL_STRING = auto()
 99    RAW_STRING = auto()
100    HEREDOC_STRING = auto()
101    UNICODE_STRING = auto()
102
103    # types
104    BIT = auto()
105    BOOLEAN = auto()
106    TINYINT = auto()
107    UTINYINT = auto()
108    SMALLINT = auto()
109    USMALLINT = auto()
110    MEDIUMINT = auto()
111    UMEDIUMINT = auto()
112    INT = auto()
113    UINT = auto()
114    BIGINT = auto()
115    UBIGINT = auto()
116    INT128 = auto()
117    UINT128 = auto()
118    INT256 = auto()
119    UINT256 = auto()
120    FLOAT = auto()
121    DOUBLE = auto()
122    DECIMAL = auto()
123    UDECIMAL = auto()
124    BIGDECIMAL = auto()
125    CHAR = auto()
126    NCHAR = auto()
127    VARCHAR = auto()
128    NVARCHAR = auto()
129    TEXT = auto()
130    MEDIUMTEXT = auto()
131    LONGTEXT = auto()
132    MEDIUMBLOB = auto()
133    LONGBLOB = auto()
134    TINYBLOB = auto()
135    TINYTEXT = auto()
136    BINARY = auto()
137    VARBINARY = auto()
138    JSON = auto()
139    JSONB = auto()
140    TIME = auto()
141    TIMETZ = auto()
142    TIMESTAMP = auto()
143    TIMESTAMPTZ = auto()
144    TIMESTAMPLTZ = auto()
145    TIMESTAMP_S = auto()
146    TIMESTAMP_MS = auto()
147    TIMESTAMP_NS = auto()
148    DATETIME = auto()
149    DATETIME64 = auto()
150    DATE = auto()
151    DATE32 = auto()
152    INT4RANGE = auto()
153    INT4MULTIRANGE = auto()
154    INT8RANGE = auto()
155    INT8MULTIRANGE = auto()
156    NUMRANGE = auto()
157    NUMMULTIRANGE = auto()
158    TSRANGE = auto()
159    TSMULTIRANGE = auto()
160    TSTZRANGE = auto()
161    TSTZMULTIRANGE = auto()
162    DATERANGE = auto()
163    DATEMULTIRANGE = auto()
164    UUID = auto()
165    GEOGRAPHY = auto()
166    NULLABLE = auto()
167    GEOMETRY = auto()
168    HLLSKETCH = auto()
169    HSTORE = auto()
170    SUPER = auto()
171    SERIAL = auto()
172    SMALLSERIAL = auto()
173    BIGSERIAL = auto()
174    XML = auto()
175    YEAR = auto()
176    UNIQUEIDENTIFIER = auto()
177    USERDEFINED = auto()
178    MONEY = auto()
179    SMALLMONEY = auto()
180    ROWVERSION = auto()
181    IMAGE = auto()
182    VARIANT = auto()
183    OBJECT = auto()
184    INET = auto()
185    IPADDRESS = auto()
186    IPPREFIX = auto()
187    IPV4 = auto()
188    IPV6 = auto()
189    ENUM = auto()
190    ENUM8 = auto()
191    ENUM16 = auto()
192    FIXEDSTRING = auto()
193    LOWCARDINALITY = auto()
194    NESTED = auto()
195    AGGREGATEFUNCTION = auto()
196    SIMPLEAGGREGATEFUNCTION = auto()
197    UNKNOWN = auto()
198
199    # keywords
200    ALIAS = auto()
201    ALTER = auto()
202    ALWAYS = auto()
203    ALL = auto()
204    ANTI = auto()
205    ANY = auto()
206    APPLY = auto()
207    ARRAY = auto()
208    ASC = auto()
209    ASOF = auto()
210    AUTO_INCREMENT = auto()
211    BEGIN = auto()
212    BETWEEN = auto()
213    CACHE = auto()
214    CASE = auto()
215    CHARACTER_SET = auto()
216    CLUSTER_BY = auto()
217    COLLATE = auto()
218    COMMAND = auto()
219    COMMENT = auto()
220    COMMIT = auto()
221    CONNECT_BY = auto()
222    CONSTRAINT = auto()
223    CREATE = auto()
224    CROSS = auto()
225    CUBE = auto()
226    CURRENT_DATE = auto()
227    CURRENT_DATETIME = auto()
228    CURRENT_TIME = auto()
229    CURRENT_TIMESTAMP = auto()
230    CURRENT_USER = auto()
231    DEFAULT = auto()
232    DELETE = auto()
233    DESC = auto()
234    DESCRIBE = auto()
235    DICTIONARY = auto()
236    DISTINCT = auto()
237    DISTRIBUTE_BY = auto()
238    DIV = auto()
239    DROP = auto()
240    ELSE = auto()
241    END = auto()
242    ESCAPE = auto()
243    EXCEPT = auto()
244    EXECUTE = auto()
245    EXISTS = auto()
246    FALSE = auto()
247    FETCH = auto()
248    FILTER = auto()
249    FINAL = auto()
250    FIRST = auto()
251    FOR = auto()
252    FORCE = auto()
253    FOREIGN_KEY = auto()
254    FORMAT = auto()
255    FROM = auto()
256    FULL = auto()
257    FUNCTION = auto()
258    GLOB = auto()
259    GLOBAL = auto()
260    GROUP_BY = auto()
261    GROUPING_SETS = auto()
262    HAVING = auto()
263    HINT = auto()
264    IGNORE = auto()
265    ILIKE = auto()
266    ILIKE_ANY = auto()
267    IN = auto()
268    INDEX = auto()
269    INNER = auto()
270    INSERT = auto()
271    INTERSECT = auto()
272    INTERVAL = auto()
273    INTO = auto()
274    INTRODUCER = auto()
275    IRLIKE = auto()
276    IS = auto()
277    ISNULL = auto()
278    JOIN = auto()
279    JOIN_MARKER = auto()
280    KEEP = auto()
281    KILL = auto()
282    LANGUAGE = auto()
283    LATERAL = auto()
284    LEFT = auto()
285    LIKE = auto()
286    LIKE_ANY = auto()
287    LIMIT = auto()
288    LOAD = auto()
289    LOCK = auto()
290    MAP = auto()
291    MATCH_RECOGNIZE = auto()
292    MEMBER_OF = auto()
293    MERGE = auto()
294    MOD = auto()
295    MODEL = auto()
296    NATURAL = auto()
297    NEXT = auto()
298    NOTNULL = auto()
299    NULL = auto()
300    OBJECT_IDENTIFIER = auto()
301    OFFSET = auto()
302    ON = auto()
303    OPERATOR = auto()
304    ORDER_BY = auto()
305    ORDER_SIBLINGS_BY = auto()
306    ORDERED = auto()
307    ORDINALITY = auto()
308    OUTER = auto()
309    OVER = auto()
310    OVERLAPS = auto()
311    OVERWRITE = auto()
312    PARTITION = auto()
313    PARTITION_BY = auto()
314    PERCENT = auto()
315    PIVOT = auto()
316    PLACEHOLDER = auto()
317    PRAGMA = auto()
318    PRIMARY_KEY = auto()
319    PROCEDURE = auto()
320    PROPERTIES = auto()
321    PSEUDO_TYPE = auto()
322    QUALIFY = auto()
323    QUOTE = auto()
324    RANGE = auto()
325    RECURSIVE = auto()
326    REFRESH = auto()
327    REPLACE = auto()
328    RETURNING = auto()
329    REFERENCES = auto()
330    RIGHT = auto()
331    RLIKE = auto()
332    ROLLBACK = auto()
333    ROLLUP = auto()
334    ROW = auto()
335    ROWS = auto()
336    SELECT = auto()
337    SEMI = auto()
338    SEPARATOR = auto()
339    SERDE_PROPERTIES = auto()
340    SET = auto()
341    SETTINGS = auto()
342    SHOW = auto()
343    SIMILAR_TO = auto()
344    SOME = auto()
345    SORT_BY = auto()
346    START_WITH = auto()
347    STRUCT = auto()
348    TABLE_SAMPLE = auto()
349    TEMPORARY = auto()
350    TOP = auto()
351    THEN = auto()
352    TRUE = auto()
353    UNCACHE = auto()
354    UNION = auto()
355    UNNEST = auto()
356    UNPIVOT = auto()
357    UPDATE = auto()
358    USE = auto()
359    USING = auto()
360    VALUES = auto()
361    VIEW = auto()
362    VOLATILE = auto()
363    WHEN = auto()
364    WHERE = auto()
365    WINDOW = auto()
366    WITH = auto()
367    UNIQUE = auto()
368    VERSION_SNAPSHOT = auto()
369    TIMESTAMP_SNAPSHOT = auto()

An enumeration.

L_PAREN = <TokenType.L_PAREN: 'L_PAREN'>
R_PAREN = <TokenType.R_PAREN: 'R_PAREN'>
L_BRACKET = <TokenType.L_BRACKET: 'L_BRACKET'>
R_BRACKET = <TokenType.R_BRACKET: 'R_BRACKET'>
L_BRACE = <TokenType.L_BRACE: 'L_BRACE'>
R_BRACE = <TokenType.R_BRACE: 'R_BRACE'>
COMMA = <TokenType.COMMA: 'COMMA'>
DOT = <TokenType.DOT: 'DOT'>
DASH = <TokenType.DASH: 'DASH'>
PLUS = <TokenType.PLUS: 'PLUS'>
COLON = <TokenType.COLON: 'COLON'>
DCOLON = <TokenType.DCOLON: 'DCOLON'>
DQMARK = <TokenType.DQMARK: 'DQMARK'>
SEMICOLON = <TokenType.SEMICOLON: 'SEMICOLON'>
STAR = <TokenType.STAR: 'STAR'>
BACKSLASH = <TokenType.BACKSLASH: 'BACKSLASH'>
SLASH = <TokenType.SLASH: 'SLASH'>
LT = <TokenType.LT: 'LT'>
LTE = <TokenType.LTE: 'LTE'>
GT = <TokenType.GT: 'GT'>
GTE = <TokenType.GTE: 'GTE'>
NOT = <TokenType.NOT: 'NOT'>
EQ = <TokenType.EQ: 'EQ'>
NEQ = <TokenType.NEQ: 'NEQ'>
NULLSAFE_EQ = <TokenType.NULLSAFE_EQ: 'NULLSAFE_EQ'>
COLON_EQ = <TokenType.COLON_EQ: 'COLON_EQ'>
AND = <TokenType.AND: 'AND'>
OR = <TokenType.OR: 'OR'>
AMP = <TokenType.AMP: 'AMP'>
DPIPE = <TokenType.DPIPE: 'DPIPE'>
PIPE = <TokenType.PIPE: 'PIPE'>
CARET = <TokenType.CARET: 'CARET'>
TILDA = <TokenType.TILDA: 'TILDA'>
ARROW = <TokenType.ARROW: 'ARROW'>
DARROW = <TokenType.DARROW: 'DARROW'>
FARROW = <TokenType.FARROW: 'FARROW'>
HASH = <TokenType.HASH: 'HASH'>
HASH_ARROW = <TokenType.HASH_ARROW: 'HASH_ARROW'>
DHASH_ARROW = <TokenType.DHASH_ARROW: 'DHASH_ARROW'>
LR_ARROW = <TokenType.LR_ARROW: 'LR_ARROW'>
DAT = <TokenType.DAT: 'DAT'>
LT_AT = <TokenType.LT_AT: 'LT_AT'>
AT_GT = <TokenType.AT_GT: 'AT_GT'>
DOLLAR = <TokenType.DOLLAR: 'DOLLAR'>
PARAMETER = <TokenType.PARAMETER: 'PARAMETER'>
SESSION_PARAMETER = <TokenType.SESSION_PARAMETER: 'SESSION_PARAMETER'>
DAMP = <TokenType.DAMP: 'DAMP'>
XOR = <TokenType.XOR: 'XOR'>
DSTAR = <TokenType.DSTAR: 'DSTAR'>
BLOCK_START = <TokenType.BLOCK_START: 'BLOCK_START'>
BLOCK_END = <TokenType.BLOCK_END: 'BLOCK_END'>
SPACE = <TokenType.SPACE: 'SPACE'>
BREAK = <TokenType.BREAK: 'BREAK'>
STRING = <TokenType.STRING: 'STRING'>
NUMBER = <TokenType.NUMBER: 'NUMBER'>
IDENTIFIER = <TokenType.IDENTIFIER: 'IDENTIFIER'>
DATABASE = <TokenType.DATABASE: 'DATABASE'>
COLUMN = <TokenType.COLUMN: 'COLUMN'>
COLUMN_DEF = <TokenType.COLUMN_DEF: 'COLUMN_DEF'>
SCHEMA = <TokenType.SCHEMA: 'SCHEMA'>
TABLE = <TokenType.TABLE: 'TABLE'>
VAR = <TokenType.VAR: 'VAR'>
BIT_STRING = <TokenType.BIT_STRING: 'BIT_STRING'>
HEX_STRING = <TokenType.HEX_STRING: 'HEX_STRING'>
BYTE_STRING = <TokenType.BYTE_STRING: 'BYTE_STRING'>
NATIONAL_STRING = <TokenType.NATIONAL_STRING: 'NATIONAL_STRING'>
RAW_STRING = <TokenType.RAW_STRING: 'RAW_STRING'>
HEREDOC_STRING = <TokenType.HEREDOC_STRING: 'HEREDOC_STRING'>
UNICODE_STRING = <TokenType.UNICODE_STRING: 'UNICODE_STRING'>
BIT = <TokenType.BIT: 'BIT'>
BOOLEAN = <TokenType.BOOLEAN: 'BOOLEAN'>
TINYINT = <TokenType.TINYINT: 'TINYINT'>
UTINYINT = <TokenType.UTINYINT: 'UTINYINT'>
SMALLINT = <TokenType.SMALLINT: 'SMALLINT'>
USMALLINT = <TokenType.USMALLINT: 'USMALLINT'>
MEDIUMINT = <TokenType.MEDIUMINT: 'MEDIUMINT'>
UMEDIUMINT = <TokenType.UMEDIUMINT: 'UMEDIUMINT'>
INT = <TokenType.INT: 'INT'>
UINT = <TokenType.UINT: 'UINT'>
BIGINT = <TokenType.BIGINT: 'BIGINT'>
UBIGINT = <TokenType.UBIGINT: 'UBIGINT'>
INT128 = <TokenType.INT128: 'INT128'>
UINT128 = <TokenType.UINT128: 'UINT128'>
INT256 = <TokenType.INT256: 'INT256'>
UINT256 = <TokenType.UINT256: 'UINT256'>
FLOAT = <TokenType.FLOAT: 'FLOAT'>
DOUBLE = <TokenType.DOUBLE: 'DOUBLE'>
DECIMAL = <TokenType.DECIMAL: 'DECIMAL'>
UDECIMAL = <TokenType.UDECIMAL: 'UDECIMAL'>
BIGDECIMAL = <TokenType.BIGDECIMAL: 'BIGDECIMAL'>
CHAR = <TokenType.CHAR: 'CHAR'>
NCHAR = <TokenType.NCHAR: 'NCHAR'>
VARCHAR = <TokenType.VARCHAR: 'VARCHAR'>
NVARCHAR = <TokenType.NVARCHAR: 'NVARCHAR'>
TEXT = <TokenType.TEXT: 'TEXT'>
MEDIUMTEXT = <TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>
LONGTEXT = <TokenType.LONGTEXT: 'LONGTEXT'>
MEDIUMBLOB = <TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>
LONGBLOB = <TokenType.LONGBLOB: 'LONGBLOB'>
TINYBLOB = <TokenType.TINYBLOB: 'TINYBLOB'>
TINYTEXT = <TokenType.TINYTEXT: 'TINYTEXT'>
BINARY = <TokenType.BINARY: 'BINARY'>
VARBINARY = <TokenType.VARBINARY: 'VARBINARY'>
JSON = <TokenType.JSON: 'JSON'>
JSONB = <TokenType.JSONB: 'JSONB'>
TIME = <TokenType.TIME: 'TIME'>
TIMETZ = <TokenType.TIMETZ: 'TIMETZ'>
TIMESTAMP = <TokenType.TIMESTAMP: 'TIMESTAMP'>
TIMESTAMPTZ = <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>
TIMESTAMPLTZ = <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>
TIMESTAMP_S = <TokenType.TIMESTAMP_S: 'TIMESTAMP_S'>
TIMESTAMP_MS = <TokenType.TIMESTAMP_MS: 'TIMESTAMP_MS'>
TIMESTAMP_NS = <TokenType.TIMESTAMP_NS: 'TIMESTAMP_NS'>
DATETIME = <TokenType.DATETIME: 'DATETIME'>
DATETIME64 = <TokenType.DATETIME64: 'DATETIME64'>
DATE = <TokenType.DATE: 'DATE'>
DATE32 = <TokenType.DATE32: 'DATE32'>
INT4RANGE = <TokenType.INT4RANGE: 'INT4RANGE'>
INT4MULTIRANGE = <TokenType.INT4MULTIRANGE: 'INT4MULTIRANGE'>
INT8RANGE = <TokenType.INT8RANGE: 'INT8RANGE'>
INT8MULTIRANGE = <TokenType.INT8MULTIRANGE: 'INT8MULTIRANGE'>
NUMRANGE = <TokenType.NUMRANGE: 'NUMRANGE'>
NUMMULTIRANGE = <TokenType.NUMMULTIRANGE: 'NUMMULTIRANGE'>
TSRANGE = <TokenType.TSRANGE: 'TSRANGE'>
TSMULTIRANGE = <TokenType.TSMULTIRANGE: 'TSMULTIRANGE'>
TSTZRANGE = <TokenType.TSTZRANGE: 'TSTZRANGE'>
TSTZMULTIRANGE = <TokenType.TSTZMULTIRANGE: 'TSTZMULTIRANGE'>
DATERANGE = <TokenType.DATERANGE: 'DATERANGE'>
DATEMULTIRANGE = <TokenType.DATEMULTIRANGE: 'DATEMULTIRANGE'>
UUID = <TokenType.UUID: 'UUID'>
GEOGRAPHY = <TokenType.GEOGRAPHY: 'GEOGRAPHY'>
NULLABLE = <TokenType.NULLABLE: 'NULLABLE'>
GEOMETRY = <TokenType.GEOMETRY: 'GEOMETRY'>
HLLSKETCH = <TokenType.HLLSKETCH: 'HLLSKETCH'>
HSTORE = <TokenType.HSTORE: 'HSTORE'>
SUPER = <TokenType.SUPER: 'SUPER'>
SERIAL = <TokenType.SERIAL: 'SERIAL'>
SMALLSERIAL = <TokenType.SMALLSERIAL: 'SMALLSERIAL'>
BIGSERIAL = <TokenType.BIGSERIAL: 'BIGSERIAL'>
XML = <TokenType.XML: 'XML'>
YEAR = <TokenType.YEAR: 'YEAR'>
UNIQUEIDENTIFIER = <TokenType.UNIQUEIDENTIFIER: 'UNIQUEIDENTIFIER'>
USERDEFINED = <TokenType.USERDEFINED: 'USERDEFINED'>
MONEY = <TokenType.MONEY: 'MONEY'>
SMALLMONEY = <TokenType.SMALLMONEY: 'SMALLMONEY'>
ROWVERSION = <TokenType.ROWVERSION: 'ROWVERSION'>
IMAGE = <TokenType.IMAGE: 'IMAGE'>
VARIANT = <TokenType.VARIANT: 'VARIANT'>
OBJECT = <TokenType.OBJECT: 'OBJECT'>
INET = <TokenType.INET: 'INET'>
IPADDRESS = <TokenType.IPADDRESS: 'IPADDRESS'>
IPPREFIX = <TokenType.IPPREFIX: 'IPPREFIX'>
IPV4 = <TokenType.IPV4: 'IPV4'>
IPV6 = <TokenType.IPV6: 'IPV6'>
ENUM = <TokenType.ENUM: 'ENUM'>
ENUM8 = <TokenType.ENUM8: 'ENUM8'>
ENUM16 = <TokenType.ENUM16: 'ENUM16'>
FIXEDSTRING = <TokenType.FIXEDSTRING: 'FIXEDSTRING'>
LOWCARDINALITY = <TokenType.LOWCARDINALITY: 'LOWCARDINALITY'>
NESTED = <TokenType.NESTED: 'NESTED'>
AGGREGATEFUNCTION = <TokenType.AGGREGATEFUNCTION: 'AGGREGATEFUNCTION'>
SIMPLEAGGREGATEFUNCTION = <TokenType.SIMPLEAGGREGATEFUNCTION: 'SIMPLEAGGREGATEFUNCTION'>
UNKNOWN = <TokenType.UNKNOWN: 'UNKNOWN'>
ALIAS = <TokenType.ALIAS: 'ALIAS'>
ALTER = <TokenType.ALTER: 'ALTER'>
ALWAYS = <TokenType.ALWAYS: 'ALWAYS'>
ALL = <TokenType.ALL: 'ALL'>
ANTI = <TokenType.ANTI: 'ANTI'>
ANY = <TokenType.ANY: 'ANY'>
APPLY = <TokenType.APPLY: 'APPLY'>
ARRAY = <TokenType.ARRAY: 'ARRAY'>
ASC = <TokenType.ASC: 'ASC'>
ASOF = <TokenType.ASOF: 'ASOF'>
AUTO_INCREMENT = <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>
BEGIN = <TokenType.BEGIN: 'BEGIN'>
BETWEEN = <TokenType.BETWEEN: 'BETWEEN'>
CACHE = <TokenType.CACHE: 'CACHE'>
CASE = <TokenType.CASE: 'CASE'>
CHARACTER_SET = <TokenType.CHARACTER_SET: 'CHARACTER_SET'>
CLUSTER_BY = <TokenType.CLUSTER_BY: 'CLUSTER_BY'>
COLLATE = <TokenType.COLLATE: 'COLLATE'>
COMMAND = <TokenType.COMMAND: 'COMMAND'>
COMMENT = <TokenType.COMMENT: 'COMMENT'>
COMMIT = <TokenType.COMMIT: 'COMMIT'>
CONNECT_BY = <TokenType.CONNECT_BY: 'CONNECT_BY'>
CONSTRAINT = <TokenType.CONSTRAINT: 'CONSTRAINT'>
CREATE = <TokenType.CREATE: 'CREATE'>
CROSS = <TokenType.CROSS: 'CROSS'>
CUBE = <TokenType.CUBE: 'CUBE'>
CURRENT_DATE = <TokenType.CURRENT_DATE: 'CURRENT_DATE'>
CURRENT_DATETIME = <TokenType.CURRENT_DATETIME: 'CURRENT_DATETIME'>
CURRENT_TIME = <TokenType.CURRENT_TIME: 'CURRENT_TIME'>
CURRENT_TIMESTAMP = <TokenType.CURRENT_TIMESTAMP: 'CURRENT_TIMESTAMP'>
CURRENT_USER = <TokenType.CURRENT_USER: 'CURRENT_USER'>
DEFAULT = <TokenType.DEFAULT: 'DEFAULT'>
DELETE = <TokenType.DELETE: 'DELETE'>
DESC = <TokenType.DESC: 'DESC'>
DESCRIBE = <TokenType.DESCRIBE: 'DESCRIBE'>
DICTIONARY = <TokenType.DICTIONARY: 'DICTIONARY'>
DISTINCT = <TokenType.DISTINCT: 'DISTINCT'>
DISTRIBUTE_BY = <TokenType.DISTRIBUTE_BY: 'DISTRIBUTE_BY'>
DIV = <TokenType.DIV: 'DIV'>
DROP = <TokenType.DROP: 'DROP'>
ELSE = <TokenType.ELSE: 'ELSE'>
END = <TokenType.END: 'END'>
ESCAPE = <TokenType.ESCAPE: 'ESCAPE'>
EXCEPT = <TokenType.EXCEPT: 'EXCEPT'>
EXECUTE = <TokenType.EXECUTE: 'EXECUTE'>
EXISTS = <TokenType.EXISTS: 'EXISTS'>
FALSE = <TokenType.FALSE: 'FALSE'>
FETCH = <TokenType.FETCH: 'FETCH'>
FILTER = <TokenType.FILTER: 'FILTER'>
FINAL = <TokenType.FINAL: 'FINAL'>
FIRST = <TokenType.FIRST: 'FIRST'>
FOR = <TokenType.FOR: 'FOR'>
FORCE = <TokenType.FORCE: 'FORCE'>
FOREIGN_KEY = <TokenType.FOREIGN_KEY: 'FOREIGN_KEY'>
FORMAT = <TokenType.FORMAT: 'FORMAT'>
FROM = <TokenType.FROM: 'FROM'>
FULL = <TokenType.FULL: 'FULL'>
FUNCTION = <TokenType.FUNCTION: 'FUNCTION'>
GLOB = <TokenType.GLOB: 'GLOB'>
GLOBAL = <TokenType.GLOBAL: 'GLOBAL'>
GROUP_BY = <TokenType.GROUP_BY: 'GROUP_BY'>
GROUPING_SETS = <TokenType.GROUPING_SETS: 'GROUPING_SETS'>
HAVING = <TokenType.HAVING: 'HAVING'>
HINT = <TokenType.HINT: 'HINT'>
IGNORE = <TokenType.IGNORE: 'IGNORE'>
ILIKE = <TokenType.ILIKE: 'ILIKE'>
ILIKE_ANY = <TokenType.ILIKE_ANY: 'ILIKE_ANY'>
IN = <TokenType.IN: 'IN'>
INDEX = <TokenType.INDEX: 'INDEX'>
INNER = <TokenType.INNER: 'INNER'>
INSERT = <TokenType.INSERT: 'INSERT'>
INTERSECT = <TokenType.INTERSECT: 'INTERSECT'>
INTERVAL = <TokenType.INTERVAL: 'INTERVAL'>
INTO = <TokenType.INTO: 'INTO'>
INTRODUCER = <TokenType.INTRODUCER: 'INTRODUCER'>
IRLIKE = <TokenType.IRLIKE: 'IRLIKE'>
IS = <TokenType.IS: 'IS'>
ISNULL = <TokenType.ISNULL: 'ISNULL'>
JOIN = <TokenType.JOIN: 'JOIN'>
JOIN_MARKER = <TokenType.JOIN_MARKER: 'JOIN_MARKER'>
KEEP = <TokenType.KEEP: 'KEEP'>
KILL = <TokenType.KILL: 'KILL'>
LANGUAGE = <TokenType.LANGUAGE: 'LANGUAGE'>
LATERAL = <TokenType.LATERAL: 'LATERAL'>
LEFT = <TokenType.LEFT: 'LEFT'>
LIKE = <TokenType.LIKE: 'LIKE'>
LIKE_ANY = <TokenType.LIKE_ANY: 'LIKE_ANY'>
LIMIT = <TokenType.LIMIT: 'LIMIT'>
LOAD = <TokenType.LOAD: 'LOAD'>
LOCK = <TokenType.LOCK: 'LOCK'>
MAP = <TokenType.MAP: 'MAP'>
MATCH_RECOGNIZE = <TokenType.MATCH_RECOGNIZE: 'MATCH_RECOGNIZE'>
MEMBER_OF = <TokenType.MEMBER_OF: 'MEMBER_OF'>
MERGE = <TokenType.MERGE: 'MERGE'>
MOD = <TokenType.MOD: 'MOD'>
MODEL = <TokenType.MODEL: 'MODEL'>
NATURAL = <TokenType.NATURAL: 'NATURAL'>
NEXT = <TokenType.NEXT: 'NEXT'>
NOTNULL = <TokenType.NOTNULL: 'NOTNULL'>
NULL = <TokenType.NULL: 'NULL'>
OBJECT_IDENTIFIER = <TokenType.OBJECT_IDENTIFIER: 'OBJECT_IDENTIFIER'>
OFFSET = <TokenType.OFFSET: 'OFFSET'>
ON = <TokenType.ON: 'ON'>
OPERATOR = <TokenType.OPERATOR: 'OPERATOR'>
ORDER_BY = <TokenType.ORDER_BY: 'ORDER_BY'>
ORDER_SIBLINGS_BY = <TokenType.ORDER_SIBLINGS_BY: 'ORDER_SIBLINGS_BY'>
ORDERED = <TokenType.ORDERED: 'ORDERED'>
ORDINALITY = <TokenType.ORDINALITY: 'ORDINALITY'>
OUTER = <TokenType.OUTER: 'OUTER'>
OVER = <TokenType.OVER: 'OVER'>
OVERLAPS = <TokenType.OVERLAPS: 'OVERLAPS'>
OVERWRITE = <TokenType.OVERWRITE: 'OVERWRITE'>
PARTITION = <TokenType.PARTITION: 'PARTITION'>
PARTITION_BY = <TokenType.PARTITION_BY: 'PARTITION_BY'>
PERCENT = <TokenType.PERCENT: 'PERCENT'>
PIVOT = <TokenType.PIVOT: 'PIVOT'>
PLACEHOLDER = <TokenType.PLACEHOLDER: 'PLACEHOLDER'>
PRAGMA = <TokenType.PRAGMA: 'PRAGMA'>
PRIMARY_KEY = <TokenType.PRIMARY_KEY: 'PRIMARY_KEY'>
PROCEDURE = <TokenType.PROCEDURE: 'PROCEDURE'>
PROPERTIES = <TokenType.PROPERTIES: 'PROPERTIES'>
PSEUDO_TYPE = <TokenType.PSEUDO_TYPE: 'PSEUDO_TYPE'>
QUALIFY = <TokenType.QUALIFY: 'QUALIFY'>
QUOTE = <TokenType.QUOTE: 'QUOTE'>
RANGE = <TokenType.RANGE: 'RANGE'>
RECURSIVE = <TokenType.RECURSIVE: 'RECURSIVE'>
REFRESH = <TokenType.REFRESH: 'REFRESH'>
REPLACE = <TokenType.REPLACE: 'REPLACE'>
RETURNING = <TokenType.RETURNING: 'RETURNING'>
REFERENCES = <TokenType.REFERENCES: 'REFERENCES'>
RIGHT = <TokenType.RIGHT: 'RIGHT'>
RLIKE = <TokenType.RLIKE: 'RLIKE'>
ROLLBACK = <TokenType.ROLLBACK: 'ROLLBACK'>
ROLLUP = <TokenType.ROLLUP: 'ROLLUP'>
ROW = <TokenType.ROW: 'ROW'>
ROWS = <TokenType.ROWS: 'ROWS'>
SELECT = <TokenType.SELECT: 'SELECT'>
SEMI = <TokenType.SEMI: 'SEMI'>
SEPARATOR = <TokenType.SEPARATOR: 'SEPARATOR'>
SERDE_PROPERTIES = <TokenType.SERDE_PROPERTIES: 'SERDE_PROPERTIES'>
SET = <TokenType.SET: 'SET'>
SETTINGS = <TokenType.SETTINGS: 'SETTINGS'>
SHOW = <TokenType.SHOW: 'SHOW'>
SIMILAR_TO = <TokenType.SIMILAR_TO: 'SIMILAR_TO'>
SOME = <TokenType.SOME: 'SOME'>
SORT_BY = <TokenType.SORT_BY: 'SORT_BY'>
START_WITH = <TokenType.START_WITH: 'START_WITH'>
STRUCT = <TokenType.STRUCT: 'STRUCT'>
TABLE_SAMPLE = <TokenType.TABLE_SAMPLE: 'TABLE_SAMPLE'>
TEMPORARY = <TokenType.TEMPORARY: 'TEMPORARY'>
TOP = <TokenType.TOP: 'TOP'>
THEN = <TokenType.THEN: 'THEN'>
TRUE = <TokenType.TRUE: 'TRUE'>
UNCACHE = <TokenType.UNCACHE: 'UNCACHE'>
UNION = <TokenType.UNION: 'UNION'>
UNNEST = <TokenType.UNNEST: 'UNNEST'>
UNPIVOT = <TokenType.UNPIVOT: 'UNPIVOT'>
UPDATE = <TokenType.UPDATE: 'UPDATE'>
USE = <TokenType.USE: 'USE'>
USING = <TokenType.USING: 'USING'>
VALUES = <TokenType.VALUES: 'VALUES'>
VIEW = <TokenType.VIEW: 'VIEW'>
VOLATILE = <TokenType.VOLATILE: 'VOLATILE'>
WHEN = <TokenType.WHEN: 'WHEN'>
WHERE = <TokenType.WHERE: 'WHERE'>
WINDOW = <TokenType.WINDOW: 'WINDOW'>
WITH = <TokenType.WITH: 'WITH'>
UNIQUE = <TokenType.UNIQUE: 'UNIQUE'>
VERSION_SNAPSHOT = <TokenType.VERSION_SNAPSHOT: 'VERSION_SNAPSHOT'>
TIMESTAMP_SNAPSHOT = <TokenType.TIMESTAMP_SNAPSHOT: 'TIMESTAMP_SNAPSHOT'>
Inherited Members
enum.Enum
name
value
class Token:
376class Token:
377    __slots__ = ("token_type", "text", "line", "col", "start", "end", "comments")
378
379    @classmethod
380    def number(cls, number: int) -> Token:
381        """Returns a NUMBER token with `number` as its text."""
382        return cls(TokenType.NUMBER, str(number))
383
384    @classmethod
385    def string(cls, string: str) -> Token:
386        """Returns a STRING token with `string` as its text."""
387        return cls(TokenType.STRING, string)
388
389    @classmethod
390    def identifier(cls, identifier: str) -> Token:
391        """Returns an IDENTIFIER token with `identifier` as its text."""
392        return cls(TokenType.IDENTIFIER, identifier)
393
394    @classmethod
395    def var(cls, var: str) -> Token:
396        """Returns an VAR token with `var` as its text."""
397        return cls(TokenType.VAR, var)
398
399    def __init__(
400        self,
401        token_type: TokenType,
402        text: str,
403        line: int = 1,
404        col: int = 1,
405        start: int = 0,
406        end: int = 0,
407        comments: t.Optional[t.List[str]] = None,
408    ) -> None:
409        """Token initializer.
410
411        Args:
412            token_type: The TokenType Enum.
413            text: The text of the token.
414            line: The line that the token ends on.
415            col: The column that the token ends on.
416            start: The start index of the token.
417            end: The ending index of the token.
418            comments: The comments to attach to the token.
419        """
420        self.token_type = token_type
421        self.text = text
422        self.line = line
423        self.col = col
424        self.start = start
425        self.end = end
426        self.comments = [] if comments is None else comments
427
428    def __repr__(self) -> str:
429        attributes = ", ".join(f"{k}: {getattr(self, k)}" for k in self.__slots__)
430        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)
399    def __init__(
400        self,
401        token_type: TokenType,
402        text: str,
403        line: int = 1,
404        col: int = 1,
405        start: int = 0,
406        end: int = 0,
407        comments: t.Optional[t.List[str]] = None,
408    ) -> None:
409        """Token initializer.
410
411        Args:
412            token_type: The TokenType Enum.
413            text: The text of the token.
414            line: The line that the token ends on.
415            col: The column that the token ends on.
416            start: The start index of the token.
417            end: The ending index of the token.
418            comments: The comments to attach to the token.
419        """
420        self.token_type = token_type
421        self.text = text
422        self.line = line
423        self.col = col
424        self.start = start
425        self.end = end
426        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.
@classmethod
def number(cls, number: int) -> Token:
379    @classmethod
380    def number(cls, number: int) -> Token:
381        """Returns a NUMBER token with `number` as its text."""
382        return cls(TokenType.NUMBER, str(number))

Returns a NUMBER token with number as its text.

@classmethod
def string(cls, string: str) -> Token:
384    @classmethod
385    def string(cls, string: str) -> Token:
386        """Returns a STRING token with `string` as its text."""
387        return cls(TokenType.STRING, string)

Returns a STRING token with string as its text.

@classmethod
def identifier(cls, identifier: str) -> Token:
389    @classmethod
390    def identifier(cls, identifier: str) -> Token:
391        """Returns an IDENTIFIER token with `identifier` as its text."""
392        return cls(TokenType.IDENTIFIER, identifier)

Returns an IDENTIFIER token with identifier as its text.

@classmethod
def var(cls, var: str) -> Token:
394    @classmethod
395    def var(cls, var: str) -> Token:
396        """Returns an VAR token with `var` as its text."""
397        return cls(TokenType.VAR, var)

Returns an VAR token with var as its text.

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

Returns a list of tokens corresponding to the SQL string sql.

def peek(self, i: int = 0) -> str:
1027    def peek(self, i: int = 0) -> str:
1028        i = self._current + i
1029        if i < self.size:
1030            return self.sql[i]
1031        return ""
def tokenize_rs(self, sql: str) -> List[Token]:
1336    def tokenize_rs(self, sql: str) -> t.List[Token]:
1337        if not self._RS_TOKENIZER:
1338            raise SqlglotError("Rust tokenizer is not available")
1339
1340        try:
1341            tokens = self._RS_TOKENIZER.tokenize(sql, self._rs_dialect_settings)
1342            for token in tokens:
1343                token.token_type = _ALL_TOKEN_TYPES[token.token_type_index]
1344            return tokens
1345        except Exception as e:
1346            raise TokenError(str(e))
size
sql
tokens