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    BPCHAR = 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()
 370
 371
 372_ALL_TOKEN_TYPES = list(TokenType)
 373_TOKEN_TYPE_TO_INDEX = {token_type: i for i, token_type in enumerate(_ALL_TOKEN_TYPES)}
 374
 375
 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}>"
 431
 432
 433class _Tokenizer(type):
 434    def __new__(cls, clsname, bases, attrs):
 435        klass = super().__new__(cls, clsname, bases, attrs)
 436
 437        def _convert_quotes(arr: t.List[str | t.Tuple[str, str]]) -> t.Dict[str, str]:
 438            return dict(
 439                (item, item) if isinstance(item, str) else (item[0], item[1]) for item in arr
 440            )
 441
 442        def _quotes_to_format(
 443            token_type: TokenType, arr: t.List[str | t.Tuple[str, str]]
 444        ) -> t.Dict[str, t.Tuple[str, TokenType]]:
 445            return {k: (v, token_type) for k, v in _convert_quotes(arr).items()}
 446
 447        klass._QUOTES = _convert_quotes(klass.QUOTES)
 448        klass._IDENTIFIERS = _convert_quotes(klass.IDENTIFIERS)
 449
 450        klass._FORMAT_STRINGS = {
 451            **{
 452                p + s: (e, TokenType.NATIONAL_STRING)
 453                for s, e in klass._QUOTES.items()
 454                for p in ("n", "N")
 455            },
 456            **_quotes_to_format(TokenType.BIT_STRING, klass.BIT_STRINGS),
 457            **_quotes_to_format(TokenType.BYTE_STRING, klass.BYTE_STRINGS),
 458            **_quotes_to_format(TokenType.HEX_STRING, klass.HEX_STRINGS),
 459            **_quotes_to_format(TokenType.RAW_STRING, klass.RAW_STRINGS),
 460            **_quotes_to_format(TokenType.HEREDOC_STRING, klass.HEREDOC_STRINGS),
 461            **_quotes_to_format(TokenType.UNICODE_STRING, klass.UNICODE_STRINGS),
 462        }
 463
 464        klass._STRING_ESCAPES = set(klass.STRING_ESCAPES)
 465        klass._IDENTIFIER_ESCAPES = set(klass.IDENTIFIER_ESCAPES)
 466        klass._COMMENTS = {
 467            **dict(
 468                (comment, None) if isinstance(comment, str) else (comment[0], comment[1])
 469                for comment in klass.COMMENTS
 470            ),
 471            "{#": "#}",  # Ensure Jinja comments are tokenized correctly in all dialects
 472        }
 473
 474        klass._KEYWORD_TRIE = new_trie(
 475            key.upper()
 476            for key in (
 477                *klass.KEYWORDS,
 478                *klass._COMMENTS,
 479                *klass._QUOTES,
 480                *klass._FORMAT_STRINGS,
 481            )
 482            if " " in key or any(single in key for single in klass.SINGLE_TOKENS)
 483        )
 484
 485        if USE_RS_TOKENIZER:
 486            settings = RsTokenizerSettings(
 487                white_space={k: _TOKEN_TYPE_TO_INDEX[v] for k, v in klass.WHITE_SPACE.items()},
 488                single_tokens={k: _TOKEN_TYPE_TO_INDEX[v] for k, v in klass.SINGLE_TOKENS.items()},
 489                keywords={k: _TOKEN_TYPE_TO_INDEX[v] for k, v in klass.KEYWORDS.items()},
 490                numeric_literals=klass.NUMERIC_LITERALS,
 491                identifiers=klass._IDENTIFIERS,
 492                identifier_escapes=klass._IDENTIFIER_ESCAPES,
 493                string_escapes=klass._STRING_ESCAPES,
 494                quotes=klass._QUOTES,
 495                format_strings={
 496                    k: (v1, _TOKEN_TYPE_TO_INDEX[v2])
 497                    for k, (v1, v2) in klass._FORMAT_STRINGS.items()
 498                },
 499                has_bit_strings=bool(klass.BIT_STRINGS),
 500                has_hex_strings=bool(klass.HEX_STRINGS),
 501                comments=klass._COMMENTS,
 502                var_single_tokens=klass.VAR_SINGLE_TOKENS,
 503                commands={_TOKEN_TYPE_TO_INDEX[v] for v in klass.COMMANDS},
 504                command_prefix_tokens={
 505                    _TOKEN_TYPE_TO_INDEX[v] for v in klass.COMMAND_PREFIX_TOKENS
 506                },
 507            )
 508            token_types = RsTokenTypeSettings(
 509                bit_string=_TOKEN_TYPE_TO_INDEX[TokenType.BIT_STRING],
 510                break_=_TOKEN_TYPE_TO_INDEX[TokenType.BREAK],
 511                dcolon=_TOKEN_TYPE_TO_INDEX[TokenType.DCOLON],
 512                heredoc_string=_TOKEN_TYPE_TO_INDEX[TokenType.HEREDOC_STRING],
 513                hex_string=_TOKEN_TYPE_TO_INDEX[TokenType.HEX_STRING],
 514                identifier=_TOKEN_TYPE_TO_INDEX[TokenType.IDENTIFIER],
 515                number=_TOKEN_TYPE_TO_INDEX[TokenType.NUMBER],
 516                parameter=_TOKEN_TYPE_TO_INDEX[TokenType.PARAMETER],
 517                semicolon=_TOKEN_TYPE_TO_INDEX[TokenType.SEMICOLON],
 518                string=_TOKEN_TYPE_TO_INDEX[TokenType.STRING],
 519                var=_TOKEN_TYPE_TO_INDEX[TokenType.VAR],
 520            )
 521            klass._RS_TOKENIZER = RsTokenizer(settings, token_types)
 522        else:
 523            klass._RS_TOKENIZER = None
 524
 525        return klass
 526
 527
 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        "BPCHAR": TokenType.BPCHAR,
 806        "STR": TokenType.TEXT,
 807        "STRING": TokenType.TEXT,
 808        "TEXT": TokenType.TEXT,
 809        "LONGTEXT": TokenType.LONGTEXT,
 810        "MEDIUMTEXT": TokenType.MEDIUMTEXT,
 811        "TINYTEXT": TokenType.TINYTEXT,
 812        "CLOB": TokenType.TEXT,
 813        "LONGVARCHAR": TokenType.TEXT,
 814        "BINARY": TokenType.BINARY,
 815        "BLOB": TokenType.VARBINARY,
 816        "LONGBLOB": TokenType.LONGBLOB,
 817        "MEDIUMBLOB": TokenType.MEDIUMBLOB,
 818        "TINYBLOB": TokenType.TINYBLOB,
 819        "BYTEA": TokenType.VARBINARY,
 820        "VARBINARY": TokenType.VARBINARY,
 821        "TIME": TokenType.TIME,
 822        "TIMETZ": TokenType.TIMETZ,
 823        "TIMESTAMP": TokenType.TIMESTAMP,
 824        "TIMESTAMPTZ": TokenType.TIMESTAMPTZ,
 825        "TIMESTAMPLTZ": TokenType.TIMESTAMPLTZ,
 826        "DATE": TokenType.DATE,
 827        "DATETIME": TokenType.DATETIME,
 828        "INT4RANGE": TokenType.INT4RANGE,
 829        "INT4MULTIRANGE": TokenType.INT4MULTIRANGE,
 830        "INT8RANGE": TokenType.INT8RANGE,
 831        "INT8MULTIRANGE": TokenType.INT8MULTIRANGE,
 832        "NUMRANGE": TokenType.NUMRANGE,
 833        "NUMMULTIRANGE": TokenType.NUMMULTIRANGE,
 834        "TSRANGE": TokenType.TSRANGE,
 835        "TSMULTIRANGE": TokenType.TSMULTIRANGE,
 836        "TSTZRANGE": TokenType.TSTZRANGE,
 837        "TSTZMULTIRANGE": TokenType.TSTZMULTIRANGE,
 838        "DATERANGE": TokenType.DATERANGE,
 839        "DATEMULTIRANGE": TokenType.DATEMULTIRANGE,
 840        "UNIQUE": TokenType.UNIQUE,
 841        "STRUCT": TokenType.STRUCT,
 842        "VARIANT": TokenType.VARIANT,
 843        "ALTER": TokenType.ALTER,
 844        "ANALYZE": TokenType.COMMAND,
 845        "CALL": TokenType.COMMAND,
 846        "COMMENT": TokenType.COMMENT,
 847        "COPY": TokenType.COMMAND,
 848        "EXPLAIN": TokenType.COMMAND,
 849        "GRANT": TokenType.COMMAND,
 850        "OPTIMIZE": TokenType.COMMAND,
 851        "PREPARE": TokenType.COMMAND,
 852        "TRUNCATE": TokenType.COMMAND,
 853        "VACUUM": TokenType.COMMAND,
 854        "USER-DEFINED": TokenType.USERDEFINED,
 855        "FOR VERSION": TokenType.VERSION_SNAPSHOT,
 856        "FOR TIMESTAMP": TokenType.TIMESTAMP_SNAPSHOT,
 857    }
 858
 859    WHITE_SPACE: t.Dict[t.Optional[str], TokenType] = {
 860        " ": TokenType.SPACE,
 861        "\t": TokenType.SPACE,
 862        "\n": TokenType.BREAK,
 863        "\r": TokenType.BREAK,
 864    }
 865
 866    COMMANDS = {
 867        TokenType.COMMAND,
 868        TokenType.EXECUTE,
 869        TokenType.FETCH,
 870        TokenType.SHOW,
 871    }
 872
 873    COMMAND_PREFIX_TOKENS = {TokenType.SEMICOLON, TokenType.BEGIN}
 874
 875    # handle numeric literals like in hive (3L = BIGINT)
 876    NUMERIC_LITERALS: t.Dict[str, str] = {}
 877
 878    COMMENTS = ["--", ("/*", "*/")]
 879
 880    __slots__ = (
 881        "sql",
 882        "size",
 883        "tokens",
 884        "dialect",
 885        "_start",
 886        "_current",
 887        "_line",
 888        "_col",
 889        "_comments",
 890        "_char",
 891        "_end",
 892        "_peek",
 893        "_prev_token_line",
 894        "_rs_dialect_settings",
 895    )
 896
 897    def __init__(self, dialect: DialectType = None) -> None:
 898        from sqlglot.dialects import Dialect
 899
 900        self.dialect = Dialect.get_or_raise(dialect)
 901
 902        if USE_RS_TOKENIZER:
 903            self._rs_dialect_settings = RsTokenizerDialectSettings(
 904                escape_sequences=self.dialect.ESCAPE_SEQUENCES,
 905                identifiers_can_start_with_digit=self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT,
 906            )
 907
 908        self.reset()
 909
 910    def reset(self) -> None:
 911        self.sql = ""
 912        self.size = 0
 913        self.tokens: t.List[Token] = []
 914        self._start = 0
 915        self._current = 0
 916        self._line = 1
 917        self._col = 0
 918        self._comments: t.List[str] = []
 919
 920        self._char = ""
 921        self._end = False
 922        self._peek = ""
 923        self._prev_token_line = -1
 924
 925    def tokenize(self, sql: str) -> t.List[Token]:
 926        """Returns a list of tokens corresponding to the SQL string `sql`."""
 927        if USE_RS_TOKENIZER:
 928            return self.tokenize_rs(sql)
 929
 930        self.reset()
 931        self.sql = sql
 932        self.size = len(sql)
 933
 934        try:
 935            self._scan()
 936        except Exception as e:
 937            start = max(self._current - 50, 0)
 938            end = min(self._current + 50, self.size - 1)
 939            context = self.sql[start:end]
 940            raise TokenError(f"Error tokenizing '{context}'") from e
 941
 942        return self.tokens
 943
 944    def _scan(self, until: t.Optional[t.Callable] = None) -> None:
 945        while self.size and not self._end:
 946            current = self._current
 947
 948            # skip spaces inline rather than iteratively call advance()
 949            # for performance reasons
 950            while current < self.size:
 951                char = self.sql[current]
 952
 953                if char.isspace() and (char == " " or char == "\t"):
 954                    current += 1
 955                else:
 956                    break
 957
 958            n = current - self._current
 959            self._start = current
 960            self._advance(n if n > 1 else 1)
 961
 962            if self._char is None:
 963                break
 964
 965            if not self._char.isspace():
 966                if self._char.isdigit():
 967                    self._scan_number()
 968                elif self._char in self._IDENTIFIERS:
 969                    self._scan_identifier(self._IDENTIFIERS[self._char])
 970                else:
 971                    self._scan_keywords()
 972
 973            if until and until():
 974                break
 975
 976        if self.tokens and self._comments:
 977            self.tokens[-1].comments.extend(self._comments)
 978
 979    def _chars(self, size: int) -> str:
 980        if size == 1:
 981            return self._char
 982
 983        start = self._current - 1
 984        end = start + size
 985
 986        return self.sql[start:end] if end <= self.size else ""
 987
 988    def _advance(self, i: int = 1, alnum: bool = False) -> None:
 989        if self.WHITE_SPACE.get(self._char) is TokenType.BREAK:
 990            # Ensures we don't count an extra line if we get a \r\n line break sequence
 991            if self._char == "\r" and self._peek == "\n":
 992                i = 2
 993                self._start += 1
 994
 995            self._col = 1
 996            self._line += 1
 997        else:
 998            self._col += i
 999
1000        self._current += i
1001        self._end = self._current >= self.size
1002        self._char = self.sql[self._current - 1]
1003        self._peek = "" if self._end else self.sql[self._current]
1004
1005        if alnum and self._char.isalnum():
1006            # Here we use local variables instead of attributes for better performance
1007            _col = self._col
1008            _current = self._current
1009            _end = self._end
1010            _peek = self._peek
1011
1012            while _peek.isalnum():
1013                _col += 1
1014                _current += 1
1015                _end = _current >= self.size
1016                _peek = "" if _end else self.sql[_current]
1017
1018            self._col = _col
1019            self._current = _current
1020            self._end = _end
1021            self._peek = _peek
1022            self._char = self.sql[_current - 1]
1023
1024    @property
1025    def _text(self) -> str:
1026        return self.sql[self._start : self._current]
1027
1028    def peek(self, i: int = 0) -> str:
1029        i = self._current + i
1030        if i < self.size:
1031            return self.sql[i]
1032        return ""
1033
1034    def _add(self, token_type: TokenType, text: t.Optional[str] = None) -> None:
1035        self._prev_token_line = self._line
1036
1037        if self._comments and token_type == TokenType.SEMICOLON and self.tokens:
1038            self.tokens[-1].comments.extend(self._comments)
1039            self._comments = []
1040
1041        self.tokens.append(
1042            Token(
1043                token_type,
1044                text=self._text if text is None else text,
1045                line=self._line,
1046                col=self._col,
1047                start=self._start,
1048                end=self._current - 1,
1049                comments=self._comments,
1050            )
1051        )
1052        self._comments = []
1053
1054        # If we have either a semicolon or a begin token before the command's token, we'll parse
1055        # whatever follows the command's token as a string
1056        if (
1057            token_type in self.COMMANDS
1058            and self._peek != ";"
1059            and (len(self.tokens) == 1 or self.tokens[-2].token_type in self.COMMAND_PREFIX_TOKENS)
1060        ):
1061            start = self._current
1062            tokens = len(self.tokens)
1063            self._scan(lambda: self._peek == ";")
1064            self.tokens = self.tokens[:tokens]
1065            text = self.sql[start : self._current].strip()
1066            if text:
1067                self._add(TokenType.STRING, text)
1068
1069    def _scan_keywords(self) -> None:
1070        size = 0
1071        word = None
1072        chars = self._text
1073        char = chars
1074        prev_space = False
1075        skip = False
1076        trie = self._KEYWORD_TRIE
1077        single_token = char in self.SINGLE_TOKENS
1078
1079        while chars:
1080            if skip:
1081                result = TrieResult.PREFIX
1082            else:
1083                result, trie = in_trie(trie, char.upper())
1084
1085            if result == TrieResult.FAILED:
1086                break
1087            if result == TrieResult.EXISTS:
1088                word = chars
1089
1090            end = self._current + size
1091            size += 1
1092
1093            if end < self.size:
1094                char = self.sql[end]
1095                single_token = single_token or char in self.SINGLE_TOKENS
1096                is_space = char.isspace()
1097
1098                if not is_space or not prev_space:
1099                    if is_space:
1100                        char = " "
1101                    chars += char
1102                    prev_space = is_space
1103                    skip = False
1104                else:
1105                    skip = True
1106            else:
1107                char = ""
1108                break
1109
1110        if word:
1111            if self._scan_string(word):
1112                return
1113            if self._scan_comment(word):
1114                return
1115            if prev_space or single_token or not char:
1116                self._advance(size - 1)
1117                word = word.upper()
1118                self._add(self.KEYWORDS[word], text=word)
1119                return
1120
1121        if self._char in self.SINGLE_TOKENS:
1122            self._add(self.SINGLE_TOKENS[self._char], text=self._char)
1123            return
1124
1125        self._scan_var()
1126
1127    def _scan_comment(self, comment_start: str) -> bool:
1128        if comment_start not in self._COMMENTS:
1129            return False
1130
1131        comment_start_line = self._line
1132        comment_start_size = len(comment_start)
1133        comment_end = self._COMMENTS[comment_start]
1134
1135        if comment_end:
1136            # Skip the comment's start delimiter
1137            self._advance(comment_start_size)
1138
1139            comment_end_size = len(comment_end)
1140            while not self._end and self._chars(comment_end_size) != comment_end:
1141                self._advance(alnum=True)
1142
1143            self._comments.append(self._text[comment_start_size : -comment_end_size + 1])
1144            self._advance(comment_end_size - 1)
1145        else:
1146            while not self._end and self.WHITE_SPACE.get(self._peek) is not TokenType.BREAK:
1147                self._advance(alnum=True)
1148            self._comments.append(self._text[comment_start_size:])
1149
1150        # Leading comment is attached to the succeeding token, whilst trailing comment to the preceding.
1151        # Multiple consecutive comments are preserved by appending them to the current comments list.
1152        if comment_start_line == self._prev_token_line:
1153            self.tokens[-1].comments.extend(self._comments)
1154            self._comments = []
1155            self._prev_token_line = self._line
1156
1157        return True
1158
1159    def _scan_number(self) -> None:
1160        if self._char == "0":
1161            peek = self._peek.upper()
1162            if peek == "B":
1163                return self._scan_bits() if self.BIT_STRINGS else self._add(TokenType.NUMBER)
1164            elif peek == "X":
1165                return self._scan_hex() if self.HEX_STRINGS else self._add(TokenType.NUMBER)
1166
1167        decimal = False
1168        scientific = 0
1169
1170        while True:
1171            if self._peek.isdigit():
1172                self._advance()
1173            elif self._peek == "." and not decimal:
1174                after = self.peek(1)
1175                if after.isdigit() or not after.isalpha():
1176                    decimal = True
1177                    self._advance()
1178                else:
1179                    return self._add(TokenType.VAR)
1180            elif self._peek in ("-", "+") and scientific == 1:
1181                scientific += 1
1182                self._advance()
1183            elif self._peek.upper() == "E" and not scientific:
1184                scientific += 1
1185                self._advance()
1186            elif self._peek.isidentifier():
1187                number_text = self._text
1188                literal = ""
1189
1190                while self._peek.strip() and self._peek not in self.SINGLE_TOKENS:
1191                    literal += self._peek
1192                    self._advance()
1193
1194                token_type = self.KEYWORDS.get(self.NUMERIC_LITERALS.get(literal.upper(), ""))
1195
1196                if token_type:
1197                    self._add(TokenType.NUMBER, number_text)
1198                    self._add(TokenType.DCOLON, "::")
1199                    return self._add(token_type, literal)
1200                elif self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT:
1201                    return self._add(TokenType.VAR)
1202
1203                self._advance(-len(literal))
1204                return self._add(TokenType.NUMBER, number_text)
1205            else:
1206                return self._add(TokenType.NUMBER)
1207
1208    def _scan_bits(self) -> None:
1209        self._advance()
1210        value = self._extract_value()
1211        try:
1212            # If `value` can't be converted to a binary, fallback to tokenizing it as an identifier
1213            int(value, 2)
1214            self._add(TokenType.BIT_STRING, value[2:])  # Drop the 0b
1215        except ValueError:
1216            self._add(TokenType.IDENTIFIER)
1217
1218    def _scan_hex(self) -> None:
1219        self._advance()
1220        value = self._extract_value()
1221        try:
1222            # If `value` can't be converted to a hex, fallback to tokenizing it as an identifier
1223            int(value, 16)
1224            self._add(TokenType.HEX_STRING, value[2:])  # Drop the 0x
1225        except ValueError:
1226            self._add(TokenType.IDENTIFIER)
1227
1228    def _extract_value(self) -> str:
1229        while True:
1230            char = self._peek.strip()
1231            if char and char not in self.SINGLE_TOKENS:
1232                self._advance(alnum=True)
1233            else:
1234                break
1235
1236        return self._text
1237
1238    def _scan_string(self, start: str) -> bool:
1239        base = None
1240        token_type = TokenType.STRING
1241
1242        if start in self._QUOTES:
1243            end = self._QUOTES[start]
1244        elif start in self._FORMAT_STRINGS:
1245            end, token_type = self._FORMAT_STRINGS[start]
1246
1247            if token_type == TokenType.HEX_STRING:
1248                base = 16
1249            elif token_type == TokenType.BIT_STRING:
1250                base = 2
1251            elif token_type == TokenType.HEREDOC_STRING:
1252                self._advance()
1253                tag = "" if self._char == end else self._extract_string(end)
1254                end = f"{start}{tag}{end}"
1255        else:
1256            return False
1257
1258        self._advance(len(start))
1259        text = self._extract_string(end)
1260
1261        if base:
1262            try:
1263                int(text, base)
1264            except Exception:
1265                raise TokenError(
1266                    f"Numeric string contains invalid characters from {self._line}:{self._start}"
1267                )
1268
1269        self._add(token_type, text)
1270        return True
1271
1272    def _scan_identifier(self, identifier_end: str) -> None:
1273        self._advance()
1274        text = self._extract_string(identifier_end, self._IDENTIFIER_ESCAPES)
1275        self._add(TokenType.IDENTIFIER, text)
1276
1277    def _scan_var(self) -> None:
1278        while True:
1279            char = self._peek.strip()
1280            if char and (char in self.VAR_SINGLE_TOKENS or char not in self.SINGLE_TOKENS):
1281                self._advance(alnum=True)
1282            else:
1283                break
1284
1285        self._add(
1286            TokenType.VAR
1287            if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER
1288            else self.KEYWORDS.get(self._text.upper(), TokenType.VAR)
1289        )
1290
1291    def _extract_string(self, delimiter: str, escapes=None) -> str:
1292        text = ""
1293        delim_size = len(delimiter)
1294        escapes = self._STRING_ESCAPES if escapes is None else escapes
1295
1296        while True:
1297            if (
1298                self._char in escapes
1299                and (self._peek == delimiter or self._peek in escapes)
1300                and (self._char not in self._QUOTES or self._char == self._peek)
1301            ):
1302                if self._peek == delimiter:
1303                    text += self._peek
1304                else:
1305                    text += self._char + self._peek
1306
1307                if self._current + 1 < self.size:
1308                    self._advance(2)
1309                else:
1310                    raise TokenError(f"Missing {delimiter} from {self._line}:{self._current}")
1311            else:
1312                if self._chars(delim_size) == delimiter:
1313                    if delim_size > 1:
1314                        self._advance(delim_size - 1)
1315                    break
1316
1317                if self._end:
1318                    raise TokenError(f"Missing {delimiter} from {self._line}:{self._start}")
1319
1320                if (
1321                    self.dialect.ESCAPE_SEQUENCES
1322                    and self._peek
1323                    and self._char in self.STRING_ESCAPES
1324                ):
1325                    escaped_sequence = self.dialect.ESCAPE_SEQUENCES.get(self._char + self._peek)
1326                    if escaped_sequence:
1327                        self._advance(2)
1328                        text += escaped_sequence
1329                        continue
1330
1331                current = self._current - 1
1332                self._advance(alnum=True)
1333                text += self.sql[current : self._current - 1]
1334
1335        return text
1336
1337    def tokenize_rs(self, sql: str) -> t.List[Token]:
1338        if not self._RS_TOKENIZER:
1339            raise SqlglotError("Rust tokenizer is not available")
1340
1341        try:
1342            tokens = self._RS_TOKENIZER.tokenize(sql, self._rs_dialect_settings)
1343            for token in tokens:
1344                token.token_type = _ALL_TOKEN_TYPES[token.token_type_index]
1345            return tokens
1346        except Exception as e:
1347            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    BPCHAR = auto()
130    TEXT = auto()
131    MEDIUMTEXT = auto()
132    LONGTEXT = auto()
133    MEDIUMBLOB = auto()
134    LONGBLOB = auto()
135    TINYBLOB = auto()
136    TINYTEXT = auto()
137    BINARY = auto()
138    VARBINARY = auto()
139    JSON = auto()
140    JSONB = auto()
141    TIME = auto()
142    TIMETZ = auto()
143    TIMESTAMP = auto()
144    TIMESTAMPTZ = auto()
145    TIMESTAMPLTZ = auto()
146    TIMESTAMP_S = auto()
147    TIMESTAMP_MS = auto()
148    TIMESTAMP_NS = auto()
149    DATETIME = auto()
150    DATETIME64 = auto()
151    DATE = auto()
152    DATE32 = auto()
153    INT4RANGE = auto()
154    INT4MULTIRANGE = auto()
155    INT8RANGE = auto()
156    INT8MULTIRANGE = auto()
157    NUMRANGE = auto()
158    NUMMULTIRANGE = auto()
159    TSRANGE = auto()
160    TSMULTIRANGE = auto()
161    TSTZRANGE = auto()
162    TSTZMULTIRANGE = auto()
163    DATERANGE = auto()
164    DATEMULTIRANGE = auto()
165    UUID = auto()
166    GEOGRAPHY = auto()
167    NULLABLE = auto()
168    GEOMETRY = auto()
169    HLLSKETCH = auto()
170    HSTORE = auto()
171    SUPER = auto()
172    SERIAL = auto()
173    SMALLSERIAL = auto()
174    BIGSERIAL = auto()
175    XML = auto()
176    YEAR = auto()
177    UNIQUEIDENTIFIER = auto()
178    USERDEFINED = auto()
179    MONEY = auto()
180    SMALLMONEY = auto()
181    ROWVERSION = auto()
182    IMAGE = auto()
183    VARIANT = auto()
184    OBJECT = auto()
185    INET = auto()
186    IPADDRESS = auto()
187    IPPREFIX = auto()
188    IPV4 = auto()
189    IPV6 = auto()
190    ENUM = auto()
191    ENUM8 = auto()
192    ENUM16 = auto()
193    FIXEDSTRING = auto()
194    LOWCARDINALITY = auto()
195    NESTED = auto()
196    AGGREGATEFUNCTION = auto()
197    SIMPLEAGGREGATEFUNCTION = auto()
198    UNKNOWN = auto()
199
200    # keywords
201    ALIAS = auto()
202    ALTER = auto()
203    ALWAYS = auto()
204    ALL = auto()
205    ANTI = auto()
206    ANY = auto()
207    APPLY = auto()
208    ARRAY = auto()
209    ASC = auto()
210    ASOF = auto()
211    AUTO_INCREMENT = auto()
212    BEGIN = auto()
213    BETWEEN = auto()
214    CACHE = auto()
215    CASE = auto()
216    CHARACTER_SET = auto()
217    CLUSTER_BY = auto()
218    COLLATE = auto()
219    COMMAND = auto()
220    COMMENT = auto()
221    COMMIT = auto()
222    CONNECT_BY = auto()
223    CONSTRAINT = auto()
224    CREATE = auto()
225    CROSS = auto()
226    CUBE = auto()
227    CURRENT_DATE = auto()
228    CURRENT_DATETIME = auto()
229    CURRENT_TIME = auto()
230    CURRENT_TIMESTAMP = auto()
231    CURRENT_USER = auto()
232    DEFAULT = auto()
233    DELETE = auto()
234    DESC = auto()
235    DESCRIBE = auto()
236    DICTIONARY = auto()
237    DISTINCT = auto()
238    DISTRIBUTE_BY = auto()
239    DIV = auto()
240    DROP = auto()
241    ELSE = auto()
242    END = auto()
243    ESCAPE = auto()
244    EXCEPT = auto()
245    EXECUTE = auto()
246    EXISTS = auto()
247    FALSE = auto()
248    FETCH = auto()
249    FILTER = auto()
250    FINAL = auto()
251    FIRST = auto()
252    FOR = auto()
253    FORCE = auto()
254    FOREIGN_KEY = auto()
255    FORMAT = auto()
256    FROM = auto()
257    FULL = auto()
258    FUNCTION = auto()
259    GLOB = auto()
260    GLOBAL = auto()
261    GROUP_BY = auto()
262    GROUPING_SETS = auto()
263    HAVING = auto()
264    HINT = auto()
265    IGNORE = auto()
266    ILIKE = auto()
267    ILIKE_ANY = auto()
268    IN = auto()
269    INDEX = auto()
270    INNER = auto()
271    INSERT = auto()
272    INTERSECT = auto()
273    INTERVAL = auto()
274    INTO = auto()
275    INTRODUCER = auto()
276    IRLIKE = auto()
277    IS = auto()
278    ISNULL = auto()
279    JOIN = auto()
280    JOIN_MARKER = auto()
281    KEEP = auto()
282    KILL = auto()
283    LANGUAGE = auto()
284    LATERAL = auto()
285    LEFT = auto()
286    LIKE = auto()
287    LIKE_ANY = auto()
288    LIMIT = auto()
289    LOAD = auto()
290    LOCK = auto()
291    MAP = auto()
292    MATCH_RECOGNIZE = auto()
293    MEMBER_OF = auto()
294    MERGE = auto()
295    MOD = auto()
296    MODEL = auto()
297    NATURAL = auto()
298    NEXT = auto()
299    NOTNULL = auto()
300    NULL = auto()
301    OBJECT_IDENTIFIER = auto()
302    OFFSET = auto()
303    ON = auto()
304    OPERATOR = auto()
305    ORDER_BY = auto()
306    ORDER_SIBLINGS_BY = auto()
307    ORDERED = auto()
308    ORDINALITY = auto()
309    OUTER = auto()
310    OVER = auto()
311    OVERLAPS = auto()
312    OVERWRITE = auto()
313    PARTITION = auto()
314    PARTITION_BY = auto()
315    PERCENT = auto()
316    PIVOT = auto()
317    PLACEHOLDER = auto()
318    PRAGMA = auto()
319    PRIMARY_KEY = auto()
320    PROCEDURE = auto()
321    PROPERTIES = auto()
322    PSEUDO_TYPE = auto()
323    QUALIFY = auto()
324    QUOTE = auto()
325    RANGE = auto()
326    RECURSIVE = auto()
327    REFRESH = auto()
328    REPLACE = auto()
329    RETURNING = auto()
330    REFERENCES = auto()
331    RIGHT = auto()
332    RLIKE = auto()
333    ROLLBACK = auto()
334    ROLLUP = auto()
335    ROW = auto()
336    ROWS = auto()
337    SELECT = auto()
338    SEMI = auto()
339    SEPARATOR = auto()
340    SERDE_PROPERTIES = auto()
341    SET = auto()
342    SETTINGS = auto()
343    SHOW = auto()
344    SIMILAR_TO = auto()
345    SOME = auto()
346    SORT_BY = auto()
347    START_WITH = auto()
348    STRUCT = auto()
349    TABLE_SAMPLE = auto()
350    TEMPORARY = auto()
351    TOP = auto()
352    THEN = auto()
353    TRUE = auto()
354    UNCACHE = auto()
355    UNION = auto()
356    UNNEST = auto()
357    UNPIVOT = auto()
358    UPDATE = auto()
359    USE = auto()
360    USING = auto()
361    VALUES = auto()
362    VIEW = auto()
363    VOLATILE = auto()
364    WHEN = auto()
365    WHERE = auto()
366    WINDOW = auto()
367    WITH = auto()
368    UNIQUE = auto()
369    VERSION_SNAPSHOT = auto()
370    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'>
BPCHAR = <TokenType.BPCHAR: 'BPCHAR'>
TEXT = <TokenType.TEXT: 'TEXT'>
MEDIUMTEXT = <TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>
LONGTEXT = <TokenType.LONGTEXT: 'LONGTEXT'>
MEDIUMBLOB = <TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>
LONGBLOB = <TokenType.LONGBLOB: 'LONGBLOB'>
TINYBLOB = <TokenType.TINYBLOB: 'TINYBLOB'>
TINYTEXT = <TokenType.TINYTEXT: 'TINYTEXT'>
BINARY = <TokenType.BINARY: 'BINARY'>
VARBINARY = <TokenType.VARBINARY: 'VARBINARY'>
JSON = <TokenType.JSON: 'JSON'>
JSONB = <TokenType.JSONB: 'JSONB'>
TIME = <TokenType.TIME: 'TIME'>
TIMETZ = <TokenType.TIMETZ: 'TIMETZ'>
TIMESTAMP = <TokenType.TIMESTAMP: 'TIMESTAMP'>
TIMESTAMPTZ = <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>
TIMESTAMPLTZ = <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>
TIMESTAMP_S = <TokenType.TIMESTAMP_S: 'TIMESTAMP_S'>
TIMESTAMP_MS = <TokenType.TIMESTAMP_MS: 'TIMESTAMP_MS'>
TIMESTAMP_NS = <TokenType.TIMESTAMP_NS: 'TIMESTAMP_NS'>
DATETIME = <TokenType.DATETIME: 'DATETIME'>
DATETIME64 = <TokenType.DATETIME64: 'DATETIME64'>
DATE = <TokenType.DATE: 'DATE'>
DATE32 = <TokenType.DATE32: 'DATE32'>
INT4RANGE = <TokenType.INT4RANGE: 'INT4RANGE'>
INT4MULTIRANGE = <TokenType.INT4MULTIRANGE: 'INT4MULTIRANGE'>
INT8RANGE = <TokenType.INT8RANGE: 'INT8RANGE'>
INT8MULTIRANGE = <TokenType.INT8MULTIRANGE: 'INT8MULTIRANGE'>
NUMRANGE = <TokenType.NUMRANGE: 'NUMRANGE'>
NUMMULTIRANGE = <TokenType.NUMMULTIRANGE: 'NUMMULTIRANGE'>
TSRANGE = <TokenType.TSRANGE: 'TSRANGE'>
TSMULTIRANGE = <TokenType.TSMULTIRANGE: 'TSMULTIRANGE'>
TSTZRANGE = <TokenType.TSTZRANGE: 'TSTZRANGE'>
TSTZMULTIRANGE = <TokenType.TSTZMULTIRANGE: 'TSTZMULTIRANGE'>
DATERANGE = <TokenType.DATERANGE: 'DATERANGE'>
DATEMULTIRANGE = <TokenType.DATEMULTIRANGE: 'DATEMULTIRANGE'>
UUID = <TokenType.UUID: 'UUID'>
GEOGRAPHY = <TokenType.GEOGRAPHY: 'GEOGRAPHY'>
NULLABLE = <TokenType.NULLABLE: 'NULLABLE'>
GEOMETRY = <TokenType.GEOMETRY: 'GEOMETRY'>
HLLSKETCH = <TokenType.HLLSKETCH: 'HLLSKETCH'>
HSTORE = <TokenType.HSTORE: 'HSTORE'>
SUPER = <TokenType.SUPER: 'SUPER'>
SERIAL = <TokenType.SERIAL: 'SERIAL'>
SMALLSERIAL = <TokenType.SMALLSERIAL: 'SMALLSERIAL'>
BIGSERIAL = <TokenType.BIGSERIAL: 'BIGSERIAL'>
XML = <TokenType.XML: 'XML'>
YEAR = <TokenType.YEAR: 'YEAR'>
UNIQUEIDENTIFIER = <TokenType.UNIQUEIDENTIFIER: 'UNIQUEIDENTIFIER'>
USERDEFINED = <TokenType.USERDEFINED: 'USERDEFINED'>
MONEY = <TokenType.MONEY: 'MONEY'>
SMALLMONEY = <TokenType.SMALLMONEY: 'SMALLMONEY'>
ROWVERSION = <TokenType.ROWVERSION: 'ROWVERSION'>
IMAGE = <TokenType.IMAGE: 'IMAGE'>
VARIANT = <TokenType.VARIANT: 'VARIANT'>
OBJECT = <TokenType.OBJECT: 'OBJECT'>
INET = <TokenType.INET: 'INET'>
IPADDRESS = <TokenType.IPADDRESS: 'IPADDRESS'>
IPPREFIX = <TokenType.IPPREFIX: 'IPPREFIX'>
IPV4 = <TokenType.IPV4: 'IPV4'>
IPV6 = <TokenType.IPV6: 'IPV6'>
ENUM = <TokenType.ENUM: 'ENUM'>
ENUM8 = <TokenType.ENUM8: 'ENUM8'>
ENUM16 = <TokenType.ENUM16: 'ENUM16'>
FIXEDSTRING = <TokenType.FIXEDSTRING: 'FIXEDSTRING'>
LOWCARDINALITY = <TokenType.LOWCARDINALITY: 'LOWCARDINALITY'>
NESTED = <TokenType.NESTED: 'NESTED'>
AGGREGATEFUNCTION = <TokenType.AGGREGATEFUNCTION: 'AGGREGATEFUNCTION'>
SIMPLEAGGREGATEFUNCTION = <TokenType.SIMPLEAGGREGATEFUNCTION: 'SIMPLEAGGREGATEFUNCTION'>
UNKNOWN = <TokenType.UNKNOWN: 'UNKNOWN'>
ALIAS = <TokenType.ALIAS: 'ALIAS'>
ALTER = <TokenType.ALTER: 'ALTER'>
ALWAYS = <TokenType.ALWAYS: 'ALWAYS'>
ALL = <TokenType.ALL: 'ALL'>
ANTI = <TokenType.ANTI: 'ANTI'>
ANY = <TokenType.ANY: 'ANY'>
APPLY = <TokenType.APPLY: 'APPLY'>
ARRAY = <TokenType.ARRAY: 'ARRAY'>
ASC = <TokenType.ASC: 'ASC'>
ASOF = <TokenType.ASOF: 'ASOF'>
AUTO_INCREMENT = <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>
BEGIN = <TokenType.BEGIN: 'BEGIN'>
BETWEEN = <TokenType.BETWEEN: 'BETWEEN'>
CACHE = <TokenType.CACHE: 'CACHE'>
CASE = <TokenType.CASE: 'CASE'>
CHARACTER_SET = <TokenType.CHARACTER_SET: 'CHARACTER_SET'>
CLUSTER_BY = <TokenType.CLUSTER_BY: 'CLUSTER_BY'>
COLLATE = <TokenType.COLLATE: 'COLLATE'>
COMMAND = <TokenType.COMMAND: 'COMMAND'>
COMMENT = <TokenType.COMMENT: 'COMMENT'>
COMMIT = <TokenType.COMMIT: 'COMMIT'>
CONNECT_BY = <TokenType.CONNECT_BY: 'CONNECT_BY'>
CONSTRAINT = <TokenType.CONSTRAINT: 'CONSTRAINT'>
CREATE = <TokenType.CREATE: 'CREATE'>
CROSS = <TokenType.CROSS: 'CROSS'>
CUBE = <TokenType.CUBE: 'CUBE'>
CURRENT_DATE = <TokenType.CURRENT_DATE: 'CURRENT_DATE'>
CURRENT_DATETIME = <TokenType.CURRENT_DATETIME: 'CURRENT_DATETIME'>
CURRENT_TIME = <TokenType.CURRENT_TIME: 'CURRENT_TIME'>
CURRENT_TIMESTAMP = <TokenType.CURRENT_TIMESTAMP: 'CURRENT_TIMESTAMP'>
CURRENT_USER = <TokenType.CURRENT_USER: 'CURRENT_USER'>
DEFAULT = <TokenType.DEFAULT: 'DEFAULT'>
DELETE = <TokenType.DELETE: 'DELETE'>
DESC = <TokenType.DESC: 'DESC'>
DESCRIBE = <TokenType.DESCRIBE: 'DESCRIBE'>
DICTIONARY = <TokenType.DICTIONARY: 'DICTIONARY'>
DISTINCT = <TokenType.DISTINCT: 'DISTINCT'>
DISTRIBUTE_BY = <TokenType.DISTRIBUTE_BY: 'DISTRIBUTE_BY'>
DIV = <TokenType.DIV: 'DIV'>
DROP = <TokenType.DROP: 'DROP'>
ELSE = <TokenType.ELSE: 'ELSE'>
END = <TokenType.END: 'END'>
ESCAPE = <TokenType.ESCAPE: 'ESCAPE'>
EXCEPT = <TokenType.EXCEPT: 'EXCEPT'>
EXECUTE = <TokenType.EXECUTE: 'EXECUTE'>
EXISTS = <TokenType.EXISTS: 'EXISTS'>
FALSE = <TokenType.FALSE: 'FALSE'>
FETCH = <TokenType.FETCH: 'FETCH'>
FILTER = <TokenType.FILTER: 'FILTER'>
FINAL = <TokenType.FINAL: 'FINAL'>
FIRST = <TokenType.FIRST: 'FIRST'>
FOR = <TokenType.FOR: 'FOR'>
FORCE = <TokenType.FORCE: 'FORCE'>
FOREIGN_KEY = <TokenType.FOREIGN_KEY: 'FOREIGN_KEY'>
FORMAT = <TokenType.FORMAT: 'FORMAT'>
FROM = <TokenType.FROM: 'FROM'>
FULL = <TokenType.FULL: 'FULL'>
FUNCTION = <TokenType.FUNCTION: 'FUNCTION'>
GLOB = <TokenType.GLOB: 'GLOB'>
GLOBAL = <TokenType.GLOBAL: 'GLOBAL'>
GROUP_BY = <TokenType.GROUP_BY: 'GROUP_BY'>
GROUPING_SETS = <TokenType.GROUPING_SETS: 'GROUPING_SETS'>
HAVING = <TokenType.HAVING: 'HAVING'>
HINT = <TokenType.HINT: 'HINT'>
IGNORE = <TokenType.IGNORE: 'IGNORE'>
ILIKE = <TokenType.ILIKE: 'ILIKE'>
ILIKE_ANY = <TokenType.ILIKE_ANY: 'ILIKE_ANY'>
IN = <TokenType.IN: 'IN'>
INDEX = <TokenType.INDEX: 'INDEX'>
INNER = <TokenType.INNER: 'INNER'>
INSERT = <TokenType.INSERT: 'INSERT'>
INTERSECT = <TokenType.INTERSECT: 'INTERSECT'>
INTERVAL = <TokenType.INTERVAL: 'INTERVAL'>
INTO = <TokenType.INTO: 'INTO'>
INTRODUCER = <TokenType.INTRODUCER: 'INTRODUCER'>
IRLIKE = <TokenType.IRLIKE: 'IRLIKE'>
IS = <TokenType.IS: 'IS'>
ISNULL = <TokenType.ISNULL: 'ISNULL'>
JOIN = <TokenType.JOIN: 'JOIN'>
JOIN_MARKER = <TokenType.JOIN_MARKER: 'JOIN_MARKER'>
KEEP = <TokenType.KEEP: 'KEEP'>
KILL = <TokenType.KILL: 'KILL'>
LANGUAGE = <TokenType.LANGUAGE: 'LANGUAGE'>
LATERAL = <TokenType.LATERAL: 'LATERAL'>
LEFT = <TokenType.LEFT: 'LEFT'>
LIKE = <TokenType.LIKE: 'LIKE'>
LIKE_ANY = <TokenType.LIKE_ANY: 'LIKE_ANY'>
LIMIT = <TokenType.LIMIT: 'LIMIT'>
LOAD = <TokenType.LOAD: 'LOAD'>
LOCK = <TokenType.LOCK: 'LOCK'>
MAP = <TokenType.MAP: 'MAP'>
MATCH_RECOGNIZE = <TokenType.MATCH_RECOGNIZE: 'MATCH_RECOGNIZE'>
MEMBER_OF = <TokenType.MEMBER_OF: 'MEMBER_OF'>
MERGE = <TokenType.MERGE: 'MERGE'>
MOD = <TokenType.MOD: 'MOD'>
MODEL = <TokenType.MODEL: 'MODEL'>
NATURAL = <TokenType.NATURAL: 'NATURAL'>
NEXT = <TokenType.NEXT: 'NEXT'>
NOTNULL = <TokenType.NOTNULL: 'NOTNULL'>
NULL = <TokenType.NULL: 'NULL'>
OBJECT_IDENTIFIER = <TokenType.OBJECT_IDENTIFIER: 'OBJECT_IDENTIFIER'>
OFFSET = <TokenType.OFFSET: 'OFFSET'>
ON = <TokenType.ON: 'ON'>
OPERATOR = <TokenType.OPERATOR: 'OPERATOR'>
ORDER_BY = <TokenType.ORDER_BY: 'ORDER_BY'>
ORDER_SIBLINGS_BY = <TokenType.ORDER_SIBLINGS_BY: 'ORDER_SIBLINGS_BY'>
ORDERED = <TokenType.ORDERED: 'ORDERED'>
ORDINALITY = <TokenType.ORDINALITY: 'ORDINALITY'>
OUTER = <TokenType.OUTER: 'OUTER'>
OVER = <TokenType.OVER: 'OVER'>
OVERLAPS = <TokenType.OVERLAPS: 'OVERLAPS'>
OVERWRITE = <TokenType.OVERWRITE: 'OVERWRITE'>
PARTITION = <TokenType.PARTITION: 'PARTITION'>
PARTITION_BY = <TokenType.PARTITION_BY: 'PARTITION_BY'>
PERCENT = <TokenType.PERCENT: 'PERCENT'>
PIVOT = <TokenType.PIVOT: 'PIVOT'>
PLACEHOLDER = <TokenType.PLACEHOLDER: 'PLACEHOLDER'>
PRAGMA = <TokenType.PRAGMA: 'PRAGMA'>
PRIMARY_KEY = <TokenType.PRIMARY_KEY: 'PRIMARY_KEY'>
PROCEDURE = <TokenType.PROCEDURE: 'PROCEDURE'>
PROPERTIES = <TokenType.PROPERTIES: 'PROPERTIES'>
PSEUDO_TYPE = <TokenType.PSEUDO_TYPE: 'PSEUDO_TYPE'>
QUALIFY = <TokenType.QUALIFY: 'QUALIFY'>
QUOTE = <TokenType.QUOTE: 'QUOTE'>
RANGE = <TokenType.RANGE: 'RANGE'>
RECURSIVE = <TokenType.RECURSIVE: 'RECURSIVE'>
REFRESH = <TokenType.REFRESH: 'REFRESH'>
REPLACE = <TokenType.REPLACE: 'REPLACE'>
RETURNING = <TokenType.RETURNING: 'RETURNING'>
REFERENCES = <TokenType.REFERENCES: 'REFERENCES'>
RIGHT = <TokenType.RIGHT: 'RIGHT'>
RLIKE = <TokenType.RLIKE: 'RLIKE'>
ROLLBACK = <TokenType.ROLLBACK: 'ROLLBACK'>
ROLLUP = <TokenType.ROLLUP: 'ROLLUP'>
ROW = <TokenType.ROW: 'ROW'>
ROWS = <TokenType.ROWS: 'ROWS'>
SELECT = <TokenType.SELECT: 'SELECT'>
SEMI = <TokenType.SEMI: 'SEMI'>
SEPARATOR = <TokenType.SEPARATOR: 'SEPARATOR'>
SERDE_PROPERTIES = <TokenType.SERDE_PROPERTIES: 'SERDE_PROPERTIES'>
SET = <TokenType.SET: 'SET'>
SETTINGS = <TokenType.SETTINGS: 'SETTINGS'>
SHOW = <TokenType.SHOW: 'SHOW'>
SIMILAR_TO = <TokenType.SIMILAR_TO: 'SIMILAR_TO'>
SOME = <TokenType.SOME: 'SOME'>
SORT_BY = <TokenType.SORT_BY: 'SORT_BY'>
START_WITH = <TokenType.START_WITH: 'START_WITH'>
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:
377class Token:
378    __slots__ = ("token_type", "text", "line", "col", "start", "end", "comments")
379
380    @classmethod
381    def number(cls, number: int) -> Token:
382        """Returns a NUMBER token with `number` as its text."""
383        return cls(TokenType.NUMBER, str(number))
384
385    @classmethod
386    def string(cls, string: str) -> Token:
387        """Returns a STRING token with `string` as its text."""
388        return cls(TokenType.STRING, string)
389
390    @classmethod
391    def identifier(cls, identifier: str) -> Token:
392        """Returns an IDENTIFIER token with `identifier` as its text."""
393        return cls(TokenType.IDENTIFIER, identifier)
394
395    @classmethod
396    def var(cls, var: str) -> Token:
397        """Returns an VAR token with `var` as its text."""
398        return cls(TokenType.VAR, var)
399
400    def __init__(
401        self,
402        token_type: TokenType,
403        text: str,
404        line: int = 1,
405        col: int = 1,
406        start: int = 0,
407        end: int = 0,
408        comments: t.Optional[t.List[str]] = None,
409    ) -> None:
410        """Token initializer.
411
412        Args:
413            token_type: The TokenType Enum.
414            text: The text of the token.
415            line: The line that the token ends on.
416            col: The column that the token ends on.
417            start: The start index of the token.
418            end: The ending index of the token.
419            comments: The comments to attach to the token.
420        """
421        self.token_type = token_type
422        self.text = text
423        self.line = line
424        self.col = col
425        self.start = start
426        self.end = end
427        self.comments = [] if comments is None else comments
428
429    def __repr__(self) -> str:
430        attributes = ", ".join(f"{k}: {getattr(self, k)}" for k in self.__slots__)
431        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)
400    def __init__(
401        self,
402        token_type: TokenType,
403        text: str,
404        line: int = 1,
405        col: int = 1,
406        start: int = 0,
407        end: int = 0,
408        comments: t.Optional[t.List[str]] = None,
409    ) -> None:
410        """Token initializer.
411
412        Args:
413            token_type: The TokenType Enum.
414            text: The text of the token.
415            line: The line that the token ends on.
416            col: The column that the token ends on.
417            start: The start index of the token.
418            end: The ending index of the token.
419            comments: The comments to attach to the token.
420        """
421        self.token_type = token_type
422        self.text = text
423        self.line = line
424        self.col = col
425        self.start = start
426        self.end = end
427        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:
380    @classmethod
381    def number(cls, number: int) -> Token:
382        """Returns a NUMBER token with `number` as its text."""
383        return cls(TokenType.NUMBER, str(number))

Returns a NUMBER token with number as its text.

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

Returns a STRING token with string as its text.

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

Returns an IDENTIFIER token with identifier as its text.

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

Returns an VAR token with var as its text.

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

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

def peek(self, i: int = 0) -> str:
1029    def peek(self, i: int = 0) -> str:
1030        i = self._current + i
1031        if i < self.size:
1032            return self.sql[i]
1033        return ""
def tokenize_rs(self, sql: str) -> List[Token]:
1338    def tokenize_rs(self, sql: str) -> t.List[Token]:
1339        if not self._RS_TOKENIZER:
1340            raise SqlglotError("Rust tokenizer is not available")
1341
1342        try:
1343            tokens = self._RS_TOKENIZER.tokenize(sql, self._rs_dialect_settings)
1344            for token in tokens:
1345                token.token_type = _ALL_TOKEN_TYPES[token.token_type_index]
1346            return tokens
1347        except Exception as e:
1348            raise TokenError(str(e))
size
sql
tokens