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    DOTCOLON = auto()
  41    DCOLON = auto()
  42    DCOLONDOLLAR = auto()
  43    DCOLONPERCENT = auto()
  44    DQMARK = auto()
  45    SEMICOLON = auto()
  46    STAR = auto()
  47    BACKSLASH = auto()
  48    SLASH = auto()
  49    LT = auto()
  50    LTE = auto()
  51    GT = auto()
  52    GTE = auto()
  53    NOT = auto()
  54    EQ = auto()
  55    NEQ = auto()
  56    NULLSAFE_EQ = auto()
  57    COLON_EQ = auto()
  58    COLON_GT = auto()
  59    NCOLON_GT = auto()
  60    AND = auto()
  61    OR = auto()
  62    AMP = auto()
  63    DPIPE = auto()
  64    PIPE_GT = auto()
  65    PIPE = auto()
  66    PIPE_SLASH = auto()
  67    DPIPE_SLASH = auto()
  68    CARET = auto()
  69    CARET_AT = auto()
  70    TILDA = auto()
  71    ARROW = auto()
  72    DARROW = auto()
  73    FARROW = auto()
  74    HASH = auto()
  75    HASH_ARROW = auto()
  76    DHASH_ARROW = auto()
  77    LR_ARROW = auto()
  78    DAT = auto()
  79    LT_AT = auto()
  80    AT_GT = auto()
  81    DOLLAR = auto()
  82    PARAMETER = auto()
  83    SESSION_PARAMETER = auto()
  84    DAMP = auto()
  85    XOR = auto()
  86    DSTAR = auto()
  87
  88    URI_START = auto()
  89
  90    BLOCK_START = auto()
  91    BLOCK_END = auto()
  92
  93    SPACE = auto()
  94    BREAK = auto()
  95
  96    STRING = auto()
  97    NUMBER = auto()
  98    IDENTIFIER = auto()
  99    DATABASE = auto()
 100    COLUMN = auto()
 101    COLUMN_DEF = auto()
 102    SCHEMA = auto()
 103    TABLE = auto()
 104    WAREHOUSE = auto()
 105    STAGE = auto()
 106    STREAMLIT = auto()
 107    VAR = auto()
 108    BIT_STRING = auto()
 109    HEX_STRING = auto()
 110    BYTE_STRING = auto()
 111    NATIONAL_STRING = auto()
 112    RAW_STRING = auto()
 113    HEREDOC_STRING = auto()
 114    UNICODE_STRING = auto()
 115
 116    # types
 117    BIT = auto()
 118    BOOLEAN = auto()
 119    TINYINT = auto()
 120    UTINYINT = auto()
 121    SMALLINT = auto()
 122    USMALLINT = auto()
 123    MEDIUMINT = auto()
 124    UMEDIUMINT = auto()
 125    INT = auto()
 126    UINT = auto()
 127    BIGINT = auto()
 128    UBIGINT = auto()
 129    INT128 = auto()
 130    UINT128 = auto()
 131    INT256 = auto()
 132    UINT256 = auto()
 133    FLOAT = auto()
 134    DOUBLE = auto()
 135    UDOUBLE = auto()
 136    DECIMAL = auto()
 137    DECIMAL32 = auto()
 138    DECIMAL64 = auto()
 139    DECIMAL128 = auto()
 140    DECIMAL256 = auto()
 141    UDECIMAL = auto()
 142    BIGDECIMAL = auto()
 143    CHAR = auto()
 144    NCHAR = auto()
 145    VARCHAR = auto()
 146    NVARCHAR = auto()
 147    BPCHAR = auto()
 148    TEXT = auto()
 149    MEDIUMTEXT = auto()
 150    LONGTEXT = auto()
 151    BLOB = auto()
 152    MEDIUMBLOB = auto()
 153    LONGBLOB = auto()
 154    TINYBLOB = auto()
 155    TINYTEXT = auto()
 156    NAME = auto()
 157    BINARY = auto()
 158    VARBINARY = auto()
 159    JSON = auto()
 160    JSONB = auto()
 161    TIME = auto()
 162    TIMETZ = auto()
 163    TIMESTAMP = auto()
 164    TIMESTAMPTZ = auto()
 165    TIMESTAMPLTZ = auto()
 166    TIMESTAMPNTZ = auto()
 167    TIMESTAMP_S = auto()
 168    TIMESTAMP_MS = auto()
 169    TIMESTAMP_NS = auto()
 170    DATETIME = auto()
 171    DATETIME2 = auto()
 172    DATETIME64 = auto()
 173    SMALLDATETIME = auto()
 174    DATE = auto()
 175    DATE32 = auto()
 176    INT4RANGE = auto()
 177    INT4MULTIRANGE = auto()
 178    INT8RANGE = auto()
 179    INT8MULTIRANGE = auto()
 180    NUMRANGE = auto()
 181    NUMMULTIRANGE = auto()
 182    TSRANGE = auto()
 183    TSMULTIRANGE = auto()
 184    TSTZRANGE = auto()
 185    TSTZMULTIRANGE = auto()
 186    DATERANGE = auto()
 187    DATEMULTIRANGE = auto()
 188    UUID = auto()
 189    GEOGRAPHY = auto()
 190    GEOGRAPHYPOINT = auto()
 191    NULLABLE = auto()
 192    GEOMETRY = auto()
 193    POINT = auto()
 194    RING = auto()
 195    LINESTRING = auto()
 196    MULTILINESTRING = auto()
 197    POLYGON = auto()
 198    MULTIPOLYGON = auto()
 199    HLLSKETCH = auto()
 200    HSTORE = auto()
 201    SUPER = auto()
 202    SERIAL = auto()
 203    SMALLSERIAL = auto()
 204    BIGSERIAL = auto()
 205    XML = auto()
 206    YEAR = auto()
 207    USERDEFINED = auto()
 208    MONEY = auto()
 209    SMALLMONEY = auto()
 210    ROWVERSION = auto()
 211    IMAGE = auto()
 212    VARIANT = auto()
 213    OBJECT = auto()
 214    INET = auto()
 215    IPADDRESS = auto()
 216    IPPREFIX = auto()
 217    IPV4 = auto()
 218    IPV6 = auto()
 219    ENUM = auto()
 220    ENUM8 = auto()
 221    ENUM16 = auto()
 222    FIXEDSTRING = auto()
 223    LOWCARDINALITY = auto()
 224    NESTED = auto()
 225    AGGREGATEFUNCTION = auto()
 226    SIMPLEAGGREGATEFUNCTION = auto()
 227    TDIGEST = auto()
 228    UNKNOWN = auto()
 229    VECTOR = auto()
 230    DYNAMIC = auto()
 231    VOID = auto()
 232
 233    # keywords
 234    ALIAS = auto()
 235    ALTER = auto()
 236    ALWAYS = auto()
 237    ALL = auto()
 238    ANTI = auto()
 239    ANY = auto()
 240    APPLY = auto()
 241    ARRAY = auto()
 242    ASC = auto()
 243    ASOF = auto()
 244    ATTACH = auto()
 245    AUTO_INCREMENT = auto()
 246    BEGIN = auto()
 247    BETWEEN = auto()
 248    BULK_COLLECT_INTO = auto()
 249    CACHE = auto()
 250    CASE = auto()
 251    CHARACTER_SET = auto()
 252    CLUSTER_BY = auto()
 253    COLLATE = auto()
 254    COMMAND = auto()
 255    COMMENT = auto()
 256    COMMIT = auto()
 257    CONNECT_BY = auto()
 258    CONSTRAINT = auto()
 259    COPY = auto()
 260    CREATE = auto()
 261    CROSS = auto()
 262    CUBE = auto()
 263    CURRENT_DATE = auto()
 264    CURRENT_DATETIME = auto()
 265    CURRENT_SCHEMA = auto()
 266    CURRENT_TIME = auto()
 267    CURRENT_TIMESTAMP = auto()
 268    CURRENT_USER = auto()
 269    DECLARE = auto()
 270    DEFAULT = auto()
 271    DELETE = auto()
 272    DESC = auto()
 273    DESCRIBE = auto()
 274    DETACH = auto()
 275    DICTIONARY = auto()
 276    DISTINCT = auto()
 277    DISTRIBUTE_BY = auto()
 278    DIV = auto()
 279    DROP = auto()
 280    ELSE = auto()
 281    END = auto()
 282    ESCAPE = auto()
 283    EXCEPT = auto()
 284    EXECUTE = auto()
 285    EXISTS = auto()
 286    FALSE = auto()
 287    FETCH = auto()
 288    FILE_FORMAT = auto()
 289    FILTER = auto()
 290    FINAL = auto()
 291    FIRST = auto()
 292    FOR = auto()
 293    FORCE = auto()
 294    FOREIGN_KEY = auto()
 295    FORMAT = auto()
 296    FROM = auto()
 297    FULL = auto()
 298    FUNCTION = auto()
 299    GET = auto()
 300    GLOB = auto()
 301    GLOBAL = auto()
 302    GRANT = auto()
 303    GROUP_BY = auto()
 304    GROUPING_SETS = auto()
 305    HAVING = auto()
 306    HINT = auto()
 307    IGNORE = auto()
 308    ILIKE = auto()
 309    IN = auto()
 310    INDEX = auto()
 311    INNER = auto()
 312    INSERT = auto()
 313    INTERSECT = auto()
 314    INTERVAL = auto()
 315    INTO = auto()
 316    INTRODUCER = auto()
 317    IRLIKE = auto()
 318    IS = auto()
 319    ISNULL = auto()
 320    JOIN = auto()
 321    JOIN_MARKER = auto()
 322    KEEP = auto()
 323    KEY = auto()
 324    KILL = auto()
 325    LANGUAGE = auto()
 326    LATERAL = auto()
 327    LEFT = auto()
 328    LIKE = auto()
 329    LIMIT = auto()
 330    LIST = auto()
 331    LOAD = auto()
 332    LOCK = auto()
 333    MAP = auto()
 334    MATCH_CONDITION = auto()
 335    MATCH_RECOGNIZE = auto()
 336    MEMBER_OF = auto()
 337    MERGE = auto()
 338    MOD = auto()
 339    MODEL = auto()
 340    NATURAL = auto()
 341    NEXT = auto()
 342    NOTHING = auto()
 343    NOTNULL = auto()
 344    NULL = auto()
 345    OBJECT_IDENTIFIER = auto()
 346    OFFSET = auto()
 347    ON = auto()
 348    ONLY = auto()
 349    OPERATOR = auto()
 350    ORDER_BY = auto()
 351    ORDER_SIBLINGS_BY = auto()
 352    ORDERED = auto()
 353    ORDINALITY = auto()
 354    OUTER = auto()
 355    OVER = auto()
 356    OVERLAPS = auto()
 357    OVERWRITE = auto()
 358    PARTITION = auto()
 359    PARTITION_BY = auto()
 360    PERCENT = auto()
 361    PIVOT = auto()
 362    PLACEHOLDER = auto()
 363    POSITIONAL = auto()
 364    PRAGMA = auto()
 365    PREWHERE = auto()
 366    PRIMARY_KEY = auto()
 367    PROCEDURE = auto()
 368    PROPERTIES = auto()
 369    PSEUDO_TYPE = auto()
 370    PUT = auto()
 371    QUALIFY = auto()
 372    QUOTE = auto()
 373    RANGE = auto()
 374    RECURSIVE = auto()
 375    REFRESH = auto()
 376    RENAME = auto()
 377    REPLACE = auto()
 378    RETURNING = auto()
 379    REVOKE = auto()
 380    REFERENCES = auto()
 381    RIGHT = auto()
 382    RLIKE = auto()
 383    ROLLBACK = auto()
 384    ROLLUP = auto()
 385    ROW = auto()
 386    ROWS = auto()
 387    SELECT = auto()
 388    SEMI = auto()
 389    SEPARATOR = auto()
 390    SEQUENCE = auto()
 391    SERDE_PROPERTIES = auto()
 392    SET = auto()
 393    SETTINGS = auto()
 394    SHOW = auto()
 395    SIMILAR_TO = auto()
 396    SOME = auto()
 397    SORT_BY = auto()
 398    START_WITH = auto()
 399    STORAGE_INTEGRATION = auto()
 400    STRAIGHT_JOIN = auto()
 401    STRUCT = auto()
 402    SUMMARIZE = auto()
 403    TABLE_SAMPLE = auto()
 404    TAG = auto()
 405    TEMPORARY = auto()
 406    TOP = auto()
 407    THEN = auto()
 408    TRUE = auto()
 409    TRUNCATE = auto()
 410    UNCACHE = auto()
 411    UNION = auto()
 412    UNNEST = auto()
 413    UNPIVOT = auto()
 414    UPDATE = auto()
 415    USE = auto()
 416    USING = auto()
 417    VALUES = auto()
 418    VIEW = auto()
 419    SEMANTIC_VIEW = auto()
 420    VOLATILE = auto()
 421    WHEN = auto()
 422    WHERE = auto()
 423    WINDOW = auto()
 424    WITH = auto()
 425    UNIQUE = auto()
 426    VERSION_SNAPSHOT = auto()
 427    TIMESTAMP_SNAPSHOT = auto()
 428    OPTION = auto()
 429    SINK = auto()
 430    SOURCE = auto()
 431    ANALYZE = auto()
 432    NAMESPACE = auto()
 433    EXPORT = auto()
 434
 435    # sentinel
 436    HIVE_TOKEN_STREAM = auto()
 437
 438
 439_ALL_TOKEN_TYPES = list(TokenType)
 440_TOKEN_TYPE_TO_INDEX = {token_type: i for i, token_type in enumerate(_ALL_TOKEN_TYPES)}
 441
 442
 443class Token:
 444    __slots__ = ("token_type", "text", "line", "col", "start", "end", "comments")
 445
 446    @classmethod
 447    def number(cls, number: int) -> Token:
 448        """Returns a NUMBER token with `number` as its text."""
 449        return cls(TokenType.NUMBER, str(number))
 450
 451    @classmethod
 452    def string(cls, string: str) -> Token:
 453        """Returns a STRING token with `string` as its text."""
 454        return cls(TokenType.STRING, string)
 455
 456    @classmethod
 457    def identifier(cls, identifier: str) -> Token:
 458        """Returns an IDENTIFIER token with `identifier` as its text."""
 459        return cls(TokenType.IDENTIFIER, identifier)
 460
 461    @classmethod
 462    def var(cls, var: str) -> Token:
 463        """Returns an VAR token with `var` as its text."""
 464        return cls(TokenType.VAR, var)
 465
 466    def __init__(
 467        self,
 468        token_type: TokenType,
 469        text: str,
 470        line: int = 1,
 471        col: int = 1,
 472        start: int = 0,
 473        end: int = 0,
 474        comments: t.Optional[t.List[str]] = None,
 475    ) -> None:
 476        """Token initializer.
 477
 478        Args:
 479            token_type: The TokenType Enum.
 480            text: The text of the token.
 481            line: The line that the token ends on.
 482            col: The column that the token ends on.
 483            start: The start index of the token.
 484            end: The ending index of the token.
 485            comments: The comments to attach to the token.
 486        """
 487        self.token_type = token_type
 488        self.text = text
 489        self.line = line
 490        self.col = col
 491        self.start = start
 492        self.end = end
 493        self.comments = [] if comments is None else comments
 494
 495    def __repr__(self) -> str:
 496        attributes = ", ".join(f"{k}: {getattr(self, k)}" for k in self.__slots__)
 497        return f"<Token {attributes}>"
 498
 499
 500class _Tokenizer(type):
 501    def __new__(cls, clsname, bases, attrs):
 502        klass = super().__new__(cls, clsname, bases, attrs)
 503
 504        def _convert_quotes(arr: t.List[str | t.Tuple[str, str]]) -> t.Dict[str, str]:
 505            return dict(
 506                (item, item) if isinstance(item, str) else (item[0], item[1]) for item in arr
 507            )
 508
 509        def _quotes_to_format(
 510            token_type: TokenType, arr: t.List[str | t.Tuple[str, str]]
 511        ) -> t.Dict[str, t.Tuple[str, TokenType]]:
 512            return {k: (v, token_type) for k, v in _convert_quotes(arr).items()}
 513
 514        klass._QUOTES = _convert_quotes(klass.QUOTES)
 515        klass._IDENTIFIERS = _convert_quotes(klass.IDENTIFIERS)
 516
 517        klass._FORMAT_STRINGS = {
 518            **{
 519                p + s: (e, TokenType.NATIONAL_STRING)
 520                for s, e in klass._QUOTES.items()
 521                for p in ("n", "N")
 522            },
 523            **_quotes_to_format(TokenType.BIT_STRING, klass.BIT_STRINGS),
 524            **_quotes_to_format(TokenType.BYTE_STRING, klass.BYTE_STRINGS),
 525            **_quotes_to_format(TokenType.HEX_STRING, klass.HEX_STRINGS),
 526            **_quotes_to_format(TokenType.RAW_STRING, klass.RAW_STRINGS),
 527            **_quotes_to_format(TokenType.HEREDOC_STRING, klass.HEREDOC_STRINGS),
 528            **_quotes_to_format(TokenType.UNICODE_STRING, klass.UNICODE_STRINGS),
 529        }
 530
 531        klass._STRING_ESCAPES = set(klass.STRING_ESCAPES)
 532        klass._IDENTIFIER_ESCAPES = set(klass.IDENTIFIER_ESCAPES)
 533        klass._COMMENTS = {
 534            **dict(
 535                (comment, None) if isinstance(comment, str) else (comment[0], comment[1])
 536                for comment in klass.COMMENTS
 537            ),
 538            "{#": "#}",  # Ensure Jinja comments are tokenized correctly in all dialects
 539        }
 540        if klass.HINT_START in klass.KEYWORDS:
 541            klass._COMMENTS[klass.HINT_START] = "*/"
 542
 543        klass._KEYWORD_TRIE = new_trie(
 544            key.upper()
 545            for key in (
 546                *klass.KEYWORDS,
 547                *klass._COMMENTS,
 548                *klass._QUOTES,
 549                *klass._FORMAT_STRINGS,
 550            )
 551            if " " in key or any(single in key for single in klass.SINGLE_TOKENS)
 552        )
 553
 554        if USE_RS_TOKENIZER:
 555            settings = RsTokenizerSettings(
 556                white_space={k: _TOKEN_TYPE_TO_INDEX[v] for k, v in klass.WHITE_SPACE.items()},
 557                single_tokens={k: _TOKEN_TYPE_TO_INDEX[v] for k, v in klass.SINGLE_TOKENS.items()},
 558                keywords={k: _TOKEN_TYPE_TO_INDEX[v] for k, v in klass.KEYWORDS.items()},
 559                numeric_literals=klass.NUMERIC_LITERALS,
 560                identifiers=klass._IDENTIFIERS,
 561                identifier_escapes=klass._IDENTIFIER_ESCAPES,
 562                string_escapes=klass._STRING_ESCAPES,
 563                quotes=klass._QUOTES,
 564                format_strings={
 565                    k: (v1, _TOKEN_TYPE_TO_INDEX[v2])
 566                    for k, (v1, v2) in klass._FORMAT_STRINGS.items()
 567                },
 568                has_bit_strings=bool(klass.BIT_STRINGS),
 569                has_hex_strings=bool(klass.HEX_STRINGS),
 570                comments=klass._COMMENTS,
 571                var_single_tokens=klass.VAR_SINGLE_TOKENS,
 572                commands={_TOKEN_TYPE_TO_INDEX[v] for v in klass.COMMANDS},
 573                command_prefix_tokens={
 574                    _TOKEN_TYPE_TO_INDEX[v] for v in klass.COMMAND_PREFIX_TOKENS
 575                },
 576                heredoc_tag_is_identifier=klass.HEREDOC_TAG_IS_IDENTIFIER,
 577                string_escapes_allowed_in_raw_strings=klass.STRING_ESCAPES_ALLOWED_IN_RAW_STRINGS,
 578                nested_comments=klass.NESTED_COMMENTS,
 579                hint_start=klass.HINT_START,
 580                tokens_preceding_hint={
 581                    _TOKEN_TYPE_TO_INDEX[v] for v in klass.TOKENS_PRECEDING_HINT
 582                },
 583            )
 584            token_types = RsTokenTypeSettings(
 585                bit_string=_TOKEN_TYPE_TO_INDEX[TokenType.BIT_STRING],
 586                break_=_TOKEN_TYPE_TO_INDEX[TokenType.BREAK],
 587                dcolon=_TOKEN_TYPE_TO_INDEX[TokenType.DCOLON],
 588                heredoc_string=_TOKEN_TYPE_TO_INDEX[TokenType.HEREDOC_STRING],
 589                raw_string=_TOKEN_TYPE_TO_INDEX[TokenType.RAW_STRING],
 590                hex_string=_TOKEN_TYPE_TO_INDEX[TokenType.HEX_STRING],
 591                identifier=_TOKEN_TYPE_TO_INDEX[TokenType.IDENTIFIER],
 592                number=_TOKEN_TYPE_TO_INDEX[TokenType.NUMBER],
 593                parameter=_TOKEN_TYPE_TO_INDEX[TokenType.PARAMETER],
 594                semicolon=_TOKEN_TYPE_TO_INDEX[TokenType.SEMICOLON],
 595                string=_TOKEN_TYPE_TO_INDEX[TokenType.STRING],
 596                var=_TOKEN_TYPE_TO_INDEX[TokenType.VAR],
 597                heredoc_string_alternative=_TOKEN_TYPE_TO_INDEX[klass.HEREDOC_STRING_ALTERNATIVE],
 598                hint=_TOKEN_TYPE_TO_INDEX[TokenType.HINT],
 599            )
 600            klass._RS_TOKENIZER = RsTokenizer(settings, token_types)
 601        else:
 602            klass._RS_TOKENIZER = None
 603
 604        return klass
 605
 606
 607class Tokenizer(metaclass=_Tokenizer):
 608    SINGLE_TOKENS = {
 609        "(": TokenType.L_PAREN,
 610        ")": TokenType.R_PAREN,
 611        "[": TokenType.L_BRACKET,
 612        "]": TokenType.R_BRACKET,
 613        "{": TokenType.L_BRACE,
 614        "}": TokenType.R_BRACE,
 615        "&": TokenType.AMP,
 616        "^": TokenType.CARET,
 617        ":": TokenType.COLON,
 618        ",": TokenType.COMMA,
 619        ".": TokenType.DOT,
 620        "-": TokenType.DASH,
 621        "=": TokenType.EQ,
 622        ">": TokenType.GT,
 623        "<": TokenType.LT,
 624        "%": TokenType.MOD,
 625        "!": TokenType.NOT,
 626        "|": TokenType.PIPE,
 627        "+": TokenType.PLUS,
 628        ";": TokenType.SEMICOLON,
 629        "/": TokenType.SLASH,
 630        "\\": TokenType.BACKSLASH,
 631        "*": TokenType.STAR,
 632        "~": TokenType.TILDA,
 633        "?": TokenType.PLACEHOLDER,
 634        "@": TokenType.PARAMETER,
 635        "#": TokenType.HASH,
 636        # Used for breaking a var like x'y' but nothing else the token type doesn't matter
 637        "'": TokenType.UNKNOWN,
 638        "`": TokenType.UNKNOWN,
 639        '"': TokenType.UNKNOWN,
 640    }
 641
 642    BIT_STRINGS: t.List[str | t.Tuple[str, str]] = []
 643    BYTE_STRINGS: t.List[str | t.Tuple[str, str]] = []
 644    HEX_STRINGS: t.List[str | t.Tuple[str, str]] = []
 645    RAW_STRINGS: t.List[str | t.Tuple[str, str]] = []
 646    HEREDOC_STRINGS: t.List[str | t.Tuple[str, str]] = []
 647    UNICODE_STRINGS: t.List[str | t.Tuple[str, str]] = []
 648    IDENTIFIERS: t.List[str | t.Tuple[str, str]] = ['"']
 649    QUOTES: t.List[t.Tuple[str, str] | str] = ["'"]
 650    STRING_ESCAPES = ["'"]
 651    VAR_SINGLE_TOKENS: t.Set[str] = set()
 652
 653    # The strings in this list can always be used as escapes, regardless of the surrounding
 654    # identifier delimiters. By default, the closing delimiter is assumed to also act as an
 655    # identifier escape, e.g. if we use double-quotes, then they also act as escapes: "x"""
 656    IDENTIFIER_ESCAPES: t.List[str] = []
 657
 658    # Whether the heredoc tags follow the same lexical rules as unquoted identifiers
 659    HEREDOC_TAG_IS_IDENTIFIER = False
 660
 661    # Token that we'll generate as a fallback if the heredoc prefix doesn't correspond to a heredoc
 662    HEREDOC_STRING_ALTERNATIVE = TokenType.VAR
 663
 664    # Whether string escape characters function as such when placed within raw strings
 665    STRING_ESCAPES_ALLOWED_IN_RAW_STRINGS = True
 666
 667    NESTED_COMMENTS = True
 668
 669    HINT_START = "/*+"
 670
 671    TOKENS_PRECEDING_HINT = {TokenType.SELECT, TokenType.INSERT, TokenType.UPDATE, TokenType.DELETE}
 672
 673    # Autofilled
 674    _COMMENTS: t.Dict[str, str] = {}
 675    _FORMAT_STRINGS: t.Dict[str, t.Tuple[str, TokenType]] = {}
 676    _IDENTIFIERS: t.Dict[str, str] = {}
 677    _IDENTIFIER_ESCAPES: t.Set[str] = set()
 678    _QUOTES: t.Dict[str, str] = {}
 679    _STRING_ESCAPES: t.Set[str] = set()
 680    _KEYWORD_TRIE: t.Dict = {}
 681    _RS_TOKENIZER: t.Optional[t.Any] = None
 682
 683    KEYWORDS: t.Dict[str, TokenType] = {
 684        **{f"{{%{postfix}": TokenType.BLOCK_START for postfix in ("", "+", "-")},
 685        **{f"{prefix}%}}": TokenType.BLOCK_END for prefix in ("", "+", "-")},
 686        **{f"{{{{{postfix}": TokenType.BLOCK_START for postfix in ("+", "-")},
 687        **{f"{prefix}}}}}": TokenType.BLOCK_END for prefix in ("+", "-")},
 688        HINT_START: TokenType.HINT,
 689        "==": TokenType.EQ,
 690        "::": TokenType.DCOLON,
 691        "||": TokenType.DPIPE,
 692        "|>": TokenType.PIPE_GT,
 693        ">=": TokenType.GTE,
 694        "<=": TokenType.LTE,
 695        "<>": TokenType.NEQ,
 696        "!=": TokenType.NEQ,
 697        ":=": TokenType.COLON_EQ,
 698        "<=>": TokenType.NULLSAFE_EQ,
 699        "->": TokenType.ARROW,
 700        "->>": TokenType.DARROW,
 701        "=>": TokenType.FARROW,
 702        "#>": TokenType.HASH_ARROW,
 703        "#>>": TokenType.DHASH_ARROW,
 704        "<->": TokenType.LR_ARROW,
 705        "&&": TokenType.DAMP,
 706        "??": TokenType.DQMARK,
 707        "~~~": TokenType.GLOB,
 708        "~~": TokenType.LIKE,
 709        "~~*": TokenType.ILIKE,
 710        "~*": TokenType.IRLIKE,
 711        "ALL": TokenType.ALL,
 712        "ALWAYS": TokenType.ALWAYS,
 713        "AND": TokenType.AND,
 714        "ANTI": TokenType.ANTI,
 715        "ANY": TokenType.ANY,
 716        "ASC": TokenType.ASC,
 717        "AS": TokenType.ALIAS,
 718        "ASOF": TokenType.ASOF,
 719        "AUTOINCREMENT": TokenType.AUTO_INCREMENT,
 720        "AUTO_INCREMENT": TokenType.AUTO_INCREMENT,
 721        "BEGIN": TokenType.BEGIN,
 722        "BETWEEN": TokenType.BETWEEN,
 723        "CACHE": TokenType.CACHE,
 724        "UNCACHE": TokenType.UNCACHE,
 725        "CASE": TokenType.CASE,
 726        "CHARACTER SET": TokenType.CHARACTER_SET,
 727        "CLUSTER BY": TokenType.CLUSTER_BY,
 728        "COLLATE": TokenType.COLLATE,
 729        "COLUMN": TokenType.COLUMN,
 730        "COMMIT": TokenType.COMMIT,
 731        "CONNECT BY": TokenType.CONNECT_BY,
 732        "CONSTRAINT": TokenType.CONSTRAINT,
 733        "COPY": TokenType.COPY,
 734        "CREATE": TokenType.CREATE,
 735        "CROSS": TokenType.CROSS,
 736        "CUBE": TokenType.CUBE,
 737        "CURRENT_DATE": TokenType.CURRENT_DATE,
 738        "CURRENT_SCHEMA": TokenType.CURRENT_SCHEMA,
 739        "CURRENT_TIME": TokenType.CURRENT_TIME,
 740        "CURRENT_TIMESTAMP": TokenType.CURRENT_TIMESTAMP,
 741        "CURRENT_USER": TokenType.CURRENT_USER,
 742        "DATABASE": TokenType.DATABASE,
 743        "DEFAULT": TokenType.DEFAULT,
 744        "DELETE": TokenType.DELETE,
 745        "DESC": TokenType.DESC,
 746        "DESCRIBE": TokenType.DESCRIBE,
 747        "DISTINCT": TokenType.DISTINCT,
 748        "DISTRIBUTE BY": TokenType.DISTRIBUTE_BY,
 749        "DIV": TokenType.DIV,
 750        "DROP": TokenType.DROP,
 751        "ELSE": TokenType.ELSE,
 752        "END": TokenType.END,
 753        "ENUM": TokenType.ENUM,
 754        "ESCAPE": TokenType.ESCAPE,
 755        "EXCEPT": TokenType.EXCEPT,
 756        "EXECUTE": TokenType.EXECUTE,
 757        "EXISTS": TokenType.EXISTS,
 758        "FALSE": TokenType.FALSE,
 759        "FETCH": TokenType.FETCH,
 760        "FILTER": TokenType.FILTER,
 761        "FIRST": TokenType.FIRST,
 762        "FULL": TokenType.FULL,
 763        "FUNCTION": TokenType.FUNCTION,
 764        "FOR": TokenType.FOR,
 765        "FOREIGN KEY": TokenType.FOREIGN_KEY,
 766        "FORMAT": TokenType.FORMAT,
 767        "FROM": TokenType.FROM,
 768        "GEOGRAPHY": TokenType.GEOGRAPHY,
 769        "GEOMETRY": TokenType.GEOMETRY,
 770        "GLOB": TokenType.GLOB,
 771        "GROUP BY": TokenType.GROUP_BY,
 772        "GROUPING SETS": TokenType.GROUPING_SETS,
 773        "HAVING": TokenType.HAVING,
 774        "ILIKE": TokenType.ILIKE,
 775        "IN": TokenType.IN,
 776        "INDEX": TokenType.INDEX,
 777        "INET": TokenType.INET,
 778        "INNER": TokenType.INNER,
 779        "INSERT": TokenType.INSERT,
 780        "INTERVAL": TokenType.INTERVAL,
 781        "INTERSECT": TokenType.INTERSECT,
 782        "INTO": TokenType.INTO,
 783        "IS": TokenType.IS,
 784        "ISNULL": TokenType.ISNULL,
 785        "JOIN": TokenType.JOIN,
 786        "KEEP": TokenType.KEEP,
 787        "KILL": TokenType.KILL,
 788        "LATERAL": TokenType.LATERAL,
 789        "LEFT": TokenType.LEFT,
 790        "LIKE": TokenType.LIKE,
 791        "LIMIT": TokenType.LIMIT,
 792        "LOAD": TokenType.LOAD,
 793        "LOCK": TokenType.LOCK,
 794        "MERGE": TokenType.MERGE,
 795        "NAMESPACE": TokenType.NAMESPACE,
 796        "NATURAL": TokenType.NATURAL,
 797        "NEXT": TokenType.NEXT,
 798        "NOT": TokenType.NOT,
 799        "NOTNULL": TokenType.NOTNULL,
 800        "NULL": TokenType.NULL,
 801        "OBJECT": TokenType.OBJECT,
 802        "OFFSET": TokenType.OFFSET,
 803        "ON": TokenType.ON,
 804        "OR": TokenType.OR,
 805        "XOR": TokenType.XOR,
 806        "ORDER BY": TokenType.ORDER_BY,
 807        "ORDINALITY": TokenType.ORDINALITY,
 808        "OUTER": TokenType.OUTER,
 809        "OVER": TokenType.OVER,
 810        "OVERLAPS": TokenType.OVERLAPS,
 811        "OVERWRITE": TokenType.OVERWRITE,
 812        "PARTITION": TokenType.PARTITION,
 813        "PARTITION BY": TokenType.PARTITION_BY,
 814        "PARTITIONED BY": TokenType.PARTITION_BY,
 815        "PARTITIONED_BY": TokenType.PARTITION_BY,
 816        "PERCENT": TokenType.PERCENT,
 817        "PIVOT": TokenType.PIVOT,
 818        "PRAGMA": TokenType.PRAGMA,
 819        "PRIMARY KEY": TokenType.PRIMARY_KEY,
 820        "PROCEDURE": TokenType.PROCEDURE,
 821        "QUALIFY": TokenType.QUALIFY,
 822        "RANGE": TokenType.RANGE,
 823        "RECURSIVE": TokenType.RECURSIVE,
 824        "REGEXP": TokenType.RLIKE,
 825        "RENAME": TokenType.RENAME,
 826        "REPLACE": TokenType.REPLACE,
 827        "RETURNING": TokenType.RETURNING,
 828        "REFERENCES": TokenType.REFERENCES,
 829        "RIGHT": TokenType.RIGHT,
 830        "RLIKE": TokenType.RLIKE,
 831        "ROLLBACK": TokenType.ROLLBACK,
 832        "ROLLUP": TokenType.ROLLUP,
 833        "ROW": TokenType.ROW,
 834        "ROWS": TokenType.ROWS,
 835        "SCHEMA": TokenType.SCHEMA,
 836        "SELECT": TokenType.SELECT,
 837        "SEMI": TokenType.SEMI,
 838        "SET": TokenType.SET,
 839        "SETTINGS": TokenType.SETTINGS,
 840        "SHOW": TokenType.SHOW,
 841        "SIMILAR TO": TokenType.SIMILAR_TO,
 842        "SOME": TokenType.SOME,
 843        "SORT BY": TokenType.SORT_BY,
 844        "START WITH": TokenType.START_WITH,
 845        "STRAIGHT_JOIN": TokenType.STRAIGHT_JOIN,
 846        "TABLE": TokenType.TABLE,
 847        "TABLESAMPLE": TokenType.TABLE_SAMPLE,
 848        "TEMP": TokenType.TEMPORARY,
 849        "TEMPORARY": TokenType.TEMPORARY,
 850        "THEN": TokenType.THEN,
 851        "TRUE": TokenType.TRUE,
 852        "TRUNCATE": TokenType.TRUNCATE,
 853        "UNION": TokenType.UNION,
 854        "UNKNOWN": TokenType.UNKNOWN,
 855        "UNNEST": TokenType.UNNEST,
 856        "UNPIVOT": TokenType.UNPIVOT,
 857        "UPDATE": TokenType.UPDATE,
 858        "USE": TokenType.USE,
 859        "USING": TokenType.USING,
 860        "UUID": TokenType.UUID,
 861        "VALUES": TokenType.VALUES,
 862        "VIEW": TokenType.VIEW,
 863        "VOLATILE": TokenType.VOLATILE,
 864        "WHEN": TokenType.WHEN,
 865        "WHERE": TokenType.WHERE,
 866        "WINDOW": TokenType.WINDOW,
 867        "WITH": TokenType.WITH,
 868        "APPLY": TokenType.APPLY,
 869        "ARRAY": TokenType.ARRAY,
 870        "BIT": TokenType.BIT,
 871        "BOOL": TokenType.BOOLEAN,
 872        "BOOLEAN": TokenType.BOOLEAN,
 873        "BYTE": TokenType.TINYINT,
 874        "MEDIUMINT": TokenType.MEDIUMINT,
 875        "INT1": TokenType.TINYINT,
 876        "TINYINT": TokenType.TINYINT,
 877        "INT16": TokenType.SMALLINT,
 878        "SHORT": TokenType.SMALLINT,
 879        "SMALLINT": TokenType.SMALLINT,
 880        "HUGEINT": TokenType.INT128,
 881        "UHUGEINT": TokenType.UINT128,
 882        "INT2": TokenType.SMALLINT,
 883        "INTEGER": TokenType.INT,
 884        "INT": TokenType.INT,
 885        "INT4": TokenType.INT,
 886        "INT32": TokenType.INT,
 887        "INT64": TokenType.BIGINT,
 888        "INT128": TokenType.INT128,
 889        "INT256": TokenType.INT256,
 890        "LONG": TokenType.BIGINT,
 891        "BIGINT": TokenType.BIGINT,
 892        "INT8": TokenType.TINYINT,
 893        "UINT": TokenType.UINT,
 894        "UINT128": TokenType.UINT128,
 895        "UINT256": TokenType.UINT256,
 896        "DEC": TokenType.DECIMAL,
 897        "DECIMAL": TokenType.DECIMAL,
 898        "DECIMAL32": TokenType.DECIMAL32,
 899        "DECIMAL64": TokenType.DECIMAL64,
 900        "DECIMAL128": TokenType.DECIMAL128,
 901        "DECIMAL256": TokenType.DECIMAL256,
 902        "BIGDECIMAL": TokenType.BIGDECIMAL,
 903        "BIGNUMERIC": TokenType.BIGDECIMAL,
 904        "LIST": TokenType.LIST,
 905        "MAP": TokenType.MAP,
 906        "NULLABLE": TokenType.NULLABLE,
 907        "NUMBER": TokenType.DECIMAL,
 908        "NUMERIC": TokenType.DECIMAL,
 909        "FIXED": TokenType.DECIMAL,
 910        "REAL": TokenType.FLOAT,
 911        "FLOAT": TokenType.FLOAT,
 912        "FLOAT4": TokenType.FLOAT,
 913        "FLOAT8": TokenType.DOUBLE,
 914        "DOUBLE": TokenType.DOUBLE,
 915        "DOUBLE PRECISION": TokenType.DOUBLE,
 916        "JSON": TokenType.JSON,
 917        "JSONB": TokenType.JSONB,
 918        "CHAR": TokenType.CHAR,
 919        "CHARACTER": TokenType.CHAR,
 920        "CHAR VARYING": TokenType.VARCHAR,
 921        "CHARACTER VARYING": TokenType.VARCHAR,
 922        "NCHAR": TokenType.NCHAR,
 923        "VARCHAR": TokenType.VARCHAR,
 924        "VARCHAR2": TokenType.VARCHAR,
 925        "NVARCHAR": TokenType.NVARCHAR,
 926        "NVARCHAR2": TokenType.NVARCHAR,
 927        "BPCHAR": TokenType.BPCHAR,
 928        "STR": TokenType.TEXT,
 929        "STRING": TokenType.TEXT,
 930        "TEXT": TokenType.TEXT,
 931        "LONGTEXT": TokenType.LONGTEXT,
 932        "MEDIUMTEXT": TokenType.MEDIUMTEXT,
 933        "TINYTEXT": TokenType.TINYTEXT,
 934        "CLOB": TokenType.TEXT,
 935        "LONGVARCHAR": TokenType.TEXT,
 936        "BINARY": TokenType.BINARY,
 937        "BLOB": TokenType.VARBINARY,
 938        "LONGBLOB": TokenType.LONGBLOB,
 939        "MEDIUMBLOB": TokenType.MEDIUMBLOB,
 940        "TINYBLOB": TokenType.TINYBLOB,
 941        "BYTEA": TokenType.VARBINARY,
 942        "VARBINARY": TokenType.VARBINARY,
 943        "TIME": TokenType.TIME,
 944        "TIMETZ": TokenType.TIMETZ,
 945        "TIMESTAMP": TokenType.TIMESTAMP,
 946        "TIMESTAMPTZ": TokenType.TIMESTAMPTZ,
 947        "TIMESTAMPLTZ": TokenType.TIMESTAMPLTZ,
 948        "TIMESTAMP_LTZ": TokenType.TIMESTAMPLTZ,
 949        "TIMESTAMPNTZ": TokenType.TIMESTAMPNTZ,
 950        "TIMESTAMP_NTZ": TokenType.TIMESTAMPNTZ,
 951        "DATE": TokenType.DATE,
 952        "DATETIME": TokenType.DATETIME,
 953        "INT4RANGE": TokenType.INT4RANGE,
 954        "INT4MULTIRANGE": TokenType.INT4MULTIRANGE,
 955        "INT8RANGE": TokenType.INT8RANGE,
 956        "INT8MULTIRANGE": TokenType.INT8MULTIRANGE,
 957        "NUMRANGE": TokenType.NUMRANGE,
 958        "NUMMULTIRANGE": TokenType.NUMMULTIRANGE,
 959        "TSRANGE": TokenType.TSRANGE,
 960        "TSMULTIRANGE": TokenType.TSMULTIRANGE,
 961        "TSTZRANGE": TokenType.TSTZRANGE,
 962        "TSTZMULTIRANGE": TokenType.TSTZMULTIRANGE,
 963        "DATERANGE": TokenType.DATERANGE,
 964        "DATEMULTIRANGE": TokenType.DATEMULTIRANGE,
 965        "UNIQUE": TokenType.UNIQUE,
 966        "VECTOR": TokenType.VECTOR,
 967        "STRUCT": TokenType.STRUCT,
 968        "SEQUENCE": TokenType.SEQUENCE,
 969        "VARIANT": TokenType.VARIANT,
 970        "ALTER": TokenType.ALTER,
 971        "ANALYZE": TokenType.ANALYZE,
 972        "CALL": TokenType.COMMAND,
 973        "COMMENT": TokenType.COMMENT,
 974        "EXPLAIN": TokenType.COMMAND,
 975        "GRANT": TokenType.GRANT,
 976        "REVOKE": TokenType.REVOKE,
 977        "OPTIMIZE": TokenType.COMMAND,
 978        "PREPARE": TokenType.COMMAND,
 979        "VACUUM": TokenType.COMMAND,
 980        "USER-DEFINED": TokenType.USERDEFINED,
 981        "FOR VERSION": TokenType.VERSION_SNAPSHOT,
 982        "FOR TIMESTAMP": TokenType.TIMESTAMP_SNAPSHOT,
 983    }
 984
 985    WHITE_SPACE: t.Dict[t.Optional[str], TokenType] = {
 986        " ": TokenType.SPACE,
 987        "\t": TokenType.SPACE,
 988        "\n": TokenType.BREAK,
 989        "\r": TokenType.BREAK,
 990    }
 991
 992    COMMANDS = {
 993        TokenType.COMMAND,
 994        TokenType.EXECUTE,
 995        TokenType.FETCH,
 996        TokenType.SHOW,
 997        TokenType.RENAME,
 998    }
 999
1000    COMMAND_PREFIX_TOKENS = {TokenType.SEMICOLON, TokenType.BEGIN}
1001
1002    # Handle numeric literals like in hive (3L = BIGINT)
1003    NUMERIC_LITERALS: t.Dict[str, str] = {}
1004
1005    COMMENTS = ["--", ("/*", "*/")]
1006
1007    __slots__ = (
1008        "sql",
1009        "size",
1010        "tokens",
1011        "dialect",
1012        "use_rs_tokenizer",
1013        "_start",
1014        "_current",
1015        "_line",
1016        "_col",
1017        "_comments",
1018        "_char",
1019        "_end",
1020        "_peek",
1021        "_prev_token_line",
1022        "_rs_dialect_settings",
1023    )
1024
1025    def __init__(
1026        self,
1027        dialect: DialectType = None,
1028        use_rs_tokenizer: t.Optional[bool] = None,
1029        **opts: t.Any,
1030    ) -> None:
1031        from sqlglot.dialects import Dialect
1032
1033        self.dialect = Dialect.get_or_raise(dialect)
1034
1035        # initialize `use_rs_tokenizer`, and allow it to be overwritten per Tokenizer instance
1036        self.use_rs_tokenizer = (
1037            use_rs_tokenizer if use_rs_tokenizer is not None else USE_RS_TOKENIZER
1038        )
1039
1040        if self.use_rs_tokenizer:
1041            self._rs_dialect_settings = RsTokenizerDialectSettings(
1042                unescaped_sequences=self.dialect.UNESCAPED_SEQUENCES,
1043                identifiers_can_start_with_digit=self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT,
1044                numbers_can_be_underscore_separated=self.dialect.NUMBERS_CAN_BE_UNDERSCORE_SEPARATED,
1045            )
1046
1047        self.reset()
1048
1049    def reset(self) -> None:
1050        self.sql = ""
1051        self.size = 0
1052        self.tokens: t.List[Token] = []
1053        self._start = 0
1054        self._current = 0
1055        self._line = 1
1056        self._col = 0
1057        self._comments: t.List[str] = []
1058
1059        self._char = ""
1060        self._end = False
1061        self._peek = ""
1062        self._prev_token_line = -1
1063
1064    def tokenize(self, sql: str) -> t.List[Token]:
1065        """Returns a list of tokens corresponding to the SQL string `sql`."""
1066        if self.use_rs_tokenizer:
1067            return self.tokenize_rs(sql)
1068
1069        self.reset()
1070        self.sql = sql
1071        self.size = len(sql)
1072
1073        try:
1074            self._scan()
1075        except Exception as e:
1076            start = max(self._current - 50, 0)
1077            end = min(self._current + 50, self.size - 1)
1078            context = self.sql[start:end]
1079            raise TokenError(f"Error tokenizing '{context}'") from e
1080
1081        return self.tokens
1082
1083    def _scan(self, until: t.Optional[t.Callable] = None) -> None:
1084        while self.size and not self._end:
1085            current = self._current
1086
1087            # Skip spaces here rather than iteratively calling advance() for performance reasons
1088            while current < self.size:
1089                char = self.sql[current]
1090
1091                if char.isspace() and (char == " " or char == "\t"):
1092                    current += 1
1093                else:
1094                    break
1095
1096            offset = current - self._current if current > self._current else 1
1097
1098            self._start = current
1099            self._advance(offset)
1100
1101            if not self._char.isspace():
1102                if self._char.isdigit():
1103                    self._scan_number()
1104                elif self._char in self._IDENTIFIERS:
1105                    self._scan_identifier(self._IDENTIFIERS[self._char])
1106                else:
1107                    self._scan_keywords()
1108
1109            if until and until():
1110                break
1111
1112        if self.tokens and self._comments:
1113            self.tokens[-1].comments.extend(self._comments)
1114
1115    def _chars(self, size: int) -> str:
1116        if size == 1:
1117            return self._char
1118
1119        start = self._current - 1
1120        end = start + size
1121
1122        return self.sql[start:end] if end <= self.size else ""
1123
1124    def _advance(self, i: int = 1, alnum: bool = False) -> None:
1125        if self.WHITE_SPACE.get(self._char) is TokenType.BREAK:
1126            # Ensures we don't count an extra line if we get a \r\n line break sequence
1127            if not (self._char == "\r" and self._peek == "\n"):
1128                self._col = i
1129                self._line += 1
1130        else:
1131            self._col += i
1132
1133        self._current += i
1134        self._end = self._current >= self.size
1135        self._char = self.sql[self._current - 1]
1136        self._peek = "" if self._end else self.sql[self._current]
1137
1138        if alnum and self._char.isalnum():
1139            # Here we use local variables instead of attributes for better performance
1140            _col = self._col
1141            _current = self._current
1142            _end = self._end
1143            _peek = self._peek
1144
1145            while _peek.isalnum():
1146                _col += 1
1147                _current += 1
1148                _end = _current >= self.size
1149                _peek = "" if _end else self.sql[_current]
1150
1151            self._col = _col
1152            self._current = _current
1153            self._end = _end
1154            self._peek = _peek
1155            self._char = self.sql[_current - 1]
1156
1157    @property
1158    def _text(self) -> str:
1159        return self.sql[self._start : self._current]
1160
1161    def _add(self, token_type: TokenType, text: t.Optional[str] = None) -> None:
1162        self._prev_token_line = self._line
1163
1164        if self._comments and token_type == TokenType.SEMICOLON and self.tokens:
1165            self.tokens[-1].comments.extend(self._comments)
1166            self._comments = []
1167
1168        self.tokens.append(
1169            Token(
1170                token_type,
1171                text=self._text if text is None else text,
1172                line=self._line,
1173                col=self._col,
1174                start=self._start,
1175                end=self._current - 1,
1176                comments=self._comments,
1177            )
1178        )
1179        self._comments = []
1180
1181        # If we have either a semicolon or a begin token before the command's token, we'll parse
1182        # whatever follows the command's token as a string
1183        if (
1184            token_type in self.COMMANDS
1185            and self._peek != ";"
1186            and (len(self.tokens) == 1 or self.tokens[-2].token_type in self.COMMAND_PREFIX_TOKENS)
1187        ):
1188            start = self._current
1189            tokens = len(self.tokens)
1190            self._scan(lambda: self._peek == ";")
1191            self.tokens = self.tokens[:tokens]
1192            text = self.sql[start : self._current].strip()
1193            if text:
1194                self._add(TokenType.STRING, text)
1195
1196    def _scan_keywords(self) -> None:
1197        size = 0
1198        word = None
1199        chars = self._text
1200        char = chars
1201        prev_space = False
1202        skip = False
1203        trie = self._KEYWORD_TRIE
1204        single_token = char in self.SINGLE_TOKENS
1205
1206        while chars:
1207            if skip:
1208                result = TrieResult.PREFIX
1209            else:
1210                result, trie = in_trie(trie, char.upper())
1211
1212            if result == TrieResult.FAILED:
1213                break
1214            if result == TrieResult.EXISTS:
1215                word = chars
1216
1217            end = self._current + size
1218            size += 1
1219
1220            if end < self.size:
1221                char = self.sql[end]
1222                single_token = single_token or char in self.SINGLE_TOKENS
1223                is_space = char.isspace()
1224
1225                if not is_space or not prev_space:
1226                    if is_space:
1227                        char = " "
1228                    chars += char
1229                    prev_space = is_space
1230                    skip = False
1231                else:
1232                    skip = True
1233            else:
1234                char = ""
1235                break
1236
1237        if word:
1238            if self._scan_string(word):
1239                return
1240            if self._scan_comment(word):
1241                return
1242            if prev_space or single_token or not char:
1243                self._advance(size - 1)
1244                word = word.upper()
1245                self._add(self.KEYWORDS[word], text=word)
1246                return
1247
1248        if self._char in self.SINGLE_TOKENS:
1249            self._add(self.SINGLE_TOKENS[self._char], text=self._char)
1250            return
1251
1252        self._scan_var()
1253
1254    def _scan_comment(self, comment_start: str) -> bool:
1255        if comment_start not in self._COMMENTS:
1256            return False
1257
1258        comment_start_line = self._line
1259        comment_start_size = len(comment_start)
1260        comment_end = self._COMMENTS[comment_start]
1261
1262        if comment_end:
1263            # Skip the comment's start delimiter
1264            self._advance(comment_start_size)
1265
1266            comment_count = 1
1267            comment_end_size = len(comment_end)
1268
1269            while not self._end:
1270                if self._chars(comment_end_size) == comment_end:
1271                    comment_count -= 1
1272                    if not comment_count:
1273                        break
1274
1275                self._advance(alnum=True)
1276
1277                # Nested comments are allowed by some dialects, e.g. databricks, duckdb, postgres
1278                if (
1279                    self.NESTED_COMMENTS
1280                    and not self._end
1281                    and self._chars(comment_end_size) == comment_start
1282                ):
1283                    self._advance(comment_start_size)
1284                    comment_count += 1
1285
1286            self._comments.append(self._text[comment_start_size : -comment_end_size + 1])
1287            self._advance(comment_end_size - 1)
1288        else:
1289            while not self._end and self.WHITE_SPACE.get(self._peek) is not TokenType.BREAK:
1290                self._advance(alnum=True)
1291            self._comments.append(self._text[comment_start_size:])
1292
1293        if (
1294            comment_start == self.HINT_START
1295            and self.tokens
1296            and self.tokens[-1].token_type in self.TOKENS_PRECEDING_HINT
1297        ):
1298            self._add(TokenType.HINT)
1299
1300        # Leading comment is attached to the succeeding token, whilst trailing comment to the preceding.
1301        # Multiple consecutive comments are preserved by appending them to the current comments list.
1302        if comment_start_line == self._prev_token_line:
1303            self.tokens[-1].comments.extend(self._comments)
1304            self._comments = []
1305            self._prev_token_line = self._line
1306
1307        return True
1308
1309    def _scan_number(self) -> None:
1310        if self._char == "0":
1311            peek = self._peek.upper()
1312            if peek == "B":
1313                return self._scan_bits() if self.BIT_STRINGS else self._add(TokenType.NUMBER)
1314            elif peek == "X":
1315                return self._scan_hex() if self.HEX_STRINGS else self._add(TokenType.NUMBER)
1316
1317        decimal = False
1318        scientific = 0
1319
1320        while True:
1321            if self._peek.isdigit():
1322                self._advance()
1323            elif self._peek == "." and not decimal:
1324                if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER:
1325                    return self._add(TokenType.NUMBER)
1326                decimal = True
1327                self._advance()
1328            elif self._peek in ("-", "+") and scientific == 1:
1329                scientific += 1
1330                self._advance()
1331            elif self._peek.upper() == "E" and not scientific:
1332                scientific += 1
1333                self._advance()
1334            elif self._peek.isidentifier():
1335                number_text = self._text
1336                literal = ""
1337
1338                while self._peek.strip() and self._peek not in self.SINGLE_TOKENS:
1339                    literal += self._peek
1340                    self._advance()
1341
1342                token_type = self.KEYWORDS.get(self.NUMERIC_LITERALS.get(literal.upper(), ""))
1343
1344                if token_type:
1345                    self._add(TokenType.NUMBER, number_text)
1346                    self._add(TokenType.DCOLON, "::")
1347                    return self._add(token_type, literal)
1348                else:
1349                    replaced = literal.replace("_", "")
1350                    if self.dialect.NUMBERS_CAN_BE_UNDERSCORE_SEPARATED and replaced.isdigit():
1351                        return self._add(TokenType.NUMBER, number_text + replaced)
1352                    if self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT:
1353                        return self._add(TokenType.VAR)
1354
1355                self._advance(-len(literal))
1356                return self._add(TokenType.NUMBER, number_text)
1357            else:
1358                return self._add(TokenType.NUMBER)
1359
1360    def _scan_bits(self) -> None:
1361        self._advance()
1362        value = self._extract_value()
1363        try:
1364            # If `value` can't be converted to a binary, fallback to tokenizing it as an identifier
1365            int(value, 2)
1366            self._add(TokenType.BIT_STRING, value[2:])  # Drop the 0b
1367        except ValueError:
1368            self._add(TokenType.IDENTIFIER)
1369
1370    def _scan_hex(self) -> None:
1371        self._advance()
1372        value = self._extract_value()
1373        try:
1374            # If `value` can't be converted to a hex, fallback to tokenizing it as an identifier
1375            int(value, 16)
1376            self._add(TokenType.HEX_STRING, value[2:])  # Drop the 0x
1377        except ValueError:
1378            self._add(TokenType.IDENTIFIER)
1379
1380    def _extract_value(self) -> str:
1381        while True:
1382            char = self._peek.strip()
1383            if char and char not in self.SINGLE_TOKENS:
1384                self._advance(alnum=True)
1385            else:
1386                break
1387
1388        return self._text
1389
1390    def _scan_string(self, start: str) -> bool:
1391        base = None
1392        token_type = TokenType.STRING
1393
1394        if start in self._QUOTES:
1395            end = self._QUOTES[start]
1396        elif start in self._FORMAT_STRINGS:
1397            end, token_type = self._FORMAT_STRINGS[start]
1398
1399            if token_type == TokenType.HEX_STRING:
1400                base = 16
1401            elif token_type == TokenType.BIT_STRING:
1402                base = 2
1403            elif token_type == TokenType.HEREDOC_STRING:
1404                self._advance()
1405
1406                if self._char == end:
1407                    tag = ""
1408                else:
1409                    tag = self._extract_string(
1410                        end,
1411                        raw_string=True,
1412                        raise_unmatched=not self.HEREDOC_TAG_IS_IDENTIFIER,
1413                    )
1414
1415                if tag and self.HEREDOC_TAG_IS_IDENTIFIER and (self._end or not tag.isidentifier()):
1416                    if not self._end:
1417                        self._advance(-1)
1418
1419                    self._advance(-len(tag))
1420                    self._add(self.HEREDOC_STRING_ALTERNATIVE)
1421                    return True
1422
1423                end = f"{start}{tag}{end}"
1424        else:
1425            return False
1426
1427        self._advance(len(start))
1428        text = self._extract_string(end, raw_string=token_type == TokenType.RAW_STRING)
1429
1430        if base and text:
1431            try:
1432                int(text, base)
1433            except Exception:
1434                raise TokenError(
1435                    f"Numeric string contains invalid characters from {self._line}:{self._start}"
1436                )
1437
1438        self._add(token_type, text)
1439        return True
1440
1441    def _scan_identifier(self, identifier_end: str) -> None:
1442        self._advance()
1443        text = self._extract_string(
1444            identifier_end, escapes=self._IDENTIFIER_ESCAPES | {identifier_end}
1445        )
1446        self._add(TokenType.IDENTIFIER, text)
1447
1448    def _scan_var(self) -> None:
1449        while True:
1450            char = self._peek.strip()
1451            if char and (char in self.VAR_SINGLE_TOKENS or char not in self.SINGLE_TOKENS):
1452                self._advance(alnum=True)
1453            else:
1454                break
1455
1456        self._add(
1457            TokenType.VAR
1458            if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER
1459            else self.KEYWORDS.get(self._text.upper(), TokenType.VAR)
1460        )
1461
1462    def _extract_string(
1463        self,
1464        delimiter: str,
1465        escapes: t.Optional[t.Set[str]] = None,
1466        raw_string: bool = False,
1467        raise_unmatched: bool = True,
1468    ) -> str:
1469        text = ""
1470        delim_size = len(delimiter)
1471        escapes = self._STRING_ESCAPES if escapes is None else escapes
1472
1473        while True:
1474            if (
1475                not raw_string
1476                and self.dialect.UNESCAPED_SEQUENCES
1477                and self._peek
1478                and self._char in self.STRING_ESCAPES
1479            ):
1480                unescaped_sequence = self.dialect.UNESCAPED_SEQUENCES.get(self._char + self._peek)
1481                if unescaped_sequence:
1482                    self._advance(2)
1483                    text += unescaped_sequence
1484                    continue
1485            if (
1486                (self.STRING_ESCAPES_ALLOWED_IN_RAW_STRINGS or not raw_string)
1487                and self._char in escapes
1488                and (self._peek == delimiter or self._peek in escapes)
1489                and (self._char not in self._QUOTES or self._char == self._peek)
1490            ):
1491                if self._peek == delimiter:
1492                    text += self._peek
1493                else:
1494                    text += self._char + self._peek
1495
1496                if self._current + 1 < self.size:
1497                    self._advance(2)
1498                else:
1499                    raise TokenError(f"Missing {delimiter} from {self._line}:{self._current}")
1500            else:
1501                if self._chars(delim_size) == delimiter:
1502                    if delim_size > 1:
1503                        self._advance(delim_size - 1)
1504                    break
1505
1506                if self._end:
1507                    if not raise_unmatched:
1508                        return text + self._char
1509
1510                    raise TokenError(f"Missing {delimiter} from {self._line}:{self._start}")
1511
1512                current = self._current - 1
1513                self._advance(alnum=True)
1514                text += self.sql[current : self._current - 1]
1515
1516        return text
1517
1518    def tokenize_rs(self, sql: str) -> t.List[Token]:
1519        if not self._RS_TOKENIZER:
1520            raise SqlglotError("Rust tokenizer is not available")
1521
1522        tokens, error_msg = self._RS_TOKENIZER.tokenize(sql, self._rs_dialect_settings)
1523        for token in tokens:
1524            token.token_type = _ALL_TOKEN_TYPES[token.token_type_index]
1525
1526        # Setting this here so partial token lists can be inspected even if there is a failure
1527        self.tokens = tokens
1528
1529        if error_msg is not None:
1530            raise TokenError(error_msg)
1531
1532        return tokens
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    DOTCOLON = auto()
 42    DCOLON = auto()
 43    DCOLONDOLLAR = auto()
 44    DCOLONPERCENT = auto()
 45    DQMARK = auto()
 46    SEMICOLON = auto()
 47    STAR = auto()
 48    BACKSLASH = auto()
 49    SLASH = auto()
 50    LT = auto()
 51    LTE = auto()
 52    GT = auto()
 53    GTE = auto()
 54    NOT = auto()
 55    EQ = auto()
 56    NEQ = auto()
 57    NULLSAFE_EQ = auto()
 58    COLON_EQ = auto()
 59    COLON_GT = auto()
 60    NCOLON_GT = auto()
 61    AND = auto()
 62    OR = auto()
 63    AMP = auto()
 64    DPIPE = auto()
 65    PIPE_GT = auto()
 66    PIPE = auto()
 67    PIPE_SLASH = auto()
 68    DPIPE_SLASH = auto()
 69    CARET = auto()
 70    CARET_AT = auto()
 71    TILDA = auto()
 72    ARROW = auto()
 73    DARROW = auto()
 74    FARROW = auto()
 75    HASH = auto()
 76    HASH_ARROW = auto()
 77    DHASH_ARROW = auto()
 78    LR_ARROW = auto()
 79    DAT = auto()
 80    LT_AT = auto()
 81    AT_GT = auto()
 82    DOLLAR = auto()
 83    PARAMETER = auto()
 84    SESSION_PARAMETER = auto()
 85    DAMP = auto()
 86    XOR = auto()
 87    DSTAR = auto()
 88
 89    URI_START = auto()
 90
 91    BLOCK_START = auto()
 92    BLOCK_END = auto()
 93
 94    SPACE = auto()
 95    BREAK = auto()
 96
 97    STRING = auto()
 98    NUMBER = auto()
 99    IDENTIFIER = auto()
100    DATABASE = auto()
101    COLUMN = auto()
102    COLUMN_DEF = auto()
103    SCHEMA = auto()
104    TABLE = auto()
105    WAREHOUSE = auto()
106    STAGE = auto()
107    STREAMLIT = auto()
108    VAR = auto()
109    BIT_STRING = auto()
110    HEX_STRING = auto()
111    BYTE_STRING = auto()
112    NATIONAL_STRING = auto()
113    RAW_STRING = auto()
114    HEREDOC_STRING = auto()
115    UNICODE_STRING = auto()
116
117    # types
118    BIT = auto()
119    BOOLEAN = auto()
120    TINYINT = auto()
121    UTINYINT = auto()
122    SMALLINT = auto()
123    USMALLINT = auto()
124    MEDIUMINT = auto()
125    UMEDIUMINT = auto()
126    INT = auto()
127    UINT = auto()
128    BIGINT = auto()
129    UBIGINT = auto()
130    INT128 = auto()
131    UINT128 = auto()
132    INT256 = auto()
133    UINT256 = auto()
134    FLOAT = auto()
135    DOUBLE = auto()
136    UDOUBLE = auto()
137    DECIMAL = auto()
138    DECIMAL32 = auto()
139    DECIMAL64 = auto()
140    DECIMAL128 = auto()
141    DECIMAL256 = auto()
142    UDECIMAL = auto()
143    BIGDECIMAL = auto()
144    CHAR = auto()
145    NCHAR = auto()
146    VARCHAR = auto()
147    NVARCHAR = auto()
148    BPCHAR = auto()
149    TEXT = auto()
150    MEDIUMTEXT = auto()
151    LONGTEXT = auto()
152    BLOB = auto()
153    MEDIUMBLOB = auto()
154    LONGBLOB = auto()
155    TINYBLOB = auto()
156    TINYTEXT = auto()
157    NAME = auto()
158    BINARY = auto()
159    VARBINARY = auto()
160    JSON = auto()
161    JSONB = auto()
162    TIME = auto()
163    TIMETZ = auto()
164    TIMESTAMP = auto()
165    TIMESTAMPTZ = auto()
166    TIMESTAMPLTZ = auto()
167    TIMESTAMPNTZ = auto()
168    TIMESTAMP_S = auto()
169    TIMESTAMP_MS = auto()
170    TIMESTAMP_NS = auto()
171    DATETIME = auto()
172    DATETIME2 = auto()
173    DATETIME64 = auto()
174    SMALLDATETIME = auto()
175    DATE = auto()
176    DATE32 = auto()
177    INT4RANGE = auto()
178    INT4MULTIRANGE = auto()
179    INT8RANGE = auto()
180    INT8MULTIRANGE = auto()
181    NUMRANGE = auto()
182    NUMMULTIRANGE = auto()
183    TSRANGE = auto()
184    TSMULTIRANGE = auto()
185    TSTZRANGE = auto()
186    TSTZMULTIRANGE = auto()
187    DATERANGE = auto()
188    DATEMULTIRANGE = auto()
189    UUID = auto()
190    GEOGRAPHY = auto()
191    GEOGRAPHYPOINT = auto()
192    NULLABLE = auto()
193    GEOMETRY = auto()
194    POINT = auto()
195    RING = auto()
196    LINESTRING = auto()
197    MULTILINESTRING = auto()
198    POLYGON = auto()
199    MULTIPOLYGON = auto()
200    HLLSKETCH = auto()
201    HSTORE = auto()
202    SUPER = auto()
203    SERIAL = auto()
204    SMALLSERIAL = auto()
205    BIGSERIAL = auto()
206    XML = auto()
207    YEAR = auto()
208    USERDEFINED = auto()
209    MONEY = auto()
210    SMALLMONEY = auto()
211    ROWVERSION = auto()
212    IMAGE = auto()
213    VARIANT = auto()
214    OBJECT = auto()
215    INET = auto()
216    IPADDRESS = auto()
217    IPPREFIX = auto()
218    IPV4 = auto()
219    IPV6 = auto()
220    ENUM = auto()
221    ENUM8 = auto()
222    ENUM16 = auto()
223    FIXEDSTRING = auto()
224    LOWCARDINALITY = auto()
225    NESTED = auto()
226    AGGREGATEFUNCTION = auto()
227    SIMPLEAGGREGATEFUNCTION = auto()
228    TDIGEST = auto()
229    UNKNOWN = auto()
230    VECTOR = auto()
231    DYNAMIC = auto()
232    VOID = auto()
233
234    # keywords
235    ALIAS = auto()
236    ALTER = auto()
237    ALWAYS = auto()
238    ALL = auto()
239    ANTI = auto()
240    ANY = auto()
241    APPLY = auto()
242    ARRAY = auto()
243    ASC = auto()
244    ASOF = auto()
245    ATTACH = auto()
246    AUTO_INCREMENT = auto()
247    BEGIN = auto()
248    BETWEEN = auto()
249    BULK_COLLECT_INTO = auto()
250    CACHE = auto()
251    CASE = auto()
252    CHARACTER_SET = auto()
253    CLUSTER_BY = auto()
254    COLLATE = auto()
255    COMMAND = auto()
256    COMMENT = auto()
257    COMMIT = auto()
258    CONNECT_BY = auto()
259    CONSTRAINT = auto()
260    COPY = auto()
261    CREATE = auto()
262    CROSS = auto()
263    CUBE = auto()
264    CURRENT_DATE = auto()
265    CURRENT_DATETIME = auto()
266    CURRENT_SCHEMA = auto()
267    CURRENT_TIME = auto()
268    CURRENT_TIMESTAMP = auto()
269    CURRENT_USER = auto()
270    DECLARE = auto()
271    DEFAULT = auto()
272    DELETE = auto()
273    DESC = auto()
274    DESCRIBE = auto()
275    DETACH = auto()
276    DICTIONARY = auto()
277    DISTINCT = auto()
278    DISTRIBUTE_BY = auto()
279    DIV = auto()
280    DROP = auto()
281    ELSE = auto()
282    END = auto()
283    ESCAPE = auto()
284    EXCEPT = auto()
285    EXECUTE = auto()
286    EXISTS = auto()
287    FALSE = auto()
288    FETCH = auto()
289    FILE_FORMAT = auto()
290    FILTER = auto()
291    FINAL = auto()
292    FIRST = auto()
293    FOR = auto()
294    FORCE = auto()
295    FOREIGN_KEY = auto()
296    FORMAT = auto()
297    FROM = auto()
298    FULL = auto()
299    FUNCTION = auto()
300    GET = auto()
301    GLOB = auto()
302    GLOBAL = auto()
303    GRANT = auto()
304    GROUP_BY = auto()
305    GROUPING_SETS = auto()
306    HAVING = auto()
307    HINT = auto()
308    IGNORE = auto()
309    ILIKE = auto()
310    IN = auto()
311    INDEX = auto()
312    INNER = auto()
313    INSERT = auto()
314    INTERSECT = auto()
315    INTERVAL = auto()
316    INTO = auto()
317    INTRODUCER = auto()
318    IRLIKE = auto()
319    IS = auto()
320    ISNULL = auto()
321    JOIN = auto()
322    JOIN_MARKER = auto()
323    KEEP = auto()
324    KEY = auto()
325    KILL = auto()
326    LANGUAGE = auto()
327    LATERAL = auto()
328    LEFT = auto()
329    LIKE = auto()
330    LIMIT = auto()
331    LIST = auto()
332    LOAD = auto()
333    LOCK = auto()
334    MAP = auto()
335    MATCH_CONDITION = auto()
336    MATCH_RECOGNIZE = auto()
337    MEMBER_OF = auto()
338    MERGE = auto()
339    MOD = auto()
340    MODEL = auto()
341    NATURAL = auto()
342    NEXT = auto()
343    NOTHING = auto()
344    NOTNULL = auto()
345    NULL = auto()
346    OBJECT_IDENTIFIER = auto()
347    OFFSET = auto()
348    ON = auto()
349    ONLY = auto()
350    OPERATOR = auto()
351    ORDER_BY = auto()
352    ORDER_SIBLINGS_BY = auto()
353    ORDERED = auto()
354    ORDINALITY = auto()
355    OUTER = auto()
356    OVER = auto()
357    OVERLAPS = auto()
358    OVERWRITE = auto()
359    PARTITION = auto()
360    PARTITION_BY = auto()
361    PERCENT = auto()
362    PIVOT = auto()
363    PLACEHOLDER = auto()
364    POSITIONAL = auto()
365    PRAGMA = auto()
366    PREWHERE = auto()
367    PRIMARY_KEY = auto()
368    PROCEDURE = auto()
369    PROPERTIES = auto()
370    PSEUDO_TYPE = auto()
371    PUT = auto()
372    QUALIFY = auto()
373    QUOTE = auto()
374    RANGE = auto()
375    RECURSIVE = auto()
376    REFRESH = auto()
377    RENAME = auto()
378    REPLACE = auto()
379    RETURNING = auto()
380    REVOKE = auto()
381    REFERENCES = auto()
382    RIGHT = auto()
383    RLIKE = auto()
384    ROLLBACK = auto()
385    ROLLUP = auto()
386    ROW = auto()
387    ROWS = auto()
388    SELECT = auto()
389    SEMI = auto()
390    SEPARATOR = auto()
391    SEQUENCE = auto()
392    SERDE_PROPERTIES = auto()
393    SET = auto()
394    SETTINGS = auto()
395    SHOW = auto()
396    SIMILAR_TO = auto()
397    SOME = auto()
398    SORT_BY = auto()
399    START_WITH = auto()
400    STORAGE_INTEGRATION = auto()
401    STRAIGHT_JOIN = auto()
402    STRUCT = auto()
403    SUMMARIZE = auto()
404    TABLE_SAMPLE = auto()
405    TAG = auto()
406    TEMPORARY = auto()
407    TOP = auto()
408    THEN = auto()
409    TRUE = auto()
410    TRUNCATE = auto()
411    UNCACHE = auto()
412    UNION = auto()
413    UNNEST = auto()
414    UNPIVOT = auto()
415    UPDATE = auto()
416    USE = auto()
417    USING = auto()
418    VALUES = auto()
419    VIEW = auto()
420    SEMANTIC_VIEW = auto()
421    VOLATILE = auto()
422    WHEN = auto()
423    WHERE = auto()
424    WINDOW = auto()
425    WITH = auto()
426    UNIQUE = auto()
427    VERSION_SNAPSHOT = auto()
428    TIMESTAMP_SNAPSHOT = auto()
429    OPTION = auto()
430    SINK = auto()
431    SOURCE = auto()
432    ANALYZE = auto()
433    NAMESPACE = auto()
434    EXPORT = auto()
435
436    # sentinel
437    HIVE_TOKEN_STREAM = auto()

An enumeration.

L_PAREN = <TokenType.L_PAREN: 'L_PAREN'>
R_PAREN = <TokenType.R_PAREN: 'R_PAREN'>
L_BRACKET = <TokenType.L_BRACKET: 'L_BRACKET'>
R_BRACKET = <TokenType.R_BRACKET: 'R_BRACKET'>
L_BRACE = <TokenType.L_BRACE: 'L_BRACE'>
R_BRACE = <TokenType.R_BRACE: 'R_BRACE'>
COMMA = <TokenType.COMMA: 'COMMA'>
DOT = <TokenType.DOT: 'DOT'>
DASH = <TokenType.DASH: 'DASH'>
PLUS = <TokenType.PLUS: 'PLUS'>
COLON = <TokenType.COLON: 'COLON'>
DOTCOLON = <TokenType.DOTCOLON: 'DOTCOLON'>
DCOLON = <TokenType.DCOLON: 'DCOLON'>
DCOLONDOLLAR = <TokenType.DCOLONDOLLAR: 'DCOLONDOLLAR'>
DCOLONPERCENT = <TokenType.DCOLONPERCENT: 'DCOLONPERCENT'>
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'>
COLON_GT = <TokenType.COLON_GT: 'COLON_GT'>
NCOLON_GT = <TokenType.NCOLON_GT: 'NCOLON_GT'>
AND = <TokenType.AND: 'AND'>
OR = <TokenType.OR: 'OR'>
AMP = <TokenType.AMP: 'AMP'>
DPIPE = <TokenType.DPIPE: 'DPIPE'>
PIPE_GT = <TokenType.PIPE_GT: 'PIPE_GT'>
PIPE = <TokenType.PIPE: 'PIPE'>
PIPE_SLASH = <TokenType.PIPE_SLASH: 'PIPE_SLASH'>
DPIPE_SLASH = <TokenType.DPIPE_SLASH: 'DPIPE_SLASH'>
CARET = <TokenType.CARET: 'CARET'>
CARET_AT = <TokenType.CARET_AT: 'CARET_AT'>
TILDA = <TokenType.TILDA: 'TILDA'>
ARROW = <TokenType.ARROW: 'ARROW'>
DARROW = <TokenType.DARROW: 'DARROW'>
FARROW = <TokenType.FARROW: 'FARROW'>
HASH = <TokenType.HASH: 'HASH'>
HASH_ARROW = <TokenType.HASH_ARROW: 'HASH_ARROW'>
DHASH_ARROW = <TokenType.DHASH_ARROW: 'DHASH_ARROW'>
LR_ARROW = <TokenType.LR_ARROW: 'LR_ARROW'>
DAT = <TokenType.DAT: 'DAT'>
LT_AT = <TokenType.LT_AT: 'LT_AT'>
AT_GT = <TokenType.AT_GT: 'AT_GT'>
DOLLAR = <TokenType.DOLLAR: 'DOLLAR'>
PARAMETER = <TokenType.PARAMETER: 'PARAMETER'>
SESSION_PARAMETER = <TokenType.SESSION_PARAMETER: 'SESSION_PARAMETER'>
DAMP = <TokenType.DAMP: 'DAMP'>
XOR = <TokenType.XOR: 'XOR'>
DSTAR = <TokenType.DSTAR: 'DSTAR'>
URI_START = <TokenType.URI_START: 'URI_START'>
BLOCK_START = <TokenType.BLOCK_START: 'BLOCK_START'>
BLOCK_END = <TokenType.BLOCK_END: 'BLOCK_END'>
SPACE = <TokenType.SPACE: 'SPACE'>
BREAK = <TokenType.BREAK: 'BREAK'>
STRING = <TokenType.STRING: 'STRING'>
NUMBER = <TokenType.NUMBER: 'NUMBER'>
IDENTIFIER = <TokenType.IDENTIFIER: 'IDENTIFIER'>
DATABASE = <TokenType.DATABASE: 'DATABASE'>
COLUMN = <TokenType.COLUMN: 'COLUMN'>
COLUMN_DEF = <TokenType.COLUMN_DEF: 'COLUMN_DEF'>
SCHEMA = <TokenType.SCHEMA: 'SCHEMA'>
TABLE = <TokenType.TABLE: 'TABLE'>
WAREHOUSE = <TokenType.WAREHOUSE: 'WAREHOUSE'>
STAGE = <TokenType.STAGE: 'STAGE'>
STREAMLIT = <TokenType.STREAMLIT: 'STREAMLIT'>
VAR = <TokenType.VAR: 'VAR'>
BIT_STRING = <TokenType.BIT_STRING: 'BIT_STRING'>
HEX_STRING = <TokenType.HEX_STRING: 'HEX_STRING'>
BYTE_STRING = <TokenType.BYTE_STRING: 'BYTE_STRING'>
NATIONAL_STRING = <TokenType.NATIONAL_STRING: 'NATIONAL_STRING'>
RAW_STRING = <TokenType.RAW_STRING: 'RAW_STRING'>
HEREDOC_STRING = <TokenType.HEREDOC_STRING: 'HEREDOC_STRING'>
UNICODE_STRING = <TokenType.UNICODE_STRING: 'UNICODE_STRING'>
BIT = <TokenType.BIT: 'BIT'>
BOOLEAN = <TokenType.BOOLEAN: 'BOOLEAN'>
TINYINT = <TokenType.TINYINT: 'TINYINT'>
UTINYINT = <TokenType.UTINYINT: 'UTINYINT'>
SMALLINT = <TokenType.SMALLINT: 'SMALLINT'>
USMALLINT = <TokenType.USMALLINT: 'USMALLINT'>
MEDIUMINT = <TokenType.MEDIUMINT: 'MEDIUMINT'>
UMEDIUMINT = <TokenType.UMEDIUMINT: 'UMEDIUMINT'>
INT = <TokenType.INT: 'INT'>
UINT = <TokenType.UINT: 'UINT'>
BIGINT = <TokenType.BIGINT: 'BIGINT'>
UBIGINT = <TokenType.UBIGINT: 'UBIGINT'>
INT128 = <TokenType.INT128: 'INT128'>
UINT128 = <TokenType.UINT128: 'UINT128'>
INT256 = <TokenType.INT256: 'INT256'>
UINT256 = <TokenType.UINT256: 'UINT256'>
FLOAT = <TokenType.FLOAT: 'FLOAT'>
DOUBLE = <TokenType.DOUBLE: 'DOUBLE'>
UDOUBLE = <TokenType.UDOUBLE: 'UDOUBLE'>
DECIMAL = <TokenType.DECIMAL: 'DECIMAL'>
DECIMAL32 = <TokenType.DECIMAL32: 'DECIMAL32'>
DECIMAL64 = <TokenType.DECIMAL64: 'DECIMAL64'>
DECIMAL128 = <TokenType.DECIMAL128: 'DECIMAL128'>
DECIMAL256 = <TokenType.DECIMAL256: 'DECIMAL256'>
UDECIMAL = <TokenType.UDECIMAL: 'UDECIMAL'>
BIGDECIMAL = <TokenType.BIGDECIMAL: 'BIGDECIMAL'>
CHAR = <TokenType.CHAR: 'CHAR'>
NCHAR = <TokenType.NCHAR: 'NCHAR'>
VARCHAR = <TokenType.VARCHAR: 'VARCHAR'>
NVARCHAR = <TokenType.NVARCHAR: 'NVARCHAR'>
BPCHAR = <TokenType.BPCHAR: 'BPCHAR'>
TEXT = <TokenType.TEXT: 'TEXT'>
MEDIUMTEXT = <TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>
LONGTEXT = <TokenType.LONGTEXT: 'LONGTEXT'>
BLOB = <TokenType.BLOB: 'BLOB'>
MEDIUMBLOB = <TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>
LONGBLOB = <TokenType.LONGBLOB: 'LONGBLOB'>
TINYBLOB = <TokenType.TINYBLOB: 'TINYBLOB'>
TINYTEXT = <TokenType.TINYTEXT: 'TINYTEXT'>
NAME = <TokenType.NAME: 'NAME'>
BINARY = <TokenType.BINARY: 'BINARY'>
VARBINARY = <TokenType.VARBINARY: 'VARBINARY'>
JSON = <TokenType.JSON: 'JSON'>
JSONB = <TokenType.JSONB: 'JSONB'>
TIME = <TokenType.TIME: 'TIME'>
TIMETZ = <TokenType.TIMETZ: 'TIMETZ'>
TIMESTAMP = <TokenType.TIMESTAMP: 'TIMESTAMP'>
TIMESTAMPTZ = <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>
TIMESTAMPLTZ = <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>
TIMESTAMPNTZ = <TokenType.TIMESTAMPNTZ: 'TIMESTAMPNTZ'>
TIMESTAMP_S = <TokenType.TIMESTAMP_S: 'TIMESTAMP_S'>
TIMESTAMP_MS = <TokenType.TIMESTAMP_MS: 'TIMESTAMP_MS'>
TIMESTAMP_NS = <TokenType.TIMESTAMP_NS: 'TIMESTAMP_NS'>
DATETIME = <TokenType.DATETIME: 'DATETIME'>
DATETIME2 = <TokenType.DATETIME2: 'DATETIME2'>
DATETIME64 = <TokenType.DATETIME64: 'DATETIME64'>
SMALLDATETIME = <TokenType.SMALLDATETIME: 'SMALLDATETIME'>
DATE = <TokenType.DATE: 'DATE'>
DATE32 = <TokenType.DATE32: 'DATE32'>
INT4RANGE = <TokenType.INT4RANGE: 'INT4RANGE'>
INT4MULTIRANGE = <TokenType.INT4MULTIRANGE: 'INT4MULTIRANGE'>
INT8RANGE = <TokenType.INT8RANGE: 'INT8RANGE'>
INT8MULTIRANGE = <TokenType.INT8MULTIRANGE: 'INT8MULTIRANGE'>
NUMRANGE = <TokenType.NUMRANGE: 'NUMRANGE'>
NUMMULTIRANGE = <TokenType.NUMMULTIRANGE: 'NUMMULTIRANGE'>
TSRANGE = <TokenType.TSRANGE: 'TSRANGE'>
TSMULTIRANGE = <TokenType.TSMULTIRANGE: 'TSMULTIRANGE'>
TSTZRANGE = <TokenType.TSTZRANGE: 'TSTZRANGE'>
TSTZMULTIRANGE = <TokenType.TSTZMULTIRANGE: 'TSTZMULTIRANGE'>
DATERANGE = <TokenType.DATERANGE: 'DATERANGE'>
DATEMULTIRANGE = <TokenType.DATEMULTIRANGE: 'DATEMULTIRANGE'>
UUID = <TokenType.UUID: 'UUID'>
GEOGRAPHY = <TokenType.GEOGRAPHY: 'GEOGRAPHY'>
GEOGRAPHYPOINT = <TokenType.GEOGRAPHYPOINT: 'GEOGRAPHYPOINT'>
NULLABLE = <TokenType.NULLABLE: 'NULLABLE'>
GEOMETRY = <TokenType.GEOMETRY: 'GEOMETRY'>
POINT = <TokenType.POINT: 'POINT'>
RING = <TokenType.RING: 'RING'>
LINESTRING = <TokenType.LINESTRING: 'LINESTRING'>
MULTILINESTRING = <TokenType.MULTILINESTRING: 'MULTILINESTRING'>
POLYGON = <TokenType.POLYGON: 'POLYGON'>
MULTIPOLYGON = <TokenType.MULTIPOLYGON: 'MULTIPOLYGON'>
HLLSKETCH = <TokenType.HLLSKETCH: 'HLLSKETCH'>
HSTORE = <TokenType.HSTORE: 'HSTORE'>
SUPER = <TokenType.SUPER: 'SUPER'>
SERIAL = <TokenType.SERIAL: 'SERIAL'>
SMALLSERIAL = <TokenType.SMALLSERIAL: 'SMALLSERIAL'>
BIGSERIAL = <TokenType.BIGSERIAL: 'BIGSERIAL'>
XML = <TokenType.XML: 'XML'>
YEAR = <TokenType.YEAR: 'YEAR'>
USERDEFINED = <TokenType.USERDEFINED: 'USERDEFINED'>
MONEY = <TokenType.MONEY: 'MONEY'>
SMALLMONEY = <TokenType.SMALLMONEY: 'SMALLMONEY'>
ROWVERSION = <TokenType.ROWVERSION: 'ROWVERSION'>
IMAGE = <TokenType.IMAGE: 'IMAGE'>
VARIANT = <TokenType.VARIANT: 'VARIANT'>
OBJECT = <TokenType.OBJECT: 'OBJECT'>
INET = <TokenType.INET: 'INET'>
IPADDRESS = <TokenType.IPADDRESS: 'IPADDRESS'>
IPPREFIX = <TokenType.IPPREFIX: 'IPPREFIX'>
IPV4 = <TokenType.IPV4: 'IPV4'>
IPV6 = <TokenType.IPV6: 'IPV6'>
ENUM = <TokenType.ENUM: 'ENUM'>
ENUM8 = <TokenType.ENUM8: 'ENUM8'>
ENUM16 = <TokenType.ENUM16: 'ENUM16'>
FIXEDSTRING = <TokenType.FIXEDSTRING: 'FIXEDSTRING'>
LOWCARDINALITY = <TokenType.LOWCARDINALITY: 'LOWCARDINALITY'>
NESTED = <TokenType.NESTED: 'NESTED'>
AGGREGATEFUNCTION = <TokenType.AGGREGATEFUNCTION: 'AGGREGATEFUNCTION'>
SIMPLEAGGREGATEFUNCTION = <TokenType.SIMPLEAGGREGATEFUNCTION: 'SIMPLEAGGREGATEFUNCTION'>
TDIGEST = <TokenType.TDIGEST: 'TDIGEST'>
UNKNOWN = <TokenType.UNKNOWN: 'UNKNOWN'>
VECTOR = <TokenType.VECTOR: 'VECTOR'>
DYNAMIC = <TokenType.DYNAMIC: 'DYNAMIC'>
VOID = <TokenType.VOID: 'VOID'>
ALIAS = <TokenType.ALIAS: 'ALIAS'>
ALTER = <TokenType.ALTER: 'ALTER'>
ALWAYS = <TokenType.ALWAYS: 'ALWAYS'>
ALL = <TokenType.ALL: 'ALL'>
ANTI = <TokenType.ANTI: 'ANTI'>
ANY = <TokenType.ANY: 'ANY'>
APPLY = <TokenType.APPLY: 'APPLY'>
ARRAY = <TokenType.ARRAY: 'ARRAY'>
ASC = <TokenType.ASC: 'ASC'>
ASOF = <TokenType.ASOF: 'ASOF'>
ATTACH = <TokenType.ATTACH: 'ATTACH'>
AUTO_INCREMENT = <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>
BEGIN = <TokenType.BEGIN: 'BEGIN'>
BETWEEN = <TokenType.BETWEEN: 'BETWEEN'>
BULK_COLLECT_INTO = <TokenType.BULK_COLLECT_INTO: 'BULK_COLLECT_INTO'>
CACHE = <TokenType.CACHE: 'CACHE'>
CASE = <TokenType.CASE: 'CASE'>
CHARACTER_SET = <TokenType.CHARACTER_SET: 'CHARACTER_SET'>
CLUSTER_BY = <TokenType.CLUSTER_BY: 'CLUSTER_BY'>
COLLATE = <TokenType.COLLATE: 'COLLATE'>
COMMAND = <TokenType.COMMAND: 'COMMAND'>
COMMENT = <TokenType.COMMENT: 'COMMENT'>
COMMIT = <TokenType.COMMIT: 'COMMIT'>
CONNECT_BY = <TokenType.CONNECT_BY: 'CONNECT_BY'>
CONSTRAINT = <TokenType.CONSTRAINT: 'CONSTRAINT'>
COPY = <TokenType.COPY: 'COPY'>
CREATE = <TokenType.CREATE: 'CREATE'>
CROSS = <TokenType.CROSS: 'CROSS'>
CUBE = <TokenType.CUBE: 'CUBE'>
CURRENT_DATE = <TokenType.CURRENT_DATE: 'CURRENT_DATE'>
CURRENT_DATETIME = <TokenType.CURRENT_DATETIME: 'CURRENT_DATETIME'>
CURRENT_SCHEMA = <TokenType.CURRENT_SCHEMA: 'CURRENT_SCHEMA'>
CURRENT_TIME = <TokenType.CURRENT_TIME: 'CURRENT_TIME'>
CURRENT_TIMESTAMP = <TokenType.CURRENT_TIMESTAMP: 'CURRENT_TIMESTAMP'>
CURRENT_USER = <TokenType.CURRENT_USER: 'CURRENT_USER'>
DECLARE = <TokenType.DECLARE: 'DECLARE'>
DEFAULT = <TokenType.DEFAULT: 'DEFAULT'>
DELETE = <TokenType.DELETE: 'DELETE'>
DESC = <TokenType.DESC: 'DESC'>
DESCRIBE = <TokenType.DESCRIBE: 'DESCRIBE'>
DETACH = <TokenType.DETACH: 'DETACH'>
DICTIONARY = <TokenType.DICTIONARY: 'DICTIONARY'>
DISTINCT = <TokenType.DISTINCT: 'DISTINCT'>
DISTRIBUTE_BY = <TokenType.DISTRIBUTE_BY: 'DISTRIBUTE_BY'>
DIV = <TokenType.DIV: 'DIV'>
DROP = <TokenType.DROP: 'DROP'>
ELSE = <TokenType.ELSE: 'ELSE'>
END = <TokenType.END: 'END'>
ESCAPE = <TokenType.ESCAPE: 'ESCAPE'>
EXCEPT = <TokenType.EXCEPT: 'EXCEPT'>
EXECUTE = <TokenType.EXECUTE: 'EXECUTE'>
EXISTS = <TokenType.EXISTS: 'EXISTS'>
FALSE = <TokenType.FALSE: 'FALSE'>
FETCH = <TokenType.FETCH: 'FETCH'>
FILE_FORMAT = <TokenType.FILE_FORMAT: 'FILE_FORMAT'>
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'>
GET = <TokenType.GET: 'GET'>
GLOB = <TokenType.GLOB: 'GLOB'>
GLOBAL = <TokenType.GLOBAL: 'GLOBAL'>
GRANT = <TokenType.GRANT: 'GRANT'>
GROUP_BY = <TokenType.GROUP_BY: 'GROUP_BY'>
GROUPING_SETS = <TokenType.GROUPING_SETS: 'GROUPING_SETS'>
HAVING = <TokenType.HAVING: 'HAVING'>
HINT = <TokenType.HINT: 'HINT'>
IGNORE = <TokenType.IGNORE: 'IGNORE'>
ILIKE = <TokenType.ILIKE: 'ILIKE'>
IN = <TokenType.IN: 'IN'>
INDEX = <TokenType.INDEX: 'INDEX'>
INNER = <TokenType.INNER: 'INNER'>
INSERT = <TokenType.INSERT: 'INSERT'>
INTERSECT = <TokenType.INTERSECT: 'INTERSECT'>
INTERVAL = <TokenType.INTERVAL: 'INTERVAL'>
INTO = <TokenType.INTO: 'INTO'>
INTRODUCER = <TokenType.INTRODUCER: 'INTRODUCER'>
IRLIKE = <TokenType.IRLIKE: 'IRLIKE'>
IS = <TokenType.IS: 'IS'>
ISNULL = <TokenType.ISNULL: 'ISNULL'>
JOIN = <TokenType.JOIN: 'JOIN'>
JOIN_MARKER = <TokenType.JOIN_MARKER: 'JOIN_MARKER'>
KEEP = <TokenType.KEEP: 'KEEP'>
KEY = <TokenType.KEY: 'KEY'>
KILL = <TokenType.KILL: 'KILL'>
LANGUAGE = <TokenType.LANGUAGE: 'LANGUAGE'>
LATERAL = <TokenType.LATERAL: 'LATERAL'>
LEFT = <TokenType.LEFT: 'LEFT'>
LIKE = <TokenType.LIKE: 'LIKE'>
LIMIT = <TokenType.LIMIT: 'LIMIT'>
LIST = <TokenType.LIST: 'LIST'>
LOAD = <TokenType.LOAD: 'LOAD'>
LOCK = <TokenType.LOCK: 'LOCK'>
MAP = <TokenType.MAP: 'MAP'>
MATCH_CONDITION = <TokenType.MATCH_CONDITION: 'MATCH_CONDITION'>
MATCH_RECOGNIZE = <TokenType.MATCH_RECOGNIZE: 'MATCH_RECOGNIZE'>
MEMBER_OF = <TokenType.MEMBER_OF: 'MEMBER_OF'>
MERGE = <TokenType.MERGE: 'MERGE'>
MOD = <TokenType.MOD: 'MOD'>
MODEL = <TokenType.MODEL: 'MODEL'>
NATURAL = <TokenType.NATURAL: 'NATURAL'>
NEXT = <TokenType.NEXT: 'NEXT'>
NOTHING = <TokenType.NOTHING: 'NOTHING'>
NOTNULL = <TokenType.NOTNULL: 'NOTNULL'>
NULL = <TokenType.NULL: 'NULL'>
OBJECT_IDENTIFIER = <TokenType.OBJECT_IDENTIFIER: 'OBJECT_IDENTIFIER'>
OFFSET = <TokenType.OFFSET: 'OFFSET'>
ON = <TokenType.ON: 'ON'>
ONLY = <TokenType.ONLY: 'ONLY'>
OPERATOR = <TokenType.OPERATOR: 'OPERATOR'>
ORDER_BY = <TokenType.ORDER_BY: 'ORDER_BY'>
ORDER_SIBLINGS_BY = <TokenType.ORDER_SIBLINGS_BY: 'ORDER_SIBLINGS_BY'>
ORDERED = <TokenType.ORDERED: 'ORDERED'>
ORDINALITY = <TokenType.ORDINALITY: 'ORDINALITY'>
OUTER = <TokenType.OUTER: 'OUTER'>
OVER = <TokenType.OVER: 'OVER'>
OVERLAPS = <TokenType.OVERLAPS: 'OVERLAPS'>
OVERWRITE = <TokenType.OVERWRITE: 'OVERWRITE'>
PARTITION = <TokenType.PARTITION: 'PARTITION'>
PARTITION_BY = <TokenType.PARTITION_BY: 'PARTITION_BY'>
PERCENT = <TokenType.PERCENT: 'PERCENT'>
PIVOT = <TokenType.PIVOT: 'PIVOT'>
PLACEHOLDER = <TokenType.PLACEHOLDER: 'PLACEHOLDER'>
POSITIONAL = <TokenType.POSITIONAL: 'POSITIONAL'>
PRAGMA = <TokenType.PRAGMA: 'PRAGMA'>
PREWHERE = <TokenType.PREWHERE: 'PREWHERE'>
PRIMARY_KEY = <TokenType.PRIMARY_KEY: 'PRIMARY_KEY'>
PROCEDURE = <TokenType.PROCEDURE: 'PROCEDURE'>
PROPERTIES = <TokenType.PROPERTIES: 'PROPERTIES'>
PSEUDO_TYPE = <TokenType.PSEUDO_TYPE: 'PSEUDO_TYPE'>
PUT = <TokenType.PUT: 'PUT'>
QUALIFY = <TokenType.QUALIFY: 'QUALIFY'>
QUOTE = <TokenType.QUOTE: 'QUOTE'>
RANGE = <TokenType.RANGE: 'RANGE'>
RECURSIVE = <TokenType.RECURSIVE: 'RECURSIVE'>
REFRESH = <TokenType.REFRESH: 'REFRESH'>
RENAME = <TokenType.RENAME: 'RENAME'>
REPLACE = <TokenType.REPLACE: 'REPLACE'>
RETURNING = <TokenType.RETURNING: 'RETURNING'>
REVOKE = <TokenType.REVOKE: 'REVOKE'>
REFERENCES = <TokenType.REFERENCES: 'REFERENCES'>
RIGHT = <TokenType.RIGHT: 'RIGHT'>
RLIKE = <TokenType.RLIKE: 'RLIKE'>
ROLLBACK = <TokenType.ROLLBACK: 'ROLLBACK'>
ROLLUP = <TokenType.ROLLUP: 'ROLLUP'>
ROW = <TokenType.ROW: 'ROW'>
ROWS = <TokenType.ROWS: 'ROWS'>
SELECT = <TokenType.SELECT: 'SELECT'>
SEMI = <TokenType.SEMI: 'SEMI'>
SEPARATOR = <TokenType.SEPARATOR: 'SEPARATOR'>
SEQUENCE = <TokenType.SEQUENCE: 'SEQUENCE'>
SERDE_PROPERTIES = <TokenType.SERDE_PROPERTIES: 'SERDE_PROPERTIES'>
SET = <TokenType.SET: 'SET'>
SETTINGS = <TokenType.SETTINGS: 'SETTINGS'>
SHOW = <TokenType.SHOW: 'SHOW'>
SIMILAR_TO = <TokenType.SIMILAR_TO: 'SIMILAR_TO'>
SOME = <TokenType.SOME: 'SOME'>
SORT_BY = <TokenType.SORT_BY: 'SORT_BY'>
START_WITH = <TokenType.START_WITH: 'START_WITH'>
STORAGE_INTEGRATION = <TokenType.STORAGE_INTEGRATION: 'STORAGE_INTEGRATION'>
STRAIGHT_JOIN = <TokenType.STRAIGHT_JOIN: 'STRAIGHT_JOIN'>
STRUCT = <TokenType.STRUCT: 'STRUCT'>
SUMMARIZE = <TokenType.SUMMARIZE: 'SUMMARIZE'>
TABLE_SAMPLE = <TokenType.TABLE_SAMPLE: 'TABLE_SAMPLE'>
TAG = <TokenType.TAG: 'TAG'>
TEMPORARY = <TokenType.TEMPORARY: 'TEMPORARY'>
TOP = <TokenType.TOP: 'TOP'>
THEN = <TokenType.THEN: 'THEN'>
TRUE = <TokenType.TRUE: 'TRUE'>
TRUNCATE = <TokenType.TRUNCATE: 'TRUNCATE'>
UNCACHE = <TokenType.UNCACHE: 'UNCACHE'>
UNION = <TokenType.UNION: 'UNION'>
UNNEST = <TokenType.UNNEST: 'UNNEST'>
UNPIVOT = <TokenType.UNPIVOT: 'UNPIVOT'>
UPDATE = <TokenType.UPDATE: 'UPDATE'>
USE = <TokenType.USE: 'USE'>
USING = <TokenType.USING: 'USING'>
VALUES = <TokenType.VALUES: 'VALUES'>
VIEW = <TokenType.VIEW: 'VIEW'>
SEMANTIC_VIEW = <TokenType.SEMANTIC_VIEW: 'SEMANTIC_VIEW'>
VOLATILE = <TokenType.VOLATILE: 'VOLATILE'>
WHEN = <TokenType.WHEN: 'WHEN'>
WHERE = <TokenType.WHERE: 'WHERE'>
WINDOW = <TokenType.WINDOW: 'WINDOW'>
WITH = <TokenType.WITH: 'WITH'>
UNIQUE = <TokenType.UNIQUE: 'UNIQUE'>
VERSION_SNAPSHOT = <TokenType.VERSION_SNAPSHOT: 'VERSION_SNAPSHOT'>
TIMESTAMP_SNAPSHOT = <TokenType.TIMESTAMP_SNAPSHOT: 'TIMESTAMP_SNAPSHOT'>
OPTION = <TokenType.OPTION: 'OPTION'>
SINK = <TokenType.SINK: 'SINK'>
SOURCE = <TokenType.SOURCE: 'SOURCE'>
ANALYZE = <TokenType.ANALYZE: 'ANALYZE'>
NAMESPACE = <TokenType.NAMESPACE: 'NAMESPACE'>
EXPORT = <TokenType.EXPORT: 'EXPORT'>
HIVE_TOKEN_STREAM = <TokenType.HIVE_TOKEN_STREAM: 'HIVE_TOKEN_STREAM'>
class Token:
444class Token:
445    __slots__ = ("token_type", "text", "line", "col", "start", "end", "comments")
446
447    @classmethod
448    def number(cls, number: int) -> Token:
449        """Returns a NUMBER token with `number` as its text."""
450        return cls(TokenType.NUMBER, str(number))
451
452    @classmethod
453    def string(cls, string: str) -> Token:
454        """Returns a STRING token with `string` as its text."""
455        return cls(TokenType.STRING, string)
456
457    @classmethod
458    def identifier(cls, identifier: str) -> Token:
459        """Returns an IDENTIFIER token with `identifier` as its text."""
460        return cls(TokenType.IDENTIFIER, identifier)
461
462    @classmethod
463    def var(cls, var: str) -> Token:
464        """Returns an VAR token with `var` as its text."""
465        return cls(TokenType.VAR, var)
466
467    def __init__(
468        self,
469        token_type: TokenType,
470        text: str,
471        line: int = 1,
472        col: int = 1,
473        start: int = 0,
474        end: int = 0,
475        comments: t.Optional[t.List[str]] = None,
476    ) -> None:
477        """Token initializer.
478
479        Args:
480            token_type: The TokenType Enum.
481            text: The text of the token.
482            line: The line that the token ends on.
483            col: The column that the token ends on.
484            start: The start index of the token.
485            end: The ending index of the token.
486            comments: The comments to attach to the token.
487        """
488        self.token_type = token_type
489        self.text = text
490        self.line = line
491        self.col = col
492        self.start = start
493        self.end = end
494        self.comments = [] if comments is None else comments
495
496    def __repr__(self) -> str:
497        attributes = ", ".join(f"{k}: {getattr(self, k)}" for k in self.__slots__)
498        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)
467    def __init__(
468        self,
469        token_type: TokenType,
470        text: str,
471        line: int = 1,
472        col: int = 1,
473        start: int = 0,
474        end: int = 0,
475        comments: t.Optional[t.List[str]] = None,
476    ) -> None:
477        """Token initializer.
478
479        Args:
480            token_type: The TokenType Enum.
481            text: The text of the token.
482            line: The line that the token ends on.
483            col: The column that the token ends on.
484            start: The start index of the token.
485            end: The ending index of the token.
486            comments: The comments to attach to the token.
487        """
488        self.token_type = token_type
489        self.text = text
490        self.line = line
491        self.col = col
492        self.start = start
493        self.end = end
494        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:
447    @classmethod
448    def number(cls, number: int) -> Token:
449        """Returns a NUMBER token with `number` as its text."""
450        return cls(TokenType.NUMBER, str(number))

Returns a NUMBER token with number as its text.

@classmethod
def string(cls, string: str) -> Token:
452    @classmethod
453    def string(cls, string: str) -> Token:
454        """Returns a STRING token with `string` as its text."""
455        return cls(TokenType.STRING, string)

Returns a STRING token with string as its text.

@classmethod
def identifier(cls, identifier: str) -> Token:
457    @classmethod
458    def identifier(cls, identifier: str) -> Token:
459        """Returns an IDENTIFIER token with `identifier` as its text."""
460        return cls(TokenType.IDENTIFIER, identifier)

Returns an IDENTIFIER token with identifier as its text.

@classmethod
def var(cls, var: str) -> Token:
462    @classmethod
463    def var(cls, var: str) -> Token:
464        """Returns an VAR token with `var` as its text."""
465        return cls(TokenType.VAR, var)

Returns an VAR token with var as its text.

token_type
text
line
col
start
end
comments
class Tokenizer:
 608class Tokenizer(metaclass=_Tokenizer):
 609    SINGLE_TOKENS = {
 610        "(": TokenType.L_PAREN,
 611        ")": TokenType.R_PAREN,
 612        "[": TokenType.L_BRACKET,
 613        "]": TokenType.R_BRACKET,
 614        "{": TokenType.L_BRACE,
 615        "}": TokenType.R_BRACE,
 616        "&": TokenType.AMP,
 617        "^": TokenType.CARET,
 618        ":": TokenType.COLON,
 619        ",": TokenType.COMMA,
 620        ".": TokenType.DOT,
 621        "-": TokenType.DASH,
 622        "=": TokenType.EQ,
 623        ">": TokenType.GT,
 624        "<": TokenType.LT,
 625        "%": TokenType.MOD,
 626        "!": TokenType.NOT,
 627        "|": TokenType.PIPE,
 628        "+": TokenType.PLUS,
 629        ";": TokenType.SEMICOLON,
 630        "/": TokenType.SLASH,
 631        "\\": TokenType.BACKSLASH,
 632        "*": TokenType.STAR,
 633        "~": TokenType.TILDA,
 634        "?": TokenType.PLACEHOLDER,
 635        "@": TokenType.PARAMETER,
 636        "#": TokenType.HASH,
 637        # Used for breaking a var like x'y' but nothing else the token type doesn't matter
 638        "'": TokenType.UNKNOWN,
 639        "`": TokenType.UNKNOWN,
 640        '"': TokenType.UNKNOWN,
 641    }
 642
 643    BIT_STRINGS: t.List[str | t.Tuple[str, str]] = []
 644    BYTE_STRINGS: t.List[str | t.Tuple[str, str]] = []
 645    HEX_STRINGS: t.List[str | t.Tuple[str, str]] = []
 646    RAW_STRINGS: t.List[str | t.Tuple[str, str]] = []
 647    HEREDOC_STRINGS: t.List[str | t.Tuple[str, str]] = []
 648    UNICODE_STRINGS: t.List[str | t.Tuple[str, str]] = []
 649    IDENTIFIERS: t.List[str | t.Tuple[str, str]] = ['"']
 650    QUOTES: t.List[t.Tuple[str, str] | str] = ["'"]
 651    STRING_ESCAPES = ["'"]
 652    VAR_SINGLE_TOKENS: t.Set[str] = set()
 653
 654    # The strings in this list can always be used as escapes, regardless of the surrounding
 655    # identifier delimiters. By default, the closing delimiter is assumed to also act as an
 656    # identifier escape, e.g. if we use double-quotes, then they also act as escapes: "x"""
 657    IDENTIFIER_ESCAPES: t.List[str] = []
 658
 659    # Whether the heredoc tags follow the same lexical rules as unquoted identifiers
 660    HEREDOC_TAG_IS_IDENTIFIER = False
 661
 662    # Token that we'll generate as a fallback if the heredoc prefix doesn't correspond to a heredoc
 663    HEREDOC_STRING_ALTERNATIVE = TokenType.VAR
 664
 665    # Whether string escape characters function as such when placed within raw strings
 666    STRING_ESCAPES_ALLOWED_IN_RAW_STRINGS = True
 667
 668    NESTED_COMMENTS = True
 669
 670    HINT_START = "/*+"
 671
 672    TOKENS_PRECEDING_HINT = {TokenType.SELECT, TokenType.INSERT, TokenType.UPDATE, TokenType.DELETE}
 673
 674    # Autofilled
 675    _COMMENTS: t.Dict[str, str] = {}
 676    _FORMAT_STRINGS: t.Dict[str, t.Tuple[str, TokenType]] = {}
 677    _IDENTIFIERS: t.Dict[str, str] = {}
 678    _IDENTIFIER_ESCAPES: t.Set[str] = set()
 679    _QUOTES: t.Dict[str, str] = {}
 680    _STRING_ESCAPES: t.Set[str] = set()
 681    _KEYWORD_TRIE: t.Dict = {}
 682    _RS_TOKENIZER: t.Optional[t.Any] = None
 683
 684    KEYWORDS: t.Dict[str, TokenType] = {
 685        **{f"{{%{postfix}": TokenType.BLOCK_START for postfix in ("", "+", "-")},
 686        **{f"{prefix}%}}": TokenType.BLOCK_END for prefix in ("", "+", "-")},
 687        **{f"{{{{{postfix}": TokenType.BLOCK_START for postfix in ("+", "-")},
 688        **{f"{prefix}}}}}": TokenType.BLOCK_END for prefix in ("+", "-")},
 689        HINT_START: TokenType.HINT,
 690        "==": TokenType.EQ,
 691        "::": TokenType.DCOLON,
 692        "||": TokenType.DPIPE,
 693        "|>": TokenType.PIPE_GT,
 694        ">=": TokenType.GTE,
 695        "<=": TokenType.LTE,
 696        "<>": TokenType.NEQ,
 697        "!=": TokenType.NEQ,
 698        ":=": TokenType.COLON_EQ,
 699        "<=>": TokenType.NULLSAFE_EQ,
 700        "->": TokenType.ARROW,
 701        "->>": TokenType.DARROW,
 702        "=>": TokenType.FARROW,
 703        "#>": TokenType.HASH_ARROW,
 704        "#>>": TokenType.DHASH_ARROW,
 705        "<->": TokenType.LR_ARROW,
 706        "&&": TokenType.DAMP,
 707        "??": TokenType.DQMARK,
 708        "~~~": TokenType.GLOB,
 709        "~~": TokenType.LIKE,
 710        "~~*": TokenType.ILIKE,
 711        "~*": TokenType.IRLIKE,
 712        "ALL": TokenType.ALL,
 713        "ALWAYS": TokenType.ALWAYS,
 714        "AND": TokenType.AND,
 715        "ANTI": TokenType.ANTI,
 716        "ANY": TokenType.ANY,
 717        "ASC": TokenType.ASC,
 718        "AS": TokenType.ALIAS,
 719        "ASOF": TokenType.ASOF,
 720        "AUTOINCREMENT": TokenType.AUTO_INCREMENT,
 721        "AUTO_INCREMENT": TokenType.AUTO_INCREMENT,
 722        "BEGIN": TokenType.BEGIN,
 723        "BETWEEN": TokenType.BETWEEN,
 724        "CACHE": TokenType.CACHE,
 725        "UNCACHE": TokenType.UNCACHE,
 726        "CASE": TokenType.CASE,
 727        "CHARACTER SET": TokenType.CHARACTER_SET,
 728        "CLUSTER BY": TokenType.CLUSTER_BY,
 729        "COLLATE": TokenType.COLLATE,
 730        "COLUMN": TokenType.COLUMN,
 731        "COMMIT": TokenType.COMMIT,
 732        "CONNECT BY": TokenType.CONNECT_BY,
 733        "CONSTRAINT": TokenType.CONSTRAINT,
 734        "COPY": TokenType.COPY,
 735        "CREATE": TokenType.CREATE,
 736        "CROSS": TokenType.CROSS,
 737        "CUBE": TokenType.CUBE,
 738        "CURRENT_DATE": TokenType.CURRENT_DATE,
 739        "CURRENT_SCHEMA": TokenType.CURRENT_SCHEMA,
 740        "CURRENT_TIME": TokenType.CURRENT_TIME,
 741        "CURRENT_TIMESTAMP": TokenType.CURRENT_TIMESTAMP,
 742        "CURRENT_USER": TokenType.CURRENT_USER,
 743        "DATABASE": TokenType.DATABASE,
 744        "DEFAULT": TokenType.DEFAULT,
 745        "DELETE": TokenType.DELETE,
 746        "DESC": TokenType.DESC,
 747        "DESCRIBE": TokenType.DESCRIBE,
 748        "DISTINCT": TokenType.DISTINCT,
 749        "DISTRIBUTE BY": TokenType.DISTRIBUTE_BY,
 750        "DIV": TokenType.DIV,
 751        "DROP": TokenType.DROP,
 752        "ELSE": TokenType.ELSE,
 753        "END": TokenType.END,
 754        "ENUM": TokenType.ENUM,
 755        "ESCAPE": TokenType.ESCAPE,
 756        "EXCEPT": TokenType.EXCEPT,
 757        "EXECUTE": TokenType.EXECUTE,
 758        "EXISTS": TokenType.EXISTS,
 759        "FALSE": TokenType.FALSE,
 760        "FETCH": TokenType.FETCH,
 761        "FILTER": TokenType.FILTER,
 762        "FIRST": TokenType.FIRST,
 763        "FULL": TokenType.FULL,
 764        "FUNCTION": TokenType.FUNCTION,
 765        "FOR": TokenType.FOR,
 766        "FOREIGN KEY": TokenType.FOREIGN_KEY,
 767        "FORMAT": TokenType.FORMAT,
 768        "FROM": TokenType.FROM,
 769        "GEOGRAPHY": TokenType.GEOGRAPHY,
 770        "GEOMETRY": TokenType.GEOMETRY,
 771        "GLOB": TokenType.GLOB,
 772        "GROUP BY": TokenType.GROUP_BY,
 773        "GROUPING SETS": TokenType.GROUPING_SETS,
 774        "HAVING": TokenType.HAVING,
 775        "ILIKE": TokenType.ILIKE,
 776        "IN": TokenType.IN,
 777        "INDEX": TokenType.INDEX,
 778        "INET": TokenType.INET,
 779        "INNER": TokenType.INNER,
 780        "INSERT": TokenType.INSERT,
 781        "INTERVAL": TokenType.INTERVAL,
 782        "INTERSECT": TokenType.INTERSECT,
 783        "INTO": TokenType.INTO,
 784        "IS": TokenType.IS,
 785        "ISNULL": TokenType.ISNULL,
 786        "JOIN": TokenType.JOIN,
 787        "KEEP": TokenType.KEEP,
 788        "KILL": TokenType.KILL,
 789        "LATERAL": TokenType.LATERAL,
 790        "LEFT": TokenType.LEFT,
 791        "LIKE": TokenType.LIKE,
 792        "LIMIT": TokenType.LIMIT,
 793        "LOAD": TokenType.LOAD,
 794        "LOCK": TokenType.LOCK,
 795        "MERGE": TokenType.MERGE,
 796        "NAMESPACE": TokenType.NAMESPACE,
 797        "NATURAL": TokenType.NATURAL,
 798        "NEXT": TokenType.NEXT,
 799        "NOT": TokenType.NOT,
 800        "NOTNULL": TokenType.NOTNULL,
 801        "NULL": TokenType.NULL,
 802        "OBJECT": TokenType.OBJECT,
 803        "OFFSET": TokenType.OFFSET,
 804        "ON": TokenType.ON,
 805        "OR": TokenType.OR,
 806        "XOR": TokenType.XOR,
 807        "ORDER BY": TokenType.ORDER_BY,
 808        "ORDINALITY": TokenType.ORDINALITY,
 809        "OUTER": TokenType.OUTER,
 810        "OVER": TokenType.OVER,
 811        "OVERLAPS": TokenType.OVERLAPS,
 812        "OVERWRITE": TokenType.OVERWRITE,
 813        "PARTITION": TokenType.PARTITION,
 814        "PARTITION BY": TokenType.PARTITION_BY,
 815        "PARTITIONED BY": TokenType.PARTITION_BY,
 816        "PARTITIONED_BY": TokenType.PARTITION_BY,
 817        "PERCENT": TokenType.PERCENT,
 818        "PIVOT": TokenType.PIVOT,
 819        "PRAGMA": TokenType.PRAGMA,
 820        "PRIMARY KEY": TokenType.PRIMARY_KEY,
 821        "PROCEDURE": TokenType.PROCEDURE,
 822        "QUALIFY": TokenType.QUALIFY,
 823        "RANGE": TokenType.RANGE,
 824        "RECURSIVE": TokenType.RECURSIVE,
 825        "REGEXP": TokenType.RLIKE,
 826        "RENAME": TokenType.RENAME,
 827        "REPLACE": TokenType.REPLACE,
 828        "RETURNING": TokenType.RETURNING,
 829        "REFERENCES": TokenType.REFERENCES,
 830        "RIGHT": TokenType.RIGHT,
 831        "RLIKE": TokenType.RLIKE,
 832        "ROLLBACK": TokenType.ROLLBACK,
 833        "ROLLUP": TokenType.ROLLUP,
 834        "ROW": TokenType.ROW,
 835        "ROWS": TokenType.ROWS,
 836        "SCHEMA": TokenType.SCHEMA,
 837        "SELECT": TokenType.SELECT,
 838        "SEMI": TokenType.SEMI,
 839        "SET": TokenType.SET,
 840        "SETTINGS": TokenType.SETTINGS,
 841        "SHOW": TokenType.SHOW,
 842        "SIMILAR TO": TokenType.SIMILAR_TO,
 843        "SOME": TokenType.SOME,
 844        "SORT BY": TokenType.SORT_BY,
 845        "START WITH": TokenType.START_WITH,
 846        "STRAIGHT_JOIN": TokenType.STRAIGHT_JOIN,
 847        "TABLE": TokenType.TABLE,
 848        "TABLESAMPLE": TokenType.TABLE_SAMPLE,
 849        "TEMP": TokenType.TEMPORARY,
 850        "TEMPORARY": TokenType.TEMPORARY,
 851        "THEN": TokenType.THEN,
 852        "TRUE": TokenType.TRUE,
 853        "TRUNCATE": TokenType.TRUNCATE,
 854        "UNION": TokenType.UNION,
 855        "UNKNOWN": TokenType.UNKNOWN,
 856        "UNNEST": TokenType.UNNEST,
 857        "UNPIVOT": TokenType.UNPIVOT,
 858        "UPDATE": TokenType.UPDATE,
 859        "USE": TokenType.USE,
 860        "USING": TokenType.USING,
 861        "UUID": TokenType.UUID,
 862        "VALUES": TokenType.VALUES,
 863        "VIEW": TokenType.VIEW,
 864        "VOLATILE": TokenType.VOLATILE,
 865        "WHEN": TokenType.WHEN,
 866        "WHERE": TokenType.WHERE,
 867        "WINDOW": TokenType.WINDOW,
 868        "WITH": TokenType.WITH,
 869        "APPLY": TokenType.APPLY,
 870        "ARRAY": TokenType.ARRAY,
 871        "BIT": TokenType.BIT,
 872        "BOOL": TokenType.BOOLEAN,
 873        "BOOLEAN": TokenType.BOOLEAN,
 874        "BYTE": TokenType.TINYINT,
 875        "MEDIUMINT": TokenType.MEDIUMINT,
 876        "INT1": TokenType.TINYINT,
 877        "TINYINT": TokenType.TINYINT,
 878        "INT16": TokenType.SMALLINT,
 879        "SHORT": TokenType.SMALLINT,
 880        "SMALLINT": TokenType.SMALLINT,
 881        "HUGEINT": TokenType.INT128,
 882        "UHUGEINT": TokenType.UINT128,
 883        "INT2": TokenType.SMALLINT,
 884        "INTEGER": TokenType.INT,
 885        "INT": TokenType.INT,
 886        "INT4": TokenType.INT,
 887        "INT32": TokenType.INT,
 888        "INT64": TokenType.BIGINT,
 889        "INT128": TokenType.INT128,
 890        "INT256": TokenType.INT256,
 891        "LONG": TokenType.BIGINT,
 892        "BIGINT": TokenType.BIGINT,
 893        "INT8": TokenType.TINYINT,
 894        "UINT": TokenType.UINT,
 895        "UINT128": TokenType.UINT128,
 896        "UINT256": TokenType.UINT256,
 897        "DEC": TokenType.DECIMAL,
 898        "DECIMAL": TokenType.DECIMAL,
 899        "DECIMAL32": TokenType.DECIMAL32,
 900        "DECIMAL64": TokenType.DECIMAL64,
 901        "DECIMAL128": TokenType.DECIMAL128,
 902        "DECIMAL256": TokenType.DECIMAL256,
 903        "BIGDECIMAL": TokenType.BIGDECIMAL,
 904        "BIGNUMERIC": TokenType.BIGDECIMAL,
 905        "LIST": TokenType.LIST,
 906        "MAP": TokenType.MAP,
 907        "NULLABLE": TokenType.NULLABLE,
 908        "NUMBER": TokenType.DECIMAL,
 909        "NUMERIC": TokenType.DECIMAL,
 910        "FIXED": TokenType.DECIMAL,
 911        "REAL": TokenType.FLOAT,
 912        "FLOAT": TokenType.FLOAT,
 913        "FLOAT4": TokenType.FLOAT,
 914        "FLOAT8": TokenType.DOUBLE,
 915        "DOUBLE": TokenType.DOUBLE,
 916        "DOUBLE PRECISION": TokenType.DOUBLE,
 917        "JSON": TokenType.JSON,
 918        "JSONB": TokenType.JSONB,
 919        "CHAR": TokenType.CHAR,
 920        "CHARACTER": TokenType.CHAR,
 921        "CHAR VARYING": TokenType.VARCHAR,
 922        "CHARACTER VARYING": TokenType.VARCHAR,
 923        "NCHAR": TokenType.NCHAR,
 924        "VARCHAR": TokenType.VARCHAR,
 925        "VARCHAR2": TokenType.VARCHAR,
 926        "NVARCHAR": TokenType.NVARCHAR,
 927        "NVARCHAR2": TokenType.NVARCHAR,
 928        "BPCHAR": TokenType.BPCHAR,
 929        "STR": TokenType.TEXT,
 930        "STRING": TokenType.TEXT,
 931        "TEXT": TokenType.TEXT,
 932        "LONGTEXT": TokenType.LONGTEXT,
 933        "MEDIUMTEXT": TokenType.MEDIUMTEXT,
 934        "TINYTEXT": TokenType.TINYTEXT,
 935        "CLOB": TokenType.TEXT,
 936        "LONGVARCHAR": TokenType.TEXT,
 937        "BINARY": TokenType.BINARY,
 938        "BLOB": TokenType.VARBINARY,
 939        "LONGBLOB": TokenType.LONGBLOB,
 940        "MEDIUMBLOB": TokenType.MEDIUMBLOB,
 941        "TINYBLOB": TokenType.TINYBLOB,
 942        "BYTEA": TokenType.VARBINARY,
 943        "VARBINARY": TokenType.VARBINARY,
 944        "TIME": TokenType.TIME,
 945        "TIMETZ": TokenType.TIMETZ,
 946        "TIMESTAMP": TokenType.TIMESTAMP,
 947        "TIMESTAMPTZ": TokenType.TIMESTAMPTZ,
 948        "TIMESTAMPLTZ": TokenType.TIMESTAMPLTZ,
 949        "TIMESTAMP_LTZ": TokenType.TIMESTAMPLTZ,
 950        "TIMESTAMPNTZ": TokenType.TIMESTAMPNTZ,
 951        "TIMESTAMP_NTZ": TokenType.TIMESTAMPNTZ,
 952        "DATE": TokenType.DATE,
 953        "DATETIME": TokenType.DATETIME,
 954        "INT4RANGE": TokenType.INT4RANGE,
 955        "INT4MULTIRANGE": TokenType.INT4MULTIRANGE,
 956        "INT8RANGE": TokenType.INT8RANGE,
 957        "INT8MULTIRANGE": TokenType.INT8MULTIRANGE,
 958        "NUMRANGE": TokenType.NUMRANGE,
 959        "NUMMULTIRANGE": TokenType.NUMMULTIRANGE,
 960        "TSRANGE": TokenType.TSRANGE,
 961        "TSMULTIRANGE": TokenType.TSMULTIRANGE,
 962        "TSTZRANGE": TokenType.TSTZRANGE,
 963        "TSTZMULTIRANGE": TokenType.TSTZMULTIRANGE,
 964        "DATERANGE": TokenType.DATERANGE,
 965        "DATEMULTIRANGE": TokenType.DATEMULTIRANGE,
 966        "UNIQUE": TokenType.UNIQUE,
 967        "VECTOR": TokenType.VECTOR,
 968        "STRUCT": TokenType.STRUCT,
 969        "SEQUENCE": TokenType.SEQUENCE,
 970        "VARIANT": TokenType.VARIANT,
 971        "ALTER": TokenType.ALTER,
 972        "ANALYZE": TokenType.ANALYZE,
 973        "CALL": TokenType.COMMAND,
 974        "COMMENT": TokenType.COMMENT,
 975        "EXPLAIN": TokenType.COMMAND,
 976        "GRANT": TokenType.GRANT,
 977        "REVOKE": TokenType.REVOKE,
 978        "OPTIMIZE": TokenType.COMMAND,
 979        "PREPARE": TokenType.COMMAND,
 980        "VACUUM": TokenType.COMMAND,
 981        "USER-DEFINED": TokenType.USERDEFINED,
 982        "FOR VERSION": TokenType.VERSION_SNAPSHOT,
 983        "FOR TIMESTAMP": TokenType.TIMESTAMP_SNAPSHOT,
 984    }
 985
 986    WHITE_SPACE: t.Dict[t.Optional[str], TokenType] = {
 987        " ": TokenType.SPACE,
 988        "\t": TokenType.SPACE,
 989        "\n": TokenType.BREAK,
 990        "\r": TokenType.BREAK,
 991    }
 992
 993    COMMANDS = {
 994        TokenType.COMMAND,
 995        TokenType.EXECUTE,
 996        TokenType.FETCH,
 997        TokenType.SHOW,
 998        TokenType.RENAME,
 999    }
1000
1001    COMMAND_PREFIX_TOKENS = {TokenType.SEMICOLON, TokenType.BEGIN}
1002
1003    # Handle numeric literals like in hive (3L = BIGINT)
1004    NUMERIC_LITERALS: t.Dict[str, str] = {}
1005
1006    COMMENTS = ["--", ("/*", "*/")]
1007
1008    __slots__ = (
1009        "sql",
1010        "size",
1011        "tokens",
1012        "dialect",
1013        "use_rs_tokenizer",
1014        "_start",
1015        "_current",
1016        "_line",
1017        "_col",
1018        "_comments",
1019        "_char",
1020        "_end",
1021        "_peek",
1022        "_prev_token_line",
1023        "_rs_dialect_settings",
1024    )
1025
1026    def __init__(
1027        self,
1028        dialect: DialectType = None,
1029        use_rs_tokenizer: t.Optional[bool] = None,
1030        **opts: t.Any,
1031    ) -> None:
1032        from sqlglot.dialects import Dialect
1033
1034        self.dialect = Dialect.get_or_raise(dialect)
1035
1036        # initialize `use_rs_tokenizer`, and allow it to be overwritten per Tokenizer instance
1037        self.use_rs_tokenizer = (
1038            use_rs_tokenizer if use_rs_tokenizer is not None else USE_RS_TOKENIZER
1039        )
1040
1041        if self.use_rs_tokenizer:
1042            self._rs_dialect_settings = RsTokenizerDialectSettings(
1043                unescaped_sequences=self.dialect.UNESCAPED_SEQUENCES,
1044                identifiers_can_start_with_digit=self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT,
1045                numbers_can_be_underscore_separated=self.dialect.NUMBERS_CAN_BE_UNDERSCORE_SEPARATED,
1046            )
1047
1048        self.reset()
1049
1050    def reset(self) -> None:
1051        self.sql = ""
1052        self.size = 0
1053        self.tokens: t.List[Token] = []
1054        self._start = 0
1055        self._current = 0
1056        self._line = 1
1057        self._col = 0
1058        self._comments: t.List[str] = []
1059
1060        self._char = ""
1061        self._end = False
1062        self._peek = ""
1063        self._prev_token_line = -1
1064
1065    def tokenize(self, sql: str) -> t.List[Token]:
1066        """Returns a list of tokens corresponding to the SQL string `sql`."""
1067        if self.use_rs_tokenizer:
1068            return self.tokenize_rs(sql)
1069
1070        self.reset()
1071        self.sql = sql
1072        self.size = len(sql)
1073
1074        try:
1075            self._scan()
1076        except Exception as e:
1077            start = max(self._current - 50, 0)
1078            end = min(self._current + 50, self.size - 1)
1079            context = self.sql[start:end]
1080            raise TokenError(f"Error tokenizing '{context}'") from e
1081
1082        return self.tokens
1083
1084    def _scan(self, until: t.Optional[t.Callable] = None) -> None:
1085        while self.size and not self._end:
1086            current = self._current
1087
1088            # Skip spaces here rather than iteratively calling advance() for performance reasons
1089            while current < self.size:
1090                char = self.sql[current]
1091
1092                if char.isspace() and (char == " " or char == "\t"):
1093                    current += 1
1094                else:
1095                    break
1096
1097            offset = current - self._current if current > self._current else 1
1098
1099            self._start = current
1100            self._advance(offset)
1101
1102            if not self._char.isspace():
1103                if self._char.isdigit():
1104                    self._scan_number()
1105                elif self._char in self._IDENTIFIERS:
1106                    self._scan_identifier(self._IDENTIFIERS[self._char])
1107                else:
1108                    self._scan_keywords()
1109
1110            if until and until():
1111                break
1112
1113        if self.tokens and self._comments:
1114            self.tokens[-1].comments.extend(self._comments)
1115
1116    def _chars(self, size: int) -> str:
1117        if size == 1:
1118            return self._char
1119
1120        start = self._current - 1
1121        end = start + size
1122
1123        return self.sql[start:end] if end <= self.size else ""
1124
1125    def _advance(self, i: int = 1, alnum: bool = False) -> None:
1126        if self.WHITE_SPACE.get(self._char) is TokenType.BREAK:
1127            # Ensures we don't count an extra line if we get a \r\n line break sequence
1128            if not (self._char == "\r" and self._peek == "\n"):
1129                self._col = i
1130                self._line += 1
1131        else:
1132            self._col += i
1133
1134        self._current += i
1135        self._end = self._current >= self.size
1136        self._char = self.sql[self._current - 1]
1137        self._peek = "" if self._end else self.sql[self._current]
1138
1139        if alnum and self._char.isalnum():
1140            # Here we use local variables instead of attributes for better performance
1141            _col = self._col
1142            _current = self._current
1143            _end = self._end
1144            _peek = self._peek
1145
1146            while _peek.isalnum():
1147                _col += 1
1148                _current += 1
1149                _end = _current >= self.size
1150                _peek = "" if _end else self.sql[_current]
1151
1152            self._col = _col
1153            self._current = _current
1154            self._end = _end
1155            self._peek = _peek
1156            self._char = self.sql[_current - 1]
1157
1158    @property
1159    def _text(self) -> str:
1160        return self.sql[self._start : self._current]
1161
1162    def _add(self, token_type: TokenType, text: t.Optional[str] = None) -> None:
1163        self._prev_token_line = self._line
1164
1165        if self._comments and token_type == TokenType.SEMICOLON and self.tokens:
1166            self.tokens[-1].comments.extend(self._comments)
1167            self._comments = []
1168
1169        self.tokens.append(
1170            Token(
1171                token_type,
1172                text=self._text if text is None else text,
1173                line=self._line,
1174                col=self._col,
1175                start=self._start,
1176                end=self._current - 1,
1177                comments=self._comments,
1178            )
1179        )
1180        self._comments = []
1181
1182        # If we have either a semicolon or a begin token before the command's token, we'll parse
1183        # whatever follows the command's token as a string
1184        if (
1185            token_type in self.COMMANDS
1186            and self._peek != ";"
1187            and (len(self.tokens) == 1 or self.tokens[-2].token_type in self.COMMAND_PREFIX_TOKENS)
1188        ):
1189            start = self._current
1190            tokens = len(self.tokens)
1191            self._scan(lambda: self._peek == ";")
1192            self.tokens = self.tokens[:tokens]
1193            text = self.sql[start : self._current].strip()
1194            if text:
1195                self._add(TokenType.STRING, text)
1196
1197    def _scan_keywords(self) -> None:
1198        size = 0
1199        word = None
1200        chars = self._text
1201        char = chars
1202        prev_space = False
1203        skip = False
1204        trie = self._KEYWORD_TRIE
1205        single_token = char in self.SINGLE_TOKENS
1206
1207        while chars:
1208            if skip:
1209                result = TrieResult.PREFIX
1210            else:
1211                result, trie = in_trie(trie, char.upper())
1212
1213            if result == TrieResult.FAILED:
1214                break
1215            if result == TrieResult.EXISTS:
1216                word = chars
1217
1218            end = self._current + size
1219            size += 1
1220
1221            if end < self.size:
1222                char = self.sql[end]
1223                single_token = single_token or char in self.SINGLE_TOKENS
1224                is_space = char.isspace()
1225
1226                if not is_space or not prev_space:
1227                    if is_space:
1228                        char = " "
1229                    chars += char
1230                    prev_space = is_space
1231                    skip = False
1232                else:
1233                    skip = True
1234            else:
1235                char = ""
1236                break
1237
1238        if word:
1239            if self._scan_string(word):
1240                return
1241            if self._scan_comment(word):
1242                return
1243            if prev_space or single_token or not char:
1244                self._advance(size - 1)
1245                word = word.upper()
1246                self._add(self.KEYWORDS[word], text=word)
1247                return
1248
1249        if self._char in self.SINGLE_TOKENS:
1250            self._add(self.SINGLE_TOKENS[self._char], text=self._char)
1251            return
1252
1253        self._scan_var()
1254
1255    def _scan_comment(self, comment_start: str) -> bool:
1256        if comment_start not in self._COMMENTS:
1257            return False
1258
1259        comment_start_line = self._line
1260        comment_start_size = len(comment_start)
1261        comment_end = self._COMMENTS[comment_start]
1262
1263        if comment_end:
1264            # Skip the comment's start delimiter
1265            self._advance(comment_start_size)
1266
1267            comment_count = 1
1268            comment_end_size = len(comment_end)
1269
1270            while not self._end:
1271                if self._chars(comment_end_size) == comment_end:
1272                    comment_count -= 1
1273                    if not comment_count:
1274                        break
1275
1276                self._advance(alnum=True)
1277
1278                # Nested comments are allowed by some dialects, e.g. databricks, duckdb, postgres
1279                if (
1280                    self.NESTED_COMMENTS
1281                    and not self._end
1282                    and self._chars(comment_end_size) == comment_start
1283                ):
1284                    self._advance(comment_start_size)
1285                    comment_count += 1
1286
1287            self._comments.append(self._text[comment_start_size : -comment_end_size + 1])
1288            self._advance(comment_end_size - 1)
1289        else:
1290            while not self._end and self.WHITE_SPACE.get(self._peek) is not TokenType.BREAK:
1291                self._advance(alnum=True)
1292            self._comments.append(self._text[comment_start_size:])
1293
1294        if (
1295            comment_start == self.HINT_START
1296            and self.tokens
1297            and self.tokens[-1].token_type in self.TOKENS_PRECEDING_HINT
1298        ):
1299            self._add(TokenType.HINT)
1300
1301        # Leading comment is attached to the succeeding token, whilst trailing comment to the preceding.
1302        # Multiple consecutive comments are preserved by appending them to the current comments list.
1303        if comment_start_line == self._prev_token_line:
1304            self.tokens[-1].comments.extend(self._comments)
1305            self._comments = []
1306            self._prev_token_line = self._line
1307
1308        return True
1309
1310    def _scan_number(self) -> None:
1311        if self._char == "0":
1312            peek = self._peek.upper()
1313            if peek == "B":
1314                return self._scan_bits() if self.BIT_STRINGS else self._add(TokenType.NUMBER)
1315            elif peek == "X":
1316                return self._scan_hex() if self.HEX_STRINGS else self._add(TokenType.NUMBER)
1317
1318        decimal = False
1319        scientific = 0
1320
1321        while True:
1322            if self._peek.isdigit():
1323                self._advance()
1324            elif self._peek == "." and not decimal:
1325                if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER:
1326                    return self._add(TokenType.NUMBER)
1327                decimal = True
1328                self._advance()
1329            elif self._peek in ("-", "+") and scientific == 1:
1330                scientific += 1
1331                self._advance()
1332            elif self._peek.upper() == "E" and not scientific:
1333                scientific += 1
1334                self._advance()
1335            elif self._peek.isidentifier():
1336                number_text = self._text
1337                literal = ""
1338
1339                while self._peek.strip() and self._peek not in self.SINGLE_TOKENS:
1340                    literal += self._peek
1341                    self._advance()
1342
1343                token_type = self.KEYWORDS.get(self.NUMERIC_LITERALS.get(literal.upper(), ""))
1344
1345                if token_type:
1346                    self._add(TokenType.NUMBER, number_text)
1347                    self._add(TokenType.DCOLON, "::")
1348                    return self._add(token_type, literal)
1349                else:
1350                    replaced = literal.replace("_", "")
1351                    if self.dialect.NUMBERS_CAN_BE_UNDERSCORE_SEPARATED and replaced.isdigit():
1352                        return self._add(TokenType.NUMBER, number_text + replaced)
1353                    if self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT:
1354                        return self._add(TokenType.VAR)
1355
1356                self._advance(-len(literal))
1357                return self._add(TokenType.NUMBER, number_text)
1358            else:
1359                return self._add(TokenType.NUMBER)
1360
1361    def _scan_bits(self) -> None:
1362        self._advance()
1363        value = self._extract_value()
1364        try:
1365            # If `value` can't be converted to a binary, fallback to tokenizing it as an identifier
1366            int(value, 2)
1367            self._add(TokenType.BIT_STRING, value[2:])  # Drop the 0b
1368        except ValueError:
1369            self._add(TokenType.IDENTIFIER)
1370
1371    def _scan_hex(self) -> None:
1372        self._advance()
1373        value = self._extract_value()
1374        try:
1375            # If `value` can't be converted to a hex, fallback to tokenizing it as an identifier
1376            int(value, 16)
1377            self._add(TokenType.HEX_STRING, value[2:])  # Drop the 0x
1378        except ValueError:
1379            self._add(TokenType.IDENTIFIER)
1380
1381    def _extract_value(self) -> str:
1382        while True:
1383            char = self._peek.strip()
1384            if char and char not in self.SINGLE_TOKENS:
1385                self._advance(alnum=True)
1386            else:
1387                break
1388
1389        return self._text
1390
1391    def _scan_string(self, start: str) -> bool:
1392        base = None
1393        token_type = TokenType.STRING
1394
1395        if start in self._QUOTES:
1396            end = self._QUOTES[start]
1397        elif start in self._FORMAT_STRINGS:
1398            end, token_type = self._FORMAT_STRINGS[start]
1399
1400            if token_type == TokenType.HEX_STRING:
1401                base = 16
1402            elif token_type == TokenType.BIT_STRING:
1403                base = 2
1404            elif token_type == TokenType.HEREDOC_STRING:
1405                self._advance()
1406
1407                if self._char == end:
1408                    tag = ""
1409                else:
1410                    tag = self._extract_string(
1411                        end,
1412                        raw_string=True,
1413                        raise_unmatched=not self.HEREDOC_TAG_IS_IDENTIFIER,
1414                    )
1415
1416                if tag and self.HEREDOC_TAG_IS_IDENTIFIER and (self._end or not tag.isidentifier()):
1417                    if not self._end:
1418                        self._advance(-1)
1419
1420                    self._advance(-len(tag))
1421                    self._add(self.HEREDOC_STRING_ALTERNATIVE)
1422                    return True
1423
1424                end = f"{start}{tag}{end}"
1425        else:
1426            return False
1427
1428        self._advance(len(start))
1429        text = self._extract_string(end, raw_string=token_type == TokenType.RAW_STRING)
1430
1431        if base and text:
1432            try:
1433                int(text, base)
1434            except Exception:
1435                raise TokenError(
1436                    f"Numeric string contains invalid characters from {self._line}:{self._start}"
1437                )
1438
1439        self._add(token_type, text)
1440        return True
1441
1442    def _scan_identifier(self, identifier_end: str) -> None:
1443        self._advance()
1444        text = self._extract_string(
1445            identifier_end, escapes=self._IDENTIFIER_ESCAPES | {identifier_end}
1446        )
1447        self._add(TokenType.IDENTIFIER, text)
1448
1449    def _scan_var(self) -> None:
1450        while True:
1451            char = self._peek.strip()
1452            if char and (char in self.VAR_SINGLE_TOKENS or char not in self.SINGLE_TOKENS):
1453                self._advance(alnum=True)
1454            else:
1455                break
1456
1457        self._add(
1458            TokenType.VAR
1459            if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER
1460            else self.KEYWORDS.get(self._text.upper(), TokenType.VAR)
1461        )
1462
1463    def _extract_string(
1464        self,
1465        delimiter: str,
1466        escapes: t.Optional[t.Set[str]] = None,
1467        raw_string: bool = False,
1468        raise_unmatched: bool = True,
1469    ) -> str:
1470        text = ""
1471        delim_size = len(delimiter)
1472        escapes = self._STRING_ESCAPES if escapes is None else escapes
1473
1474        while True:
1475            if (
1476                not raw_string
1477                and self.dialect.UNESCAPED_SEQUENCES
1478                and self._peek
1479                and self._char in self.STRING_ESCAPES
1480            ):
1481                unescaped_sequence = self.dialect.UNESCAPED_SEQUENCES.get(self._char + self._peek)
1482                if unescaped_sequence:
1483                    self._advance(2)
1484                    text += unescaped_sequence
1485                    continue
1486            if (
1487                (self.STRING_ESCAPES_ALLOWED_IN_RAW_STRINGS or not raw_string)
1488                and self._char in escapes
1489                and (self._peek == delimiter or self._peek in escapes)
1490                and (self._char not in self._QUOTES or self._char == self._peek)
1491            ):
1492                if self._peek == delimiter:
1493                    text += self._peek
1494                else:
1495                    text += self._char + self._peek
1496
1497                if self._current + 1 < self.size:
1498                    self._advance(2)
1499                else:
1500                    raise TokenError(f"Missing {delimiter} from {self._line}:{self._current}")
1501            else:
1502                if self._chars(delim_size) == delimiter:
1503                    if delim_size > 1:
1504                        self._advance(delim_size - 1)
1505                    break
1506
1507                if self._end:
1508                    if not raise_unmatched:
1509                        return text + self._char
1510
1511                    raise TokenError(f"Missing {delimiter} from {self._line}:{self._start}")
1512
1513                current = self._current - 1
1514                self._advance(alnum=True)
1515                text += self.sql[current : self._current - 1]
1516
1517        return text
1518
1519    def tokenize_rs(self, sql: str) -> t.List[Token]:
1520        if not self._RS_TOKENIZER:
1521            raise SqlglotError("Rust tokenizer is not available")
1522
1523        tokens, error_msg = self._RS_TOKENIZER.tokenize(sql, self._rs_dialect_settings)
1524        for token in tokens:
1525            token.token_type = _ALL_TOKEN_TYPES[token.token_type_index]
1526
1527        # Setting this here so partial token lists can be inspected even if there is a failure
1528        self.tokens = tokens
1529
1530        if error_msg is not None:
1531            raise TokenError(error_msg)
1532
1533        return tokens
Tokenizer( dialect: Union[str, sqlglot.dialects.Dialect, Type[sqlglot.dialects.Dialect], NoneType] = None, use_rs_tokenizer: Optional[bool] = None, **opts: Any)
1026    def __init__(
1027        self,
1028        dialect: DialectType = None,
1029        use_rs_tokenizer: t.Optional[bool] = None,
1030        **opts: t.Any,
1031    ) -> None:
1032        from sqlglot.dialects import Dialect
1033
1034        self.dialect = Dialect.get_or_raise(dialect)
1035
1036        # initialize `use_rs_tokenizer`, and allow it to be overwritten per Tokenizer instance
1037        self.use_rs_tokenizer = (
1038            use_rs_tokenizer if use_rs_tokenizer is not None else USE_RS_TOKENIZER
1039        )
1040
1041        if self.use_rs_tokenizer:
1042            self._rs_dialect_settings = RsTokenizerDialectSettings(
1043                unescaped_sequences=self.dialect.UNESCAPED_SEQUENCES,
1044                identifiers_can_start_with_digit=self.dialect.IDENTIFIERS_CAN_START_WITH_DIGIT,
1045                numbers_can_be_underscore_separated=self.dialect.NUMBERS_CAN_BE_UNDERSCORE_SEPARATED,
1046            )
1047
1048        self.reset()
SINGLE_TOKENS = {'(': <TokenType.L_PAREN: 'L_PAREN'>, ')': <TokenType.R_PAREN: 'R_PAREN'>, '[': <TokenType.L_BRACKET: 'L_BRACKET'>, ']': <TokenType.R_BRACKET: 'R_BRACKET'>, '{': <TokenType.L_BRACE: 'L_BRACE'>, '}': <TokenType.R_BRACE: 'R_BRACE'>, '&': <TokenType.AMP: 'AMP'>, '^': <TokenType.CARET: 'CARET'>, ':': <TokenType.COLON: 'COLON'>, ',': <TokenType.COMMA: 'COMMA'>, '.': <TokenType.DOT: 'DOT'>, '-': <TokenType.DASH: 'DASH'>, '=': <TokenType.EQ: 'EQ'>, '>': <TokenType.GT: 'GT'>, '<': <TokenType.LT: 'LT'>, '%': <TokenType.MOD: 'MOD'>, '!': <TokenType.NOT: 'NOT'>, '|': <TokenType.PIPE: 'PIPE'>, '+': <TokenType.PLUS: 'PLUS'>, ';': <TokenType.SEMICOLON: 'SEMICOLON'>, '/': <TokenType.SLASH: 'SLASH'>, '\\': <TokenType.BACKSLASH: 'BACKSLASH'>, '*': <TokenType.STAR: 'STAR'>, '~': <TokenType.TILDA: 'TILDA'>, '?': <TokenType.PLACEHOLDER: 'PLACEHOLDER'>, '@': <TokenType.PARAMETER: 'PARAMETER'>, '#': <TokenType.HASH: 'HASH'>, "'": <TokenType.UNKNOWN: 'UNKNOWN'>, '`': <TokenType.UNKNOWN: 'UNKNOWN'>, '"': <TokenType.UNKNOWN: 'UNKNOWN'>}
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]]] = ['"']
QUOTES: List[Union[str, Tuple[str, str]]] = ["'"]
STRING_ESCAPES = ["'"]
VAR_SINGLE_TOKENS: Set[str] = set()
IDENTIFIER_ESCAPES: List[str] = []
HEREDOC_TAG_IS_IDENTIFIER = False
HEREDOC_STRING_ALTERNATIVE = <TokenType.VAR: 'VAR'>
STRING_ESCAPES_ALLOWED_IN_RAW_STRINGS = True
NESTED_COMMENTS = True
HINT_START = '/*+'
TOKENS_PRECEDING_HINT = {<TokenType.UPDATE: 'UPDATE'>, <TokenType.DELETE: 'DELETE'>, <TokenType.SELECT: 'SELECT'>, <TokenType.INSERT: 'INSERT'>}
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.PIPE_GT: 'PIPE_GT'>, '>=': <TokenType.GTE: 'GTE'>, '<=': <TokenType.LTE: 'LTE'>, '<>': <TokenType.NEQ: 'NEQ'>, '!=': <TokenType.NEQ: 'NEQ'>, ':=': <TokenType.COLON_EQ: 'COLON_EQ'>, '<=>': <TokenType.NULLSAFE_EQ: 'NULLSAFE_EQ'>, '->': <TokenType.ARROW: 'ARROW'>, '->>': <TokenType.DARROW: 'DARROW'>, '=>': <TokenType.FARROW: 'FARROW'>, '#>': <TokenType.HASH_ARROW: 'HASH_ARROW'>, '#>>': <TokenType.DHASH_ARROW: 'DHASH_ARROW'>, '<->': <TokenType.LR_ARROW: 'LR_ARROW'>, '&&': <TokenType.DAMP: 'DAMP'>, '??': <TokenType.DQMARK: 'DQMARK'>, '~~~': <TokenType.GLOB: 'GLOB'>, '~~': <TokenType.LIKE: 'LIKE'>, '~~*': <TokenType.ILIKE: 'ILIKE'>, '~*': <TokenType.IRLIKE: 'IRLIKE'>, 'ALL': <TokenType.ALL: 'ALL'>, 'ALWAYS': <TokenType.ALWAYS: 'ALWAYS'>, 'AND': <TokenType.AND: 'AND'>, 'ANTI': <TokenType.ANTI: 'ANTI'>, 'ANY': <TokenType.ANY: 'ANY'>, 'ASC': <TokenType.ASC: 'ASC'>, 'AS': <TokenType.ALIAS: 'ALIAS'>, 'ASOF': <TokenType.ASOF: 'ASOF'>, 'AUTOINCREMENT': <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, 'AUTO_INCREMENT': <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, 'BEGIN': <TokenType.BEGIN: 'BEGIN'>, 'BETWEEN': <TokenType.BETWEEN: 'BETWEEN'>, 'CACHE': <TokenType.CACHE: 'CACHE'>, 'UNCACHE': <TokenType.UNCACHE: 'UNCACHE'>, 'CASE': <TokenType.CASE: 'CASE'>, 'CHARACTER SET': <TokenType.CHARACTER_SET: 'CHARACTER_SET'>, 'CLUSTER BY': <TokenType.CLUSTER_BY: 'CLUSTER_BY'>, 'COLLATE': <TokenType.COLLATE: 'COLLATE'>, 'COLUMN': <TokenType.COLUMN: 'COLUMN'>, 'COMMIT': <TokenType.COMMIT: 'COMMIT'>, 'CONNECT BY': <TokenType.CONNECT_BY: 'CONNECT_BY'>, 'CONSTRAINT': <TokenType.CONSTRAINT: 'CONSTRAINT'>, 'COPY': <TokenType.COPY: 'COPY'>, 'CREATE': <TokenType.CREATE: 'CREATE'>, 'CROSS': <TokenType.CROSS: 'CROSS'>, 'CUBE': <TokenType.CUBE: 'CUBE'>, 'CURRENT_DATE': <TokenType.CURRENT_DATE: 'CURRENT_DATE'>, 'CURRENT_SCHEMA': <TokenType.CURRENT_SCHEMA: 'CURRENT_SCHEMA'>, 'CURRENT_TIME': <TokenType.CURRENT_TIME: 'CURRENT_TIME'>, 'CURRENT_TIMESTAMP': <TokenType.CURRENT_TIMESTAMP: 'CURRENT_TIMESTAMP'>, 'CURRENT_USER': <TokenType.CURRENT_USER: 'CURRENT_USER'>, 'DATABASE': <TokenType.DATABASE: 'DATABASE'>, 'DEFAULT': <TokenType.DEFAULT: 'DEFAULT'>, 'DELETE': <TokenType.DELETE: 'DELETE'>, 'DESC': <TokenType.DESC: 'DESC'>, 'DESCRIBE': <TokenType.DESCRIBE: 'DESCRIBE'>, 'DISTINCT': <TokenType.DISTINCT: 'DISTINCT'>, 'DISTRIBUTE BY': <TokenType.DISTRIBUTE_BY: 'DISTRIBUTE_BY'>, 'DIV': <TokenType.DIV: 'DIV'>, 'DROP': <TokenType.DROP: 'DROP'>, 'ELSE': <TokenType.ELSE: 'ELSE'>, 'END': <TokenType.END: 'END'>, 'ENUM': <TokenType.ENUM: 'ENUM'>, 'ESCAPE': <TokenType.ESCAPE: 'ESCAPE'>, 'EXCEPT': <TokenType.EXCEPT: 'EXCEPT'>, 'EXECUTE': <TokenType.EXECUTE: 'EXECUTE'>, 'EXISTS': <TokenType.EXISTS: 'EXISTS'>, 'FALSE': <TokenType.FALSE: 'FALSE'>, 'FETCH': <TokenType.FETCH: 'FETCH'>, 'FILTER': <TokenType.FILTER: 'FILTER'>, 'FIRST': <TokenType.FIRST: 'FIRST'>, 'FULL': <TokenType.FULL: 'FULL'>, 'FUNCTION': <TokenType.FUNCTION: 'FUNCTION'>, 'FOR': <TokenType.FOR: 'FOR'>, 'FOREIGN KEY': <TokenType.FOREIGN_KEY: 'FOREIGN_KEY'>, 'FORMAT': <TokenType.FORMAT: 'FORMAT'>, 'FROM': <TokenType.FROM: 'FROM'>, 'GEOGRAPHY': <TokenType.GEOGRAPHY: 'GEOGRAPHY'>, 'GEOMETRY': <TokenType.GEOMETRY: 'GEOMETRY'>, 'GLOB': <TokenType.GLOB: 'GLOB'>, 'GROUP BY': <TokenType.GROUP_BY: 'GROUP_BY'>, 'GROUPING SETS': <TokenType.GROUPING_SETS: 'GROUPING_SETS'>, 'HAVING': <TokenType.HAVING: 'HAVING'>, 'ILIKE': <TokenType.ILIKE: 'ILIKE'>, 'IN': <TokenType.IN: 'IN'>, 'INDEX': <TokenType.INDEX: 'INDEX'>, 'INET': <TokenType.INET: 'INET'>, 'INNER': <TokenType.INNER: 'INNER'>, 'INSERT': <TokenType.INSERT: 'INSERT'>, 'INTERVAL': <TokenType.INTERVAL: 'INTERVAL'>, 'INTERSECT': <TokenType.INTERSECT: 'INTERSECT'>, 'INTO': <TokenType.INTO: 'INTO'>, 'IS': <TokenType.IS: 'IS'>, 'ISNULL': <TokenType.ISNULL: 'ISNULL'>, 'JOIN': <TokenType.JOIN: 'JOIN'>, 'KEEP': <TokenType.KEEP: 'KEEP'>, 'KILL': <TokenType.KILL: 'KILL'>, 'LATERAL': <TokenType.LATERAL: 'LATERAL'>, 'LEFT': <TokenType.LEFT: 'LEFT'>, 'LIKE': <TokenType.LIKE: 'LIKE'>, 'LIMIT': <TokenType.LIMIT: 'LIMIT'>, 'LOAD': <TokenType.LOAD: 'LOAD'>, 'LOCK': <TokenType.LOCK: 'LOCK'>, 'MERGE': <TokenType.MERGE: 'MERGE'>, 'NAMESPACE': <TokenType.NAMESPACE: 'NAMESPACE'>, 'NATURAL': <TokenType.NATURAL: 'NATURAL'>, 'NEXT': <TokenType.NEXT: 'NEXT'>, 'NOT': <TokenType.NOT: 'NOT'>, 'NOTNULL': <TokenType.NOTNULL: 'NOTNULL'>, 'NULL': <TokenType.NULL: 'NULL'>, 'OBJECT': <TokenType.OBJECT: 'OBJECT'>, 'OFFSET': <TokenType.OFFSET: 'OFFSET'>, 'ON': <TokenType.ON: 'ON'>, 'OR': <TokenType.OR: 'OR'>, 'XOR': <TokenType.XOR: 'XOR'>, 'ORDER BY': <TokenType.ORDER_BY: 'ORDER_BY'>, 'ORDINALITY': <TokenType.ORDINALITY: 'ORDINALITY'>, 'OUTER': <TokenType.OUTER: 'OUTER'>, 'OVER': <TokenType.OVER: 'OVER'>, 'OVERLAPS': <TokenType.OVERLAPS: 'OVERLAPS'>, 'OVERWRITE': <TokenType.OVERWRITE: 'OVERWRITE'>, 'PARTITION': <TokenType.PARTITION: 'PARTITION'>, 'PARTITION BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PARTITIONED BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PARTITIONED_BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PERCENT': <TokenType.PERCENT: 'PERCENT'>, 'PIVOT': <TokenType.PIVOT: 'PIVOT'>, 'PRAGMA': <TokenType.PRAGMA: 'PRAGMA'>, 'PRIMARY KEY': <TokenType.PRIMARY_KEY: 'PRIMARY_KEY'>, 'PROCEDURE': <TokenType.PROCEDURE: 'PROCEDURE'>, 'QUALIFY': <TokenType.QUALIFY: 'QUALIFY'>, 'RANGE': <TokenType.RANGE: 'RANGE'>, 'RECURSIVE': <TokenType.RECURSIVE: 'RECURSIVE'>, 'REGEXP': <TokenType.RLIKE: 'RLIKE'>, 'RENAME': <TokenType.RENAME: 'RENAME'>, 'REPLACE': <TokenType.REPLACE: 'REPLACE'>, 'RETURNING': <TokenType.RETURNING: 'RETURNING'>, 'REFERENCES': <TokenType.REFERENCES: 'REFERENCES'>, 'RIGHT': <TokenType.RIGHT: 'RIGHT'>, 'RLIKE': <TokenType.RLIKE: 'RLIKE'>, 'ROLLBACK': <TokenType.ROLLBACK: 'ROLLBACK'>, 'ROLLUP': <TokenType.ROLLUP: 'ROLLUP'>, 'ROW': <TokenType.ROW: 'ROW'>, 'ROWS': <TokenType.ROWS: 'ROWS'>, 'SCHEMA': <TokenType.SCHEMA: 'SCHEMA'>, 'SELECT': <TokenType.SELECT: 'SELECT'>, 'SEMI': <TokenType.SEMI: 'SEMI'>, 'SET': <TokenType.SET: 'SET'>, 'SETTINGS': <TokenType.SETTINGS: 'SETTINGS'>, 'SHOW': <TokenType.SHOW: 'SHOW'>, 'SIMILAR TO': <TokenType.SIMILAR_TO: 'SIMILAR_TO'>, 'SOME': <TokenType.SOME: 'SOME'>, 'SORT BY': <TokenType.SORT_BY: 'SORT_BY'>, 'START WITH': <TokenType.START_WITH: 'START_WITH'>, 'STRAIGHT_JOIN': <TokenType.STRAIGHT_JOIN: 'STRAIGHT_JOIN'>, 'TABLE': <TokenType.TABLE: 'TABLE'>, 'TABLESAMPLE': <TokenType.TABLE_SAMPLE: 'TABLE_SAMPLE'>, 'TEMP': <TokenType.TEMPORARY: 'TEMPORARY'>, 'TEMPORARY': <TokenType.TEMPORARY: 'TEMPORARY'>, 'THEN': <TokenType.THEN: 'THEN'>, 'TRUE': <TokenType.TRUE: 'TRUE'>, 'TRUNCATE': <TokenType.TRUNCATE: 'TRUNCATE'>, 'UNION': <TokenType.UNION: 'UNION'>, 'UNKNOWN': <TokenType.UNKNOWN: 'UNKNOWN'>, 'UNNEST': <TokenType.UNNEST: 'UNNEST'>, 'UNPIVOT': <TokenType.UNPIVOT: 'UNPIVOT'>, 'UPDATE': <TokenType.UPDATE: 'UPDATE'>, 'USE': <TokenType.USE: 'USE'>, 'USING': <TokenType.USING: 'USING'>, 'UUID': <TokenType.UUID: 'UUID'>, 'VALUES': <TokenType.VALUES: 'VALUES'>, 'VIEW': <TokenType.VIEW: 'VIEW'>, 'VOLATILE': <TokenType.VOLATILE: 'VOLATILE'>, 'WHEN': <TokenType.WHEN: 'WHEN'>, 'WHERE': <TokenType.WHERE: 'WHERE'>, 'WINDOW': <TokenType.WINDOW: 'WINDOW'>, 'WITH': <TokenType.WITH: 'WITH'>, 'APPLY': <TokenType.APPLY: 'APPLY'>, 'ARRAY': <TokenType.ARRAY: 'ARRAY'>, 'BIT': <TokenType.BIT: 'BIT'>, 'BOOL': <TokenType.BOOLEAN: 'BOOLEAN'>, 'BOOLEAN': <TokenType.BOOLEAN: 'BOOLEAN'>, 'BYTE': <TokenType.TINYINT: 'TINYINT'>, 'MEDIUMINT': <TokenType.MEDIUMINT: 'MEDIUMINT'>, 'INT1': <TokenType.TINYINT: 'TINYINT'>, 'TINYINT': <TokenType.TINYINT: 'TINYINT'>, 'INT16': <TokenType.SMALLINT: 'SMALLINT'>, 'SHORT': <TokenType.SMALLINT: 'SMALLINT'>, 'SMALLINT': <TokenType.SMALLINT: 'SMALLINT'>, 'HUGEINT': <TokenType.INT128: 'INT128'>, 'UHUGEINT': <TokenType.UINT128: 'UINT128'>, 'INT2': <TokenType.SMALLINT: 'SMALLINT'>, 'INTEGER': <TokenType.INT: 'INT'>, 'INT': <TokenType.INT: 'INT'>, 'INT4': <TokenType.INT: 'INT'>, 'INT32': <TokenType.INT: 'INT'>, 'INT64': <TokenType.BIGINT: 'BIGINT'>, 'INT128': <TokenType.INT128: 'INT128'>, 'INT256': <TokenType.INT256: 'INT256'>, 'LONG': <TokenType.BIGINT: 'BIGINT'>, 'BIGINT': <TokenType.BIGINT: 'BIGINT'>, 'INT8': <TokenType.TINYINT: 'TINYINT'>, 'UINT': <TokenType.UINT: 'UINT'>, 'UINT128': <TokenType.UINT128: 'UINT128'>, 'UINT256': <TokenType.UINT256: 'UINT256'>, 'DEC': <TokenType.DECIMAL: 'DECIMAL'>, 'DECIMAL': <TokenType.DECIMAL: 'DECIMAL'>, 'DECIMAL32': <TokenType.DECIMAL32: 'DECIMAL32'>, 'DECIMAL64': <TokenType.DECIMAL64: 'DECIMAL64'>, 'DECIMAL128': <TokenType.DECIMAL128: 'DECIMAL128'>, 'DECIMAL256': <TokenType.DECIMAL256: 'DECIMAL256'>, 'BIGDECIMAL': <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, 'BIGNUMERIC': <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, 'LIST': <TokenType.LIST: 'LIST'>, 'MAP': <TokenType.MAP: 'MAP'>, 'NULLABLE': <TokenType.NULLABLE: 'NULLABLE'>, 'NUMBER': <TokenType.DECIMAL: 'DECIMAL'>, 'NUMERIC': <TokenType.DECIMAL: 'DECIMAL'>, 'FIXED': <TokenType.DECIMAL: 'DECIMAL'>, 'REAL': <TokenType.FLOAT: 'FLOAT'>, 'FLOAT': <TokenType.FLOAT: 'FLOAT'>, 'FLOAT4': <TokenType.FLOAT: 'FLOAT'>, 'FLOAT8': <TokenType.DOUBLE: 'DOUBLE'>, 'DOUBLE': <TokenType.DOUBLE: 'DOUBLE'>, 'DOUBLE PRECISION': <TokenType.DOUBLE: 'DOUBLE'>, 'JSON': <TokenType.JSON: 'JSON'>, 'JSONB': <TokenType.JSONB: 'JSONB'>, 'CHAR': <TokenType.CHAR: 'CHAR'>, 'CHARACTER': <TokenType.CHAR: 'CHAR'>, 'CHAR VARYING': <TokenType.VARCHAR: 'VARCHAR'>, 'CHARACTER VARYING': <TokenType.VARCHAR: 'VARCHAR'>, 'NCHAR': <TokenType.NCHAR: 'NCHAR'>, 'VARCHAR': <TokenType.VARCHAR: 'VARCHAR'>, 'VARCHAR2': <TokenType.VARCHAR: 'VARCHAR'>, 'NVARCHAR': <TokenType.NVARCHAR: 'NVARCHAR'>, 'NVARCHAR2': <TokenType.NVARCHAR: 'NVARCHAR'>, 'BPCHAR': <TokenType.BPCHAR: 'BPCHAR'>, 'STR': <TokenType.TEXT: 'TEXT'>, 'STRING': <TokenType.TEXT: 'TEXT'>, 'TEXT': <TokenType.TEXT: 'TEXT'>, 'LONGTEXT': <TokenType.LONGTEXT: 'LONGTEXT'>, 'MEDIUMTEXT': <TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>, 'TINYTEXT': <TokenType.TINYTEXT: 'TINYTEXT'>, 'CLOB': <TokenType.TEXT: 'TEXT'>, 'LONGVARCHAR': <TokenType.TEXT: 'TEXT'>, 'BINARY': <TokenType.BINARY: 'BINARY'>, 'BLOB': <TokenType.VARBINARY: 'VARBINARY'>, 'LONGBLOB': <TokenType.LONGBLOB: 'LONGBLOB'>, 'MEDIUMBLOB': <TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>, 'TINYBLOB': <TokenType.TINYBLOB: 'TINYBLOB'>, 'BYTEA': <TokenType.VARBINARY: 'VARBINARY'>, 'VARBINARY': <TokenType.VARBINARY: 'VARBINARY'>, 'TIME': <TokenType.TIME: 'TIME'>, 'TIMETZ': <TokenType.TIMETZ: 'TIMETZ'>, 'TIMESTAMP': <TokenType.TIMESTAMP: 'TIMESTAMP'>, 'TIMESTAMPTZ': <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>, 'TIMESTAMPLTZ': <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>, 'TIMESTAMP_LTZ': <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>, 'TIMESTAMPNTZ': <TokenType.TIMESTAMPNTZ: 'TIMESTAMPNTZ'>, 'TIMESTAMP_NTZ': <TokenType.TIMESTAMPNTZ: 'TIMESTAMPNTZ'>, 'DATE': <TokenType.DATE: 'DATE'>, 'DATETIME': <TokenType.DATETIME: 'DATETIME'>, 'INT4RANGE': <TokenType.INT4RANGE: 'INT4RANGE'>, 'INT4MULTIRANGE': <TokenType.INT4MULTIRANGE: 'INT4MULTIRANGE'>, 'INT8RANGE': <TokenType.INT8RANGE: 'INT8RANGE'>, 'INT8MULTIRANGE': <TokenType.INT8MULTIRANGE: 'INT8MULTIRANGE'>, 'NUMRANGE': <TokenType.NUMRANGE: 'NUMRANGE'>, 'NUMMULTIRANGE': <TokenType.NUMMULTIRANGE: 'NUMMULTIRANGE'>, 'TSRANGE': <TokenType.TSRANGE: 'TSRANGE'>, 'TSMULTIRANGE': <TokenType.TSMULTIRANGE: 'TSMULTIRANGE'>, 'TSTZRANGE': <TokenType.TSTZRANGE: 'TSTZRANGE'>, 'TSTZMULTIRANGE': <TokenType.TSTZMULTIRANGE: 'TSTZMULTIRANGE'>, 'DATERANGE': <TokenType.DATERANGE: 'DATERANGE'>, 'DATEMULTIRANGE': <TokenType.DATEMULTIRANGE: 'DATEMULTIRANGE'>, 'UNIQUE': <TokenType.UNIQUE: 'UNIQUE'>, 'VECTOR': <TokenType.VECTOR: 'VECTOR'>, 'STRUCT': <TokenType.STRUCT: 'STRUCT'>, 'SEQUENCE': <TokenType.SEQUENCE: 'SEQUENCE'>, 'VARIANT': <TokenType.VARIANT: 'VARIANT'>, 'ALTER': <TokenType.ALTER: 'ALTER'>, 'ANALYZE': <TokenType.ANALYZE: 'ANALYZE'>, 'CALL': <TokenType.COMMAND: 'COMMAND'>, 'COMMENT': <TokenType.COMMENT: 'COMMENT'>, 'EXPLAIN': <TokenType.COMMAND: 'COMMAND'>, 'GRANT': <TokenType.GRANT: 'GRANT'>, 'REVOKE': <TokenType.REVOKE: 'REVOKE'>, 'OPTIMIZE': <TokenType.COMMAND: 'COMMAND'>, 'PREPARE': <TokenType.COMMAND: 'COMMAND'>, 'VACUUM': <TokenType.COMMAND: 'COMMAND'>, 'USER-DEFINED': <TokenType.USERDEFINED: 'USERDEFINED'>, 'FOR VERSION': <TokenType.VERSION_SNAPSHOT: 'VERSION_SNAPSHOT'>, 'FOR TIMESTAMP': <TokenType.TIMESTAMP_SNAPSHOT: 'TIMESTAMP_SNAPSHOT'>}
WHITE_SPACE: Dict[Optional[str], TokenType] = {' ': <TokenType.SPACE: 'SPACE'>, '\t': <TokenType.SPACE: 'SPACE'>, '\n': <TokenType.BREAK: 'BREAK'>, '\r': <TokenType.BREAK: 'BREAK'>}
COMMANDS = {<TokenType.RENAME: 'RENAME'>, <TokenType.COMMAND: 'COMMAND'>, <TokenType.SHOW: 'SHOW'>, <TokenType.FETCH: 'FETCH'>, <TokenType.EXECUTE: 'EXECUTE'>}
COMMAND_PREFIX_TOKENS = {<TokenType.BEGIN: 'BEGIN'>, <TokenType.SEMICOLON: 'SEMICOLON'>}
NUMERIC_LITERALS: Dict[str, str] = {}
COMMENTS = ['--', ('/*', '*/')]
dialect
use_rs_tokenizer
def reset(self) -> None:
1050    def reset(self) -> None:
1051        self.sql = ""
1052        self.size = 0
1053        self.tokens: t.List[Token] = []
1054        self._start = 0
1055        self._current = 0
1056        self._line = 1
1057        self._col = 0
1058        self._comments: t.List[str] = []
1059
1060        self._char = ""
1061        self._end = False
1062        self._peek = ""
1063        self._prev_token_line = -1
def tokenize(self, sql: str) -> List[Token]:
1065    def tokenize(self, sql: str) -> t.List[Token]:
1066        """Returns a list of tokens corresponding to the SQL string `sql`."""
1067        if self.use_rs_tokenizer:
1068            return self.tokenize_rs(sql)
1069
1070        self.reset()
1071        self.sql = sql
1072        self.size = len(sql)
1073
1074        try:
1075            self._scan()
1076        except Exception as e:
1077            start = max(self._current - 50, 0)
1078            end = min(self._current + 50, self.size - 1)
1079            context = self.sql[start:end]
1080            raise TokenError(f"Error tokenizing '{context}'") from e
1081
1082        return self.tokens

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

def tokenize_rs(self, sql: str) -> List[Token]:
1519    def tokenize_rs(self, sql: str) -> t.List[Token]:
1520        if not self._RS_TOKENIZER:
1521            raise SqlglotError("Rust tokenizer is not available")
1522
1523        tokens, error_msg = self._RS_TOKENIZER.tokenize(sql, self._rs_dialect_settings)
1524        for token in tokens:
1525            token.token_type = _ALL_TOKEN_TYPES[token.token_type_index]
1526
1527        # Setting this here so partial token lists can be inspected even if there is a failure
1528        self.tokens = tokens
1529
1530        if error_msg is not None:
1531            raise TokenError(error_msg)
1532
1533        return tokens
size
sql
tokens