Edit on GitHub

sqlglot.tokens

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

An enumeration.

L_PAREN = <TokenType.L_PAREN: 'L_PAREN'>
R_PAREN = <TokenType.R_PAREN: 'R_PAREN'>
L_BRACKET = <TokenType.L_BRACKET: 'L_BRACKET'>
R_BRACKET = <TokenType.R_BRACKET: 'R_BRACKET'>
L_BRACE = <TokenType.L_BRACE: 'L_BRACE'>
R_BRACE = <TokenType.R_BRACE: 'R_BRACE'>
COMMA = <TokenType.COMMA: 'COMMA'>
DOT = <TokenType.DOT: 'DOT'>
DASH = <TokenType.DASH: 'DASH'>
PLUS = <TokenType.PLUS: 'PLUS'>
COLON = <TokenType.COLON: 'COLON'>
DCOLON = <TokenType.DCOLON: 'DCOLON'>
DQMARK = <TokenType.DQMARK: 'DQMARK'>
SEMICOLON = <TokenType.SEMICOLON: 'SEMICOLON'>
STAR = <TokenType.STAR: 'STAR'>
BACKSLASH = <TokenType.BACKSLASH: 'BACKSLASH'>
SLASH = <TokenType.SLASH: 'SLASH'>
LT = <TokenType.LT: 'LT'>
LTE = <TokenType.LTE: 'LTE'>
GT = <TokenType.GT: 'GT'>
GTE = <TokenType.GTE: 'GTE'>
NOT = <TokenType.NOT: 'NOT'>
EQ = <TokenType.EQ: 'EQ'>
NEQ = <TokenType.NEQ: 'NEQ'>
NULLSAFE_EQ = <TokenType.NULLSAFE_EQ: 'NULLSAFE_EQ'>
COLON_EQ = <TokenType.COLON_EQ: 'COLON_EQ'>
AND = <TokenType.AND: 'AND'>
OR = <TokenType.OR: 'OR'>
AMP = <TokenType.AMP: 'AMP'>
DPIPE = <TokenType.DPIPE: 'DPIPE'>
PIPE = <TokenType.PIPE: 'PIPE'>
CARET = <TokenType.CARET: 'CARET'>
TILDA = <TokenType.TILDA: 'TILDA'>
ARROW = <TokenType.ARROW: 'ARROW'>
DARROW = <TokenType.DARROW: 'DARROW'>
FARROW = <TokenType.FARROW: 'FARROW'>
HASH = <TokenType.HASH: 'HASH'>
HASH_ARROW = <TokenType.HASH_ARROW: 'HASH_ARROW'>
DHASH_ARROW = <TokenType.DHASH_ARROW: 'DHASH_ARROW'>
LR_ARROW = <TokenType.LR_ARROW: 'LR_ARROW'>
DAT = <TokenType.DAT: 'DAT'>
LT_AT = <TokenType.LT_AT: 'LT_AT'>
AT_GT = <TokenType.AT_GT: 'AT_GT'>
DOLLAR = <TokenType.DOLLAR: 'DOLLAR'>
PARAMETER = <TokenType.PARAMETER: 'PARAMETER'>
SESSION_PARAMETER = <TokenType.SESSION_PARAMETER: 'SESSION_PARAMETER'>
DAMP = <TokenType.DAMP: 'DAMP'>
XOR = <TokenType.XOR: 'XOR'>
DSTAR = <TokenType.DSTAR: 'DSTAR'>
BLOCK_START = <TokenType.BLOCK_START: 'BLOCK_START'>
BLOCK_END = <TokenType.BLOCK_END: 'BLOCK_END'>
SPACE = <TokenType.SPACE: 'SPACE'>
BREAK = <TokenType.BREAK: 'BREAK'>
STRING = <TokenType.STRING: 'STRING'>
NUMBER = <TokenType.NUMBER: 'NUMBER'>
IDENTIFIER = <TokenType.IDENTIFIER: 'IDENTIFIER'>
DATABASE = <TokenType.DATABASE: 'DATABASE'>
COLUMN = <TokenType.COLUMN: 'COLUMN'>
COLUMN_DEF = <TokenType.COLUMN_DEF: 'COLUMN_DEF'>
SCHEMA = <TokenType.SCHEMA: 'SCHEMA'>
TABLE = <TokenType.TABLE: 'TABLE'>
VAR = <TokenType.VAR: 'VAR'>
BIT_STRING = <TokenType.BIT_STRING: 'BIT_STRING'>
HEX_STRING = <TokenType.HEX_STRING: 'HEX_STRING'>
BYTE_STRING = <TokenType.BYTE_STRING: 'BYTE_STRING'>
NATIONAL_STRING = <TokenType.NATIONAL_STRING: 'NATIONAL_STRING'>
RAW_STRING = <TokenType.RAW_STRING: 'RAW_STRING'>
HEREDOC_STRING = <TokenType.HEREDOC_STRING: 'HEREDOC_STRING'>
BIT = <TokenType.BIT: 'BIT'>
BOOLEAN = <TokenType.BOOLEAN: 'BOOLEAN'>
TINYINT = <TokenType.TINYINT: 'TINYINT'>
UTINYINT = <TokenType.UTINYINT: 'UTINYINT'>
SMALLINT = <TokenType.SMALLINT: 'SMALLINT'>
USMALLINT = <TokenType.USMALLINT: 'USMALLINT'>
MEDIUMINT = <TokenType.MEDIUMINT: 'MEDIUMINT'>
UMEDIUMINT = <TokenType.UMEDIUMINT: 'UMEDIUMINT'>
INT = <TokenType.INT: 'INT'>
UINT = <TokenType.UINT: 'UINT'>
BIGINT = <TokenType.BIGINT: 'BIGINT'>
UBIGINT = <TokenType.UBIGINT: 'UBIGINT'>
INT128 = <TokenType.INT128: 'INT128'>
UINT128 = <TokenType.UINT128: 'UINT128'>
INT256 = <TokenType.INT256: 'INT256'>
UINT256 = <TokenType.UINT256: 'UINT256'>
FLOAT = <TokenType.FLOAT: 'FLOAT'>
DOUBLE = <TokenType.DOUBLE: 'DOUBLE'>
DECIMAL = <TokenType.DECIMAL: 'DECIMAL'>
UDECIMAL = <TokenType.UDECIMAL: 'UDECIMAL'>
BIGDECIMAL = <TokenType.BIGDECIMAL: 'BIGDECIMAL'>
CHAR = <TokenType.CHAR: 'CHAR'>
NCHAR = <TokenType.NCHAR: 'NCHAR'>
VARCHAR = <TokenType.VARCHAR: 'VARCHAR'>
NVARCHAR = <TokenType.NVARCHAR: 'NVARCHAR'>
TEXT = <TokenType.TEXT: 'TEXT'>
MEDIUMTEXT = <TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>
LONGTEXT = <TokenType.LONGTEXT: 'LONGTEXT'>
MEDIUMBLOB = <TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>
LONGBLOB = <TokenType.LONGBLOB: 'LONGBLOB'>
TINYBLOB = <TokenType.TINYBLOB: 'TINYBLOB'>
TINYTEXT = <TokenType.TINYTEXT: 'TINYTEXT'>
BINARY = <TokenType.BINARY: 'BINARY'>
VARBINARY = <TokenType.VARBINARY: 'VARBINARY'>
JSON = <TokenType.JSON: 'JSON'>
JSONB = <TokenType.JSONB: 'JSONB'>
TIME = <TokenType.TIME: 'TIME'>
TIMETZ = <TokenType.TIMETZ: 'TIMETZ'>
TIMESTAMP = <TokenType.TIMESTAMP: 'TIMESTAMP'>
TIMESTAMPTZ = <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>
TIMESTAMPLTZ = <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>
TIMESTAMP_S = <TokenType.TIMESTAMP_S: 'TIMESTAMP_S'>
TIMESTAMP_MS = <TokenType.TIMESTAMP_MS: 'TIMESTAMP_MS'>
TIMESTAMP_NS = <TokenType.TIMESTAMP_NS: 'TIMESTAMP_NS'>
DATETIME = <TokenType.DATETIME: 'DATETIME'>
DATETIME64 = <TokenType.DATETIME64: 'DATETIME64'>
DATE = <TokenType.DATE: 'DATE'>
INT4RANGE = <TokenType.INT4RANGE: 'INT4RANGE'>
INT4MULTIRANGE = <TokenType.INT4MULTIRANGE: 'INT4MULTIRANGE'>
INT8RANGE = <TokenType.INT8RANGE: 'INT8RANGE'>
INT8MULTIRANGE = <TokenType.INT8MULTIRANGE: 'INT8MULTIRANGE'>
NUMRANGE = <TokenType.NUMRANGE: 'NUMRANGE'>
NUMMULTIRANGE = <TokenType.NUMMULTIRANGE: 'NUMMULTIRANGE'>
TSRANGE = <TokenType.TSRANGE: 'TSRANGE'>
TSMULTIRANGE = <TokenType.TSMULTIRANGE: 'TSMULTIRANGE'>
TSTZRANGE = <TokenType.TSTZRANGE: 'TSTZRANGE'>
TSTZMULTIRANGE = <TokenType.TSTZMULTIRANGE: 'TSTZMULTIRANGE'>
DATERANGE = <TokenType.DATERANGE: 'DATERANGE'>
DATEMULTIRANGE = <TokenType.DATEMULTIRANGE: 'DATEMULTIRANGE'>
UUID = <TokenType.UUID: 'UUID'>
GEOGRAPHY = <TokenType.GEOGRAPHY: 'GEOGRAPHY'>
NULLABLE = <TokenType.NULLABLE: 'NULLABLE'>
GEOMETRY = <TokenType.GEOMETRY: 'GEOMETRY'>
HLLSKETCH = <TokenType.HLLSKETCH: 'HLLSKETCH'>
HSTORE = <TokenType.HSTORE: 'HSTORE'>
SUPER = <TokenType.SUPER: 'SUPER'>
SERIAL = <TokenType.SERIAL: 'SERIAL'>
SMALLSERIAL = <TokenType.SMALLSERIAL: 'SMALLSERIAL'>
BIGSERIAL = <TokenType.BIGSERIAL: 'BIGSERIAL'>
XML = <TokenType.XML: 'XML'>
YEAR = <TokenType.YEAR: 'YEAR'>
UNIQUEIDENTIFIER = <TokenType.UNIQUEIDENTIFIER: 'UNIQUEIDENTIFIER'>
USERDEFINED = <TokenType.USERDEFINED: 'USERDEFINED'>
MONEY = <TokenType.MONEY: 'MONEY'>
SMALLMONEY = <TokenType.SMALLMONEY: 'SMALLMONEY'>
ROWVERSION = <TokenType.ROWVERSION: 'ROWVERSION'>
IMAGE = <TokenType.IMAGE: 'IMAGE'>
VARIANT = <TokenType.VARIANT: 'VARIANT'>
OBJECT = <TokenType.OBJECT: 'OBJECT'>
INET = <TokenType.INET: 'INET'>
IPADDRESS = <TokenType.IPADDRESS: 'IPADDRESS'>
IPPREFIX = <TokenType.IPPREFIX: 'IPPREFIX'>
ENUM = <TokenType.ENUM: 'ENUM'>
ENUM8 = <TokenType.ENUM8: 'ENUM8'>
ENUM16 = <TokenType.ENUM16: 'ENUM16'>
FIXEDSTRING = <TokenType.FIXEDSTRING: 'FIXEDSTRING'>
LOWCARDINALITY = <TokenType.LOWCARDINALITY: 'LOWCARDINALITY'>
NESTED = <TokenType.NESTED: 'NESTED'>
UNKNOWN = <TokenType.UNKNOWN: 'UNKNOWN'>
ALIAS = <TokenType.ALIAS: 'ALIAS'>
ALTER = <TokenType.ALTER: 'ALTER'>
ALWAYS = <TokenType.ALWAYS: 'ALWAYS'>
ALL = <TokenType.ALL: 'ALL'>
ANTI = <TokenType.ANTI: 'ANTI'>
ANY = <TokenType.ANY: 'ANY'>
APPLY = <TokenType.APPLY: 'APPLY'>
ARRAY = <TokenType.ARRAY: 'ARRAY'>
ASC = <TokenType.ASC: 'ASC'>
ASOF = <TokenType.ASOF: 'ASOF'>
AUTO_INCREMENT = <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>
BEGIN = <TokenType.BEGIN: 'BEGIN'>
BETWEEN = <TokenType.BETWEEN: 'BETWEEN'>
CACHE = <TokenType.CACHE: 'CACHE'>
CASE = <TokenType.CASE: 'CASE'>
CHARACTER_SET = <TokenType.CHARACTER_SET: 'CHARACTER_SET'>
CLUSTER_BY = <TokenType.CLUSTER_BY: 'CLUSTER_BY'>
COLLATE = <TokenType.COLLATE: 'COLLATE'>
COMMAND = <TokenType.COMMAND: 'COMMAND'>
COMMENT = <TokenType.COMMENT: 'COMMENT'>
COMMIT = <TokenType.COMMIT: 'COMMIT'>
CONNECT_BY = <TokenType.CONNECT_BY: 'CONNECT_BY'>
CONSTRAINT = <TokenType.CONSTRAINT: 'CONSTRAINT'>
CREATE = <TokenType.CREATE: 'CREATE'>
CROSS = <TokenType.CROSS: 'CROSS'>
CUBE = <TokenType.CUBE: 'CUBE'>
CURRENT_DATE = <TokenType.CURRENT_DATE: 'CURRENT_DATE'>
CURRENT_DATETIME = <TokenType.CURRENT_DATETIME: 'CURRENT_DATETIME'>
CURRENT_TIME = <TokenType.CURRENT_TIME: 'CURRENT_TIME'>
CURRENT_TIMESTAMP = <TokenType.CURRENT_TIMESTAMP: 'CURRENT_TIMESTAMP'>
CURRENT_USER = <TokenType.CURRENT_USER: 'CURRENT_USER'>
DEFAULT = <TokenType.DEFAULT: 'DEFAULT'>
DELETE = <TokenType.DELETE: 'DELETE'>
DESC = <TokenType.DESC: 'DESC'>
DESCRIBE = <TokenType.DESCRIBE: 'DESCRIBE'>
DICTIONARY = <TokenType.DICTIONARY: 'DICTIONARY'>
DISTINCT = <TokenType.DISTINCT: 'DISTINCT'>
DISTRIBUTE_BY = <TokenType.DISTRIBUTE_BY: 'DISTRIBUTE_BY'>
DIV = <TokenType.DIV: 'DIV'>
DROP = <TokenType.DROP: 'DROP'>
ELSE = <TokenType.ELSE: 'ELSE'>
END = <TokenType.END: 'END'>
ESCAPE = <TokenType.ESCAPE: 'ESCAPE'>
EXCEPT = <TokenType.EXCEPT: 'EXCEPT'>
EXECUTE = <TokenType.EXECUTE: 'EXECUTE'>
EXISTS = <TokenType.EXISTS: 'EXISTS'>
FALSE = <TokenType.FALSE: 'FALSE'>
FETCH = <TokenType.FETCH: 'FETCH'>
FILTER = <TokenType.FILTER: 'FILTER'>
FINAL = <TokenType.FINAL: 'FINAL'>
FIRST = <TokenType.FIRST: 'FIRST'>
FOR = <TokenType.FOR: 'FOR'>
FORCE = <TokenType.FORCE: 'FORCE'>
FOREIGN_KEY = <TokenType.FOREIGN_KEY: 'FOREIGN_KEY'>
FORMAT = <TokenType.FORMAT: 'FORMAT'>
FROM = <TokenType.FROM: 'FROM'>
FULL = <TokenType.FULL: 'FULL'>
FUNCTION = <TokenType.FUNCTION: 'FUNCTION'>
GLOB = <TokenType.GLOB: 'GLOB'>
GLOBAL = <TokenType.GLOBAL: 'GLOBAL'>
GROUP_BY = <TokenType.GROUP_BY: 'GROUP_BY'>
GROUPING_SETS = <TokenType.GROUPING_SETS: 'GROUPING_SETS'>
HAVING = <TokenType.HAVING: 'HAVING'>
HINT = <TokenType.HINT: 'HINT'>
IGNORE = <TokenType.IGNORE: 'IGNORE'>
ILIKE = <TokenType.ILIKE: 'ILIKE'>
ILIKE_ANY = <TokenType.ILIKE_ANY: 'ILIKE_ANY'>
IN = <TokenType.IN: 'IN'>
INDEX = <TokenType.INDEX: 'INDEX'>
INNER = <TokenType.INNER: 'INNER'>
INSERT = <TokenType.INSERT: 'INSERT'>
INTERSECT = <TokenType.INTERSECT: 'INTERSECT'>
INTERVAL = <TokenType.INTERVAL: 'INTERVAL'>
INTO = <TokenType.INTO: 'INTO'>
INTRODUCER = <TokenType.INTRODUCER: 'INTRODUCER'>
IRLIKE = <TokenType.IRLIKE: 'IRLIKE'>
IS = <TokenType.IS: 'IS'>
ISNULL = <TokenType.ISNULL: 'ISNULL'>
JOIN = <TokenType.JOIN: 'JOIN'>
JOIN_MARKER = <TokenType.JOIN_MARKER: 'JOIN_MARKER'>
KEEP = <TokenType.KEEP: 'KEEP'>
KILL = <TokenType.KILL: 'KILL'>
LANGUAGE = <TokenType.LANGUAGE: 'LANGUAGE'>
LATERAL = <TokenType.LATERAL: 'LATERAL'>
LEFT = <TokenType.LEFT: 'LEFT'>
LIKE = <TokenType.LIKE: 'LIKE'>
LIKE_ANY = <TokenType.LIKE_ANY: 'LIKE_ANY'>
LIMIT = <TokenType.LIMIT: 'LIMIT'>
LOAD = <TokenType.LOAD: 'LOAD'>
LOCK = <TokenType.LOCK: 'LOCK'>
MAP = <TokenType.MAP: 'MAP'>
MATCH_RECOGNIZE = <TokenType.MATCH_RECOGNIZE: 'MATCH_RECOGNIZE'>
MEMBER_OF = <TokenType.MEMBER_OF: 'MEMBER_OF'>
MERGE = <TokenType.MERGE: 'MERGE'>
MOD = <TokenType.MOD: 'MOD'>
MODEL = <TokenType.MODEL: 'MODEL'>
NATURAL = <TokenType.NATURAL: 'NATURAL'>
NEXT = <TokenType.NEXT: 'NEXT'>
NOTNULL = <TokenType.NOTNULL: 'NOTNULL'>
NULL = <TokenType.NULL: 'NULL'>
OBJECT_IDENTIFIER = <TokenType.OBJECT_IDENTIFIER: 'OBJECT_IDENTIFIER'>
OFFSET = <TokenType.OFFSET: 'OFFSET'>
ON = <TokenType.ON: 'ON'>
ORDER_BY = <TokenType.ORDER_BY: 'ORDER_BY'>
ORDERED = <TokenType.ORDERED: 'ORDERED'>
ORDINALITY = <TokenType.ORDINALITY: 'ORDINALITY'>
OUTER = <TokenType.OUTER: 'OUTER'>
OVER = <TokenType.OVER: 'OVER'>
OVERLAPS = <TokenType.OVERLAPS: 'OVERLAPS'>
OVERWRITE = <TokenType.OVERWRITE: 'OVERWRITE'>
PARTITION = <TokenType.PARTITION: 'PARTITION'>
PARTITION_BY = <TokenType.PARTITION_BY: 'PARTITION_BY'>
PERCENT = <TokenType.PERCENT: 'PERCENT'>
PIVOT = <TokenType.PIVOT: 'PIVOT'>
PLACEHOLDER = <TokenType.PLACEHOLDER: 'PLACEHOLDER'>
PRAGMA = <TokenType.PRAGMA: 'PRAGMA'>
PRIMARY_KEY = <TokenType.PRIMARY_KEY: 'PRIMARY_KEY'>
PROCEDURE = <TokenType.PROCEDURE: 'PROCEDURE'>
PROPERTIES = <TokenType.PROPERTIES: 'PROPERTIES'>
PSEUDO_TYPE = <TokenType.PSEUDO_TYPE: 'PSEUDO_TYPE'>
QUALIFY = <TokenType.QUALIFY: 'QUALIFY'>
QUOTE = <TokenType.QUOTE: 'QUOTE'>
RANGE = <TokenType.RANGE: 'RANGE'>
RECURSIVE = <TokenType.RECURSIVE: 'RECURSIVE'>
REFRESH = <TokenType.REFRESH: 'REFRESH'>
REPLACE = <TokenType.REPLACE: 'REPLACE'>
RETURNING = <TokenType.RETURNING: 'RETURNING'>
REFERENCES = <TokenType.REFERENCES: 'REFERENCES'>
RIGHT = <TokenType.RIGHT: 'RIGHT'>
RLIKE = <TokenType.RLIKE: 'RLIKE'>
ROLLBACK = <TokenType.ROLLBACK: 'ROLLBACK'>
ROLLUP = <TokenType.ROLLUP: 'ROLLUP'>
ROW = <TokenType.ROW: 'ROW'>
ROWS = <TokenType.ROWS: 'ROWS'>
SELECT = <TokenType.SELECT: 'SELECT'>
SEMI = <TokenType.SEMI: 'SEMI'>
SEPARATOR = <TokenType.SEPARATOR: 'SEPARATOR'>
SERDE_PROPERTIES = <TokenType.SERDE_PROPERTIES: 'SERDE_PROPERTIES'>
SET = <TokenType.SET: 'SET'>
SETTINGS = <TokenType.SETTINGS: 'SETTINGS'>
SHOW = <TokenType.SHOW: 'SHOW'>
SIMILAR_TO = <TokenType.SIMILAR_TO: 'SIMILAR_TO'>
SOME = <TokenType.SOME: 'SOME'>
SORT_BY = <TokenType.SORT_BY: 'SORT_BY'>
START_WITH = <TokenType.START_WITH: 'START_WITH'>
STRUCT = <TokenType.STRUCT: 'STRUCT'>
TABLE_SAMPLE = <TokenType.TABLE_SAMPLE: 'TABLE_SAMPLE'>
TEMPORARY = <TokenType.TEMPORARY: 'TEMPORARY'>
TOP = <TokenType.TOP: 'TOP'>
THEN = <TokenType.THEN: 'THEN'>
TRUE = <TokenType.TRUE: 'TRUE'>
UNCACHE = <TokenType.UNCACHE: 'UNCACHE'>
UNION = <TokenType.UNION: 'UNION'>
UNNEST = <TokenType.UNNEST: 'UNNEST'>
UNPIVOT = <TokenType.UNPIVOT: 'UNPIVOT'>
UPDATE = <TokenType.UPDATE: 'UPDATE'>
USE = <TokenType.USE: 'USE'>
USING = <TokenType.USING: 'USING'>
VALUES = <TokenType.VALUES: 'VALUES'>
VIEW = <TokenType.VIEW: 'VIEW'>
VOLATILE = <TokenType.VOLATILE: 'VOLATILE'>
WHEN = <TokenType.WHEN: 'WHEN'>
WHERE = <TokenType.WHERE: 'WHERE'>
WINDOW = <TokenType.WINDOW: 'WINDOW'>
WITH = <TokenType.WITH: 'WITH'>
UNIQUE = <TokenType.UNIQUE: 'UNIQUE'>
VERSION_SNAPSHOT = <TokenType.VERSION_SNAPSHOT: 'VERSION_SNAPSHOT'>
TIMESTAMP_SNAPSHOT = <TokenType.TIMESTAMP_SNAPSHOT: 'TIMESTAMP_SNAPSHOT'>
Inherited Members
enum.Enum
name
value
class Token:
347class Token:
348    __slots__ = ("token_type", "text", "line", "col", "start", "end", "comments")
349
350    @classmethod
351    def number(cls, number: int) -> Token:
352        """Returns a NUMBER token with `number` as its text."""
353        return cls(TokenType.NUMBER, str(number))
354
355    @classmethod
356    def string(cls, string: str) -> Token:
357        """Returns a STRING token with `string` as its text."""
358        return cls(TokenType.STRING, string)
359
360    @classmethod
361    def identifier(cls, identifier: str) -> Token:
362        """Returns an IDENTIFIER token with `identifier` as its text."""
363        return cls(TokenType.IDENTIFIER, identifier)
364
365    @classmethod
366    def var(cls, var: str) -> Token:
367        """Returns an VAR token with `var` as its text."""
368        return cls(TokenType.VAR, var)
369
370    def __init__(
371        self,
372        token_type: TokenType,
373        text: str,
374        line: int = 1,
375        col: int = 1,
376        start: int = 0,
377        end: int = 0,
378        comments: t.List[str] = [],
379    ) -> None:
380        """Token initializer.
381
382        Args:
383            token_type: The TokenType Enum.
384            text: The text of the token.
385            line: The line that the token ends on.
386            col: The column that the token ends on.
387            start: The start index of the token.
388            end: The ending index of the token.
389            comments: The comments to attach to the token.
390        """
391        self.token_type = token_type
392        self.text = text
393        self.line = line
394        self.col = col
395        self.start = start
396        self.end = end
397        self.comments = comments
398
399    def __repr__(self) -> str:
400        attributes = ", ".join(f"{k}: {getattr(self, k)}" for k in self.__slots__)
401        return f"<Token {attributes}>"
Token( token_type: TokenType, text: str, line: int = 1, col: int = 1, start: int = 0, end: int = 0, comments: List[str] = [])
370    def __init__(
371        self,
372        token_type: TokenType,
373        text: str,
374        line: int = 1,
375        col: int = 1,
376        start: int = 0,
377        end: int = 0,
378        comments: t.List[str] = [],
379    ) -> None:
380        """Token initializer.
381
382        Args:
383            token_type: The TokenType Enum.
384            text: The text of the token.
385            line: The line that the token ends on.
386            col: The column that the token ends on.
387            start: The start index of the token.
388            end: The ending index of the token.
389            comments: The comments to attach to the token.
390        """
391        self.token_type = token_type
392        self.text = text
393        self.line = line
394        self.col = col
395        self.start = start
396        self.end = end
397        self.comments = 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:
350    @classmethod
351    def number(cls, number: int) -> Token:
352        """Returns a NUMBER token with `number` as its text."""
353        return cls(TokenType.NUMBER, str(number))

Returns a NUMBER token with number as its text.

@classmethod
def string(cls, string: str) -> Token:
355    @classmethod
356    def string(cls, string: str) -> Token:
357        """Returns a STRING token with `string` as its text."""
358        return cls(TokenType.STRING, string)

Returns a STRING token with string as its text.

@classmethod
def identifier(cls, identifier: str) -> Token:
360    @classmethod
361    def identifier(cls, identifier: str) -> Token:
362        """Returns an IDENTIFIER token with `identifier` as its text."""
363        return cls(TokenType.IDENTIFIER, identifier)

Returns an IDENTIFIER token with identifier as its text.

@classmethod
def var(cls, var: str) -> Token:
365    @classmethod
366    def var(cls, var: str) -> Token:
367        """Returns an VAR token with `var` as its text."""
368        return cls(TokenType.VAR, var)

Returns an VAR token with var as its text.

token_type
text
line
col
start
end
comments
class Tokenizer:
 458class Tokenizer(metaclass=_Tokenizer):
 459    SINGLE_TOKENS = {
 460        "(": TokenType.L_PAREN,
 461        ")": TokenType.R_PAREN,
 462        "[": TokenType.L_BRACKET,
 463        "]": TokenType.R_BRACKET,
 464        "{": TokenType.L_BRACE,
 465        "}": TokenType.R_BRACE,
 466        "&": TokenType.AMP,
 467        "^": TokenType.CARET,
 468        ":": TokenType.COLON,
 469        ",": TokenType.COMMA,
 470        ".": TokenType.DOT,
 471        "-": TokenType.DASH,
 472        "=": TokenType.EQ,
 473        ">": TokenType.GT,
 474        "<": TokenType.LT,
 475        "%": TokenType.MOD,
 476        "!": TokenType.NOT,
 477        "|": TokenType.PIPE,
 478        "+": TokenType.PLUS,
 479        ";": TokenType.SEMICOLON,
 480        "/": TokenType.SLASH,
 481        "\\": TokenType.BACKSLASH,
 482        "*": TokenType.STAR,
 483        "~": TokenType.TILDA,
 484        "?": TokenType.PLACEHOLDER,
 485        "@": TokenType.PARAMETER,
 486        # used for breaking a var like x'y' but nothing else
 487        # the token type doesn't matter
 488        "'": TokenType.QUOTE,
 489        "`": TokenType.IDENTIFIER,
 490        '"': TokenType.IDENTIFIER,
 491        "#": TokenType.HASH,
 492    }
 493
 494    BIT_STRINGS: t.List[str | t.Tuple[str, str]] = []
 495    BYTE_STRINGS: t.List[str | t.Tuple[str, str]] = []
 496    HEX_STRINGS: t.List[str | t.Tuple[str, str]] = []
 497    RAW_STRINGS: t.List[str | t.Tuple[str, str]] = []
 498    HEREDOC_STRINGS: t.List[str | t.Tuple[str, str]] = []
 499    IDENTIFIERS: t.List[str | t.Tuple[str, str]] = ['"']
 500    IDENTIFIER_ESCAPES = ['"']
 501    QUOTES: t.List[t.Tuple[str, str] | str] = ["'"]
 502    STRING_ESCAPES = ["'"]
 503    VAR_SINGLE_TOKENS: t.Set[str] = set()
 504    ESCAPE_SEQUENCES: t.Dict[str, str] = {}
 505
 506    # Autofilled
 507    IDENTIFIERS_CAN_START_WITH_DIGIT: bool = False
 508
 509    _COMMENTS: t.Dict[str, str] = {}
 510    _FORMAT_STRINGS: t.Dict[str, t.Tuple[str, TokenType]] = {}
 511    _IDENTIFIERS: t.Dict[str, str] = {}
 512    _IDENTIFIER_ESCAPES: t.Set[str] = set()
 513    _QUOTES: t.Dict[str, str] = {}
 514    _STRING_ESCAPES: t.Set[str] = set()
 515    _KEYWORD_TRIE: t.Dict = {}
 516
 517    KEYWORDS: t.Dict[str, TokenType] = {
 518        **{f"{{%{postfix}": TokenType.BLOCK_START for postfix in ("", "+", "-")},
 519        **{f"{prefix}%}}": TokenType.BLOCK_END for prefix in ("", "+", "-")},
 520        **{f"{{{{{postfix}": TokenType.BLOCK_START for postfix in ("+", "-")},
 521        **{f"{prefix}}}}}": TokenType.BLOCK_END for prefix in ("+", "-")},
 522        "/*+": TokenType.HINT,
 523        "==": TokenType.EQ,
 524        "::": TokenType.DCOLON,
 525        "||": TokenType.DPIPE,
 526        ">=": TokenType.GTE,
 527        "<=": TokenType.LTE,
 528        "<>": TokenType.NEQ,
 529        "!=": TokenType.NEQ,
 530        "<=>": TokenType.NULLSAFE_EQ,
 531        "->": TokenType.ARROW,
 532        "->>": TokenType.DARROW,
 533        "=>": TokenType.FARROW,
 534        "#>": TokenType.HASH_ARROW,
 535        "#>>": TokenType.DHASH_ARROW,
 536        "<->": TokenType.LR_ARROW,
 537        "&&": TokenType.DAMP,
 538        "??": TokenType.DQMARK,
 539        "ALL": TokenType.ALL,
 540        "ALWAYS": TokenType.ALWAYS,
 541        "AND": TokenType.AND,
 542        "ANTI": TokenType.ANTI,
 543        "ANY": TokenType.ANY,
 544        "ASC": TokenType.ASC,
 545        "AS": TokenType.ALIAS,
 546        "ASOF": TokenType.ASOF,
 547        "AUTOINCREMENT": TokenType.AUTO_INCREMENT,
 548        "AUTO_INCREMENT": TokenType.AUTO_INCREMENT,
 549        "BEGIN": TokenType.BEGIN,
 550        "BETWEEN": TokenType.BETWEEN,
 551        "CACHE": TokenType.CACHE,
 552        "UNCACHE": TokenType.UNCACHE,
 553        "CASE": TokenType.CASE,
 554        "CHARACTER SET": TokenType.CHARACTER_SET,
 555        "CLUSTER BY": TokenType.CLUSTER_BY,
 556        "COLLATE": TokenType.COLLATE,
 557        "COLUMN": TokenType.COLUMN,
 558        "COMMIT": TokenType.COMMIT,
 559        "CONNECT BY": TokenType.CONNECT_BY,
 560        "CONSTRAINT": TokenType.CONSTRAINT,
 561        "CREATE": TokenType.CREATE,
 562        "CROSS": TokenType.CROSS,
 563        "CUBE": TokenType.CUBE,
 564        "CURRENT_DATE": TokenType.CURRENT_DATE,
 565        "CURRENT_TIME": TokenType.CURRENT_TIME,
 566        "CURRENT_TIMESTAMP": TokenType.CURRENT_TIMESTAMP,
 567        "CURRENT_USER": TokenType.CURRENT_USER,
 568        "DATABASE": TokenType.DATABASE,
 569        "DEFAULT": TokenType.DEFAULT,
 570        "DELETE": TokenType.DELETE,
 571        "DESC": TokenType.DESC,
 572        "DESCRIBE": TokenType.DESCRIBE,
 573        "DISTINCT": TokenType.DISTINCT,
 574        "DISTRIBUTE BY": TokenType.DISTRIBUTE_BY,
 575        "DIV": TokenType.DIV,
 576        "DROP": TokenType.DROP,
 577        "ELSE": TokenType.ELSE,
 578        "END": TokenType.END,
 579        "ESCAPE": TokenType.ESCAPE,
 580        "EXCEPT": TokenType.EXCEPT,
 581        "EXECUTE": TokenType.EXECUTE,
 582        "EXISTS": TokenType.EXISTS,
 583        "FALSE": TokenType.FALSE,
 584        "FETCH": TokenType.FETCH,
 585        "FILTER": TokenType.FILTER,
 586        "FIRST": TokenType.FIRST,
 587        "FULL": TokenType.FULL,
 588        "FUNCTION": TokenType.FUNCTION,
 589        "FOR": TokenType.FOR,
 590        "FOREIGN KEY": TokenType.FOREIGN_KEY,
 591        "FORMAT": TokenType.FORMAT,
 592        "FROM": TokenType.FROM,
 593        "GEOGRAPHY": TokenType.GEOGRAPHY,
 594        "GEOMETRY": TokenType.GEOMETRY,
 595        "GLOB": TokenType.GLOB,
 596        "GROUP BY": TokenType.GROUP_BY,
 597        "GROUPING SETS": TokenType.GROUPING_SETS,
 598        "HAVING": TokenType.HAVING,
 599        "ILIKE": TokenType.ILIKE,
 600        "IN": TokenType.IN,
 601        "INDEX": TokenType.INDEX,
 602        "INET": TokenType.INET,
 603        "INNER": TokenType.INNER,
 604        "INSERT": TokenType.INSERT,
 605        "INTERVAL": TokenType.INTERVAL,
 606        "INTERSECT": TokenType.INTERSECT,
 607        "INTO": TokenType.INTO,
 608        "IS": TokenType.IS,
 609        "ISNULL": TokenType.ISNULL,
 610        "JOIN": TokenType.JOIN,
 611        "KEEP": TokenType.KEEP,
 612        "KILL": TokenType.KILL,
 613        "LATERAL": TokenType.LATERAL,
 614        "LEFT": TokenType.LEFT,
 615        "LIKE": TokenType.LIKE,
 616        "LIMIT": TokenType.LIMIT,
 617        "LOAD": TokenType.LOAD,
 618        "LOCK": TokenType.LOCK,
 619        "MERGE": TokenType.MERGE,
 620        "NATURAL": TokenType.NATURAL,
 621        "NEXT": TokenType.NEXT,
 622        "NOT": TokenType.NOT,
 623        "NOTNULL": TokenType.NOTNULL,
 624        "NULL": TokenType.NULL,
 625        "OBJECT": TokenType.OBJECT,
 626        "OFFSET": TokenType.OFFSET,
 627        "ON": TokenType.ON,
 628        "OR": TokenType.OR,
 629        "XOR": TokenType.XOR,
 630        "ORDER BY": TokenType.ORDER_BY,
 631        "ORDINALITY": TokenType.ORDINALITY,
 632        "OUTER": TokenType.OUTER,
 633        "OVER": TokenType.OVER,
 634        "OVERLAPS": TokenType.OVERLAPS,
 635        "OVERWRITE": TokenType.OVERWRITE,
 636        "PARTITION": TokenType.PARTITION,
 637        "PARTITION BY": TokenType.PARTITION_BY,
 638        "PARTITIONED BY": TokenType.PARTITION_BY,
 639        "PARTITIONED_BY": TokenType.PARTITION_BY,
 640        "PERCENT": TokenType.PERCENT,
 641        "PIVOT": TokenType.PIVOT,
 642        "PRAGMA": TokenType.PRAGMA,
 643        "PRIMARY KEY": TokenType.PRIMARY_KEY,
 644        "PROCEDURE": TokenType.PROCEDURE,
 645        "QUALIFY": TokenType.QUALIFY,
 646        "RANGE": TokenType.RANGE,
 647        "RECURSIVE": TokenType.RECURSIVE,
 648        "REGEXP": TokenType.RLIKE,
 649        "REPLACE": TokenType.REPLACE,
 650        "RETURNING": TokenType.RETURNING,
 651        "REFERENCES": TokenType.REFERENCES,
 652        "RIGHT": TokenType.RIGHT,
 653        "RLIKE": TokenType.RLIKE,
 654        "ROLLBACK": TokenType.ROLLBACK,
 655        "ROLLUP": TokenType.ROLLUP,
 656        "ROW": TokenType.ROW,
 657        "ROWS": TokenType.ROWS,
 658        "SCHEMA": TokenType.SCHEMA,
 659        "SELECT": TokenType.SELECT,
 660        "SEMI": TokenType.SEMI,
 661        "SET": TokenType.SET,
 662        "SETTINGS": TokenType.SETTINGS,
 663        "SHOW": TokenType.SHOW,
 664        "SIMILAR TO": TokenType.SIMILAR_TO,
 665        "SOME": TokenType.SOME,
 666        "SORT BY": TokenType.SORT_BY,
 667        "START WITH": TokenType.START_WITH,
 668        "TABLE": TokenType.TABLE,
 669        "TABLESAMPLE": TokenType.TABLE_SAMPLE,
 670        "TEMP": TokenType.TEMPORARY,
 671        "TEMPORARY": TokenType.TEMPORARY,
 672        "THEN": TokenType.THEN,
 673        "TRUE": TokenType.TRUE,
 674        "UNION": TokenType.UNION,
 675        "UNKNOWN": TokenType.UNKNOWN,
 676        "UNNEST": TokenType.UNNEST,
 677        "UNPIVOT": TokenType.UNPIVOT,
 678        "UPDATE": TokenType.UPDATE,
 679        "USE": TokenType.USE,
 680        "USING": TokenType.USING,
 681        "UUID": TokenType.UUID,
 682        "VALUES": TokenType.VALUES,
 683        "VIEW": TokenType.VIEW,
 684        "VOLATILE": TokenType.VOLATILE,
 685        "WHEN": TokenType.WHEN,
 686        "WHERE": TokenType.WHERE,
 687        "WINDOW": TokenType.WINDOW,
 688        "WITH": TokenType.WITH,
 689        "APPLY": TokenType.APPLY,
 690        "ARRAY": TokenType.ARRAY,
 691        "BIT": TokenType.BIT,
 692        "BOOL": TokenType.BOOLEAN,
 693        "BOOLEAN": TokenType.BOOLEAN,
 694        "BYTE": TokenType.TINYINT,
 695        "MEDIUMINT": TokenType.MEDIUMINT,
 696        "TINYINT": TokenType.TINYINT,
 697        "SHORT": TokenType.SMALLINT,
 698        "SMALLINT": TokenType.SMALLINT,
 699        "INT128": TokenType.INT128,
 700        "INT2": TokenType.SMALLINT,
 701        "INTEGER": TokenType.INT,
 702        "INT": TokenType.INT,
 703        "INT4": TokenType.INT,
 704        "LONG": TokenType.BIGINT,
 705        "BIGINT": TokenType.BIGINT,
 706        "INT8": TokenType.BIGINT,
 707        "DEC": TokenType.DECIMAL,
 708        "DECIMAL": TokenType.DECIMAL,
 709        "BIGDECIMAL": TokenType.BIGDECIMAL,
 710        "BIGNUMERIC": TokenType.BIGDECIMAL,
 711        "MAP": TokenType.MAP,
 712        "NULLABLE": TokenType.NULLABLE,
 713        "NUMBER": TokenType.DECIMAL,
 714        "NUMERIC": TokenType.DECIMAL,
 715        "FIXED": TokenType.DECIMAL,
 716        "REAL": TokenType.FLOAT,
 717        "FLOAT": TokenType.FLOAT,
 718        "FLOAT4": TokenType.FLOAT,
 719        "FLOAT8": TokenType.DOUBLE,
 720        "DOUBLE": TokenType.DOUBLE,
 721        "DOUBLE PRECISION": TokenType.DOUBLE,
 722        "JSON": TokenType.JSON,
 723        "CHAR": TokenType.CHAR,
 724        "CHARACTER": TokenType.CHAR,
 725        "NCHAR": TokenType.NCHAR,
 726        "VARCHAR": TokenType.VARCHAR,
 727        "VARCHAR2": TokenType.VARCHAR,
 728        "NVARCHAR": TokenType.NVARCHAR,
 729        "NVARCHAR2": TokenType.NVARCHAR,
 730        "STR": TokenType.TEXT,
 731        "STRING": TokenType.TEXT,
 732        "TEXT": TokenType.TEXT,
 733        "LONGTEXT": TokenType.LONGTEXT,
 734        "MEDIUMTEXT": TokenType.MEDIUMTEXT,
 735        "TINYTEXT": TokenType.TINYTEXT,
 736        "CLOB": TokenType.TEXT,
 737        "LONGVARCHAR": TokenType.TEXT,
 738        "BINARY": TokenType.BINARY,
 739        "BLOB": TokenType.VARBINARY,
 740        "LONGBLOB": TokenType.LONGBLOB,
 741        "MEDIUMBLOB": TokenType.MEDIUMBLOB,
 742        "TINYBLOB": TokenType.TINYBLOB,
 743        "BYTEA": TokenType.VARBINARY,
 744        "VARBINARY": TokenType.VARBINARY,
 745        "TIME": TokenType.TIME,
 746        "TIMETZ": TokenType.TIMETZ,
 747        "TIMESTAMP": TokenType.TIMESTAMP,
 748        "TIMESTAMPTZ": TokenType.TIMESTAMPTZ,
 749        "TIMESTAMPLTZ": TokenType.TIMESTAMPLTZ,
 750        "DATE": TokenType.DATE,
 751        "DATETIME": TokenType.DATETIME,
 752        "INT4RANGE": TokenType.INT4RANGE,
 753        "INT4MULTIRANGE": TokenType.INT4MULTIRANGE,
 754        "INT8RANGE": TokenType.INT8RANGE,
 755        "INT8MULTIRANGE": TokenType.INT8MULTIRANGE,
 756        "NUMRANGE": TokenType.NUMRANGE,
 757        "NUMMULTIRANGE": TokenType.NUMMULTIRANGE,
 758        "TSRANGE": TokenType.TSRANGE,
 759        "TSMULTIRANGE": TokenType.TSMULTIRANGE,
 760        "TSTZRANGE": TokenType.TSTZRANGE,
 761        "TSTZMULTIRANGE": TokenType.TSTZMULTIRANGE,
 762        "DATERANGE": TokenType.DATERANGE,
 763        "DATEMULTIRANGE": TokenType.DATEMULTIRANGE,
 764        "UNIQUE": TokenType.UNIQUE,
 765        "STRUCT": TokenType.STRUCT,
 766        "VARIANT": TokenType.VARIANT,
 767        "ALTER": TokenType.ALTER,
 768        "ANALYZE": TokenType.COMMAND,
 769        "CALL": TokenType.COMMAND,
 770        "COMMENT": TokenType.COMMENT,
 771        "COPY": TokenType.COMMAND,
 772        "EXPLAIN": TokenType.COMMAND,
 773        "GRANT": TokenType.COMMAND,
 774        "OPTIMIZE": TokenType.COMMAND,
 775        "PREPARE": TokenType.COMMAND,
 776        "TRUNCATE": TokenType.COMMAND,
 777        "VACUUM": TokenType.COMMAND,
 778        "USER-DEFINED": TokenType.USERDEFINED,
 779        "FOR VERSION": TokenType.VERSION_SNAPSHOT,
 780        "FOR TIMESTAMP": TokenType.TIMESTAMP_SNAPSHOT,
 781    }
 782
 783    WHITE_SPACE: t.Dict[t.Optional[str], TokenType] = {
 784        " ": TokenType.SPACE,
 785        "\t": TokenType.SPACE,
 786        "\n": TokenType.BREAK,
 787        "\r": TokenType.BREAK,
 788        "\r\n": TokenType.BREAK,
 789    }
 790
 791    COMMANDS = {
 792        TokenType.COMMAND,
 793        TokenType.EXECUTE,
 794        TokenType.FETCH,
 795        TokenType.SHOW,
 796    }
 797
 798    COMMAND_PREFIX_TOKENS = {TokenType.SEMICOLON, TokenType.BEGIN}
 799
 800    # handle numeric literals like in hive (3L = BIGINT)
 801    NUMERIC_LITERALS: t.Dict[str, str] = {}
 802    ENCODE: t.Optional[str] = None
 803
 804    COMMENTS = ["--", ("/*", "*/")]
 805
 806    __slots__ = (
 807        "sql",
 808        "size",
 809        "tokens",
 810        "_start",
 811        "_current",
 812        "_line",
 813        "_col",
 814        "_comments",
 815        "_char",
 816        "_end",
 817        "_peek",
 818        "_prev_token_line",
 819    )
 820
 821    def __init__(self) -> None:
 822        self.reset()
 823
 824    def reset(self) -> None:
 825        self.sql = ""
 826        self.size = 0
 827        self.tokens: t.List[Token] = []
 828        self._start = 0
 829        self._current = 0
 830        self._line = 1
 831        self._col = 0
 832        self._comments: t.List[str] = []
 833
 834        self._char = ""
 835        self._end = False
 836        self._peek = ""
 837        self._prev_token_line = -1
 838
 839    def tokenize(self, sql: str) -> t.List[Token]:
 840        """Returns a list of tokens corresponding to the SQL string `sql`."""
 841        self.reset()
 842        self.sql = sql
 843        self.size = len(sql)
 844
 845        try:
 846            self._scan()
 847        except Exception as e:
 848            start = max(self._current - 50, 0)
 849            end = min(self._current + 50, self.size - 1)
 850            context = self.sql[start:end]
 851            raise TokenError(f"Error tokenizing '{context}'") from e
 852
 853        return self.tokens
 854
 855    def _scan(self, until: t.Optional[t.Callable] = None) -> None:
 856        while self.size and not self._end:
 857            self._start = self._current
 858            self._advance()
 859
 860            if self._char is None:
 861                break
 862
 863            if self._char not in self.WHITE_SPACE:
 864                if self._char.isdigit():
 865                    self._scan_number()
 866                elif self._char in self._IDENTIFIERS:
 867                    self._scan_identifier(self._IDENTIFIERS[self._char])
 868                else:
 869                    self._scan_keywords()
 870
 871            if until and until():
 872                break
 873
 874        if self.tokens and self._comments:
 875            self.tokens[-1].comments.extend(self._comments)
 876
 877    def _chars(self, size: int) -> str:
 878        if size == 1:
 879            return self._char
 880
 881        start = self._current - 1
 882        end = start + size
 883
 884        return self.sql[start:end] if end <= self.size else ""
 885
 886    def _advance(self, i: int = 1, alnum: bool = False) -> None:
 887        if self.WHITE_SPACE.get(self._char) is TokenType.BREAK:
 888            self._col = 1
 889            self._line += 1
 890        else:
 891            self._col += i
 892
 893        self._current += i
 894        self._end = self._current >= self.size
 895        self._char = self.sql[self._current - 1]
 896        self._peek = "" if self._end else self.sql[self._current]
 897
 898        if alnum and self._char.isalnum():
 899            # Here we use local variables instead of attributes for better performance
 900            _col = self._col
 901            _current = self._current
 902            _end = self._end
 903            _peek = self._peek
 904
 905            while _peek.isalnum():
 906                _col += 1
 907                _current += 1
 908                _end = _current >= self.size
 909                _peek = "" if _end else self.sql[_current]
 910
 911            self._col = _col
 912            self._current = _current
 913            self._end = _end
 914            self._peek = _peek
 915            self._char = self.sql[_current - 1]
 916
 917    @property
 918    def _text(self) -> str:
 919        return self.sql[self._start : self._current]
 920
 921    def peek(self, i: int = 0) -> str:
 922        i = self._current + i
 923        if i < self.size:
 924            return self.sql[i]
 925        return ""
 926
 927    def _add(self, token_type: TokenType, text: t.Optional[str] = None) -> None:
 928        self._prev_token_line = self._line
 929
 930        if self._comments and token_type == TokenType.SEMICOLON and self.tokens:
 931            self.tokens[-1].comments.extend(self._comments)
 932            self._comments = []
 933
 934        self.tokens.append(
 935            Token(
 936                token_type,
 937                text=self._text if text is None else text,
 938                line=self._line,
 939                col=self._col,
 940                start=self._start,
 941                end=self._current - 1,
 942                comments=self._comments,
 943            )
 944        )
 945        self._comments = []
 946
 947        # If we have either a semicolon or a begin token before the command's token, we'll parse
 948        # whatever follows the command's token as a string
 949        if (
 950            token_type in self.COMMANDS
 951            and self._peek != ";"
 952            and (len(self.tokens) == 1 or self.tokens[-2].token_type in self.COMMAND_PREFIX_TOKENS)
 953        ):
 954            start = self._current
 955            tokens = len(self.tokens)
 956            self._scan(lambda: self._peek == ";")
 957            self.tokens = self.tokens[:tokens]
 958            text = self.sql[start : self._current].strip()
 959            if text:
 960                self._add(TokenType.STRING, text)
 961
 962    def _scan_keywords(self) -> None:
 963        size = 0
 964        word = None
 965        chars = self._text
 966        char = chars
 967        prev_space = False
 968        skip = False
 969        trie = self._KEYWORD_TRIE
 970        single_token = char in self.SINGLE_TOKENS
 971
 972        while chars:
 973            if skip:
 974                result = TrieResult.PREFIX
 975            else:
 976                result, trie = in_trie(trie, char.upper())
 977
 978            if result == TrieResult.FAILED:
 979                break
 980            if result == TrieResult.EXISTS:
 981                word = chars
 982
 983            end = self._current + size
 984            size += 1
 985
 986            if end < self.size:
 987                char = self.sql[end]
 988                single_token = single_token or char in self.SINGLE_TOKENS
 989                is_space = char in self.WHITE_SPACE
 990
 991                if not is_space or not prev_space:
 992                    if is_space:
 993                        char = " "
 994                    chars += char
 995                    prev_space = is_space
 996                    skip = False
 997                else:
 998                    skip = True
 999            else:
1000                char = ""
1001                chars = " "
1002
1003        if word:
1004            if self._scan_string(word):
1005                return
1006            if self._scan_comment(word):
1007                return
1008            if prev_space or single_token or not char:
1009                self._advance(size - 1)
1010                word = word.upper()
1011                self._add(self.KEYWORDS[word], text=word)
1012                return
1013
1014        if self._char in self.SINGLE_TOKENS:
1015            self._add(self.SINGLE_TOKENS[self._char], text=self._char)
1016            return
1017
1018        self._scan_var()
1019
1020    def _scan_comment(self, comment_start: str) -> bool:
1021        if comment_start not in self._COMMENTS:
1022            return False
1023
1024        comment_start_line = self._line
1025        comment_start_size = len(comment_start)
1026        comment_end = self._COMMENTS[comment_start]
1027
1028        if comment_end:
1029            # Skip the comment's start delimiter
1030            self._advance(comment_start_size)
1031
1032            comment_end_size = len(comment_end)
1033            while not self._end and self._chars(comment_end_size) != comment_end:
1034                self._advance(alnum=True)
1035
1036            self._comments.append(self._text[comment_start_size : -comment_end_size + 1])
1037            self._advance(comment_end_size - 1)
1038        else:
1039            while not self._end and not self.WHITE_SPACE.get(self._peek) is TokenType.BREAK:
1040                self._advance(alnum=True)
1041            self._comments.append(self._text[comment_start_size:])
1042
1043        # Leading comment is attached to the succeeding token, whilst trailing comment to the preceding.
1044        # Multiple consecutive comments are preserved by appending them to the current comments list.
1045        if comment_start_line == self._prev_token_line:
1046            self.tokens[-1].comments.extend(self._comments)
1047            self._comments = []
1048            self._prev_token_line = self._line
1049
1050        return True
1051
1052    def _scan_number(self) -> None:
1053        if self._char == "0":
1054            peek = self._peek.upper()
1055            if peek == "B":
1056                return self._scan_bits() if self.BIT_STRINGS else self._add(TokenType.NUMBER)
1057            elif peek == "X":
1058                return self._scan_hex() if self.HEX_STRINGS else self._add(TokenType.NUMBER)
1059
1060        decimal = False
1061        scientific = 0
1062
1063        while True:
1064            if self._peek.isdigit():
1065                self._advance()
1066            elif self._peek == "." and not decimal:
1067                after = self.peek(1)
1068                if after.isdigit() or not after.isalpha():
1069                    decimal = True
1070                    self._advance()
1071                else:
1072                    return self._add(TokenType.VAR)
1073            elif self._peek in ("-", "+") and scientific == 1:
1074                scientific += 1
1075                self._advance()
1076            elif self._peek.upper() == "E" and not scientific:
1077                scientific += 1
1078                self._advance()
1079            elif self._peek.isidentifier():
1080                number_text = self._text
1081                literal = ""
1082
1083                while self._peek.strip() and self._peek not in self.SINGLE_TOKENS:
1084                    literal += self._peek
1085                    self._advance()
1086
1087                token_type = self.KEYWORDS.get(self.NUMERIC_LITERALS.get(literal.upper(), ""))
1088
1089                if token_type:
1090                    self._add(TokenType.NUMBER, number_text)
1091                    self._add(TokenType.DCOLON, "::")
1092                    return self._add(token_type, literal)
1093                elif self.IDENTIFIERS_CAN_START_WITH_DIGIT:
1094                    return self._add(TokenType.VAR)
1095
1096                self._advance(-len(literal))
1097                return self._add(TokenType.NUMBER, number_text)
1098            else:
1099                return self._add(TokenType.NUMBER)
1100
1101    def _scan_bits(self) -> None:
1102        self._advance()
1103        value = self._extract_value()
1104        try:
1105            # If `value` can't be converted to a binary, fallback to tokenizing it as an identifier
1106            int(value, 2)
1107            self._add(TokenType.BIT_STRING, value[2:])  # Drop the 0b
1108        except ValueError:
1109            self._add(TokenType.IDENTIFIER)
1110
1111    def _scan_hex(self) -> None:
1112        self._advance()
1113        value = self._extract_value()
1114        try:
1115            # If `value` can't be converted to a hex, fallback to tokenizing it as an identifier
1116            int(value, 16)
1117            self._add(TokenType.HEX_STRING, value[2:])  # Drop the 0x
1118        except ValueError:
1119            self._add(TokenType.IDENTIFIER)
1120
1121    def _extract_value(self) -> str:
1122        while True:
1123            char = self._peek.strip()
1124            if char and char not in self.SINGLE_TOKENS:
1125                self._advance(alnum=True)
1126            else:
1127                break
1128
1129        return self._text
1130
1131    def _scan_string(self, start: str) -> bool:
1132        base = None
1133        token_type = TokenType.STRING
1134
1135        if start in self._QUOTES:
1136            end = self._QUOTES[start]
1137        elif start in self._FORMAT_STRINGS:
1138            end, token_type = self._FORMAT_STRINGS[start]
1139
1140            if token_type == TokenType.HEX_STRING:
1141                base = 16
1142            elif token_type == TokenType.BIT_STRING:
1143                base = 2
1144            elif token_type == TokenType.HEREDOC_STRING:
1145                self._advance()
1146                tag = "" if self._char == end else self._extract_string(end)
1147                end = f"{start}{tag}{end}"
1148        else:
1149            return False
1150
1151        self._advance(len(start))
1152        text = self._extract_string(end)
1153
1154        if base:
1155            try:
1156                int(text, base)
1157            except:
1158                raise TokenError(
1159                    f"Numeric string contains invalid characters from {self._line}:{self._start}"
1160                )
1161        else:
1162            text = text.encode(self.ENCODE).decode(self.ENCODE) if self.ENCODE else text
1163
1164        self._add(token_type, text)
1165        return True
1166
1167    def _scan_identifier(self, identifier_end: str) -> None:
1168        self._advance()
1169        text = self._extract_string(identifier_end, self._IDENTIFIER_ESCAPES)
1170        self._add(TokenType.IDENTIFIER, text)
1171
1172    def _scan_var(self) -> None:
1173        while True:
1174            char = self._peek.strip()
1175            if char and (char in self.VAR_SINGLE_TOKENS or char not in self.SINGLE_TOKENS):
1176                self._advance(alnum=True)
1177            else:
1178                break
1179
1180        self._add(
1181            TokenType.VAR
1182            if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER
1183            else self.KEYWORDS.get(self._text.upper(), TokenType.VAR)
1184        )
1185
1186    def _extract_string(self, delimiter: str, escapes=None) -> str:
1187        text = ""
1188        delim_size = len(delimiter)
1189        escapes = self._STRING_ESCAPES if escapes is None else escapes
1190
1191        while True:
1192            if (
1193                self._char in escapes
1194                and (self._peek == delimiter or self._peek in escapes)
1195                and (self._char not in self._QUOTES or self._char == self._peek)
1196            ):
1197                if self._peek == delimiter:
1198                    text += self._peek
1199                else:
1200                    text += self._char + self._peek
1201
1202                if self._current + 1 < self.size:
1203                    self._advance(2)
1204                else:
1205                    raise TokenError(f"Missing {delimiter} from {self._line}:{self._current}")
1206            else:
1207                if self._chars(delim_size) == delimiter:
1208                    if delim_size > 1:
1209                        self._advance(delim_size - 1)
1210                    break
1211
1212                if self._end:
1213                    raise TokenError(f"Missing {delimiter} from {self._line}:{self._start}")
1214
1215                if self.ESCAPE_SEQUENCES and self._peek and self._char in self.STRING_ESCAPES:
1216                    escaped_sequence = self.ESCAPE_SEQUENCES.get(self._char + self._peek)
1217                    if escaped_sequence:
1218                        self._advance(2)
1219                        text += escaped_sequence
1220                        continue
1221
1222                current = self._current - 1
1223                self._advance(alnum=True)
1224                text += self.sql[current : self._current - 1]
1225
1226        return text
SINGLE_TOKENS = {'(': <TokenType.L_PAREN: 'L_PAREN'>, ')': <TokenType.R_PAREN: 'R_PAREN'>, '[': <TokenType.L_BRACKET: 'L_BRACKET'>, ']': <TokenType.R_BRACKET: 'R_BRACKET'>, '{': <TokenType.L_BRACE: 'L_BRACE'>, '}': <TokenType.R_BRACE: 'R_BRACE'>, '&': <TokenType.AMP: 'AMP'>, '^': <TokenType.CARET: 'CARET'>, ':': <TokenType.COLON: 'COLON'>, ',': <TokenType.COMMA: 'COMMA'>, '.': <TokenType.DOT: 'DOT'>, '-': <TokenType.DASH: 'DASH'>, '=': <TokenType.EQ: 'EQ'>, '>': <TokenType.GT: 'GT'>, '<': <TokenType.LT: 'LT'>, '%': <TokenType.MOD: 'MOD'>, '!': <TokenType.NOT: 'NOT'>, '|': <TokenType.PIPE: 'PIPE'>, '+': <TokenType.PLUS: 'PLUS'>, ';': <TokenType.SEMICOLON: 'SEMICOLON'>, '/': <TokenType.SLASH: 'SLASH'>, '\\': <TokenType.BACKSLASH: 'BACKSLASH'>, '*': <TokenType.STAR: 'STAR'>, '~': <TokenType.TILDA: 'TILDA'>, '?': <TokenType.PLACEHOLDER: 'PLACEHOLDER'>, '@': <TokenType.PARAMETER: 'PARAMETER'>, "'": <TokenType.QUOTE: 'QUOTE'>, '`': <TokenType.IDENTIFIER: 'IDENTIFIER'>, '"': <TokenType.IDENTIFIER: 'IDENTIFIER'>, '#': <TokenType.HASH: 'HASH'>}
BIT_STRINGS: List[Union[str, Tuple[str, str]]] = []
BYTE_STRINGS: List[Union[str, Tuple[str, str]]] = []
HEX_STRINGS: List[Union[str, Tuple[str, str]]] = []
RAW_STRINGS: List[Union[str, Tuple[str, str]]] = []
HEREDOC_STRINGS: List[Union[str, Tuple[str, str]]] = []
IDENTIFIERS: List[Union[str, Tuple[str, str]]] = ['"']
IDENTIFIER_ESCAPES = ['"']
QUOTES: List[Union[str, Tuple[str, str]]] = ["'"]
STRING_ESCAPES = ["'"]
VAR_SINGLE_TOKENS: Set[str] = set()
ESCAPE_SEQUENCES: Dict[str, str] = {}
IDENTIFIERS_CAN_START_WITH_DIGIT: bool = False
KEYWORDS: Dict[str, TokenType] = {'{%': <TokenType.BLOCK_START: 'BLOCK_START'>, '{%+': <TokenType.BLOCK_START: 'BLOCK_START'>, '{%-': <TokenType.BLOCK_START: 'BLOCK_START'>, '%}': <TokenType.BLOCK_END: 'BLOCK_END'>, '+%}': <TokenType.BLOCK_END: 'BLOCK_END'>, '-%}': <TokenType.BLOCK_END: 'BLOCK_END'>, '{{+': <TokenType.BLOCK_START: 'BLOCK_START'>, '{{-': <TokenType.BLOCK_START: 'BLOCK_START'>, '+}}': <TokenType.BLOCK_END: 'BLOCK_END'>, '-}}': <TokenType.BLOCK_END: 'BLOCK_END'>, '/*+': <TokenType.HINT: 'HINT'>, '==': <TokenType.EQ: 'EQ'>, '::': <TokenType.DCOLON: 'DCOLON'>, '||': <TokenType.DPIPE: 'DPIPE'>, '>=': <TokenType.GTE: 'GTE'>, '<=': <TokenType.LTE: 'LTE'>, '<>': <TokenType.NEQ: 'NEQ'>, '!=': <TokenType.NEQ: 'NEQ'>, '<=>': <TokenType.NULLSAFE_EQ: 'NULLSAFE_EQ'>, '->': <TokenType.ARROW: 'ARROW'>, '->>': <TokenType.DARROW: 'DARROW'>, '=>': <TokenType.FARROW: 'FARROW'>, '#>': <TokenType.HASH_ARROW: 'HASH_ARROW'>, '#>>': <TokenType.DHASH_ARROW: 'DHASH_ARROW'>, '<->': <TokenType.LR_ARROW: 'LR_ARROW'>, '&&': <TokenType.DAMP: 'DAMP'>, '??': <TokenType.DQMARK: 'DQMARK'>, 'ALL': <TokenType.ALL: 'ALL'>, 'ALWAYS': <TokenType.ALWAYS: 'ALWAYS'>, 'AND': <TokenType.AND: 'AND'>, 'ANTI': <TokenType.ANTI: 'ANTI'>, 'ANY': <TokenType.ANY: 'ANY'>, 'ASC': <TokenType.ASC: 'ASC'>, 'AS': <TokenType.ALIAS: 'ALIAS'>, 'ASOF': <TokenType.ASOF: 'ASOF'>, 'AUTOINCREMENT': <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, 'AUTO_INCREMENT': <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, 'BEGIN': <TokenType.BEGIN: 'BEGIN'>, 'BETWEEN': <TokenType.BETWEEN: 'BETWEEN'>, 'CACHE': <TokenType.CACHE: 'CACHE'>, 'UNCACHE': <TokenType.UNCACHE: 'UNCACHE'>, 'CASE': <TokenType.CASE: 'CASE'>, 'CHARACTER SET': <TokenType.CHARACTER_SET: 'CHARACTER_SET'>, 'CLUSTER BY': <TokenType.CLUSTER_BY: 'CLUSTER_BY'>, 'COLLATE': <TokenType.COLLATE: 'COLLATE'>, 'COLUMN': <TokenType.COLUMN: 'COLUMN'>, 'COMMIT': <TokenType.COMMIT: 'COMMIT'>, 'CONNECT BY': <TokenType.CONNECT_BY: 'CONNECT_BY'>, 'CONSTRAINT': <TokenType.CONSTRAINT: 'CONSTRAINT'>, 'CREATE': <TokenType.CREATE: 'CREATE'>, 'CROSS': <TokenType.CROSS: 'CROSS'>, 'CUBE': <TokenType.CUBE: 'CUBE'>, 'CURRENT_DATE': <TokenType.CURRENT_DATE: 'CURRENT_DATE'>, 'CURRENT_TIME': <TokenType.CURRENT_TIME: 'CURRENT_TIME'>, 'CURRENT_TIMESTAMP': <TokenType.CURRENT_TIMESTAMP: 'CURRENT_TIMESTAMP'>, 'CURRENT_USER': <TokenType.CURRENT_USER: 'CURRENT_USER'>, 'DATABASE': <TokenType.DATABASE: 'DATABASE'>, 'DEFAULT': <TokenType.DEFAULT: 'DEFAULT'>, 'DELETE': <TokenType.DELETE: 'DELETE'>, 'DESC': <TokenType.DESC: 'DESC'>, 'DESCRIBE': <TokenType.DESCRIBE: 'DESCRIBE'>, 'DISTINCT': <TokenType.DISTINCT: 'DISTINCT'>, 'DISTRIBUTE BY': <TokenType.DISTRIBUTE_BY: 'DISTRIBUTE_BY'>, 'DIV': <TokenType.DIV: 'DIV'>, 'DROP': <TokenType.DROP: 'DROP'>, 'ELSE': <TokenType.ELSE: 'ELSE'>, 'END': <TokenType.END: 'END'>, 'ESCAPE': <TokenType.ESCAPE: 'ESCAPE'>, 'EXCEPT': <TokenType.EXCEPT: 'EXCEPT'>, 'EXECUTE': <TokenType.EXECUTE: 'EXECUTE'>, 'EXISTS': <TokenType.EXISTS: 'EXISTS'>, 'FALSE': <TokenType.FALSE: 'FALSE'>, 'FETCH': <TokenType.FETCH: 'FETCH'>, 'FILTER': <TokenType.FILTER: 'FILTER'>, 'FIRST': <TokenType.FIRST: 'FIRST'>, 'FULL': <TokenType.FULL: 'FULL'>, 'FUNCTION': <TokenType.FUNCTION: 'FUNCTION'>, 'FOR': <TokenType.FOR: 'FOR'>, 'FOREIGN KEY': <TokenType.FOREIGN_KEY: 'FOREIGN_KEY'>, 'FORMAT': <TokenType.FORMAT: 'FORMAT'>, 'FROM': <TokenType.FROM: 'FROM'>, 'GEOGRAPHY': <TokenType.GEOGRAPHY: 'GEOGRAPHY'>, 'GEOMETRY': <TokenType.GEOMETRY: 'GEOMETRY'>, 'GLOB': <TokenType.GLOB: 'GLOB'>, 'GROUP BY': <TokenType.GROUP_BY: 'GROUP_BY'>, 'GROUPING SETS': <TokenType.GROUPING_SETS: 'GROUPING_SETS'>, 'HAVING': <TokenType.HAVING: 'HAVING'>, 'ILIKE': <TokenType.ILIKE: 'ILIKE'>, 'IN': <TokenType.IN: 'IN'>, 'INDEX': <TokenType.INDEX: 'INDEX'>, 'INET': <TokenType.INET: 'INET'>, 'INNER': <TokenType.INNER: 'INNER'>, 'INSERT': <TokenType.INSERT: 'INSERT'>, 'INTERVAL': <TokenType.INTERVAL: 'INTERVAL'>, 'INTERSECT': <TokenType.INTERSECT: 'INTERSECT'>, 'INTO': <TokenType.INTO: 'INTO'>, 'IS': <TokenType.IS: 'IS'>, 'ISNULL': <TokenType.ISNULL: 'ISNULL'>, 'JOIN': <TokenType.JOIN: 'JOIN'>, 'KEEP': <TokenType.KEEP: 'KEEP'>, 'KILL': <TokenType.KILL: 'KILL'>, 'LATERAL': <TokenType.LATERAL: 'LATERAL'>, 'LEFT': <TokenType.LEFT: 'LEFT'>, 'LIKE': <TokenType.LIKE: 'LIKE'>, 'LIMIT': <TokenType.LIMIT: 'LIMIT'>, 'LOAD': <TokenType.LOAD: 'LOAD'>, 'LOCK': <TokenType.LOCK: 'LOCK'>, 'MERGE': <TokenType.MERGE: 'MERGE'>, 'NATURAL': <TokenType.NATURAL: 'NATURAL'>, 'NEXT': <TokenType.NEXT: 'NEXT'>, 'NOT': <TokenType.NOT: 'NOT'>, 'NOTNULL': <TokenType.NOTNULL: 'NOTNULL'>, 'NULL': <TokenType.NULL: 'NULL'>, 'OBJECT': <TokenType.OBJECT: 'OBJECT'>, 'OFFSET': <TokenType.OFFSET: 'OFFSET'>, 'ON': <TokenType.ON: 'ON'>, 'OR': <TokenType.OR: 'OR'>, 'XOR': <TokenType.XOR: 'XOR'>, 'ORDER BY': <TokenType.ORDER_BY: 'ORDER_BY'>, 'ORDINALITY': <TokenType.ORDINALITY: 'ORDINALITY'>, 'OUTER': <TokenType.OUTER: 'OUTER'>, 'OVER': <TokenType.OVER: 'OVER'>, 'OVERLAPS': <TokenType.OVERLAPS: 'OVERLAPS'>, 'OVERWRITE': <TokenType.OVERWRITE: 'OVERWRITE'>, 'PARTITION': <TokenType.PARTITION: 'PARTITION'>, 'PARTITION BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PARTITIONED BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PARTITIONED_BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PERCENT': <TokenType.PERCENT: 'PERCENT'>, 'PIVOT': <TokenType.PIVOT: 'PIVOT'>, 'PRAGMA': <TokenType.PRAGMA: 'PRAGMA'>, 'PRIMARY KEY': <TokenType.PRIMARY_KEY: 'PRIMARY_KEY'>, 'PROCEDURE': <TokenType.PROCEDURE: 'PROCEDURE'>, 'QUALIFY': <TokenType.QUALIFY: 'QUALIFY'>, 'RANGE': <TokenType.RANGE: 'RANGE'>, 'RECURSIVE': <TokenType.RECURSIVE: 'RECURSIVE'>, 'REGEXP': <TokenType.RLIKE: 'RLIKE'>, 'REPLACE': <TokenType.REPLACE: 'REPLACE'>, 'RETURNING': <TokenType.RETURNING: 'RETURNING'>, 'REFERENCES': <TokenType.REFERENCES: 'REFERENCES'>, 'RIGHT': <TokenType.RIGHT: 'RIGHT'>, 'RLIKE': <TokenType.RLIKE: 'RLIKE'>, 'ROLLBACK': <TokenType.ROLLBACK: 'ROLLBACK'>, 'ROLLUP': <TokenType.ROLLUP: 'ROLLUP'>, 'ROW': <TokenType.ROW: 'ROW'>, 'ROWS': <TokenType.ROWS: 'ROWS'>, 'SCHEMA': <TokenType.SCHEMA: 'SCHEMA'>, 'SELECT': <TokenType.SELECT: 'SELECT'>, 'SEMI': <TokenType.SEMI: 'SEMI'>, 'SET': <TokenType.SET: 'SET'>, 'SETTINGS': <TokenType.SETTINGS: 'SETTINGS'>, 'SHOW': <TokenType.SHOW: 'SHOW'>, 'SIMILAR TO': <TokenType.SIMILAR_TO: 'SIMILAR_TO'>, 'SOME': <TokenType.SOME: 'SOME'>, 'SORT BY': <TokenType.SORT_BY: 'SORT_BY'>, 'START WITH': <TokenType.START_WITH: 'START_WITH'>, 'TABLE': <TokenType.TABLE: 'TABLE'>, 'TABLESAMPLE': <TokenType.TABLE_SAMPLE: 'TABLE_SAMPLE'>, 'TEMP': <TokenType.TEMPORARY: 'TEMPORARY'>, 'TEMPORARY': <TokenType.TEMPORARY: 'TEMPORARY'>, 'THEN': <TokenType.THEN: 'THEN'>, 'TRUE': <TokenType.TRUE: 'TRUE'>, 'UNION': <TokenType.UNION: 'UNION'>, 'UNKNOWN': <TokenType.UNKNOWN: 'UNKNOWN'>, 'UNNEST': <TokenType.UNNEST: 'UNNEST'>, 'UNPIVOT': <TokenType.UNPIVOT: 'UNPIVOT'>, 'UPDATE': <TokenType.UPDATE: 'UPDATE'>, 'USE': <TokenType.USE: 'USE'>, 'USING': <TokenType.USING: 'USING'>, 'UUID': <TokenType.UUID: 'UUID'>, 'VALUES': <TokenType.VALUES: 'VALUES'>, 'VIEW': <TokenType.VIEW: 'VIEW'>, 'VOLATILE': <TokenType.VOLATILE: 'VOLATILE'>, 'WHEN': <TokenType.WHEN: 'WHEN'>, 'WHERE': <TokenType.WHERE: 'WHERE'>, 'WINDOW': <TokenType.WINDOW: 'WINDOW'>, 'WITH': <TokenType.WITH: 'WITH'>, 'APPLY': <TokenType.APPLY: 'APPLY'>, 'ARRAY': <TokenType.ARRAY: 'ARRAY'>, 'BIT': <TokenType.BIT: 'BIT'>, 'BOOL': <TokenType.BOOLEAN: 'BOOLEAN'>, 'BOOLEAN': <TokenType.BOOLEAN: 'BOOLEAN'>, 'BYTE': <TokenType.TINYINT: 'TINYINT'>, 'MEDIUMINT': <TokenType.MEDIUMINT: 'MEDIUMINT'>, 'TINYINT': <TokenType.TINYINT: 'TINYINT'>, 'SHORT': <TokenType.SMALLINT: 'SMALLINT'>, 'SMALLINT': <TokenType.SMALLINT: 'SMALLINT'>, 'INT128': <TokenType.INT128: 'INT128'>, 'INT2': <TokenType.SMALLINT: 'SMALLINT'>, 'INTEGER': <TokenType.INT: 'INT'>, 'INT': <TokenType.INT: 'INT'>, 'INT4': <TokenType.INT: 'INT'>, 'LONG': <TokenType.BIGINT: 'BIGINT'>, 'BIGINT': <TokenType.BIGINT: 'BIGINT'>, 'INT8': <TokenType.BIGINT: 'BIGINT'>, 'DEC': <TokenType.DECIMAL: 'DECIMAL'>, 'DECIMAL': <TokenType.DECIMAL: 'DECIMAL'>, 'BIGDECIMAL': <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, 'BIGNUMERIC': <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, 'MAP': <TokenType.MAP: 'MAP'>, 'NULLABLE': <TokenType.NULLABLE: 'NULLABLE'>, 'NUMBER': <TokenType.DECIMAL: 'DECIMAL'>, 'NUMERIC': <TokenType.DECIMAL: 'DECIMAL'>, 'FIXED': <TokenType.DECIMAL: 'DECIMAL'>, 'REAL': <TokenType.FLOAT: 'FLOAT'>, 'FLOAT': <TokenType.FLOAT: 'FLOAT'>, 'FLOAT4': <TokenType.FLOAT: 'FLOAT'>, 'FLOAT8': <TokenType.DOUBLE: 'DOUBLE'>, 'DOUBLE': <TokenType.DOUBLE: 'DOUBLE'>, 'DOUBLE PRECISION': <TokenType.DOUBLE: 'DOUBLE'>, 'JSON': <TokenType.JSON: 'JSON'>, 'CHAR': <TokenType.CHAR: 'CHAR'>, 'CHARACTER': <TokenType.CHAR: 'CHAR'>, 'NCHAR': <TokenType.NCHAR: 'NCHAR'>, 'VARCHAR': <TokenType.VARCHAR: 'VARCHAR'>, 'VARCHAR2': <TokenType.VARCHAR: 'VARCHAR'>, 'NVARCHAR': <TokenType.NVARCHAR: 'NVARCHAR'>, 'NVARCHAR2': <TokenType.NVARCHAR: 'NVARCHAR'>, 'STR': <TokenType.TEXT: 'TEXT'>, 'STRING': <TokenType.TEXT: 'TEXT'>, 'TEXT': <TokenType.TEXT: 'TEXT'>, 'LONGTEXT': <TokenType.LONGTEXT: 'LONGTEXT'>, 'MEDIUMTEXT': <TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>, 'TINYTEXT': <TokenType.TINYTEXT: 'TINYTEXT'>, 'CLOB': <TokenType.TEXT: 'TEXT'>, 'LONGVARCHAR': <TokenType.TEXT: 'TEXT'>, 'BINARY': <TokenType.BINARY: 'BINARY'>, 'BLOB': <TokenType.VARBINARY: 'VARBINARY'>, 'LONGBLOB': <TokenType.LONGBLOB: 'LONGBLOB'>, 'MEDIUMBLOB': <TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>, 'TINYBLOB': <TokenType.TINYBLOB: 'TINYBLOB'>, 'BYTEA': <TokenType.VARBINARY: 'VARBINARY'>, 'VARBINARY': <TokenType.VARBINARY: 'VARBINARY'>, 'TIME': <TokenType.TIME: 'TIME'>, 'TIMETZ': <TokenType.TIMETZ: 'TIMETZ'>, 'TIMESTAMP': <TokenType.TIMESTAMP: 'TIMESTAMP'>, 'TIMESTAMPTZ': <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>, 'TIMESTAMPLTZ': <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>, 'DATE': <TokenType.DATE: 'DATE'>, 'DATETIME': <TokenType.DATETIME: 'DATETIME'>, 'INT4RANGE': <TokenType.INT4RANGE: 'INT4RANGE'>, 'INT4MULTIRANGE': <TokenType.INT4MULTIRANGE: 'INT4MULTIRANGE'>, 'INT8RANGE': <TokenType.INT8RANGE: 'INT8RANGE'>, 'INT8MULTIRANGE': <TokenType.INT8MULTIRANGE: 'INT8MULTIRANGE'>, 'NUMRANGE': <TokenType.NUMRANGE: 'NUMRANGE'>, 'NUMMULTIRANGE': <TokenType.NUMMULTIRANGE: 'NUMMULTIRANGE'>, 'TSRANGE': <TokenType.TSRANGE: 'TSRANGE'>, 'TSMULTIRANGE': <TokenType.TSMULTIRANGE: 'TSMULTIRANGE'>, 'TSTZRANGE': <TokenType.TSTZRANGE: 'TSTZRANGE'>, 'TSTZMULTIRANGE': <TokenType.TSTZMULTIRANGE: 'TSTZMULTIRANGE'>, 'DATERANGE': <TokenType.DATERANGE: 'DATERANGE'>, 'DATEMULTIRANGE': <TokenType.DATEMULTIRANGE: 'DATEMULTIRANGE'>, 'UNIQUE': <TokenType.UNIQUE: 'UNIQUE'>, 'STRUCT': <TokenType.STRUCT: 'STRUCT'>, 'VARIANT': <TokenType.VARIANT: 'VARIANT'>, 'ALTER': <TokenType.ALTER: 'ALTER'>, 'ANALYZE': <TokenType.COMMAND: 'COMMAND'>, 'CALL': <TokenType.COMMAND: 'COMMAND'>, 'COMMENT': <TokenType.COMMENT: 'COMMENT'>, 'COPY': <TokenType.COMMAND: 'COMMAND'>, 'EXPLAIN': <TokenType.COMMAND: 'COMMAND'>, 'GRANT': <TokenType.COMMAND: 'COMMAND'>, 'OPTIMIZE': <TokenType.COMMAND: 'COMMAND'>, 'PREPARE': <TokenType.COMMAND: 'COMMAND'>, 'TRUNCATE': <TokenType.COMMAND: 'COMMAND'>, 'VACUUM': <TokenType.COMMAND: 'COMMAND'>, 'USER-DEFINED': <TokenType.USERDEFINED: 'USERDEFINED'>, 'FOR VERSION': <TokenType.VERSION_SNAPSHOT: 'VERSION_SNAPSHOT'>, 'FOR TIMESTAMP': <TokenType.TIMESTAMP_SNAPSHOT: 'TIMESTAMP_SNAPSHOT'>}
WHITE_SPACE: Dict[Optional[str], TokenType] = {' ': <TokenType.SPACE: 'SPACE'>, '\t': <TokenType.SPACE: 'SPACE'>, '\n': <TokenType.BREAK: 'BREAK'>, '\r': <TokenType.BREAK: 'BREAK'>, '\r\n': <TokenType.BREAK: 'BREAK'>}
COMMANDS = {<TokenType.EXECUTE: 'EXECUTE'>, <TokenType.COMMAND: 'COMMAND'>, <TokenType.FETCH: 'FETCH'>, <TokenType.SHOW: 'SHOW'>}
COMMAND_PREFIX_TOKENS = {<TokenType.SEMICOLON: 'SEMICOLON'>, <TokenType.BEGIN: 'BEGIN'>}
NUMERIC_LITERALS: Dict[str, str] = {}
ENCODE: Optional[str] = None
COMMENTS = ['--', ('/*', '*/')]
def reset(self) -> None:
824    def reset(self) -> None:
825        self.sql = ""
826        self.size = 0
827        self.tokens: t.List[Token] = []
828        self._start = 0
829        self._current = 0
830        self._line = 1
831        self._col = 0
832        self._comments: t.List[str] = []
833
834        self._char = ""
835        self._end = False
836        self._peek = ""
837        self._prev_token_line = -1
def tokenize(self, sql: str) -> List[Token]:
839    def tokenize(self, sql: str) -> t.List[Token]:
840        """Returns a list of tokens corresponding to the SQL string `sql`."""
841        self.reset()
842        self.sql = sql
843        self.size = len(sql)
844
845        try:
846            self._scan()
847        except Exception as e:
848            start = max(self._current - 50, 0)
849            end = min(self._current + 50, self.size - 1)
850            context = self.sql[start:end]
851            raise TokenError(f"Error tokenizing '{context}'") from e
852
853        return self.tokens

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

def peek(self, i: int = 0) -> str:
921    def peek(self, i: int = 0) -> str:
922        i = self._current + i
923        if i < self.size:
924            return self.sql[i]
925        return ""
size
sql
tokens