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

Returns a NUMBER token with number as its text.

@classmethod
def string(cls, string: str) -> Token:
347    @classmethod
348    def string(cls, string: str) -> Token:
349        """Returns a STRING token with `string` as its text."""
350        return cls(TokenType.STRING, string)

Returns a STRING token with string as its text.

@classmethod
def identifier(cls, identifier: str) -> Token:
352    @classmethod
353    def identifier(cls, identifier: str) -> Token:
354        """Returns an IDENTIFIER token with `identifier` as its text."""
355        return cls(TokenType.IDENTIFIER, identifier)

Returns an IDENTIFIER token with identifier as its text.

@classmethod
def var(cls, var: str) -> Token:
357    @classmethod
358    def var(cls, var: str) -> Token:
359        """Returns an VAR token with `var` as its text."""
360        return cls(TokenType.VAR, var)

Returns an VAR token with var as its text.

token_type
text
line
col
start
end
comments
class Tokenizer:
 450class Tokenizer(metaclass=_Tokenizer):
 451    SINGLE_TOKENS = {
 452        "(": TokenType.L_PAREN,
 453        ")": TokenType.R_PAREN,
 454        "[": TokenType.L_BRACKET,
 455        "]": TokenType.R_BRACKET,
 456        "{": TokenType.L_BRACE,
 457        "}": TokenType.R_BRACE,
 458        "&": TokenType.AMP,
 459        "^": TokenType.CARET,
 460        ":": TokenType.COLON,
 461        ",": TokenType.COMMA,
 462        ".": TokenType.DOT,
 463        "-": TokenType.DASH,
 464        "=": TokenType.EQ,
 465        ">": TokenType.GT,
 466        "<": TokenType.LT,
 467        "%": TokenType.MOD,
 468        "!": TokenType.NOT,
 469        "|": TokenType.PIPE,
 470        "+": TokenType.PLUS,
 471        ";": TokenType.SEMICOLON,
 472        "/": TokenType.SLASH,
 473        "\\": TokenType.BACKSLASH,
 474        "*": TokenType.STAR,
 475        "~": TokenType.TILDA,
 476        "?": TokenType.PLACEHOLDER,
 477        "@": TokenType.PARAMETER,
 478        # used for breaking a var like x'y' but nothing else
 479        # the token type doesn't matter
 480        "'": TokenType.QUOTE,
 481        "`": TokenType.IDENTIFIER,
 482        '"': TokenType.IDENTIFIER,
 483        "#": TokenType.HASH,
 484    }
 485
 486    BIT_STRINGS: t.List[str | t.Tuple[str, str]] = []
 487    BYTE_STRINGS: t.List[str | t.Tuple[str, str]] = []
 488    HEX_STRINGS: t.List[str | t.Tuple[str, str]] = []
 489    RAW_STRINGS: t.List[str | t.Tuple[str, str]] = []
 490    HEREDOC_STRINGS: t.List[str | t.Tuple[str, str]] = []
 491    IDENTIFIERS: t.List[str | t.Tuple[str, str]] = ['"']
 492    IDENTIFIER_ESCAPES = ['"']
 493    QUOTES: t.List[t.Tuple[str, str] | str] = ["'"]
 494    STRING_ESCAPES = ["'"]
 495    VAR_SINGLE_TOKENS: t.Set[str] = set()
 496
 497    # Autofilled
 498    IDENTIFIERS_CAN_START_WITH_DIGIT: bool = False
 499
 500    _COMMENTS: t.Dict[str, str] = {}
 501    _FORMAT_STRINGS: t.Dict[str, t.Tuple[str, TokenType]] = {}
 502    _IDENTIFIERS: t.Dict[str, str] = {}
 503    _IDENTIFIER_ESCAPES: t.Set[str] = set()
 504    _QUOTES: t.Dict[str, str] = {}
 505    _STRING_ESCAPES: t.Set[str] = set()
 506    _KEYWORD_TRIE: t.Dict = {}
 507
 508    KEYWORDS: t.Dict[str, TokenType] = {
 509        **{f"{{%{postfix}": TokenType.BLOCK_START for postfix in ("", "+", "-")},
 510        **{f"{prefix}%}}": TokenType.BLOCK_END for prefix in ("", "+", "-")},
 511        **{f"{{{{{postfix}": TokenType.BLOCK_START for postfix in ("+", "-")},
 512        **{f"{prefix}}}}}": TokenType.BLOCK_END for prefix in ("+", "-")},
 513        "/*+": TokenType.HINT,
 514        "==": TokenType.EQ,
 515        "::": TokenType.DCOLON,
 516        "||": TokenType.DPIPE,
 517        ">=": TokenType.GTE,
 518        "<=": TokenType.LTE,
 519        "<>": TokenType.NEQ,
 520        "!=": TokenType.NEQ,
 521        "<=>": TokenType.NULLSAFE_EQ,
 522        "->": TokenType.ARROW,
 523        "->>": TokenType.DARROW,
 524        "=>": TokenType.FARROW,
 525        "#>": TokenType.HASH_ARROW,
 526        "#>>": TokenType.DHASH_ARROW,
 527        "<->": TokenType.LR_ARROW,
 528        "&&": TokenType.DAMP,
 529        "??": TokenType.DQMARK,
 530        "ALL": TokenType.ALL,
 531        "ALWAYS": TokenType.ALWAYS,
 532        "AND": TokenType.AND,
 533        "ANTI": TokenType.ANTI,
 534        "ANY": TokenType.ANY,
 535        "ASC": TokenType.ASC,
 536        "AS": TokenType.ALIAS,
 537        "ASOF": TokenType.ASOF,
 538        "AUTOINCREMENT": TokenType.AUTO_INCREMENT,
 539        "AUTO_INCREMENT": TokenType.AUTO_INCREMENT,
 540        "BEGIN": TokenType.BEGIN,
 541        "BETWEEN": TokenType.BETWEEN,
 542        "CACHE": TokenType.CACHE,
 543        "UNCACHE": TokenType.UNCACHE,
 544        "CASE": TokenType.CASE,
 545        "CHARACTER SET": TokenType.CHARACTER_SET,
 546        "CLUSTER BY": TokenType.CLUSTER_BY,
 547        "COLLATE": TokenType.COLLATE,
 548        "COLUMN": TokenType.COLUMN,
 549        "COMMIT": TokenType.COMMIT,
 550        "CONNECT BY": TokenType.CONNECT_BY,
 551        "CONSTRAINT": TokenType.CONSTRAINT,
 552        "CREATE": TokenType.CREATE,
 553        "CROSS": TokenType.CROSS,
 554        "CUBE": TokenType.CUBE,
 555        "CURRENT_DATE": TokenType.CURRENT_DATE,
 556        "CURRENT_TIME": TokenType.CURRENT_TIME,
 557        "CURRENT_TIMESTAMP": TokenType.CURRENT_TIMESTAMP,
 558        "CURRENT_USER": TokenType.CURRENT_USER,
 559        "DATABASE": TokenType.DATABASE,
 560        "DEFAULT": TokenType.DEFAULT,
 561        "DELETE": TokenType.DELETE,
 562        "DESC": TokenType.DESC,
 563        "DESCRIBE": TokenType.DESCRIBE,
 564        "DISTINCT": TokenType.DISTINCT,
 565        "DISTRIBUTE BY": TokenType.DISTRIBUTE_BY,
 566        "DIV": TokenType.DIV,
 567        "DROP": TokenType.DROP,
 568        "ELSE": TokenType.ELSE,
 569        "END": TokenType.END,
 570        "ESCAPE": TokenType.ESCAPE,
 571        "EXCEPT": TokenType.EXCEPT,
 572        "EXECUTE": TokenType.EXECUTE,
 573        "EXISTS": TokenType.EXISTS,
 574        "FALSE": TokenType.FALSE,
 575        "FETCH": TokenType.FETCH,
 576        "FILTER": TokenType.FILTER,
 577        "FIRST": TokenType.FIRST,
 578        "FULL": TokenType.FULL,
 579        "FUNCTION": TokenType.FUNCTION,
 580        "FOR": TokenType.FOR,
 581        "FOREIGN KEY": TokenType.FOREIGN_KEY,
 582        "FORMAT": TokenType.FORMAT,
 583        "FROM": TokenType.FROM,
 584        "GEOGRAPHY": TokenType.GEOGRAPHY,
 585        "GEOMETRY": TokenType.GEOMETRY,
 586        "GLOB": TokenType.GLOB,
 587        "GROUP BY": TokenType.GROUP_BY,
 588        "GROUPING SETS": TokenType.GROUPING_SETS,
 589        "HAVING": TokenType.HAVING,
 590        "ILIKE": TokenType.ILIKE,
 591        "IN": TokenType.IN,
 592        "INDEX": TokenType.INDEX,
 593        "INET": TokenType.INET,
 594        "INNER": TokenType.INNER,
 595        "INSERT": TokenType.INSERT,
 596        "INTERVAL": TokenType.INTERVAL,
 597        "INTERSECT": TokenType.INTERSECT,
 598        "INTO": TokenType.INTO,
 599        "IS": TokenType.IS,
 600        "ISNULL": TokenType.ISNULL,
 601        "JOIN": TokenType.JOIN,
 602        "KEEP": TokenType.KEEP,
 603        "KILL": TokenType.KILL,
 604        "LATERAL": TokenType.LATERAL,
 605        "LEFT": TokenType.LEFT,
 606        "LIKE": TokenType.LIKE,
 607        "LIMIT": TokenType.LIMIT,
 608        "LOAD": TokenType.LOAD,
 609        "LOCK": TokenType.LOCK,
 610        "MERGE": TokenType.MERGE,
 611        "NATURAL": TokenType.NATURAL,
 612        "NEXT": TokenType.NEXT,
 613        "NOT": TokenType.NOT,
 614        "NOTNULL": TokenType.NOTNULL,
 615        "NULL": TokenType.NULL,
 616        "OBJECT": TokenType.OBJECT,
 617        "OFFSET": TokenType.OFFSET,
 618        "ON": TokenType.ON,
 619        "OR": TokenType.OR,
 620        "XOR": TokenType.XOR,
 621        "ORDER BY": TokenType.ORDER_BY,
 622        "ORDINALITY": TokenType.ORDINALITY,
 623        "OUTER": TokenType.OUTER,
 624        "OVER": TokenType.OVER,
 625        "OVERLAPS": TokenType.OVERLAPS,
 626        "OVERWRITE": TokenType.OVERWRITE,
 627        "PARTITION": TokenType.PARTITION,
 628        "PARTITION BY": TokenType.PARTITION_BY,
 629        "PARTITIONED BY": TokenType.PARTITION_BY,
 630        "PARTITIONED_BY": TokenType.PARTITION_BY,
 631        "PERCENT": TokenType.PERCENT,
 632        "PIVOT": TokenType.PIVOT,
 633        "PRAGMA": TokenType.PRAGMA,
 634        "PRIMARY KEY": TokenType.PRIMARY_KEY,
 635        "PROCEDURE": TokenType.PROCEDURE,
 636        "QUALIFY": TokenType.QUALIFY,
 637        "RANGE": TokenType.RANGE,
 638        "RECURSIVE": TokenType.RECURSIVE,
 639        "REGEXP": TokenType.RLIKE,
 640        "REPLACE": TokenType.REPLACE,
 641        "RETURNING": TokenType.RETURNING,
 642        "REFERENCES": TokenType.REFERENCES,
 643        "RIGHT": TokenType.RIGHT,
 644        "RLIKE": TokenType.RLIKE,
 645        "ROLLBACK": TokenType.ROLLBACK,
 646        "ROLLUP": TokenType.ROLLUP,
 647        "ROW": TokenType.ROW,
 648        "ROWS": TokenType.ROWS,
 649        "SCHEMA": TokenType.SCHEMA,
 650        "SELECT": TokenType.SELECT,
 651        "SEMI": TokenType.SEMI,
 652        "SET": TokenType.SET,
 653        "SETTINGS": TokenType.SETTINGS,
 654        "SHOW": TokenType.SHOW,
 655        "SIMILAR TO": TokenType.SIMILAR_TO,
 656        "SOME": TokenType.SOME,
 657        "SORT BY": TokenType.SORT_BY,
 658        "START WITH": TokenType.START_WITH,
 659        "TABLE": TokenType.TABLE,
 660        "TABLESAMPLE": TokenType.TABLE_SAMPLE,
 661        "TEMP": TokenType.TEMPORARY,
 662        "TEMPORARY": TokenType.TEMPORARY,
 663        "THEN": TokenType.THEN,
 664        "TRUE": TokenType.TRUE,
 665        "UNION": TokenType.UNION,
 666        "UNKNOWN": TokenType.UNKNOWN,
 667        "UNNEST": TokenType.UNNEST,
 668        "UNPIVOT": TokenType.UNPIVOT,
 669        "UPDATE": TokenType.UPDATE,
 670        "USE": TokenType.USE,
 671        "USING": TokenType.USING,
 672        "UUID": TokenType.UUID,
 673        "VALUES": TokenType.VALUES,
 674        "VIEW": TokenType.VIEW,
 675        "VOLATILE": TokenType.VOLATILE,
 676        "WHEN": TokenType.WHEN,
 677        "WHERE": TokenType.WHERE,
 678        "WINDOW": TokenType.WINDOW,
 679        "WITH": TokenType.WITH,
 680        "APPLY": TokenType.APPLY,
 681        "ARRAY": TokenType.ARRAY,
 682        "BIT": TokenType.BIT,
 683        "BOOL": TokenType.BOOLEAN,
 684        "BOOLEAN": TokenType.BOOLEAN,
 685        "BYTE": TokenType.TINYINT,
 686        "MEDIUMINT": TokenType.MEDIUMINT,
 687        "TINYINT": TokenType.TINYINT,
 688        "SHORT": TokenType.SMALLINT,
 689        "SMALLINT": TokenType.SMALLINT,
 690        "INT128": TokenType.INT128,
 691        "INT2": TokenType.SMALLINT,
 692        "INTEGER": TokenType.INT,
 693        "INT": TokenType.INT,
 694        "INT4": TokenType.INT,
 695        "LONG": TokenType.BIGINT,
 696        "BIGINT": TokenType.BIGINT,
 697        "INT8": TokenType.BIGINT,
 698        "DEC": TokenType.DECIMAL,
 699        "DECIMAL": TokenType.DECIMAL,
 700        "BIGDECIMAL": TokenType.BIGDECIMAL,
 701        "BIGNUMERIC": TokenType.BIGDECIMAL,
 702        "MAP": TokenType.MAP,
 703        "NULLABLE": TokenType.NULLABLE,
 704        "NUMBER": TokenType.DECIMAL,
 705        "NUMERIC": TokenType.DECIMAL,
 706        "FIXED": TokenType.DECIMAL,
 707        "REAL": TokenType.FLOAT,
 708        "FLOAT": TokenType.FLOAT,
 709        "FLOAT4": TokenType.FLOAT,
 710        "FLOAT8": TokenType.DOUBLE,
 711        "DOUBLE": TokenType.DOUBLE,
 712        "DOUBLE PRECISION": TokenType.DOUBLE,
 713        "JSON": TokenType.JSON,
 714        "CHAR": TokenType.CHAR,
 715        "CHARACTER": TokenType.CHAR,
 716        "NCHAR": TokenType.NCHAR,
 717        "VARCHAR": TokenType.VARCHAR,
 718        "VARCHAR2": TokenType.VARCHAR,
 719        "NVARCHAR": TokenType.NVARCHAR,
 720        "NVARCHAR2": TokenType.NVARCHAR,
 721        "STR": TokenType.TEXT,
 722        "STRING": TokenType.TEXT,
 723        "TEXT": TokenType.TEXT,
 724        "LONGTEXT": TokenType.LONGTEXT,
 725        "MEDIUMTEXT": TokenType.MEDIUMTEXT,
 726        "TINYTEXT": TokenType.TINYTEXT,
 727        "CLOB": TokenType.TEXT,
 728        "LONGVARCHAR": TokenType.TEXT,
 729        "BINARY": TokenType.BINARY,
 730        "BLOB": TokenType.VARBINARY,
 731        "LONGBLOB": TokenType.LONGBLOB,
 732        "MEDIUMBLOB": TokenType.MEDIUMBLOB,
 733        "TINYBLOB": TokenType.TINYBLOB,
 734        "BYTEA": TokenType.VARBINARY,
 735        "VARBINARY": TokenType.VARBINARY,
 736        "TIME": TokenType.TIME,
 737        "TIMETZ": TokenType.TIMETZ,
 738        "TIMESTAMP": TokenType.TIMESTAMP,
 739        "TIMESTAMPTZ": TokenType.TIMESTAMPTZ,
 740        "TIMESTAMPLTZ": TokenType.TIMESTAMPLTZ,
 741        "DATE": TokenType.DATE,
 742        "DATETIME": TokenType.DATETIME,
 743        "INT4RANGE": TokenType.INT4RANGE,
 744        "INT4MULTIRANGE": TokenType.INT4MULTIRANGE,
 745        "INT8RANGE": TokenType.INT8RANGE,
 746        "INT8MULTIRANGE": TokenType.INT8MULTIRANGE,
 747        "NUMRANGE": TokenType.NUMRANGE,
 748        "NUMMULTIRANGE": TokenType.NUMMULTIRANGE,
 749        "TSRANGE": TokenType.TSRANGE,
 750        "TSMULTIRANGE": TokenType.TSMULTIRANGE,
 751        "TSTZRANGE": TokenType.TSTZRANGE,
 752        "TSTZMULTIRANGE": TokenType.TSTZMULTIRANGE,
 753        "DATERANGE": TokenType.DATERANGE,
 754        "DATEMULTIRANGE": TokenType.DATEMULTIRANGE,
 755        "UNIQUE": TokenType.UNIQUE,
 756        "STRUCT": TokenType.STRUCT,
 757        "VARIANT": TokenType.VARIANT,
 758        "ALTER": TokenType.ALTER,
 759        "ANALYZE": TokenType.COMMAND,
 760        "CALL": TokenType.COMMAND,
 761        "COMMENT": TokenType.COMMENT,
 762        "COPY": TokenType.COMMAND,
 763        "EXPLAIN": TokenType.COMMAND,
 764        "GRANT": TokenType.COMMAND,
 765        "OPTIMIZE": TokenType.COMMAND,
 766        "PREPARE": TokenType.COMMAND,
 767        "TRUNCATE": TokenType.COMMAND,
 768        "VACUUM": TokenType.COMMAND,
 769        "USER-DEFINED": TokenType.USERDEFINED,
 770        "FOR VERSION": TokenType.VERSION_SNAPSHOT,
 771        "FOR TIMESTAMP": TokenType.TIMESTAMP_SNAPSHOT,
 772    }
 773
 774    WHITE_SPACE: t.Dict[t.Optional[str], TokenType] = {
 775        " ": TokenType.SPACE,
 776        "\t": TokenType.SPACE,
 777        "\n": TokenType.BREAK,
 778        "\r": TokenType.BREAK,
 779        "\r\n": TokenType.BREAK,
 780    }
 781
 782    COMMANDS = {
 783        TokenType.COMMAND,
 784        TokenType.EXECUTE,
 785        TokenType.FETCH,
 786        TokenType.SHOW,
 787    }
 788
 789    COMMAND_PREFIX_TOKENS = {TokenType.SEMICOLON, TokenType.BEGIN}
 790
 791    # handle numeric literals like in hive (3L = BIGINT)
 792    NUMERIC_LITERALS: t.Dict[str, str] = {}
 793    ENCODE: t.Optional[str] = None
 794
 795    COMMENTS = ["--", ("/*", "*/")]
 796
 797    __slots__ = (
 798        "sql",
 799        "size",
 800        "tokens",
 801        "_start",
 802        "_current",
 803        "_line",
 804        "_col",
 805        "_comments",
 806        "_char",
 807        "_end",
 808        "_peek",
 809        "_prev_token_line",
 810    )
 811
 812    def __init__(self) -> None:
 813        self.reset()
 814
 815    def reset(self) -> None:
 816        self.sql = ""
 817        self.size = 0
 818        self.tokens: t.List[Token] = []
 819        self._start = 0
 820        self._current = 0
 821        self._line = 1
 822        self._col = 0
 823        self._comments: t.List[str] = []
 824
 825        self._char = ""
 826        self._end = False
 827        self._peek = ""
 828        self._prev_token_line = -1
 829
 830    def tokenize(self, sql: str) -> t.List[Token]:
 831        """Returns a list of tokens corresponding to the SQL string `sql`."""
 832        self.reset()
 833        self.sql = sql
 834        self.size = len(sql)
 835
 836        try:
 837            self._scan()
 838        except Exception as e:
 839            start = max(self._current - 50, 0)
 840            end = min(self._current + 50, self.size - 1)
 841            context = self.sql[start:end]
 842            raise TokenError(f"Error tokenizing '{context}'") from e
 843
 844        return self.tokens
 845
 846    def _scan(self, until: t.Optional[t.Callable] = None) -> None:
 847        while self.size and not self._end:
 848            self._start = self._current
 849            self._advance()
 850
 851            if self._char is None:
 852                break
 853
 854            if self._char not in self.WHITE_SPACE:
 855                if self._char.isdigit():
 856                    self._scan_number()
 857                elif self._char in self._IDENTIFIERS:
 858                    self._scan_identifier(self._IDENTIFIERS[self._char])
 859                else:
 860                    self._scan_keywords()
 861
 862            if until and until():
 863                break
 864
 865        if self.tokens and self._comments:
 866            self.tokens[-1].comments.extend(self._comments)
 867
 868    def _chars(self, size: int) -> str:
 869        if size == 1:
 870            return self._char
 871
 872        start = self._current - 1
 873        end = start + size
 874
 875        return self.sql[start:end] if end <= self.size else ""
 876
 877    def _advance(self, i: int = 1, alnum: bool = False) -> None:
 878        if self.WHITE_SPACE.get(self._char) is TokenType.BREAK:
 879            self._col = 1
 880            self._line += 1
 881        else:
 882            self._col += i
 883
 884        self._current += i
 885        self._end = self._current >= self.size
 886        self._char = self.sql[self._current - 1]
 887        self._peek = "" if self._end else self.sql[self._current]
 888
 889        if alnum and self._char.isalnum():
 890            # Here we use local variables instead of attributes for better performance
 891            _col = self._col
 892            _current = self._current
 893            _end = self._end
 894            _peek = self._peek
 895
 896            while _peek.isalnum():
 897                _col += 1
 898                _current += 1
 899                _end = _current >= self.size
 900                _peek = "" if _end else self.sql[_current]
 901
 902            self._col = _col
 903            self._current = _current
 904            self._end = _end
 905            self._peek = _peek
 906            self._char = self.sql[_current - 1]
 907
 908    @property
 909    def _text(self) -> str:
 910        return self.sql[self._start : self._current]
 911
 912    def peek(self, i: int = 0) -> str:
 913        i = self._current + i
 914        if i < self.size:
 915            return self.sql[i]
 916        return ""
 917
 918    def _add(self, token_type: TokenType, text: t.Optional[str] = None) -> None:
 919        self._prev_token_line = self._line
 920
 921        if self._comments and token_type == TokenType.SEMICOLON and self.tokens:
 922            self.tokens[-1].comments.extend(self._comments)
 923            self._comments = []
 924
 925        self.tokens.append(
 926            Token(
 927                token_type,
 928                text=self._text if text is None else text,
 929                line=self._line,
 930                col=self._col,
 931                start=self._start,
 932                end=self._current - 1,
 933                comments=self._comments,
 934            )
 935        )
 936        self._comments = []
 937
 938        # If we have either a semicolon or a begin token before the command's token, we'll parse
 939        # whatever follows the command's token as a string
 940        if (
 941            token_type in self.COMMANDS
 942            and self._peek != ";"
 943            and (len(self.tokens) == 1 or self.tokens[-2].token_type in self.COMMAND_PREFIX_TOKENS)
 944        ):
 945            start = self._current
 946            tokens = len(self.tokens)
 947            self._scan(lambda: self._peek == ";")
 948            self.tokens = self.tokens[:tokens]
 949            text = self.sql[start : self._current].strip()
 950            if text:
 951                self._add(TokenType.STRING, text)
 952
 953    def _scan_keywords(self) -> None:
 954        size = 0
 955        word = None
 956        chars = self._text
 957        char = chars
 958        prev_space = False
 959        skip = False
 960        trie = self._KEYWORD_TRIE
 961        single_token = char in self.SINGLE_TOKENS
 962
 963        while chars:
 964            if skip:
 965                result = TrieResult.PREFIX
 966            else:
 967                result, trie = in_trie(trie, char.upper())
 968
 969            if result == TrieResult.FAILED:
 970                break
 971            if result == TrieResult.EXISTS:
 972                word = chars
 973
 974            end = self._current + size
 975            size += 1
 976
 977            if end < self.size:
 978                char = self.sql[end]
 979                single_token = single_token or char in self.SINGLE_TOKENS
 980                is_space = char in self.WHITE_SPACE
 981
 982                if not is_space or not prev_space:
 983                    if is_space:
 984                        char = " "
 985                    chars += char
 986                    prev_space = is_space
 987                    skip = False
 988                else:
 989                    skip = True
 990            else:
 991                char = ""
 992                chars = " "
 993
 994        if word:
 995            if self._scan_string(word):
 996                return
 997            if self._scan_comment(word):
 998                return
 999            if prev_space or single_token or not char:
1000                self._advance(size - 1)
1001                word = word.upper()
1002                self._add(self.KEYWORDS[word], text=word)
1003                return
1004
1005        if self._char in self.SINGLE_TOKENS:
1006            self._add(self.SINGLE_TOKENS[self._char], text=self._char)
1007            return
1008
1009        self._scan_var()
1010
1011    def _scan_comment(self, comment_start: str) -> bool:
1012        if comment_start not in self._COMMENTS:
1013            return False
1014
1015        comment_start_line = self._line
1016        comment_start_size = len(comment_start)
1017        comment_end = self._COMMENTS[comment_start]
1018
1019        if comment_end:
1020            # Skip the comment's start delimiter
1021            self._advance(comment_start_size)
1022
1023            comment_end_size = len(comment_end)
1024            while not self._end and self._chars(comment_end_size) != comment_end:
1025                self._advance(alnum=True)
1026
1027            self._comments.append(self._text[comment_start_size : -comment_end_size + 1])
1028            self._advance(comment_end_size - 1)
1029        else:
1030            while not self._end and not self.WHITE_SPACE.get(self._peek) is TokenType.BREAK:
1031                self._advance(alnum=True)
1032            self._comments.append(self._text[comment_start_size:])
1033
1034        # Leading comment is attached to the succeeding token, whilst trailing comment to the preceding.
1035        # Multiple consecutive comments are preserved by appending them to the current comments list.
1036        if comment_start_line == self._prev_token_line:
1037            self.tokens[-1].comments.extend(self._comments)
1038            self._comments = []
1039            self._prev_token_line = self._line
1040
1041        return True
1042
1043    def _scan_number(self) -> None:
1044        if self._char == "0":
1045            peek = self._peek.upper()
1046            if peek == "B":
1047                return self._scan_bits() if self.BIT_STRINGS else self._add(TokenType.NUMBER)
1048            elif peek == "X":
1049                return self._scan_hex() if self.HEX_STRINGS else self._add(TokenType.NUMBER)
1050
1051        decimal = False
1052        scientific = 0
1053
1054        while True:
1055            if self._peek.isdigit():
1056                self._advance()
1057            elif self._peek == "." and not decimal:
1058                after = self.peek(1)
1059                if after.isdigit() or not after.isalpha():
1060                    decimal = True
1061                    self._advance()
1062                else:
1063                    return self._add(TokenType.VAR)
1064            elif self._peek in ("-", "+") and scientific == 1:
1065                scientific += 1
1066                self._advance()
1067            elif self._peek.upper() == "E" and not scientific:
1068                scientific += 1
1069                self._advance()
1070            elif self._peek.isidentifier():
1071                number_text = self._text
1072                literal = ""
1073
1074                while self._peek.strip() and self._peek not in self.SINGLE_TOKENS:
1075                    literal += self._peek.upper()
1076                    self._advance()
1077
1078                token_type = self.KEYWORDS.get(self.NUMERIC_LITERALS.get(literal, ""))
1079
1080                if token_type:
1081                    self._add(TokenType.NUMBER, number_text)
1082                    self._add(TokenType.DCOLON, "::")
1083                    return self._add(token_type, literal)
1084                elif self.IDENTIFIERS_CAN_START_WITH_DIGIT:
1085                    return self._add(TokenType.VAR)
1086
1087                self._advance(-len(literal))
1088                return self._add(TokenType.NUMBER, number_text)
1089            else:
1090                return self._add(TokenType.NUMBER)
1091
1092    def _scan_bits(self) -> None:
1093        self._advance()
1094        value = self._extract_value()
1095        try:
1096            # If `value` can't be converted to a binary, fallback to tokenizing it as an identifier
1097            int(value, 2)
1098            self._add(TokenType.BIT_STRING, value[2:])  # Drop the 0b
1099        except ValueError:
1100            self._add(TokenType.IDENTIFIER)
1101
1102    def _scan_hex(self) -> None:
1103        self._advance()
1104        value = self._extract_value()
1105        try:
1106            # If `value` can't be converted to a hex, fallback to tokenizing it as an identifier
1107            int(value, 16)
1108            self._add(TokenType.HEX_STRING, value[2:])  # Drop the 0x
1109        except ValueError:
1110            self._add(TokenType.IDENTIFIER)
1111
1112    def _extract_value(self) -> str:
1113        while True:
1114            char = self._peek.strip()
1115            if char and char not in self.SINGLE_TOKENS:
1116                self._advance(alnum=True)
1117            else:
1118                break
1119
1120        return self._text
1121
1122    def _scan_string(self, start: str) -> bool:
1123        base = None
1124        token_type = TokenType.STRING
1125
1126        if start in self._QUOTES:
1127            end = self._QUOTES[start]
1128        elif start in self._FORMAT_STRINGS:
1129            end, token_type = self._FORMAT_STRINGS[start]
1130
1131            if token_type == TokenType.HEX_STRING:
1132                base = 16
1133            elif token_type == TokenType.BIT_STRING:
1134                base = 2
1135            elif token_type == TokenType.HEREDOC_STRING:
1136                self._advance()
1137                tag = "" if self._char == end else self._extract_string(end)
1138                end = f"{start}{tag}{end}"
1139        else:
1140            return False
1141
1142        self._advance(len(start))
1143        text = self._extract_string(end)
1144
1145        if base:
1146            try:
1147                int(text, base)
1148            except:
1149                raise TokenError(
1150                    f"Numeric string contains invalid characters from {self._line}:{self._start}"
1151                )
1152        else:
1153            text = text.encode(self.ENCODE).decode(self.ENCODE) if self.ENCODE else text
1154
1155        self._add(token_type, text)
1156        return True
1157
1158    def _scan_identifier(self, identifier_end: str) -> None:
1159        self._advance()
1160        text = self._extract_string(identifier_end, self._IDENTIFIER_ESCAPES)
1161        self._add(TokenType.IDENTIFIER, text)
1162
1163    def _scan_var(self) -> None:
1164        while True:
1165            char = self._peek.strip()
1166            if char and (char in self.VAR_SINGLE_TOKENS or char not in self.SINGLE_TOKENS):
1167                self._advance(alnum=True)
1168            else:
1169                break
1170
1171        self._add(
1172            TokenType.VAR
1173            if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER
1174            else self.KEYWORDS.get(self._text.upper(), TokenType.VAR)
1175        )
1176
1177    def _extract_string(self, delimiter: str, escapes=None) -> str:
1178        text = ""
1179        delim_size = len(delimiter)
1180        escapes = self._STRING_ESCAPES if escapes is None else escapes
1181
1182        while True:
1183            if (
1184                self._char in escapes
1185                and (self._peek == delimiter or self._peek in escapes)
1186                and (self._char not in self._QUOTES or self._char == self._peek)
1187            ):
1188                if self._peek == delimiter:
1189                    text += self._peek
1190                else:
1191                    text += self._char + self._peek
1192
1193                if self._current + 1 < self.size:
1194                    self._advance(2)
1195                else:
1196                    raise TokenError(f"Missing {delimiter} from {self._line}:{self._current}")
1197            else:
1198                if self._chars(delim_size) == delimiter:
1199                    if delim_size > 1:
1200                        self._advance(delim_size - 1)
1201                    break
1202
1203                if self._end:
1204                    raise TokenError(f"Missing {delimiter} from {self._line}:{self._start}")
1205
1206                current = self._current - 1
1207                self._advance(alnum=True)
1208                text += self.sql[current : self._current - 1]
1209
1210        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()
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.FETCH: 'FETCH'>, <TokenType.COMMAND: 'COMMAND'>, <TokenType.EXECUTE: 'EXECUTE'>, <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:
815    def reset(self) -> None:
816        self.sql = ""
817        self.size = 0
818        self.tokens: t.List[Token] = []
819        self._start = 0
820        self._current = 0
821        self._line = 1
822        self._col = 0
823        self._comments: t.List[str] = []
824
825        self._char = ""
826        self._end = False
827        self._peek = ""
828        self._prev_token_line = -1
def tokenize(self, sql: str) -> List[Token]:
830    def tokenize(self, sql: str) -> t.List[Token]:
831        """Returns a list of tokens corresponding to the SQL string `sql`."""
832        self.reset()
833        self.sql = sql
834        self.size = len(sql)
835
836        try:
837            self._scan()
838        except Exception as e:
839            start = max(self._current - 50, 0)
840            end = min(self._current + 50, self.size - 1)
841            context = self.sql[start:end]
842            raise TokenError(f"Error tokenizing '{context}'") from e
843
844        return self.tokens

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

def peek(self, i: int = 0) -> str:
912    def peek(self, i: int = 0) -> str:
913        i = self._current + i
914        if i < self.size:
915            return self.sql[i]
916        return ""
size
sql
tokens