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

Returns a NUMBER token with number as its text.

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

Returns a STRING token with string as its text.

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

Returns an IDENTIFIER token with identifier as its text.

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

Returns an VAR token with var as its text.

token_type
text
line
col
start
end
comments
class Tokenizer:
 456class Tokenizer(metaclass=_Tokenizer):
 457    SINGLE_TOKENS = {
 458        "(": TokenType.L_PAREN,
 459        ")": TokenType.R_PAREN,
 460        "[": TokenType.L_BRACKET,
 461        "]": TokenType.R_BRACKET,
 462        "{": TokenType.L_BRACE,
 463        "}": TokenType.R_BRACE,
 464        "&": TokenType.AMP,
 465        "^": TokenType.CARET,
 466        ":": TokenType.COLON,
 467        ",": TokenType.COMMA,
 468        ".": TokenType.DOT,
 469        "-": TokenType.DASH,
 470        "=": TokenType.EQ,
 471        ">": TokenType.GT,
 472        "<": TokenType.LT,
 473        "%": TokenType.MOD,
 474        "!": TokenType.NOT,
 475        "|": TokenType.PIPE,
 476        "+": TokenType.PLUS,
 477        ";": TokenType.SEMICOLON,
 478        "/": TokenType.SLASH,
 479        "\\": TokenType.BACKSLASH,
 480        "*": TokenType.STAR,
 481        "~": TokenType.TILDA,
 482        "?": TokenType.PLACEHOLDER,
 483        "@": TokenType.PARAMETER,
 484        # used for breaking a var like x'y' but nothing else
 485        # the token type doesn't matter
 486        "'": TokenType.QUOTE,
 487        "`": TokenType.IDENTIFIER,
 488        '"': TokenType.IDENTIFIER,
 489        "#": TokenType.HASH,
 490    }
 491
 492    BIT_STRINGS: t.List[str | t.Tuple[str, str]] = []
 493    BYTE_STRINGS: t.List[str | t.Tuple[str, str]] = []
 494    HEX_STRINGS: t.List[str | t.Tuple[str, str]] = []
 495    RAW_STRINGS: t.List[str | t.Tuple[str, str]] = []
 496    HEREDOC_STRINGS: t.List[str | t.Tuple[str, str]] = []
 497    IDENTIFIERS: t.List[str | t.Tuple[str, str]] = ['"']
 498    IDENTIFIER_ESCAPES = ['"']
 499    QUOTES: t.List[t.Tuple[str, str] | str] = ["'"]
 500    STRING_ESCAPES = ["'"]
 501    VAR_SINGLE_TOKENS: t.Set[str] = set()
 502    ESCAPE_SEQUENCES: t.Dict[str, str] = {}
 503
 504    # Autofilled
 505    IDENTIFIERS_CAN_START_WITH_DIGIT: bool = False
 506
 507    _COMMENTS: t.Dict[str, str] = {}
 508    _FORMAT_STRINGS: t.Dict[str, t.Tuple[str, TokenType]] = {}
 509    _IDENTIFIERS: t.Dict[str, str] = {}
 510    _IDENTIFIER_ESCAPES: t.Set[str] = set()
 511    _QUOTES: t.Dict[str, str] = {}
 512    _STRING_ESCAPES: t.Set[str] = set()
 513    _KEYWORD_TRIE: t.Dict = {}
 514
 515    KEYWORDS: t.Dict[str, TokenType] = {
 516        **{f"{{%{postfix}": TokenType.BLOCK_START for postfix in ("", "+", "-")},
 517        **{f"{prefix}%}}": TokenType.BLOCK_END for prefix in ("", "+", "-")},
 518        **{f"{{{{{postfix}": TokenType.BLOCK_START for postfix in ("+", "-")},
 519        **{f"{prefix}}}}}": TokenType.BLOCK_END for prefix in ("+", "-")},
 520        "/*+": TokenType.HINT,
 521        "==": TokenType.EQ,
 522        "::": TokenType.DCOLON,
 523        "||": TokenType.DPIPE,
 524        ">=": TokenType.GTE,
 525        "<=": TokenType.LTE,
 526        "<>": TokenType.NEQ,
 527        "!=": TokenType.NEQ,
 528        "<=>": TokenType.NULLSAFE_EQ,
 529        "->": TokenType.ARROW,
 530        "->>": TokenType.DARROW,
 531        "=>": TokenType.FARROW,
 532        "#>": TokenType.HASH_ARROW,
 533        "#>>": TokenType.DHASH_ARROW,
 534        "<->": TokenType.LR_ARROW,
 535        "&&": TokenType.DAMP,
 536        "??": TokenType.DQMARK,
 537        "ALL": TokenType.ALL,
 538        "ALWAYS": TokenType.ALWAYS,
 539        "AND": TokenType.AND,
 540        "ANTI": TokenType.ANTI,
 541        "ANY": TokenType.ANY,
 542        "ASC": TokenType.ASC,
 543        "AS": TokenType.ALIAS,
 544        "ASOF": TokenType.ASOF,
 545        "AUTOINCREMENT": TokenType.AUTO_INCREMENT,
 546        "AUTO_INCREMENT": TokenType.AUTO_INCREMENT,
 547        "BEGIN": TokenType.BEGIN,
 548        "BETWEEN": TokenType.BETWEEN,
 549        "CACHE": TokenType.CACHE,
 550        "UNCACHE": TokenType.UNCACHE,
 551        "CASE": TokenType.CASE,
 552        "CHARACTER SET": TokenType.CHARACTER_SET,
 553        "CLUSTER BY": TokenType.CLUSTER_BY,
 554        "COLLATE": TokenType.COLLATE,
 555        "COLUMN": TokenType.COLUMN,
 556        "COMMIT": TokenType.COMMIT,
 557        "CONNECT BY": TokenType.CONNECT_BY,
 558        "CONSTRAINT": TokenType.CONSTRAINT,
 559        "CREATE": TokenType.CREATE,
 560        "CROSS": TokenType.CROSS,
 561        "CUBE": TokenType.CUBE,
 562        "CURRENT_DATE": TokenType.CURRENT_DATE,
 563        "CURRENT_TIME": TokenType.CURRENT_TIME,
 564        "CURRENT_TIMESTAMP": TokenType.CURRENT_TIMESTAMP,
 565        "CURRENT_USER": TokenType.CURRENT_USER,
 566        "DATABASE": TokenType.DATABASE,
 567        "DEFAULT": TokenType.DEFAULT,
 568        "DELETE": TokenType.DELETE,
 569        "DESC": TokenType.DESC,
 570        "DESCRIBE": TokenType.DESCRIBE,
 571        "DISTINCT": TokenType.DISTINCT,
 572        "DISTRIBUTE BY": TokenType.DISTRIBUTE_BY,
 573        "DIV": TokenType.DIV,
 574        "DROP": TokenType.DROP,
 575        "ELSE": TokenType.ELSE,
 576        "END": TokenType.END,
 577        "ESCAPE": TokenType.ESCAPE,
 578        "EXCEPT": TokenType.EXCEPT,
 579        "EXECUTE": TokenType.EXECUTE,
 580        "EXISTS": TokenType.EXISTS,
 581        "FALSE": TokenType.FALSE,
 582        "FETCH": TokenType.FETCH,
 583        "FILTER": TokenType.FILTER,
 584        "FIRST": TokenType.FIRST,
 585        "FULL": TokenType.FULL,
 586        "FUNCTION": TokenType.FUNCTION,
 587        "FOR": TokenType.FOR,
 588        "FOREIGN KEY": TokenType.FOREIGN_KEY,
 589        "FORMAT": TokenType.FORMAT,
 590        "FROM": TokenType.FROM,
 591        "GEOGRAPHY": TokenType.GEOGRAPHY,
 592        "GEOMETRY": TokenType.GEOMETRY,
 593        "GLOB": TokenType.GLOB,
 594        "GROUP BY": TokenType.GROUP_BY,
 595        "GROUPING SETS": TokenType.GROUPING_SETS,
 596        "HAVING": TokenType.HAVING,
 597        "ILIKE": TokenType.ILIKE,
 598        "IN": TokenType.IN,
 599        "INDEX": TokenType.INDEX,
 600        "INET": TokenType.INET,
 601        "INNER": TokenType.INNER,
 602        "INSERT": TokenType.INSERT,
 603        "INTERVAL": TokenType.INTERVAL,
 604        "INTERSECT": TokenType.INTERSECT,
 605        "INTO": TokenType.INTO,
 606        "IS": TokenType.IS,
 607        "ISNULL": TokenType.ISNULL,
 608        "JOIN": TokenType.JOIN,
 609        "KEEP": TokenType.KEEP,
 610        "KILL": TokenType.KILL,
 611        "LATERAL": TokenType.LATERAL,
 612        "LEFT": TokenType.LEFT,
 613        "LIKE": TokenType.LIKE,
 614        "LIMIT": TokenType.LIMIT,
 615        "LOAD": TokenType.LOAD,
 616        "LOCK": TokenType.LOCK,
 617        "MERGE": TokenType.MERGE,
 618        "NATURAL": TokenType.NATURAL,
 619        "NEXT": TokenType.NEXT,
 620        "NOT": TokenType.NOT,
 621        "NOTNULL": TokenType.NOTNULL,
 622        "NULL": TokenType.NULL,
 623        "OBJECT": TokenType.OBJECT,
 624        "OFFSET": TokenType.OFFSET,
 625        "ON": TokenType.ON,
 626        "OR": TokenType.OR,
 627        "XOR": TokenType.XOR,
 628        "ORDER BY": TokenType.ORDER_BY,
 629        "ORDINALITY": TokenType.ORDINALITY,
 630        "OUTER": TokenType.OUTER,
 631        "OVER": TokenType.OVER,
 632        "OVERLAPS": TokenType.OVERLAPS,
 633        "OVERWRITE": TokenType.OVERWRITE,
 634        "PARTITION": TokenType.PARTITION,
 635        "PARTITION BY": TokenType.PARTITION_BY,
 636        "PARTITIONED BY": TokenType.PARTITION_BY,
 637        "PARTITIONED_BY": TokenType.PARTITION_BY,
 638        "PERCENT": TokenType.PERCENT,
 639        "PIVOT": TokenType.PIVOT,
 640        "PRAGMA": TokenType.PRAGMA,
 641        "PRIMARY KEY": TokenType.PRIMARY_KEY,
 642        "PROCEDURE": TokenType.PROCEDURE,
 643        "QUALIFY": TokenType.QUALIFY,
 644        "RANGE": TokenType.RANGE,
 645        "RECURSIVE": TokenType.RECURSIVE,
 646        "REGEXP": TokenType.RLIKE,
 647        "REPLACE": TokenType.REPLACE,
 648        "RETURNING": TokenType.RETURNING,
 649        "REFERENCES": TokenType.REFERENCES,
 650        "RIGHT": TokenType.RIGHT,
 651        "RLIKE": TokenType.RLIKE,
 652        "ROLLBACK": TokenType.ROLLBACK,
 653        "ROLLUP": TokenType.ROLLUP,
 654        "ROW": TokenType.ROW,
 655        "ROWS": TokenType.ROWS,
 656        "SCHEMA": TokenType.SCHEMA,
 657        "SELECT": TokenType.SELECT,
 658        "SEMI": TokenType.SEMI,
 659        "SET": TokenType.SET,
 660        "SETTINGS": TokenType.SETTINGS,
 661        "SHOW": TokenType.SHOW,
 662        "SIMILAR TO": TokenType.SIMILAR_TO,
 663        "SOME": TokenType.SOME,
 664        "SORT BY": TokenType.SORT_BY,
 665        "START WITH": TokenType.START_WITH,
 666        "TABLE": TokenType.TABLE,
 667        "TABLESAMPLE": TokenType.TABLE_SAMPLE,
 668        "TEMP": TokenType.TEMPORARY,
 669        "TEMPORARY": TokenType.TEMPORARY,
 670        "THEN": TokenType.THEN,
 671        "TRUE": TokenType.TRUE,
 672        "UNION": TokenType.UNION,
 673        "UNKNOWN": TokenType.UNKNOWN,
 674        "UNNEST": TokenType.UNNEST,
 675        "UNPIVOT": TokenType.UNPIVOT,
 676        "UPDATE": TokenType.UPDATE,
 677        "USE": TokenType.USE,
 678        "USING": TokenType.USING,
 679        "UUID": TokenType.UUID,
 680        "VALUES": TokenType.VALUES,
 681        "VIEW": TokenType.VIEW,
 682        "VOLATILE": TokenType.VOLATILE,
 683        "WHEN": TokenType.WHEN,
 684        "WHERE": TokenType.WHERE,
 685        "WINDOW": TokenType.WINDOW,
 686        "WITH": TokenType.WITH,
 687        "APPLY": TokenType.APPLY,
 688        "ARRAY": TokenType.ARRAY,
 689        "BIT": TokenType.BIT,
 690        "BOOL": TokenType.BOOLEAN,
 691        "BOOLEAN": TokenType.BOOLEAN,
 692        "BYTE": TokenType.TINYINT,
 693        "MEDIUMINT": TokenType.MEDIUMINT,
 694        "TINYINT": TokenType.TINYINT,
 695        "SHORT": TokenType.SMALLINT,
 696        "SMALLINT": TokenType.SMALLINT,
 697        "INT128": TokenType.INT128,
 698        "INT2": TokenType.SMALLINT,
 699        "INTEGER": TokenType.INT,
 700        "INT": TokenType.INT,
 701        "INT4": TokenType.INT,
 702        "LONG": TokenType.BIGINT,
 703        "BIGINT": TokenType.BIGINT,
 704        "INT8": TokenType.BIGINT,
 705        "DEC": TokenType.DECIMAL,
 706        "DECIMAL": TokenType.DECIMAL,
 707        "BIGDECIMAL": TokenType.BIGDECIMAL,
 708        "BIGNUMERIC": TokenType.BIGDECIMAL,
 709        "MAP": TokenType.MAP,
 710        "NULLABLE": TokenType.NULLABLE,
 711        "NUMBER": TokenType.DECIMAL,
 712        "NUMERIC": TokenType.DECIMAL,
 713        "FIXED": TokenType.DECIMAL,
 714        "REAL": TokenType.FLOAT,
 715        "FLOAT": TokenType.FLOAT,
 716        "FLOAT4": TokenType.FLOAT,
 717        "FLOAT8": TokenType.DOUBLE,
 718        "DOUBLE": TokenType.DOUBLE,
 719        "DOUBLE PRECISION": TokenType.DOUBLE,
 720        "JSON": TokenType.JSON,
 721        "CHAR": TokenType.CHAR,
 722        "CHARACTER": TokenType.CHAR,
 723        "NCHAR": TokenType.NCHAR,
 724        "VARCHAR": TokenType.VARCHAR,
 725        "VARCHAR2": TokenType.VARCHAR,
 726        "NVARCHAR": TokenType.NVARCHAR,
 727        "NVARCHAR2": TokenType.NVARCHAR,
 728        "STR": TokenType.TEXT,
 729        "STRING": TokenType.TEXT,
 730        "TEXT": TokenType.TEXT,
 731        "LONGTEXT": TokenType.LONGTEXT,
 732        "MEDIUMTEXT": TokenType.MEDIUMTEXT,
 733        "TINYTEXT": TokenType.TINYTEXT,
 734        "CLOB": TokenType.TEXT,
 735        "LONGVARCHAR": TokenType.TEXT,
 736        "BINARY": TokenType.BINARY,
 737        "BLOB": TokenType.VARBINARY,
 738        "LONGBLOB": TokenType.LONGBLOB,
 739        "MEDIUMBLOB": TokenType.MEDIUMBLOB,
 740        "TINYBLOB": TokenType.TINYBLOB,
 741        "BYTEA": TokenType.VARBINARY,
 742        "VARBINARY": TokenType.VARBINARY,
 743        "TIME": TokenType.TIME,
 744        "TIMETZ": TokenType.TIMETZ,
 745        "TIMESTAMP": TokenType.TIMESTAMP,
 746        "TIMESTAMPTZ": TokenType.TIMESTAMPTZ,
 747        "TIMESTAMPLTZ": TokenType.TIMESTAMPLTZ,
 748        "DATE": TokenType.DATE,
 749        "DATETIME": TokenType.DATETIME,
 750        "INT4RANGE": TokenType.INT4RANGE,
 751        "INT4MULTIRANGE": TokenType.INT4MULTIRANGE,
 752        "INT8RANGE": TokenType.INT8RANGE,
 753        "INT8MULTIRANGE": TokenType.INT8MULTIRANGE,
 754        "NUMRANGE": TokenType.NUMRANGE,
 755        "NUMMULTIRANGE": TokenType.NUMMULTIRANGE,
 756        "TSRANGE": TokenType.TSRANGE,
 757        "TSMULTIRANGE": TokenType.TSMULTIRANGE,
 758        "TSTZRANGE": TokenType.TSTZRANGE,
 759        "TSTZMULTIRANGE": TokenType.TSTZMULTIRANGE,
 760        "DATERANGE": TokenType.DATERANGE,
 761        "DATEMULTIRANGE": TokenType.DATEMULTIRANGE,
 762        "UNIQUE": TokenType.UNIQUE,
 763        "STRUCT": TokenType.STRUCT,
 764        "VARIANT": TokenType.VARIANT,
 765        "ALTER": TokenType.ALTER,
 766        "ANALYZE": TokenType.COMMAND,
 767        "CALL": TokenType.COMMAND,
 768        "COMMENT": TokenType.COMMENT,
 769        "COPY": TokenType.COMMAND,
 770        "EXPLAIN": TokenType.COMMAND,
 771        "GRANT": TokenType.COMMAND,
 772        "OPTIMIZE": TokenType.COMMAND,
 773        "PREPARE": TokenType.COMMAND,
 774        "TRUNCATE": TokenType.COMMAND,
 775        "VACUUM": TokenType.COMMAND,
 776        "USER-DEFINED": TokenType.USERDEFINED,
 777        "FOR VERSION": TokenType.VERSION_SNAPSHOT,
 778        "FOR TIMESTAMP": TokenType.TIMESTAMP_SNAPSHOT,
 779    }
 780
 781    WHITE_SPACE: t.Dict[t.Optional[str], TokenType] = {
 782        " ": TokenType.SPACE,
 783        "\t": TokenType.SPACE,
 784        "\n": TokenType.BREAK,
 785        "\r": TokenType.BREAK,
 786        "\r\n": TokenType.BREAK,
 787    }
 788
 789    COMMANDS = {
 790        TokenType.COMMAND,
 791        TokenType.EXECUTE,
 792        TokenType.FETCH,
 793        TokenType.SHOW,
 794    }
 795
 796    COMMAND_PREFIX_TOKENS = {TokenType.SEMICOLON, TokenType.BEGIN}
 797
 798    # handle numeric literals like in hive (3L = BIGINT)
 799    NUMERIC_LITERALS: t.Dict[str, str] = {}
 800    ENCODE: t.Optional[str] = None
 801
 802    COMMENTS = ["--", ("/*", "*/")]
 803
 804    __slots__ = (
 805        "sql",
 806        "size",
 807        "tokens",
 808        "_start",
 809        "_current",
 810        "_line",
 811        "_col",
 812        "_comments",
 813        "_char",
 814        "_end",
 815        "_peek",
 816        "_prev_token_line",
 817    )
 818
 819    def __init__(self) -> None:
 820        self.reset()
 821
 822    def reset(self) -> None:
 823        self.sql = ""
 824        self.size = 0
 825        self.tokens: t.List[Token] = []
 826        self._start = 0
 827        self._current = 0
 828        self._line = 1
 829        self._col = 0
 830        self._comments: t.List[str] = []
 831
 832        self._char = ""
 833        self._end = False
 834        self._peek = ""
 835        self._prev_token_line = -1
 836
 837    def tokenize(self, sql: str) -> t.List[Token]:
 838        """Returns a list of tokens corresponding to the SQL string `sql`."""
 839        self.reset()
 840        self.sql = sql
 841        self.size = len(sql)
 842
 843        try:
 844            self._scan()
 845        except Exception as e:
 846            start = max(self._current - 50, 0)
 847            end = min(self._current + 50, self.size - 1)
 848            context = self.sql[start:end]
 849            raise TokenError(f"Error tokenizing '{context}'") from e
 850
 851        return self.tokens
 852
 853    def _scan(self, until: t.Optional[t.Callable] = None) -> None:
 854        while self.size and not self._end:
 855            self._start = self._current
 856            self._advance()
 857
 858            if self._char is None:
 859                break
 860
 861            if self._char not in self.WHITE_SPACE:
 862                if self._char.isdigit():
 863                    self._scan_number()
 864                elif self._char in self._IDENTIFIERS:
 865                    self._scan_identifier(self._IDENTIFIERS[self._char])
 866                else:
 867                    self._scan_keywords()
 868
 869            if until and until():
 870                break
 871
 872        if self.tokens and self._comments:
 873            self.tokens[-1].comments.extend(self._comments)
 874
 875    def _chars(self, size: int) -> str:
 876        if size == 1:
 877            return self._char
 878
 879        start = self._current - 1
 880        end = start + size
 881
 882        return self.sql[start:end] if end <= self.size else ""
 883
 884    def _advance(self, i: int = 1, alnum: bool = False) -> None:
 885        if self.WHITE_SPACE.get(self._char) is TokenType.BREAK:
 886            self._col = 1
 887            self._line += 1
 888        else:
 889            self._col += i
 890
 891        self._current += i
 892        self._end = self._current >= self.size
 893        self._char = self.sql[self._current - 1]
 894        self._peek = "" if self._end else self.sql[self._current]
 895
 896        if alnum and self._char.isalnum():
 897            # Here we use local variables instead of attributes for better performance
 898            _col = self._col
 899            _current = self._current
 900            _end = self._end
 901            _peek = self._peek
 902
 903            while _peek.isalnum():
 904                _col += 1
 905                _current += 1
 906                _end = _current >= self.size
 907                _peek = "" if _end else self.sql[_current]
 908
 909            self._col = _col
 910            self._current = _current
 911            self._end = _end
 912            self._peek = _peek
 913            self._char = self.sql[_current - 1]
 914
 915    @property
 916    def _text(self) -> str:
 917        return self.sql[self._start : self._current]
 918
 919    def peek(self, i: int = 0) -> str:
 920        i = self._current + i
 921        if i < self.size:
 922            return self.sql[i]
 923        return ""
 924
 925    def _add(self, token_type: TokenType, text: t.Optional[str] = None) -> None:
 926        self._prev_token_line = self._line
 927
 928        if self._comments and token_type == TokenType.SEMICOLON and self.tokens:
 929            self.tokens[-1].comments.extend(self._comments)
 930            self._comments = []
 931
 932        self.tokens.append(
 933            Token(
 934                token_type,
 935                text=self._text if text is None else text,
 936                line=self._line,
 937                col=self._col,
 938                start=self._start,
 939                end=self._current - 1,
 940                comments=self._comments,
 941            )
 942        )
 943        self._comments = []
 944
 945        # If we have either a semicolon or a begin token before the command's token, we'll parse
 946        # whatever follows the command's token as a string
 947        if (
 948            token_type in self.COMMANDS
 949            and self._peek != ";"
 950            and (len(self.tokens) == 1 or self.tokens[-2].token_type in self.COMMAND_PREFIX_TOKENS)
 951        ):
 952            start = self._current
 953            tokens = len(self.tokens)
 954            self._scan(lambda: self._peek == ";")
 955            self.tokens = self.tokens[:tokens]
 956            text = self.sql[start : self._current].strip()
 957            if text:
 958                self._add(TokenType.STRING, text)
 959
 960    def _scan_keywords(self) -> None:
 961        size = 0
 962        word = None
 963        chars = self._text
 964        char = chars
 965        prev_space = False
 966        skip = False
 967        trie = self._KEYWORD_TRIE
 968        single_token = char in self.SINGLE_TOKENS
 969
 970        while chars:
 971            if skip:
 972                result = TrieResult.PREFIX
 973            else:
 974                result, trie = in_trie(trie, char.upper())
 975
 976            if result == TrieResult.FAILED:
 977                break
 978            if result == TrieResult.EXISTS:
 979                word = chars
 980
 981            end = self._current + size
 982            size += 1
 983
 984            if end < self.size:
 985                char = self.sql[end]
 986                single_token = single_token or char in self.SINGLE_TOKENS
 987                is_space = char in self.WHITE_SPACE
 988
 989                if not is_space or not prev_space:
 990                    if is_space:
 991                        char = " "
 992                    chars += char
 993                    prev_space = is_space
 994                    skip = False
 995                else:
 996                    skip = True
 997            else:
 998                char = ""
 999                chars = " "
1000
1001        if word:
1002            if self._scan_string(word):
1003                return
1004            if self._scan_comment(word):
1005                return
1006            if prev_space or single_token or not char:
1007                self._advance(size - 1)
1008                word = word.upper()
1009                self._add(self.KEYWORDS[word], text=word)
1010                return
1011
1012        if self._char in self.SINGLE_TOKENS:
1013            self._add(self.SINGLE_TOKENS[self._char], text=self._char)
1014            return
1015
1016        self._scan_var()
1017
1018    def _scan_comment(self, comment_start: str) -> bool:
1019        if comment_start not in self._COMMENTS:
1020            return False
1021
1022        comment_start_line = self._line
1023        comment_start_size = len(comment_start)
1024        comment_end = self._COMMENTS[comment_start]
1025
1026        if comment_end:
1027            # Skip the comment's start delimiter
1028            self._advance(comment_start_size)
1029
1030            comment_end_size = len(comment_end)
1031            while not self._end and self._chars(comment_end_size) != comment_end:
1032                self._advance(alnum=True)
1033
1034            self._comments.append(self._text[comment_start_size : -comment_end_size + 1])
1035            self._advance(comment_end_size - 1)
1036        else:
1037            while not self._end and not self.WHITE_SPACE.get(self._peek) is TokenType.BREAK:
1038                self._advance(alnum=True)
1039            self._comments.append(self._text[comment_start_size:])
1040
1041        # Leading comment is attached to the succeeding token, whilst trailing comment to the preceding.
1042        # Multiple consecutive comments are preserved by appending them to the current comments list.
1043        if comment_start_line == self._prev_token_line:
1044            self.tokens[-1].comments.extend(self._comments)
1045            self._comments = []
1046            self._prev_token_line = self._line
1047
1048        return True
1049
1050    def _scan_number(self) -> None:
1051        if self._char == "0":
1052            peek = self._peek.upper()
1053            if peek == "B":
1054                return self._scan_bits() if self.BIT_STRINGS else self._add(TokenType.NUMBER)
1055            elif peek == "X":
1056                return self._scan_hex() if self.HEX_STRINGS else self._add(TokenType.NUMBER)
1057
1058        decimal = False
1059        scientific = 0
1060
1061        while True:
1062            if self._peek.isdigit():
1063                self._advance()
1064            elif self._peek == "." and not decimal:
1065                after = self.peek(1)
1066                if after.isdigit() or not after.isalpha():
1067                    decimal = True
1068                    self._advance()
1069                else:
1070                    return self._add(TokenType.VAR)
1071            elif self._peek in ("-", "+") and scientific == 1:
1072                scientific += 1
1073                self._advance()
1074            elif self._peek.upper() == "E" and not scientific:
1075                scientific += 1
1076                self._advance()
1077            elif self._peek.isidentifier():
1078                number_text = self._text
1079                literal = ""
1080
1081                while self._peek.strip() and self._peek not in self.SINGLE_TOKENS:
1082                    literal += self._peek
1083                    self._advance()
1084
1085                token_type = self.KEYWORDS.get(self.NUMERIC_LITERALS.get(literal.upper(), ""))
1086
1087                if token_type:
1088                    self._add(TokenType.NUMBER, number_text)
1089                    self._add(TokenType.DCOLON, "::")
1090                    return self._add(token_type, literal)
1091                elif self.IDENTIFIERS_CAN_START_WITH_DIGIT:
1092                    return self._add(TokenType.VAR)
1093
1094                self._advance(-len(literal))
1095                return self._add(TokenType.NUMBER, number_text)
1096            else:
1097                return self._add(TokenType.NUMBER)
1098
1099    def _scan_bits(self) -> None:
1100        self._advance()
1101        value = self._extract_value()
1102        try:
1103            # If `value` can't be converted to a binary, fallback to tokenizing it as an identifier
1104            int(value, 2)
1105            self._add(TokenType.BIT_STRING, value[2:])  # Drop the 0b
1106        except ValueError:
1107            self._add(TokenType.IDENTIFIER)
1108
1109    def _scan_hex(self) -> None:
1110        self._advance()
1111        value = self._extract_value()
1112        try:
1113            # If `value` can't be converted to a hex, fallback to tokenizing it as an identifier
1114            int(value, 16)
1115            self._add(TokenType.HEX_STRING, value[2:])  # Drop the 0x
1116        except ValueError:
1117            self._add(TokenType.IDENTIFIER)
1118
1119    def _extract_value(self) -> str:
1120        while True:
1121            char = self._peek.strip()
1122            if char and char not in self.SINGLE_TOKENS:
1123                self._advance(alnum=True)
1124            else:
1125                break
1126
1127        return self._text
1128
1129    def _scan_string(self, start: str) -> bool:
1130        base = None
1131        token_type = TokenType.STRING
1132
1133        if start in self._QUOTES:
1134            end = self._QUOTES[start]
1135        elif start in self._FORMAT_STRINGS:
1136            end, token_type = self._FORMAT_STRINGS[start]
1137
1138            if token_type == TokenType.HEX_STRING:
1139                base = 16
1140            elif token_type == TokenType.BIT_STRING:
1141                base = 2
1142            elif token_type == TokenType.HEREDOC_STRING:
1143                self._advance()
1144                tag = "" if self._char == end else self._extract_string(end)
1145                end = f"{start}{tag}{end}"
1146        else:
1147            return False
1148
1149        self._advance(len(start))
1150        text = self._extract_string(end)
1151
1152        if base:
1153            try:
1154                int(text, base)
1155            except:
1156                raise TokenError(
1157                    f"Numeric string contains invalid characters from {self._line}:{self._start}"
1158                )
1159        else:
1160            text = text.encode(self.ENCODE).decode(self.ENCODE) if self.ENCODE else text
1161
1162        self._add(token_type, text)
1163        return True
1164
1165    def _scan_identifier(self, identifier_end: str) -> None:
1166        self._advance()
1167        text = self._extract_string(identifier_end, self._IDENTIFIER_ESCAPES)
1168        self._add(TokenType.IDENTIFIER, text)
1169
1170    def _scan_var(self) -> None:
1171        while True:
1172            char = self._peek.strip()
1173            if char and (char in self.VAR_SINGLE_TOKENS or char not in self.SINGLE_TOKENS):
1174                self._advance(alnum=True)
1175            else:
1176                break
1177
1178        self._add(
1179            TokenType.VAR
1180            if self.tokens and self.tokens[-1].token_type == TokenType.PARAMETER
1181            else self.KEYWORDS.get(self._text.upper(), TokenType.VAR)
1182        )
1183
1184    def _extract_string(self, delimiter: str, escapes=None) -> str:
1185        text = ""
1186        delim_size = len(delimiter)
1187        escapes = self._STRING_ESCAPES if escapes is None else escapes
1188
1189        while True:
1190            if (
1191                self._char in escapes
1192                and (self._peek == delimiter or self._peek in escapes)
1193                and (self._char not in self._QUOTES or self._char == self._peek)
1194            ):
1195                if self._peek == delimiter:
1196                    text += self._peek
1197                else:
1198                    text += self._char + self._peek
1199
1200                if self._current + 1 < self.size:
1201                    self._advance(2)
1202                else:
1203                    raise TokenError(f"Missing {delimiter} from {self._line}:{self._current}")
1204            else:
1205                if self._chars(delim_size) == delimiter:
1206                    if delim_size > 1:
1207                        self._advance(delim_size - 1)
1208                    break
1209
1210                if self._end:
1211                    raise TokenError(f"Missing {delimiter} from {self._line}:{self._start}")
1212
1213                if self.ESCAPE_SEQUENCES and self._peek and self._char in self.STRING_ESCAPES:
1214                    escaped_sequence = self.ESCAPE_SEQUENCES.get(self._char + self._peek)
1215                    if escaped_sequence:
1216                        self._advance(2)
1217                        text += escaped_sequence
1218                        continue
1219
1220                current = self._current - 1
1221                self._advance(alnum=True)
1222                text += self.sql[current : self._current - 1]
1223
1224        return text
SINGLE_TOKENS = {'(': <TokenType.L_PAREN: 'L_PAREN'>, ')': <TokenType.R_PAREN: 'R_PAREN'>, '[': <TokenType.L_BRACKET: 'L_BRACKET'>, ']': <TokenType.R_BRACKET: 'R_BRACKET'>, '{': <TokenType.L_BRACE: 'L_BRACE'>, '}': <TokenType.R_BRACE: 'R_BRACE'>, '&': <TokenType.AMP: 'AMP'>, '^': <TokenType.CARET: 'CARET'>, ':': <TokenType.COLON: 'COLON'>, ',': <TokenType.COMMA: 'COMMA'>, '.': <TokenType.DOT: 'DOT'>, '-': <TokenType.DASH: 'DASH'>, '=': <TokenType.EQ: 'EQ'>, '>': <TokenType.GT: 'GT'>, '<': <TokenType.LT: 'LT'>, '%': <TokenType.MOD: 'MOD'>, '!': <TokenType.NOT: 'NOT'>, '|': <TokenType.PIPE: 'PIPE'>, '+': <TokenType.PLUS: 'PLUS'>, ';': <TokenType.SEMICOLON: 'SEMICOLON'>, '/': <TokenType.SLASH: 'SLASH'>, '\\': <TokenType.BACKSLASH: 'BACKSLASH'>, '*': <TokenType.STAR: 'STAR'>, '~': <TokenType.TILDA: 'TILDA'>, '?': <TokenType.PLACEHOLDER: 'PLACEHOLDER'>, '@': <TokenType.PARAMETER: 'PARAMETER'>, "'": <TokenType.QUOTE: 'QUOTE'>, '`': <TokenType.IDENTIFIER: 'IDENTIFIER'>, '"': <TokenType.IDENTIFIER: 'IDENTIFIER'>, '#': <TokenType.HASH: 'HASH'>}
BIT_STRINGS: List[Union[str, Tuple[str, str]]] = []
BYTE_STRINGS: List[Union[str, Tuple[str, str]]] = []
HEX_STRINGS: List[Union[str, Tuple[str, str]]] = []
RAW_STRINGS: List[Union[str, Tuple[str, str]]] = []
HEREDOC_STRINGS: List[Union[str, Tuple[str, str]]] = []
IDENTIFIERS: List[Union[str, Tuple[str, str]]] = ['"']
IDENTIFIER_ESCAPES = ['"']
QUOTES: List[Union[str, Tuple[str, str]]] = ["'"]
STRING_ESCAPES = ["'"]
VAR_SINGLE_TOKENS: Set[str] = set()
ESCAPE_SEQUENCES: Dict[str, str] = {}
IDENTIFIERS_CAN_START_WITH_DIGIT: bool = False
KEYWORDS: Dict[str, TokenType] = {'{%': <TokenType.BLOCK_START: 'BLOCK_START'>, '{%+': <TokenType.BLOCK_START: 'BLOCK_START'>, '{%-': <TokenType.BLOCK_START: 'BLOCK_START'>, '%}': <TokenType.BLOCK_END: 'BLOCK_END'>, '+%}': <TokenType.BLOCK_END: 'BLOCK_END'>, '-%}': <TokenType.BLOCK_END: 'BLOCK_END'>, '{{+': <TokenType.BLOCK_START: 'BLOCK_START'>, '{{-': <TokenType.BLOCK_START: 'BLOCK_START'>, '+}}': <TokenType.BLOCK_END: 'BLOCK_END'>, '-}}': <TokenType.BLOCK_END: 'BLOCK_END'>, '/*+': <TokenType.HINT: 'HINT'>, '==': <TokenType.EQ: 'EQ'>, '::': <TokenType.DCOLON: 'DCOLON'>, '||': <TokenType.DPIPE: 'DPIPE'>, '>=': <TokenType.GTE: 'GTE'>, '<=': <TokenType.LTE: 'LTE'>, '<>': <TokenType.NEQ: 'NEQ'>, '!=': <TokenType.NEQ: 'NEQ'>, '<=>': <TokenType.NULLSAFE_EQ: 'NULLSAFE_EQ'>, '->': <TokenType.ARROW: 'ARROW'>, '->>': <TokenType.DARROW: 'DARROW'>, '=>': <TokenType.FARROW: 'FARROW'>, '#>': <TokenType.HASH_ARROW: 'HASH_ARROW'>, '#>>': <TokenType.DHASH_ARROW: 'DHASH_ARROW'>, '<->': <TokenType.LR_ARROW: 'LR_ARROW'>, '&&': <TokenType.DAMP: 'DAMP'>, '??': <TokenType.DQMARK: 'DQMARK'>, 'ALL': <TokenType.ALL: 'ALL'>, 'ALWAYS': <TokenType.ALWAYS: 'ALWAYS'>, 'AND': <TokenType.AND: 'AND'>, 'ANTI': <TokenType.ANTI: 'ANTI'>, 'ANY': <TokenType.ANY: 'ANY'>, 'ASC': <TokenType.ASC: 'ASC'>, 'AS': <TokenType.ALIAS: 'ALIAS'>, 'ASOF': <TokenType.ASOF: 'ASOF'>, 'AUTOINCREMENT': <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, 'AUTO_INCREMENT': <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, 'BEGIN': <TokenType.BEGIN: 'BEGIN'>, 'BETWEEN': <TokenType.BETWEEN: 'BETWEEN'>, 'CACHE': <TokenType.CACHE: 'CACHE'>, 'UNCACHE': <TokenType.UNCACHE: 'UNCACHE'>, 'CASE': <TokenType.CASE: 'CASE'>, 'CHARACTER SET': <TokenType.CHARACTER_SET: 'CHARACTER_SET'>, 'CLUSTER BY': <TokenType.CLUSTER_BY: 'CLUSTER_BY'>, 'COLLATE': <TokenType.COLLATE: 'COLLATE'>, 'COLUMN': <TokenType.COLUMN: 'COLUMN'>, 'COMMIT': <TokenType.COMMIT: 'COMMIT'>, 'CONNECT BY': <TokenType.CONNECT_BY: 'CONNECT_BY'>, 'CONSTRAINT': <TokenType.CONSTRAINT: 'CONSTRAINT'>, 'CREATE': <TokenType.CREATE: 'CREATE'>, 'CROSS': <TokenType.CROSS: 'CROSS'>, 'CUBE': <TokenType.CUBE: 'CUBE'>, 'CURRENT_DATE': <TokenType.CURRENT_DATE: 'CURRENT_DATE'>, 'CURRENT_TIME': <TokenType.CURRENT_TIME: 'CURRENT_TIME'>, 'CURRENT_TIMESTAMP': <TokenType.CURRENT_TIMESTAMP: 'CURRENT_TIMESTAMP'>, 'CURRENT_USER': <TokenType.CURRENT_USER: 'CURRENT_USER'>, 'DATABASE': <TokenType.DATABASE: 'DATABASE'>, 'DEFAULT': <TokenType.DEFAULT: 'DEFAULT'>, 'DELETE': <TokenType.DELETE: 'DELETE'>, 'DESC': <TokenType.DESC: 'DESC'>, 'DESCRIBE': <TokenType.DESCRIBE: 'DESCRIBE'>, 'DISTINCT': <TokenType.DISTINCT: 'DISTINCT'>, 'DISTRIBUTE BY': <TokenType.DISTRIBUTE_BY: 'DISTRIBUTE_BY'>, 'DIV': <TokenType.DIV: 'DIV'>, 'DROP': <TokenType.DROP: 'DROP'>, 'ELSE': <TokenType.ELSE: 'ELSE'>, 'END': <TokenType.END: 'END'>, 'ESCAPE': <TokenType.ESCAPE: 'ESCAPE'>, 'EXCEPT': <TokenType.EXCEPT: 'EXCEPT'>, 'EXECUTE': <TokenType.EXECUTE: 'EXECUTE'>, 'EXISTS': <TokenType.EXISTS: 'EXISTS'>, 'FALSE': <TokenType.FALSE: 'FALSE'>, 'FETCH': <TokenType.FETCH: 'FETCH'>, 'FILTER': <TokenType.FILTER: 'FILTER'>, 'FIRST': <TokenType.FIRST: 'FIRST'>, 'FULL': <TokenType.FULL: 'FULL'>, 'FUNCTION': <TokenType.FUNCTION: 'FUNCTION'>, 'FOR': <TokenType.FOR: 'FOR'>, 'FOREIGN KEY': <TokenType.FOREIGN_KEY: 'FOREIGN_KEY'>, 'FORMAT': <TokenType.FORMAT: 'FORMAT'>, 'FROM': <TokenType.FROM: 'FROM'>, 'GEOGRAPHY': <TokenType.GEOGRAPHY: 'GEOGRAPHY'>, 'GEOMETRY': <TokenType.GEOMETRY: 'GEOMETRY'>, 'GLOB': <TokenType.GLOB: 'GLOB'>, 'GROUP BY': <TokenType.GROUP_BY: 'GROUP_BY'>, 'GROUPING SETS': <TokenType.GROUPING_SETS: 'GROUPING_SETS'>, 'HAVING': <TokenType.HAVING: 'HAVING'>, 'ILIKE': <TokenType.ILIKE: 'ILIKE'>, 'IN': <TokenType.IN: 'IN'>, 'INDEX': <TokenType.INDEX: 'INDEX'>, 'INET': <TokenType.INET: 'INET'>, 'INNER': <TokenType.INNER: 'INNER'>, 'INSERT': <TokenType.INSERT: 'INSERT'>, 'INTERVAL': <TokenType.INTERVAL: 'INTERVAL'>, 'INTERSECT': <TokenType.INTERSECT: 'INTERSECT'>, 'INTO': <TokenType.INTO: 'INTO'>, 'IS': <TokenType.IS: 'IS'>, 'ISNULL': <TokenType.ISNULL: 'ISNULL'>, 'JOIN': <TokenType.JOIN: 'JOIN'>, 'KEEP': <TokenType.KEEP: 'KEEP'>, 'KILL': <TokenType.KILL: 'KILL'>, 'LATERAL': <TokenType.LATERAL: 'LATERAL'>, 'LEFT': <TokenType.LEFT: 'LEFT'>, 'LIKE': <TokenType.LIKE: 'LIKE'>, 'LIMIT': <TokenType.LIMIT: 'LIMIT'>, 'LOAD': <TokenType.LOAD: 'LOAD'>, 'LOCK': <TokenType.LOCK: 'LOCK'>, 'MERGE': <TokenType.MERGE: 'MERGE'>, 'NATURAL': <TokenType.NATURAL: 'NATURAL'>, 'NEXT': <TokenType.NEXT: 'NEXT'>, 'NOT': <TokenType.NOT: 'NOT'>, 'NOTNULL': <TokenType.NOTNULL: 'NOTNULL'>, 'NULL': <TokenType.NULL: 'NULL'>, 'OBJECT': <TokenType.OBJECT: 'OBJECT'>, 'OFFSET': <TokenType.OFFSET: 'OFFSET'>, 'ON': <TokenType.ON: 'ON'>, 'OR': <TokenType.OR: 'OR'>, 'XOR': <TokenType.XOR: 'XOR'>, 'ORDER BY': <TokenType.ORDER_BY: 'ORDER_BY'>, 'ORDINALITY': <TokenType.ORDINALITY: 'ORDINALITY'>, 'OUTER': <TokenType.OUTER: 'OUTER'>, 'OVER': <TokenType.OVER: 'OVER'>, 'OVERLAPS': <TokenType.OVERLAPS: 'OVERLAPS'>, 'OVERWRITE': <TokenType.OVERWRITE: 'OVERWRITE'>, 'PARTITION': <TokenType.PARTITION: 'PARTITION'>, 'PARTITION BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PARTITIONED BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PARTITIONED_BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PERCENT': <TokenType.PERCENT: 'PERCENT'>, 'PIVOT': <TokenType.PIVOT: 'PIVOT'>, 'PRAGMA': <TokenType.PRAGMA: 'PRAGMA'>, 'PRIMARY KEY': <TokenType.PRIMARY_KEY: 'PRIMARY_KEY'>, 'PROCEDURE': <TokenType.PROCEDURE: 'PROCEDURE'>, 'QUALIFY': <TokenType.QUALIFY: 'QUALIFY'>, 'RANGE': <TokenType.RANGE: 'RANGE'>, 'RECURSIVE': <TokenType.RECURSIVE: 'RECURSIVE'>, 'REGEXP': <TokenType.RLIKE: 'RLIKE'>, 'REPLACE': <TokenType.REPLACE: 'REPLACE'>, 'RETURNING': <TokenType.RETURNING: 'RETURNING'>, 'REFERENCES': <TokenType.REFERENCES: 'REFERENCES'>, 'RIGHT': <TokenType.RIGHT: 'RIGHT'>, 'RLIKE': <TokenType.RLIKE: 'RLIKE'>, 'ROLLBACK': <TokenType.ROLLBACK: 'ROLLBACK'>, 'ROLLUP': <TokenType.ROLLUP: 'ROLLUP'>, 'ROW': <TokenType.ROW: 'ROW'>, 'ROWS': <TokenType.ROWS: 'ROWS'>, 'SCHEMA': <TokenType.SCHEMA: 'SCHEMA'>, 'SELECT': <TokenType.SELECT: 'SELECT'>, 'SEMI': <TokenType.SEMI: 'SEMI'>, 'SET': <TokenType.SET: 'SET'>, 'SETTINGS': <TokenType.SETTINGS: 'SETTINGS'>, 'SHOW': <TokenType.SHOW: 'SHOW'>, 'SIMILAR TO': <TokenType.SIMILAR_TO: 'SIMILAR_TO'>, 'SOME': <TokenType.SOME: 'SOME'>, 'SORT BY': <TokenType.SORT_BY: 'SORT_BY'>, 'START WITH': <TokenType.START_WITH: 'START_WITH'>, 'TABLE': <TokenType.TABLE: 'TABLE'>, 'TABLESAMPLE': <TokenType.TABLE_SAMPLE: 'TABLE_SAMPLE'>, 'TEMP': <TokenType.TEMPORARY: 'TEMPORARY'>, 'TEMPORARY': <TokenType.TEMPORARY: 'TEMPORARY'>, 'THEN': <TokenType.THEN: 'THEN'>, 'TRUE': <TokenType.TRUE: 'TRUE'>, 'UNION': <TokenType.UNION: 'UNION'>, 'UNKNOWN': <TokenType.UNKNOWN: 'UNKNOWN'>, 'UNNEST': <TokenType.UNNEST: 'UNNEST'>, 'UNPIVOT': <TokenType.UNPIVOT: 'UNPIVOT'>, 'UPDATE': <TokenType.UPDATE: 'UPDATE'>, 'USE': <TokenType.USE: 'USE'>, 'USING': <TokenType.USING: 'USING'>, 'UUID': <TokenType.UUID: 'UUID'>, 'VALUES': <TokenType.VALUES: 'VALUES'>, 'VIEW': <TokenType.VIEW: 'VIEW'>, 'VOLATILE': <TokenType.VOLATILE: 'VOLATILE'>, 'WHEN': <TokenType.WHEN: 'WHEN'>, 'WHERE': <TokenType.WHERE: 'WHERE'>, 'WINDOW': <TokenType.WINDOW: 'WINDOW'>, 'WITH': <TokenType.WITH: 'WITH'>, 'APPLY': <TokenType.APPLY: 'APPLY'>, 'ARRAY': <TokenType.ARRAY: 'ARRAY'>, 'BIT': <TokenType.BIT: 'BIT'>, 'BOOL': <TokenType.BOOLEAN: 'BOOLEAN'>, 'BOOLEAN': <TokenType.BOOLEAN: 'BOOLEAN'>, 'BYTE': <TokenType.TINYINT: 'TINYINT'>, 'MEDIUMINT': <TokenType.MEDIUMINT: 'MEDIUMINT'>, 'TINYINT': <TokenType.TINYINT: 'TINYINT'>, 'SHORT': <TokenType.SMALLINT: 'SMALLINT'>, 'SMALLINT': <TokenType.SMALLINT: 'SMALLINT'>, 'INT128': <TokenType.INT128: 'INT128'>, 'INT2': <TokenType.SMALLINT: 'SMALLINT'>, 'INTEGER': <TokenType.INT: 'INT'>, 'INT': <TokenType.INT: 'INT'>, 'INT4': <TokenType.INT: 'INT'>, 'LONG': <TokenType.BIGINT: 'BIGINT'>, 'BIGINT': <TokenType.BIGINT: 'BIGINT'>, 'INT8': <TokenType.BIGINT: 'BIGINT'>, 'DEC': <TokenType.DECIMAL: 'DECIMAL'>, 'DECIMAL': <TokenType.DECIMAL: 'DECIMAL'>, 'BIGDECIMAL': <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, 'BIGNUMERIC': <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, 'MAP': <TokenType.MAP: 'MAP'>, 'NULLABLE': <TokenType.NULLABLE: 'NULLABLE'>, 'NUMBER': <TokenType.DECIMAL: 'DECIMAL'>, 'NUMERIC': <TokenType.DECIMAL: 'DECIMAL'>, 'FIXED': <TokenType.DECIMAL: 'DECIMAL'>, 'REAL': <TokenType.FLOAT: 'FLOAT'>, 'FLOAT': <TokenType.FLOAT: 'FLOAT'>, 'FLOAT4': <TokenType.FLOAT: 'FLOAT'>, 'FLOAT8': <TokenType.DOUBLE: 'DOUBLE'>, 'DOUBLE': <TokenType.DOUBLE: 'DOUBLE'>, 'DOUBLE PRECISION': <TokenType.DOUBLE: 'DOUBLE'>, 'JSON': <TokenType.JSON: 'JSON'>, 'CHAR': <TokenType.CHAR: 'CHAR'>, 'CHARACTER': <TokenType.CHAR: 'CHAR'>, 'NCHAR': <TokenType.NCHAR: 'NCHAR'>, 'VARCHAR': <TokenType.VARCHAR: 'VARCHAR'>, 'VARCHAR2': <TokenType.VARCHAR: 'VARCHAR'>, 'NVARCHAR': <TokenType.NVARCHAR: 'NVARCHAR'>, 'NVARCHAR2': <TokenType.NVARCHAR: 'NVARCHAR'>, 'STR': <TokenType.TEXT: 'TEXT'>, 'STRING': <TokenType.TEXT: 'TEXT'>, 'TEXT': <TokenType.TEXT: 'TEXT'>, 'LONGTEXT': <TokenType.LONGTEXT: 'LONGTEXT'>, 'MEDIUMTEXT': <TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>, 'TINYTEXT': <TokenType.TINYTEXT: 'TINYTEXT'>, 'CLOB': <TokenType.TEXT: 'TEXT'>, 'LONGVARCHAR': <TokenType.TEXT: 'TEXT'>, 'BINARY': <TokenType.BINARY: 'BINARY'>, 'BLOB': <TokenType.VARBINARY: 'VARBINARY'>, 'LONGBLOB': <TokenType.LONGBLOB: 'LONGBLOB'>, 'MEDIUMBLOB': <TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>, 'TINYBLOB': <TokenType.TINYBLOB: 'TINYBLOB'>, 'BYTEA': <TokenType.VARBINARY: 'VARBINARY'>, 'VARBINARY': <TokenType.VARBINARY: 'VARBINARY'>, 'TIME': <TokenType.TIME: 'TIME'>, 'TIMETZ': <TokenType.TIMETZ: 'TIMETZ'>, 'TIMESTAMP': <TokenType.TIMESTAMP: 'TIMESTAMP'>, 'TIMESTAMPTZ': <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>, 'TIMESTAMPLTZ': <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>, 'DATE': <TokenType.DATE: 'DATE'>, 'DATETIME': <TokenType.DATETIME: 'DATETIME'>, 'INT4RANGE': <TokenType.INT4RANGE: 'INT4RANGE'>, 'INT4MULTIRANGE': <TokenType.INT4MULTIRANGE: 'INT4MULTIRANGE'>, 'INT8RANGE': <TokenType.INT8RANGE: 'INT8RANGE'>, 'INT8MULTIRANGE': <TokenType.INT8MULTIRANGE: 'INT8MULTIRANGE'>, 'NUMRANGE': <TokenType.NUMRANGE: 'NUMRANGE'>, 'NUMMULTIRANGE': <TokenType.NUMMULTIRANGE: 'NUMMULTIRANGE'>, 'TSRANGE': <TokenType.TSRANGE: 'TSRANGE'>, 'TSMULTIRANGE': <TokenType.TSMULTIRANGE: 'TSMULTIRANGE'>, 'TSTZRANGE': <TokenType.TSTZRANGE: 'TSTZRANGE'>, 'TSTZMULTIRANGE': <TokenType.TSTZMULTIRANGE: 'TSTZMULTIRANGE'>, 'DATERANGE': <TokenType.DATERANGE: 'DATERANGE'>, 'DATEMULTIRANGE': <TokenType.DATEMULTIRANGE: 'DATEMULTIRANGE'>, 'UNIQUE': <TokenType.UNIQUE: 'UNIQUE'>, 'STRUCT': <TokenType.STRUCT: 'STRUCT'>, 'VARIANT': <TokenType.VARIANT: 'VARIANT'>, 'ALTER': <TokenType.ALTER: 'ALTER'>, 'ANALYZE': <TokenType.COMMAND: 'COMMAND'>, 'CALL': <TokenType.COMMAND: 'COMMAND'>, 'COMMENT': <TokenType.COMMENT: 'COMMENT'>, 'COPY': <TokenType.COMMAND: 'COMMAND'>, 'EXPLAIN': <TokenType.COMMAND: 'COMMAND'>, 'GRANT': <TokenType.COMMAND: 'COMMAND'>, 'OPTIMIZE': <TokenType.COMMAND: 'COMMAND'>, 'PREPARE': <TokenType.COMMAND: 'COMMAND'>, 'TRUNCATE': <TokenType.COMMAND: 'COMMAND'>, 'VACUUM': <TokenType.COMMAND: 'COMMAND'>, 'USER-DEFINED': <TokenType.USERDEFINED: 'USERDEFINED'>, 'FOR VERSION': <TokenType.VERSION_SNAPSHOT: 'VERSION_SNAPSHOT'>, 'FOR TIMESTAMP': <TokenType.TIMESTAMP_SNAPSHOT: 'TIMESTAMP_SNAPSHOT'>}
WHITE_SPACE: Dict[Optional[str], TokenType] = {' ': <TokenType.SPACE: 'SPACE'>, '\t': <TokenType.SPACE: 'SPACE'>, '\n': <TokenType.BREAK: 'BREAK'>, '\r': <TokenType.BREAK: 'BREAK'>, '\r\n': <TokenType.BREAK: 'BREAK'>}
COMMANDS = {<TokenType.COMMAND: 'COMMAND'>, <TokenType.SHOW: 'SHOW'>, <TokenType.FETCH: 'FETCH'>, <TokenType.EXECUTE: 'EXECUTE'>}
COMMAND_PREFIX_TOKENS = {<TokenType.BEGIN: 'BEGIN'>, <TokenType.SEMICOLON: 'SEMICOLON'>}
NUMERIC_LITERALS: Dict[str, str] = {}
ENCODE: Optional[str] = None
COMMENTS = ['--', ('/*', '*/')]
def reset(self) -> None:
822    def reset(self) -> None:
823        self.sql = ""
824        self.size = 0
825        self.tokens: t.List[Token] = []
826        self._start = 0
827        self._current = 0
828        self._line = 1
829        self._col = 0
830        self._comments: t.List[str] = []
831
832        self._char = ""
833        self._end = False
834        self._peek = ""
835        self._prev_token_line = -1
def tokenize(self, sql: str) -> List[Token]:
837    def tokenize(self, sql: str) -> t.List[Token]:
838        """Returns a list of tokens corresponding to the SQL string `sql`."""
839        self.reset()
840        self.sql = sql
841        self.size = len(sql)
842
843        try:
844            self._scan()
845        except Exception as e:
846            start = max(self._current - 50, 0)
847            end = min(self._current + 50, self.size - 1)
848            context = self.sql[start:end]
849            raise TokenError(f"Error tokenizing '{context}'") from e
850
851        return self.tokens

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

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