datakiln.metadata.dialect module

SQL dialects.

class datakiln.metadata.dialect.ExtendedPostgres(**kwargs)[source]

Bases: Postgres

PostgreSQL with the syntax that SQLGlot does not read. An aggregate is created like a function, with options in place of a body.

class Tokenizer(dialect: DialectType = None)[source]

Bases: Tokenizer

Tokenizer that reads AGGREGATE as it reads FUNCTION.

KEYWORDS: ClassVar[dict[str, TokenType]] = {'!=': TokenType.NEQ, '#-': TokenType.HASH_DASH, '#>': TokenType.HASH_ARROW, '#>>': TokenType.DHASH_ARROW, '%}': TokenType.BLOCK_END, '&&': TokenType.DAMP, '&<': TokenType.AMP_LT, '&>': TokenType.AMP_GT, '+%}': TokenType.BLOCK_END, '+}}': TokenType.BLOCK_END, '-%}': TokenType.BLOCK_END, '->': TokenType.ARROW, '->>': TokenType.DARROW, '-|-': TokenType.ADJACENT, '-}}': TokenType.BLOCK_END, '::': TokenType.DCOLON, ':=': TokenType.COLON_EQ, '<->': TokenType.LR_ARROW, '<<->>': TokenType.LLRR_ARROW, '<=': TokenType.LTE, '<=>': TokenType.NULLSAFE_EQ, '<>': TokenType.NEQ, '<@': TokenType.LT_AT, '==': TokenType.EQ, '=>': TokenType.FARROW, '>=': TokenType.GTE, '?&': TokenType.QMARK_AMP, '?::': TokenType.QDCOLON, '??': TokenType.DQMARK, '?|': TokenType.QMARK_PIPE, '@>': TokenType.AT_GT, '@?': TokenType.AT_QMARK, '@@': TokenType.DAT, 'AGGREGATE': TokenType.FUNCTION, 'ALL': TokenType.ALL, 'ALTER': TokenType.ALTER, 'ANALYZE': TokenType.ANALYZE, 'AND': TokenType.AND, 'ANTI': TokenType.ANTI, 'ANY': TokenType.ANY, 'APPLY': TokenType.APPLY, 'ARRAY': TokenType.ARRAY, 'AS': TokenType.ALIAS, 'ASC': TokenType.ASC, 'ASOF': TokenType.ASOF, 'AUTOINCREMENT': TokenType.AUTO_INCREMENT, 'AUTO_INCREMENT': TokenType.AUTO_INCREMENT, 'BEGIN': TokenType.BEGIN, 'BETWEEN': TokenType.BETWEEN, 'BIGDECIMAL': TokenType.BIGDECIMAL, 'BIGINT': TokenType.BIGINT, 'BIGNUM': TokenType.BIGNUM, 'BIGNUMERIC': TokenType.BIGDECIMAL, 'BIGSERIAL': TokenType.BIGSERIAL, 'BINARY': TokenType.BINARY, 'BIT': TokenType.BIT, 'BLOB': TokenType.VARBINARY, 'BOOL': TokenType.BOOLEAN, 'BOOLEAN': TokenType.BOOLEAN, 'BPCHAR': TokenType.BPCHAR, 'BYTE': TokenType.TINYINT, 'BYTEA': TokenType.VARBINARY, 'CACHE': TokenType.CACHE, 'CALL': TokenType.COMMAND, 'CASE': TokenType.CASE, 'CHAR': TokenType.CHAR, 'CHAR VARYING': TokenType.VARCHAR, 'CHARACTER': TokenType.CHAR, 'CHARACTER VARYING': TokenType.VARCHAR, 'CLOB': TokenType.TEXT, 'CLUSTER BY': TokenType.CLUSTER_BY, 'COLLATE': TokenType.COLLATE, 'COLUMN': TokenType.COLUMN, 'COMMENT': TokenType.COMMENT, 'COMMIT': TokenType.COMMIT, 'CONNECT BY': TokenType.CONNECT_BY, 'CONSTRAINT': TokenType.CONSTRAINT, 'COPY': TokenType.COPY, 'CREATE': TokenType.CREATE, 'CROSS': TokenType.CROSS, 'CSTRING': TokenType.PSEUDO_TYPE, 'CUBE': TokenType.CUBE, 'CURRENT_CATALOG': TokenType.CURRENT_CATALOG, 'CURRENT_DATE': TokenType.CURRENT_DATE, 'CURRENT_SCHEMA': TokenType.CURRENT_SCHEMA, 'CURRENT_TIME': TokenType.CURRENT_TIME, 'CURRENT_TIMESTAMP': TokenType.CURRENT_TIMESTAMP, 'CURRENT_USER': TokenType.CURRENT_USER, 'DATABASE': TokenType.DATABASE, 'DATE': TokenType.DATE, 'DATEMULTIRANGE': TokenType.DATEMULTIRANGE, 'DATERANGE': TokenType.DATERANGE, 'DATETIME': TokenType.DATETIME, 'DEC': TokenType.DECIMAL, 'DECFLOAT': TokenType.DECFLOAT, 'DECIMAL': TokenType.DECIMAL, 'DECIMAL128': TokenType.DECIMAL128, 'DECIMAL256': TokenType.DECIMAL256, 'DECIMAL32': TokenType.DECIMAL32, 'DECIMAL64': TokenType.DECIMAL64, 'DECLARE': TokenType.COMMAND, 'DEFAULT': TokenType.DEFAULT, 'DELETE': TokenType.DELETE, 'DESC': TokenType.DESC, 'DESCRIBE': TokenType.DESCRIBE, 'DISTINCT': TokenType.DISTINCT, 'DISTRIBUTE BY': TokenType.DISTRIBUTE_BY, 'DO': TokenType.COMMAND, 'DOUBLE': TokenType.DOUBLE, 'DOUBLE PRECISION': TokenType.DOUBLE, 'DROP': TokenType.DROP, 'ELSE': TokenType.ELSE, 'END': TokenType.END, 'ENUM': TokenType.ENUM, 'ESCAPE': TokenType.ESCAPE, 'EXCEPT': TokenType.EXCEPT, 'EXEC': TokenType.COMMAND, 'EXECUTE': TokenType.EXECUTE, 'EXISTS': TokenType.EXISTS, 'EXPLAIN': TokenType.COMMAND, 'FALSE': TokenType.FALSE, 'FETCH': TokenType.FETCH, 'FILE': TokenType.FILE, 'FILTER': TokenType.FILTER, 'FIRST': TokenType.FIRST, 'FIXED': TokenType.DECIMAL, 'FLOAT': TokenType.DOUBLE, 'FLOAT4': TokenType.FLOAT, 'FLOAT8': TokenType.DOUBLE, 'FOR': TokenType.FOR, 'FOREIGN KEY': TokenType.FOREIGN_KEY, 'FORMAT': TokenType.FORMAT, 'FROM': TokenType.FROM, 'FULL': TokenType.FULL, 'FUNCTION': TokenType.FUNCTION, 'GEOGRAPHY': TokenType.GEOGRAPHY, 'GEOMETRY': TokenType.GEOMETRY, 'GLOB': TokenType.GLOB, 'GRANT': TokenType.GRANT, 'GROUP BY': TokenType.GROUP_BY, 'GROUPING SETS': TokenType.GROUPING_SETS, 'HAVING': TokenType.HAVING, 'HSTORE': TokenType.HSTORE, 'HUGEINT': TokenType.INT128, 'ILIKE': TokenType.ILIKE, 'IN': TokenType.IN, 'INDEX': TokenType.INDEX, 'INET': TokenType.INET, 'INNER': TokenType.INNER, 'INOUT': TokenType.INOUT, 'INSERT': TokenType.INSERT, 'INT': TokenType.INT, 'INT1': TokenType.TINYINT, 'INT128': TokenType.INT128, 'INT16': TokenType.SMALLINT, 'INT2': TokenType.SMALLINT, 'INT256': TokenType.INT256, 'INT32': TokenType.INT, 'INT4': TokenType.INT, 'INT4MULTIRANGE': TokenType.INT4MULTIRANGE, 'INT4RANGE': TokenType.INT4RANGE, 'INT64': TokenType.BIGINT, 'INT8': TokenType.BIGINT, 'INT8MULTIRANGE': TokenType.INT8MULTIRANGE, 'INT8RANGE': TokenType.INT8RANGE, 'INTEGER': TokenType.INT, 'INTERSECT': TokenType.INTERSECT, 'INTERVAL': TokenType.INTERVAL, 'INTO': TokenType.INTO, 'IS': TokenType.IS, 'ISNULL': TokenType.ISNULL, 'JOIN': TokenType.JOIN, 'JSON': TokenType.JSON, 'JSONB': TokenType.JSONB, 'KEEP': TokenType.KEEP, 'KILL': TokenType.KILL, 'LATERAL': TokenType.LATERAL, 'LEFT': TokenType.LEFT, 'LIKE': TokenType.LIKE, 'LIMIT': TokenType.LIMIT, 'LIST': TokenType.LIST, 'LOAD': TokenType.LOAD, 'LOCALTIME': TokenType.LOCALTIME, 'LOCALTIMESTAMP': TokenType.LOCALTIMESTAMP, 'LOCK': TokenType.LOCK, 'LONG': TokenType.BIGINT, 'LONGBLOB': TokenType.LONGBLOB, 'LONGTEXT': TokenType.LONGTEXT, 'LONGVARCHAR': TokenType.TEXT, 'MAP': TokenType.MAP, 'MEDIUMBLOB': TokenType.MEDIUMBLOB, 'MEDIUMINT': TokenType.MEDIUMINT, 'MEDIUMTEXT': TokenType.MEDIUMTEXT, 'MERGE': TokenType.MERGE, 'MONEY': TokenType.MONEY, 'NAME': TokenType.NAME, 'NAMESPACE': TokenType.NAMESPACE, 'NATURAL': TokenType.NATURAL, 'NCHAR': TokenType.NCHAR, 'NEXT': TokenType.NEXT, 'NOT': TokenType.NOT, 'NOTNULL': TokenType.NOTNULL, 'NULL': TokenType.NULL, 'NULLABLE': TokenType.NULLABLE, 'NUMBER': TokenType.DECIMAL, 'NUMERIC': TokenType.DECIMAL, 'NUMMULTIRANGE': TokenType.NUMMULTIRANGE, 'NUMRANGE': TokenType.NUMRANGE, 'NVARCHAR': TokenType.NVARCHAR, 'NVARCHAR2': TokenType.NVARCHAR, 'OBJECT': TokenType.OBJECT, 'OFFSET': TokenType.OFFSET, 'OID': TokenType.OBJECT_IDENTIFIER, 'ON': TokenType.ON, 'ONLY': TokenType.ONLY, 'OPERATOR': TokenType.OPERATOR, 'OPTIMIZE': TokenType.COMMAND, 'OR': TokenType.OR, 'ORDER BY': TokenType.ORDER_BY, 'ORDINALITY': TokenType.ORDINALITY, 'OUT': TokenType.OUT, 'OUTER': TokenType.OUTER, 'OVER': TokenType.OVER, 'OVERLAPS': TokenType.OVERLAPS, 'OVERWRITE': TokenType.OVERWRITE, 'PARTITION': TokenType.PARTITION, 'PARTITION BY': TokenType.PARTITION_BY, 'PARTITIONED BY': TokenType.PARTITION_BY, 'PARTITIONED_BY': TokenType.PARTITION_BY, 'PERCENT': TokenType.PERCENT, 'PIVOT': TokenType.PIVOT, 'POINT': TokenType.POINT, 'PRAGMA': TokenType.PRAGMA, 'PREPARE': TokenType.COMMAND, 'PRIMARY KEY': TokenType.PRIMARY_KEY, 'PROCEDURE': TokenType.PROCEDURE, 'QUALIFY': TokenType.QUALIFY, 'RANGE': TokenType.RANGE, 'REAL': TokenType.FLOAT, 'RECURSIVE': TokenType.RECURSIVE, 'REF': TokenType.REF, 'REFERENCES': TokenType.REFERENCES, 'REFRESH': TokenType.COMMAND, 'REGCLASS': TokenType.OBJECT_IDENTIFIER, 'REGCOLLATION': TokenType.OBJECT_IDENTIFIER, 'REGCONFIG': TokenType.OBJECT_IDENTIFIER, 'REGDICTIONARY': TokenType.OBJECT_IDENTIFIER, 'REGEXP': TokenType.RLIKE, 'REGNAMESPACE': TokenType.OBJECT_IDENTIFIER, 'REGOPER': TokenType.OBJECT_IDENTIFIER, 'REGOPERATOR': TokenType.OBJECT_IDENTIFIER, 'REGPROC': TokenType.OBJECT_IDENTIFIER, 'REGPROCEDURE': TokenType.OBJECT_IDENTIFIER, 'REGROLE': TokenType.OBJECT_IDENTIFIER, 'REGTYPE': TokenType.OBJECT_IDENTIFIER, 'REINDEX': TokenType.COMMAND, 'RELEASE': TokenType.COMMAND, 'RENAME': TokenType.RENAME, 'REPLACE': TokenType.REPLACE, 'RESET': TokenType.COMMAND, 'RETURNING': TokenType.RETURNING, 'REVOKE': TokenType.REVOKE, 'RIGHT': TokenType.RIGHT, 'RLIKE': TokenType.RLIKE, 'ROLLBACK': TokenType.ROLLBACK, 'ROLLUP': TokenType.ROLLUP, 'ROW': TokenType.ROW, 'ROWS': TokenType.ROWS, 'SAVEPOINT': TokenType.COMMAND, 'SCHEMA': TokenType.SCHEMA, 'SELECT': TokenType.SELECT, 'SEMI': TokenType.SEMI, 'SEQUENCE': TokenType.SEQUENCE, 'SERIAL': TokenType.SERIAL, 'SESSION': TokenType.SESSION, 'SESSION_USER': TokenType.SESSION_USER, 'SET': TokenType.SET, 'SETTINGS': TokenType.SETTINGS, 'SHORT': TokenType.SMALLINT, 'SHOW': TokenType.SHOW, 'SIMILAR TO': TokenType.SIMILAR_TO, 'SMALLINT': TokenType.SMALLINT, 'SMALLSERIAL': TokenType.SMALLSERIAL, 'SOME': TokenType.SOME, 'SORT BY': TokenType.SORT_BY, 'SQL SECURITY': TokenType.SQL_SECURITY, 'STR': TokenType.TEXT, 'STRAIGHT_JOIN': TokenType.STRAIGHT_JOIN, 'STRING': TokenType.TEXT, 'STRUCT': TokenType.STRUCT, 'TABLE': TokenType.TABLE, 'TABLESAMPLE': TokenType.TABLE_SAMPLE, 'TEMP': TokenType.TEMPORARY, 'TEMPORARY': TokenType.TEMPORARY, 'TEXT': TokenType.TEXT, 'THEN': TokenType.THEN, 'TIME': TokenType.TIME, 'TIMESTAMP': TokenType.TIMESTAMP, 'TIMESTAMPLTZ': TokenType.TIMESTAMPLTZ, 'TIMESTAMPNTZ': TokenType.TIMESTAMPNTZ, 'TIMESTAMPTZ': TokenType.TIMESTAMPTZ, 'TIMESTAMP_LTZ': TokenType.TIMESTAMPLTZ, 'TIMESTAMP_NTZ': TokenType.TIMESTAMPNTZ, 'TIMETZ': TokenType.TIMETZ, 'TIME_NS': TokenType.TIME_NS, 'TINYBLOB': TokenType.TINYBLOB, 'TINYINT': TokenType.TINYINT, 'TINYTEXT': TokenType.TINYTEXT, 'TRIGGER': TokenType.TRIGGER, 'TRUE': TokenType.TRUE, 'TRUNCATE': TokenType.TRUNCATE, 'TSMULTIRANGE': TokenType.TSMULTIRANGE, 'TSRANGE': TokenType.TSRANGE, 'TSTZMULTIRANGE': TokenType.TSTZMULTIRANGE, 'TSTZRANGE': TokenType.TSTZRANGE, 'TYPE': TokenType.TYPE, 'UHUGEINT': TokenType.UINT128, 'UINT': TokenType.UINT, 'UINT128': TokenType.UINT128, 'UINT256': TokenType.UINT256, 'UNCACHE': TokenType.UNCACHE, 'UNION': TokenType.UNION, 'UNIQUE': TokenType.UNIQUE, 'UNKNOWN': TokenType.UNKNOWN, 'UNNEST': TokenType.UNNEST, 'UNPIVOT': TokenType.UNPIVOT, 'UPDATE': TokenType.UPDATE, 'USE': TokenType.USE, 'USER-DEFINED': TokenType.USERDEFINED, 'USING': TokenType.USING, 'UUID': TokenType.UUID, 'VACUUM': TokenType.COMMAND, 'VALUES': TokenType.VALUES, 'VARBINARY': TokenType.VARBINARY, 'VARCHAR': TokenType.VARCHAR, 'VARCHAR2': TokenType.VARCHAR, 'VARIADIC': TokenType.VARIADIC, 'VARIANT': TokenType.VARIANT, 'VECTOR': TokenType.VECTOR, 'VIEW': TokenType.VIEW, 'VOLATILE': TokenType.VOLATILE, 'WHEN': TokenType.WHEN, 'WHERE': TokenType.WHERE, 'WINDOW': TokenType.WINDOW, 'WITH': TokenType.WITH, 'XML': TokenType.XML, 'XOR': TokenType.XOR, '^@': TokenType.CARET_AT, '{%': TokenType.BLOCK_START, '{%+': TokenType.BLOCK_START, '{%-': TokenType.BLOCK_START, '{{+': TokenType.BLOCK_START, '{{-': TokenType.BLOCK_START, '|/': TokenType.PIPE_SLASH, '|>': TokenType.PIPE_GT, '||': TokenType.DPIPE, '||/': TokenType.DPIPE_SLASH, '~': TokenType.RLIKE, '~*': TokenType.IRLIKE, '~~': TokenType.LIKE, '~~*': TokenType.ILIKE, '~~~': TokenType.GLOB}
dialect
BIT_END: str | None = "'"
BIT_START: str | None = "b'"
BYTE_END: str | None = "'"
BYTE_START: str | None = "e'"
BYTE_STRINGS_SUPPORT_ESCAPED_SEQUENCES: bool = True

Whether byte string literals support escape sequences. Set by the metaclass based on the tokenizer’s BYTE_STRING_ESCAPES.

ESCAPED_SEQUENCES: dict[str, str] = {'\x00': '\\x00', '\x01': '\\x01', '\x02': '\\x02', '\x03': '\\x03', '\x04': '\\x04', '\x05': '\\x05', '\x06': '\\x06', '\x07': '\\x07', '\x08': '\\b', '\t': '\\t', '\n': '\\n', '\x0b': '\\v', '\x0c': '\\f', '\r': '\\r', '\x0e': '\\x0e', '\x0f': '\\x0f', '\x10': '\\x10', '\x11': '\\x11', '\x12': '\\x12', '\x13': '\\x13', '\x14': '\\x14', '\x15': '\\x15', '\x16': '\\x16', '\x17': '\\x17', '\x18': '\\x18', '\x19': '\\x19', '\x1a': '\\x1a', '\x1b': '\\x1b', '\x1c': '\\x1c', '\x1d': '\\x1d', '\x1e': '\\x1e', '\x1f': '\\x1f', '\\': '\\\\', '\x7f': '\\x7f'}
FORMAT_TRIE: dict = {'D': {'D': {'D': {0: True}, 0: True}, 0: True}, 'F': {'M': {'D': {'D': {'D': {0: True}, 0: True}}, 'H': {'H': {'1': {'2': {0: True}}, '2': {'4': {0: True}}}}, 'M': {'I': {0: True}, 'M': {0: True}}, 'S': {'S': {0: True}}}}, 'H': {'H': {'1': {'2': {0: True}}, '2': {'4': {0: True}}}}, 'I': {'W': {0: True}, 'Y': {'Y': {'Y': {0: True}}}}, 'M': {'I': {0: True}, 'M': {0: True}}, 'O': {'F': {0: True}}, 'S': {'S': {0: True}}, 'T': {'M': {'D': {'a': {'y': {0: True}}, 'y': {0: True}}, 'M': {'o': {'n': {'t': {'h': {0: True}}, 0: True}}}}, 'Z': {0: True}}, 'U': {'S': {0: True}}, 'W': {'W': {0: True}}, 'Y': {'Y': {'Y': {'Y': {0: True}, 0: True}, 0: True}}, 'd': {'a': {'y': {0: True}}, 'd': {'d': {0: True}, 0: True}, 'y': {0: True}, 0: True}, 'i': {'w': {0: True}, 'y': {'y': {'y': {0: True}}}}, 'm': {'i': {0: True}, 'm': {0: True}}, 's': {'s': {0: True}}, 'w': {'w': {0: True}}, 'y': {'y': {'y': {'y': {0: True}, 0: True}, 0: True}}}
HEX_END: str | None = "'"
HEX_START: str | None = "x'"
IDENTIFIER_END = '"'
IDENTIFIER_ESCAPED_SEQUENCES: dict[str, str] = {}

Mapping of an identifier escape char (`) to its escaped version (\`). Set by the metaclass based on the tokenizer’s IDENTIFIER_ESCAPES.

IDENTIFIER_START = '"'
INITCAP_SUPPORTS_CUSTOM_DELIMITERS = False
INVERSE_CREATABLE_KIND_MAPPING: dict[str, str] = {}
INVERSE_FORMAT_MAPPING: dict[str, str] = {'%Hstrict': '%H', '%Istrict': '%I', '%Mstrict': '%M', '%Sstrict': '%S', '%dstrict': '%d', '%mstrict': '%m'}
INVERSE_FORMAT_TRIE: dict = {'%': {'H': {'s': {'t': {'r': {'i': {'c': {'t': {0: True}}}}}}}, 'I': {'s': {'t': {'r': {'i': {'c': {'t': {0: True}}}}}}}, 'M': {'s': {'t': {'r': {'i': {'c': {'t': {0: True}}}}}}}, 'S': {'s': {'t': {'r': {'i': {'c': {'t': {0: True}}}}}}}, 'd': {'s': {'t': {'r': {'i': {'c': {'t': {0: True}}}}}}}, 'm': {'s': {'t': {'r': {'i': {'c': {'t': {0: True}}}}}}}}}
INVERSE_TIME_MAPPING: dict[str, str] = {'%-H': 'FMHH24', '%-I': 'FMHH12', '%-M': 'FMMI', '%-S': 'FMSS', '%-d': 'FMDD', '%-j': 'FMDDD', '%-m': 'FMMM', '%A': 'TMDay', '%Aenlower': 'day', '%B': 'TMMonth', '%G': 'IYYY', '%H': 'HH24', '%Hstrict': 'HH24', '%I': 'HH12', '%Istrict': 'HH12', '%M': 'MI', '%Mstrict': 'MI', '%S': 'SS', '%Sstrict': 'SS', '%U': 'WW', '%V': 'IW', '%Y': 'YYYY', '%Ythree': 'YYY', '%Z': 'TZ', '%a': 'TMDy', '%aenlower': 'dy', '%b': 'TMMon', '%d': 'DD', '%dstrict': 'DD', '%f': 'US', '%j': 'DDD', '%m': 'MM', '%mstrict': 'MM', '%u': 'D', '%y': 'YY', '%z': 'OF'}
INVERSE_TIME_TRIE: dict = {'%': {'-': {'H': {0: True}, 'I': {0: True}, 'M': {0: True}, 'S': {0: True}, 'd': {0: True}, 'j': {0: True}, 'm': {0: True}}, 'A': {'e': {'n': {'l': {'o': {'w': {'e': {'r': {0: True}}}}}}}, 0: True}, 'B': {0: True}, 'G': {0: True}, 'H': {'s': {'t': {'r': {'i': {'c': {'t': {0: True}}}}}}, 0: True}, 'I': {'s': {'t': {'r': {'i': {'c': {'t': {0: True}}}}}}, 0: True}, 'M': {'s': {'t': {'r': {'i': {'c': {'t': {0: True}}}}}}, 0: True}, 'S': {'s': {'t': {'r': {'i': {'c': {'t': {0: True}}}}}}, 0: True}, 'U': {0: True}, 'V': {0: True}, 'Y': {'t': {'h': {'r': {'e': {'e': {0: True}}}}}, 0: True}, 'Z': {0: True}, 'a': {'e': {'n': {'l': {'o': {'w': {'e': {'r': {0: True}}}}}}}, 0: True}, 'b': {0: True}, 'd': {'s': {'t': {'r': {'i': {'c': {'t': {0: True}}}}}}, 0: True}, 'f': {0: True}, 'j': {0: True}, 'm': {'s': {'t': {'r': {'i': {'c': {'t': {0: True}}}}}}, 0: True}, 'u': {0: True}, 'y': {0: True}, 'z': {0: True}}}
QUOTE_END = "'"
QUOTE_START = "'"
STRINGS_SUPPORT_ESCAPED_SEQUENCES: bool = False

Whether string literals support escape sequences (e.g. n). Set by the metaclass based on the tokenizer’s STRING_ESCAPES.

SUPPORTS_COLUMN_JOIN_MARKS = False

Whether the old-style outer join (+) syntax is supported.

TIME_TRIE: dict = {'D': {'D': {'D': {0: True}, 0: True}, 0: True}, 'F': {'M': {'D': {'D': {'D': {0: True}, 0: True}}, 'H': {'H': {'1': {'2': {0: True}}, '2': {'4': {0: True}}}}, 'M': {'I': {0: True}, 'M': {0: True}}, 'S': {'S': {0: True}}}}, 'H': {'H': {'1': {'2': {0: True}}, '2': {'4': {0: True}}}}, 'I': {'W': {0: True}, 'Y': {'Y': {'Y': {0: True}}}}, 'M': {'I': {0: True}, 'M': {0: True}}, 'O': {'F': {0: True}}, 'S': {'S': {0: True}}, 'T': {'M': {'D': {'a': {'y': {0: True}}, 'y': {0: True}}, 'M': {'o': {'n': {'t': {'h': {0: True}}, 0: True}}}}, 'Z': {0: True}}, 'U': {'S': {0: True}}, 'W': {'W': {0: True}}, 'Y': {'Y': {'Y': {'Y': {0: True}, 0: True}, 0: True}}, 'd': {'a': {'y': {0: True}}, 'd': {'d': {0: True}, 0: True}, 'y': {0: True}, 0: True}, 'i': {'w': {0: True}, 'y': {'y': {'y': {0: True}}}}, 'm': {'i': {0: True}, 'm': {0: True}}, 's': {'s': {0: True}}, 'w': {'w': {0: True}}, 'y': {'y': {'y': {'y': {0: True}, 0: True}, 0: True}}}
UNESCAPED_SEQUENCES: dict[str, str] = {'\\\\': '\\', '\\a': 'a', '\\b': '\x08', '\\f': '\x0c', '\\n': '\n', '\\r': '\r', '\\t': '\t', '\\v': '\x0b'}

Mapping of an escaped sequence (n) to its unescaped version (` `).

UNICODE_END: str | None = "'"
UNICODE_START: str | None = "U&'"
VALID_INTERVAL_UNITS: set[str] = {'C', 'CENT', 'CENTS', 'CENTURIES', 'CENTURY', 'D', 'DAY', 'DAY OF WEEK', 'DAY OF YEAR', 'DAYOFMONTH', 'DAYOFWEEK', 'DAYOFWEEKISO', 'DAYOFWEEK_ISO', 'DAYOFYEAR', 'DAYS', 'DD', 'DEC', 'DECADE', 'DECADES', 'DECS', 'DOW', 'DOW_ISO', 'DOY', 'DW', 'DW_ISO', 'DY', 'EPOCH', 'EPOCH_MICROSECOND', 'EPOCH_MICROSECONDS', 'EPOCH_MILLISECOND', 'EPOCH_MILLISECONDS', 'EPOCH_NANOSECOND', 'EPOCH_NANOSECONDS', 'EPOCH_SECOND', 'EPOCH_SECONDS', 'H', 'HH', 'HOUR', 'HOURS', 'HR', 'HRS', 'M', 'MI', 'MICROSEC', 'MICROSECOND', 'MICROSECONDS', 'MICROSECS', 'MIL', 'MILLENIA', 'MILLENNIUM', 'MILLISEC', 'MILLISECON', 'MILLISECOND', 'MILLISECONDS', 'MILLISECS', 'MILS', 'MIN', 'MINS', 'MINUTE', 'MINUTES', 'MM', 'MON', 'MONS', 'MONTH', 'MONTHS', 'MS', 'MSEC', 'MSECOND', 'MSECONDS', 'MSECS', 'NANOSEC', 'NANOSECOND', 'NANOSECS', 'NS', 'NSEC', 'NSECOND', 'NSECONDS', 'Q', 'QTR', 'QTRS', 'QUARTER', 'QUARTERS', 'S', 'SEC', 'SECOND', 'SECONDS', 'SECS', 'TIMEZONE_HOUR', 'TIMEZONE_MINUTE', 'TZH', 'TZM', 'US', 'USEC', 'USECOND', 'USECONDS', 'USECS', 'W', 'WEEK', 'WEEKDAY', 'WEEKDAY_ISO', 'WEEKISO', 'WEEKOFYEAR', 'WEEKOFYEARISO', 'WEEKOFYEAR_ISO', 'WEEK_ISO', 'WK', 'WOY', 'WY', 'Y', 'YEAR', 'YEARS', 'YR', 'YRS', 'YY', 'YYY', 'YYYY'}
generator_class

alias of PostgresGenerator

jsonpath_tokenizer_class

alias of JSONPathTokenizer

parser_class

alias of PostgresParser

tokenizer_class

alias of Tokenizer