Edit on GitHub

sqlglot.dialects.doris

View Source

 1from __future__ import annotations
 2
 3from sqlglot import exp
 4from sqlglot.dialects.dialect import AliasPrecedence
 5from sqlglot.dialects.mysql import MySQL
 6from sqlglot.generators.doris import DorisGenerator
 7from sqlglot.parsers.doris import DorisParser
 8
 9
10class Doris(MySQL):
11    COLUMN_ALIAS_PRECEDENCE = {
12        **MySQL.COLUMN_ALIAS_PRECEDENCE,
13        exp.Having: AliasPrecedence.ALIAS,
14        exp.Qualify: AliasPrecedence.ALIAS,
15    }
16    DATE_FORMAT = "'yyyy-MM-dd'"
17    DATEINT_FORMAT = "'yyyyMMdd'"
18    TIME_FORMAT = "'yyyy-MM-dd HH:mm:ss'"
19
20    class Tokenizer(MySQL.Tokenizer):
21        DASH_COMMENT_REQUIRES_BOUNDARY = False
22        COMMENTS_TERMINATE_AT_NEWLINE_ONLY = False
23
24    Parser = DorisParser
25
26    Generator = DorisGenerator

class Doris(sqlglot.dialects.mysql.MySQL): View Source

11class Doris(MySQL):
12    COLUMN_ALIAS_PRECEDENCE = {
13        **MySQL.COLUMN_ALIAS_PRECEDENCE,
14        exp.Having: AliasPrecedence.ALIAS,
15        exp.Qualify: AliasPrecedence.ALIAS,
16    }
17    DATE_FORMAT = "'yyyy-MM-dd'"
18    DATEINT_FORMAT = "'yyyyMMdd'"
19    TIME_FORMAT = "'yyyy-MM-dd HH:mm:ss'"
20
21    class Tokenizer(MySQL.Tokenizer):
22        DASH_COMMENT_REQUIRES_BOUNDARY = False
23        COMMENTS_TERMINATE_AT_NEWLINE_ONLY = False
24
25    Parser = DorisParser
26
27    Generator = DorisGenerator

COLUMN_ALIAS_PRECEDENCE: dict[type[sqlglot.expressions.core.Expr], sqlglot.dialects.dialect.AliasPrecedence] = {<class 'sqlglot.expressions.query.Having'>: <AliasPrecedence.ALIAS: 'ALIAS'>, <class 'sqlglot.expressions.query.Qualify'>: <AliasPrecedence.ALIAS: 'ALIAS'>}

Alias lookup policies for HAVING, QUALIFY, ORDER BY and DISTINCT ON.

Unspecified clauses prefer aliases. GROUPED_SOURCE prefers grouped input columns and input columns inside aggregates, then aliases. MERGED_SOURCE prefers merged USING keys over other input columns. Standalone ORDER BY / DISTINCT ON names prefer aliases regardless of their clause's expression precedence.

DATE_FORMAT = "'yyyy-MM-dd'"

DATEINT_FORMAT = "'yyyyMMdd'"

TIME_FORMAT = "'yyyy-MM-dd HH:mm:ss'"

Parser = <class 'sqlglot.parsers.doris.DorisParser'>

Generator = <class 'sqlglot.generators.doris.DorisGenerator'>

VALID_INTERVAL_UNITS: set[str] = {'MILLENNIUM', 'DAY', 'QTRS', 'WEEK_ISO', 'YY', 'WY', 'MILLISECONDS', 'MONTHS', 'CENTS', 'DECADES', 'HOUR_MINUTE', 'EPOCH_NANOSECOND', 'NSECOND', 'EPOCH_MILLISECOND', 'USECONDS', 'WK', 'YEARS', 'WEEKDAY_ISO', 'NS', 'MICROSECONDS', 'DAYOFMONTH', 'S', 'Y', 'USEC', 'Q', 'NSECONDS', 'TZM', 'MILS', 'QUARTERS', 'TIMEZONE_HOUR', 'TZH', 'DD', 'DEC', 'WEEK', 'SECOND_MICROSECOND', 'TIMEZONE_MINUTE', 'HH', 'EPOCH_NANOSECONDS', 'MON', 'HOUR_MICROSECOND', 'DW_ISO', 'MSECOND', 'MSECS', 'NANOSEC', 'NANOSECOND', 'USECOND', 'DOY', 'QUARTER', 'MM', 'DECS', 'EPOCH_MICROSECOND', 'MI', 'HRS', 'DAY_SECOND', 'DAYOFYEAR', 'MINUTE_MICROSECOND', 'YR', 'EPOCH', 'MSECONDS', 'DOW', 'EPOCH_SECOND', 'DAY_MINUTE', 'MINUTE', 'MICROSECS', 'DAY_HOUR', 'DAY OF YEAR', 'MILLISEC', 'YEAR', 'WEEKDAY', 'CENTURY', 'DAYOFWEEK', 'HOURS', 'DY', 'WEEKISO', 'MILLISECON', 'NANOSECS', 'DAY_MICROSECOND', 'YEAR_MONTH', 'HOUR', 'M', 'DAY OF WEEK', 'SECS', 'DAYOFWEEK_ISO', 'QTR', 'US', 'YYYY', 'MILLISECS', 'CENTURIES', 'HR', 'DW', 'HOUR_SECOND', 'MONTH', 'MILLISECOND', 'WEEKOFYEAR_ISO', 'C', 'H', 'D', 'WOY', 'DAYOFWEEKISO', 'SECONDS', 'MINUTES', 'MICROSEC', 'MONS', 'W', 'MS', 'EPOCH_MICROSECONDS', 'MILLENIA', 'SEC', 'MINUTE_SECOND', 'MICROSECOND', 'DECADE', 'SECOND', 'EPOCH_SECONDS', 'WEEKOFYEARISO', 'DAYS', 'WEEKOFYEAR', 'MIN', 'NSEC', 'MIL', 'YYY', 'MSEC', 'CENT', 'USECS', 'MINS', 'EPOCH_MILLISECONDS', 'YRS', 'DOW_ISO'}

UNESCAPED_SEQUENCES: dict[str, str] = {'\\a': 'a', '\\b': '\x08', '\\f': 'f', '\\n': '\n', '\\r': '\r', '\\t': '\t', '\\v': 'v', '\\\\': '\\', '\\0': '\x00', '\\Z': '\x1a', '\\%': '\\%', '\\_': '\\_'}

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

SUPPORTS_COLUMN_JOIN_MARKS = False

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

STRINGS_SUPPORT_ESCAPED_SEQUENCES: bool = True

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

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.

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.

INITCAP_SUPPORTS_CUSTOM_DELIMITERS = False

tokenizer_class = <class 'Doris.Tokenizer'>

jsonpath_tokenizer_class = <class 'sqlglot.dialects.dialect.JSONPathTokenizer'>

parser_class = <class 'sqlglot.parsers.doris.DorisParser'>

generator_class = <class 'sqlglot.generators.doris.DorisGenerator'>

TIME_TRIE: dict = {'%': {'M': {0: True}, 'c': {0: True}, 'e': {0: True}, 'h': {0: True}, 'i': {0: True}, 's': {0: True}, 'u': {0: True}, 'k': {0: True}, 'l': {0: True}, 'r': {0: True}, 'T': {0: True}, 'W': {0: True}, 'x': {0: True}}}

FORMAT_TRIE: dict = {'%': {'M': {0: True}, 'c': {0: True}, 'e': {0: True}, 'h': {0: True}, 'i': {0: True}, 's': {0: True}, 'u': {0: True}, 'k': {0: True}, 'l': {0: True}, 'r': {0: True}, 'T': {0: True}, 'W': {0: True}, 'x': {0: True}}}

INVERSE_TIME_MAPPING: dict[str, str] = {'%B': '%M', '%-m': '%c', '%-d': '%e', '%I': '%h', '%M': '%i', '%S': '%s', '%W': '%u', '%-H': '%k', '%-I': '%l', '%I:%M:%S %p': '%r', '%H:%M:%S': '%T', '%A': '%W', '%G': '%x', '%mstrict': '%m', '%dstrict': '%d', '%Hstrict': '%H', '%Istrict': '%h', '%Mstrict': '%i', '%Sstrict': '%s'}

INVERSE_TIME_TRIE: dict = {'%': {'B': {0: True}, '-': {'m': {0: True}, 'd': {0: True}, 'H': {0: True}, 'I': {0: True}}, 'I': {0: True, ':': {'%': {'M': {':': {'%': {'S': {' ': {'%': {'p': {0: True}}}}}}}}}, 's': {'t': {'r': {'i': {'c': {'t': {0: True}}}}}}}, 'M': {0: True, 's': {'t': {'r': {'i': {'c': {'t': {0: True}}}}}}}, 'S': {0: True, 's': {'t': {'r': {'i': {'c': {'t': {0: True}}}}}}}, 'W': {0: True}, 'H': {':': {'%': {'M': {':': {'%': {'S': {0: True}}}}}}, 's': {'t': {'r': {'i': {'c': {'t': {0: True}}}}}}}, 'A': {0: True}, 'G': {0: True}, 'm': {'s': {'t': {'r': {'i': {'c': {'t': {0: True}}}}}}}, 'd': {'s': {'t': {'r': {'i': {'c': {'t': {0: True}}}}}}}}}

INVERSE_FORMAT_MAPPING: dict[str, str] = {'%mstrict': '%m', '%dstrict': '%d', '%Hstrict': '%H', '%Istrict': '%I', '%Mstrict': '%M', '%Sstrict': '%S'}

INVERSE_FORMAT_TRIE: dict = {'%': {'m': {'s': {'t': {'r': {'i': {'c': {'t': {0: True}}}}}}}, 'd': {'s': {'t': {'r': {'i': {'c': {'t': {0: True}}}}}}}, '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}}}}}}}}}

INVERSE_CREATABLE_KIND_MAPPING: dict[str, str] = {}

ESCAPED_SEQUENCES: dict[str, str] = {'\x08': '\\b', '\n': '\\n', '\r': '\\r', '\t': '\\t', '\\': '\\\\', '\x00': '\\0', '\x1a': '\\Z'}

QUOTE_START = "'"

QUOTE_END = "'"

IDENTIFIER_START = '`'

IDENTIFIER_END = '`'

BIT_START: str | None = "b'"

BIT_END: str | None = "'"

HEX_START: str | None = "x'"

HEX_END: str | None = "'"

BYTE_START: str | None = None

BYTE_END: str | None = None

UNICODE_START: str | None = None

UNICODE_END: str | None = None

Inherited Members

sqlglot.dialects.mysql.MySQL: PROMOTE_TO_INFERRED_DATETIME_TYPE; USING_COLUMN_ORDER; IDENTIFIERS_CAN_START_WITH_DIGIT; NORMALIZATION_STRATEGY; DPIPE_IS_STRING_CONCAT; CONCAT_WS_COALESCE; SUPPORTS_USER_DEFINED_TYPES; SAFE_DIVISION; SAFE_TO_ELIMINATE_DOUBLE_NEGATION; LEAST_GREATEST_IGNORES_NULLS; EXPRESSION_METADATA; TIME_MAPPING

class Doris.Tokenizer(sqlglot.dialects.mysql.MySQL.Tokenizer): View Source

21    class Tokenizer(MySQL.Tokenizer):
22        DASH_COMMENT_REQUIRES_BOUNDARY = False
23        COMMENTS_TERMINATE_AT_NEWLINE_ONLY = False

DASH_COMMENT_REQUIRES_BOUNDARY = False

COMMENTS_TERMINATE_AT_NEWLINE_ONLY = False

Inherited Members

sqlglot.tokens.Tokenizer: Tokenizer; SINGLE_TOKENS; BYTE_STRINGS; NATIONAL_RAW_STRINGS; RAW_STRINGS; HEREDOC_STRINGS; UNICODE_STRINGS; VAR_SINGLE_TOKENS; IDENTIFIER_ESCAPES; HEREDOC_TAG_IS_IDENTIFIER; HEREDOC_STRING_ALTERNATIVE; STRING_ESCAPES_ALLOWED_IN_RAW_STRINGS; NUMERIC_ESCAPES; NUMERIC_ESCAPES_ARE_BYTES; LONE_SURROGATE_REPLACEMENT; HINT_START; TOKENS_PRECEDING_HINT; COMMAND_PREFIX_TOKENS; NUMERIC_LITERALS; NUMBERS_CAN_HAVE_DECIMALS; dialect; tokenize; sql; size; tokens
sqlglot.dialects.mysql.MySQL.Tokenizer: QUOTES; COMMENTS; IDENTIFIERS; STRING_ESCAPES; BIT_STRINGS; HEX_STRINGS; DROP_UNKNOWN_ESCAPES; NESTED_COMMENTS; KEYWORDS; COMMANDS; BYTE_STRING_ESCAPES