sqlglot.dialects.postgres

 12class Postgres(Dialect):
 13    EXPRESSION_METADATA = EXPRESSION_METADATA.copy()
 14    INDEX_OFFSET = 1
 15    # Normalizing `x IS NOT NULL` to `NOT x IS NULL` is unsafe due to row values,
 16    # e.g. `ROW(1, NULL) IS NOT NULL` is false whereas `NOT ROW(1, NULL) IS NULL` is true
 17    NORMALIZE_NOT_NULL = False
 18    TYPED_DIVISION = True
 19    CONCAT_COALESCE = True
 20    CONCAT_WS_COALESCE = True
 21    NULL_ORDERING = "nulls_are_large"
 22    SUPPORTS_LIMIT_ALL = True
 23    TIME_FORMAT = "'YYYY-MM-DD HH24:MI:SS'"
 24    TABLESAMPLE_SIZE_IS_PERCENT = True
 25    TABLES_REFERENCEABLE_AS_COLUMNS = True
 26
 27    DEFAULT_FUNCTIONS_COLUMN_NAMES = {
 28        exp.ExplodingGenerateSeries: "generate_series",
 29    }
 30
 31    TIME_MAPPING = {
 32        "d": "%u",  # 1-based day of week
 33        "D": "%u",  # 1-based day of week
 34        "dd": "%d",  # day of month
 35        "DD": "%d",  # day of month
 36        "ddd": "%j",  # zero padded day of year
 37        "DDD": "%j",  # zero padded day of year
 38        "FMDD": "%-d",  # - is no leading zero for Python; same for FM in postgres
 39        "FMDDD": "%-j",  # day of year
 40        "FMHH12": "%-I",  # 9
 41        "FMHH24": "%-H",  # 9
 42        "FMMI": "%-M",  # Minute
 43        "FMMM": "%-m",  # 1
 44        "FMSS": "%-S",  # Second
 45        "HH12": "%I",  # 09
 46        "HH24": "%H",  # 09
 47        "mi": "%M",  # zero padded minute
 48        "MI": "%M",  # zero padded minute
 49        "mm": "%m",  # 01
 50        "MM": "%m",  # 01
 51        "OF": "%z",  # utc offset
 52        "ss": "%S",  # zero padded second
 53        "SS": "%S",  # zero padded second
 54        "TMDay": "%A",  # TM is locale dependent
 55        "TMDy": "%a",
 56        "TMMon": "%b",  # Sep
 57        "TMMonth": "%B",  # September
 58        "day": "%Aenlower",  # tuesday
 59        "dy": "%aenlower",  # tue
 60        "TZ": "%Z",  # uppercase timezone name
 61        "US": "%f",  # zero padded microsecond
 62        "ww": "%U",  # 1-based week of year
 63        "WW": "%U",  # 1-based week of year
 64        "yy": "%y",  # 15
 65        "YY": "%y",  # 15
 66        "yyy": "%Ythree",  # 015
 67        "YYY": "%Ythree",  # 015
 68        "yyyy": "%Y",  # 2015
 69        "YYYY": "%Y",  # 2015
 70    }
 71
 72    class Tokenizer(tokens.Tokenizer):
 73        BIT_STRINGS = [("b'", "'"), ("B'", "'")]
 74        HEX_STRINGS = [("x'", "'"), ("X'", "'")]
 75        BYTE_STRINGS = [("e'", "'"), ("E'", "'")]
 76        UNICODE_STRINGS = [("U&'", "'"), ("u&'", "'")]
 77        BYTE_STRING_ESCAPES = ["'", "\\"]
 78        HEREDOC_STRINGS = ["$"]
 79
 80        HEREDOC_TAG_IS_IDENTIFIER = True
 81        HEREDOC_STRING_ALTERNATIVE = TokenType.PARAMETER
 82
 83        KEYWORDS = {
 84            **tokens.Tokenizer.KEYWORDS,
 85            "~": TokenType.RLIKE,
 86            "@@": TokenType.DAT,
 87            "@?": TokenType.AT_QMARK,
 88            "@>": TokenType.AT_GT,
 89            "<@": TokenType.LT_AT,
 90            "?&": TokenType.QMARK_AMP,
 91            "?|": TokenType.QMARK_PIPE,
 92            "#-": TokenType.HASH_DASH,
 93            "|/": TokenType.PIPE_SLASH,
 94            "||/": TokenType.DPIPE_SLASH,
 95            "BEGIN": TokenType.BEGIN,
 96            "BIGSERIAL": TokenType.BIGSERIAL,
 97            "CSTRING": TokenType.PSEUDO_TYPE,
 98            "DECLARE": TokenType.COMMAND,
 99            "DO": TokenType.COMMAND,
100            "EXEC": TokenType.COMMAND,
101            "HSTORE": TokenType.HSTORE,
102            "INT8": TokenType.BIGINT,
103            "MONEY": TokenType.MONEY,
104            "NAME": TokenType.NAME,
105            "OID": TokenType.OBJECT_IDENTIFIER,
106            "ONLY": TokenType.ONLY,
107            "POINT": TokenType.POINT,
108            "REFRESH": TokenType.COMMAND,
109            "REINDEX": TokenType.COMMAND,
110            "RESET": TokenType.COMMAND,
111            "SERIAL": TokenType.SERIAL,
112            "SMALLSERIAL": TokenType.SMALLSERIAL,
113            "TEMP": TokenType.TEMPORARY,
114            "TYPE": TokenType.TYPE,
115            "REGCLASS": TokenType.OBJECT_IDENTIFIER,
116            "REGCOLLATION": TokenType.OBJECT_IDENTIFIER,
117            "REGCONFIG": TokenType.OBJECT_IDENTIFIER,
118            "REGDICTIONARY": TokenType.OBJECT_IDENTIFIER,
119            "REGNAMESPACE": TokenType.OBJECT_IDENTIFIER,
120            "REGOPER": TokenType.OBJECT_IDENTIFIER,
121            "REGOPERATOR": TokenType.OBJECT_IDENTIFIER,
122            "REGPROC": TokenType.OBJECT_IDENTIFIER,
123            "REGPROCEDURE": TokenType.OBJECT_IDENTIFIER,
124            "REGROLE": TokenType.OBJECT_IDENTIFIER,
125            "REGTYPE": TokenType.OBJECT_IDENTIFIER,
126            "FLOAT": TokenType.DOUBLE,
127            "XML": TokenType.XML,
128            "VARIADIC": TokenType.VARIADIC,
129            "INOUT": TokenType.INOUT,
130        }
131        KEYWORDS.pop("/*+")
132        KEYWORDS.pop("DIV")
133
134        SINGLE_TOKENS = {
135            **tokens.Tokenizer.SINGLE_TOKENS,
136            "$": TokenType.HEREDOC_STRING,
137        }
138
139        VAR_SINGLE_TOKENS = {"$"}
140
141    Parser = PostgresParser
142
143    Generator = PostgresGenerator

 72    class Tokenizer(tokens.Tokenizer):
 73        BIT_STRINGS = [("b'", "'"), ("B'", "'")]
 74        HEX_STRINGS = [("x'", "'"), ("X'", "'")]
 75        BYTE_STRINGS = [("e'", "'"), ("E'", "'")]
 76        UNICODE_STRINGS = [("U&'", "'"), ("u&'", "'")]
 77        BYTE_STRING_ESCAPES = ["'", "\\"]
 78        HEREDOC_STRINGS = ["$"]
 79
 80        HEREDOC_TAG_IS_IDENTIFIER = True
 81        HEREDOC_STRING_ALTERNATIVE = TokenType.PARAMETER
 82
 83        KEYWORDS = {
 84            **tokens.Tokenizer.KEYWORDS,
 85            "~": TokenType.RLIKE,
 86            "@@": TokenType.DAT,
 87            "@?": TokenType.AT_QMARK,
 88            "@>": TokenType.AT_GT,
 89            "<@": TokenType.LT_AT,
 90            "?&": TokenType.QMARK_AMP,
 91            "?|": TokenType.QMARK_PIPE,
 92            "#-": TokenType.HASH_DASH,
 93            "|/": TokenType.PIPE_SLASH,
 94            "||/": TokenType.DPIPE_SLASH,
 95            "BEGIN": TokenType.BEGIN,
 96            "BIGSERIAL": TokenType.BIGSERIAL,
 97            "CSTRING": TokenType.PSEUDO_TYPE,
 98            "DECLARE": TokenType.COMMAND,
 99            "DO": TokenType.COMMAND,
100            "EXEC": TokenType.COMMAND,
101            "HSTORE": TokenType.HSTORE,
102            "INT8": TokenType.BIGINT,
103            "MONEY": TokenType.MONEY,
104            "NAME": TokenType.NAME,
105            "OID": TokenType.OBJECT_IDENTIFIER,
106            "ONLY": TokenType.ONLY,
107            "POINT": TokenType.POINT,
108            "REFRESH": TokenType.COMMAND,
109            "REINDEX": TokenType.COMMAND,
110            "RESET": TokenType.COMMAND,
111            "SERIAL": TokenType.SERIAL,
112            "SMALLSERIAL": TokenType.SMALLSERIAL,
113            "TEMP": TokenType.TEMPORARY,
114            "TYPE": TokenType.TYPE,
115            "REGCLASS": TokenType.OBJECT_IDENTIFIER,
116            "REGCOLLATION": TokenType.OBJECT_IDENTIFIER,
117            "REGCONFIG": TokenType.OBJECT_IDENTIFIER,
118            "REGDICTIONARY": TokenType.OBJECT_IDENTIFIER,
119            "REGNAMESPACE": TokenType.OBJECT_IDENTIFIER,
120            "REGOPER": TokenType.OBJECT_IDENTIFIER,
121            "REGOPERATOR": TokenType.OBJECT_IDENTIFIER,
122            "REGPROC": TokenType.OBJECT_IDENTIFIER,
123            "REGPROCEDURE": TokenType.OBJECT_IDENTIFIER,
124            "REGROLE": TokenType.OBJECT_IDENTIFIER,
125            "REGTYPE": TokenType.OBJECT_IDENTIFIER,
126            "FLOAT": TokenType.DOUBLE,
127            "XML": TokenType.XML,
128            "VARIADIC": TokenType.VARIADIC,
129            "INOUT": TokenType.INOUT,
130        }
131        KEYWORDS.pop("/*+")
132        KEYWORDS.pop("DIV")
133
134        SINGLE_TOKENS = {
135            **tokens.Tokenizer.SINGLE_TOKENS,
136            "$": TokenType.HEREDOC_STRING,
137        }
138
139        VAR_SINGLE_TOKENS = {"$"}