sqlglot.dialects.hive

 19class Hive(Dialect):
 20    ALIAS_POST_TABLESAMPLE = True
 21    IDENTIFIERS_CAN_START_WITH_DIGIT = True
 22    SUPPORTS_USER_DEFINED_TYPES = False
 23    SAFE_DIVISION = True
 24    CONCAT_WS_COALESCE = True
 25    ARRAY_AGG_INCLUDES_NULLS = None
 26    REGEXP_EXTRACT_DEFAULT_GROUP = 1
 27    ALTER_TABLE_SUPPORTS_CASCADE = True
 28
 29    # https://spark.apache.org/docs/latest/sql-ref-identifier.html#description
 30    NORMALIZATION_STRATEGY = NormalizationStrategy.CASE_INSENSITIVE
 31
 32    EXPRESSION_METADATA = EXPRESSION_METADATA.copy()
 33
 34    # https://cwiki.apache.org/confluence/pages/viewpage.action?pageId=27362046#LanguageManualUDF-StringFunctions
 35    # https://github.com/apache/hive/blob/master/ql/src/java/org/apache/hadoop/hive/ql/exec/Utilities.java#L266-L269
 36    INITCAP_DEFAULT_DELIMITER_CHARS = " \t\n\r\f\u000b\u001c\u001d\u001e\u001f"
 37
 38    # Support only the non-ANSI mode (default for Hive, Spark2, Spark)
 39    COERCES_TO = defaultdict(set, deepcopy(TypeAnnotator.COERCES_TO))
 40    for target_type in {
 41        *exp.DataType.NUMERIC_TYPES,
 42        *exp.DataType.TEMPORAL_TYPES,
 43        exp.DType.INTERVAL,
 44    }:
 45        COERCES_TO[target_type] |= exp.DataType.TEXT_TYPES
 46
 47    TIME_MAPPING = {
 48        "y": "%Y",
 49        "Y": "%Y",
 50        "YYYY": "%Y",
 51        "yyyy": "%Y",
 52        "YY": "%y",
 53        "yy": "%y",
 54        "MMMM": "%B",
 55        "MMM": "%b",
 56        # Hive 4.0+ parses MM/dd/HH/hh/mm/ss strictly (java.time.DateTimeFormatter, see
 57        # HIVE-25458/HIVE-25576)
 58        "MM": "%mstrict",
 59        "M": "%-m",
 60        "dd": "%dstrict",
 61        "d": "%-d",
 62        "HH": "%Hstrict",
 63        "H": "%-H",
 64        "hh": "%Istrict",
 65        "h": "%-I",
 66        "mm": "%Mstrict",
 67        "m": "%-M",
 68        "ss": "%Sstrict",
 69        "s": "%-S",
 70        "SSSSSS": "%f",
 71        "a": "%p",
 72        "DD": "%j",
 73        "D": "%-j",
 74        "E": "%a",
 75        "EE": "%a",
 76        "EEE": "%a",
 77        "EEEE": "%A",
 78        "z": "%Z",
 79        "Z": "%z",
 80    }
 81
 82    DATE_FORMAT = "'yyyy-MM-dd'"
 83    DATEINT_FORMAT = "'yyyyMMdd'"
 84    TIME_FORMAT = "'yyyy-MM-dd HH:mm:ss'"
 85
 86    class JSONPathTokenizer(jsonpath.JSONPathTokenizer):
 87        VAR_TOKENS = {
 88            *jsonpath.JSONPathTokenizer.VAR_TOKENS,
 89            TokenType.DASH,
 90        }
 91
 92    UNESCAPED_SEQUENCES = {
 93        "\\0": "\0",
 94        "\\Z": "\x1a",
 95        "\\%": "\\%",
 96        "\\_": "\\_",
 97        "\\a": "a",
 98        "\\f": "f",
 99        "\\v": "v",
100    }
101
102    class Tokenizer(tokens.Tokenizer):
103        NUMERIC_ESCAPES = {"u": (16, 4, 4, 0xFFFF), "0": (8, 3, 3, 0x7F)}
104        DROP_UNKNOWN_ESCAPES = True
105        LONE_SURROGATE_REPLACEMENT = "?"
106        QUOTES = ["'", '"']
107        IDENTIFIERS = ["`"]
108        STRING_ESCAPES = ["\\"]
109
110        SINGLE_TOKENS = {
111            **tokens.Tokenizer.SINGLE_TOKENS,
112            "$": TokenType.PARAMETER,
113        }
114
115        KEYWORDS = {
116            **tokens.Tokenizer.KEYWORDS,
117            "ADD ARCHIVE": TokenType.COMMAND,
118            "ADD ARCHIVES": TokenType.COMMAND,
119            "ADD FILE": TokenType.COMMAND,
120            "ADD FILES": TokenType.COMMAND,
121            "ADD JAR": TokenType.COMMAND,
122            "ADD JARS": TokenType.COMMAND,
123            "MINUS": TokenType.EXCEPT,
124            "MSCK REPAIR": TokenType.COMMAND,
125            "REFRESH": TokenType.REFRESH,
126            "SERDEPROPERTIES": TokenType.SERDE_PROPERTIES,
127        }
128
129        NUMERIC_LITERALS = {
130            "L": "BIGINT",
131            "S": "SMALLINT",
132            "Y": "TINYINT",
133            "D": "DOUBLE",
134            "F": "FLOAT",
135            "BD": "DECIMAL",
136        }
137
138    Parser = HiveParser
139
140    Generator = HiveGenerator

86    class JSONPathTokenizer(jsonpath.JSONPathTokenizer):
87        VAR_TOKENS = {
88            *jsonpath.JSONPathTokenizer.VAR_TOKENS,
89            TokenType.DASH,
90        }

102    class Tokenizer(tokens.Tokenizer):
103        NUMERIC_ESCAPES = {"u": (16, 4, 4, 0xFFFF), "0": (8, 3, 3, 0x7F)}
104        DROP_UNKNOWN_ESCAPES = True
105        LONE_SURROGATE_REPLACEMENT = "?"
106        QUOTES = ["'", '"']
107        IDENTIFIERS = ["`"]
108        STRING_ESCAPES = ["\\"]
109
110        SINGLE_TOKENS = {
111            **tokens.Tokenizer.SINGLE_TOKENS,
112            "$": TokenType.PARAMETER,
113        }
114
115        KEYWORDS = {
116            **tokens.Tokenizer.KEYWORDS,
117            "ADD ARCHIVE": TokenType.COMMAND,
118            "ADD ARCHIVES": TokenType.COMMAND,
119            "ADD FILE": TokenType.COMMAND,
120            "ADD FILES": TokenType.COMMAND,
121            "ADD JAR": TokenType.COMMAND,
122            "ADD JARS": TokenType.COMMAND,
123            "MINUS": TokenType.EXCEPT,
124            "MSCK REPAIR": TokenType.COMMAND,
125            "REFRESH": TokenType.REFRESH,
126            "SERDEPROPERTIES": TokenType.SERDE_PROPERTIES,
127        }
128
129        NUMERIC_LITERALS = {
130            "L": "BIGINT",
131            "S": "SMALLINT",
132            "Y": "TINYINT",
133            "D": "DOUBLE",
134            "F": "FLOAT",
135            "BD": "DECIMAL",
136        }