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    INTERSECT_BINDS_TIGHTER_THAN_UNION_AND_EXCEPT = False
 29
 30    # https://spark.apache.org/docs/latest/sql-ref-identifier.html#description
 31    NORMALIZATION_STRATEGY = NormalizationStrategy.CASE_INSENSITIVE
 32
 33    EXPRESSION_METADATA = EXPRESSION_METADATA.copy()
 34
 35    # https://cwiki.apache.org/confluence/pages/viewpage.action?pageId=27362046#LanguageManualUDF-StringFunctions
 36    # https://github.com/apache/hive/blob/master/ql/src/java/org/apache/hadoop/hive/ql/exec/Utilities.java#L266-L269
 37    INITCAP_DEFAULT_DELIMITER_CHARS = " \t\n\r\f\u000b\u001c\u001d\u001e\u001f"
 38
 39    # Support only the non-ANSI mode (default for Hive, Spark2, Spark)
 40    COERCES_TO = defaultdict(set, deepcopy(TypeAnnotator.COERCES_TO))
 41    for target_type in {
 42        *exp.DataType.NUMERIC_TYPES,
 43        *exp.DataType.TEMPORAL_TYPES,
 44        exp.DType.INTERVAL,
 45    }:
 46        COERCES_TO[target_type] |= exp.DataType.TEXT_TYPES
 47
 48    TIME_MAPPING = {
 49        "y": "%Y",
 50        "Y": "%Y",
 51        "YYYY": "%Y",
 52        "yyyy": "%Y",
 53        "YY": "%y",
 54        "yy": "%y",
 55        "MMMM": "%B",
 56        "MMM": "%b",
 57        # Hive 4.0+ parses MM/dd/HH/hh/mm/ss strictly (java.time.DateTimeFormatter, see
 58        # HIVE-25458/HIVE-25576)
 59        "MM": "%mstrict",
 60        "M": "%-m",
 61        "dd": "%dstrict",
 62        "d": "%-d",
 63        "HH": "%Hstrict",
 64        "H": "%-H",
 65        "hh": "%Istrict",
 66        "h": "%-I",
 67        "mm": "%Mstrict",
 68        "m": "%-M",
 69        "ss": "%Sstrict",
 70        "s": "%-S",
 71        "SSSSSS": "%f",
 72        "a": "%p",
 73        "DD": "%j",
 74        "D": "%-j",
 75        "E": "%a",
 76        "EE": "%a",
 77        "EEE": "%a",
 78        "EEEE": "%A",
 79        "z": "%Z",
 80        "Z": "%z",
 81    }
 82
 83    DATE_FORMAT = "'yyyy-MM-dd'"
 84    DATEINT_FORMAT = "'yyyyMMdd'"
 85    TIME_FORMAT = "'yyyy-MM-dd HH:mm:ss'"
 86
 87    class JSONPathTokenizer(jsonpath.JSONPathTokenizer):
 88        VAR_TOKENS = {
 89            *jsonpath.JSONPathTokenizer.VAR_TOKENS,
 90            TokenType.DASH,
 91        }
 92
 93    UNESCAPED_SEQUENCES = {
 94        "\\0": "\0",
 95        "\\Z": "\x1a",
 96        "\\%": "\\%",
 97        "\\_": "\\_",
 98        "\\a": "a",
 99        "\\f": "f",
100        "\\v": "v",
101    }
102
103    class Tokenizer(tokens.Tokenizer):
104        NUMERIC_ESCAPES = {"u": (16, 4, 4, 0xFFFF), "0": (8, 3, 3, 0x7F)}
105        DROP_UNKNOWN_ESCAPES = True
106        LONE_SURROGATE_REPLACEMENT = "?"
107        QUOTES = ["'", '"']
108        IDENTIFIERS = ["`"]
109        STRING_ESCAPES = ["\\"]
110
111        SINGLE_TOKENS = {
112            **tokens.Tokenizer.SINGLE_TOKENS,
113            "$": TokenType.PARAMETER,
114        }
115
116        KEYWORDS = {
117            **tokens.Tokenizer.KEYWORDS,
118            "ADD ARCHIVE": TokenType.COMMAND,
119            "ADD ARCHIVES": TokenType.COMMAND,
120            "ADD FILE": TokenType.COMMAND,
121            "ADD FILES": TokenType.COMMAND,
122            "ADD JAR": TokenType.COMMAND,
123            "ADD JARS": TokenType.COMMAND,
124            "MINUS": TokenType.EXCEPT,
125            "MSCK REPAIR": TokenType.COMMAND,
126            "REFRESH": TokenType.REFRESH,
127            "SERDEPROPERTIES": TokenType.SERDE_PROPERTIES,
128        }
129
130        NUMERIC_LITERALS = {
131            "L": "BIGINT",
132            "S": "SMALLINT",
133            "Y": "TINYINT",
134            "D": "DOUBLE",
135            "F": "FLOAT",
136            "BD": "DECIMAL",
137        }
138
139    Parser = HiveParser
140
141    Generator = HiveGenerator

87    class JSONPathTokenizer(jsonpath.JSONPathTokenizer):
88        VAR_TOKENS = {
89            *jsonpath.JSONPathTokenizer.VAR_TOKENS,
90            TokenType.DASH,
91        }

103    class Tokenizer(tokens.Tokenizer):
104        NUMERIC_ESCAPES = {"u": (16, 4, 4, 0xFFFF), "0": (8, 3, 3, 0x7F)}
105        DROP_UNKNOWN_ESCAPES = True
106        LONE_SURROGATE_REPLACEMENT = "?"
107        QUOTES = ["'", '"']
108        IDENTIFIERS = ["`"]
109        STRING_ESCAPES = ["\\"]
110
111        SINGLE_TOKENS = {
112            **tokens.Tokenizer.SINGLE_TOKENS,
113            "$": TokenType.PARAMETER,
114        }
115
116        KEYWORDS = {
117            **tokens.Tokenizer.KEYWORDS,
118            "ADD ARCHIVE": TokenType.COMMAND,
119            "ADD ARCHIVES": TokenType.COMMAND,
120            "ADD FILE": TokenType.COMMAND,
121            "ADD FILES": TokenType.COMMAND,
122            "ADD JAR": TokenType.COMMAND,
123            "ADD JARS": TokenType.COMMAND,
124            "MINUS": TokenType.EXCEPT,
125            "MSCK REPAIR": TokenType.COMMAND,
126            "REFRESH": TokenType.REFRESH,
127            "SERDEPROPERTIES": TokenType.SERDE_PROPERTIES,
128        }
129
130        NUMERIC_LITERALS = {
131            "L": "BIGINT",
132            "S": "SMALLINT",
133            "Y": "TINYINT",
134            "D": "DOUBLE",
135            "F": "FLOAT",
136            "BD": "DECIMAL",
137        }