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

83    class JSONPathTokenizer(jsonpath.JSONPathTokenizer):
84        VAR_TOKENS = {
85            *jsonpath.JSONPathTokenizer.VAR_TOKENS,
86            TokenType.DASH,
87        }

 89    class Tokenizer(tokens.Tokenizer):
 90        QUOTES = ["'", '"']
 91        IDENTIFIERS = ["`"]
 92        STRING_ESCAPES = ["\\"]
 93
 94        SINGLE_TOKENS = {
 95            **tokens.Tokenizer.SINGLE_TOKENS,
 96            "$": TokenType.PARAMETER,
 97        }
 98
 99        KEYWORDS = {
100            **tokens.Tokenizer.KEYWORDS,
101            "ADD ARCHIVE": TokenType.COMMAND,
102            "ADD ARCHIVES": TokenType.COMMAND,
103            "ADD FILE": TokenType.COMMAND,
104            "ADD FILES": TokenType.COMMAND,
105            "ADD JAR": TokenType.COMMAND,
106            "ADD JARS": TokenType.COMMAND,
107            "MINUS": TokenType.EXCEPT,
108            "MSCK REPAIR": TokenType.COMMAND,
109            "REFRESH": TokenType.REFRESH,
110            "TIMESTAMP AS OF": TokenType.TIMESTAMP_SNAPSHOT,
111            "VERSION AS OF": TokenType.VERSION_SNAPSHOT,
112            "SERDEPROPERTIES": TokenType.SERDE_PROPERTIES,
113        }
114
115        NUMERIC_LITERALS = {
116            "L": "BIGINT",
117            "S": "SMALLINT",
118            "Y": "TINYINT",
119            "D": "DOUBLE",
120            "F": "FLOAT",
121            "BD": "DECIMAL",
122        }