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        "MM": "%m",
 57        "M": "%-m",
 58        "dd": "%d",
 59        "d": "%-d",
 60        "HH": "%H",
 61        "H": "%-H",
 62        "hh": "%I",
 63        "h": "%-I",
 64        "mm": "%M",
 65        "m": "%-M",
 66        "ss": "%S",
 67        "s": "%-S",
 68        "SSSSSS": "%f",
 69        "a": "%p",
 70        "DD": "%j",
 71        "D": "%-j",
 72        "E": "%a",
 73        "EE": "%a",
 74        "EEE": "%a",
 75        "EEEE": "%A",
 76        "z": "%Z",
 77        "Z": "%z",
 78    }
 79
 80    DATE_FORMAT = "'yyyy-MM-dd'"
 81    DATEINT_FORMAT = "'yyyyMMdd'"
 82    TIME_FORMAT = "'yyyy-MM-dd HH:mm:ss'"
 83
 84    class JSONPathTokenizer(jsonpath.JSONPathTokenizer):
 85        VAR_TOKENS = {
 86            *jsonpath.JSONPathTokenizer.VAR_TOKENS,
 87            TokenType.DASH,
 88        }
 89
 90    class Tokenizer(tokens.Tokenizer):
 91        QUOTES = ["'", '"']
 92        IDENTIFIERS = ["`"]
 93        STRING_ESCAPES = ["\\"]
 94
 95        SINGLE_TOKENS = {
 96            **tokens.Tokenizer.SINGLE_TOKENS,
 97            "$": TokenType.PARAMETER,
 98        }
 99
100        KEYWORDS = {
101            **tokens.Tokenizer.KEYWORDS,
102            "ADD ARCHIVE": TokenType.COMMAND,
103            "ADD ARCHIVES": TokenType.COMMAND,
104            "ADD FILE": TokenType.COMMAND,
105            "ADD FILES": TokenType.COMMAND,
106            "ADD JAR": TokenType.COMMAND,
107            "ADD JARS": TokenType.COMMAND,
108            "MINUS": TokenType.EXCEPT,
109            "MSCK REPAIR": TokenType.COMMAND,
110            "REFRESH": TokenType.REFRESH,
111            "TIMESTAMP AS OF": TokenType.TIMESTAMP_SNAPSHOT,
112            "VERSION AS OF": TokenType.VERSION_SNAPSHOT,
113            "SERDEPROPERTIES": TokenType.SERDE_PROPERTIES,
114        }
115
116        NUMERIC_LITERALS = {
117            "L": "BIGINT",
118            "S": "SMALLINT",
119            "Y": "TINYINT",
120            "D": "DOUBLE",
121            "F": "FLOAT",
122            "BD": "DECIMAL",
123        }
124
125    Parser = HiveParser
126
127    Generator = HiveGenerator

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

 90    class Tokenizer(tokens.Tokenizer):
 91        QUOTES = ["'", '"']
 92        IDENTIFIERS = ["`"]
 93        STRING_ESCAPES = ["\\"]
 94
 95        SINGLE_TOKENS = {
 96            **tokens.Tokenizer.SINGLE_TOKENS,
 97            "$": TokenType.PARAMETER,
 98        }
 99
100        KEYWORDS = {
101            **tokens.Tokenizer.KEYWORDS,
102            "ADD ARCHIVE": TokenType.COMMAND,
103            "ADD ARCHIVES": TokenType.COMMAND,
104            "ADD FILE": TokenType.COMMAND,
105            "ADD FILES": TokenType.COMMAND,
106            "ADD JAR": TokenType.COMMAND,
107            "ADD JARS": TokenType.COMMAND,
108            "MINUS": TokenType.EXCEPT,
109            "MSCK REPAIR": TokenType.COMMAND,
110            "REFRESH": TokenType.REFRESH,
111            "TIMESTAMP AS OF": TokenType.TIMESTAMP_SNAPSHOT,
112            "VERSION AS OF": TokenType.VERSION_SNAPSHOT,
113            "SERDEPROPERTIES": TokenType.SERDE_PROPERTIES,
114        }
115
116        NUMERIC_LITERALS = {
117            "L": "BIGINT",
118            "S": "SMALLINT",
119            "Y": "TINYINT",
120            "D": "DOUBLE",
121            "F": "FLOAT",
122            "BD": "DECIMAL",
123        }