Edit on GitHub

sqlglot.dialects.spark2

View Source

  1from __future__ import annotations
  2
  3import typing as t
  4
  5from sqlglot import exp, transforms
  6from sqlglot.dialects.dialect import (
  7    binary_from_function,
  8    build_formatted_time,
  9    is_parse_json,
 10    pivot_column_names,
 11    rename_func,
 12    trim_sql,
 13    unit_to_str,
 14)
 15from sqlglot.dialects.hive import Hive
 16from sqlglot.helper import seq_get
 17from sqlglot.transforms import (
 18    preprocess,
 19    remove_unique_constraints,
 20    ctas_with_tmp_tables_to_create_tmp_view,
 21    move_schema_columns_to_partitioned_by,
 22)
 23
 24
 25def _map_sql(self: Spark2.Generator, expression: exp.Map) -> str:
 26    keys = expression.args.get("keys")
 27    values = expression.args.get("values")
 28
 29    if not keys or not values:
 30        return self.func("MAP")
 31
 32    return self.func("MAP_FROM_ARRAYS", keys, values)
 33
 34
 35def _build_as_cast(to_type: str) -> t.Callable[[t.List], exp.Expression]:
 36    return lambda args: exp.Cast(this=seq_get(args, 0), to=exp.DataType.build(to_type))
 37
 38
 39def _str_to_date(self: Spark2.Generator, expression: exp.StrToDate) -> str:
 40    time_format = self.format_time(expression)
 41    if time_format == Hive.DATE_FORMAT:
 42        return self.func("TO_DATE", expression.this)
 43    return self.func("TO_DATE", expression.this, time_format)
 44
 45
 46def _unix_to_time_sql(self: Spark2.Generator, expression: exp.UnixToTime) -> str:
 47    scale = expression.args.get("scale")
 48    timestamp = expression.this
 49
 50    if scale is None:
 51        return self.sql(exp.cast(exp.func("from_unixtime", timestamp), exp.DataType.Type.TIMESTAMP))
 52    if scale == exp.UnixToTime.SECONDS:
 53        return self.func("TIMESTAMP_SECONDS", timestamp)
 54    if scale == exp.UnixToTime.MILLIS:
 55        return self.func("TIMESTAMP_MILLIS", timestamp)
 56    if scale == exp.UnixToTime.MICROS:
 57        return self.func("TIMESTAMP_MICROS", timestamp)
 58
 59    unix_seconds = exp.Div(this=timestamp, expression=exp.func("POW", 10, scale))
 60    return self.func("TIMESTAMP_SECONDS", unix_seconds)
 61
 62
 63def _unalias_pivot(expression: exp.Expression) -> exp.Expression:
 64    """
 65    Spark doesn't allow PIVOT aliases, so we need to remove them and possibly wrap a
 66    pivoted source in a subquery with the same alias to preserve the query's semantics.
 67
 68    Example:
 69        >>> from sqlglot import parse_one
 70        >>> expr = parse_one("SELECT piv.x FROM tbl PIVOT (SUM(a) FOR b IN ('x')) piv")
 71        >>> print(_unalias_pivot(expr).sql(dialect="spark"))
 72        SELECT piv.x FROM (SELECT * FROM tbl PIVOT(SUM(a) FOR b IN ('x'))) AS piv
 73    """
 74    if isinstance(expression, exp.From) and expression.this.args.get("pivots"):
 75        pivot = expression.this.args["pivots"][0]
 76        if pivot.alias:
 77            alias = pivot.args["alias"].pop()
 78            return exp.From(
 79                this=expression.this.replace(
 80                    exp.select("*")
 81                    .from_(expression.this.copy(), copy=False)
 82                    .subquery(alias=alias, copy=False)
 83                )
 84            )
 85
 86    return expression
 87
 88
 89def _unqualify_pivot_columns(expression: exp.Expression) -> exp.Expression:
 90    """
 91    Spark doesn't allow the column referenced in the PIVOT's field to be qualified,
 92    so we need to unqualify it.
 93
 94    Example:
 95        >>> from sqlglot import parse_one
 96        >>> expr = parse_one("SELECT * FROM tbl PIVOT (SUM(tbl.sales) FOR tbl.quarter IN ('Q1', 'Q2'))")
 97        >>> print(_unqualify_pivot_columns(expr).sql(dialect="spark"))
 98        SELECT * FROM tbl PIVOT(SUM(tbl.sales) FOR quarter IN ('Q1', 'Q1'))
 99    """
100    if isinstance(expression, exp.Pivot):
101        expression.set("field", transforms.unqualify_columns(expression.args["field"]))
102
103    return expression
104
105
106def temporary_storage_provider(expression: exp.Expression) -> exp.Expression:
107    # spark2, spark, Databricks require a storage provider for temporary tables
108    provider = exp.FileFormatProperty(this=exp.Literal.string("parquet"))
109    expression.args["properties"].append("expressions", provider)
110    return expression
111
112
113class Spark2(Hive):
114    class Parser(Hive.Parser):
115        TRIM_PATTERN_FIRST = True
116
117        FUNCTIONS = {
118            **Hive.Parser.FUNCTIONS,
119            "AGGREGATE": exp.Reduce.from_arg_list,
120            "APPROX_PERCENTILE": exp.ApproxQuantile.from_arg_list,
121            "BOOLEAN": _build_as_cast("boolean"),
122            "DATE": _build_as_cast("date"),
123            "DATE_TRUNC": lambda args: exp.TimestampTrunc(
124                this=seq_get(args, 1), unit=exp.var(seq_get(args, 0))
125            ),
126            "DAYOFMONTH": lambda args: exp.DayOfMonth(this=exp.TsOrDsToDate(this=seq_get(args, 0))),
127            "DAYOFWEEK": lambda args: exp.DayOfWeek(this=exp.TsOrDsToDate(this=seq_get(args, 0))),
128            "DAYOFYEAR": lambda args: exp.DayOfYear(this=exp.TsOrDsToDate(this=seq_get(args, 0))),
129            "DOUBLE": _build_as_cast("double"),
130            "FLOAT": _build_as_cast("float"),
131            "FROM_UTC_TIMESTAMP": lambda args: exp.AtTimeZone(
132                this=exp.cast(seq_get(args, 0) or exp.Var(this=""), exp.DataType.Type.TIMESTAMP),
133                zone=seq_get(args, 1),
134            ),
135            "INT": _build_as_cast("int"),
136            "MAP_FROM_ARRAYS": exp.Map.from_arg_list,
137            "RLIKE": exp.RegexpLike.from_arg_list,
138            "SHIFTLEFT": binary_from_function(exp.BitwiseLeftShift),
139            "SHIFTRIGHT": binary_from_function(exp.BitwiseRightShift),
140            "STRING": _build_as_cast("string"),
141            "TIMESTAMP": _build_as_cast("timestamp"),
142            "TO_TIMESTAMP": lambda args: (
143                _build_as_cast("timestamp")(args)
144                if len(args) == 1
145                else build_formatted_time(exp.StrToTime, "spark")(args)
146            ),
147            "TO_UNIX_TIMESTAMP": exp.StrToUnix.from_arg_list,
148            "TO_UTC_TIMESTAMP": lambda args: exp.FromTimeZone(
149                this=exp.cast(seq_get(args, 0) or exp.Var(this=""), exp.DataType.Type.TIMESTAMP),
150                zone=seq_get(args, 1),
151            ),
152            "TRUNC": lambda args: exp.DateTrunc(unit=seq_get(args, 1), this=seq_get(args, 0)),
153            "WEEKOFYEAR": lambda args: exp.WeekOfYear(this=exp.TsOrDsToDate(this=seq_get(args, 0))),
154        }
155
156        FUNCTION_PARSERS = {
157            **Hive.Parser.FUNCTION_PARSERS,
158            "BROADCAST": lambda self: self._parse_join_hint("BROADCAST"),
159            "BROADCASTJOIN": lambda self: self._parse_join_hint("BROADCASTJOIN"),
160            "MAPJOIN": lambda self: self._parse_join_hint("MAPJOIN"),
161            "MERGE": lambda self: self._parse_join_hint("MERGE"),
162            "SHUFFLEMERGE": lambda self: self._parse_join_hint("SHUFFLEMERGE"),
163            "MERGEJOIN": lambda self: self._parse_join_hint("MERGEJOIN"),
164            "SHUFFLE_HASH": lambda self: self._parse_join_hint("SHUFFLE_HASH"),
165            "SHUFFLE_REPLICATE_NL": lambda self: self._parse_join_hint("SHUFFLE_REPLICATE_NL"),
166        }
167
168        def _parse_add_column(self) -> t.Optional[exp.Expression]:
169            return self._match_text_seq("ADD", "COLUMNS") and self._parse_schema()
170
171        def _parse_drop_column(self) -> t.Optional[exp.Drop | exp.Command]:
172            return self._match_text_seq("DROP", "COLUMNS") and self.expression(
173                exp.Drop, this=self._parse_schema(), kind="COLUMNS"
174            )
175
176        def _pivot_column_names(self, aggregations: t.List[exp.Expression]) -> t.List[str]:
177            if len(aggregations) == 1:
178                return [""]
179            return pivot_column_names(aggregations, dialect="spark")
180
181    class Generator(Hive.Generator):
182        QUERY_HINTS = True
183        NVL2_SUPPORTED = True
184        CAN_IMPLEMENT_ARRAY_ANY = True
185
186        PROPERTIES_LOCATION = {
187            **Hive.Generator.PROPERTIES_LOCATION,
188            exp.EngineProperty: exp.Properties.Location.UNSUPPORTED,
189            exp.AutoIncrementProperty: exp.Properties.Location.UNSUPPORTED,
190            exp.CharacterSetProperty: exp.Properties.Location.UNSUPPORTED,
191            exp.CollateProperty: exp.Properties.Location.UNSUPPORTED,
192        }
193
194        TRANSFORMS = {
195            **Hive.Generator.TRANSFORMS,
196            exp.ApproxDistinct: rename_func("APPROX_COUNT_DISTINCT"),
197            exp.ArraySum: lambda self,
198            e: f"AGGREGATE({self.sql(e, 'this')}, 0, (acc, x) -> acc + x, acc -> acc)",
199            exp.ArrayToString: rename_func("ARRAY_JOIN"),
200            exp.AtTimeZone: lambda self, e: self.func(
201                "FROM_UTC_TIMESTAMP", e.this, e.args.get("zone")
202            ),
203            exp.BitwiseLeftShift: rename_func("SHIFTLEFT"),
204            exp.BitwiseRightShift: rename_func("SHIFTRIGHT"),
205            exp.Create: preprocess(
206                [
207                    remove_unique_constraints,
208                    lambda e: ctas_with_tmp_tables_to_create_tmp_view(
209                        e, temporary_storage_provider
210                    ),
211                    move_schema_columns_to_partitioned_by,
212                ]
213            ),
214            exp.DateFromParts: rename_func("MAKE_DATE"),
215            exp.DateTrunc: lambda self, e: self.func("TRUNC", e.this, unit_to_str(e)),
216            exp.DayOfMonth: rename_func("DAYOFMONTH"),
217            exp.DayOfWeek: rename_func("DAYOFWEEK"),
218            exp.DayOfYear: rename_func("DAYOFYEAR"),
219            exp.FileFormatProperty: lambda self, e: f"USING {e.name.upper()}",
220            exp.From: transforms.preprocess([_unalias_pivot]),
221            exp.FromTimeZone: lambda self, e: self.func(
222                "TO_UTC_TIMESTAMP", e.this, e.args.get("zone")
223            ),
224            exp.LogicalAnd: rename_func("BOOL_AND"),
225            exp.LogicalOr: rename_func("BOOL_OR"),
226            exp.Map: _map_sql,
227            exp.Pivot: transforms.preprocess([_unqualify_pivot_columns]),
228            exp.Reduce: rename_func("AGGREGATE"),
229            exp.RegexpReplace: lambda self, e: self.func(
230                "REGEXP_REPLACE",
231                e.this,
232                e.expression,
233                e.args["replacement"],
234                e.args.get("position"),
235            ),
236            exp.StrToDate: _str_to_date,
237            exp.StrToTime: lambda self, e: self.func("TO_TIMESTAMP", e.this, self.format_time(e)),
238            exp.TimestampTrunc: lambda self, e: self.func("DATE_TRUNC", unit_to_str(e), e.this),
239            exp.Trim: trim_sql,
240            exp.UnixToTime: _unix_to_time_sql,
241            exp.VariancePop: rename_func("VAR_POP"),
242            exp.WeekOfYear: rename_func("WEEKOFYEAR"),
243            exp.WithinGroup: transforms.preprocess(
244                [transforms.remove_within_group_for_percentiles]
245            ),
246        }
247        TRANSFORMS.pop(exp.ArraySort)
248        TRANSFORMS.pop(exp.ILike)
249        TRANSFORMS.pop(exp.Left)
250        TRANSFORMS.pop(exp.MonthsBetween)
251        TRANSFORMS.pop(exp.Right)
252
253        WRAP_DERIVED_VALUES = False
254        CREATE_FUNCTION_RETURN_AS = False
255
256        def struct_sql(self, expression: exp.Struct) -> str:
257            from sqlglot.generator import Generator
258
259            return Generator.struct_sql(self, expression)
260
261        def cast_sql(self, expression: exp.Cast, safe_prefix: t.Optional[str] = None) -> str:
262            arg = expression.this
263            is_json_extract = isinstance(arg, (exp.JSONExtract, exp.JSONExtractScalar))
264
265            # We can't use a non-nested type (eg. STRING) as a schema
266            if expression.to.args.get("nested") and (is_parse_json(arg) or is_json_extract):
267                schema = f"'{self.sql(expression, 'to')}'"
268                return self.func("FROM_JSON", arg if is_json_extract else arg.this, schema)
269
270            if is_parse_json(expression):
271                return self.func("TO_JSON", arg)
272
273            return super(Hive.Generator, self).cast_sql(expression, safe_prefix=safe_prefix)
274
275        def columndef_sql(self, expression: exp.ColumnDef, sep: str = " ") -> str:
276            return super().columndef_sql(
277                expression,
278                sep=(
279                    ": "
280                    if isinstance(expression.parent, exp.DataType)
281                    and expression.parent.is_type("struct")
282                    else sep
283                ),
284            )
285
286    class Tokenizer(Hive.Tokenizer):
287        HEX_STRINGS = [("X'", "'"), ("x'", "'")]

def temporary_storage_provider( expression: sqlglot.expressions.Expression) -> sqlglot.expressions.Expression: View Source

107def temporary_storage_provider(expression: exp.Expression) -> exp.Expression:
108    # spark2, spark, Databricks require a storage provider for temporary tables
109    provider = exp.FileFormatProperty(this=exp.Literal.string("parquet"))
110    expression.args["properties"].append("expressions", provider)
111    return expression

class Spark2(sqlglot.dialects.hive.Hive): View Source

114class Spark2(Hive):
115    class Parser(Hive.Parser):
116        TRIM_PATTERN_FIRST = True
117
118        FUNCTIONS = {
119            **Hive.Parser.FUNCTIONS,
120            "AGGREGATE": exp.Reduce.from_arg_list,
121            "APPROX_PERCENTILE": exp.ApproxQuantile.from_arg_list,
122            "BOOLEAN": _build_as_cast("boolean"),
123            "DATE": _build_as_cast("date"),
124            "DATE_TRUNC": lambda args: exp.TimestampTrunc(
125                this=seq_get(args, 1), unit=exp.var(seq_get(args, 0))
126            ),
127            "DAYOFMONTH": lambda args: exp.DayOfMonth(this=exp.TsOrDsToDate(this=seq_get(args, 0))),
128            "DAYOFWEEK": lambda args: exp.DayOfWeek(this=exp.TsOrDsToDate(this=seq_get(args, 0))),
129            "DAYOFYEAR": lambda args: exp.DayOfYear(this=exp.TsOrDsToDate(this=seq_get(args, 0))),
130            "DOUBLE": _build_as_cast("double"),
131            "FLOAT": _build_as_cast("float"),
132            "FROM_UTC_TIMESTAMP": lambda args: exp.AtTimeZone(
133                this=exp.cast(seq_get(args, 0) or exp.Var(this=""), exp.DataType.Type.TIMESTAMP),
134                zone=seq_get(args, 1),
135            ),
136            "INT": _build_as_cast("int"),
137            "MAP_FROM_ARRAYS": exp.Map.from_arg_list,
138            "RLIKE": exp.RegexpLike.from_arg_list,
139            "SHIFTLEFT": binary_from_function(exp.BitwiseLeftShift),
140            "SHIFTRIGHT": binary_from_function(exp.BitwiseRightShift),
141            "STRING": _build_as_cast("string"),
142            "TIMESTAMP": _build_as_cast("timestamp"),
143            "TO_TIMESTAMP": lambda args: (
144                _build_as_cast("timestamp")(args)
145                if len(args) == 1
146                else build_formatted_time(exp.StrToTime, "spark")(args)
147            ),
148            "TO_UNIX_TIMESTAMP": exp.StrToUnix.from_arg_list,
149            "TO_UTC_TIMESTAMP": lambda args: exp.FromTimeZone(
150                this=exp.cast(seq_get(args, 0) or exp.Var(this=""), exp.DataType.Type.TIMESTAMP),
151                zone=seq_get(args, 1),
152            ),
153            "TRUNC": lambda args: exp.DateTrunc(unit=seq_get(args, 1), this=seq_get(args, 0)),
154            "WEEKOFYEAR": lambda args: exp.WeekOfYear(this=exp.TsOrDsToDate(this=seq_get(args, 0))),
155        }
156
157        FUNCTION_PARSERS = {
158            **Hive.Parser.FUNCTION_PARSERS,
159            "BROADCAST": lambda self: self._parse_join_hint("BROADCAST"),
160            "BROADCASTJOIN": lambda self: self._parse_join_hint("BROADCASTJOIN"),
161            "MAPJOIN": lambda self: self._parse_join_hint("MAPJOIN"),
162            "MERGE": lambda self: self._parse_join_hint("MERGE"),
163            "SHUFFLEMERGE": lambda self: self._parse_join_hint("SHUFFLEMERGE"),
164            "MERGEJOIN": lambda self: self._parse_join_hint("MERGEJOIN"),
165            "SHUFFLE_HASH": lambda self: self._parse_join_hint("SHUFFLE_HASH"),
166            "SHUFFLE_REPLICATE_NL": lambda self: self._parse_join_hint("SHUFFLE_REPLICATE_NL"),
167        }
168
169        def _parse_add_column(self) -> t.Optional[exp.Expression]:
170            return self._match_text_seq("ADD", "COLUMNS") and self._parse_schema()
171
172        def _parse_drop_column(self) -> t.Optional[exp.Drop | exp.Command]:
173            return self._match_text_seq("DROP", "COLUMNS") and self.expression(
174                exp.Drop, this=self._parse_schema(), kind="COLUMNS"
175            )
176
177        def _pivot_column_names(self, aggregations: t.List[exp.Expression]) -> t.List[str]:
178            if len(aggregations) == 1:
179                return [""]
180            return pivot_column_names(aggregations, dialect="spark")
181
182    class Generator(Hive.Generator):
183        QUERY_HINTS = True
184        NVL2_SUPPORTED = True
185        CAN_IMPLEMENT_ARRAY_ANY = True
186
187        PROPERTIES_LOCATION = {
188            **Hive.Generator.PROPERTIES_LOCATION,
189            exp.EngineProperty: exp.Properties.Location.UNSUPPORTED,
190            exp.AutoIncrementProperty: exp.Properties.Location.UNSUPPORTED,
191            exp.CharacterSetProperty: exp.Properties.Location.UNSUPPORTED,
192            exp.CollateProperty: exp.Properties.Location.UNSUPPORTED,
193        }
194
195        TRANSFORMS = {
196            **Hive.Generator.TRANSFORMS,
197            exp.ApproxDistinct: rename_func("APPROX_COUNT_DISTINCT"),
198            exp.ArraySum: lambda self,
199            e: f"AGGREGATE({self.sql(e, 'this')}, 0, (acc, x) -> acc + x, acc -> acc)",
200            exp.ArrayToString: rename_func("ARRAY_JOIN"),
201            exp.AtTimeZone: lambda self, e: self.func(
202                "FROM_UTC_TIMESTAMP", e.this, e.args.get("zone")
203            ),
204            exp.BitwiseLeftShift: rename_func("SHIFTLEFT"),
205            exp.BitwiseRightShift: rename_func("SHIFTRIGHT"),
206            exp.Create: preprocess(
207                [
208                    remove_unique_constraints,
209                    lambda e: ctas_with_tmp_tables_to_create_tmp_view(
210                        e, temporary_storage_provider
211                    ),
212                    move_schema_columns_to_partitioned_by,
213                ]
214            ),
215            exp.DateFromParts: rename_func("MAKE_DATE"),
216            exp.DateTrunc: lambda self, e: self.func("TRUNC", e.this, unit_to_str(e)),
217            exp.DayOfMonth: rename_func("DAYOFMONTH"),
218            exp.DayOfWeek: rename_func("DAYOFWEEK"),
219            exp.DayOfYear: rename_func("DAYOFYEAR"),
220            exp.FileFormatProperty: lambda self, e: f"USING {e.name.upper()}",
221            exp.From: transforms.preprocess([_unalias_pivot]),
222            exp.FromTimeZone: lambda self, e: self.func(
223                "TO_UTC_TIMESTAMP", e.this, e.args.get("zone")
224            ),
225            exp.LogicalAnd: rename_func("BOOL_AND"),
226            exp.LogicalOr: rename_func("BOOL_OR"),
227            exp.Map: _map_sql,
228            exp.Pivot: transforms.preprocess([_unqualify_pivot_columns]),
229            exp.Reduce: rename_func("AGGREGATE"),
230            exp.RegexpReplace: lambda self, e: self.func(
231                "REGEXP_REPLACE",
232                e.this,
233                e.expression,
234                e.args["replacement"],
235                e.args.get("position"),
236            ),
237            exp.StrToDate: _str_to_date,
238            exp.StrToTime: lambda self, e: self.func("TO_TIMESTAMP", e.this, self.format_time(e)),
239            exp.TimestampTrunc: lambda self, e: self.func("DATE_TRUNC", unit_to_str(e), e.this),
240            exp.Trim: trim_sql,
241            exp.UnixToTime: _unix_to_time_sql,
242            exp.VariancePop: rename_func("VAR_POP"),
243            exp.WeekOfYear: rename_func("WEEKOFYEAR"),
244            exp.WithinGroup: transforms.preprocess(
245                [transforms.remove_within_group_for_percentiles]
246            ),
247        }
248        TRANSFORMS.pop(exp.ArraySort)
249        TRANSFORMS.pop(exp.ILike)
250        TRANSFORMS.pop(exp.Left)
251        TRANSFORMS.pop(exp.MonthsBetween)
252        TRANSFORMS.pop(exp.Right)
253
254        WRAP_DERIVED_VALUES = False
255        CREATE_FUNCTION_RETURN_AS = False
256
257        def struct_sql(self, expression: exp.Struct) -> str:
258            from sqlglot.generator import Generator
259
260            return Generator.struct_sql(self, expression)
261
262        def cast_sql(self, expression: exp.Cast, safe_prefix: t.Optional[str] = None) -> str:
263            arg = expression.this
264            is_json_extract = isinstance(arg, (exp.JSONExtract, exp.JSONExtractScalar))
265
266            # We can't use a non-nested type (eg. STRING) as a schema
267            if expression.to.args.get("nested") and (is_parse_json(arg) or is_json_extract):
268                schema = f"'{self.sql(expression, 'to')}'"
269                return self.func("FROM_JSON", arg if is_json_extract else arg.this, schema)
270
271            if is_parse_json(expression):
272                return self.func("TO_JSON", arg)
273
274            return super(Hive.Generator, self).cast_sql(expression, safe_prefix=safe_prefix)
275
276        def columndef_sql(self, expression: exp.ColumnDef, sep: str = " ") -> str:
277            return super().columndef_sql(
278                expression,
279                sep=(
280                    ": "
281                    if isinstance(expression.parent, exp.DataType)
282                    and expression.parent.is_type("struct")
283                    else sep
284                ),
285            )
286
287    class Tokenizer(Hive.Tokenizer):
288        HEX_STRINGS = [("X'", "'"), ("x'", "'")]

UNESCAPED_SEQUENCES: Dict[str, str] = {'\\a': '\x07', '\\b': '\x08', '\\f': '\x0c', '\\n': '\n', '\\r': '\r', '\\t': '\t', '\\v': '\x0b', '\\\\': '\\'}

Mapping of an escaped sequence (\n) to its unescaped version ().

tokenizer_class = <class 'Spark2.Tokenizer'>

parser_class = <class 'Spark2.Parser'>

generator_class = <class 'Spark2.Generator'>

TIME_TRIE: Dict = {'y': {0: True, 'y': {'y': {'y': {0: True}}, 0: True}}, 'Y': {0: True, 'Y': {'Y': {'Y': {0: True}}, 0: True}}, 'M': {'M': {'M': {'M': {0: True}, 0: True}, 0: True}, 0: True}, 'd': {'d': {0: True}, 0: True}, 'H': {'H': {0: True}, 0: True}, 'h': {'h': {0: True}, 0: True}, 'm': {'m': {0: True}, 0: True}, 's': {'s': {0: True}, 0: True}, 'S': {'S': {'S': {'S': {'S': {'S': {0: True}}}}}}, 'a': {0: True}, 'D': {'D': {0: True}, 0: True}, 'E': {0: True, 'E': {0: True, 'E': {0: True, 'E': {0: True}}}}}

FORMAT_TRIE: Dict = {'y': {0: True, 'y': {'y': {'y': {0: True}}, 0: True}}, 'Y': {0: True, 'Y': {'Y': {'Y': {0: True}}, 0: True}}, 'M': {'M': {'M': {'M': {0: True}, 0: True}, 0: True}, 0: True}, 'd': {'d': {0: True}, 0: True}, 'H': {'H': {0: True}, 0: True}, 'h': {'h': {0: True}, 0: True}, 'm': {'m': {0: True}, 0: True}, 's': {'s': {0: True}, 0: True}, 'S': {'S': {'S': {'S': {'S': {'S': {0: True}}}}}}, 'a': {0: True}, 'D': {'D': {0: True}, 0: True}, 'E': {0: True, 'E': {0: True, 'E': {0: True, 'E': {0: True}}}}}

INVERSE_TIME_MAPPING: Dict[str, str] = {'%Y': 'yyyy', '%y': 'yy', '%B': 'MMMM', '%b': 'MMM', '%m': 'MM', '%-m': 'M', '%d': 'dd', '%-d': 'd', '%H': 'HH', '%-H': 'H', '%I': 'hh', '%-I': 'h', '%M': 'mm', '%-M': 'm', '%S': 'ss', '%-S': 's', '%f': 'SSSSSS', '%p': 'a', '%j': 'DD', '%-j': 'D', '%a': 'EEE', '%A': 'EEEE'}

INVERSE_TIME_TRIE: Dict = {'%': {'Y': {0: True}, 'y': {0: True}, 'B': {0: True}, 'b': {0: True}, 'm': {0: True}, '-': {'m': {0: True}, 'd': {0: True}, 'H': {0: True}, 'I': {0: True}, 'M': {0: True}, 'S': {0: True}, 'j': {0: True}}, 'd': {0: True}, 'H': {0: True}, 'I': {0: True}, 'M': {0: True}, 'S': {0: True}, 'f': {0: True}, 'p': {0: True}, 'j': {0: True}, 'a': {0: True}, 'A': {0: True}}}

ESCAPED_SEQUENCES: Dict[str, str] = {'\x07': '\\a', '\x08': '\\b', '\x0c': '\\f', '\n': '\\n', '\r': '\\r', '\t': '\\t', '\x0b': '\\v', '\\': '\\\\'}

QUOTE_START = "'"

QUOTE_END = "'"

IDENTIFIER_START = '`'

IDENTIFIER_END = '`'

BIT_START: Optional[str] = None

BIT_END: Optional[str] = None

HEX_START: Optional[str] = "X'"

HEX_END: Optional[str] = "'"

BYTE_START: Optional[str] = None

BYTE_END: Optional[str] = None

UNICODE_START: Optional[str] = None

UNICODE_END: Optional[str] = None

Inherited Members

sqlglot.dialects.dialect.Dialect: Dialect; INDEX_OFFSET; WEEK_OFFSET; UNNEST_COLUMN_ONLY; TABLESAMPLE_SIZE_IS_PERCENT; DPIPE_IS_STRING_CONCAT; STRICT_STRING_CONCAT; SUPPORTS_SEMI_ANTI_JOIN; NORMALIZE_FUNCTIONS; LOG_BASE_FIRST; NULL_ORDERING; TYPED_DIVISION; CONCAT_COALESCE; HEX_LOWERCASE; FORMAT_MAPPING; PSEUDOCOLUMNS; PREFER_CTE_ALIAS_COLUMN; COPY_PARAMS_ARE_CSV; get_or_raise; format_time; normalize_identifier; case_sensitive; can_identify; quote_identifier; to_json_path; parse; parse_into; generate; transpile; tokenize; tokenizer; parser; generator
sqlglot.dialects.hive.Hive: ALIAS_POST_TABLESAMPLE; IDENTIFIERS_CAN_START_WITH_DIGIT; SUPPORTS_USER_DEFINED_TYPES; SAFE_DIVISION; NORMALIZATION_STRATEGY; TIME_MAPPING; DATE_FORMAT; DATEINT_FORMAT; TIME_FORMAT

class Spark2.Parser(sqlglot.dialects.hive.Hive.Parser): View Source

115    class Parser(Hive.Parser):
116        TRIM_PATTERN_FIRST = True
117
118        FUNCTIONS = {
119            **Hive.Parser.FUNCTIONS,
120            "AGGREGATE": exp.Reduce.from_arg_list,
121            "APPROX_PERCENTILE": exp.ApproxQuantile.from_arg_list,
122            "BOOLEAN": _build_as_cast("boolean"),
123            "DATE": _build_as_cast("date"),
124            "DATE_TRUNC": lambda args: exp.TimestampTrunc(
125                this=seq_get(args, 1), unit=exp.var(seq_get(args, 0))
126            ),
127            "DAYOFMONTH": lambda args: exp.DayOfMonth(this=exp.TsOrDsToDate(this=seq_get(args, 0))),
128            "DAYOFWEEK": lambda args: exp.DayOfWeek(this=exp.TsOrDsToDate(this=seq_get(args, 0))),
129            "DAYOFYEAR": lambda args: exp.DayOfYear(this=exp.TsOrDsToDate(this=seq_get(args, 0))),
130            "DOUBLE": _build_as_cast("double"),
131            "FLOAT": _build_as_cast("float"),
132            "FROM_UTC_TIMESTAMP": lambda args: exp.AtTimeZone(
133                this=exp.cast(seq_get(args, 0) or exp.Var(this=""), exp.DataType.Type.TIMESTAMP),
134                zone=seq_get(args, 1),
135            ),
136            "INT": _build_as_cast("int"),
137            "MAP_FROM_ARRAYS": exp.Map.from_arg_list,
138            "RLIKE": exp.RegexpLike.from_arg_list,
139            "SHIFTLEFT": binary_from_function(exp.BitwiseLeftShift),
140            "SHIFTRIGHT": binary_from_function(exp.BitwiseRightShift),
141            "STRING": _build_as_cast("string"),
142            "TIMESTAMP": _build_as_cast("timestamp"),
143            "TO_TIMESTAMP": lambda args: (
144                _build_as_cast("timestamp")(args)
145                if len(args) == 1
146                else build_formatted_time(exp.StrToTime, "spark")(args)
147            ),
148            "TO_UNIX_TIMESTAMP": exp.StrToUnix.from_arg_list,
149            "TO_UTC_TIMESTAMP": lambda args: exp.FromTimeZone(
150                this=exp.cast(seq_get(args, 0) or exp.Var(this=""), exp.DataType.Type.TIMESTAMP),
151                zone=seq_get(args, 1),
152            ),
153            "TRUNC": lambda args: exp.DateTrunc(unit=seq_get(args, 1), this=seq_get(args, 0)),
154            "WEEKOFYEAR": lambda args: exp.WeekOfYear(this=exp.TsOrDsToDate(this=seq_get(args, 0))),
155        }
156
157        FUNCTION_PARSERS = {
158            **Hive.Parser.FUNCTION_PARSERS,
159            "BROADCAST": lambda self: self._parse_join_hint("BROADCAST"),
160            "BROADCASTJOIN": lambda self: self._parse_join_hint("BROADCASTJOIN"),
161            "MAPJOIN": lambda self: self._parse_join_hint("MAPJOIN"),
162            "MERGE": lambda self: self._parse_join_hint("MERGE"),
163            "SHUFFLEMERGE": lambda self: self._parse_join_hint("SHUFFLEMERGE"),
164            "MERGEJOIN": lambda self: self._parse_join_hint("MERGEJOIN"),
165            "SHUFFLE_HASH": lambda self: self._parse_join_hint("SHUFFLE_HASH"),
166            "SHUFFLE_REPLICATE_NL": lambda self: self._parse_join_hint("SHUFFLE_REPLICATE_NL"),
167        }
168
169        def _parse_add_column(self) -> t.Optional[exp.Expression]:
170            return self._match_text_seq("ADD", "COLUMNS") and self._parse_schema()
171
172        def _parse_drop_column(self) -> t.Optional[exp.Drop | exp.Command]:
173            return self._match_text_seq("DROP", "COLUMNS") and self.expression(
174                exp.Drop, this=self._parse_schema(), kind="COLUMNS"
175            )
176
177        def _pivot_column_names(self, aggregations: t.List[exp.Expression]) -> t.List[str]:
178            if len(aggregations) == 1:
179                return [""]
180            return pivot_column_names(aggregations, dialect="spark")

Parser consumes a list of tokens produced by the Tokenizer and produces a parsed syntax tree.

Arguments:

error_level: The desired error level. Default: ErrorLevel.IMMEDIATE
error_message_context: The amount of context to capture from a query string when displaying the error message (in number of characters). Default: 100
max_errors: Maximum number of error messages to include in a raised ParseError. This is only relevant if error_level is ErrorLevel.RAISE. Default: 3

TRIM_PATTERN_FIRST = True

FUNCTIONS = {'ABS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Abs'>>, 'ADD_MONTHS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.AddMonths'>>, 'ANONYMOUS_AGG_FUNC': <bound method Func.from_arg_list of <class 'sqlglot.expressions.AnonymousAggFunc'>>, 'ANY_VALUE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.AnyValue'>>, 'APPROX_DISTINCT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ApproxDistinct'>>, 'APPROX_COUNT_DISTINCT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ApproxDistinct'>>, 'APPROX_QUANTILE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ApproxQuantile'>>, 'APPROX_TOP_K': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ApproxTopK'>>, 'ARG_MAX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArgMax'>>, 'ARGMAX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArgMax'>>, 'MAX_BY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArgMax'>>, 'ARG_MIN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArgMin'>>, 'ARGMIN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArgMin'>>, 'MIN_BY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArgMin'>>, 'ARRAY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Array'>>, 'ARRAY_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayAgg'>>, 'ARRAY_ALL': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayAll'>>, 'ARRAY_ANY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayAny'>>, 'ARRAY_CONCAT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayConcat'>>, 'ARRAY_CAT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayConcat'>>, 'ARRAY_CONSTRUCT_COMPACT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayConstructCompact'>>, 'ARRAY_CONTAINS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayContains'>>, 'ARRAY_HAS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayContains'>>, 'ARRAY_CONTAINS_ALL': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayContainsAll'>>, 'ARRAY_HAS_ALL': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayContainsAll'>>, 'FILTER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayFilter'>>, 'ARRAY_FILTER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayFilter'>>, 'ARRAY_OVERLAPS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayOverlaps'>>, 'ARRAY_SIZE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArraySize'>>, 'ARRAY_LENGTH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArraySize'>>, 'ARRAY_SORT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArraySort'>>, 'ARRAY_SUM': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArraySum'>>, 'ARRAY_TO_STRING': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayToString'>>, 'ARRAY_JOIN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayToString'>>, 'ARRAY_UNION_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayUnionAgg'>>, 'ARRAY_UNIQUE_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayUniqueAgg'>>, 'AVG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Avg'>>, 'CASE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Case'>>, 'CAST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Cast'>>, 'CAST_TO_STR_TYPE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CastToStrType'>>, 'CBRT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Cbrt'>>, 'CEIL': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Ceil'>>, 'CEILING': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Ceil'>>, 'CHR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Chr'>>, 'CHAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Chr'>>, 'COALESCE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Coalesce'>>, 'IFNULL': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Coalesce'>>, 'NVL': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Coalesce'>>, 'COLLATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Collate'>>, 'COMBINED_AGG_FUNC': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CombinedAggFunc'>>, 'COMBINED_PARAMETERIZED_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CombinedParameterizedAgg'>>, 'CONCAT': <function Parser.<lambda>>, 'CONCAT_WS': <function Parser.<lambda>>, 'CONNECT_BY_ROOT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ConnectByRoot'>>, 'CONVERT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Convert'>>, 'CORR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Corr'>>, 'COUNT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Count'>>, 'COUNT_IF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CountIf'>>, 'COUNTIF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CountIf'>>, 'COVAR_POP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CovarPop'>>, 'COVAR_SAMP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CovarSamp'>>, 'CURRENT_DATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CurrentDate'>>, 'CURRENT_DATETIME': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CurrentDatetime'>>, 'CURRENT_TIME': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CurrentTime'>>, 'CURRENT_TIMESTAMP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CurrentTimestamp'>>, 'CURRENT_USER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CurrentUser'>>, 'DATE': <function _build_as_cast.<locals>.<lambda>>, 'DATE_ADD': <function Hive.Parser.<lambda>>, 'DATEDIFF': <function Hive.Parser.<lambda>>, 'DATE_DIFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateDiff'>>, 'DATE_FROM_PARTS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateFromParts'>>, 'DATEFROMPARTS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateFromParts'>>, 'DATE_STR_TO_DATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateStrToDate'>>, 'DATE_SUB': <function Hive.Parser.<lambda>>, 'DATE_TO_DATE_STR': <function Parser.<lambda>>, 'DATE_TO_DI': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateToDi'>>, 'DATE_TRUNC': <function Spark2.Parser.<lambda>>, 'DATETIME_ADD': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DatetimeAdd'>>, 'DATETIME_DIFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DatetimeDiff'>>, 'DATETIME_SUB': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DatetimeSub'>>, 'DATETIME_TRUNC': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DatetimeTrunc'>>, 'DAY': <function Hive.Parser.<lambda>>, 'DAY_OF_MONTH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DayOfMonth'>>, 'DAYOFMONTH': <function Spark2.Parser.<lambda>>, 'DAY_OF_WEEK': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DayOfWeek'>>, 'DAYOFWEEK': <function Spark2.Parser.<lambda>>, 'DAY_OF_YEAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DayOfYear'>>, 'DAYOFYEAR': <function Spark2.Parser.<lambda>>, 'DECODE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Decode'>>, 'DI_TO_DATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DiToDate'>>, 'ENCODE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Encode'>>, 'EXP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Exp'>>, 'EXPLODE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Explode'>>, 'EXPLODE_OUTER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ExplodeOuter'>>, 'EXTRACT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Extract'>>, 'FIRST': <function _build_with_ignore_nulls.<locals>._parse>, 'FIRST_VALUE': <function _build_with_ignore_nulls.<locals>._parse>, 'FLATTEN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Flatten'>>, 'FLOOR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Floor'>>, 'FROM_BASE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.FromBase'>>, 'FROM_BASE64': <bound method Func.from_arg_list of <class 'sqlglot.expressions.FromBase64'>>, 'GENERATE_DATE_ARRAY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.GenerateDateArray'>>, 'GENERATE_SERIES': <bound method Func.from_arg_list of <class 'sqlglot.expressions.GenerateSeries'>>, 'GREATEST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Greatest'>>, 'GROUP_CONCAT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.GroupConcat'>>, 'HEX': <function build_hex>, 'HLL': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Hll'>>, 'IF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.If'>>, 'IIF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.If'>>, 'INITCAP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Initcap'>>, 'IS_INF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.IsInf'>>, 'ISINF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.IsInf'>>, 'IS_NAN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.IsNan'>>, 'ISNAN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.IsNan'>>, 'J_S_O_N_ARRAY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONArray'>>, 'J_S_O_N_ARRAY_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONArrayAgg'>>, 'JSON_ARRAY_CONTAINS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONArrayContains'>>, 'JSONB_EXTRACT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONBExtract'>>, 'JSONB_EXTRACT_SCALAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONBExtractScalar'>>, 'JSON_EXTRACT': <function build_extract_json_with_path.<locals>._builder>, 'JSON_EXTRACT_SCALAR': <function build_extract_json_with_path.<locals>._builder>, 'JSON_FORMAT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONFormat'>>, 'J_S_O_N_OBJECT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONObject'>>, 'J_S_O_N_OBJECT_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONObjectAgg'>>, 'J_S_O_N_TABLE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONTable'>>, 'LAG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Lag'>>, 'LAST': <function _build_with_ignore_nulls.<locals>._parse>, 'LAST_DAY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LastDay'>>, 'LAST_DAY_OF_MONTH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LastDay'>>, 'LAST_VALUE': <function _build_with_ignore_nulls.<locals>._parse>, 'LEAD': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Lead'>>, 'LEAST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Least'>>, 'LEFT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Left'>>, 'LENGTH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Length'>>, 'LEN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Length'>>, 'LEVENSHTEIN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Levenshtein'>>, 'LN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Ln'>>, 'LOG': <function build_logarithm>, 'LOGICAL_AND': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LogicalAnd'>>, 'BOOL_AND': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LogicalAnd'>>, 'BOOLAND_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LogicalAnd'>>, 'LOGICAL_OR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LogicalOr'>>, 'BOOL_OR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LogicalOr'>>, 'BOOLOR_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LogicalOr'>>, 'LOWER': <function build_lower>, 'LCASE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Lower'>>, 'LOWER_HEX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LowerHex'>>, 'MD5': <bound method Func.from_arg_list of <class 'sqlglot.expressions.MD5'>>, 'MD5_DIGEST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.MD5Digest'>>, 'MAP': <function build_var_map>, 'MAP_FROM_ENTRIES': <bound method Func.from_arg_list of <class 'sqlglot.expressions.MapFromEntries'>>, 'MATCH_AGAINST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.MatchAgainst'>>, 'MAX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Max'>>, 'MIN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Min'>>, 'MONTH': <function Hive.Parser.<lambda>>, 'MONTHS_BETWEEN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.MonthsBetween'>>, 'NEXT_VALUE_FOR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.NextValueFor'>>, 'NTH_VALUE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.NthValue'>>, 'NULLIF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Nullif'>>, 'NUMBER_TO_STR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.NumberToStr'>>, 'NVL2': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Nvl2'>>, 'OPEN_J_S_O_N': <bound method Func.from_arg_list of <class 'sqlglot.expressions.OpenJSON'>>, 'PARAMETERIZED_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ParameterizedAgg'>>, 'PARSE_JSON': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ParseJSON'>>, 'JSON_PARSE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ParseJSON'>>, 'PERCENTILE_CONT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.PercentileCont'>>, 'PERCENTILE_DISC': <bound method Func.from_arg_list of <class 'sqlglot.expressions.PercentileDisc'>>, 'POSEXPLODE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Posexplode'>>, 'POSEXPLODE_OUTER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.PosexplodeOuter'>>, 'POWER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Pow'>>, 'POW': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Pow'>>, 'PREDICT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Predict'>>, 'QUANTILE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Quantile'>>, 'QUARTER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Quarter'>>, 'RAND': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Rand'>>, 'RANDOM': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Rand'>>, 'RANDN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Randn'>>, 'RANGE_N': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RangeN'>>, 'READ_CSV': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ReadCSV'>>, 'REDUCE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Reduce'>>, 'REGEXP_EXTRACT': <function Hive.Parser.<lambda>>, 'REGEXP_I_LIKE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RegexpILike'>>, 'REGEXP_LIKE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RegexpLike'>>, 'REGEXP_REPLACE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RegexpReplace'>>, 'REGEXP_SPLIT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RegexpSplit'>>, 'REPEAT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Repeat'>>, 'RIGHT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Right'>>, 'ROUND': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Round'>>, 'ROW_NUMBER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RowNumber'>>, 'SHA': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SHA'>>, 'SHA1': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SHA'>>, 'SHA2': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SHA2'>>, 'SAFE_DIVIDE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SafeDivide'>>, 'SIGN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Sign'>>, 'SIGNUM': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Sign'>>, 'SORT_ARRAY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SortArray'>>, 'SPLIT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RegexpSplit'>>, 'SQRT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Sqrt'>>, 'STANDARD_HASH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StandardHash'>>, 'STAR_MAP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StarMap'>>, 'STARTS_WITH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StartsWith'>>, 'STARTSWITH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StartsWith'>>, 'STDDEV': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Stddev'>>, 'STDDEV_POP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StddevPop'>>, 'STDDEV_SAMP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StddevSamp'>>, 'STR_POSITION': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StrPosition'>>, 'STR_TO_DATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StrToDate'>>, 'STR_TO_MAP': <function Hive.Parser.<lambda>>, 'STR_TO_TIME': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StrToTime'>>, 'STR_TO_UNIX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StrToUnix'>>, 'STRING_TO_ARRAY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StringToArray'>>, 'SPLIT_BY_STRING': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StringToArray'>>, 'STRUCT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Struct'>>, 'STRUCT_EXTRACT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StructExtract'>>, 'STUFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Stuff'>>, 'INSERT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Stuff'>>, 'SUBSTRING': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Substring'>>, 'SUM': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Sum'>>, 'TIME_ADD': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeAdd'>>, 'TIME_DIFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeDiff'>>, 'TIME_FROM_PARTS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeFromParts'>>, 'TIMEFROMPARTS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeFromParts'>>, 'TIME_STR_TO_DATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeStrToDate'>>, 'TIME_STR_TO_TIME': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeStrToTime'>>, 'TIME_STR_TO_UNIX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeStrToUnix'>>, 'TIME_SUB': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeSub'>>, 'TIME_TO_STR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeToStr'>>, 'TIME_TO_TIME_STR': <function Parser.<lambda>>, 'TIME_TO_UNIX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeToUnix'>>, 'TIME_TRUNC': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeTrunc'>>, 'TIMESTAMP': <function _build_as_cast.<locals>.<lambda>>, 'TIMESTAMP_ADD': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimestampAdd'>>, 'TIMESTAMPDIFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimestampDiff'>>, 'TIMESTAMP_DIFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimestampDiff'>>, 'TIMESTAMP_FROM_PARTS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimestampFromParts'>>, 'TIMESTAMPFROMPARTS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimestampFromParts'>>, 'TIMESTAMP_SUB': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimestampSub'>>, 'TIMESTAMP_TRUNC': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimestampTrunc'>>, 'TO_ARRAY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ToArray'>>, 'TO_BASE64': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ToBase64'>>, 'TO_CHAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ToChar'>>, 'TO_DAYS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ToDays'>>, 'TO_MAP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ToMap'>>, 'TO_NUMBER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ToNumber'>>, 'TRANSFORM': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Transform'>>, 'TRIM': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Trim'>>, 'TRY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Try'>>, 'TRY_CAST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TryCast'>>, 'TS_OR_DI_TO_DI': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TsOrDiToDi'>>, 'TS_OR_DS_ADD': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TsOrDsAdd'>>, 'TS_OR_DS_DIFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TsOrDsDiff'>>, 'TS_OR_DS_TO_DATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TsOrDsToDate'>>, 'TS_OR_DS_TO_DATE_STR': <function Parser.<lambda>>, 'TS_OR_DS_TO_TIME': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TsOrDsToTime'>>, 'TS_OR_DS_TO_TIMESTAMP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TsOrDsToTimestamp'>>, 'UNHEX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Unhex'>>, 'UNIX_DATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.UnixDate'>>, 'UNIX_TO_STR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.UnixToStr'>>, 'UNIX_TO_TIME': <bound method Func.from_arg_list of <class 'sqlglot.expressions.UnixToTime'>>, 'UNIX_TO_TIME_STR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.UnixToTimeStr'>>, 'UPPER': <function build_upper>, 'UCASE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Upper'>>, 'VAR_MAP': <function build_var_map>, 'VARIANCE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Variance'>>, 'VARIANCE_SAMP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Variance'>>, 'VAR_SAMP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Variance'>>, 'VARIANCE_POP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.VariancePop'>>, 'VAR_POP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.VariancePop'>>, 'WEEK': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Week'>>, 'WEEK_OF_YEAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.WeekOfYear'>>, 'WEEKOFYEAR': <function Spark2.Parser.<lambda>>, 'WHEN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.When'>>, 'X_M_L_TABLE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.XMLTable'>>, 'XOR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Xor'>>, 'YEAR': <function Hive.Parser.<lambda>>, 'GLOB': <function Parser.<lambda>>, 'JSON_EXTRACT_PATH_TEXT': <function build_extract_json_with_path.<locals>._builder>, 'LIKE': <function build_like>, 'LOG2': <function Parser.<lambda>>, 'LOG10': <function Parser.<lambda>>, 'MOD': <function build_mod>, 'TO_HEX': <function build_hex>, 'BASE64': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ToBase64'>>, 'COLLECT_LIST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayAgg'>>, 'COLLECT_SET': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayUniqueAgg'>>, 'DATE_FORMAT': <function Hive.Parser.<lambda>>, 'FROM_UNIXTIME': <function build_formatted_time.<locals>._builder>, 'GET_JSON_OBJECT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONExtractScalar'>>, 'LOCATE': <function locate_to_strposition>, 'PERCENTILE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Quantile'>>, 'PERCENTILE_APPROX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ApproxQuantile'>>, 'SIZE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArraySize'>>, 'TO_DATE': <function build_formatted_time.<locals>._builder>, 'TO_JSON': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONFormat'>>, 'UNBASE64': <bound method Func.from_arg_list of <class 'sqlglot.expressions.FromBase64'>>, 'UNIX_TIMESTAMP': <function Hive.Parser.<lambda>>, 'AGGREGATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Reduce'>>, 'APPROX_PERCENTILE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ApproxQuantile'>>, 'BOOLEAN': <function _build_as_cast.<locals>.<lambda>>, 'DOUBLE': <function _build_as_cast.<locals>.<lambda>>, 'FLOAT': <function _build_as_cast.<locals>.<lambda>>, 'FROM_UTC_TIMESTAMP': <function Spark2.Parser.<lambda>>, 'INT': <function _build_as_cast.<locals>.<lambda>>, 'MAP_FROM_ARRAYS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Map'>>, 'RLIKE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RegexpLike'>>, 'SHIFTLEFT': <function binary_from_function.<locals>.<lambda>>, 'SHIFTRIGHT': <function binary_from_function.<locals>.<lambda>>, 'STRING': <function _build_as_cast.<locals>.<lambda>>, 'TO_TIMESTAMP': <function Spark2.Parser.<lambda>>, 'TO_UNIX_TIMESTAMP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StrToUnix'>>, 'TO_UTC_TIMESTAMP': <function Spark2.Parser.<lambda>>, 'TRUNC': <function Spark2.Parser.<lambda>>}

FUNCTION_PARSERS = {'CAST': <function Parser.<lambda>>, 'CONVERT': <function Parser.<lambda>>, 'DECODE': <function Parser.<lambda>>, 'EXTRACT': <function Parser.<lambda>>, 'JSON_OBJECT': <function Parser.<lambda>>, 'JSON_OBJECTAGG': <function Parser.<lambda>>, 'JSON_TABLE': <function Parser.<lambda>>, 'MATCH': <function Parser.<lambda>>, 'OPENJSON': <function Parser.<lambda>>, 'POSITION': <function Parser.<lambda>>, 'PREDICT': <function Parser.<lambda>>, 'SAFE_CAST': <function Parser.<lambda>>, 'STRING_AGG': <function Parser.<lambda>>, 'SUBSTRING': <function Parser.<lambda>>, 'TRIM': <function Parser.<lambda>>, 'TRY_CAST': <function Parser.<lambda>>, 'TRY_CONVERT': <function Parser.<lambda>>, 'BROADCAST': <function Spark2.Parser.<lambda>>, 'BROADCASTJOIN': <function Spark2.Parser.<lambda>>, 'MAPJOIN': <function Spark2.Parser.<lambda>>, 'MERGE': <function Spark2.Parser.<lambda>>, 'SHUFFLEMERGE': <function Spark2.Parser.<lambda>>, 'MERGEJOIN': <function Spark2.Parser.<lambda>>, 'SHUFFLE_HASH': <function Spark2.Parser.<lambda>>, 'SHUFFLE_REPLICATE_NL': <function Spark2.Parser.<lambda>>}

SHOW_TRIE: Dict = {}

SET_TRIE: Dict = {'GLOBAL': {0: True}, 'LOCAL': {0: True}, 'SESSION': {0: True}, 'TRANSACTION': {0: True}}

Inherited Members

sqlglot.parser.Parser: Parser; NO_PAREN_FUNCTIONS; STRUCT_TYPE_TOKENS; NESTED_TYPE_TOKENS; ENUM_TYPE_TOKENS; AGGREGATE_TYPE_TOKENS; TYPE_TOKENS; SIGNED_TO_UNSIGNED_TYPE_TOKEN; SUBQUERY_PREDICATES; RESERVED_TOKENS; DB_CREATABLES; CREATABLES; ID_VAR_TOKENS; INTERVAL_VARS; TABLE_ALIAS_TOKENS; ALIAS_TOKENS; COMMENT_TABLE_ALIAS_TOKENS; UPDATE_ALIAS_TOKENS; TRIM_TYPES; FUNC_TOKENS; CONJUNCTION; EQUALITY; COMPARISON; BITWISE; TERM; FACTOR; EXPONENT; TIMES; TIMESTAMPS; SET_OPERATIONS; JOIN_METHODS; JOIN_SIDES; JOIN_KINDS; JOIN_HINTS; LAMBDAS; COLUMN_OPERATORS; EXPRESSION_PARSERS; STATEMENT_PARSERS; UNARY_PARSERS; STRING_PARSERS; NUMERIC_PARSERS; PRIMARY_PARSERS; PLACEHOLDER_PARSERS; RANGE_PARSERS; CONSTRAINT_PARSERS; ALTER_PARSERS; ALTER_ALTER_PARSERS; SCHEMA_UNNAMED_CONSTRAINTS; INVALID_FUNC_NAME_TOKENS; FUNCTIONS_WITH_ALIASED_ARGS; KEY_VALUE_DEFINITIONS; QUERY_MODIFIER_PARSERS; SET_PARSERS; SHOW_PARSERS; TYPE_LITERAL_PARSERS; TYPE_CONVERTER; DDL_SELECT_TOKENS; PRE_VOLATILE_TOKENS; TRANSACTION_KIND; TRANSACTION_CHARACTERISTICS; CONFLICT_ACTIONS; CREATE_SEQUENCE; ISOLATED_LOADING_OPTIONS; USABLES; CAST_ACTIONS; INSERT_ALTERNATIVES; CLONE_KEYWORDS; HISTORICAL_DATA_KIND; OPCLASS_FOLLOW_KEYWORDS; OPTYPE_FOLLOW_TOKENS; TABLE_INDEX_HINT_TOKENS; VIEW_ATTRIBUTES; WINDOW_ALIAS_TOKENS; WINDOW_BEFORE_PAREN_TOKENS; WINDOW_SIDES; JSON_KEY_VALUE_SEPARATOR_TOKENS; FETCH_TOKENS; ADD_CONSTRAINT_TOKENS; DISTINCT_TOKENS; NULL_TOKENS; UNNEST_OFFSET_ALIAS_TOKENS; SELECT_START_TOKENS; PREFIXED_PIVOT_COLUMNS; IDENTIFY_PIVOT_STRINGS; ALTER_TABLE_ADD_REQUIRED_FOR_EACH_COLUMN; TABLESAMPLE_CSV; DEFAULT_SAMPLING_METHOD; SET_REQUIRES_ASSIGNMENT_DELIMITER; STRING_ALIASES; MODIFIERS_ATTACHED_TO_UNION; UNION_MODIFIERS; NO_PAREN_IF_COMMANDS; JSON_ARROWS_REQUIRE_JSON_TYPE; COLON_IS_JSON_EXTRACT; SUPPORTS_IMPLICIT_UNNEST; INTERVAL_SPANS; SUPPORTS_PARTITION_SELECTION; error_level; error_message_context; max_errors; dialect; reset; parse; parse_into; check_errors; raise_error; expression; validate_expression; errors; sql
sqlglot.dialects.hive.Hive.Parser: LOG_DEFAULTS_TO_LN; STRICT_CAST; VALUES_FOLLOWED_BY_PAREN; NO_PAREN_FUNCTION_PARSERS; PROPERTY_PARSERS

class Spark2.Generator(sqlglot.dialects.hive.Hive.Generator): View Source

182    class Generator(Hive.Generator):
183        QUERY_HINTS = True
184        NVL2_SUPPORTED = True
185        CAN_IMPLEMENT_ARRAY_ANY = True
186
187        PROPERTIES_LOCATION = {
188            **Hive.Generator.PROPERTIES_LOCATION,
189            exp.EngineProperty: exp.Properties.Location.UNSUPPORTED,
190            exp.AutoIncrementProperty: exp.Properties.Location.UNSUPPORTED,
191            exp.CharacterSetProperty: exp.Properties.Location.UNSUPPORTED,
192            exp.CollateProperty: exp.Properties.Location.UNSUPPORTED,
193        }
194
195        TRANSFORMS = {
196            **Hive.Generator.TRANSFORMS,
197            exp.ApproxDistinct: rename_func("APPROX_COUNT_DISTINCT"),
198            exp.ArraySum: lambda self,
199            e: f"AGGREGATE({self.sql(e, 'this')}, 0, (acc, x) -> acc + x, acc -> acc)",
200            exp.ArrayToString: rename_func("ARRAY_JOIN"),
201            exp.AtTimeZone: lambda self, e: self.func(
202                "FROM_UTC_TIMESTAMP", e.this, e.args.get("zone")
203            ),
204            exp.BitwiseLeftShift: rename_func("SHIFTLEFT"),
205            exp.BitwiseRightShift: rename_func("SHIFTRIGHT"),
206            exp.Create: preprocess(
207                [
208                    remove_unique_constraints,
209                    lambda e: ctas_with_tmp_tables_to_create_tmp_view(
210                        e, temporary_storage_provider
211                    ),
212                    move_schema_columns_to_partitioned_by,
213                ]
214            ),
215            exp.DateFromParts: rename_func("MAKE_DATE"),
216            exp.DateTrunc: lambda self, e: self.func("TRUNC", e.this, unit_to_str(e)),
217            exp.DayOfMonth: rename_func("DAYOFMONTH"),
218            exp.DayOfWeek: rename_func("DAYOFWEEK"),
219            exp.DayOfYear: rename_func("DAYOFYEAR"),
220            exp.FileFormatProperty: lambda self, e: f"USING {e.name.upper()}",
221            exp.From: transforms.preprocess([_unalias_pivot]),
222            exp.FromTimeZone: lambda self, e: self.func(
223                "TO_UTC_TIMESTAMP", e.this, e.args.get("zone")
224            ),
225            exp.LogicalAnd: rename_func("BOOL_AND"),
226            exp.LogicalOr: rename_func("BOOL_OR"),
227            exp.Map: _map_sql,
228            exp.Pivot: transforms.preprocess([_unqualify_pivot_columns]),
229            exp.Reduce: rename_func("AGGREGATE"),
230            exp.RegexpReplace: lambda self, e: self.func(
231                "REGEXP_REPLACE",
232                e.this,
233                e.expression,
234                e.args["replacement"],
235                e.args.get("position"),
236            ),
237            exp.StrToDate: _str_to_date,
238            exp.StrToTime: lambda self, e: self.func("TO_TIMESTAMP", e.this, self.format_time(e)),
239            exp.TimestampTrunc: lambda self, e: self.func("DATE_TRUNC", unit_to_str(e), e.this),
240            exp.Trim: trim_sql,
241            exp.UnixToTime: _unix_to_time_sql,
242            exp.VariancePop: rename_func("VAR_POP"),
243            exp.WeekOfYear: rename_func("WEEKOFYEAR"),
244            exp.WithinGroup: transforms.preprocess(
245                [transforms.remove_within_group_for_percentiles]
246            ),
247        }
248        TRANSFORMS.pop(exp.ArraySort)
249        TRANSFORMS.pop(exp.ILike)
250        TRANSFORMS.pop(exp.Left)
251        TRANSFORMS.pop(exp.MonthsBetween)
252        TRANSFORMS.pop(exp.Right)
253
254        WRAP_DERIVED_VALUES = False
255        CREATE_FUNCTION_RETURN_AS = False
256
257        def struct_sql(self, expression: exp.Struct) -> str:
258            from sqlglot.generator import Generator
259
260            return Generator.struct_sql(self, expression)
261
262        def cast_sql(self, expression: exp.Cast, safe_prefix: t.Optional[str] = None) -> str:
263            arg = expression.this
264            is_json_extract = isinstance(arg, (exp.JSONExtract, exp.JSONExtractScalar))
265
266            # We can't use a non-nested type (eg. STRING) as a schema
267            if expression.to.args.get("nested") and (is_parse_json(arg) or is_json_extract):
268                schema = f"'{self.sql(expression, 'to')}'"
269                return self.func("FROM_JSON", arg if is_json_extract else arg.this, schema)
270
271            if is_parse_json(expression):
272                return self.func("TO_JSON", arg)
273
274            return super(Hive.Generator, self).cast_sql(expression, safe_prefix=safe_prefix)
275
276        def columndef_sql(self, expression: exp.ColumnDef, sep: str = " ") -> str:
277            return super().columndef_sql(
278                expression,
279                sep=(
280                    ": "
281                    if isinstance(expression.parent, exp.DataType)
282                    and expression.parent.is_type("struct")
283                    else sep
284                ),
285            )

Generator converts a given syntax tree to the corresponding SQL string.

Arguments:

pretty: Whether to format the produced SQL string. Default: False.
identify: Determines when an identifier should be quoted. Possible values are: False (default): Never quote, except in cases where it's mandatory by the dialect. True or 'always': Always quote. 'safe': Only quote identifiers that are case insensitive.
normalize: Whether to normalize identifiers to lowercase. Default: False.
pad: The pad size in a formatted string. For example, this affects the indentation of a projection in a query, relative to its nesting level. Default: 2.
indent: The indentation size in a formatted string. For example, this affects the indentation of subqueries and filters under a WHERE clause. Default: 2.
normalize_functions: How to normalize function names. Possible values are: "upper" or True (default): Convert names to uppercase. "lower": Convert names to lowercase. False: Disables function name normalization.
unsupported_level: Determines the generator's behavior when it encounters unsupported expressions. Default ErrorLevel.WARN.
max_unsupported: Maximum number of unsupported messages to include in a raised UnsupportedError. This is only relevant if unsupported_level is ErrorLevel.RAISE. Default: 3
leading_comma: Whether the comma is leading or trailing in select expressions. This is only relevant when generating in pretty mode. Default: False
max_text_width: The max number of characters in a segment before creating new lines in pretty mode. The default is on the smaller end because the length only represents a segment and not the true line length. Default: 80
comments: Whether to preserve comments in the output SQL code. Default: True

QUERY_HINTS = True

NVL2_SUPPORTED = True

CAN_IMPLEMENT_ARRAY_ANY = True

PROPERTIES_LOCATION = {<class 'sqlglot.expressions.AllowedValuesProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.AlgorithmProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.AutoIncrementProperty'>: <Location.UNSUPPORTED: 'UNSUPPORTED'>, <class 'sqlglot.expressions.AutoRefreshProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.BackupProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.BlockCompressionProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.CharacterSetProperty'>: <Location.UNSUPPORTED: 'UNSUPPORTED'>, <class 'sqlglot.expressions.ChecksumProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.CollateProperty'>: <Location.UNSUPPORTED: 'UNSUPPORTED'>, <class 'sqlglot.expressions.CopyGrantsProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.Cluster'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.ClusteredByProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.DataBlocksizeProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.DataDeletionProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.DefinerProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.DictRange'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.DictProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.DistKeyProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.DistStyleProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.EngineProperty'>: <Location.UNSUPPORTED: 'UNSUPPORTED'>, <class 'sqlglot.expressions.ExecuteAsProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.ExternalProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.FallbackProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.FileFormatProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.FreespaceProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.GlobalProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.HeapProperty'>: <Location.POST_WITH: 'POST_WITH'>, <class 'sqlglot.expressions.InheritsProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.IcebergProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.InputModelProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.IsolatedLoadingProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.JournalProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.LanguageProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.LikeProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.LocationProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.LockProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.LockingProperty'>: <Location.POST_ALIAS: 'POST_ALIAS'>, <class 'sqlglot.expressions.LogProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.MaterializedProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.MergeBlockRatioProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.NoPrimaryIndexProperty'>: <Location.POST_EXPRESSION: 'POST_EXPRESSION'>, <class 'sqlglot.expressions.OnProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.OnCommitProperty'>: <Location.POST_EXPRESSION: 'POST_EXPRESSION'>, <class 'sqlglot.expressions.Order'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.OutputModelProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.PartitionedByProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.PartitionedOfProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.PrimaryKey'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.Property'>: <Location.POST_WITH: 'POST_WITH'>, <class 'sqlglot.expressions.RemoteWithConnectionModelProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.ReturnsProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.RowFormatProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.RowFormatDelimitedProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.RowFormatSerdeProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SampleProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SchemaCommentProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SerdeProperties'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.Set'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SettingsProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SetProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.SetConfigProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SharingProperty'>: <Location.POST_EXPRESSION: 'POST_EXPRESSION'>, <class 'sqlglot.expressions.SequenceProperties'>: <Location.POST_EXPRESSION: 'POST_EXPRESSION'>, <class 'sqlglot.expressions.SortKeyProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SqlReadWriteProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SqlSecurityProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.StabilityProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.StrictProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.TemporaryProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.ToTableProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.TransientProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.TransformModelProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.MergeTreeTTL'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.UnloggedProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.ViewAttributeProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.VolatileProperty'>: <Location.UNSUPPORTED: 'UNSUPPORTED'>, <class 'sqlglot.expressions.WithDataProperty'>: <Location.UNSUPPORTED: 'UNSUPPORTED'>, <class 'sqlglot.expressions.WithJournalTableProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.WithSystemVersioningProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>}

TRANSFORMS = {<class 'sqlglot.expressions.JSONPathKey'>: <function <lambda>>, <class 'sqlglot.expressions.JSONPathRoot'>: <function <lambda>>, <class 'sqlglot.expressions.JSONPathSubscript'>: <function <lambda>>, <class 'sqlglot.expressions.JSONPathWildcard'>: <function <lambda>>, <class 'sqlglot.expressions.AllowedValuesProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.AutoRefreshProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.BackupProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CaseSpecificColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CharacterSetColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CharacterSetProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ClusteredColumnConstraint'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.CollateColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CommentColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CopyGrantsProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.DateFormatColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.DefaultColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.EncodeColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.EphemeralColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ExcludeColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ExecuteAsProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ExternalProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.GlobalProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.HeapProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.IcebergProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.InheritsProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.InlineLengthColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.InputModelProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.IntervalSpan'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.JSONExtract'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.JSONExtractScalar'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.LanguageProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.LocationProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.LogProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.MaterializedProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.NonClusteredColumnConstraint'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.NoPrimaryIndexProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.NotForReplicationColumnConstraint'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.OnCommitProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.OnProperty'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.OnUpdateColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.OutputModelProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.PathColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ProjectionPolicyColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.RemoteWithConnectionModelProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ReturnsProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SampleProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SetConfigProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SetProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SettingsProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SharingProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SqlReadWriteProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SqlSecurityProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.StabilityProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.StrictProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.TemporaryProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.TagColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.TitleColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.Timestamp'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ToMap'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ToTableProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.TransformModelProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.TransientProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.UppercaseColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.UnloggedProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.VarMap'>: <function var_map_sql>, <class 'sqlglot.expressions.ViewAttributeProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.VolatileProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.WithJournalTableProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.WithOperator'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.Group'>: <function preprocess.<locals>._to_sql>, <class 'sqlglot.expressions.Select'>: <function preprocess.<locals>._to_sql>, <class 'sqlglot.expressions.Property'>: <function _property_sql>, <class 'sqlglot.expressions.AnyValue'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.ApproxDistinct'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.ArgMax'>: <function arg_max_or_min_no_count.<locals>._arg_max_or_min_sql>, <class 'sqlglot.expressions.ArgMin'>: <function arg_max_or_min_no_count.<locals>._arg_max_or_min_sql>, <class 'sqlglot.expressions.ArrayConcat'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.ArrayToString'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.ArraySize'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.With'>: <function no_recursive_cte_sql>, <class 'sqlglot.expressions.DateAdd'>: <function _add_date_sql>, <class 'sqlglot.expressions.DateDiff'>: <function _date_diff_sql>, <class 'sqlglot.expressions.DateStrToDate'>: <function datestrtodate_sql>, <class 'sqlglot.expressions.DateSub'>: <function _add_date_sql>, <class 'sqlglot.expressions.DateToDi'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.DiToDate'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.FileFormatProperty'>: <function Spark2.Generator.<lambda>>, <class 'sqlglot.expressions.FromBase64'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.If'>: <function if_sql.<locals>._if_sql>, <class 'sqlglot.expressions.IsNan'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.JSONFormat'>: <function _json_format_sql>, <class 'sqlglot.expressions.Map'>: <function _map_sql>, <class 'sqlglot.expressions.Max'>: <function max_or_greatest>, <class 'sqlglot.expressions.MD5Digest'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.Min'>: <function min_or_least>, <class 'sqlglot.expressions.NotNullColumnConstraint'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.Create'>: <function preprocess.<locals>._to_sql>, <class 'sqlglot.expressions.Quantile'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.ApproxQuantile'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.RegexpExtract'>: <function regexp_extract_sql>, <class 'sqlglot.expressions.RegexpReplace'>: <function Spark2.Generator.<lambda>>, <class 'sqlglot.expressions.RegexpLike'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.RegexpSplit'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.SafeDivide'>: <function no_safe_divide_sql>, <class 'sqlglot.expressions.SchemaCommentProperty'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.ArrayUniqueAgg'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.Split'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.StrPosition'>: <function strposition_to_locate_sql>, <class 'sqlglot.expressions.StrToDate'>: <function _str_to_date>, <class 'sqlglot.expressions.StrToTime'>: <function Spark2.Generator.<lambda>>, <class 'sqlglot.expressions.StrToUnix'>: <function _str_to_unix_sql>, <class 'sqlglot.expressions.StructExtract'>: <function struct_extract_sql>, <class 'sqlglot.expressions.TimeStrToDate'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.TimeStrToTime'>: <function timestrtotime_sql>, <class 'sqlglot.expressions.TimeStrToUnix'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.TimeToStr'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.TimeToUnix'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.ToBase64'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.TsOrDiToDi'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.TsOrDsAdd'>: <function _add_date_sql>, <class 'sqlglot.expressions.TsOrDsDiff'>: <function _date_diff_sql>, <class 'sqlglot.expressions.TsOrDsToDate'>: <function _to_date_sql>, <class 'sqlglot.expressions.TryCast'>: <function no_trycast_sql>, <class 'sqlglot.expressions.UnixToStr'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.UnixToTime'>: <function _unix_to_time_sql>, <class 'sqlglot.expressions.UnixToTimeStr'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.PartitionedByProperty'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.NumberToStr'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.National'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.PrimaryKeyColumnConstraint'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.ParseJSON'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.WeekOfYear'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.DayOfMonth'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.DayOfWeek'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.ArraySum'>: <function Spark2.Generator.<lambda>>, <class 'sqlglot.expressions.AtTimeZone'>: <function Spark2.Generator.<lambda>>, <class 'sqlglot.expressions.BitwiseLeftShift'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.BitwiseRightShift'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.DateFromParts'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.DateTrunc'>: <function Spark2.Generator.<lambda>>, <class 'sqlglot.expressions.DayOfYear'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.From'>: <function preprocess.<locals>._to_sql>, <class 'sqlglot.expressions.FromTimeZone'>: <function Spark2.Generator.<lambda>>, <class 'sqlglot.expressions.LogicalAnd'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.LogicalOr'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.Pivot'>: <function preprocess.<locals>._to_sql>, <class 'sqlglot.expressions.Reduce'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.TimestampTrunc'>: <function Spark2.Generator.<lambda>>, <class 'sqlglot.expressions.Trim'>: <function trim_sql>, <class 'sqlglot.expressions.VariancePop'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.WithinGroup'>: <function preprocess.<locals>._to_sql>}

WRAP_DERIVED_VALUES = False

CREATE_FUNCTION_RETURN_AS = False

def struct_sql(self, expression: sqlglot.expressions.Struct) -> str: View Source

257        def struct_sql(self, expression: exp.Struct) -> str:
258            from sqlglot.generator import Generator
259
260            return Generator.struct_sql(self, expression)

def cast_sql( self, expression: sqlglot.expressions.Cast, safe_prefix: Optional[str] = None) -> str: View Source

262        def cast_sql(self, expression: exp.Cast, safe_prefix: t.Optional[str] = None) -> str:
263            arg = expression.this
264            is_json_extract = isinstance(arg, (exp.JSONExtract, exp.JSONExtractScalar))
265
266            # We can't use a non-nested type (eg. STRING) as a schema
267            if expression.to.args.get("nested") and (is_parse_json(arg) or is_json_extract):
268                schema = f"'{self.sql(expression, 'to')}'"
269                return self.func("FROM_JSON", arg if is_json_extract else arg.this, schema)
270
271            if is_parse_json(expression):
272                return self.func("TO_JSON", arg)
273
274            return super(Hive.Generator, self).cast_sql(expression, safe_prefix=safe_prefix)

def columndef_sql(self, expression: sqlglot.expressions.ColumnDef, sep: str = ' ') -> str: View Source

276        def columndef_sql(self, expression: exp.ColumnDef, sep: str = " ") -> str:
277            return super().columndef_sql(
278                expression,
279                sep=(
280                    ": "
281                    if isinstance(expression.parent, exp.DataType)
282                    and expression.parent.is_type("struct")
283                    else sep
284                ),
285            )

SELECT_KINDS: Tuple[str, ...] = ()

TRY_SUPPORTED = False

Inherited Members

sqlglot.generator.Generator: Generator; NULL_ORDERING_SUPPORTED; IGNORE_NULLS_IN_FUNC; LOCKING_READS_SUPPORTED; EXPLICIT_UNION; MATCHED_BY_SOURCE; SINGLE_STRING_INTERVAL; INTERVAL_ALLOWS_PLURAL_FORM; LIMIT_ONLY_LITERALS; RENAME_TABLE_WITH_DB; GROUPINGS_SEP; QUERY_HINT_SEP; IS_BOOL_ALLOWED; DUPLICATE_KEY_UPDATE_WITH_SET; LIMIT_IS_TOP; RETURNING_END; COLUMN_JOIN_MARKS_SUPPORTED; TZ_TO_WITH_TIME_ZONE; VALUES_AS_TABLE; ALTER_TABLE_INCLUDE_COLUMN_KEYWORD; UNNEST_WITH_ORDINALITY; AGGREGATE_FILTER_SUPPORTED; SEMI_ANTI_JOIN_WITH_SIDE; COMPUTED_COLUMN_WITH_TYPE; SUPPORTS_TABLE_COPY; TABLESAMPLE_REQUIRES_PARENS; TABLESAMPLE_SIZE_IS_ROWS; TABLESAMPLE_KEYWORDS; TABLESAMPLE_SEED_KEYWORD; COLLATE_IS_FUNC; DATA_TYPE_SPECIFIERS_ALLOWED; ENSURE_BOOLS; CTE_RECURSIVE_KEYWORD_REQUIRED; SUPPORTS_SINGLE_ARG_CONCAT; SUPPORTS_TABLE_ALIAS_COLUMNS; UNPIVOT_ALIASES_ARE_IDENTIFIERS; JSON_KEY_VALUE_PAIR_SEP; INSERT_OVERWRITE; SUPPORTS_SELECT_INTO; SUPPORTS_UNLOGGED_TABLES; SUPPORTS_CREATE_TABLE_LIKE; LIKE_PROPERTY_INSIDE_SCHEMA; MULTI_ARG_DISTINCT; JSON_TYPE_REQUIRED_FOR_EXTRACTION; JSON_PATH_BRACKETED_KEY_SUPPORTED; OUTER_UNION_MODIFIERS; COPY_PARAMS_ARE_WRAPPED; COPY_PARAMS_EQ_REQUIRED; COPY_HAS_INTO_KEYWORD; STAR_EXCEPT; HEX_FUNC; TIME_PART_SINGULARS; AFTER_HAVING_MODIFIER_TRANSFORMS; TOKEN_MAPPING; STRUCT_DELIMITER; PARAMETER_TOKEN; NAMED_PLACEHOLDER_TOKEN; RESERVED_KEYWORDS; WITH_SEPARATED_COMMENTS; EXCLUDE_COMMENTS; UNWRAPPED_INTERVAL_VALUES; PARAMETERIZABLE_TEXT_TYPES; SENTINEL_LINE_BREAK; pretty; identify; normalize; pad; unsupported_level; max_unsupported; leading_comma; max_text_width; comments; dialect; normalize_functions; unsupported_messages; generate; preprocess; unsupported; sep; seg; pad_comment; maybe_comment; wrap; no_identify; normalize_func; indent; sql; uncache_sql; cache_sql; characterset_sql; column_parts; column_sql; columnposition_sql; columnconstraint_sql; computedcolumnconstraint_sql; autoincrementcolumnconstraint_sql; compresscolumnconstraint_sql; generatedasidentitycolumnconstraint_sql; generatedasrowcolumnconstraint_sql; periodforsystemtimeconstraint_sql; notnullcolumnconstraint_sql; transformcolumnconstraint_sql; primarykeycolumnconstraint_sql; uniquecolumnconstraint_sql; createable_sql; create_sql; sequenceproperties_sql; clone_sql; describe_sql; heredoc_sql; prepend_ctes; with_sql; cte_sql; tablealias_sql; bitstring_sql; hexstring_sql; bytestring_sql; unicodestring_sql; rawstring_sql; datatypeparam_sql; directory_sql; delete_sql; drop_sql; except_sql; except_op; fetch_sql; filter_sql; hint_sql; indexparameters_sql; index_sql; identifier_sql; hex_sql; lowerhex_sql; inputoutputformat_sql; national_sql; partition_sql; properties_sql; root_properties; properties; with_properties; locate_properties; property_name; property_sql; likeproperty_sql; fallbackproperty_sql; journalproperty_sql; freespaceproperty_sql; checksumproperty_sql; mergeblockratioproperty_sql; datablocksizeproperty_sql; blockcompressionproperty_sql; isolatedloadingproperty_sql; partitionboundspec_sql; partitionedofproperty_sql; lockingproperty_sql; withdataproperty_sql; withsystemversioningproperty_sql; insert_sql; intersect_sql; intersect_op; introducer_sql; kill_sql; pseudotype_sql; objectidentifier_sql; onconflict_sql; returning_sql; rowformatdelimitedproperty_sql; withtablehint_sql; indextablehint_sql; historicaldata_sql; table_parts; table_sql; tablesample_sql; pivot_sql; tuple_sql; update_sql; values_sql; var_sql; into_sql; from_sql; group_sql; having_sql; connect_sql; prior_sql; join_sql; lambda_sql; lateral_op; lateral_sql; limit_sql; offset_sql; setitem_sql; set_sql; pragma_sql; lock_sql; literal_sql; escape_str; loaddata_sql; null_sql; boolean_sql; order_sql; withfill_sql; cluster_sql; distribute_sql; sort_sql; ordered_sql; matchrecognizemeasure_sql; matchrecognize_sql; query_modifiers; queryoption_sql; offset_limit_modifiers; after_limit_modifiers; select_sql; schema_columns_sql; star_sql; sessionparameter_sql; placeholder_sql; subquery_sql; qualify_sql; set_operations; union_sql; union_op; unnest_sql; prewhere_sql; where_sql; window_sql; partition_by_sql; windowspec_sql; withingroup_sql; between_sql; bracket_offset_expressions; bracket_sql; all_sql; any_sql; exists_sql; case_sql; nextvaluefor_sql; extract_sql; trim_sql; convert_concat_args; concat_sql; concatws_sql; check_sql; foreignkey_sql; primarykey_sql; if_sql; matchagainst_sql; jsonkeyvalue_sql; jsonpath_sql; json_path_part; formatjson_sql; jsonobject_sql; jsonobjectagg_sql; jsonarray_sql; jsonarrayagg_sql; jsoncolumndef_sql; jsonschema_sql; jsontable_sql; openjsoncolumndef_sql; openjson_sql; in_sql; in_unnest_op; interval_sql; return_sql; reference_sql; anonymous_sql; paren_sql; neg_sql; not_sql; alias_sql; pivotalias_sql; aliases_sql; atindex_sql; attimezone_sql; fromtimezone_sql; add_sql; and_sql; or_sql; xor_sql; connector_sql; bitwiseand_sql; bitwiseleftshift_sql; bitwisenot_sql; bitwiseor_sql; bitwiserightshift_sql; bitwisexor_sql; currentdate_sql; currenttimestamp_sql; collate_sql; command_sql; comment_sql; mergetreettlaction_sql; mergetreettl_sql; transaction_sql; commit_sql; rollback_sql; altercolumn_sql; alterdiststyle_sql; altersortkey_sql; renametable_sql; renamecolumn_sql; altertable_sql; add_column_sql; droppartition_sql; addconstraint_sql; distinct_sql; ignorenulls_sql; respectnulls_sql; havingmax_sql; intdiv_sql; dpipe_sql; div_sql; overlaps_sql; distance_sql; dot_sql; eq_sql; propertyeq_sql; escape_sql; glob_sql; gt_sql; gte_sql; ilike_sql; ilikeany_sql; is_sql; like_sql; likeany_sql; similarto_sql; lt_sql; lte_sql; mod_sql; mul_sql; neq_sql; nullsafeeq_sql; nullsafeneq_sql; slice_sql; sub_sql; trycast_sql; try_sql; log_sql; use_sql; binary; function_fallback_sql; func; format_args; too_wide; format_time; expressions; op_expressions; naked_property; tag_sql; token_sql; userdefinedfunction_sql; joinhint_sql; kwarg_sql; when_sql; merge_sql; tochar_sql; tonumber_sql; dictproperty_sql; dictrange_sql; dictsubproperty_sql; oncluster_sql; clusteredbyproperty_sql; anyvalue_sql; querytransform_sql; indexconstraintoption_sql; checkcolumnconstraint_sql; indexcolumnconstraint_sql; nvl2_sql; comprehension_sql; columnprefix_sql; opclass_sql; predict_sql; forin_sql; refresh_sql; operator_sql; toarray_sql; tsordstotime_sql; tsordstotimestamp_sql; tsordstodate_sql; unixdate_sql; lastday_sql; dateadd_sql; arrayany_sql; generateseries_sql; partitionrange_sql; truncatetable_sql; convert_sql; copyparameter_sql; credentials_sql; copy_sql; semicolon_sql; datadeletionproperty_sql; maskingpolicycolumnconstraint_sql
sqlglot.dialects.hive.Hive.Generator: LIMIT_FETCH; TABLESAMPLE_WITH_METHOD; JOIN_HINTS; TABLE_HINTS; INDEX_ON; EXTRACT_ALLOWS_QUOTES; LAST_DAY_SUPPORTS_DATE_PART; JSON_PATH_SINGLE_QUOTE_ESCAPE; SUPPORTS_TO_NUMBER; WITH_PROPERTIES_PREFIX; EXPRESSIONS_WITHOUT_NESTED_CTES; SUPPORTED_JSON_PATH_PARTS; TYPE_MAPPING; parameter_sql; schema_sql; constraint_sql; rowformatserdeproperty_sql; arrayagg_sql; datatype_sql; version_sql; alterset_sql; serdeproperties_sql

class Spark2.Tokenizer(sqlglot.dialects.hive.Hive.Tokenizer): View Source

287    class Tokenizer(Hive.Tokenizer):
288        HEX_STRINGS = [("X'", "'"), ("x'", "'")]

HEX_STRINGS = [("X'", "'"), ("x'", "'")]

Inherited Members

sqlglot.tokens.Tokenizer: Tokenizer; BIT_STRINGS; BYTE_STRINGS; RAW_STRINGS; HEREDOC_STRINGS; UNICODE_STRINGS; IDENTIFIER_ESCAPES; VAR_SINGLE_TOKENS; HEREDOC_TAG_IS_IDENTIFIER; HEREDOC_STRING_ALTERNATIVE; WHITE_SPACE; COMMANDS; COMMAND_PREFIX_TOKENS; COMMENTS; dialect; reset; tokenize; tokenize_rs; size; sql; tokens
sqlglot.dialects.hive.Hive.Tokenizer: QUOTES; IDENTIFIERS; STRING_ESCAPES; SINGLE_TOKENS; KEYWORDS; NUMERIC_LITERALS