Edit on GitHub

sqlglot.dialects.duckdb

  1from __future__ import annotations
  2
  3import typing as t
  4
  5from sqlglot import exp, generator, parser, tokens
  6from sqlglot.dialects.dialect import (
  7    Dialect,
  8    approx_count_distinct_sql,
  9    arrow_json_extract_scalar_sql,
 10    arrow_json_extract_sql,
 11    binary_from_function,
 12    bool_xor_sql,
 13    date_trunc_to_time,
 14    datestrtodate_sql,
 15    encode_decode_sql,
 16    format_time_lambda,
 17    inline_array_sql,
 18    no_comment_column_constraint_sql,
 19    no_properties_sql,
 20    no_safe_divide_sql,
 21    pivot_column_names,
 22    regexp_extract_sql,
 23    regexp_replace_sql,
 24    rename_func,
 25    str_position_sql,
 26    str_to_time_sql,
 27    timestamptrunc_sql,
 28    timestrtotime_sql,
 29    ts_or_ds_to_date_sql,
 30)
 31from sqlglot.helper import seq_get
 32from sqlglot.tokens import TokenType
 33
 34
 35def _ts_or_ds_add_sql(self: DuckDB.Generator, expression: exp.TsOrDsAdd) -> str:
 36    this = self.sql(expression, "this")
 37    unit = self.sql(expression, "unit").strip("'") or "DAY"
 38    return f"CAST({this} AS DATE) + {self.sql(exp.Interval(this=expression.expression.copy(), unit=unit))}"
 39
 40
 41def _date_delta_sql(self: DuckDB.Generator, expression: exp.DateAdd | exp.DateSub) -> str:
 42    this = self.sql(expression, "this")
 43    unit = self.sql(expression, "unit").strip("'") or "DAY"
 44    op = "+" if isinstance(expression, exp.DateAdd) else "-"
 45    return f"{this} {op} {self.sql(exp.Interval(this=expression.expression.copy(), unit=unit))}"
 46
 47
 48# BigQuery -> DuckDB conversion for the DATE function
 49def _date_sql(self: DuckDB.Generator, expression: exp.Date) -> str:
 50    result = f"CAST({self.sql(expression, 'this')} AS DATE)"
 51    zone = self.sql(expression, "zone")
 52
 53    if zone:
 54        date_str = self.func("STRFTIME", result, "'%d/%m/%Y'")
 55        date_str = f"{date_str} || ' ' || {zone}"
 56
 57        # This will create a TIMESTAMP with time zone information
 58        result = self.func("STRPTIME", date_str, "'%d/%m/%Y %Z'")
 59
 60    return result
 61
 62
 63def _array_sort_sql(self: DuckDB.Generator, expression: exp.ArraySort) -> str:
 64    if expression.expression:
 65        self.unsupported("DUCKDB ARRAY_SORT does not support a comparator")
 66    return f"ARRAY_SORT({self.sql(expression, 'this')})"
 67
 68
 69def _sort_array_sql(self: DuckDB.Generator, expression: exp.SortArray) -> str:
 70    this = self.sql(expression, "this")
 71    if expression.args.get("asc") == exp.false():
 72        return f"ARRAY_REVERSE_SORT({this})"
 73    return f"ARRAY_SORT({this})"
 74
 75
 76def _sort_array_reverse(args: t.List) -> exp.Expression:
 77    return exp.SortArray(this=seq_get(args, 0), asc=exp.false())
 78
 79
 80def _parse_date_diff(args: t.List) -> exp.Expression:
 81    return exp.DateDiff(this=seq_get(args, 2), expression=seq_get(args, 1), unit=seq_get(args, 0))
 82
 83
 84def _struct_sql(self: DuckDB.Generator, expression: exp.Struct) -> str:
 85    args = [
 86        f"'{e.name or e.this.name}': {self.sql(e, 'expression')}" for e in expression.expressions
 87    ]
 88    return f"{{{', '.join(args)}}}"
 89
 90
 91def _datatype_sql(self: DuckDB.Generator, expression: exp.DataType) -> str:
 92    if expression.is_type("array"):
 93        return f"{self.expressions(expression, flat=True)}[]"
 94
 95    # Type TIMESTAMP / TIME WITH TIME ZONE does not support any modifiers
 96    if expression.is_type("timestamptz", "timetz"):
 97        return expression.this.value
 98
 99    return self.datatype_sql(expression)
100
101
102def _json_format_sql(self: DuckDB.Generator, expression: exp.JSONFormat) -> str:
103    sql = self.func("TO_JSON", expression.this, expression.args.get("options"))
104    return f"CAST({sql} AS TEXT)"
105
106
107class DuckDB(Dialect):
108    NULL_ORDERING = "nulls_are_last"
109    SUPPORTS_USER_DEFINED_TYPES = False
110
111    # https://duckdb.org/docs/sql/introduction.html#creating-a-new-table
112    RESOLVES_IDENTIFIERS_AS_UPPERCASE = None
113
114    class Tokenizer(tokens.Tokenizer):
115        KEYWORDS = {
116            **tokens.Tokenizer.KEYWORDS,
117            ":=": TokenType.EQ,
118            "//": TokenType.DIV,
119            "ATTACH": TokenType.COMMAND,
120            "BINARY": TokenType.VARBINARY,
121            "BITSTRING": TokenType.BIT,
122            "BPCHAR": TokenType.TEXT,
123            "CHAR": TokenType.TEXT,
124            "CHARACTER VARYING": TokenType.TEXT,
125            "EXCLUDE": TokenType.EXCEPT,
126            "HUGEINT": TokenType.INT128,
127            "INT1": TokenType.TINYINT,
128            "LOGICAL": TokenType.BOOLEAN,
129            "PIVOT_WIDER": TokenType.PIVOT,
130            "SIGNED": TokenType.INT,
131            "STRING": TokenType.VARCHAR,
132            "UBIGINT": TokenType.UBIGINT,
133            "UINTEGER": TokenType.UINT,
134            "USMALLINT": TokenType.USMALLINT,
135            "UTINYINT": TokenType.UTINYINT,
136        }
137
138    class Parser(parser.Parser):
139        CONCAT_NULL_OUTPUTS_STRING = True
140
141        BITWISE = {
142            **parser.Parser.BITWISE,
143            TokenType.TILDA: exp.RegexpLike,
144        }
145
146        FUNCTIONS = {
147            **parser.Parser.FUNCTIONS,
148            "ARRAY_LENGTH": exp.ArraySize.from_arg_list,
149            "ARRAY_SORT": exp.SortArray.from_arg_list,
150            "ARRAY_REVERSE_SORT": _sort_array_reverse,
151            "DATEDIFF": _parse_date_diff,
152            "DATE_DIFF": _parse_date_diff,
153            "DATE_TRUNC": date_trunc_to_time,
154            "DATETRUNC": date_trunc_to_time,
155            "EPOCH": exp.TimeToUnix.from_arg_list,
156            "EPOCH_MS": lambda args: exp.UnixToTime(
157                this=exp.Div(this=seq_get(args, 0), expression=exp.Literal.number(1000))
158            ),
159            "LIST_REVERSE_SORT": _sort_array_reverse,
160            "LIST_SORT": exp.SortArray.from_arg_list,
161            "LIST_VALUE": exp.Array.from_arg_list,
162            "MEDIAN": lambda args: exp.PercentileCont(
163                this=seq_get(args, 0), expression=exp.Literal.number(0.5)
164            ),
165            "QUANTILE_CONT": exp.PercentileCont.from_arg_list,
166            "QUANTILE_DISC": exp.PercentileDisc.from_arg_list,
167            "REGEXP_EXTRACT": lambda args: exp.RegexpExtract(
168                this=seq_get(args, 0), expression=seq_get(args, 1), group=seq_get(args, 2)
169            ),
170            "REGEXP_MATCHES": exp.RegexpLike.from_arg_list,
171            "STRFTIME": format_time_lambda(exp.TimeToStr, "duckdb"),
172            "STRING_SPLIT": exp.Split.from_arg_list,
173            "STRING_SPLIT_REGEX": exp.RegexpSplit.from_arg_list,
174            "STRING_TO_ARRAY": exp.Split.from_arg_list,
175            "STRPTIME": format_time_lambda(exp.StrToTime, "duckdb"),
176            "STRUCT_PACK": exp.Struct.from_arg_list,
177            "STR_SPLIT": exp.Split.from_arg_list,
178            "STR_SPLIT_REGEX": exp.RegexpSplit.from_arg_list,
179            "TO_TIMESTAMP": exp.UnixToTime.from_arg_list,
180            "UNNEST": exp.Explode.from_arg_list,
181            "XOR": binary_from_function(exp.BitwiseXor),
182        }
183
184        FUNCTION_PARSERS = {
185            **parser.Parser.FUNCTION_PARSERS,
186            "DECODE": lambda self: self.expression(
187                exp.Decode, this=self._parse_conjunction(), charset=exp.Literal.string("utf-8")
188            ),
189            "ENCODE": lambda self: self.expression(
190                exp.Encode, this=self._parse_conjunction(), charset=exp.Literal.string("utf-8")
191            ),
192        }
193
194        TABLE_ALIAS_TOKENS = parser.Parser.TABLE_ALIAS_TOKENS - {
195            TokenType.SEMI,
196            TokenType.ANTI,
197        }
198
199        def _parse_types(
200            self, check_func: bool = False, schema: bool = False, allow_identifiers: bool = True
201        ) -> t.Optional[exp.Expression]:
202            this = super()._parse_types(
203                check_func=check_func, schema=schema, allow_identifiers=allow_identifiers
204            )
205
206            # DuckDB treats NUMERIC and DECIMAL without precision as DECIMAL(18, 3)
207            # See: https://duckdb.org/docs/sql/data_types/numeric
208            if (
209                isinstance(this, exp.DataType)
210                and this.is_type("numeric", "decimal")
211                and not this.expressions
212            ):
213                return exp.DataType.build("DECIMAL(18, 3)")
214
215            return this
216
217        def _parse_struct_types(self) -> t.Optional[exp.Expression]:
218            return self._parse_field_def()
219
220        def _pivot_column_names(self, aggregations: t.List[exp.Expression]) -> t.List[str]:
221            if len(aggregations) == 1:
222                return super()._pivot_column_names(aggregations)
223            return pivot_column_names(aggregations, dialect="duckdb")
224
225    class Generator(generator.Generator):
226        JOIN_HINTS = False
227        TABLE_HINTS = False
228        QUERY_HINTS = False
229        LIMIT_FETCH = "LIMIT"
230        STRUCT_DELIMITER = ("(", ")")
231        RENAME_TABLE_WITH_DB = False
232        NVL2_SUPPORTED = False
233        SEMI_ANTI_JOIN_WITH_SIDE = False
234
235        TRANSFORMS = {
236            **generator.Generator.TRANSFORMS,
237            exp.ApproxDistinct: approx_count_distinct_sql,
238            exp.Array: lambda self, e: self.func("ARRAY", e.expressions[0])
239            if e.expressions and e.expressions[0].find(exp.Select)
240            else inline_array_sql(self, e),
241            exp.ArraySize: rename_func("ARRAY_LENGTH"),
242            exp.ArraySort: _array_sort_sql,
243            exp.ArraySum: rename_func("LIST_SUM"),
244            exp.BitwiseXor: rename_func("XOR"),
245            exp.CommentColumnConstraint: no_comment_column_constraint_sql,
246            exp.CurrentDate: lambda self, e: "CURRENT_DATE",
247            exp.CurrentTime: lambda self, e: "CURRENT_TIME",
248            exp.CurrentTimestamp: lambda self, e: "CURRENT_TIMESTAMP",
249            exp.DayOfMonth: rename_func("DAYOFMONTH"),
250            exp.DayOfWeek: rename_func("DAYOFWEEK"),
251            exp.DayOfYear: rename_func("DAYOFYEAR"),
252            exp.DataType: _datatype_sql,
253            exp.Date: _date_sql,
254            exp.DateAdd: _date_delta_sql,
255            exp.DateFromParts: rename_func("MAKE_DATE"),
256            exp.DateSub: _date_delta_sql,
257            exp.DateDiff: lambda self, e: self.func(
258                "DATE_DIFF", f"'{e.args.get('unit') or 'day'}'", e.expression, e.this
259            ),
260            exp.DateStrToDate: datestrtodate_sql,
261            exp.DateToDi: lambda self, e: f"CAST(STRFTIME({self.sql(e, 'this')}, {DuckDB.DATEINT_FORMAT}) AS INT)",
262            exp.Decode: lambda self, e: encode_decode_sql(self, e, "DECODE", replace=False),
263            exp.DiToDate: lambda self, e: f"CAST(STRPTIME(CAST({self.sql(e, 'this')} AS TEXT), {DuckDB.DATEINT_FORMAT}) AS DATE)",
264            exp.Encode: lambda self, e: encode_decode_sql(self, e, "ENCODE", replace=False),
265            exp.Explode: rename_func("UNNEST"),
266            exp.IntDiv: lambda self, e: self.binary(e, "//"),
267            exp.IsNan: rename_func("ISNAN"),
268            exp.JSONExtract: arrow_json_extract_sql,
269            exp.JSONExtractScalar: arrow_json_extract_scalar_sql,
270            exp.JSONFormat: _json_format_sql,
271            exp.JSONBExtract: arrow_json_extract_sql,
272            exp.JSONBExtractScalar: arrow_json_extract_scalar_sql,
273            exp.LogicalOr: rename_func("BOOL_OR"),
274            exp.LogicalAnd: rename_func("BOOL_AND"),
275            exp.MonthsBetween: lambda self, e: self.func(
276                "DATEDIFF",
277                "'month'",
278                exp.cast(e.expression, "timestamp", copy=True),
279                exp.cast(e.this, "timestamp", copy=True),
280            ),
281            exp.ParseJSON: rename_func("JSON"),
282            exp.PercentileCont: rename_func("QUANTILE_CONT"),
283            exp.PercentileDisc: rename_func("QUANTILE_DISC"),
284            exp.Properties: no_properties_sql,
285            exp.RegexpExtract: regexp_extract_sql,
286            exp.RegexpReplace: regexp_replace_sql,
287            exp.RegexpLike: rename_func("REGEXP_MATCHES"),
288            exp.RegexpSplit: rename_func("STR_SPLIT_REGEX"),
289            exp.SafeDivide: no_safe_divide_sql,
290            exp.Split: rename_func("STR_SPLIT"),
291            exp.SortArray: _sort_array_sql,
292            exp.StrPosition: str_position_sql,
293            exp.StrToDate: lambda self, e: f"CAST({str_to_time_sql(self, e)} AS DATE)",
294            exp.StrToTime: str_to_time_sql,
295            exp.StrToUnix: lambda self, e: f"EPOCH(STRPTIME({self.sql(e, 'this')}, {self.format_time(e)}))",
296            exp.Struct: _struct_sql,
297            exp.TimestampTrunc: timestamptrunc_sql,
298            exp.TimeStrToDate: lambda self, e: f"CAST({self.sql(e, 'this')} AS DATE)",
299            exp.TimeStrToTime: timestrtotime_sql,
300            exp.TimeStrToUnix: lambda self, e: f"EPOCH(CAST({self.sql(e, 'this')} AS TIMESTAMP))",
301            exp.TimeToStr: lambda self, e: f"STRFTIME({self.sql(e, 'this')}, {self.format_time(e)})",
302            exp.TimeToUnix: rename_func("EPOCH"),
303            exp.TsOrDiToDi: lambda self, e: f"CAST(SUBSTR(REPLACE(CAST({self.sql(e, 'this')} AS TEXT), '-', ''), 1, 8) AS INT)",
304            exp.TsOrDsAdd: _ts_or_ds_add_sql,
305            exp.TsOrDsToDate: ts_or_ds_to_date_sql("duckdb"),
306            exp.UnixToStr: lambda self, e: f"STRFTIME(TO_TIMESTAMP({self.sql(e, 'this')}), {self.format_time(e)})",
307            exp.UnixToTime: rename_func("TO_TIMESTAMP"),
308            exp.UnixToTimeStr: lambda self, e: f"CAST(TO_TIMESTAMP({self.sql(e, 'this')}) AS TEXT)",
309            exp.VariancePop: rename_func("VAR_POP"),
310            exp.WeekOfYear: rename_func("WEEKOFYEAR"),
311            exp.Xor: bool_xor_sql,
312        }
313
314        TYPE_MAPPING = {
315            **generator.Generator.TYPE_MAPPING,
316            exp.DataType.Type.BINARY: "BLOB",
317            exp.DataType.Type.CHAR: "TEXT",
318            exp.DataType.Type.FLOAT: "REAL",
319            exp.DataType.Type.NCHAR: "TEXT",
320            exp.DataType.Type.NVARCHAR: "TEXT",
321            exp.DataType.Type.UINT: "UINTEGER",
322            exp.DataType.Type.VARBINARY: "BLOB",
323            exp.DataType.Type.VARCHAR: "TEXT",
324        }
325
326        STAR_MAPPING = {**generator.Generator.STAR_MAPPING, "except": "EXCLUDE"}
327
328        UNWRAPPED_INTERVAL_VALUES = (exp.Column, exp.Literal, exp.Paren)
329
330        PROPERTIES_LOCATION = {
331            **generator.Generator.PROPERTIES_LOCATION,
332            exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED,
333        }
334
335        def interval_sql(self, expression: exp.Interval) -> str:
336            multiplier: t.Optional[int] = None
337            unit = expression.text("unit").lower()
338
339            if unit.startswith("week"):
340                multiplier = 7
341            if unit.startswith("quarter"):
342                multiplier = 90
343
344            if multiplier:
345                return f"({multiplier} * {super().interval_sql(exp.Interval(this=expression.this.copy(), unit=exp.var('day')))})"
346
347            return super().interval_sql(expression)
348
349        def tablesample_sql(
350            self, expression: exp.TableSample, seed_prefix: str = "SEED", sep: str = " AS "
351        ) -> str:
352            return super().tablesample_sql(expression, seed_prefix="REPEATABLE", sep=sep)
class DuckDB(sqlglot.dialects.dialect.Dialect):
108class DuckDB(Dialect):
109    NULL_ORDERING = "nulls_are_last"
110    SUPPORTS_USER_DEFINED_TYPES = False
111
112    # https://duckdb.org/docs/sql/introduction.html#creating-a-new-table
113    RESOLVES_IDENTIFIERS_AS_UPPERCASE = None
114
115    class Tokenizer(tokens.Tokenizer):
116        KEYWORDS = {
117            **tokens.Tokenizer.KEYWORDS,
118            ":=": TokenType.EQ,
119            "//": TokenType.DIV,
120            "ATTACH": TokenType.COMMAND,
121            "BINARY": TokenType.VARBINARY,
122            "BITSTRING": TokenType.BIT,
123            "BPCHAR": TokenType.TEXT,
124            "CHAR": TokenType.TEXT,
125            "CHARACTER VARYING": TokenType.TEXT,
126            "EXCLUDE": TokenType.EXCEPT,
127            "HUGEINT": TokenType.INT128,
128            "INT1": TokenType.TINYINT,
129            "LOGICAL": TokenType.BOOLEAN,
130            "PIVOT_WIDER": TokenType.PIVOT,
131            "SIGNED": TokenType.INT,
132            "STRING": TokenType.VARCHAR,
133            "UBIGINT": TokenType.UBIGINT,
134            "UINTEGER": TokenType.UINT,
135            "USMALLINT": TokenType.USMALLINT,
136            "UTINYINT": TokenType.UTINYINT,
137        }
138
139    class Parser(parser.Parser):
140        CONCAT_NULL_OUTPUTS_STRING = True
141
142        BITWISE = {
143            **parser.Parser.BITWISE,
144            TokenType.TILDA: exp.RegexpLike,
145        }
146
147        FUNCTIONS = {
148            **parser.Parser.FUNCTIONS,
149            "ARRAY_LENGTH": exp.ArraySize.from_arg_list,
150            "ARRAY_SORT": exp.SortArray.from_arg_list,
151            "ARRAY_REVERSE_SORT": _sort_array_reverse,
152            "DATEDIFF": _parse_date_diff,
153            "DATE_DIFF": _parse_date_diff,
154            "DATE_TRUNC": date_trunc_to_time,
155            "DATETRUNC": date_trunc_to_time,
156            "EPOCH": exp.TimeToUnix.from_arg_list,
157            "EPOCH_MS": lambda args: exp.UnixToTime(
158                this=exp.Div(this=seq_get(args, 0), expression=exp.Literal.number(1000))
159            ),
160            "LIST_REVERSE_SORT": _sort_array_reverse,
161            "LIST_SORT": exp.SortArray.from_arg_list,
162            "LIST_VALUE": exp.Array.from_arg_list,
163            "MEDIAN": lambda args: exp.PercentileCont(
164                this=seq_get(args, 0), expression=exp.Literal.number(0.5)
165            ),
166            "QUANTILE_CONT": exp.PercentileCont.from_arg_list,
167            "QUANTILE_DISC": exp.PercentileDisc.from_arg_list,
168            "REGEXP_EXTRACT": lambda args: exp.RegexpExtract(
169                this=seq_get(args, 0), expression=seq_get(args, 1), group=seq_get(args, 2)
170            ),
171            "REGEXP_MATCHES": exp.RegexpLike.from_arg_list,
172            "STRFTIME": format_time_lambda(exp.TimeToStr, "duckdb"),
173            "STRING_SPLIT": exp.Split.from_arg_list,
174            "STRING_SPLIT_REGEX": exp.RegexpSplit.from_arg_list,
175            "STRING_TO_ARRAY": exp.Split.from_arg_list,
176            "STRPTIME": format_time_lambda(exp.StrToTime, "duckdb"),
177            "STRUCT_PACK": exp.Struct.from_arg_list,
178            "STR_SPLIT": exp.Split.from_arg_list,
179            "STR_SPLIT_REGEX": exp.RegexpSplit.from_arg_list,
180            "TO_TIMESTAMP": exp.UnixToTime.from_arg_list,
181            "UNNEST": exp.Explode.from_arg_list,
182            "XOR": binary_from_function(exp.BitwiseXor),
183        }
184
185        FUNCTION_PARSERS = {
186            **parser.Parser.FUNCTION_PARSERS,
187            "DECODE": lambda self: self.expression(
188                exp.Decode, this=self._parse_conjunction(), charset=exp.Literal.string("utf-8")
189            ),
190            "ENCODE": lambda self: self.expression(
191                exp.Encode, this=self._parse_conjunction(), charset=exp.Literal.string("utf-8")
192            ),
193        }
194
195        TABLE_ALIAS_TOKENS = parser.Parser.TABLE_ALIAS_TOKENS - {
196            TokenType.SEMI,
197            TokenType.ANTI,
198        }
199
200        def _parse_types(
201            self, check_func: bool = False, schema: bool = False, allow_identifiers: bool = True
202        ) -> t.Optional[exp.Expression]:
203            this = super()._parse_types(
204                check_func=check_func, schema=schema, allow_identifiers=allow_identifiers
205            )
206
207            # DuckDB treats NUMERIC and DECIMAL without precision as DECIMAL(18, 3)
208            # See: https://duckdb.org/docs/sql/data_types/numeric
209            if (
210                isinstance(this, exp.DataType)
211                and this.is_type("numeric", "decimal")
212                and not this.expressions
213            ):
214                return exp.DataType.build("DECIMAL(18, 3)")
215
216            return this
217
218        def _parse_struct_types(self) -> t.Optional[exp.Expression]:
219            return self._parse_field_def()
220
221        def _pivot_column_names(self, aggregations: t.List[exp.Expression]) -> t.List[str]:
222            if len(aggregations) == 1:
223                return super()._pivot_column_names(aggregations)
224            return pivot_column_names(aggregations, dialect="duckdb")
225
226    class Generator(generator.Generator):
227        JOIN_HINTS = False
228        TABLE_HINTS = False
229        QUERY_HINTS = False
230        LIMIT_FETCH = "LIMIT"
231        STRUCT_DELIMITER = ("(", ")")
232        RENAME_TABLE_WITH_DB = False
233        NVL2_SUPPORTED = False
234        SEMI_ANTI_JOIN_WITH_SIDE = False
235
236        TRANSFORMS = {
237            **generator.Generator.TRANSFORMS,
238            exp.ApproxDistinct: approx_count_distinct_sql,
239            exp.Array: lambda self, e: self.func("ARRAY", e.expressions[0])
240            if e.expressions and e.expressions[0].find(exp.Select)
241            else inline_array_sql(self, e),
242            exp.ArraySize: rename_func("ARRAY_LENGTH"),
243            exp.ArraySort: _array_sort_sql,
244            exp.ArraySum: rename_func("LIST_SUM"),
245            exp.BitwiseXor: rename_func("XOR"),
246            exp.CommentColumnConstraint: no_comment_column_constraint_sql,
247            exp.CurrentDate: lambda self, e: "CURRENT_DATE",
248            exp.CurrentTime: lambda self, e: "CURRENT_TIME",
249            exp.CurrentTimestamp: lambda self, e: "CURRENT_TIMESTAMP",
250            exp.DayOfMonth: rename_func("DAYOFMONTH"),
251            exp.DayOfWeek: rename_func("DAYOFWEEK"),
252            exp.DayOfYear: rename_func("DAYOFYEAR"),
253            exp.DataType: _datatype_sql,
254            exp.Date: _date_sql,
255            exp.DateAdd: _date_delta_sql,
256            exp.DateFromParts: rename_func("MAKE_DATE"),
257            exp.DateSub: _date_delta_sql,
258            exp.DateDiff: lambda self, e: self.func(
259                "DATE_DIFF", f"'{e.args.get('unit') or 'day'}'", e.expression, e.this
260            ),
261            exp.DateStrToDate: datestrtodate_sql,
262            exp.DateToDi: lambda self, e: f"CAST(STRFTIME({self.sql(e, 'this')}, {DuckDB.DATEINT_FORMAT}) AS INT)",
263            exp.Decode: lambda self, e: encode_decode_sql(self, e, "DECODE", replace=False),
264            exp.DiToDate: lambda self, e: f"CAST(STRPTIME(CAST({self.sql(e, 'this')} AS TEXT), {DuckDB.DATEINT_FORMAT}) AS DATE)",
265            exp.Encode: lambda self, e: encode_decode_sql(self, e, "ENCODE", replace=False),
266            exp.Explode: rename_func("UNNEST"),
267            exp.IntDiv: lambda self, e: self.binary(e, "//"),
268            exp.IsNan: rename_func("ISNAN"),
269            exp.JSONExtract: arrow_json_extract_sql,
270            exp.JSONExtractScalar: arrow_json_extract_scalar_sql,
271            exp.JSONFormat: _json_format_sql,
272            exp.JSONBExtract: arrow_json_extract_sql,
273            exp.JSONBExtractScalar: arrow_json_extract_scalar_sql,
274            exp.LogicalOr: rename_func("BOOL_OR"),
275            exp.LogicalAnd: rename_func("BOOL_AND"),
276            exp.MonthsBetween: lambda self, e: self.func(
277                "DATEDIFF",
278                "'month'",
279                exp.cast(e.expression, "timestamp", copy=True),
280                exp.cast(e.this, "timestamp", copy=True),
281            ),
282            exp.ParseJSON: rename_func("JSON"),
283            exp.PercentileCont: rename_func("QUANTILE_CONT"),
284            exp.PercentileDisc: rename_func("QUANTILE_DISC"),
285            exp.Properties: no_properties_sql,
286            exp.RegexpExtract: regexp_extract_sql,
287            exp.RegexpReplace: regexp_replace_sql,
288            exp.RegexpLike: rename_func("REGEXP_MATCHES"),
289            exp.RegexpSplit: rename_func("STR_SPLIT_REGEX"),
290            exp.SafeDivide: no_safe_divide_sql,
291            exp.Split: rename_func("STR_SPLIT"),
292            exp.SortArray: _sort_array_sql,
293            exp.StrPosition: str_position_sql,
294            exp.StrToDate: lambda self, e: f"CAST({str_to_time_sql(self, e)} AS DATE)",
295            exp.StrToTime: str_to_time_sql,
296            exp.StrToUnix: lambda self, e: f"EPOCH(STRPTIME({self.sql(e, 'this')}, {self.format_time(e)}))",
297            exp.Struct: _struct_sql,
298            exp.TimestampTrunc: timestamptrunc_sql,
299            exp.TimeStrToDate: lambda self, e: f"CAST({self.sql(e, 'this')} AS DATE)",
300            exp.TimeStrToTime: timestrtotime_sql,
301            exp.TimeStrToUnix: lambda self, e: f"EPOCH(CAST({self.sql(e, 'this')} AS TIMESTAMP))",
302            exp.TimeToStr: lambda self, e: f"STRFTIME({self.sql(e, 'this')}, {self.format_time(e)})",
303            exp.TimeToUnix: rename_func("EPOCH"),
304            exp.TsOrDiToDi: lambda self, e: f"CAST(SUBSTR(REPLACE(CAST({self.sql(e, 'this')} AS TEXT), '-', ''), 1, 8) AS INT)",
305            exp.TsOrDsAdd: _ts_or_ds_add_sql,
306            exp.TsOrDsToDate: ts_or_ds_to_date_sql("duckdb"),
307            exp.UnixToStr: lambda self, e: f"STRFTIME(TO_TIMESTAMP({self.sql(e, 'this')}), {self.format_time(e)})",
308            exp.UnixToTime: rename_func("TO_TIMESTAMP"),
309            exp.UnixToTimeStr: lambda self, e: f"CAST(TO_TIMESTAMP({self.sql(e, 'this')}) AS TEXT)",
310            exp.VariancePop: rename_func("VAR_POP"),
311            exp.WeekOfYear: rename_func("WEEKOFYEAR"),
312            exp.Xor: bool_xor_sql,
313        }
314
315        TYPE_MAPPING = {
316            **generator.Generator.TYPE_MAPPING,
317            exp.DataType.Type.BINARY: "BLOB",
318            exp.DataType.Type.CHAR: "TEXT",
319            exp.DataType.Type.FLOAT: "REAL",
320            exp.DataType.Type.NCHAR: "TEXT",
321            exp.DataType.Type.NVARCHAR: "TEXT",
322            exp.DataType.Type.UINT: "UINTEGER",
323            exp.DataType.Type.VARBINARY: "BLOB",
324            exp.DataType.Type.VARCHAR: "TEXT",
325        }
326
327        STAR_MAPPING = {**generator.Generator.STAR_MAPPING, "except": "EXCLUDE"}
328
329        UNWRAPPED_INTERVAL_VALUES = (exp.Column, exp.Literal, exp.Paren)
330
331        PROPERTIES_LOCATION = {
332            **generator.Generator.PROPERTIES_LOCATION,
333            exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED,
334        }
335
336        def interval_sql(self, expression: exp.Interval) -> str:
337            multiplier: t.Optional[int] = None
338            unit = expression.text("unit").lower()
339
340            if unit.startswith("week"):
341                multiplier = 7
342            if unit.startswith("quarter"):
343                multiplier = 90
344
345            if multiplier:
346                return f"({multiplier} * {super().interval_sql(exp.Interval(this=expression.this.copy(), unit=exp.var('day')))})"
347
348            return super().interval_sql(expression)
349
350        def tablesample_sql(
351            self, expression: exp.TableSample, seed_prefix: str = "SEED", sep: str = " AS "
352        ) -> str:
353            return super().tablesample_sql(expression, seed_prefix="REPEATABLE", sep=sep)
NULL_ORDERING = 'nulls_are_last'
SUPPORTS_USER_DEFINED_TYPES = False
RESOLVES_IDENTIFIERS_AS_UPPERCASE: Optional[bool] = None
tokenizer_class = <class 'DuckDB.Tokenizer'>
parser_class = <class 'DuckDB.Parser'>
generator_class = <class 'DuckDB.Generator'>
TIME_TRIE: Dict = {}
FORMAT_TRIE: Dict = {}
INVERSE_TIME_MAPPING: Dict[str, str] = {}
INVERSE_TIME_TRIE: Dict = {}
INVERSE_ESCAPE_SEQUENCES: Dict[str, str] = {}
QUOTE_START = "'"
QUOTE_END = "'"
IDENTIFIER_START = '"'
IDENTIFIER_END = '"'
BIT_START = None
BIT_END = None
HEX_START = None
HEX_END = None
BYTE_START = None
BYTE_END = None
class DuckDB.Tokenizer(sqlglot.tokens.Tokenizer):
115    class Tokenizer(tokens.Tokenizer):
116        KEYWORDS = {
117            **tokens.Tokenizer.KEYWORDS,
118            ":=": TokenType.EQ,
119            "//": TokenType.DIV,
120            "ATTACH": TokenType.COMMAND,
121            "BINARY": TokenType.VARBINARY,
122            "BITSTRING": TokenType.BIT,
123            "BPCHAR": TokenType.TEXT,
124            "CHAR": TokenType.TEXT,
125            "CHARACTER VARYING": TokenType.TEXT,
126            "EXCLUDE": TokenType.EXCEPT,
127            "HUGEINT": TokenType.INT128,
128            "INT1": TokenType.TINYINT,
129            "LOGICAL": TokenType.BOOLEAN,
130            "PIVOT_WIDER": TokenType.PIVOT,
131            "SIGNED": TokenType.INT,
132            "STRING": TokenType.VARCHAR,
133            "UBIGINT": TokenType.UBIGINT,
134            "UINTEGER": TokenType.UINT,
135            "USMALLINT": TokenType.USMALLINT,
136            "UTINYINT": TokenType.UTINYINT,
137        }
KEYWORDS = {'{%': <TokenType.BLOCK_START: 'BLOCK_START'>, '{%+': <TokenType.BLOCK_START: 'BLOCK_START'>, '{%-': <TokenType.BLOCK_START: 'BLOCK_START'>, '%}': <TokenType.BLOCK_END: 'BLOCK_END'>, '+%}': <TokenType.BLOCK_END: 'BLOCK_END'>, '-%}': <TokenType.BLOCK_END: 'BLOCK_END'>, '{{+': <TokenType.BLOCK_START: 'BLOCK_START'>, '{{-': <TokenType.BLOCK_START: 'BLOCK_START'>, '+}}': <TokenType.BLOCK_END: 'BLOCK_END'>, '-}}': <TokenType.BLOCK_END: 'BLOCK_END'>, '/*+': <TokenType.HINT: 'HINT'>, '==': <TokenType.EQ: 'EQ'>, '::': <TokenType.DCOLON: 'DCOLON'>, '||': <TokenType.DPIPE: 'DPIPE'>, '>=': <TokenType.GTE: 'GTE'>, '<=': <TokenType.LTE: 'LTE'>, '<>': <TokenType.NEQ: 'NEQ'>, '!=': <TokenType.NEQ: 'NEQ'>, '<=>': <TokenType.NULLSAFE_EQ: 'NULLSAFE_EQ'>, '->': <TokenType.ARROW: 'ARROW'>, '->>': <TokenType.DARROW: 'DARROW'>, '=>': <TokenType.FARROW: 'FARROW'>, '#>': <TokenType.HASH_ARROW: 'HASH_ARROW'>, '#>>': <TokenType.DHASH_ARROW: 'DHASH_ARROW'>, '<->': <TokenType.LR_ARROW: 'LR_ARROW'>, '&&': <TokenType.DAMP: 'DAMP'>, '??': <TokenType.DQMARK: 'DQMARK'>, 'ALL': <TokenType.ALL: 'ALL'>, 'ALWAYS': <TokenType.ALWAYS: 'ALWAYS'>, 'AND': <TokenType.AND: 'AND'>, 'ANTI': <TokenType.ANTI: 'ANTI'>, 'ANY': <TokenType.ANY: 'ANY'>, 'ASC': <TokenType.ASC: 'ASC'>, 'AS': <TokenType.ALIAS: 'ALIAS'>, 'ASOF': <TokenType.ASOF: 'ASOF'>, 'AUTOINCREMENT': <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, 'AUTO_INCREMENT': <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, 'BEGIN': <TokenType.BEGIN: 'BEGIN'>, 'BETWEEN': <TokenType.BETWEEN: 'BETWEEN'>, 'CACHE': <TokenType.CACHE: 'CACHE'>, 'UNCACHE': <TokenType.UNCACHE: 'UNCACHE'>, 'CASE': <TokenType.CASE: 'CASE'>, 'CHARACTER SET': <TokenType.CHARACTER_SET: 'CHARACTER_SET'>, 'CLUSTER BY': <TokenType.CLUSTER_BY: 'CLUSTER_BY'>, 'COLLATE': <TokenType.COLLATE: 'COLLATE'>, 'COLUMN': <TokenType.COLUMN: 'COLUMN'>, 'COMMIT': <TokenType.COMMIT: 'COMMIT'>, 'CONNECT BY': <TokenType.CONNECT_BY: 'CONNECT_BY'>, 'CONSTRAINT': <TokenType.CONSTRAINT: 'CONSTRAINT'>, 'CREATE': <TokenType.CREATE: 'CREATE'>, 'CROSS': <TokenType.CROSS: 'CROSS'>, 'CUBE': <TokenType.CUBE: 'CUBE'>, 'CURRENT_DATE': <TokenType.CURRENT_DATE: 'CURRENT_DATE'>, 'CURRENT_TIME': <TokenType.CURRENT_TIME: 'CURRENT_TIME'>, 'CURRENT_TIMESTAMP': <TokenType.CURRENT_TIMESTAMP: 'CURRENT_TIMESTAMP'>, 'CURRENT_USER': <TokenType.CURRENT_USER: 'CURRENT_USER'>, 'DATABASE': <TokenType.DATABASE: 'DATABASE'>, 'DEFAULT': <TokenType.DEFAULT: 'DEFAULT'>, 'DELETE': <TokenType.DELETE: 'DELETE'>, 'DESC': <TokenType.DESC: 'DESC'>, 'DESCRIBE': <TokenType.DESCRIBE: 'DESCRIBE'>, 'DISTINCT': <TokenType.DISTINCT: 'DISTINCT'>, 'DISTRIBUTE BY': <TokenType.DISTRIBUTE_BY: 'DISTRIBUTE_BY'>, 'DIV': <TokenType.DIV: 'DIV'>, 'DROP': <TokenType.DROP: 'DROP'>, 'ELSE': <TokenType.ELSE: 'ELSE'>, 'END': <TokenType.END: 'END'>, 'ESCAPE': <TokenType.ESCAPE: 'ESCAPE'>, 'EXCEPT': <TokenType.EXCEPT: 'EXCEPT'>, 'EXECUTE': <TokenType.EXECUTE: 'EXECUTE'>, 'EXISTS': <TokenType.EXISTS: 'EXISTS'>, 'FALSE': <TokenType.FALSE: 'FALSE'>, 'FETCH': <TokenType.FETCH: 'FETCH'>, 'FILTER': <TokenType.FILTER: 'FILTER'>, 'FIRST': <TokenType.FIRST: 'FIRST'>, 'FULL': <TokenType.FULL: 'FULL'>, 'FUNCTION': <TokenType.FUNCTION: 'FUNCTION'>, 'FOR': <TokenType.FOR: 'FOR'>, 'FOREIGN KEY': <TokenType.FOREIGN_KEY: 'FOREIGN_KEY'>, 'FORMAT': <TokenType.FORMAT: 'FORMAT'>, 'FROM': <TokenType.FROM: 'FROM'>, 'GEOGRAPHY': <TokenType.GEOGRAPHY: 'GEOGRAPHY'>, 'GEOMETRY': <TokenType.GEOMETRY: 'GEOMETRY'>, 'GLOB': <TokenType.GLOB: 'GLOB'>, 'GROUP BY': <TokenType.GROUP_BY: 'GROUP_BY'>, 'GROUPING SETS': <TokenType.GROUPING_SETS: 'GROUPING_SETS'>, 'HAVING': <TokenType.HAVING: 'HAVING'>, 'ILIKE': <TokenType.ILIKE: 'ILIKE'>, 'IN': <TokenType.IN: 'IN'>, 'INDEX': <TokenType.INDEX: 'INDEX'>, 'INET': <TokenType.INET: 'INET'>, 'INNER': <TokenType.INNER: 'INNER'>, 'INSERT': <TokenType.INSERT: 'INSERT'>, 'INTERVAL': <TokenType.INTERVAL: 'INTERVAL'>, 'INTERSECT': <TokenType.INTERSECT: 'INTERSECT'>, 'INTO': <TokenType.INTO: 'INTO'>, 'IS': <TokenType.IS: 'IS'>, 'ISNULL': <TokenType.ISNULL: 'ISNULL'>, 'JOIN': <TokenType.JOIN: 'JOIN'>, 'KEEP': <TokenType.KEEP: 'KEEP'>, 'KILL': <TokenType.KILL: 'KILL'>, 'LATERAL': <TokenType.LATERAL: 'LATERAL'>, 'LEFT': <TokenType.LEFT: 'LEFT'>, 'LIKE': <TokenType.LIKE: 'LIKE'>, 'LIMIT': <TokenType.LIMIT: 'LIMIT'>, 'LOAD': <TokenType.LOAD: 'LOAD'>, 'LOCK': <TokenType.LOCK: 'LOCK'>, 'MERGE': <TokenType.MERGE: 'MERGE'>, 'NATURAL': <TokenType.NATURAL: 'NATURAL'>, 'NEXT': <TokenType.NEXT: 'NEXT'>, 'NOT': <TokenType.NOT: 'NOT'>, 'NOTNULL': <TokenType.NOTNULL: 'NOTNULL'>, 'NULL': <TokenType.NULL: 'NULL'>, 'OBJECT': <TokenType.OBJECT: 'OBJECT'>, 'OFFSET': <TokenType.OFFSET: 'OFFSET'>, 'ON': <TokenType.ON: 'ON'>, 'OR': <TokenType.OR: 'OR'>, 'XOR': <TokenType.XOR: 'XOR'>, 'ORDER BY': <TokenType.ORDER_BY: 'ORDER_BY'>, 'ORDINALITY': <TokenType.ORDINALITY: 'ORDINALITY'>, 'OUTER': <TokenType.OUTER: 'OUTER'>, 'OVER': <TokenType.OVER: 'OVER'>, 'OVERLAPS': <TokenType.OVERLAPS: 'OVERLAPS'>, 'OVERWRITE': <TokenType.OVERWRITE: 'OVERWRITE'>, 'PARTITION': <TokenType.PARTITION: 'PARTITION'>, 'PARTITION BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PARTITIONED BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PARTITIONED_BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PERCENT': <TokenType.PERCENT: 'PERCENT'>, 'PIVOT': <TokenType.PIVOT: 'PIVOT'>, 'PRAGMA': <TokenType.PRAGMA: 'PRAGMA'>, 'PRIMARY KEY': <TokenType.PRIMARY_KEY: 'PRIMARY_KEY'>, 'PROCEDURE': <TokenType.PROCEDURE: 'PROCEDURE'>, 'QUALIFY': <TokenType.QUALIFY: 'QUALIFY'>, 'RANGE': <TokenType.RANGE: 'RANGE'>, 'RECURSIVE': <TokenType.RECURSIVE: 'RECURSIVE'>, 'REGEXP': <TokenType.RLIKE: 'RLIKE'>, 'REPLACE': <TokenType.REPLACE: 'REPLACE'>, 'RETURNING': <TokenType.RETURNING: 'RETURNING'>, 'REFERENCES': <TokenType.REFERENCES: 'REFERENCES'>, 'RIGHT': <TokenType.RIGHT: 'RIGHT'>, 'RLIKE': <TokenType.RLIKE: 'RLIKE'>, 'ROLLBACK': <TokenType.ROLLBACK: 'ROLLBACK'>, 'ROLLUP': <TokenType.ROLLUP: 'ROLLUP'>, 'ROW': <TokenType.ROW: 'ROW'>, 'ROWS': <TokenType.ROWS: 'ROWS'>, 'SCHEMA': <TokenType.SCHEMA: 'SCHEMA'>, 'SELECT': <TokenType.SELECT: 'SELECT'>, 'SEMI': <TokenType.SEMI: 'SEMI'>, 'SET': <TokenType.SET: 'SET'>, 'SETTINGS': <TokenType.SETTINGS: 'SETTINGS'>, 'SHOW': <TokenType.SHOW: 'SHOW'>, 'SIMILAR TO': <TokenType.SIMILAR_TO: 'SIMILAR_TO'>, 'SOME': <TokenType.SOME: 'SOME'>, 'SORT BY': <TokenType.SORT_BY: 'SORT_BY'>, 'START WITH': <TokenType.START_WITH: 'START_WITH'>, 'TABLE': <TokenType.TABLE: 'TABLE'>, 'TABLESAMPLE': <TokenType.TABLE_SAMPLE: 'TABLE_SAMPLE'>, 'TEMP': <TokenType.TEMPORARY: 'TEMPORARY'>, 'TEMPORARY': <TokenType.TEMPORARY: 'TEMPORARY'>, 'THEN': <TokenType.THEN: 'THEN'>, 'TRUE': <TokenType.TRUE: 'TRUE'>, 'UNION': <TokenType.UNION: 'UNION'>, 'UNKNOWN': <TokenType.UNKNOWN: 'UNKNOWN'>, 'UNNEST': <TokenType.UNNEST: 'UNNEST'>, 'UNPIVOT': <TokenType.UNPIVOT: 'UNPIVOT'>, 'UPDATE': <TokenType.UPDATE: 'UPDATE'>, 'USE': <TokenType.USE: 'USE'>, 'USING': <TokenType.USING: 'USING'>, 'UUID': <TokenType.UUID: 'UUID'>, 'VALUES': <TokenType.VALUES: 'VALUES'>, 'VIEW': <TokenType.VIEW: 'VIEW'>, 'VOLATILE': <TokenType.VOLATILE: 'VOLATILE'>, 'WHEN': <TokenType.WHEN: 'WHEN'>, 'WHERE': <TokenType.WHERE: 'WHERE'>, 'WINDOW': <TokenType.WINDOW: 'WINDOW'>, 'WITH': <TokenType.WITH: 'WITH'>, 'APPLY': <TokenType.APPLY: 'APPLY'>, 'ARRAY': <TokenType.ARRAY: 'ARRAY'>, 'BIT': <TokenType.BIT: 'BIT'>, 'BOOL': <TokenType.BOOLEAN: 'BOOLEAN'>, 'BOOLEAN': <TokenType.BOOLEAN: 'BOOLEAN'>, 'BYTE': <TokenType.TINYINT: 'TINYINT'>, 'MEDIUMINT': <TokenType.MEDIUMINT: 'MEDIUMINT'>, 'TINYINT': <TokenType.TINYINT: 'TINYINT'>, 'SHORT': <TokenType.SMALLINT: 'SMALLINT'>, 'SMALLINT': <TokenType.SMALLINT: 'SMALLINT'>, 'INT128': <TokenType.INT128: 'INT128'>, 'INT2': <TokenType.SMALLINT: 'SMALLINT'>, 'INTEGER': <TokenType.INT: 'INT'>, 'INT': <TokenType.INT: 'INT'>, 'INT4': <TokenType.INT: 'INT'>, 'LONG': <TokenType.BIGINT: 'BIGINT'>, 'BIGINT': <TokenType.BIGINT: 'BIGINT'>, 'INT8': <TokenType.BIGINT: 'BIGINT'>, 'DEC': <TokenType.DECIMAL: 'DECIMAL'>, 'DECIMAL': <TokenType.DECIMAL: 'DECIMAL'>, 'BIGDECIMAL': <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, 'BIGNUMERIC': <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, 'MAP': <TokenType.MAP: 'MAP'>, 'NULLABLE': <TokenType.NULLABLE: 'NULLABLE'>, 'NUMBER': <TokenType.DECIMAL: 'DECIMAL'>, 'NUMERIC': <TokenType.DECIMAL: 'DECIMAL'>, 'FIXED': <TokenType.DECIMAL: 'DECIMAL'>, 'REAL': <TokenType.FLOAT: 'FLOAT'>, 'FLOAT': <TokenType.FLOAT: 'FLOAT'>, 'FLOAT4': <TokenType.FLOAT: 'FLOAT'>, 'FLOAT8': <TokenType.DOUBLE: 'DOUBLE'>, 'DOUBLE': <TokenType.DOUBLE: 'DOUBLE'>, 'DOUBLE PRECISION': <TokenType.DOUBLE: 'DOUBLE'>, 'JSON': <TokenType.JSON: 'JSON'>, 'CHAR': <TokenType.TEXT: 'TEXT'>, 'CHARACTER': <TokenType.CHAR: 'CHAR'>, 'NCHAR': <TokenType.NCHAR: 'NCHAR'>, 'VARCHAR': <TokenType.VARCHAR: 'VARCHAR'>, 'VARCHAR2': <TokenType.VARCHAR: 'VARCHAR'>, 'NVARCHAR': <TokenType.NVARCHAR: 'NVARCHAR'>, 'NVARCHAR2': <TokenType.NVARCHAR: 'NVARCHAR'>, 'STR': <TokenType.TEXT: 'TEXT'>, 'STRING': <TokenType.VARCHAR: 'VARCHAR'>, 'TEXT': <TokenType.TEXT: 'TEXT'>, 'LONGTEXT': <TokenType.LONGTEXT: 'LONGTEXT'>, 'MEDIUMTEXT': <TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>, 'TINYTEXT': <TokenType.TINYTEXT: 'TINYTEXT'>, 'CLOB': <TokenType.TEXT: 'TEXT'>, 'LONGVARCHAR': <TokenType.TEXT: 'TEXT'>, 'BINARY': <TokenType.VARBINARY: 'VARBINARY'>, 'BLOB': <TokenType.VARBINARY: 'VARBINARY'>, 'LONGBLOB': <TokenType.LONGBLOB: 'LONGBLOB'>, 'MEDIUMBLOB': <TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>, 'TINYBLOB': <TokenType.TINYBLOB: 'TINYBLOB'>, 'BYTEA': <TokenType.VARBINARY: 'VARBINARY'>, 'VARBINARY': <TokenType.VARBINARY: 'VARBINARY'>, 'TIME': <TokenType.TIME: 'TIME'>, 'TIMETZ': <TokenType.TIMETZ: 'TIMETZ'>, 'TIMESTAMP': <TokenType.TIMESTAMP: 'TIMESTAMP'>, 'TIMESTAMPTZ': <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>, 'TIMESTAMPLTZ': <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>, 'DATE': <TokenType.DATE: 'DATE'>, 'DATETIME': <TokenType.DATETIME: 'DATETIME'>, 'INT4RANGE': <TokenType.INT4RANGE: 'INT4RANGE'>, 'INT4MULTIRANGE': <TokenType.INT4MULTIRANGE: 'INT4MULTIRANGE'>, 'INT8RANGE': <TokenType.INT8RANGE: 'INT8RANGE'>, 'INT8MULTIRANGE': <TokenType.INT8MULTIRANGE: 'INT8MULTIRANGE'>, 'NUMRANGE': <TokenType.NUMRANGE: 'NUMRANGE'>, 'NUMMULTIRANGE': <TokenType.NUMMULTIRANGE: 'NUMMULTIRANGE'>, 'TSRANGE': <TokenType.TSRANGE: 'TSRANGE'>, 'TSMULTIRANGE': <TokenType.TSMULTIRANGE: 'TSMULTIRANGE'>, 'TSTZRANGE': <TokenType.TSTZRANGE: 'TSTZRANGE'>, 'TSTZMULTIRANGE': <TokenType.TSTZMULTIRANGE: 'TSTZMULTIRANGE'>, 'DATERANGE': <TokenType.DATERANGE: 'DATERANGE'>, 'DATEMULTIRANGE': <TokenType.DATEMULTIRANGE: 'DATEMULTIRANGE'>, 'UNIQUE': <TokenType.UNIQUE: 'UNIQUE'>, 'STRUCT': <TokenType.STRUCT: 'STRUCT'>, 'VARIANT': <TokenType.VARIANT: 'VARIANT'>, 'ALTER': <TokenType.ALTER: 'ALTER'>, 'ANALYZE': <TokenType.COMMAND: 'COMMAND'>, 'CALL': <TokenType.COMMAND: 'COMMAND'>, 'COMMENT': <TokenType.COMMENT: 'COMMENT'>, 'COPY': <TokenType.COMMAND: 'COMMAND'>, 'EXPLAIN': <TokenType.COMMAND: 'COMMAND'>, 'GRANT': <TokenType.COMMAND: 'COMMAND'>, 'OPTIMIZE': <TokenType.COMMAND: 'COMMAND'>, 'PREPARE': <TokenType.COMMAND: 'COMMAND'>, 'TRUNCATE': <TokenType.COMMAND: 'COMMAND'>, 'VACUUM': <TokenType.COMMAND: 'COMMAND'>, 'USER-DEFINED': <TokenType.USERDEFINED: 'USERDEFINED'>, 'FOR VERSION': <TokenType.VERSION_SNAPSHOT: 'VERSION_SNAPSHOT'>, 'FOR TIMESTAMP': <TokenType.TIMESTAMP_SNAPSHOT: 'TIMESTAMP_SNAPSHOT'>, ':=': <TokenType.EQ: 'EQ'>, '//': <TokenType.DIV: 'DIV'>, 'ATTACH': <TokenType.COMMAND: 'COMMAND'>, 'BITSTRING': <TokenType.BIT: 'BIT'>, 'BPCHAR': <TokenType.TEXT: 'TEXT'>, 'CHARACTER VARYING': <TokenType.TEXT: 'TEXT'>, 'EXCLUDE': <TokenType.EXCEPT: 'EXCEPT'>, 'HUGEINT': <TokenType.INT128: 'INT128'>, 'INT1': <TokenType.TINYINT: 'TINYINT'>, 'LOGICAL': <TokenType.BOOLEAN: 'BOOLEAN'>, 'PIVOT_WIDER': <TokenType.PIVOT: 'PIVOT'>, 'SIGNED': <TokenType.INT: 'INT'>, 'UBIGINT': <TokenType.UBIGINT: 'UBIGINT'>, 'UINTEGER': <TokenType.UINT: 'UINT'>, 'USMALLINT': <TokenType.USMALLINT: 'USMALLINT'>, 'UTINYINT': <TokenType.UTINYINT: 'UTINYINT'>}
class DuckDB.Parser(sqlglot.parser.Parser):
139    class Parser(parser.Parser):
140        CONCAT_NULL_OUTPUTS_STRING = True
141
142        BITWISE = {
143            **parser.Parser.BITWISE,
144            TokenType.TILDA: exp.RegexpLike,
145        }
146
147        FUNCTIONS = {
148            **parser.Parser.FUNCTIONS,
149            "ARRAY_LENGTH": exp.ArraySize.from_arg_list,
150            "ARRAY_SORT": exp.SortArray.from_arg_list,
151            "ARRAY_REVERSE_SORT": _sort_array_reverse,
152            "DATEDIFF": _parse_date_diff,
153            "DATE_DIFF": _parse_date_diff,
154            "DATE_TRUNC": date_trunc_to_time,
155            "DATETRUNC": date_trunc_to_time,
156            "EPOCH": exp.TimeToUnix.from_arg_list,
157            "EPOCH_MS": lambda args: exp.UnixToTime(
158                this=exp.Div(this=seq_get(args, 0), expression=exp.Literal.number(1000))
159            ),
160            "LIST_REVERSE_SORT": _sort_array_reverse,
161            "LIST_SORT": exp.SortArray.from_arg_list,
162            "LIST_VALUE": exp.Array.from_arg_list,
163            "MEDIAN": lambda args: exp.PercentileCont(
164                this=seq_get(args, 0), expression=exp.Literal.number(0.5)
165            ),
166            "QUANTILE_CONT": exp.PercentileCont.from_arg_list,
167            "QUANTILE_DISC": exp.PercentileDisc.from_arg_list,
168            "REGEXP_EXTRACT": lambda args: exp.RegexpExtract(
169                this=seq_get(args, 0), expression=seq_get(args, 1), group=seq_get(args, 2)
170            ),
171            "REGEXP_MATCHES": exp.RegexpLike.from_arg_list,
172            "STRFTIME": format_time_lambda(exp.TimeToStr, "duckdb"),
173            "STRING_SPLIT": exp.Split.from_arg_list,
174            "STRING_SPLIT_REGEX": exp.RegexpSplit.from_arg_list,
175            "STRING_TO_ARRAY": exp.Split.from_arg_list,
176            "STRPTIME": format_time_lambda(exp.StrToTime, "duckdb"),
177            "STRUCT_PACK": exp.Struct.from_arg_list,
178            "STR_SPLIT": exp.Split.from_arg_list,
179            "STR_SPLIT_REGEX": exp.RegexpSplit.from_arg_list,
180            "TO_TIMESTAMP": exp.UnixToTime.from_arg_list,
181            "UNNEST": exp.Explode.from_arg_list,
182            "XOR": binary_from_function(exp.BitwiseXor),
183        }
184
185        FUNCTION_PARSERS = {
186            **parser.Parser.FUNCTION_PARSERS,
187            "DECODE": lambda self: self.expression(
188                exp.Decode, this=self._parse_conjunction(), charset=exp.Literal.string("utf-8")
189            ),
190            "ENCODE": lambda self: self.expression(
191                exp.Encode, this=self._parse_conjunction(), charset=exp.Literal.string("utf-8")
192            ),
193        }
194
195        TABLE_ALIAS_TOKENS = parser.Parser.TABLE_ALIAS_TOKENS - {
196            TokenType.SEMI,
197            TokenType.ANTI,
198        }
199
200        def _parse_types(
201            self, check_func: bool = False, schema: bool = False, allow_identifiers: bool = True
202        ) -> t.Optional[exp.Expression]:
203            this = super()._parse_types(
204                check_func=check_func, schema=schema, allow_identifiers=allow_identifiers
205            )
206
207            # DuckDB treats NUMERIC and DECIMAL without precision as DECIMAL(18, 3)
208            # See: https://duckdb.org/docs/sql/data_types/numeric
209            if (
210                isinstance(this, exp.DataType)
211                and this.is_type("numeric", "decimal")
212                and not this.expressions
213            ):
214                return exp.DataType.build("DECIMAL(18, 3)")
215
216            return this
217
218        def _parse_struct_types(self) -> t.Optional[exp.Expression]:
219            return self._parse_field_def()
220
221        def _pivot_column_names(self, aggregations: t.List[exp.Expression]) -> t.List[str]:
222            if len(aggregations) == 1:
223                return super()._pivot_column_names(aggregations)
224            return pivot_column_names(aggregations, dialect="duckdb")

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: Determines 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
CONCAT_NULL_OUTPUTS_STRING = True
BITWISE = {<TokenType.AMP: 'AMP'>: <class 'sqlglot.expressions.BitwiseAnd'>, <TokenType.CARET: 'CARET'>: <class 'sqlglot.expressions.BitwiseXor'>, <TokenType.PIPE: 'PIPE'>: <class 'sqlglot.expressions.BitwiseOr'>, <TokenType.DPIPE: 'DPIPE'>: <class 'sqlglot.expressions.SafeDPipe'>, <TokenType.TILDA: 'TILDA'>: <class 'sqlglot.expressions.RegexpLike'>}
FUNCTIONS = {'ABS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Abs'>>, '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'>>, '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_CONTAINS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayContains'>>, '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_JOIN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayJoin'>>, 'ARRAY_SIZE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArraySize'>>, 'ARRAY_SORT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SortArray'>>, 'ARRAY_SUM': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArraySum'>>, 'ARRAY_UNION_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayUnionAgg'>>, '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'>>, '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'>>, 'CONCAT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Concat'>>, 'CONCAT_WS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ConcatWs'>>, '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'>>, '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': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Date'>>, 'DATE_ADD': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateAdd'>>, 'DATEDIFF': <function _parse_date_diff>, 'DATE_DIFF': <function _parse_date_diff>, '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': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateSub'>>, 'DATE_TO_DATE_STR': <function Parser.<lambda>>, 'DATE_TO_DI': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateToDi'>>, 'DATE_TRUNC': <function date_trunc_to_time>, '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': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Day'>>, 'DAY_OF_MONTH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DayOfMonth'>>, 'DAYOFMONTH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DayOfMonth'>>, 'DAY_OF_WEEK': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DayOfWeek'>>, 'DAYOFWEEK': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DayOfWeek'>>, 'DAY_OF_YEAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DayOfYear'>>, 'DAYOFYEAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DayOfYear'>>, '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'>>, 'EXTRACT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Extract'>>, 'FIRST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.First'>>, '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_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': <bound method Func.from_arg_list of <class 'sqlglot.expressions.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'>>, 'INITCAP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Initcap'>>, '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': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONExtract'>>, 'JSON_EXTRACT_SCALAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONExtractScalar'>>, '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_TABLE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONTable'>>, 'LAST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Last'>>, 'LAST_DATE_OF_MONTH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LastDateOfMonth'>>, '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': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Log'>>, 'LOG10': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Log10'>>, 'LOG2': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Log2'>>, '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': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Lower'>>, 'LCASE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Lower'>>, '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': <bound method Func.from_arg_list of <class 'sqlglot.expressions.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': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Month'>>, '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'>>, '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'>>, 'POWER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Pow'>>, 'POW': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Pow'>>, 'QUANTILE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Quantile'>>, '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 DuckDB.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_CONCAT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SafeConcat'>>, 'SAFE_DIVIDE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SafeDivide'>>, 'SET_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SetAgg'>>, 'SORT_ARRAY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SortArray'>>, 'SPLIT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Split'>>, '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': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StrToMap'>>, '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'>>, '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_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': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Timestamp'>>, 'TIMESTAMP_ADD': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimestampAdd'>>, 'TIMESTAMP_DIFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimestampDiff'>>, '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_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'>>, '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_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_TO_DATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TsOrDsToDate'>>, 'TS_OR_DS_TO_DATE_STR': <function Parser.<lambda>>, 'UNHEX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Unhex'>>, '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': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Upper'>>, 'UCASE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Upper'>>, 'VAR_MAP': <function parse_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': <bound method Func.from_arg_list of <class 'sqlglot.expressions.WeekOfYear'>>, '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': <function binary_from_function.<locals>.<lambda>>, 'YEAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Year'>>, 'GLOB': <function Parser.<lambda>>, 'LIKE': <function parse_like>, 'ARRAY_LENGTH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArraySize'>>, 'ARRAY_REVERSE_SORT': <function _sort_array_reverse>, 'DATETRUNC': <function date_trunc_to_time>, 'EPOCH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeToUnix'>>, 'EPOCH_MS': <function DuckDB.Parser.<lambda>>, 'LIST_REVERSE_SORT': <function _sort_array_reverse>, 'LIST_SORT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SortArray'>>, 'LIST_VALUE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Array'>>, 'MEDIAN': <function DuckDB.Parser.<lambda>>, 'QUANTILE_CONT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.PercentileCont'>>, 'QUANTILE_DISC': <bound method Func.from_arg_list of <class 'sqlglot.expressions.PercentileDisc'>>, 'REGEXP_MATCHES': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RegexpLike'>>, 'STRFTIME': <function format_time_lambda.<locals>._format_time>, 'STRING_SPLIT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Split'>>, 'STRING_SPLIT_REGEX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RegexpSplit'>>, 'STRING_TO_ARRAY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Split'>>, 'STRPTIME': <function format_time_lambda.<locals>._format_time>, 'STRUCT_PACK': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Struct'>>, 'STR_SPLIT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Split'>>, 'STR_SPLIT_REGEX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RegexpSplit'>>, 'TO_TIMESTAMP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.UnixToTime'>>, 'UNNEST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Explode'>>}
FUNCTION_PARSERS = {'ANY_VALUE': <function Parser.<lambda>>, 'CAST': <function Parser.<lambda>>, 'CONCAT': <function Parser.<lambda>>, 'CONCAT_WS': <function Parser.<lambda>>, 'CONVERT': <function Parser.<lambda>>, 'DECODE': <function DuckDB.Parser.<lambda>>, 'EXTRACT': <function Parser.<lambda>>, 'JSON_OBJECT': <function Parser.<lambda>>, 'LOG': <function Parser.<lambda>>, 'MATCH': <function Parser.<lambda>>, 'OPENJSON': <function Parser.<lambda>>, 'POSITION': <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>>, 'ENCODE': <function DuckDB.Parser.<lambda>>}
TABLE_ALIAS_TOKENS = {<TokenType.LOAD: 'LOAD'>, <TokenType.FUNCTION: 'FUNCTION'>, <TokenType.JSON: 'JSON'>, <TokenType.DATEMULTIRANGE: 'DATEMULTIRANGE'>, <TokenType.CURRENT_TIME: 'CURRENT_TIME'>, <TokenType.TEMPORARY: 'TEMPORARY'>, <TokenType.BEGIN: 'BEGIN'>, <TokenType.NULLABLE: 'NULLABLE'>, <TokenType.NESTED: 'NESTED'>, <TokenType.VIEW: 'VIEW'>, <TokenType.IS: 'IS'>, <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, <TokenType.REFERENCES: 'REFERENCES'>, <TokenType.UTINYINT: 'UTINYINT'>, <TokenType.NULL: 'NULL'>, <TokenType.PARTITION: 'PARTITION'>, <TokenType.TEXT: 'TEXT'>, <TokenType.ISNULL: 'ISNULL'>, <TokenType.OBJECT_IDENTIFIER: 'OBJECT_IDENTIFIER'>, <TokenType.TIME: 'TIME'>, <TokenType.COMMENT: 'COMMENT'>, <TokenType.CONSTRAINT: 'CONSTRAINT'>, <TokenType.USMALLINT: 'USMALLINT'>, <TokenType.HSTORE: 'HSTORE'>, <TokenType.FORMAT: 'FORMAT'>, <TokenType.INDEX: 'INDEX'>, <TokenType.MONEY: 'MONEY'>, <TokenType.HLLSKETCH: 'HLLSKETCH'>, <TokenType.COMMIT: 'COMMIT'>, <TokenType.MERGE: 'MERGE'>, <TokenType.TINYTEXT: 'TINYTEXT'>, <TokenType.DATERANGE: 'DATERANGE'>, <TokenType.ROWS: 'ROWS'>, <TokenType.RANGE: 'RANGE'>, <TokenType.TIMETZ: 'TIMETZ'>, <TokenType.OVERLAPS: 'OVERLAPS'>, <TokenType.TSTZMULTIRANGE: 'TSTZMULTIRANGE'>, <TokenType.JSONB: 'JSONB'>, <TokenType.BIGINT: 'BIGINT'>, <TokenType.DESC: 'DESC'>, <TokenType.UINT256: 'UINT256'>, <TokenType.NUMRANGE: 'NUMRANGE'>, <TokenType.BIT: 'BIT'>, <TokenType.EXECUTE: 'EXECUTE'>, <TokenType.UNIQUEIDENTIFIER: 'UNIQUEIDENTIFIER'>, <TokenType.VARIANT: 'VARIANT'>, <TokenType.GEOMETRY: 'GEOMETRY'>, <TokenType.SERIAL: 'SERIAL'>, <TokenType.DATE: 'DATE'>, <TokenType.CURRENT_USER: 'CURRENT_USER'>, <TokenType.BINARY: 'BINARY'>, <TokenType.NCHAR: 'NCHAR'>, <TokenType.PIVOT: 'PIVOT'>, <TokenType.SHOW: 'SHOW'>, <TokenType.KEEP: 'KEEP'>, <TokenType.INT256: 'INT256'>, <TokenType.UUID: 'UUID'>, <TokenType.TSRANGE: 'TSRANGE'>, <TokenType.FIXEDSTRING: 'FIXEDSTRING'>, <TokenType.SMALLMONEY: 'SMALLMONEY'>, <TokenType.TIMESTAMP: 'TIMESTAMP'>, <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, <TokenType.UDECIMAL: 'UDECIMAL'>, <TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>, <TokenType.IPPREFIX: 'IPPREFIX'>, <TokenType.VARCHAR: 'VARCHAR'>, <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>, <TokenType.BOOLEAN: 'BOOLEAN'>, <TokenType.UBIGINT: 'UBIGINT'>, <TokenType.TRUE: 'TRUE'>, <TokenType.DEFAULT: 'DEFAULT'>, <TokenType.COLUMN: 'COLUMN'>, <TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>, <TokenType.ANY: 'ANY'>, <TokenType.FILTER: 'FILTER'>, <TokenType.FALSE: 'FALSE'>, <TokenType.VOLATILE: 'VOLATILE'>, <TokenType.TINYBLOB: 'TINYBLOB'>, <TokenType.SCHEMA: 'SCHEMA'>, <TokenType.GEOGRAPHY: 'GEOGRAPHY'>, <TokenType.PRAGMA: 'PRAGMA'>, <TokenType.FLOAT: 'FLOAT'>, <TokenType.NEXT: 'NEXT'>, <TokenType.IPADDRESS: 'IPADDRESS'>, <TokenType.PROCEDURE: 'PROCEDURE'>, <TokenType.TINYINT: 'TINYINT'>, <TokenType.INT4MULTIRANGE: 'INT4MULTIRANGE'>, <TokenType.SMALLINT: 'SMALLINT'>, <TokenType.BIGSERIAL: 'BIGSERIAL'>, <TokenType.MEDIUMINT: 'MEDIUMINT'>, <TokenType.IMAGE: 'IMAGE'>, <TokenType.INT8MULTIRANGE: 'INT8MULTIRANGE'>, <TokenType.SETTINGS: 'SETTINGS'>, <TokenType.INET: 'INET'>, <TokenType.SET: 'SET'>, <TokenType.SMALLSERIAL: 'SMALLSERIAL'>, <TokenType.CHAR: 'CHAR'>, <TokenType.SUPER: 'SUPER'>, <TokenType.MAP: 'MAP'>, <TokenType.UNIQUE: 'UNIQUE'>, <TokenType.INT128: 'INT128'>, <TokenType.OVERWRITE: 'OVERWRITE'>, <TokenType.LOWCARDINALITY: 'LOWCARDINALITY'>, <TokenType.CASE: 'CASE'>, <TokenType.TSMULTIRANGE: 'TSMULTIRANGE'>, <TokenType.PERCENT: 'PERCENT'>, <TokenType.USERDEFINED: 'USERDEFINED'>, <TokenType.ESCAPE: 'ESCAPE'>, <TokenType.CURRENT_TIMESTAMP: 'CURRENT_TIMESTAMP'>, <TokenType.UNPIVOT: 'UNPIVOT'>, <TokenType.INT: 'INT'>, <TokenType.UMEDIUMINT: 'UMEDIUMINT'>, <TokenType.INT4RANGE: 'INT4RANGE'>, <TokenType.ENUM16: 'ENUM16'>, <TokenType.END: 'END'>, <TokenType.CURRENT_DATETIME: 'CURRENT_DATETIME'>, <TokenType.EXISTS: 'EXISTS'>, <TokenType.FIRST: 'FIRST'>, <TokenType.DELETE: 'DELETE'>, <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>, <TokenType.INTERVAL: 'INTERVAL'>, <TokenType.LONGBLOB: 'LONGBLOB'>, <TokenType.NVARCHAR: 'NVARCHAR'>, <TokenType.KILL: 'KILL'>, <TokenType.NUMMULTIRANGE: 'NUMMULTIRANGE'>, <TokenType.CURRENT_DATE: 'CURRENT_DATE'>, <TokenType.TSTZRANGE: 'TSTZRANGE'>, <TokenType.DATETIME64: 'DATETIME64'>, <TokenType.DATETIME: 'DATETIME'>, <TokenType.UINT: 'UINT'>, <TokenType.VAR: 'VAR'>, <TokenType.XML: 'XML'>, <TokenType.ENUM8: 'ENUM8'>, <TokenType.ENUM: 'ENUM'>, <TokenType.PSEUDO_TYPE: 'PSEUDO_TYPE'>, <TokenType.COMMAND: 'COMMAND'>, <TokenType.TOP: 'TOP'>, <TokenType.DOUBLE: 'DOUBLE'>, <TokenType.SOME: 'SOME'>, <TokenType.UPDATE: 'UPDATE'>, <TokenType.VARBINARY: 'VARBINARY'>, <TokenType.DATABASE: 'DATABASE'>, <TokenType.TABLE: 'TABLE'>, <TokenType.OBJECT: 'OBJECT'>, <TokenType.CACHE: 'CACHE'>, <TokenType.ORDINALITY: 'ORDINALITY'>, <TokenType.DICTIONARY: 'DICTIONARY'>, <TokenType.ASC: 'ASC'>, <TokenType.ROWVERSION: 'ROWVERSION'>, <TokenType.INT8RANGE: 'INT8RANGE'>, <TokenType.DIV: 'DIV'>, <TokenType.ROW: 'ROW'>, <TokenType.LONGTEXT: 'LONGTEXT'>, <TokenType.DECIMAL: 'DECIMAL'>, <TokenType.ARRAY: 'ARRAY'>, <TokenType.UINT128: 'UINT128'>, <TokenType.STRUCT: 'STRUCT'>, <TokenType.YEAR: 'YEAR'>, <TokenType.COLLATE: 'COLLATE'>, <TokenType.UNKNOWN: 'UNKNOWN'>, <TokenType.DESCRIBE: 'DESCRIBE'>, <TokenType.ALL: 'ALL'>}
TOKENIZER_CLASS: Type[sqlglot.tokens.Tokenizer] = <class 'DuckDB.Tokenizer'>
SUPPORTS_USER_DEFINED_TYPES = False
NULL_ORDERING: str = 'nulls_are_last'
SHOW_TRIE: Dict = {}
SET_TRIE: Dict = {'GLOBAL': {0: True}, 'LOCAL': {0: True}, 'SESSION': {0: True}, 'TRANSACTION': {0: True}}
FORMAT_TRIE: Dict = {}
TIME_TRIE: Dict = {}
Inherited Members
sqlglot.parser.Parser
Parser
NO_PAREN_FUNCTIONS
STRUCT_TYPE_TOKENS
NESTED_TYPE_TOKENS
ENUM_TYPE_TOKENS
TYPE_TOKENS
SIGNED_TO_UNSIGNED_TYPE_TOKEN
SUBQUERY_PREDICATES
RESERVED_KEYWORDS
DB_CREATABLES
CREATABLES
ID_VAR_TOKENS
INTERVAL_VARS
COMMENT_TABLE_ALIAS_TOKENS
UPDATE_ALIAS_TOKENS
TRIM_TYPES
FUNC_TOKENS
CONJUNCTION
EQUALITY
COMPARISON
TERM
FACTOR
TIMES
TIMESTAMPS
SET_OPERATIONS
JOIN_METHODS
JOIN_SIDES
JOIN_KINDS
JOIN_HINTS
LAMBDAS
COLUMN_OPERATORS
EXPRESSION_PARSERS
STATEMENT_PARSERS
UNARY_PARSERS
PRIMARY_PARSERS
PLACEHOLDER_PARSERS
RANGE_PARSERS
PROPERTY_PARSERS
CONSTRAINT_PARSERS
ALTER_PARSERS
SCHEMA_UNNAMED_CONSTRAINTS
NO_PAREN_FUNCTION_PARSERS
INVALID_FUNC_NAME_TOKENS
FUNCTIONS_WITH_ALIASED_ARGS
QUERY_MODIFIER_PARSERS
SET_PARSERS
SHOW_PARSERS
TYPE_LITERAL_PARSERS
MODIFIABLES
DDL_SELECT_TOKENS
PRE_VOLATILE_TOKENS
TRANSACTION_KIND
TRANSACTION_CHARACTERISTICS
INSERT_ALTERNATIVES
CLONE_KEYWORDS
CLONE_KINDS
OPCLASS_FOLLOW_KEYWORDS
TABLE_INDEX_HINT_TOKENS
WINDOW_ALIAS_TOKENS
WINDOW_BEFORE_PAREN_TOKENS
WINDOW_SIDES
FETCH_TOKENS
ADD_CONSTRAINT_TOKENS
DISTINCT_TOKENS
NULL_TOKENS
UNNEST_OFFSET_ALIAS_TOKENS
STRICT_CAST
PREFIXED_PIVOT_COLUMNS
IDENTIFY_PIVOT_STRINGS
LOG_BASE_FIRST
LOG_DEFAULTS_TO_LN
ALTER_TABLE_ADD_COLUMN_KEYWORD
TABLESAMPLE_CSV
SET_REQUIRES_ASSIGNMENT_DELIMITER
TRIM_PATTERN_FIRST
INDEX_OFFSET
UNNEST_COLUMN_ONLY
ALIAS_POST_TABLESAMPLE
STRICT_STRING_CONCAT
NORMALIZE_FUNCTIONS
FORMAT_MAPPING
TIME_MAPPING
error_level
error_message_context
max_errors
reset
parse
parse_into
check_errors
raise_error
expression
validate_expression
errors
sql
class DuckDB.Generator(sqlglot.generator.Generator):
226    class Generator(generator.Generator):
227        JOIN_HINTS = False
228        TABLE_HINTS = False
229        QUERY_HINTS = False
230        LIMIT_FETCH = "LIMIT"
231        STRUCT_DELIMITER = ("(", ")")
232        RENAME_TABLE_WITH_DB = False
233        NVL2_SUPPORTED = False
234        SEMI_ANTI_JOIN_WITH_SIDE = False
235
236        TRANSFORMS = {
237            **generator.Generator.TRANSFORMS,
238            exp.ApproxDistinct: approx_count_distinct_sql,
239            exp.Array: lambda self, e: self.func("ARRAY", e.expressions[0])
240            if e.expressions and e.expressions[0].find(exp.Select)
241            else inline_array_sql(self, e),
242            exp.ArraySize: rename_func("ARRAY_LENGTH"),
243            exp.ArraySort: _array_sort_sql,
244            exp.ArraySum: rename_func("LIST_SUM"),
245            exp.BitwiseXor: rename_func("XOR"),
246            exp.CommentColumnConstraint: no_comment_column_constraint_sql,
247            exp.CurrentDate: lambda self, e: "CURRENT_DATE",
248            exp.CurrentTime: lambda self, e: "CURRENT_TIME",
249            exp.CurrentTimestamp: lambda self, e: "CURRENT_TIMESTAMP",
250            exp.DayOfMonth: rename_func("DAYOFMONTH"),
251            exp.DayOfWeek: rename_func("DAYOFWEEK"),
252            exp.DayOfYear: rename_func("DAYOFYEAR"),
253            exp.DataType: _datatype_sql,
254            exp.Date: _date_sql,
255            exp.DateAdd: _date_delta_sql,
256            exp.DateFromParts: rename_func("MAKE_DATE"),
257            exp.DateSub: _date_delta_sql,
258            exp.DateDiff: lambda self, e: self.func(
259                "DATE_DIFF", f"'{e.args.get('unit') or 'day'}'", e.expression, e.this
260            ),
261            exp.DateStrToDate: datestrtodate_sql,
262            exp.DateToDi: lambda self, e: f"CAST(STRFTIME({self.sql(e, 'this')}, {DuckDB.DATEINT_FORMAT}) AS INT)",
263            exp.Decode: lambda self, e: encode_decode_sql(self, e, "DECODE", replace=False),
264            exp.DiToDate: lambda self, e: f"CAST(STRPTIME(CAST({self.sql(e, 'this')} AS TEXT), {DuckDB.DATEINT_FORMAT}) AS DATE)",
265            exp.Encode: lambda self, e: encode_decode_sql(self, e, "ENCODE", replace=False),
266            exp.Explode: rename_func("UNNEST"),
267            exp.IntDiv: lambda self, e: self.binary(e, "//"),
268            exp.IsNan: rename_func("ISNAN"),
269            exp.JSONExtract: arrow_json_extract_sql,
270            exp.JSONExtractScalar: arrow_json_extract_scalar_sql,
271            exp.JSONFormat: _json_format_sql,
272            exp.JSONBExtract: arrow_json_extract_sql,
273            exp.JSONBExtractScalar: arrow_json_extract_scalar_sql,
274            exp.LogicalOr: rename_func("BOOL_OR"),
275            exp.LogicalAnd: rename_func("BOOL_AND"),
276            exp.MonthsBetween: lambda self, e: self.func(
277                "DATEDIFF",
278                "'month'",
279                exp.cast(e.expression, "timestamp", copy=True),
280                exp.cast(e.this, "timestamp", copy=True),
281            ),
282            exp.ParseJSON: rename_func("JSON"),
283            exp.PercentileCont: rename_func("QUANTILE_CONT"),
284            exp.PercentileDisc: rename_func("QUANTILE_DISC"),
285            exp.Properties: no_properties_sql,
286            exp.RegexpExtract: regexp_extract_sql,
287            exp.RegexpReplace: regexp_replace_sql,
288            exp.RegexpLike: rename_func("REGEXP_MATCHES"),
289            exp.RegexpSplit: rename_func("STR_SPLIT_REGEX"),
290            exp.SafeDivide: no_safe_divide_sql,
291            exp.Split: rename_func("STR_SPLIT"),
292            exp.SortArray: _sort_array_sql,
293            exp.StrPosition: str_position_sql,
294            exp.StrToDate: lambda self, e: f"CAST({str_to_time_sql(self, e)} AS DATE)",
295            exp.StrToTime: str_to_time_sql,
296            exp.StrToUnix: lambda self, e: f"EPOCH(STRPTIME({self.sql(e, 'this')}, {self.format_time(e)}))",
297            exp.Struct: _struct_sql,
298            exp.TimestampTrunc: timestamptrunc_sql,
299            exp.TimeStrToDate: lambda self, e: f"CAST({self.sql(e, 'this')} AS DATE)",
300            exp.TimeStrToTime: timestrtotime_sql,
301            exp.TimeStrToUnix: lambda self, e: f"EPOCH(CAST({self.sql(e, 'this')} AS TIMESTAMP))",
302            exp.TimeToStr: lambda self, e: f"STRFTIME({self.sql(e, 'this')}, {self.format_time(e)})",
303            exp.TimeToUnix: rename_func("EPOCH"),
304            exp.TsOrDiToDi: lambda self, e: f"CAST(SUBSTR(REPLACE(CAST({self.sql(e, 'this')} AS TEXT), '-', ''), 1, 8) AS INT)",
305            exp.TsOrDsAdd: _ts_or_ds_add_sql,
306            exp.TsOrDsToDate: ts_or_ds_to_date_sql("duckdb"),
307            exp.UnixToStr: lambda self, e: f"STRFTIME(TO_TIMESTAMP({self.sql(e, 'this')}), {self.format_time(e)})",
308            exp.UnixToTime: rename_func("TO_TIMESTAMP"),
309            exp.UnixToTimeStr: lambda self, e: f"CAST(TO_TIMESTAMP({self.sql(e, 'this')}) AS TEXT)",
310            exp.VariancePop: rename_func("VAR_POP"),
311            exp.WeekOfYear: rename_func("WEEKOFYEAR"),
312            exp.Xor: bool_xor_sql,
313        }
314
315        TYPE_MAPPING = {
316            **generator.Generator.TYPE_MAPPING,
317            exp.DataType.Type.BINARY: "BLOB",
318            exp.DataType.Type.CHAR: "TEXT",
319            exp.DataType.Type.FLOAT: "REAL",
320            exp.DataType.Type.NCHAR: "TEXT",
321            exp.DataType.Type.NVARCHAR: "TEXT",
322            exp.DataType.Type.UINT: "UINTEGER",
323            exp.DataType.Type.VARBINARY: "BLOB",
324            exp.DataType.Type.VARCHAR: "TEXT",
325        }
326
327        STAR_MAPPING = {**generator.Generator.STAR_MAPPING, "except": "EXCLUDE"}
328
329        UNWRAPPED_INTERVAL_VALUES = (exp.Column, exp.Literal, exp.Paren)
330
331        PROPERTIES_LOCATION = {
332            **generator.Generator.PROPERTIES_LOCATION,
333            exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED,
334        }
335
336        def interval_sql(self, expression: exp.Interval) -> str:
337            multiplier: t.Optional[int] = None
338            unit = expression.text("unit").lower()
339
340            if unit.startswith("week"):
341                multiplier = 7
342            if unit.startswith("quarter"):
343                multiplier = 90
344
345            if multiplier:
346                return f"({multiplier} * {super().interval_sql(exp.Interval(this=expression.this.copy(), unit=exp.var('day')))})"
347
348            return super().interval_sql(expression)
349
350        def tablesample_sql(
351            self, expression: exp.TableSample, seed_prefix: str = "SEED", sep: str = " AS "
352        ) -> str:
353            return super().tablesample_sql(expression, seed_prefix="REPEATABLE", sep=sep)

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

Arguments:
  • pretty: Whether or not 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 or not to normalize identifiers to lowercase. Default: False.
  • pad: Determines the pad size in a formatted string. Default: 2.
  • indent: Determines the indentation size in a formatted string. Default: 2.
  • normalize_functions: Whether or not to normalize all 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: Determines whether or not 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 or not to preserve comments in the output SQL code. Default: True
JOIN_HINTS = False
TABLE_HINTS = False
QUERY_HINTS = False
LIMIT_FETCH = 'LIMIT'
STRUCT_DELIMITER = ('(', ')')
RENAME_TABLE_WITH_DB = False
NVL2_SUPPORTED = False
SEMI_ANTI_JOIN_WITH_SIDE = False
TRANSFORMS = {<class 'sqlglot.expressions.DateAdd'>: <function _date_delta_sql>, <class 'sqlglot.expressions.TsOrDsAdd'>: <function _ts_or_ds_add_sql>, <class 'sqlglot.expressions.CaseSpecificColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CharacterSetColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CharacterSetProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CheckColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ClusteredColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CollateColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CopyGrantsProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CommentColumnConstraint'>: <function no_comment_column_constraint_sql>, <class 'sqlglot.expressions.DateFormatColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.DefaultColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.EncodeColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ExecuteAsProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ExternalProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.HeapProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.InlineLengthColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.IntervalSpan'>: <function 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.NoPrimaryIndexProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.NonClusteredColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.NotForReplicationColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.OnCommitProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.OnProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.OnUpdateColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.PathColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ReturnsProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SampleProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SetProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SettingsProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SqlSecurityProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.StabilityProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.TemporaryProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ToTableProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.TransientProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.TitleColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.UppercaseColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.VarMap'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.VolatileProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.WithJournalTableProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ApproxDistinct'>: <function approx_count_distinct_sql>, <class 'sqlglot.expressions.Array'>: <function DuckDB.Generator.<lambda>>, <class 'sqlglot.expressions.ArraySize'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.ArraySort'>: <function _array_sort_sql>, <class 'sqlglot.expressions.ArraySum'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.BitwiseXor'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.CurrentDate'>: <function DuckDB.Generator.<lambda>>, <class 'sqlglot.expressions.CurrentTime'>: <function DuckDB.Generator.<lambda>>, <class 'sqlglot.expressions.CurrentTimestamp'>: <function DuckDB.Generator.<lambda>>, <class 'sqlglot.expressions.DayOfMonth'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.DayOfWeek'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.DayOfYear'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.DataType'>: <function _datatype_sql>, <class 'sqlglot.expressions.Date'>: <function _date_sql>, <class 'sqlglot.expressions.DateFromParts'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.DateSub'>: <function _date_delta_sql>, <class 'sqlglot.expressions.DateDiff'>: <function DuckDB.Generator.<lambda>>, <class 'sqlglot.expressions.DateStrToDate'>: <function datestrtodate_sql>, <class 'sqlglot.expressions.DateToDi'>: <function DuckDB.Generator.<lambda>>, <class 'sqlglot.expressions.Decode'>: <function DuckDB.Generator.<lambda>>, <class 'sqlglot.expressions.DiToDate'>: <function DuckDB.Generator.<lambda>>, <class 'sqlglot.expressions.Encode'>: <function DuckDB.Generator.<lambda>>, <class 'sqlglot.expressions.Explode'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.IntDiv'>: <function DuckDB.Generator.<lambda>>, <class 'sqlglot.expressions.IsNan'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.JSONExtract'>: <function arrow_json_extract_sql>, <class 'sqlglot.expressions.JSONExtractScalar'>: <function arrow_json_extract_scalar_sql>, <class 'sqlglot.expressions.JSONFormat'>: <function _json_format_sql>, <class 'sqlglot.expressions.JSONBExtract'>: <function arrow_json_extract_sql>, <class 'sqlglot.expressions.JSONBExtractScalar'>: <function arrow_json_extract_scalar_sql>, <class 'sqlglot.expressions.LogicalOr'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.LogicalAnd'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.MonthsBetween'>: <function DuckDB.Generator.<lambda>>, <class 'sqlglot.expressions.ParseJSON'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.PercentileCont'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.PercentileDisc'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.Properties'>: <function no_properties_sql>, <class 'sqlglot.expressions.RegexpExtract'>: <function regexp_extract_sql>, <class 'sqlglot.expressions.RegexpReplace'>: <function regexp_replace_sql>, <class 'sqlglot.expressions.RegexpLike'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.RegexpSplit'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.SafeDivide'>: <function no_safe_divide_sql>, <class 'sqlglot.expressions.Split'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.SortArray'>: <function _sort_array_sql>, <class 'sqlglot.expressions.StrPosition'>: <function str_position_sql>, <class 'sqlglot.expressions.StrToDate'>: <function DuckDB.Generator.<lambda>>, <class 'sqlglot.expressions.StrToTime'>: <function str_to_time_sql>, <class 'sqlglot.expressions.StrToUnix'>: <function DuckDB.Generator.<lambda>>, <class 'sqlglot.expressions.Struct'>: <function _struct_sql>, <class 'sqlglot.expressions.TimestampTrunc'>: <function timestamptrunc_sql>, <class 'sqlglot.expressions.TimeStrToDate'>: <function DuckDB.Generator.<lambda>>, <class 'sqlglot.expressions.TimeStrToTime'>: <function timestrtotime_sql>, <class 'sqlglot.expressions.TimeStrToUnix'>: <function DuckDB.Generator.<lambda>>, <class 'sqlglot.expressions.TimeToStr'>: <function DuckDB.Generator.<lambda>>, <class 'sqlglot.expressions.TimeToUnix'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.TsOrDiToDi'>: <function DuckDB.Generator.<lambda>>, <class 'sqlglot.expressions.TsOrDsToDate'>: <function ts_or_ds_to_date_sql.<locals>._ts_or_ds_to_date_sql>, <class 'sqlglot.expressions.UnixToStr'>: <function DuckDB.Generator.<lambda>>, <class 'sqlglot.expressions.UnixToTime'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.UnixToTimeStr'>: <function DuckDB.Generator.<lambda>>, <class 'sqlglot.expressions.VariancePop'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.WeekOfYear'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.Xor'>: <function bool_xor_sql>}
TYPE_MAPPING = {<Type.NCHAR: 'NCHAR'>: 'TEXT', <Type.NVARCHAR: 'NVARCHAR'>: 'TEXT', <Type.MEDIUMTEXT: 'MEDIUMTEXT'>: 'TEXT', <Type.LONGTEXT: 'LONGTEXT'>: 'TEXT', <Type.TINYTEXT: 'TINYTEXT'>: 'TEXT', <Type.MEDIUMBLOB: 'MEDIUMBLOB'>: 'BLOB', <Type.LONGBLOB: 'LONGBLOB'>: 'BLOB', <Type.TINYBLOB: 'TINYBLOB'>: 'BLOB', <Type.INET: 'INET'>: 'INET', <Type.BINARY: 'BINARY'>: 'BLOB', <Type.CHAR: 'CHAR'>: 'TEXT', <Type.FLOAT: 'FLOAT'>: 'REAL', <Type.UINT: 'UINT'>: 'UINTEGER', <Type.VARBINARY: 'VARBINARY'>: 'BLOB', <Type.VARCHAR: 'VARCHAR'>: 'TEXT'}
STAR_MAPPING = {'except': 'EXCLUDE', 'replace': 'REPLACE'}
UNWRAPPED_INTERVAL_VALUES = (<class 'sqlglot.expressions.Column'>, <class 'sqlglot.expressions.Literal'>, <class 'sqlglot.expressions.Paren'>)
PROPERTIES_LOCATION = {<class 'sqlglot.expressions.AlgorithmProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.AutoIncrementProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.BlockCompressionProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.CharacterSetProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.ChecksumProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.CollateProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <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.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.POST_SCHEMA: 'POST_SCHEMA'>, <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_WITH: 'POST_WITH'>, <class 'sqlglot.expressions.FreespaceProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.HeapProperty'>: <Location.POST_WITH: 'POST_WITH'>, <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.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.PartitionedByProperty'>: <Location.POST_WITH: 'POST_WITH'>, <class 'sqlglot.expressions.PrimaryKey'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.Property'>: <Location.POST_WITH: 'POST_WITH'>, <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.SortKeyProperty'>: <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.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.MergeTreeTTL'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.VolatileProperty'>: <Location.UNSUPPORTED: 'UNSUPPORTED'>, <class 'sqlglot.expressions.WithDataProperty'>: <Location.POST_EXPRESSION: 'POST_EXPRESSION'>, <class 'sqlglot.expressions.WithJournalTableProperty'>: <Location.POST_NAME: 'POST_NAME'>}
def interval_sql(self, expression: sqlglot.expressions.Interval) -> str:
336        def interval_sql(self, expression: exp.Interval) -> str:
337            multiplier: t.Optional[int] = None
338            unit = expression.text("unit").lower()
339
340            if unit.startswith("week"):
341                multiplier = 7
342            if unit.startswith("quarter"):
343                multiplier = 90
344
345            if multiplier:
346                return f"({multiplier} * {super().interval_sql(exp.Interval(this=expression.this.copy(), unit=exp.var('day')))})"
347
348            return super().interval_sql(expression)
def tablesample_sql( self, expression: sqlglot.expressions.TableSample, seed_prefix: str = 'SEED', sep: str = ' AS ') -> str:
350        def tablesample_sql(
351            self, expression: exp.TableSample, seed_prefix: str = "SEED", sep: str = " AS "
352        ) -> str:
353            return super().tablesample_sql(expression, seed_prefix="REPEATABLE", sep=sep)
SELECT_KINDS: Tuple[str, ...] = ()
INVERSE_TIME_MAPPING: Dict[str, str] = {}
INVERSE_TIME_TRIE: Dict = {}
INVERSE_ESCAPE_SEQUENCES: Dict[str, str] = {}
NULL_ORDERING = 'nulls_are_last'
@classmethod
def can_identify(text: str, identify: str | bool = 'safe') -> bool:
279    @classmethod
280    def can_identify(cls, text: str, identify: str | bool = "safe") -> bool:
281        """Checks if text can be identified given an identify option.
282
283        Args:
284            text: The text to check.
285            identify:
286                "always" or `True`: Always returns true.
287                "safe": True if the identifier is case-insensitive.
288
289        Returns:
290            Whether or not the given text can be identified.
291        """
292        if identify is True or identify == "always":
293            return True
294
295        if identify == "safe":
296            return not cls.case_sensitive(text)
297
298        return False

Checks if text can be identified given an identify option.

Arguments:
  • text: The text to check.
  • identify: "always" or True: Always returns true. "safe": True if the identifier is case-insensitive.
Returns:

Whether or not the given text can be identified.

QUOTE_START = "'"
QUOTE_END = "'"
IDENTIFIER_START = '"'
IDENTIFIER_END = '"'
TOKENIZER_CLASS = <class 'DuckDB.Tokenizer'>
BIT_START: Optional[str] = None
BIT_END: Optional[str] = None
HEX_START: Optional[str] = None
HEX_END: Optional[str] = None
BYTE_START: Optional[str] = None
BYTE_END: Optional[str] = None
Inherited Members
sqlglot.generator.Generator
Generator
LOG_BASE_FIRST
NULL_ORDERING_SUPPORTED
LOCKING_READS_SUPPORTED
EXPLICIT_UNION
WRAP_DERIVED_VALUES
CREATE_FUNCTION_RETURN_AS
MATCHED_BY_SOURCE
SINGLE_STRING_INTERVAL
INTERVAL_ALLOWS_PLURAL_FORM
TABLESAMPLE_WITH_METHOD
TABLESAMPLE_SIZE_IS_PERCENT
GROUPINGS_SEP
INDEX_ON
QUERY_HINT_SEP
IS_BOOL_ALLOWED
DUPLICATE_KEY_UPDATE_WITH_SET
LIMIT_IS_TOP
RETURNING_END
COLUMN_JOIN_MARKS_SUPPORTED
EXTRACT_ALLOWS_QUOTES
TZ_TO_WITH_TIME_ZONE
VALUES_AS_TABLE
ALTER_TABLE_ADD_COLUMN_KEYWORD
UNNEST_WITH_ORDINALITY
AGGREGATE_FILTER_SUPPORTED
SUPPORTS_PARAMETERS
COMPUTED_COLUMN_WITH_TYPE
SUPPORTS_TABLE_COPY
TABLESAMPLE_REQUIRES_PARENS
COLLATE_IS_FUNC
DATA_TYPE_SPECIFIERS_ALLOWED
TIME_PART_SINGULARS
TOKEN_MAPPING
PARAMETER_TOKEN
RESERVED_KEYWORDS
WITH_SEPARATED_COMMENTS
SENTINEL_LINE_BREAK
INDEX_OFFSET
UNNEST_COLUMN_ONLY
ALIAS_POST_TABLESAMPLE
IDENTIFIERS_CAN_START_WITH_DIGIT
STRICT_STRING_CONCAT
NORMALIZE_FUNCTIONS
pretty
identify
normalize
pad
unsupported_level
max_unsupported
leading_comma
max_text_width
comments
normalize_functions
unsupported_messages
generate
unsupported
sep
seg
pad_comment
maybe_comment
wrap
no_identify
normalize_func
indent
sql
uncache_sql
cache_sql
characterset_sql
column_sql
columnposition_sql
columndef_sql
columnconstraint_sql
computedcolumnconstraint_sql
autoincrementcolumnconstraint_sql
compresscolumnconstraint_sql
generatedasidentitycolumnconstraint_sql
notnullcolumnconstraint_sql
primarykeycolumnconstraint_sql
uniquecolumnconstraint_sql
createable_sql
create_sql
clone_sql
describe_sql
prepend_ctes
with_sql
cte_sql
tablealias_sql
bitstring_sql
hexstring_sql
bytestring_sql
rawstring_sql
datatypeparam_sql
datatype_sql
directory_sql
delete_sql
drop_sql
except_sql
except_op
fetch_sql
filter_sql
hint_sql
index_sql
identifier_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
lockingproperty_sql
withdataproperty_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
table_sql
pivot_sql
version_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_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
cluster_sql
distribute_sql
sort_sql
ordered_sql
matchrecognize_sql
query_modifiers
offset_limit_modifiers
after_having_modifiers
after_limit_modifiers
select_sql
schema_sql
schema_columns_sql
star_sql
parameter_sql
sessionparameter_sql
placeholder_sql
subquery_sql
qualify_sql
union_sql
union_op
unnest_sql
where_sql
window_sql
partition_by_sql
windowspec_sql
withingroup_sql
between_sql
bracket_sql
safebracket_sql
all_sql
any_sql
exists_sql
case_sql
constraint_sql
nextvaluefor_sql
extract_sql
trim_sql
safeconcat_sql
check_sql
foreignkey_sql
primarykey_sql
if_sql
matchagainst_sql
jsonkeyvalue_sql
formatjson_sql
jsonobject_sql
jsonarray_sql
jsonarrayagg_sql
jsoncolumndef_sql
jsontable_sql
openjsoncolumndef_sql
openjson_sql
in_sql
in_unnest_op
return_sql
reference_sql
anonymous_sql
paren_sql
neg_sql
not_sql
alias_sql
aliases_sql
attimezone_sql
add_sql
and_sql
xor_sql
connector_sql
bitwiseand_sql
bitwiseleftshift_sql
bitwisenot_sql
bitwiseor_sql
bitwiserightshift_sql
bitwisexor_sql
cast_sql
currentdate_sql
collate_sql
command_sql
comment_sql
mergetreettlaction_sql
mergetreettl_sql
transaction_sql
commit_sql
rollback_sql
altercolumn_sql
renametable_sql
altertable_sql
droppartition_sql
addconstraint_sql
distinct_sql
ignorenulls_sql
respectnulls_sql
intdiv_sql
dpipe_sql
safedpipe_sql
div_sql
overlaps_sql
distance_sql
dot_sql
eq_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
or_sql
slice_sql
sub_sql
trycast_sql
log_sql
use_sql
binary
function_fallback_sql
func
format_args
text_width
format_time
expressions
op_expressions
naked_property
set_operation
tag_sql
token_sql
userdefinedfunction_sql
joinhint_sql
kwarg_sql
when_sql
merge_sql
tochar_sql
dictproperty_sql
dictrange_sql
dictsubproperty_sql
oncluster_sql
clusteredbyproperty_sql
anyvalue_sql
querytransform_sql
indexconstraintoption_sql
indexcolumnconstraint_sql
nvl2_sql
comprehension_sql
columnprefix_sql
opclass_sql