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 date_trunc_to_time, 13 datestrtodate_sql, 14 encode_decode_sql, 15 format_time_lambda, 16 no_comment_column_constraint_sql, 17 no_properties_sql, 18 no_safe_divide_sql, 19 pivot_column_names, 20 regexp_extract_sql, 21 regexp_replace_sql, 22 rename_func, 23 str_position_sql, 24 str_to_time_sql, 25 timestamptrunc_sql, 26 timestrtotime_sql, 27 ts_or_ds_to_date_sql, 28) 29from sqlglot.helper import seq_get 30from sqlglot.tokens import TokenType 31 32 33def _ts_or_ds_add_sql(self: generator.Generator, expression: exp.TsOrDsAdd) -> str: 34 this = self.sql(expression, "this") 35 unit = self.sql(expression, "unit").strip("'") or "DAY" 36 return f"CAST({this} AS DATE) + {self.sql(exp.Interval(this=expression.expression.copy(), unit=unit))}" 37 38 39def _date_delta_sql(self: generator.Generator, expression: exp.DateAdd | exp.DateSub) -> str: 40 this = self.sql(expression, "this") 41 unit = self.sql(expression, "unit").strip("'") or "DAY" 42 op = "+" if isinstance(expression, exp.DateAdd) else "-" 43 return f"{this} {op} {self.sql(exp.Interval(this=expression.expression.copy(), unit=unit))}" 44 45 46# BigQuery -> DuckDB conversion for the DATE function 47def _date_sql(self: generator.Generator, expression: exp.Date) -> str: 48 result = f"CAST({self.sql(expression, 'this')} AS DATE)" 49 zone = self.sql(expression, "zone") 50 51 if zone: 52 date_str = self.func("STRFTIME", result, "'%d/%m/%Y'") 53 date_str = f"{date_str} || ' ' || {zone}" 54 55 # This will create a TIMESTAMP with time zone information 56 result = self.func("STRPTIME", date_str, "'%d/%m/%Y %Z'") 57 58 return result 59 60 61def _array_sort_sql(self: generator.Generator, expression: exp.ArraySort) -> str: 62 if expression.expression: 63 self.unsupported("DUCKDB ARRAY_SORT does not support a comparator") 64 return f"ARRAY_SORT({self.sql(expression, 'this')})" 65 66 67def _sort_array_sql(self: generator.Generator, expression: exp.SortArray) -> str: 68 this = self.sql(expression, "this") 69 if expression.args.get("asc") == exp.false(): 70 return f"ARRAY_REVERSE_SORT({this})" 71 return f"ARRAY_SORT({this})" 72 73 74def _sort_array_reverse(args: t.List) -> exp.Expression: 75 return exp.SortArray(this=seq_get(args, 0), asc=exp.false()) 76 77 78def _parse_date_diff(args: t.List) -> exp.Expression: 79 return exp.DateDiff(this=seq_get(args, 2), expression=seq_get(args, 1), unit=seq_get(args, 0)) 80 81 82def _struct_sql(self: generator.Generator, expression: exp.Struct) -> str: 83 args = [ 84 f"'{e.name or e.this.name}': {self.sql(e, 'expression')}" for e in expression.expressions 85 ] 86 return f"{{{', '.join(args)}}}" 87 88 89def _datatype_sql(self: generator.Generator, expression: exp.DataType) -> str: 90 if expression.is_type("array"): 91 return f"{self.expressions(expression, flat=True)}[]" 92 return self.datatype_sql(expression) 93 94 95def _json_format_sql(self: generator.Generator, expression: exp.JSONFormat) -> str: 96 sql = self.func("TO_JSON", expression.this, expression.args.get("options")) 97 return f"CAST({sql} AS TEXT)" 98 99 100class DuckDB(Dialect): 101 NULL_ORDERING = "nulls_are_last" 102 103 # https://duckdb.org/docs/sql/introduction.html#creating-a-new-table 104 RESOLVES_IDENTIFIERS_AS_UPPERCASE = None 105 106 class Tokenizer(tokens.Tokenizer): 107 KEYWORDS = { 108 **tokens.Tokenizer.KEYWORDS, 109 ":=": TokenType.EQ, 110 "//": TokenType.DIV, 111 "ATTACH": TokenType.COMMAND, 112 "BINARY": TokenType.VARBINARY, 113 "BPCHAR": TokenType.TEXT, 114 "BITSTRING": TokenType.BIT, 115 "CHAR": TokenType.TEXT, 116 "CHARACTER VARYING": TokenType.TEXT, 117 "EXCLUDE": TokenType.EXCEPT, 118 "INT1": TokenType.TINYINT, 119 "LOGICAL": TokenType.BOOLEAN, 120 "NUMERIC": TokenType.DOUBLE, 121 "PIVOT_WIDER": TokenType.PIVOT, 122 "SIGNED": TokenType.INT, 123 "STRING": TokenType.VARCHAR, 124 "UBIGINT": TokenType.UBIGINT, 125 "UINTEGER": TokenType.UINT, 126 "USMALLINT": TokenType.USMALLINT, 127 "UTINYINT": TokenType.UTINYINT, 128 } 129 130 class Parser(parser.Parser): 131 CONCAT_NULL_OUTPUTS_STRING = True 132 133 BITWISE = { 134 **parser.Parser.BITWISE, 135 TokenType.TILDA: exp.RegexpLike, 136 } 137 138 FUNCTIONS = { 139 **parser.Parser.FUNCTIONS, 140 "ARRAY_LENGTH": exp.ArraySize.from_arg_list, 141 "ARRAY_SORT": exp.SortArray.from_arg_list, 142 "ARRAY_REVERSE_SORT": _sort_array_reverse, 143 "DATEDIFF": _parse_date_diff, 144 "DATE_DIFF": _parse_date_diff, 145 "DATE_TRUNC": date_trunc_to_time, 146 "DATETRUNC": date_trunc_to_time, 147 "EPOCH": exp.TimeToUnix.from_arg_list, 148 "EPOCH_MS": lambda args: exp.UnixToTime( 149 this=exp.Div(this=seq_get(args, 0), expression=exp.Literal.number(1000)) 150 ), 151 "LIST_REVERSE_SORT": _sort_array_reverse, 152 "LIST_SORT": exp.SortArray.from_arg_list, 153 "LIST_VALUE": exp.Array.from_arg_list, 154 "REGEXP_EXTRACT": lambda args: exp.RegexpExtract( 155 this=seq_get(args, 0), expression=seq_get(args, 1), group=seq_get(args, 2) 156 ), 157 "REGEXP_MATCHES": exp.RegexpLike.from_arg_list, 158 "STRFTIME": format_time_lambda(exp.TimeToStr, "duckdb"), 159 "STRING_SPLIT": exp.Split.from_arg_list, 160 "STRING_SPLIT_REGEX": exp.RegexpSplit.from_arg_list, 161 "STRING_TO_ARRAY": exp.Split.from_arg_list, 162 "STRPTIME": format_time_lambda(exp.StrToTime, "duckdb"), 163 "STRUCT_PACK": exp.Struct.from_arg_list, 164 "STR_SPLIT": exp.Split.from_arg_list, 165 "STR_SPLIT_REGEX": exp.RegexpSplit.from_arg_list, 166 "TO_TIMESTAMP": exp.UnixToTime.from_arg_list, 167 "UNNEST": exp.Explode.from_arg_list, 168 "XOR": binary_from_function(exp.BitwiseXor), 169 } 170 171 FUNCTION_PARSERS = { 172 **parser.Parser.FUNCTION_PARSERS, 173 "DECODE": lambda self: self.expression( 174 exp.Decode, this=self._parse_conjunction(), charset=exp.Literal.string("utf-8") 175 ), 176 "ENCODE": lambda self: self.expression( 177 exp.Encode, this=self._parse_conjunction(), charset=exp.Literal.string("utf-8") 178 ), 179 } 180 181 TYPE_TOKENS = { 182 *parser.Parser.TYPE_TOKENS, 183 TokenType.UBIGINT, 184 TokenType.UINT, 185 TokenType.USMALLINT, 186 TokenType.UTINYINT, 187 } 188 189 def _pivot_column_names(self, aggregations: t.List[exp.Expression]) -> t.List[str]: 190 if len(aggregations) == 1: 191 return super()._pivot_column_names(aggregations) 192 return pivot_column_names(aggregations, dialect="duckdb") 193 194 class Generator(generator.Generator): 195 JOIN_HINTS = False 196 TABLE_HINTS = False 197 QUERY_HINTS = False 198 LIMIT_FETCH = "LIMIT" 199 STRUCT_DELIMITER = ("(", ")") 200 RENAME_TABLE_WITH_DB = False 201 202 TRANSFORMS = { 203 **generator.Generator.TRANSFORMS, 204 exp.ApproxDistinct: approx_count_distinct_sql, 205 exp.Array: lambda self, e: self.func("ARRAY", e.expressions[0]) 206 if e.expressions and e.expressions[0].find(exp.Select) 207 else rename_func("LIST_VALUE")(self, e), 208 exp.ArraySize: rename_func("ARRAY_LENGTH"), 209 exp.ArraySort: _array_sort_sql, 210 exp.ArraySum: rename_func("LIST_SUM"), 211 exp.BitwiseXor: lambda self, e: self.func("XOR", e.this, e.expression), 212 exp.CommentColumnConstraint: no_comment_column_constraint_sql, 213 exp.CurrentDate: lambda self, e: "CURRENT_DATE", 214 exp.CurrentTime: lambda self, e: "CURRENT_TIME", 215 exp.CurrentTimestamp: lambda self, e: "CURRENT_TIMESTAMP", 216 exp.DayOfMonth: rename_func("DAYOFMONTH"), 217 exp.DayOfWeek: rename_func("DAYOFWEEK"), 218 exp.DayOfYear: rename_func("DAYOFYEAR"), 219 exp.DataType: _datatype_sql, 220 exp.Date: _date_sql, 221 exp.DateAdd: _date_delta_sql, 222 exp.DateFromParts: rename_func("MAKE_DATE"), 223 exp.DateSub: _date_delta_sql, 224 exp.DateDiff: lambda self, e: self.func( 225 "DATE_DIFF", f"'{e.args.get('unit') or 'day'}'", e.expression, e.this 226 ), 227 exp.DateStrToDate: datestrtodate_sql, 228 exp.DateToDi: lambda self, e: f"CAST(STRFTIME({self.sql(e, 'this')}, {DuckDB.DATEINT_FORMAT}) AS INT)", 229 exp.Decode: lambda self, e: encode_decode_sql(self, e, "DECODE", replace=False), 230 exp.DiToDate: lambda self, e: f"CAST(STRPTIME(CAST({self.sql(e, 'this')} AS TEXT), {DuckDB.DATEINT_FORMAT}) AS DATE)", 231 exp.Encode: lambda self, e: encode_decode_sql(self, e, "ENCODE", replace=False), 232 exp.Explode: rename_func("UNNEST"), 233 exp.IntDiv: lambda self, e: self.binary(e, "//"), 234 exp.JSONExtract: arrow_json_extract_sql, 235 exp.JSONExtractScalar: arrow_json_extract_scalar_sql, 236 exp.JSONFormat: _json_format_sql, 237 exp.JSONBExtract: arrow_json_extract_sql, 238 exp.JSONBExtractScalar: arrow_json_extract_scalar_sql, 239 exp.LogicalOr: rename_func("BOOL_OR"), 240 exp.LogicalAnd: rename_func("BOOL_AND"), 241 exp.MonthsBetween: lambda self, e: self.func( 242 "DATEDIFF", 243 "'month'", 244 exp.cast(e.expression, "timestamp", copy=True), 245 exp.cast(e.this, "timestamp", copy=True), 246 ), 247 exp.Properties: no_properties_sql, 248 exp.RegexpExtract: regexp_extract_sql, 249 exp.RegexpReplace: regexp_replace_sql, 250 exp.RegexpLike: rename_func("REGEXP_MATCHES"), 251 exp.RegexpSplit: rename_func("STR_SPLIT_REGEX"), 252 exp.SafeDivide: no_safe_divide_sql, 253 exp.Split: rename_func("STR_SPLIT"), 254 exp.SortArray: _sort_array_sql, 255 exp.StrPosition: str_position_sql, 256 exp.StrToDate: lambda self, e: f"CAST({str_to_time_sql(self, e)} AS DATE)", 257 exp.StrToTime: str_to_time_sql, 258 exp.StrToUnix: lambda self, e: f"EPOCH(STRPTIME({self.sql(e, 'this')}, {self.format_time(e)}))", 259 exp.Struct: _struct_sql, 260 exp.TimestampTrunc: timestamptrunc_sql, 261 exp.TimeStrToDate: lambda self, e: f"CAST({self.sql(e, 'this')} AS DATE)", 262 exp.TimeStrToTime: timestrtotime_sql, 263 exp.TimeStrToUnix: lambda self, e: f"EPOCH(CAST({self.sql(e, 'this')} AS TIMESTAMP))", 264 exp.TimeToStr: lambda self, e: f"STRFTIME({self.sql(e, 'this')}, {self.format_time(e)})", 265 exp.TimeToUnix: rename_func("EPOCH"), 266 exp.TsOrDiToDi: lambda self, e: f"CAST(SUBSTR(REPLACE(CAST({self.sql(e, 'this')} AS TEXT), '-', ''), 1, 8) AS INT)", 267 exp.TsOrDsAdd: _ts_or_ds_add_sql, 268 exp.TsOrDsToDate: ts_or_ds_to_date_sql("duckdb"), 269 exp.UnixToStr: lambda self, e: f"STRFTIME(TO_TIMESTAMP({self.sql(e, 'this')}), {self.format_time(e)})", 270 exp.UnixToTime: rename_func("TO_TIMESTAMP"), 271 exp.UnixToTimeStr: lambda self, e: f"CAST(TO_TIMESTAMP({self.sql(e, 'this')}) AS TEXT)", 272 exp.WeekOfYear: rename_func("WEEKOFYEAR"), 273 } 274 275 TYPE_MAPPING = { 276 **generator.Generator.TYPE_MAPPING, 277 exp.DataType.Type.BINARY: "BLOB", 278 exp.DataType.Type.CHAR: "TEXT", 279 exp.DataType.Type.FLOAT: "REAL", 280 exp.DataType.Type.NCHAR: "TEXT", 281 exp.DataType.Type.NVARCHAR: "TEXT", 282 exp.DataType.Type.UINT: "UINTEGER", 283 exp.DataType.Type.VARBINARY: "BLOB", 284 exp.DataType.Type.VARCHAR: "TEXT", 285 } 286 287 STAR_MAPPING = {**generator.Generator.STAR_MAPPING, "except": "EXCLUDE"} 288 289 UNWRAPPED_INTERVAL_VALUES = (exp.Column, exp.Literal, exp.Paren) 290 291 PROPERTIES_LOCATION = { 292 **generator.Generator.PROPERTIES_LOCATION, 293 exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED, 294 } 295 296 def interval_sql(self, expression: exp.Interval) -> str: 297 multiplier: t.Optional[int] = None 298 unit = expression.text("unit").lower() 299 300 if unit.startswith("week"): 301 multiplier = 7 302 if unit.startswith("quarter"): 303 multiplier = 90 304 305 if multiplier: 306 return f"({multiplier} * {super().interval_sql(exp.Interval(this=expression.this.copy(), unit=exp.var('day')))})" 307 308 return super().interval_sql(expression) 309 310 def tablesample_sql( 311 self, expression: exp.TableSample, seed_prefix: str = "SEED", sep: str = " AS " 312 ) -> str: 313 return super().tablesample_sql(expression, seed_prefix="REPEATABLE", sep=sep)
101class DuckDB(Dialect): 102 NULL_ORDERING = "nulls_are_last" 103 104 # https://duckdb.org/docs/sql/introduction.html#creating-a-new-table 105 RESOLVES_IDENTIFIERS_AS_UPPERCASE = None 106 107 class Tokenizer(tokens.Tokenizer): 108 KEYWORDS = { 109 **tokens.Tokenizer.KEYWORDS, 110 ":=": TokenType.EQ, 111 "//": TokenType.DIV, 112 "ATTACH": TokenType.COMMAND, 113 "BINARY": TokenType.VARBINARY, 114 "BPCHAR": TokenType.TEXT, 115 "BITSTRING": TokenType.BIT, 116 "CHAR": TokenType.TEXT, 117 "CHARACTER VARYING": TokenType.TEXT, 118 "EXCLUDE": TokenType.EXCEPT, 119 "INT1": TokenType.TINYINT, 120 "LOGICAL": TokenType.BOOLEAN, 121 "NUMERIC": TokenType.DOUBLE, 122 "PIVOT_WIDER": TokenType.PIVOT, 123 "SIGNED": TokenType.INT, 124 "STRING": TokenType.VARCHAR, 125 "UBIGINT": TokenType.UBIGINT, 126 "UINTEGER": TokenType.UINT, 127 "USMALLINT": TokenType.USMALLINT, 128 "UTINYINT": TokenType.UTINYINT, 129 } 130 131 class Parser(parser.Parser): 132 CONCAT_NULL_OUTPUTS_STRING = True 133 134 BITWISE = { 135 **parser.Parser.BITWISE, 136 TokenType.TILDA: exp.RegexpLike, 137 } 138 139 FUNCTIONS = { 140 **parser.Parser.FUNCTIONS, 141 "ARRAY_LENGTH": exp.ArraySize.from_arg_list, 142 "ARRAY_SORT": exp.SortArray.from_arg_list, 143 "ARRAY_REVERSE_SORT": _sort_array_reverse, 144 "DATEDIFF": _parse_date_diff, 145 "DATE_DIFF": _parse_date_diff, 146 "DATE_TRUNC": date_trunc_to_time, 147 "DATETRUNC": date_trunc_to_time, 148 "EPOCH": exp.TimeToUnix.from_arg_list, 149 "EPOCH_MS": lambda args: exp.UnixToTime( 150 this=exp.Div(this=seq_get(args, 0), expression=exp.Literal.number(1000)) 151 ), 152 "LIST_REVERSE_SORT": _sort_array_reverse, 153 "LIST_SORT": exp.SortArray.from_arg_list, 154 "LIST_VALUE": exp.Array.from_arg_list, 155 "REGEXP_EXTRACT": lambda args: exp.RegexpExtract( 156 this=seq_get(args, 0), expression=seq_get(args, 1), group=seq_get(args, 2) 157 ), 158 "REGEXP_MATCHES": exp.RegexpLike.from_arg_list, 159 "STRFTIME": format_time_lambda(exp.TimeToStr, "duckdb"), 160 "STRING_SPLIT": exp.Split.from_arg_list, 161 "STRING_SPLIT_REGEX": exp.RegexpSplit.from_arg_list, 162 "STRING_TO_ARRAY": exp.Split.from_arg_list, 163 "STRPTIME": format_time_lambda(exp.StrToTime, "duckdb"), 164 "STRUCT_PACK": exp.Struct.from_arg_list, 165 "STR_SPLIT": exp.Split.from_arg_list, 166 "STR_SPLIT_REGEX": exp.RegexpSplit.from_arg_list, 167 "TO_TIMESTAMP": exp.UnixToTime.from_arg_list, 168 "UNNEST": exp.Explode.from_arg_list, 169 "XOR": binary_from_function(exp.BitwiseXor), 170 } 171 172 FUNCTION_PARSERS = { 173 **parser.Parser.FUNCTION_PARSERS, 174 "DECODE": lambda self: self.expression( 175 exp.Decode, this=self._parse_conjunction(), charset=exp.Literal.string("utf-8") 176 ), 177 "ENCODE": lambda self: self.expression( 178 exp.Encode, this=self._parse_conjunction(), charset=exp.Literal.string("utf-8") 179 ), 180 } 181 182 TYPE_TOKENS = { 183 *parser.Parser.TYPE_TOKENS, 184 TokenType.UBIGINT, 185 TokenType.UINT, 186 TokenType.USMALLINT, 187 TokenType.UTINYINT, 188 } 189 190 def _pivot_column_names(self, aggregations: t.List[exp.Expression]) -> t.List[str]: 191 if len(aggregations) == 1: 192 return super()._pivot_column_names(aggregations) 193 return pivot_column_names(aggregations, dialect="duckdb") 194 195 class Generator(generator.Generator): 196 JOIN_HINTS = False 197 TABLE_HINTS = False 198 QUERY_HINTS = False 199 LIMIT_FETCH = "LIMIT" 200 STRUCT_DELIMITER = ("(", ")") 201 RENAME_TABLE_WITH_DB = False 202 203 TRANSFORMS = { 204 **generator.Generator.TRANSFORMS, 205 exp.ApproxDistinct: approx_count_distinct_sql, 206 exp.Array: lambda self, e: self.func("ARRAY", e.expressions[0]) 207 if e.expressions and e.expressions[0].find(exp.Select) 208 else rename_func("LIST_VALUE")(self, e), 209 exp.ArraySize: rename_func("ARRAY_LENGTH"), 210 exp.ArraySort: _array_sort_sql, 211 exp.ArraySum: rename_func("LIST_SUM"), 212 exp.BitwiseXor: lambda self, e: self.func("XOR", e.this, e.expression), 213 exp.CommentColumnConstraint: no_comment_column_constraint_sql, 214 exp.CurrentDate: lambda self, e: "CURRENT_DATE", 215 exp.CurrentTime: lambda self, e: "CURRENT_TIME", 216 exp.CurrentTimestamp: lambda self, e: "CURRENT_TIMESTAMP", 217 exp.DayOfMonth: rename_func("DAYOFMONTH"), 218 exp.DayOfWeek: rename_func("DAYOFWEEK"), 219 exp.DayOfYear: rename_func("DAYOFYEAR"), 220 exp.DataType: _datatype_sql, 221 exp.Date: _date_sql, 222 exp.DateAdd: _date_delta_sql, 223 exp.DateFromParts: rename_func("MAKE_DATE"), 224 exp.DateSub: _date_delta_sql, 225 exp.DateDiff: lambda self, e: self.func( 226 "DATE_DIFF", f"'{e.args.get('unit') or 'day'}'", e.expression, e.this 227 ), 228 exp.DateStrToDate: datestrtodate_sql, 229 exp.DateToDi: lambda self, e: f"CAST(STRFTIME({self.sql(e, 'this')}, {DuckDB.DATEINT_FORMAT}) AS INT)", 230 exp.Decode: lambda self, e: encode_decode_sql(self, e, "DECODE", replace=False), 231 exp.DiToDate: lambda self, e: f"CAST(STRPTIME(CAST({self.sql(e, 'this')} AS TEXT), {DuckDB.DATEINT_FORMAT}) AS DATE)", 232 exp.Encode: lambda self, e: encode_decode_sql(self, e, "ENCODE", replace=False), 233 exp.Explode: rename_func("UNNEST"), 234 exp.IntDiv: lambda self, e: self.binary(e, "//"), 235 exp.JSONExtract: arrow_json_extract_sql, 236 exp.JSONExtractScalar: arrow_json_extract_scalar_sql, 237 exp.JSONFormat: _json_format_sql, 238 exp.JSONBExtract: arrow_json_extract_sql, 239 exp.JSONBExtractScalar: arrow_json_extract_scalar_sql, 240 exp.LogicalOr: rename_func("BOOL_OR"), 241 exp.LogicalAnd: rename_func("BOOL_AND"), 242 exp.MonthsBetween: lambda self, e: self.func( 243 "DATEDIFF", 244 "'month'", 245 exp.cast(e.expression, "timestamp", copy=True), 246 exp.cast(e.this, "timestamp", copy=True), 247 ), 248 exp.Properties: no_properties_sql, 249 exp.RegexpExtract: regexp_extract_sql, 250 exp.RegexpReplace: regexp_replace_sql, 251 exp.RegexpLike: rename_func("REGEXP_MATCHES"), 252 exp.RegexpSplit: rename_func("STR_SPLIT_REGEX"), 253 exp.SafeDivide: no_safe_divide_sql, 254 exp.Split: rename_func("STR_SPLIT"), 255 exp.SortArray: _sort_array_sql, 256 exp.StrPosition: str_position_sql, 257 exp.StrToDate: lambda self, e: f"CAST({str_to_time_sql(self, e)} AS DATE)", 258 exp.StrToTime: str_to_time_sql, 259 exp.StrToUnix: lambda self, e: f"EPOCH(STRPTIME({self.sql(e, 'this')}, {self.format_time(e)}))", 260 exp.Struct: _struct_sql, 261 exp.TimestampTrunc: timestamptrunc_sql, 262 exp.TimeStrToDate: lambda self, e: f"CAST({self.sql(e, 'this')} AS DATE)", 263 exp.TimeStrToTime: timestrtotime_sql, 264 exp.TimeStrToUnix: lambda self, e: f"EPOCH(CAST({self.sql(e, 'this')} AS TIMESTAMP))", 265 exp.TimeToStr: lambda self, e: f"STRFTIME({self.sql(e, 'this')}, {self.format_time(e)})", 266 exp.TimeToUnix: rename_func("EPOCH"), 267 exp.TsOrDiToDi: lambda self, e: f"CAST(SUBSTR(REPLACE(CAST({self.sql(e, 'this')} AS TEXT), '-', ''), 1, 8) AS INT)", 268 exp.TsOrDsAdd: _ts_or_ds_add_sql, 269 exp.TsOrDsToDate: ts_or_ds_to_date_sql("duckdb"), 270 exp.UnixToStr: lambda self, e: f"STRFTIME(TO_TIMESTAMP({self.sql(e, 'this')}), {self.format_time(e)})", 271 exp.UnixToTime: rename_func("TO_TIMESTAMP"), 272 exp.UnixToTimeStr: lambda self, e: f"CAST(TO_TIMESTAMP({self.sql(e, 'this')}) AS TEXT)", 273 exp.WeekOfYear: rename_func("WEEKOFYEAR"), 274 } 275 276 TYPE_MAPPING = { 277 **generator.Generator.TYPE_MAPPING, 278 exp.DataType.Type.BINARY: "BLOB", 279 exp.DataType.Type.CHAR: "TEXT", 280 exp.DataType.Type.FLOAT: "REAL", 281 exp.DataType.Type.NCHAR: "TEXT", 282 exp.DataType.Type.NVARCHAR: "TEXT", 283 exp.DataType.Type.UINT: "UINTEGER", 284 exp.DataType.Type.VARBINARY: "BLOB", 285 exp.DataType.Type.VARCHAR: "TEXT", 286 } 287 288 STAR_MAPPING = {**generator.Generator.STAR_MAPPING, "except": "EXCLUDE"} 289 290 UNWRAPPED_INTERVAL_VALUES = (exp.Column, exp.Literal, exp.Paren) 291 292 PROPERTIES_LOCATION = { 293 **generator.Generator.PROPERTIES_LOCATION, 294 exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED, 295 } 296 297 def interval_sql(self, expression: exp.Interval) -> str: 298 multiplier: t.Optional[int] = None 299 unit = expression.text("unit").lower() 300 301 if unit.startswith("week"): 302 multiplier = 7 303 if unit.startswith("quarter"): 304 multiplier = 90 305 306 if multiplier: 307 return f"({multiplier} * {super().interval_sql(exp.Interval(this=expression.this.copy(), unit=exp.var('day')))})" 308 309 return super().interval_sql(expression) 310 311 def tablesample_sql( 312 self, expression: exp.TableSample, seed_prefix: str = "SEED", sep: str = " AS " 313 ) -> str: 314 return super().tablesample_sql(expression, seed_prefix="REPEATABLE", sep=sep)
tokenizer_class =
<class 'sqlglot.dialects.duckdb.DuckDB.Tokenizer'>
parser_class =
<class 'sqlglot.dialects.duckdb.DuckDB.Parser'>
generator_class =
<class 'sqlglot.dialects.duckdb.DuckDB.Generator'>
Inherited Members
- sqlglot.dialects.dialect.Dialect
- INDEX_OFFSET
- UNNEST_COLUMN_ONLY
- ALIAS_POST_TABLESAMPLE
- IDENTIFIERS_CAN_START_WITH_DIGIT
- STRICT_STRING_CONCAT
- NORMALIZE_FUNCTIONS
- DATE_FORMAT
- DATEINT_FORMAT
- TIME_FORMAT
- TIME_MAPPING
- FORMAT_MAPPING
- PSEUDOCOLUMNS
- get_or_raise
- format_time
- normalize_identifier
- case_sensitive
- can_identify
- quote_identifier
- parse
- parse_into
- generate
- transpile
- tokenize
- tokenizer
- parser
- generator
107 class Tokenizer(tokens.Tokenizer): 108 KEYWORDS = { 109 **tokens.Tokenizer.KEYWORDS, 110 ":=": TokenType.EQ, 111 "//": TokenType.DIV, 112 "ATTACH": TokenType.COMMAND, 113 "BINARY": TokenType.VARBINARY, 114 "BPCHAR": TokenType.TEXT, 115 "BITSTRING": TokenType.BIT, 116 "CHAR": TokenType.TEXT, 117 "CHARACTER VARYING": TokenType.TEXT, 118 "EXCLUDE": TokenType.EXCEPT, 119 "INT1": TokenType.TINYINT, 120 "LOGICAL": TokenType.BOOLEAN, 121 "NUMERIC": TokenType.DOUBLE, 122 "PIVOT_WIDER": TokenType.PIVOT, 123 "SIGNED": TokenType.INT, 124 "STRING": TokenType.VARCHAR, 125 "UBIGINT": TokenType.UBIGINT, 126 "UINTEGER": TokenType.UINT, 127 "USMALLINT": TokenType.USMALLINT, 128 "UTINYINT": TokenType.UTINYINT, 129 }
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'>, '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'>, 'IF': <TokenType.IF: 'IF'>, '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'>, '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'>, 'NEXT VALUE FOR': <TokenType.NEXT_VALUE_FOR: 'NEXT_VALUE_FOR'>, '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'>, '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'>, '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'>, 'TINYINT': <TokenType.TINYINT: 'TINYINT'>, 'SHORT': <TokenType.SMALLINT: 'SMALLINT'>, 'SMALLINT': <TokenType.SMALLINT: 'SMALLINT'>, '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.DOUBLE: 'DOUBLE'>, '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'>, 'CLOB': <TokenType.TEXT: 'TEXT'>, 'LONGVARCHAR': <TokenType.TEXT: 'TEXT'>, 'BINARY': <TokenType.VARBINARY: 'VARBINARY'>, 'BLOB': <TokenType.VARBINARY: 'VARBINARY'>, 'BYTEA': <TokenType.VARBINARY: 'VARBINARY'>, 'VARBINARY': <TokenType.VARBINARY: 'VARBINARY'>, 'TIME': <TokenType.TIME: 'TIME'>, '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'>, ':=': <TokenType.EQ: 'EQ'>, '//': <TokenType.DIV: 'DIV'>, 'ATTACH': <TokenType.COMMAND: 'COMMAND'>, 'BPCHAR': <TokenType.TEXT: 'TEXT'>, 'BITSTRING': <TokenType.BIT: 'BIT'>, 'CHARACTER VARYING': <TokenType.TEXT: 'TEXT'>, 'EXCLUDE': <TokenType.EXCEPT: 'EXCEPT'>, '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'>}
Inherited Members
- sqlglot.tokens.Tokenizer
- SINGLE_TOKENS
- BIT_STRINGS
- BYTE_STRINGS
- HEX_STRINGS
- RAW_STRINGS
- IDENTIFIERS
- IDENTIFIER_ESCAPES
- QUOTES
- STRING_ESCAPES
- VAR_SINGLE_TOKENS
- IDENTIFIERS_CAN_START_WITH_DIGIT
- WHITE_SPACE
- COMMANDS
- COMMAND_PREFIX_TOKENS
- NUMERIC_LITERALS
- ENCODE
- COMMENTS
- reset
- tokenize
- peek
- size
- sql
- tokens
131 class Parser(parser.Parser): 132 CONCAT_NULL_OUTPUTS_STRING = True 133 134 BITWISE = { 135 **parser.Parser.BITWISE, 136 TokenType.TILDA: exp.RegexpLike, 137 } 138 139 FUNCTIONS = { 140 **parser.Parser.FUNCTIONS, 141 "ARRAY_LENGTH": exp.ArraySize.from_arg_list, 142 "ARRAY_SORT": exp.SortArray.from_arg_list, 143 "ARRAY_REVERSE_SORT": _sort_array_reverse, 144 "DATEDIFF": _parse_date_diff, 145 "DATE_DIFF": _parse_date_diff, 146 "DATE_TRUNC": date_trunc_to_time, 147 "DATETRUNC": date_trunc_to_time, 148 "EPOCH": exp.TimeToUnix.from_arg_list, 149 "EPOCH_MS": lambda args: exp.UnixToTime( 150 this=exp.Div(this=seq_get(args, 0), expression=exp.Literal.number(1000)) 151 ), 152 "LIST_REVERSE_SORT": _sort_array_reverse, 153 "LIST_SORT": exp.SortArray.from_arg_list, 154 "LIST_VALUE": exp.Array.from_arg_list, 155 "REGEXP_EXTRACT": lambda args: exp.RegexpExtract( 156 this=seq_get(args, 0), expression=seq_get(args, 1), group=seq_get(args, 2) 157 ), 158 "REGEXP_MATCHES": exp.RegexpLike.from_arg_list, 159 "STRFTIME": format_time_lambda(exp.TimeToStr, "duckdb"), 160 "STRING_SPLIT": exp.Split.from_arg_list, 161 "STRING_SPLIT_REGEX": exp.RegexpSplit.from_arg_list, 162 "STRING_TO_ARRAY": exp.Split.from_arg_list, 163 "STRPTIME": format_time_lambda(exp.StrToTime, "duckdb"), 164 "STRUCT_PACK": exp.Struct.from_arg_list, 165 "STR_SPLIT": exp.Split.from_arg_list, 166 "STR_SPLIT_REGEX": exp.RegexpSplit.from_arg_list, 167 "TO_TIMESTAMP": exp.UnixToTime.from_arg_list, 168 "UNNEST": exp.Explode.from_arg_list, 169 "XOR": binary_from_function(exp.BitwiseXor), 170 } 171 172 FUNCTION_PARSERS = { 173 **parser.Parser.FUNCTION_PARSERS, 174 "DECODE": lambda self: self.expression( 175 exp.Decode, this=self._parse_conjunction(), charset=exp.Literal.string("utf-8") 176 ), 177 "ENCODE": lambda self: self.expression( 178 exp.Encode, this=self._parse_conjunction(), charset=exp.Literal.string("utf-8") 179 ), 180 } 181 182 TYPE_TOKENS = { 183 *parser.Parser.TYPE_TOKENS, 184 TokenType.UBIGINT, 185 TokenType.UINT, 186 TokenType.USMALLINT, 187 TokenType.UTINYINT, 188 } 189 190 def _pivot_column_names(self, aggregations: t.List[exp.Expression]) -> t.List[str]: 191 if len(aggregations) == 1: 192 return super()._pivot_column_names(aggregations) 193 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
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_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'>>, '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'>>, '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'>>, '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'>>, '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'>>, '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'>>, '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_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'>>, '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_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'>>, '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'>>, '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>>, '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>>}
TYPE_TOKENS =
{<TokenType.USMALLINT: 'USMALLINT'>, <TokenType.INT4RANGE: 'INT4RANGE'>, <TokenType.VARCHAR: 'VARCHAR'>, <TokenType.IPADDRESS: 'IPADDRESS'>, <TokenType.BOOLEAN: 'BOOLEAN'>, <TokenType.INT128: 'INT128'>, <TokenType.USERDEFINED: 'USERDEFINED'>, <TokenType.JSONB: 'JSONB'>, <TokenType.JSON: 'JSON'>, <TokenType.INT8MULTIRANGE: 'INT8MULTIRANGE'>, <TokenType.BINARY: 'BINARY'>, <TokenType.INT8RANGE: 'INT8RANGE'>, <TokenType.TSRANGE: 'TSRANGE'>, <TokenType.XML: 'XML'>, <TokenType.SERIAL: 'SERIAL'>, <TokenType.UUID: 'UUID'>, <TokenType.BIGSERIAL: 'BIGSERIAL'>, <TokenType.NVARCHAR: 'NVARCHAR'>, <TokenType.OBJECT: 'OBJECT'>, <TokenType.TIME: 'TIME'>, <TokenType.VARBINARY: 'VARBINARY'>, <TokenType.MAP: 'MAP'>, <TokenType.INT4MULTIRANGE: 'INT4MULTIRANGE'>, <TokenType.DATERANGE: 'DATERANGE'>, <TokenType.DECIMAL: 'DECIMAL'>, <TokenType.CHAR: 'CHAR'>, <TokenType.TSMULTIRANGE: 'TSMULTIRANGE'>, <TokenType.STRUCT: 'STRUCT'>, <TokenType.SMALLMONEY: 'SMALLMONEY'>, <TokenType.NCHAR: 'NCHAR'>, <TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>, <TokenType.INTERVAL: 'INTERVAL'>, <TokenType.SUPER: 'SUPER'>, <TokenType.SMALLSERIAL: 'SMALLSERIAL'>, <TokenType.DATETIME: 'DATETIME'>, <TokenType.HLLSKETCH: 'HLLSKETCH'>, <TokenType.INET: 'INET'>, <TokenType.ENUM: 'ENUM'>, <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>, <TokenType.LONGBLOB: 'LONGBLOB'>, <TokenType.BIT: 'BIT'>, <TokenType.NUMRANGE: 'NUMRANGE'>, <TokenType.NULLABLE: 'NULLABLE'>, <TokenType.INT: 'INT'>, <TokenType.TINYINT: 'TINYINT'>, <TokenType.TIMESTAMP: 'TIMESTAMP'>, <TokenType.GEOGRAPHY: 'GEOGRAPHY'>, <TokenType.DATETIME64: 'DATETIME64'>, <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, <TokenType.DATEMULTIRANGE: 'DATEMULTIRANGE'>, <TokenType.IMAGE: 'IMAGE'>, <TokenType.UINT256: 'UINT256'>, <TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>, <TokenType.IPPREFIX: 'IPPREFIX'>, <TokenType.UNIQUEIDENTIFIER: 'UNIQUEIDENTIFIER'>, <TokenType.UINT: 'UINT'>, <TokenType.SMALLINT: 'SMALLINT'>, <TokenType.INT256: 'INT256'>, <TokenType.HSTORE: 'HSTORE'>, <TokenType.VARIANT: 'VARIANT'>, <TokenType.GEOMETRY: 'GEOMETRY'>, <TokenType.FLOAT: 'FLOAT'>, <TokenType.TSTZRANGE: 'TSTZRANGE'>, <TokenType.ROWVERSION: 'ROWVERSION'>, <TokenType.TEXT: 'TEXT'>, <TokenType.UINT128: 'UINT128'>, <TokenType.ARRAY: 'ARRAY'>, <TokenType.NUMMULTIRANGE: 'NUMMULTIRANGE'>, <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>, <TokenType.TSTZMULTIRANGE: 'TSTZMULTIRANGE'>, <TokenType.DOUBLE: 'DOUBLE'>, <TokenType.LONGTEXT: 'LONGTEXT'>, <TokenType.UTINYINT: 'UTINYINT'>, <TokenType.DATE: 'DATE'>, <TokenType.MONEY: 'MONEY'>, <TokenType.UBIGINT: 'UBIGINT'>, <TokenType.BIGINT: 'BIGINT'>, <TokenType.PSEUDO_TYPE: 'PSEUDO_TYPE'>}
SET_TRIE: Dict =
{'GLOBAL': {0: True}, 'LOCAL': {0: True}, 'SESSION': {0: True}, 'TRANSACTION': {0: True}}
Inherited Members
- sqlglot.parser.Parser
- Parser
- NO_PAREN_FUNCTIONS
- NESTED_TYPE_TOKENS
- ENUM_TYPE_TOKENS
- SUBQUERY_PREDICATES
- RESERVED_KEYWORDS
- DB_CREATABLES
- CREATABLES
- ID_VAR_TOKENS
- INTERVAL_VARS
- TABLE_ALIAS_TOKENS
- COMMENT_TABLE_ALIAS_TOKENS
- UPDATE_ALIAS_TOKENS
- TRIM_TYPES
- FUNC_TOKENS
- CONJUNCTION
- EQUALITY
- COMPARISON
- TERM
- FACTOR
- 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
- 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_KINDS
- TABLE_INDEX_HINT_TOKENS
- WINDOW_ALIAS_TOKENS
- WINDOW_BEFORE_PAREN_TOKENS
- WINDOW_SIDES
- ADD_CONSTRAINT_TOKENS
- STRICT_CAST
- PREFIXED_PIVOT_COLUMNS
- IDENTIFY_PIVOT_STRINGS
- LOG_BASE_FIRST
- LOG_DEFAULTS_TO_LN
- 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
195 class Generator(generator.Generator): 196 JOIN_HINTS = False 197 TABLE_HINTS = False 198 QUERY_HINTS = False 199 LIMIT_FETCH = "LIMIT" 200 STRUCT_DELIMITER = ("(", ")") 201 RENAME_TABLE_WITH_DB = False 202 203 TRANSFORMS = { 204 **generator.Generator.TRANSFORMS, 205 exp.ApproxDistinct: approx_count_distinct_sql, 206 exp.Array: lambda self, e: self.func("ARRAY", e.expressions[0]) 207 if e.expressions and e.expressions[0].find(exp.Select) 208 else rename_func("LIST_VALUE")(self, e), 209 exp.ArraySize: rename_func("ARRAY_LENGTH"), 210 exp.ArraySort: _array_sort_sql, 211 exp.ArraySum: rename_func("LIST_SUM"), 212 exp.BitwiseXor: lambda self, e: self.func("XOR", e.this, e.expression), 213 exp.CommentColumnConstraint: no_comment_column_constraint_sql, 214 exp.CurrentDate: lambda self, e: "CURRENT_DATE", 215 exp.CurrentTime: lambda self, e: "CURRENT_TIME", 216 exp.CurrentTimestamp: lambda self, e: "CURRENT_TIMESTAMP", 217 exp.DayOfMonth: rename_func("DAYOFMONTH"), 218 exp.DayOfWeek: rename_func("DAYOFWEEK"), 219 exp.DayOfYear: rename_func("DAYOFYEAR"), 220 exp.DataType: _datatype_sql, 221 exp.Date: _date_sql, 222 exp.DateAdd: _date_delta_sql, 223 exp.DateFromParts: rename_func("MAKE_DATE"), 224 exp.DateSub: _date_delta_sql, 225 exp.DateDiff: lambda self, e: self.func( 226 "DATE_DIFF", f"'{e.args.get('unit') or 'day'}'", e.expression, e.this 227 ), 228 exp.DateStrToDate: datestrtodate_sql, 229 exp.DateToDi: lambda self, e: f"CAST(STRFTIME({self.sql(e, 'this')}, {DuckDB.DATEINT_FORMAT}) AS INT)", 230 exp.Decode: lambda self, e: encode_decode_sql(self, e, "DECODE", replace=False), 231 exp.DiToDate: lambda self, e: f"CAST(STRPTIME(CAST({self.sql(e, 'this')} AS TEXT), {DuckDB.DATEINT_FORMAT}) AS DATE)", 232 exp.Encode: lambda self, e: encode_decode_sql(self, e, "ENCODE", replace=False), 233 exp.Explode: rename_func("UNNEST"), 234 exp.IntDiv: lambda self, e: self.binary(e, "//"), 235 exp.JSONExtract: arrow_json_extract_sql, 236 exp.JSONExtractScalar: arrow_json_extract_scalar_sql, 237 exp.JSONFormat: _json_format_sql, 238 exp.JSONBExtract: arrow_json_extract_sql, 239 exp.JSONBExtractScalar: arrow_json_extract_scalar_sql, 240 exp.LogicalOr: rename_func("BOOL_OR"), 241 exp.LogicalAnd: rename_func("BOOL_AND"), 242 exp.MonthsBetween: lambda self, e: self.func( 243 "DATEDIFF", 244 "'month'", 245 exp.cast(e.expression, "timestamp", copy=True), 246 exp.cast(e.this, "timestamp", copy=True), 247 ), 248 exp.Properties: no_properties_sql, 249 exp.RegexpExtract: regexp_extract_sql, 250 exp.RegexpReplace: regexp_replace_sql, 251 exp.RegexpLike: rename_func("REGEXP_MATCHES"), 252 exp.RegexpSplit: rename_func("STR_SPLIT_REGEX"), 253 exp.SafeDivide: no_safe_divide_sql, 254 exp.Split: rename_func("STR_SPLIT"), 255 exp.SortArray: _sort_array_sql, 256 exp.StrPosition: str_position_sql, 257 exp.StrToDate: lambda self, e: f"CAST({str_to_time_sql(self, e)} AS DATE)", 258 exp.StrToTime: str_to_time_sql, 259 exp.StrToUnix: lambda self, e: f"EPOCH(STRPTIME({self.sql(e, 'this')}, {self.format_time(e)}))", 260 exp.Struct: _struct_sql, 261 exp.TimestampTrunc: timestamptrunc_sql, 262 exp.TimeStrToDate: lambda self, e: f"CAST({self.sql(e, 'this')} AS DATE)", 263 exp.TimeStrToTime: timestrtotime_sql, 264 exp.TimeStrToUnix: lambda self, e: f"EPOCH(CAST({self.sql(e, 'this')} AS TIMESTAMP))", 265 exp.TimeToStr: lambda self, e: f"STRFTIME({self.sql(e, 'this')}, {self.format_time(e)})", 266 exp.TimeToUnix: rename_func("EPOCH"), 267 exp.TsOrDiToDi: lambda self, e: f"CAST(SUBSTR(REPLACE(CAST({self.sql(e, 'this')} AS TEXT), '-', ''), 1, 8) AS INT)", 268 exp.TsOrDsAdd: _ts_or_ds_add_sql, 269 exp.TsOrDsToDate: ts_or_ds_to_date_sql("duckdb"), 270 exp.UnixToStr: lambda self, e: f"STRFTIME(TO_TIMESTAMP({self.sql(e, 'this')}), {self.format_time(e)})", 271 exp.UnixToTime: rename_func("TO_TIMESTAMP"), 272 exp.UnixToTimeStr: lambda self, e: f"CAST(TO_TIMESTAMP({self.sql(e, 'this')}) AS TEXT)", 273 exp.WeekOfYear: rename_func("WEEKOFYEAR"), 274 } 275 276 TYPE_MAPPING = { 277 **generator.Generator.TYPE_MAPPING, 278 exp.DataType.Type.BINARY: "BLOB", 279 exp.DataType.Type.CHAR: "TEXT", 280 exp.DataType.Type.FLOAT: "REAL", 281 exp.DataType.Type.NCHAR: "TEXT", 282 exp.DataType.Type.NVARCHAR: "TEXT", 283 exp.DataType.Type.UINT: "UINTEGER", 284 exp.DataType.Type.VARBINARY: "BLOB", 285 exp.DataType.Type.VARCHAR: "TEXT", 286 } 287 288 STAR_MAPPING = {**generator.Generator.STAR_MAPPING, "except": "EXCLUDE"} 289 290 UNWRAPPED_INTERVAL_VALUES = (exp.Column, exp.Literal, exp.Paren) 291 292 PROPERTIES_LOCATION = { 293 **generator.Generator.PROPERTIES_LOCATION, 294 exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED, 295 } 296 297 def interval_sql(self, expression: exp.Interval) -> str: 298 multiplier: t.Optional[int] = None 299 unit = expression.text("unit").lower() 300 301 if unit.startswith("week"): 302 multiplier = 7 303 if unit.startswith("quarter"): 304 multiplier = 90 305 306 if multiplier: 307 return f"({multiplier} * {super().interval_sql(exp.Interval(this=expression.this.copy(), unit=exp.var('day')))})" 308 309 return super().interval_sql(expression) 310 311 def tablesample_sql( 312 self, expression: exp.TableSample, seed_prefix: str = "SEED", sep: str = " AS " 313 ) -> str: 314 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
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.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.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.OnCommitProperty'>: <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.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 DuckDB.Generator.<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.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.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.WeekOfYear'>: <function rename_func.<locals>.<lambda>>}
TYPE_MAPPING =
{<Type.NCHAR: 'NCHAR'>: 'TEXT', <Type.NVARCHAR: 'NVARCHAR'>: 'TEXT', <Type.MEDIUMTEXT: 'MEDIUMTEXT'>: 'TEXT', <Type.LONGTEXT: 'LONGTEXT'>: 'TEXT', <Type.MEDIUMBLOB: 'MEDIUMBLOB'>: 'BLOB', <Type.LONGBLOB: 'LONGBLOB'>: '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'}
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.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.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'>}
297 def interval_sql(self, expression: exp.Interval) -> str: 298 multiplier: t.Optional[int] = None 299 unit = expression.text("unit").lower() 300 301 if unit.startswith("week"): 302 multiplier = 7 303 if unit.startswith("quarter"): 304 multiplier = 90 305 306 if multiplier: 307 return f"({multiplier} * {super().interval_sql(exp.Interval(this=expression.this.copy(), unit=exp.var('day')))})" 308 309 return super().interval_sql(expression)
def
tablesample_sql( self, expression: sqlglot.expressions.TableSample, seed_prefix: str = 'SEED', sep: str = ' AS ') -> str:
@classmethod
def
can_identify(text: str, identify: str | bool = 'safe') -> bool:
253 @classmethod 254 def can_identify(cls, text: str, identify: str | bool = "safe") -> bool: 255 """Checks if text can be identified given an identify option. 256 257 Args: 258 text: The text to check. 259 identify: 260 "always" or `True`: Always returns true. 261 "safe": True if the identifier is case-insensitive. 262 263 Returns: 264 Whether or not the given text can be identified. 265 """ 266 if identify is True or identify == "always": 267 return True 268 269 if identify == "safe": 270 return not cls.case_sensitive(text) 271 272 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.
Inherited Members
- sqlglot.generator.Generator
- Generator
- 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
- VALUES_AS_TABLE
- 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
- ESCAPE_LINE_BREAK
- 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
- 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
- datatypesize_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_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
- pseudotype_sql
- onconflict_sql
- returning_sql
- rowformatdelimitedproperty_sql
- withtablehint_sql
- indextablehint_sql
- table_sql
- pivot_sql
- tuple_sql
- update_sql
- values_sql
- var_sql
- into_sql
- from_sql
- group_sql
- having_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
- jsonobject_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
- 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