sqlglot.dialects.presto
1from __future__ import annotations 2 3import typing as t 4 5from sqlglot import exp, generator, parser, tokens, transforms 6from sqlglot.dialects.dialect import ( 7 Dialect, 8 binary_from_function, 9 date_trunc_to_time, 10 encode_decode_sql, 11 format_time_lambda, 12 if_sql, 13 left_to_substring_sql, 14 no_ilike_sql, 15 no_pivot_sql, 16 no_safe_divide_sql, 17 regexp_extract_sql, 18 rename_func, 19 right_to_substring_sql, 20 struct_extract_sql, 21 timestamptrunc_sql, 22 timestrtotime_sql, 23) 24from sqlglot.dialects.mysql import MySQL 25from sqlglot.helper import apply_index_offset, seq_get 26from sqlglot.tokens import TokenType 27 28 29def _approx_distinct_sql(self: generator.Generator, expression: exp.ApproxDistinct) -> str: 30 accuracy = expression.args.get("accuracy") 31 accuracy = ", " + self.sql(accuracy) if accuracy else "" 32 return f"APPROX_DISTINCT({self.sql(expression, 'this')}{accuracy})" 33 34 35def _datatype_sql(self: generator.Generator, expression: exp.DataType) -> str: 36 sql = self.datatype_sql(expression) 37 if expression.is_type("timestamptz"): 38 sql = f"{sql} WITH TIME ZONE" 39 return sql 40 41 42def _explode_to_unnest_sql(self: generator.Generator, expression: exp.Lateral) -> str: 43 if isinstance(expression.this, (exp.Explode, exp.Posexplode)): 44 expression = expression.copy() 45 return self.sql( 46 exp.Join( 47 this=exp.Unnest( 48 expressions=[expression.this.this], 49 alias=expression.args.get("alias"), 50 ordinality=isinstance(expression.this, exp.Posexplode), 51 ), 52 kind="cross", 53 ) 54 ) 55 return self.lateral_sql(expression) 56 57 58def _initcap_sql(self: generator.Generator, expression: exp.Initcap) -> str: 59 regex = r"(\w)(\w*)" 60 return f"REGEXP_REPLACE({self.sql(expression, 'this')}, '{regex}', x -> UPPER(x[1]) || LOWER(x[2]))" 61 62 63def _no_sort_array(self: generator.Generator, expression: exp.SortArray) -> str: 64 if expression.args.get("asc") == exp.false(): 65 comparator = "(a, b) -> CASE WHEN a < b THEN 1 WHEN a > b THEN -1 ELSE 0 END" 66 else: 67 comparator = None 68 return self.func("ARRAY_SORT", expression.this, comparator) 69 70 71def _schema_sql(self: generator.Generator, expression: exp.Schema) -> str: 72 if isinstance(expression.parent, exp.Property): 73 columns = ", ".join(f"'{c.name}'" for c in expression.expressions) 74 return f"ARRAY[{columns}]" 75 76 if expression.parent: 77 for schema in expression.parent.find_all(exp.Schema): 78 if isinstance(schema.parent, exp.Property): 79 expression = expression.copy() 80 expression.expressions.extend(schema.expressions) 81 82 return self.schema_sql(expression) 83 84 85def _quantile_sql(self: generator.Generator, expression: exp.Quantile) -> str: 86 self.unsupported("Presto does not support exact quantiles") 87 return f"APPROX_PERCENTILE({self.sql(expression, 'this')}, {self.sql(expression, 'quantile')})" 88 89 90def _str_to_time_sql( 91 self: generator.Generator, expression: exp.StrToDate | exp.StrToTime | exp.TsOrDsToDate 92) -> str: 93 return f"DATE_PARSE({self.sql(expression, 'this')}, {self.format_time(expression)})" 94 95 96def _ts_or_ds_to_date_sql(self: generator.Generator, expression: exp.TsOrDsToDate) -> str: 97 time_format = self.format_time(expression) 98 if time_format and time_format not in (Presto.TIME_FORMAT, Presto.DATE_FORMAT): 99 return exp.cast(_str_to_time_sql(self, expression), "DATE").sql(dialect="presto") 100 return exp.cast(exp.cast(expression.this, "TIMESTAMP", copy=True), "DATE").sql(dialect="presto") 101 102 103def _ts_or_ds_add_sql(self: generator.Generator, expression: exp.TsOrDsAdd) -> str: 104 this = expression.this 105 106 if not isinstance(this, exp.CurrentDate): 107 this = exp.cast(exp.cast(expression.this, "TIMESTAMP", copy=True), "DATE") 108 109 return self.func( 110 "DATE_ADD", 111 exp.Literal.string(expression.text("unit") or "day"), 112 expression.expression, 113 this, 114 ) 115 116 117def _approx_percentile(args: t.List) -> exp.Expression: 118 if len(args) == 4: 119 return exp.ApproxQuantile( 120 this=seq_get(args, 0), 121 weight=seq_get(args, 1), 122 quantile=seq_get(args, 2), 123 accuracy=seq_get(args, 3), 124 ) 125 if len(args) == 3: 126 return exp.ApproxQuantile( 127 this=seq_get(args, 0), quantile=seq_get(args, 1), accuracy=seq_get(args, 2) 128 ) 129 return exp.ApproxQuantile.from_arg_list(args) 130 131 132def _from_unixtime(args: t.List) -> exp.Expression: 133 if len(args) == 3: 134 return exp.UnixToTime( 135 this=seq_get(args, 0), 136 hours=seq_get(args, 1), 137 minutes=seq_get(args, 2), 138 ) 139 if len(args) == 2: 140 return exp.UnixToTime(this=seq_get(args, 0), zone=seq_get(args, 1)) 141 142 return exp.UnixToTime.from_arg_list(args) 143 144 145def _parse_element_at(args: t.List) -> exp.SafeBracket: 146 this = seq_get(args, 0) 147 index = seq_get(args, 1) 148 assert isinstance(this, exp.Expression) and isinstance(index, exp.Expression) 149 return exp.SafeBracket(this=this, expressions=apply_index_offset(this, [index], -1)) 150 151 152def _unnest_sequence(expression: exp.Expression) -> exp.Expression: 153 if isinstance(expression, exp.Table): 154 if isinstance(expression.this, exp.GenerateSeries): 155 unnest = exp.Unnest(expressions=[expression.this]) 156 157 if expression.alias: 158 return exp.alias_(unnest, alias="_u", table=[expression.alias], copy=False) 159 return unnest 160 return expression 161 162 163class Presto(Dialect): 164 INDEX_OFFSET = 1 165 NULL_ORDERING = "nulls_are_last" 166 TIME_FORMAT = MySQL.TIME_FORMAT 167 TIME_MAPPING = MySQL.TIME_MAPPING 168 STRICT_STRING_CONCAT = True 169 170 # https://github.com/trinodb/trino/issues/17 171 # https://github.com/trinodb/trino/issues/12289 172 # https://github.com/prestodb/presto/issues/2863 173 RESOLVES_IDENTIFIERS_AS_UPPERCASE = None 174 175 class Tokenizer(tokens.Tokenizer): 176 KEYWORDS = { 177 **tokens.Tokenizer.KEYWORDS, 178 "START": TokenType.BEGIN, 179 "MATCH_RECOGNIZE": TokenType.MATCH_RECOGNIZE, 180 "ROW": TokenType.STRUCT, 181 "IPADDRESS": TokenType.IPADDRESS, 182 "IPPREFIX": TokenType.IPPREFIX, 183 } 184 185 class Parser(parser.Parser): 186 FUNCTIONS = { 187 **parser.Parser.FUNCTIONS, 188 "APPROX_DISTINCT": exp.ApproxDistinct.from_arg_list, 189 "APPROX_PERCENTILE": _approx_percentile, 190 "BITWISE_AND": binary_from_function(exp.BitwiseAnd), 191 "BITWISE_NOT": lambda args: exp.BitwiseNot(this=seq_get(args, 0)), 192 "BITWISE_OR": binary_from_function(exp.BitwiseOr), 193 "BITWISE_XOR": binary_from_function(exp.BitwiseXor), 194 "CARDINALITY": exp.ArraySize.from_arg_list, 195 "CONTAINS": exp.ArrayContains.from_arg_list, 196 "DATE_ADD": lambda args: exp.DateAdd( 197 this=seq_get(args, 2), expression=seq_get(args, 1), unit=seq_get(args, 0) 198 ), 199 "DATE_DIFF": lambda args: exp.DateDiff( 200 this=seq_get(args, 2), expression=seq_get(args, 1), unit=seq_get(args, 0) 201 ), 202 "DATE_FORMAT": format_time_lambda(exp.TimeToStr, "presto"), 203 "DATE_PARSE": format_time_lambda(exp.StrToTime, "presto"), 204 "DATE_TRUNC": date_trunc_to_time, 205 "ELEMENT_AT": _parse_element_at, 206 "FROM_HEX": exp.Unhex.from_arg_list, 207 "FROM_UNIXTIME": _from_unixtime, 208 "FROM_UTF8": lambda args: exp.Decode( 209 this=seq_get(args, 0), replace=seq_get(args, 1), charset=exp.Literal.string("utf-8") 210 ), 211 "NOW": exp.CurrentTimestamp.from_arg_list, 212 "REGEXP_EXTRACT": lambda args: exp.RegexpExtract( 213 this=seq_get(args, 0), expression=seq_get(args, 1), group=seq_get(args, 2) 214 ), 215 "SEQUENCE": exp.GenerateSeries.from_arg_list, 216 "STRPOS": lambda args: exp.StrPosition( 217 this=seq_get(args, 0), substr=seq_get(args, 1), instance=seq_get(args, 2) 218 ), 219 "TO_UNIXTIME": exp.TimeToUnix.from_arg_list, 220 "TO_HEX": exp.Hex.from_arg_list, 221 "TO_UTF8": lambda args: exp.Encode( 222 this=seq_get(args, 0), charset=exp.Literal.string("utf-8") 223 ), 224 } 225 FUNCTION_PARSERS = parser.Parser.FUNCTION_PARSERS.copy() 226 FUNCTION_PARSERS.pop("TRIM") 227 228 class Generator(generator.Generator): 229 INTERVAL_ALLOWS_PLURAL_FORM = False 230 JOIN_HINTS = False 231 TABLE_HINTS = False 232 QUERY_HINTS = False 233 IS_BOOL_ALLOWED = False 234 STRUCT_DELIMITER = ("(", ")") 235 236 PROPERTIES_LOCATION = { 237 **generator.Generator.PROPERTIES_LOCATION, 238 exp.LocationProperty: exp.Properties.Location.UNSUPPORTED, 239 exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED, 240 } 241 242 TYPE_MAPPING = { 243 **generator.Generator.TYPE_MAPPING, 244 exp.DataType.Type.INT: "INTEGER", 245 exp.DataType.Type.FLOAT: "REAL", 246 exp.DataType.Type.BINARY: "VARBINARY", 247 exp.DataType.Type.TEXT: "VARCHAR", 248 exp.DataType.Type.TIMESTAMPTZ: "TIMESTAMP", 249 exp.DataType.Type.STRUCT: "ROW", 250 } 251 252 TRANSFORMS = { 253 **generator.Generator.TRANSFORMS, 254 exp.ApproxDistinct: _approx_distinct_sql, 255 exp.ApproxQuantile: rename_func("APPROX_PERCENTILE"), 256 exp.Array: lambda self, e: f"ARRAY[{self.expressions(e, flat=True)}]", 257 exp.ArrayConcat: rename_func("CONCAT"), 258 exp.ArrayContains: rename_func("CONTAINS"), 259 exp.ArraySize: rename_func("CARDINALITY"), 260 exp.BitwiseAnd: lambda self, e: f"BITWISE_AND({self.sql(e, 'this')}, {self.sql(e, 'expression')})", 261 exp.BitwiseLeftShift: lambda self, e: f"BITWISE_ARITHMETIC_SHIFT_LEFT({self.sql(e, 'this')}, {self.sql(e, 'expression')})", 262 exp.BitwiseNot: lambda self, e: f"BITWISE_NOT({self.sql(e, 'this')})", 263 exp.BitwiseOr: lambda self, e: f"BITWISE_OR({self.sql(e, 'this')}, {self.sql(e, 'expression')})", 264 exp.BitwiseRightShift: lambda self, e: f"BITWISE_ARITHMETIC_SHIFT_RIGHT({self.sql(e, 'this')}, {self.sql(e, 'expression')})", 265 exp.BitwiseXor: lambda self, e: f"BITWISE_XOR({self.sql(e, 'this')}, {self.sql(e, 'expression')})", 266 exp.Cast: transforms.preprocess([transforms.epoch_cast_to_ts]), 267 exp.CurrentTimestamp: lambda *_: "CURRENT_TIMESTAMP", 268 exp.DataType: _datatype_sql, 269 exp.DateAdd: lambda self, e: self.func( 270 "DATE_ADD", exp.Literal.string(e.text("unit") or "day"), e.expression, e.this 271 ), 272 exp.DateDiff: lambda self, e: self.func( 273 "DATE_DIFF", exp.Literal.string(e.text("unit") or "day"), e.expression, e.this 274 ), 275 exp.DateStrToDate: lambda self, e: f"CAST(DATE_PARSE({self.sql(e, 'this')}, {Presto.DATE_FORMAT}) AS DATE)", 276 exp.DateToDi: lambda self, e: f"CAST(DATE_FORMAT({self.sql(e, 'this')}, {Presto.DATEINT_FORMAT}) AS INT)", 277 exp.Decode: lambda self, e: encode_decode_sql(self, e, "FROM_UTF8"), 278 exp.DiToDate: lambda self, e: f"CAST(DATE_PARSE(CAST({self.sql(e, 'this')} AS VARCHAR), {Presto.DATEINT_FORMAT}) AS DATE)", 279 exp.Encode: lambda self, e: encode_decode_sql(self, e, "TO_UTF8"), 280 exp.FileFormatProperty: lambda self, e: f"FORMAT='{e.name.upper()}'", 281 exp.Group: transforms.preprocess([transforms.unalias_group]), 282 exp.Hex: rename_func("TO_HEX"), 283 exp.If: if_sql, 284 exp.ILike: no_ilike_sql, 285 exp.Initcap: _initcap_sql, 286 exp.Lateral: _explode_to_unnest_sql, 287 exp.Left: left_to_substring_sql, 288 exp.Levenshtein: rename_func("LEVENSHTEIN_DISTANCE"), 289 exp.LogicalAnd: rename_func("BOOL_AND"), 290 exp.LogicalOr: rename_func("BOOL_OR"), 291 exp.Pivot: no_pivot_sql, 292 exp.Quantile: _quantile_sql, 293 exp.RegexpExtract: regexp_extract_sql, 294 exp.Right: right_to_substring_sql, 295 exp.SafeBracket: lambda self, e: self.func( 296 "ELEMENT_AT", e.this, seq_get(apply_index_offset(e.this, e.expressions, 1), 0) 297 ), 298 exp.SafeDivide: no_safe_divide_sql, 299 exp.Schema: _schema_sql, 300 exp.Select: transforms.preprocess( 301 [ 302 transforms.eliminate_qualify, 303 transforms.eliminate_distinct_on, 304 transforms.explode_to_unnest, 305 ] 306 ), 307 exp.SortArray: _no_sort_array, 308 exp.StrPosition: rename_func("STRPOS"), 309 exp.StrToDate: lambda self, e: f"CAST({_str_to_time_sql(self, e)} AS DATE)", 310 exp.StrToTime: _str_to_time_sql, 311 exp.StrToUnix: lambda self, e: f"TO_UNIXTIME(DATE_PARSE({self.sql(e, 'this')}, {self.format_time(e)}))", 312 exp.StructExtract: struct_extract_sql, 313 exp.Table: transforms.preprocess([_unnest_sequence]), 314 exp.TimestampTrunc: timestamptrunc_sql, 315 exp.TimeStrToDate: timestrtotime_sql, 316 exp.TimeStrToTime: timestrtotime_sql, 317 exp.TimeStrToUnix: lambda self, e: f"TO_UNIXTIME(DATE_PARSE({self.sql(e, 'this')}, {Presto.TIME_FORMAT}))", 318 exp.TimeToStr: lambda self, e: f"DATE_FORMAT({self.sql(e, 'this')}, {self.format_time(e)})", 319 exp.TimeToUnix: rename_func("TO_UNIXTIME"), 320 exp.TryCast: transforms.preprocess([transforms.epoch_cast_to_ts]), 321 exp.TsOrDiToDi: lambda self, e: f"CAST(SUBSTR(REPLACE(CAST({self.sql(e, 'this')} AS VARCHAR), '-', ''), 1, 8) AS INT)", 322 exp.TsOrDsAdd: _ts_or_ds_add_sql, 323 exp.TsOrDsToDate: _ts_or_ds_to_date_sql, 324 exp.Unhex: rename_func("FROM_HEX"), 325 exp.UnixToStr: lambda self, e: f"DATE_FORMAT(FROM_UNIXTIME({self.sql(e, 'this')}), {self.format_time(e)})", 326 exp.UnixToTime: rename_func("FROM_UNIXTIME"), 327 exp.UnixToTimeStr: lambda self, e: f"CAST(FROM_UNIXTIME({self.sql(e, 'this')}) AS VARCHAR)", 328 exp.VariancePop: rename_func("VAR_POP"), 329 exp.With: transforms.preprocess([transforms.add_recursive_cte_column_names]), 330 exp.WithinGroup: transforms.preprocess( 331 [transforms.remove_within_group_for_percentiles] 332 ), 333 } 334 335 def interval_sql(self, expression: exp.Interval) -> str: 336 unit = self.sql(expression, "unit") 337 if expression.this and unit.lower().startswith("week"): 338 return f"({expression.this.name} * INTERVAL '7' day)" 339 return super().interval_sql(expression) 340 341 def transaction_sql(self, expression: exp.Transaction) -> str: 342 modes = expression.args.get("modes") 343 modes = f" {', '.join(modes)}" if modes else "" 344 return f"START TRANSACTION{modes}" 345 346 def generateseries_sql(self, expression: exp.GenerateSeries) -> str: 347 start = expression.args["start"] 348 end = expression.args["end"] 349 step = expression.args.get("step") 350 351 if isinstance(start, exp.Cast): 352 target_type = start.to 353 elif isinstance(end, exp.Cast): 354 target_type = end.to 355 else: 356 target_type = None 357 358 if target_type and target_type.is_type("timestamp"): 359 to = target_type.copy() 360 361 if target_type is start.to: 362 end = exp.cast(end, to) 363 else: 364 start = exp.cast(start, to) 365 366 return self.func("SEQUENCE", start, end, step) 367 368 def offset_limit_modifiers( 369 self, expression: exp.Expression, fetch: bool, limit: t.Optional[exp.Fetch | exp.Limit] 370 ) -> t.List[str]: 371 return [ 372 self.sql(expression, "offset"), 373 self.sql(limit), 374 ]
164class Presto(Dialect): 165 INDEX_OFFSET = 1 166 NULL_ORDERING = "nulls_are_last" 167 TIME_FORMAT = MySQL.TIME_FORMAT 168 TIME_MAPPING = MySQL.TIME_MAPPING 169 STRICT_STRING_CONCAT = True 170 171 # https://github.com/trinodb/trino/issues/17 172 # https://github.com/trinodb/trino/issues/12289 173 # https://github.com/prestodb/presto/issues/2863 174 RESOLVES_IDENTIFIERS_AS_UPPERCASE = None 175 176 class Tokenizer(tokens.Tokenizer): 177 KEYWORDS = { 178 **tokens.Tokenizer.KEYWORDS, 179 "START": TokenType.BEGIN, 180 "MATCH_RECOGNIZE": TokenType.MATCH_RECOGNIZE, 181 "ROW": TokenType.STRUCT, 182 "IPADDRESS": TokenType.IPADDRESS, 183 "IPPREFIX": TokenType.IPPREFIX, 184 } 185 186 class Parser(parser.Parser): 187 FUNCTIONS = { 188 **parser.Parser.FUNCTIONS, 189 "APPROX_DISTINCT": exp.ApproxDistinct.from_arg_list, 190 "APPROX_PERCENTILE": _approx_percentile, 191 "BITWISE_AND": binary_from_function(exp.BitwiseAnd), 192 "BITWISE_NOT": lambda args: exp.BitwiseNot(this=seq_get(args, 0)), 193 "BITWISE_OR": binary_from_function(exp.BitwiseOr), 194 "BITWISE_XOR": binary_from_function(exp.BitwiseXor), 195 "CARDINALITY": exp.ArraySize.from_arg_list, 196 "CONTAINS": exp.ArrayContains.from_arg_list, 197 "DATE_ADD": lambda args: exp.DateAdd( 198 this=seq_get(args, 2), expression=seq_get(args, 1), unit=seq_get(args, 0) 199 ), 200 "DATE_DIFF": lambda args: exp.DateDiff( 201 this=seq_get(args, 2), expression=seq_get(args, 1), unit=seq_get(args, 0) 202 ), 203 "DATE_FORMAT": format_time_lambda(exp.TimeToStr, "presto"), 204 "DATE_PARSE": format_time_lambda(exp.StrToTime, "presto"), 205 "DATE_TRUNC": date_trunc_to_time, 206 "ELEMENT_AT": _parse_element_at, 207 "FROM_HEX": exp.Unhex.from_arg_list, 208 "FROM_UNIXTIME": _from_unixtime, 209 "FROM_UTF8": lambda args: exp.Decode( 210 this=seq_get(args, 0), replace=seq_get(args, 1), charset=exp.Literal.string("utf-8") 211 ), 212 "NOW": exp.CurrentTimestamp.from_arg_list, 213 "REGEXP_EXTRACT": lambda args: exp.RegexpExtract( 214 this=seq_get(args, 0), expression=seq_get(args, 1), group=seq_get(args, 2) 215 ), 216 "SEQUENCE": exp.GenerateSeries.from_arg_list, 217 "STRPOS": lambda args: exp.StrPosition( 218 this=seq_get(args, 0), substr=seq_get(args, 1), instance=seq_get(args, 2) 219 ), 220 "TO_UNIXTIME": exp.TimeToUnix.from_arg_list, 221 "TO_HEX": exp.Hex.from_arg_list, 222 "TO_UTF8": lambda args: exp.Encode( 223 this=seq_get(args, 0), charset=exp.Literal.string("utf-8") 224 ), 225 } 226 FUNCTION_PARSERS = parser.Parser.FUNCTION_PARSERS.copy() 227 FUNCTION_PARSERS.pop("TRIM") 228 229 class Generator(generator.Generator): 230 INTERVAL_ALLOWS_PLURAL_FORM = False 231 JOIN_HINTS = False 232 TABLE_HINTS = False 233 QUERY_HINTS = False 234 IS_BOOL_ALLOWED = False 235 STRUCT_DELIMITER = ("(", ")") 236 237 PROPERTIES_LOCATION = { 238 **generator.Generator.PROPERTIES_LOCATION, 239 exp.LocationProperty: exp.Properties.Location.UNSUPPORTED, 240 exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED, 241 } 242 243 TYPE_MAPPING = { 244 **generator.Generator.TYPE_MAPPING, 245 exp.DataType.Type.INT: "INTEGER", 246 exp.DataType.Type.FLOAT: "REAL", 247 exp.DataType.Type.BINARY: "VARBINARY", 248 exp.DataType.Type.TEXT: "VARCHAR", 249 exp.DataType.Type.TIMESTAMPTZ: "TIMESTAMP", 250 exp.DataType.Type.STRUCT: "ROW", 251 } 252 253 TRANSFORMS = { 254 **generator.Generator.TRANSFORMS, 255 exp.ApproxDistinct: _approx_distinct_sql, 256 exp.ApproxQuantile: rename_func("APPROX_PERCENTILE"), 257 exp.Array: lambda self, e: f"ARRAY[{self.expressions(e, flat=True)}]", 258 exp.ArrayConcat: rename_func("CONCAT"), 259 exp.ArrayContains: rename_func("CONTAINS"), 260 exp.ArraySize: rename_func("CARDINALITY"), 261 exp.BitwiseAnd: lambda self, e: f"BITWISE_AND({self.sql(e, 'this')}, {self.sql(e, 'expression')})", 262 exp.BitwiseLeftShift: lambda self, e: f"BITWISE_ARITHMETIC_SHIFT_LEFT({self.sql(e, 'this')}, {self.sql(e, 'expression')})", 263 exp.BitwiseNot: lambda self, e: f"BITWISE_NOT({self.sql(e, 'this')})", 264 exp.BitwiseOr: lambda self, e: f"BITWISE_OR({self.sql(e, 'this')}, {self.sql(e, 'expression')})", 265 exp.BitwiseRightShift: lambda self, e: f"BITWISE_ARITHMETIC_SHIFT_RIGHT({self.sql(e, 'this')}, {self.sql(e, 'expression')})", 266 exp.BitwiseXor: lambda self, e: f"BITWISE_XOR({self.sql(e, 'this')}, {self.sql(e, 'expression')})", 267 exp.Cast: transforms.preprocess([transforms.epoch_cast_to_ts]), 268 exp.CurrentTimestamp: lambda *_: "CURRENT_TIMESTAMP", 269 exp.DataType: _datatype_sql, 270 exp.DateAdd: lambda self, e: self.func( 271 "DATE_ADD", exp.Literal.string(e.text("unit") or "day"), e.expression, e.this 272 ), 273 exp.DateDiff: lambda self, e: self.func( 274 "DATE_DIFF", exp.Literal.string(e.text("unit") or "day"), e.expression, e.this 275 ), 276 exp.DateStrToDate: lambda self, e: f"CAST(DATE_PARSE({self.sql(e, 'this')}, {Presto.DATE_FORMAT}) AS DATE)", 277 exp.DateToDi: lambda self, e: f"CAST(DATE_FORMAT({self.sql(e, 'this')}, {Presto.DATEINT_FORMAT}) AS INT)", 278 exp.Decode: lambda self, e: encode_decode_sql(self, e, "FROM_UTF8"), 279 exp.DiToDate: lambda self, e: f"CAST(DATE_PARSE(CAST({self.sql(e, 'this')} AS VARCHAR), {Presto.DATEINT_FORMAT}) AS DATE)", 280 exp.Encode: lambda self, e: encode_decode_sql(self, e, "TO_UTF8"), 281 exp.FileFormatProperty: lambda self, e: f"FORMAT='{e.name.upper()}'", 282 exp.Group: transforms.preprocess([transforms.unalias_group]), 283 exp.Hex: rename_func("TO_HEX"), 284 exp.If: if_sql, 285 exp.ILike: no_ilike_sql, 286 exp.Initcap: _initcap_sql, 287 exp.Lateral: _explode_to_unnest_sql, 288 exp.Left: left_to_substring_sql, 289 exp.Levenshtein: rename_func("LEVENSHTEIN_DISTANCE"), 290 exp.LogicalAnd: rename_func("BOOL_AND"), 291 exp.LogicalOr: rename_func("BOOL_OR"), 292 exp.Pivot: no_pivot_sql, 293 exp.Quantile: _quantile_sql, 294 exp.RegexpExtract: regexp_extract_sql, 295 exp.Right: right_to_substring_sql, 296 exp.SafeBracket: lambda self, e: self.func( 297 "ELEMENT_AT", e.this, seq_get(apply_index_offset(e.this, e.expressions, 1), 0) 298 ), 299 exp.SafeDivide: no_safe_divide_sql, 300 exp.Schema: _schema_sql, 301 exp.Select: transforms.preprocess( 302 [ 303 transforms.eliminate_qualify, 304 transforms.eliminate_distinct_on, 305 transforms.explode_to_unnest, 306 ] 307 ), 308 exp.SortArray: _no_sort_array, 309 exp.StrPosition: rename_func("STRPOS"), 310 exp.StrToDate: lambda self, e: f"CAST({_str_to_time_sql(self, e)} AS DATE)", 311 exp.StrToTime: _str_to_time_sql, 312 exp.StrToUnix: lambda self, e: f"TO_UNIXTIME(DATE_PARSE({self.sql(e, 'this')}, {self.format_time(e)}))", 313 exp.StructExtract: struct_extract_sql, 314 exp.Table: transforms.preprocess([_unnest_sequence]), 315 exp.TimestampTrunc: timestamptrunc_sql, 316 exp.TimeStrToDate: timestrtotime_sql, 317 exp.TimeStrToTime: timestrtotime_sql, 318 exp.TimeStrToUnix: lambda self, e: f"TO_UNIXTIME(DATE_PARSE({self.sql(e, 'this')}, {Presto.TIME_FORMAT}))", 319 exp.TimeToStr: lambda self, e: f"DATE_FORMAT({self.sql(e, 'this')}, {self.format_time(e)})", 320 exp.TimeToUnix: rename_func("TO_UNIXTIME"), 321 exp.TryCast: transforms.preprocess([transforms.epoch_cast_to_ts]), 322 exp.TsOrDiToDi: lambda self, e: f"CAST(SUBSTR(REPLACE(CAST({self.sql(e, 'this')} AS VARCHAR), '-', ''), 1, 8) AS INT)", 323 exp.TsOrDsAdd: _ts_or_ds_add_sql, 324 exp.TsOrDsToDate: _ts_or_ds_to_date_sql, 325 exp.Unhex: rename_func("FROM_HEX"), 326 exp.UnixToStr: lambda self, e: f"DATE_FORMAT(FROM_UNIXTIME({self.sql(e, 'this')}), {self.format_time(e)})", 327 exp.UnixToTime: rename_func("FROM_UNIXTIME"), 328 exp.UnixToTimeStr: lambda self, e: f"CAST(FROM_UNIXTIME({self.sql(e, 'this')}) AS VARCHAR)", 329 exp.VariancePop: rename_func("VAR_POP"), 330 exp.With: transforms.preprocess([transforms.add_recursive_cte_column_names]), 331 exp.WithinGroup: transforms.preprocess( 332 [transforms.remove_within_group_for_percentiles] 333 ), 334 } 335 336 def interval_sql(self, expression: exp.Interval) -> str: 337 unit = self.sql(expression, "unit") 338 if expression.this and unit.lower().startswith("week"): 339 return f"({expression.this.name} * INTERVAL '7' day)" 340 return super().interval_sql(expression) 341 342 def transaction_sql(self, expression: exp.Transaction) -> str: 343 modes = expression.args.get("modes") 344 modes = f" {', '.join(modes)}" if modes else "" 345 return f"START TRANSACTION{modes}" 346 347 def generateseries_sql(self, expression: exp.GenerateSeries) -> str: 348 start = expression.args["start"] 349 end = expression.args["end"] 350 step = expression.args.get("step") 351 352 if isinstance(start, exp.Cast): 353 target_type = start.to 354 elif isinstance(end, exp.Cast): 355 target_type = end.to 356 else: 357 target_type = None 358 359 if target_type and target_type.is_type("timestamp"): 360 to = target_type.copy() 361 362 if target_type is start.to: 363 end = exp.cast(end, to) 364 else: 365 start = exp.cast(start, to) 366 367 return self.func("SEQUENCE", start, end, step) 368 369 def offset_limit_modifiers( 370 self, expression: exp.Expression, fetch: bool, limit: t.Optional[exp.Fetch | exp.Limit] 371 ) -> t.List[str]: 372 return [ 373 self.sql(expression, "offset"), 374 self.sql(limit), 375 ]
TIME_MAPPING: Dict[str, str] =
{'%M': '%B', '%c': '%-m', '%e': '%-d', '%h': '%I', '%i': '%M', '%s': '%S', '%S': '%S', '%u': '%W', '%k': '%-H', '%l': '%-I', '%T': '%H:%M:%S', '%W': '%a'}
tokenizer_class =
<class 'sqlglot.dialects.presto.Presto.Tokenizer'>
parser_class =
<class 'sqlglot.dialects.presto.Presto.Parser'>
generator_class =
<class 'sqlglot.dialects.presto.Presto.Generator'>
TIME_TRIE: Dict =
{'%': {'M': {0: True}, 'c': {0: True}, 'e': {0: True}, 'h': {0: True}, 'i': {0: True}, 's': {0: True}, 'S': {0: True}, 'u': {0: True}, 'k': {0: True}, 'l': {0: True}, 'T': {0: True}, 'W': {0: True}}}
FORMAT_TRIE: Dict =
{'%': {'M': {0: True}, 'c': {0: True}, 'e': {0: True}, 'h': {0: True}, 'i': {0: True}, 's': {0: True}, 'S': {0: True}, 'u': {0: True}, 'k': {0: True}, 'l': {0: True}, 'T': {0: True}, 'W': {0: True}}}
INVERSE_TIME_MAPPING: Dict[str, str] =
{'%B': '%M', '%-m': '%c', '%-d': '%e', '%I': '%h', '%M': '%i', '%S': '%S', '%W': '%u', '%-H': '%k', '%-I': '%l', '%H:%M:%S': '%T', '%a': '%W'}
INVERSE_TIME_TRIE: Dict =
{'%': {'B': {0: True}, '-': {'m': {0: True}, 'd': {0: True}, 'H': {0: True}, 'I': {0: True}}, 'I': {0: True}, 'M': {0: True}, 'S': {0: True}, 'W': {0: True}, 'H': {':': {'%': {'M': {':': {'%': {'S': {0: True}}}}}}}, 'a': {0: True}}}
Inherited Members
- sqlglot.dialects.dialect.Dialect
- UNNEST_COLUMN_ONLY
- ALIAS_POST_TABLESAMPLE
- IDENTIFIERS_CAN_START_WITH_DIGIT
- NORMALIZE_FUNCTIONS
- DATE_FORMAT
- DATEINT_FORMAT
- 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
176 class Tokenizer(tokens.Tokenizer): 177 KEYWORDS = { 178 **tokens.Tokenizer.KEYWORDS, 179 "START": TokenType.BEGIN, 180 "MATCH_RECOGNIZE": TokenType.MATCH_RECOGNIZE, 181 "ROW": TokenType.STRUCT, 182 "IPADDRESS": TokenType.IPADDRESS, 183 "IPPREFIX": TokenType.IPPREFIX, 184 }
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'>, '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'>, '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.STRUCT: 'STRUCT'>, '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.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.CHAR: 'CHAR'>, '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.TEXT: 'TEXT'>, 'TEXT': <TokenType.TEXT: 'TEXT'>, 'CLOB': <TokenType.TEXT: 'TEXT'>, 'LONGVARCHAR': <TokenType.TEXT: 'TEXT'>, 'BINARY': <TokenType.BINARY: 'BINARY'>, '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'>, 'START': <TokenType.BEGIN: 'BEGIN'>, 'MATCH_RECOGNIZE': <TokenType.MATCH_RECOGNIZE: 'MATCH_RECOGNIZE'>, 'IPADDRESS': <TokenType.IPADDRESS: 'IPADDRESS'>, 'IPPREFIX': <TokenType.IPPREFIX: 'IPPREFIX'>}
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
186 class Parser(parser.Parser): 187 FUNCTIONS = { 188 **parser.Parser.FUNCTIONS, 189 "APPROX_DISTINCT": exp.ApproxDistinct.from_arg_list, 190 "APPROX_PERCENTILE": _approx_percentile, 191 "BITWISE_AND": binary_from_function(exp.BitwiseAnd), 192 "BITWISE_NOT": lambda args: exp.BitwiseNot(this=seq_get(args, 0)), 193 "BITWISE_OR": binary_from_function(exp.BitwiseOr), 194 "BITWISE_XOR": binary_from_function(exp.BitwiseXor), 195 "CARDINALITY": exp.ArraySize.from_arg_list, 196 "CONTAINS": exp.ArrayContains.from_arg_list, 197 "DATE_ADD": lambda args: exp.DateAdd( 198 this=seq_get(args, 2), expression=seq_get(args, 1), unit=seq_get(args, 0) 199 ), 200 "DATE_DIFF": lambda args: exp.DateDiff( 201 this=seq_get(args, 2), expression=seq_get(args, 1), unit=seq_get(args, 0) 202 ), 203 "DATE_FORMAT": format_time_lambda(exp.TimeToStr, "presto"), 204 "DATE_PARSE": format_time_lambda(exp.StrToTime, "presto"), 205 "DATE_TRUNC": date_trunc_to_time, 206 "ELEMENT_AT": _parse_element_at, 207 "FROM_HEX": exp.Unhex.from_arg_list, 208 "FROM_UNIXTIME": _from_unixtime, 209 "FROM_UTF8": lambda args: exp.Decode( 210 this=seq_get(args, 0), replace=seq_get(args, 1), charset=exp.Literal.string("utf-8") 211 ), 212 "NOW": exp.CurrentTimestamp.from_arg_list, 213 "REGEXP_EXTRACT": lambda args: exp.RegexpExtract( 214 this=seq_get(args, 0), expression=seq_get(args, 1), group=seq_get(args, 2) 215 ), 216 "SEQUENCE": exp.GenerateSeries.from_arg_list, 217 "STRPOS": lambda args: exp.StrPosition( 218 this=seq_get(args, 0), substr=seq_get(args, 1), instance=seq_get(args, 2) 219 ), 220 "TO_UNIXTIME": exp.TimeToUnix.from_arg_list, 221 "TO_HEX": exp.Hex.from_arg_list, 222 "TO_UTF8": lambda args: exp.Encode( 223 this=seq_get(args, 0), charset=exp.Literal.string("utf-8") 224 ), 225 } 226 FUNCTION_PARSERS = parser.Parser.FUNCTION_PARSERS.copy() 227 FUNCTION_PARSERS.pop("TRIM")
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
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.ArraySort'>>, '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': <function Presto.Parser.<lambda>>, 'DATEDIFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateDiff'>>, 'DATE_DIFF': <function Presto.Parser.<lambda>>, '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 Presto.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': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Xor'>>, 'YEAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Year'>>, 'GLOB': <function Parser.<lambda>>, 'LIKE': <function parse_like>, 'APPROX_PERCENTILE': <function _approx_percentile>, 'BITWISE_AND': <function binary_from_function.<locals>.<lambda>>, 'BITWISE_NOT': <function Presto.Parser.<lambda>>, 'BITWISE_OR': <function binary_from_function.<locals>.<lambda>>, 'BITWISE_XOR': <function binary_from_function.<locals>.<lambda>>, 'CARDINALITY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArraySize'>>, 'CONTAINS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayContains'>>, 'DATE_FORMAT': <function format_time_lambda.<locals>._format_time>, 'DATE_PARSE': <function format_time_lambda.<locals>._format_time>, 'ELEMENT_AT': <function _parse_element_at>, 'FROM_HEX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Unhex'>>, 'FROM_UNIXTIME': <function _from_unixtime>, 'FROM_UTF8': <function Presto.Parser.<lambda>>, 'NOW': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CurrentTimestamp'>>, 'SEQUENCE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.GenerateSeries'>>, 'STRPOS': <function Presto.Parser.<lambda>>, 'TO_UNIXTIME': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeToUnix'>>, 'TO_HEX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Hex'>>, 'TO_UTF8': <function Presto.Parser.<lambda>>}
FUNCTION_PARSERS =
{'ANY_VALUE': <function Parser.<lambda>>, 'CAST': <function Parser.<lambda>>, 'CONCAT': <function Parser.<lambda>>, 'CONVERT': <function Parser.<lambda>>, 'DECODE': <function 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>>, 'TRY_CAST': <function Parser.<lambda>>, 'TRY_CONVERT': <function Parser.<lambda>>}
SET_TRIE: Dict =
{'GLOBAL': {0: True}, 'LOCAL': {0: True}, 'SESSION': {0: True}, 'TRANSACTION': {0: True}}
FORMAT_TRIE: Dict =
{'%': {'M': {0: True}, 'c': {0: True}, 'e': {0: True}, 'h': {0: True}, 'i': {0: True}, 's': {0: True}, 'S': {0: True}, 'u': {0: True}, 'k': {0: True}, 'l': {0: True}, 'T': {0: True}, 'W': {0: True}}}
TIME_MAPPING: Dict[str, str] =
{'%M': '%B', '%c': '%-m', '%e': '%-d', '%h': '%I', '%i': '%M', '%s': '%S', '%S': '%S', '%u': '%W', '%k': '%-H', '%l': '%-I', '%T': '%H:%M:%S', '%W': '%a'}
TIME_TRIE: Dict =
{'%': {'M': {0: True}, 'c': {0: True}, 'e': {0: True}, 'h': {0: True}, 'i': {0: True}, 's': {0: True}, 'S': {0: True}, 'u': {0: True}, 'k': {0: True}, 'l': {0: True}, 'T': {0: True}, 'W': {0: True}}}
Inherited Members
- sqlglot.parser.Parser
- Parser
- NO_PAREN_FUNCTIONS
- NESTED_TYPE_TOKENS
- ENUM_TYPE_TOKENS
- 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
- BITWISE
- 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
- CONCAT_NULL_OUTPUTS_STRING
- PREFIXED_PIVOT_COLUMNS
- IDENTIFY_PIVOT_STRINGS
- LOG_BASE_FIRST
- LOG_DEFAULTS_TO_LN
- UNNEST_COLUMN_ONLY
- ALIAS_POST_TABLESAMPLE
- NORMALIZE_FUNCTIONS
- FORMAT_MAPPING
- error_level
- error_message_context
- max_errors
- reset
- parse
- parse_into
- check_errors
- raise_error
- expression
- validate_expression
- errors
- sql
229 class Generator(generator.Generator): 230 INTERVAL_ALLOWS_PLURAL_FORM = False 231 JOIN_HINTS = False 232 TABLE_HINTS = False 233 QUERY_HINTS = False 234 IS_BOOL_ALLOWED = False 235 STRUCT_DELIMITER = ("(", ")") 236 237 PROPERTIES_LOCATION = { 238 **generator.Generator.PROPERTIES_LOCATION, 239 exp.LocationProperty: exp.Properties.Location.UNSUPPORTED, 240 exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED, 241 } 242 243 TYPE_MAPPING = { 244 **generator.Generator.TYPE_MAPPING, 245 exp.DataType.Type.INT: "INTEGER", 246 exp.DataType.Type.FLOAT: "REAL", 247 exp.DataType.Type.BINARY: "VARBINARY", 248 exp.DataType.Type.TEXT: "VARCHAR", 249 exp.DataType.Type.TIMESTAMPTZ: "TIMESTAMP", 250 exp.DataType.Type.STRUCT: "ROW", 251 } 252 253 TRANSFORMS = { 254 **generator.Generator.TRANSFORMS, 255 exp.ApproxDistinct: _approx_distinct_sql, 256 exp.ApproxQuantile: rename_func("APPROX_PERCENTILE"), 257 exp.Array: lambda self, e: f"ARRAY[{self.expressions(e, flat=True)}]", 258 exp.ArrayConcat: rename_func("CONCAT"), 259 exp.ArrayContains: rename_func("CONTAINS"), 260 exp.ArraySize: rename_func("CARDINALITY"), 261 exp.BitwiseAnd: lambda self, e: f"BITWISE_AND({self.sql(e, 'this')}, {self.sql(e, 'expression')})", 262 exp.BitwiseLeftShift: lambda self, e: f"BITWISE_ARITHMETIC_SHIFT_LEFT({self.sql(e, 'this')}, {self.sql(e, 'expression')})", 263 exp.BitwiseNot: lambda self, e: f"BITWISE_NOT({self.sql(e, 'this')})", 264 exp.BitwiseOr: lambda self, e: f"BITWISE_OR({self.sql(e, 'this')}, {self.sql(e, 'expression')})", 265 exp.BitwiseRightShift: lambda self, e: f"BITWISE_ARITHMETIC_SHIFT_RIGHT({self.sql(e, 'this')}, {self.sql(e, 'expression')})", 266 exp.BitwiseXor: lambda self, e: f"BITWISE_XOR({self.sql(e, 'this')}, {self.sql(e, 'expression')})", 267 exp.Cast: transforms.preprocess([transforms.epoch_cast_to_ts]), 268 exp.CurrentTimestamp: lambda *_: "CURRENT_TIMESTAMP", 269 exp.DataType: _datatype_sql, 270 exp.DateAdd: lambda self, e: self.func( 271 "DATE_ADD", exp.Literal.string(e.text("unit") or "day"), e.expression, e.this 272 ), 273 exp.DateDiff: lambda self, e: self.func( 274 "DATE_DIFF", exp.Literal.string(e.text("unit") or "day"), e.expression, e.this 275 ), 276 exp.DateStrToDate: lambda self, e: f"CAST(DATE_PARSE({self.sql(e, 'this')}, {Presto.DATE_FORMAT}) AS DATE)", 277 exp.DateToDi: lambda self, e: f"CAST(DATE_FORMAT({self.sql(e, 'this')}, {Presto.DATEINT_FORMAT}) AS INT)", 278 exp.Decode: lambda self, e: encode_decode_sql(self, e, "FROM_UTF8"), 279 exp.DiToDate: lambda self, e: f"CAST(DATE_PARSE(CAST({self.sql(e, 'this')} AS VARCHAR), {Presto.DATEINT_FORMAT}) AS DATE)", 280 exp.Encode: lambda self, e: encode_decode_sql(self, e, "TO_UTF8"), 281 exp.FileFormatProperty: lambda self, e: f"FORMAT='{e.name.upper()}'", 282 exp.Group: transforms.preprocess([transforms.unalias_group]), 283 exp.Hex: rename_func("TO_HEX"), 284 exp.If: if_sql, 285 exp.ILike: no_ilike_sql, 286 exp.Initcap: _initcap_sql, 287 exp.Lateral: _explode_to_unnest_sql, 288 exp.Left: left_to_substring_sql, 289 exp.Levenshtein: rename_func("LEVENSHTEIN_DISTANCE"), 290 exp.LogicalAnd: rename_func("BOOL_AND"), 291 exp.LogicalOr: rename_func("BOOL_OR"), 292 exp.Pivot: no_pivot_sql, 293 exp.Quantile: _quantile_sql, 294 exp.RegexpExtract: regexp_extract_sql, 295 exp.Right: right_to_substring_sql, 296 exp.SafeBracket: lambda self, e: self.func( 297 "ELEMENT_AT", e.this, seq_get(apply_index_offset(e.this, e.expressions, 1), 0) 298 ), 299 exp.SafeDivide: no_safe_divide_sql, 300 exp.Schema: _schema_sql, 301 exp.Select: transforms.preprocess( 302 [ 303 transforms.eliminate_qualify, 304 transforms.eliminate_distinct_on, 305 transforms.explode_to_unnest, 306 ] 307 ), 308 exp.SortArray: _no_sort_array, 309 exp.StrPosition: rename_func("STRPOS"), 310 exp.StrToDate: lambda self, e: f"CAST({_str_to_time_sql(self, e)} AS DATE)", 311 exp.StrToTime: _str_to_time_sql, 312 exp.StrToUnix: lambda self, e: f"TO_UNIXTIME(DATE_PARSE({self.sql(e, 'this')}, {self.format_time(e)}))", 313 exp.StructExtract: struct_extract_sql, 314 exp.Table: transforms.preprocess([_unnest_sequence]), 315 exp.TimestampTrunc: timestamptrunc_sql, 316 exp.TimeStrToDate: timestrtotime_sql, 317 exp.TimeStrToTime: timestrtotime_sql, 318 exp.TimeStrToUnix: lambda self, e: f"TO_UNIXTIME(DATE_PARSE({self.sql(e, 'this')}, {Presto.TIME_FORMAT}))", 319 exp.TimeToStr: lambda self, e: f"DATE_FORMAT({self.sql(e, 'this')}, {self.format_time(e)})", 320 exp.TimeToUnix: rename_func("TO_UNIXTIME"), 321 exp.TryCast: transforms.preprocess([transforms.epoch_cast_to_ts]), 322 exp.TsOrDiToDi: lambda self, e: f"CAST(SUBSTR(REPLACE(CAST({self.sql(e, 'this')} AS VARCHAR), '-', ''), 1, 8) AS INT)", 323 exp.TsOrDsAdd: _ts_or_ds_add_sql, 324 exp.TsOrDsToDate: _ts_or_ds_to_date_sql, 325 exp.Unhex: rename_func("FROM_HEX"), 326 exp.UnixToStr: lambda self, e: f"DATE_FORMAT(FROM_UNIXTIME({self.sql(e, 'this')}), {self.format_time(e)})", 327 exp.UnixToTime: rename_func("FROM_UNIXTIME"), 328 exp.UnixToTimeStr: lambda self, e: f"CAST(FROM_UNIXTIME({self.sql(e, 'this')}) AS VARCHAR)", 329 exp.VariancePop: rename_func("VAR_POP"), 330 exp.With: transforms.preprocess([transforms.add_recursive_cte_column_names]), 331 exp.WithinGroup: transforms.preprocess( 332 [transforms.remove_within_group_for_percentiles] 333 ), 334 } 335 336 def interval_sql(self, expression: exp.Interval) -> str: 337 unit = self.sql(expression, "unit") 338 if expression.this and unit.lower().startswith("week"): 339 return f"({expression.this.name} * INTERVAL '7' day)" 340 return super().interval_sql(expression) 341 342 def transaction_sql(self, expression: exp.Transaction) -> str: 343 modes = expression.args.get("modes") 344 modes = f" {', '.join(modes)}" if modes else "" 345 return f"START TRANSACTION{modes}" 346 347 def generateseries_sql(self, expression: exp.GenerateSeries) -> str: 348 start = expression.args["start"] 349 end = expression.args["end"] 350 step = expression.args.get("step") 351 352 if isinstance(start, exp.Cast): 353 target_type = start.to 354 elif isinstance(end, exp.Cast): 355 target_type = end.to 356 else: 357 target_type = None 358 359 if target_type and target_type.is_type("timestamp"): 360 to = target_type.copy() 361 362 if target_type is start.to: 363 end = exp.cast(end, to) 364 else: 365 start = exp.cast(start, to) 366 367 return self.func("SEQUENCE", start, end, step) 368 369 def offset_limit_modifiers( 370 self, expression: exp.Expression, fetch: bool, limit: t.Optional[exp.Fetch | exp.Limit] 371 ) -> t.List[str]: 372 return [ 373 self.sql(expression, "offset"), 374 self.sql(limit), 375 ]
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
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.UNSUPPORTED: 'UNSUPPORTED'>, <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'>}
TYPE_MAPPING =
{<Type.NCHAR: 'NCHAR'>: 'CHAR', <Type.NVARCHAR: 'NVARCHAR'>: 'VARCHAR', <Type.MEDIUMTEXT: 'MEDIUMTEXT'>: 'TEXT', <Type.LONGTEXT: 'LONGTEXT'>: 'TEXT', <Type.MEDIUMBLOB: 'MEDIUMBLOB'>: 'BLOB', <Type.LONGBLOB: 'LONGBLOB'>: 'BLOB', <Type.INET: 'INET'>: 'INET', <Type.INT: 'INT'>: 'INTEGER', <Type.FLOAT: 'FLOAT'>: 'REAL', <Type.BINARY: 'BINARY'>: 'VARBINARY', <Type.TEXT: 'TEXT'>: 'VARCHAR', <Type.TIMESTAMPTZ: 'TIMESTAMPTZ'>: 'TIMESTAMP', <Type.STRUCT: 'STRUCT'>: 'ROW'}
TRANSFORMS =
{<class 'sqlglot.expressions.DateAdd'>: <function Presto.Generator.<lambda>>, <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 Generator.<lambda>>, <class 'sqlglot.expressions.DateFormatColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.DefaultColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.EncodeColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.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_distinct_sql>, <class 'sqlglot.expressions.ApproxQuantile'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.Array'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.ArrayConcat'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.ArrayContains'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.ArraySize'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.BitwiseAnd'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.BitwiseLeftShift'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.BitwiseNot'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.BitwiseOr'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.BitwiseRightShift'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.BitwiseXor'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.Cast'>: <function preprocess.<locals>._to_sql>, <class 'sqlglot.expressions.CurrentTimestamp'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.DataType'>: <function _datatype_sql>, <class 'sqlglot.expressions.DateDiff'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.DateStrToDate'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.DateToDi'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.Decode'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.DiToDate'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.Encode'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.FileFormatProperty'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.Group'>: <function preprocess.<locals>._to_sql>, <class 'sqlglot.expressions.Hex'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.If'>: <function if_sql>, <class 'sqlglot.expressions.ILike'>: <function no_ilike_sql>, <class 'sqlglot.expressions.Initcap'>: <function _initcap_sql>, <class 'sqlglot.expressions.Lateral'>: <function _explode_to_unnest_sql>, <class 'sqlglot.expressions.Left'>: <function left_to_substring_sql>, <class 'sqlglot.expressions.Levenshtein'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.LogicalAnd'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.LogicalOr'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.Pivot'>: <function no_pivot_sql>, <class 'sqlglot.expressions.Quantile'>: <function _quantile_sql>, <class 'sqlglot.expressions.RegexpExtract'>: <function regexp_extract_sql>, <class 'sqlglot.expressions.Right'>: <function right_to_substring_sql>, <class 'sqlglot.expressions.SafeBracket'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.SafeDivide'>: <function no_safe_divide_sql>, <class 'sqlglot.expressions.Schema'>: <function _schema_sql>, <class 'sqlglot.expressions.Select'>: <function preprocess.<locals>._to_sql>, <class 'sqlglot.expressions.SortArray'>: <function _no_sort_array>, <class 'sqlglot.expressions.StrPosition'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.StrToDate'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.StrToTime'>: <function _str_to_time_sql>, <class 'sqlglot.expressions.StrToUnix'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.StructExtract'>: <function struct_extract_sql>, <class 'sqlglot.expressions.Table'>: <function preprocess.<locals>._to_sql>, <class 'sqlglot.expressions.TimestampTrunc'>: <function timestamptrunc_sql>, <class 'sqlglot.expressions.TimeStrToDate'>: <function timestrtotime_sql>, <class 'sqlglot.expressions.TimeStrToTime'>: <function timestrtotime_sql>, <class 'sqlglot.expressions.TimeStrToUnix'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.TimeToStr'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.TimeToUnix'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.TryCast'>: <function preprocess.<locals>._to_sql>, <class 'sqlglot.expressions.TsOrDiToDi'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.TsOrDsToDate'>: <function _ts_or_ds_to_date_sql>, <class 'sqlglot.expressions.Unhex'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.UnixToStr'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.UnixToTime'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.UnixToTimeStr'>: <function Presto.Generator.<lambda>>, <class 'sqlglot.expressions.VariancePop'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.With'>: <function preprocess.<locals>._to_sql>, <class 'sqlglot.expressions.WithinGroup'>: <function preprocess.<locals>._to_sql>}
347 def generateseries_sql(self, expression: exp.GenerateSeries) -> str: 348 start = expression.args["start"] 349 end = expression.args["end"] 350 step = expression.args.get("step") 351 352 if isinstance(start, exp.Cast): 353 target_type = start.to 354 elif isinstance(end, exp.Cast): 355 target_type = end.to 356 else: 357 target_type = None 358 359 if target_type and target_type.is_type("timestamp"): 360 to = target_type.copy() 361 362 if target_type is start.to: 363 end = exp.cast(end, to) 364 else: 365 start = exp.cast(start, to) 366 367 return self.func("SEQUENCE", start, end, step)
def
offset_limit_modifiers( self, expression: sqlglot.expressions.Expression, fetch: bool, limit: Union[sqlglot.expressions.Fetch, sqlglot.expressions.Limit, NoneType]) -> List[str]:
INVERSE_TIME_MAPPING: Dict[str, str] =
{'%B': '%M', '%-m': '%c', '%-d': '%e', '%I': '%h', '%M': '%i', '%S': '%S', '%W': '%u', '%-H': '%k', '%-I': '%l', '%H:%M:%S': '%T', '%a': '%W'}
INVERSE_TIME_TRIE: Dict =
{'%': {'B': {0: True}, '-': {'m': {0: True}, 'd': {0: True}, 'H': {0: True}, 'I': {0: True}}, 'I': {0: True}, 'M': {0: True}, 'S': {0: True}, 'W': {0: True}, 'H': {':': {'%': {'M': {':': {'%': {'S': {0: True}}}}}}}, 'a': {0: True}}}
@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
- TABLESAMPLE_WITH_METHOD
- TABLESAMPLE_SIZE_IS_PERCENT
- LIMIT_FETCH
- RENAME_TABLE_WITH_DB
- GROUPINGS_SEP
- INDEX_ON
- QUERY_HINT_SEP
- DUPLICATE_KEY_UPDATE_WITH_SET
- LIMIT_IS_TOP
- RETURNING_END
- COLUMN_JOIN_MARKS_SUPPORTED
- EXTRACT_ALLOWS_QUOTES
- VALUES_AS_TABLE
- STAR_MAPPING
- TIME_PART_SINGULARS
- TOKEN_MAPPING
- PARAMETER_TOKEN
- RESERVED_KEYWORDS
- WITH_SEPARATED_COMMENTS
- UNWRAPPED_INTERVAL_VALUES
- SENTINEL_LINE_BREAK
- UNNEST_COLUMN_ONLY
- ALIAS_POST_TABLESAMPLE
- IDENTIFIERS_CAN_START_WITH_DIGIT
- 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
- tablesample_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
- 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
- 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