sqlglot.dialects.hive
1from __future__ import annotations 2 3import typing as t 4 5from sqlglot import exp, generator, parser, tokens, transforms 6from sqlglot.dialects.dialect import ( 7 DATE_ADD_OR_SUB, 8 Dialect, 9 NormalizationStrategy, 10 approx_count_distinct_sql, 11 arg_max_or_min_no_count, 12 datestrtodate_sql, 13 build_formatted_time, 14 if_sql, 15 is_parse_json, 16 left_to_substring_sql, 17 locate_to_strposition, 18 max_or_greatest, 19 min_or_least, 20 no_ilike_sql, 21 no_recursive_cte_sql, 22 no_safe_divide_sql, 23 no_trycast_sql, 24 regexp_extract_sql, 25 regexp_replace_sql, 26 rename_func, 27 right_to_substring_sql, 28 strposition_to_locate_sql, 29 struct_extract_sql, 30 time_format, 31 timestrtotime_sql, 32 unit_to_str, 33 var_map_sql, 34 sequence_sql, 35) 36from sqlglot.transforms import ( 37 remove_unique_constraints, 38 ctas_with_tmp_tables_to_create_tmp_view, 39 preprocess, 40 move_schema_columns_to_partitioned_by, 41) 42from sqlglot.helper import seq_get 43from sqlglot.tokens import TokenType 44 45# (FuncType, Multiplier) 46DATE_DELTA_INTERVAL = { 47 "YEAR": ("ADD_MONTHS", 12), 48 "MONTH": ("ADD_MONTHS", 1), 49 "QUARTER": ("ADD_MONTHS", 3), 50 "WEEK": ("DATE_ADD", 7), 51 "DAY": ("DATE_ADD", 1), 52} 53 54TIME_DIFF_FACTOR = { 55 "MILLISECOND": " * 1000", 56 "SECOND": "", 57 "MINUTE": " / 60", 58 "HOUR": " / 3600", 59} 60 61DIFF_MONTH_SWITCH = ("YEAR", "QUARTER", "MONTH") 62 63 64def _add_date_sql(self: Hive.Generator, expression: DATE_ADD_OR_SUB) -> str: 65 if isinstance(expression, exp.TsOrDsAdd) and not expression.unit: 66 return self.func("DATE_ADD", expression.this, expression.expression) 67 68 unit = expression.text("unit").upper() 69 func, multiplier = DATE_DELTA_INTERVAL.get(unit, ("DATE_ADD", 1)) 70 71 if isinstance(expression, exp.DateSub): 72 multiplier *= -1 73 74 if expression.expression.is_number: 75 modified_increment = exp.Literal.number(expression.expression.to_py() * multiplier) 76 else: 77 modified_increment = expression.expression 78 if multiplier != 1: 79 modified_increment = exp.Mul( # type: ignore 80 this=modified_increment, expression=exp.Literal.number(multiplier) 81 ) 82 83 return self.func(func, expression.this, modified_increment) 84 85 86def _date_diff_sql(self: Hive.Generator, expression: exp.DateDiff | exp.TsOrDsDiff) -> str: 87 unit = expression.text("unit").upper() 88 89 factor = TIME_DIFF_FACTOR.get(unit) 90 if factor is not None: 91 left = self.sql(expression, "this") 92 right = self.sql(expression, "expression") 93 sec_diff = f"UNIX_TIMESTAMP({left}) - UNIX_TIMESTAMP({right})" 94 return f"({sec_diff}){factor}" if factor else sec_diff 95 96 months_between = unit in DIFF_MONTH_SWITCH 97 sql_func = "MONTHS_BETWEEN" if months_between else "DATEDIFF" 98 _, multiplier = DATE_DELTA_INTERVAL.get(unit, ("", 1)) 99 multiplier_sql = f" / {multiplier}" if multiplier > 1 else "" 100 diff_sql = f"{sql_func}({self.format_args(expression.this, expression.expression)})" 101 102 if months_between or multiplier_sql: 103 # MONTHS_BETWEEN returns a float, so we need to truncate the fractional part. 104 # For the same reason, we want to truncate if there's a divisor present. 105 diff_sql = f"CAST({diff_sql}{multiplier_sql} AS INT)" 106 107 return diff_sql 108 109 110def _json_format_sql(self: Hive.Generator, expression: exp.JSONFormat) -> str: 111 this = expression.this 112 113 if is_parse_json(this): 114 if this.this.is_string: 115 # Since FROM_JSON requires a nested type, we always wrap the json string with 116 # an array to ensure that "naked" strings like "'a'" will be handled correctly 117 wrapped_json = exp.Literal.string(f"[{this.this.name}]") 118 119 from_json = self.func( 120 "FROM_JSON", wrapped_json, self.func("SCHEMA_OF_JSON", wrapped_json) 121 ) 122 to_json = self.func("TO_JSON", from_json) 123 124 # This strips the [, ] delimiters of the dummy array printed by TO_JSON 125 return self.func("REGEXP_EXTRACT", to_json, "'^.(.*).$'", "1") 126 return self.sql(this) 127 128 return self.func("TO_JSON", this, expression.args.get("options")) 129 130 131def _array_sort_sql(self: Hive.Generator, expression: exp.ArraySort) -> str: 132 if expression.expression: 133 self.unsupported("Hive SORT_ARRAY does not support a comparator") 134 return self.func("SORT_ARRAY", expression.this) 135 136 137def _property_sql(self: Hive.Generator, expression: exp.Property) -> str: 138 return f"{self.property_name(expression, string_key=True)}={self.sql(expression, 'value')}" 139 140 141def _str_to_unix_sql(self: Hive.Generator, expression: exp.StrToUnix) -> str: 142 return self.func("UNIX_TIMESTAMP", expression.this, time_format("hive")(self, expression)) 143 144 145def _unix_to_time_sql(self: Hive.Generator, expression: exp.UnixToTime) -> str: 146 timestamp = self.sql(expression, "this") 147 scale = expression.args.get("scale") 148 if scale in (None, exp.UnixToTime.SECONDS): 149 return rename_func("FROM_UNIXTIME")(self, expression) 150 151 return f"FROM_UNIXTIME({timestamp} / POW(10, {scale}))" 152 153 154def _str_to_date_sql(self: Hive.Generator, expression: exp.StrToDate) -> str: 155 this = self.sql(expression, "this") 156 time_format = self.format_time(expression) 157 if time_format not in (Hive.TIME_FORMAT, Hive.DATE_FORMAT): 158 this = f"FROM_UNIXTIME(UNIX_TIMESTAMP({this}, {time_format}))" 159 return f"CAST({this} AS DATE)" 160 161 162def _str_to_time_sql(self: Hive.Generator, expression: exp.StrToTime) -> str: 163 this = self.sql(expression, "this") 164 time_format = self.format_time(expression) 165 if time_format not in (Hive.TIME_FORMAT, Hive.DATE_FORMAT): 166 this = f"FROM_UNIXTIME(UNIX_TIMESTAMP({this}, {time_format}))" 167 return f"CAST({this} AS TIMESTAMP)" 168 169 170def _to_date_sql(self: Hive.Generator, expression: exp.TsOrDsToDate) -> str: 171 time_format = self.format_time(expression) 172 if time_format and time_format not in (Hive.TIME_FORMAT, Hive.DATE_FORMAT): 173 return self.func("TO_DATE", expression.this, time_format) 174 175 if isinstance(expression.this, exp.TsOrDsToDate): 176 return self.sql(expression, "this") 177 178 return self.func("TO_DATE", expression.this) 179 180 181def _build_with_ignore_nulls( 182 exp_class: t.Type[exp.Expression], 183) -> t.Callable[[t.List[exp.Expression]], exp.Expression]: 184 def _parse(args: t.List[exp.Expression]) -> exp.Expression: 185 this = exp_class(this=seq_get(args, 0)) 186 if seq_get(args, 1) == exp.true(): 187 return exp.IgnoreNulls(this=this) 188 return this 189 190 return _parse 191 192 193class Hive(Dialect): 194 ALIAS_POST_TABLESAMPLE = True 195 IDENTIFIERS_CAN_START_WITH_DIGIT = True 196 SUPPORTS_USER_DEFINED_TYPES = False 197 SAFE_DIVISION = True 198 199 # https://spark.apache.org/docs/latest/sql-ref-identifier.html#description 200 NORMALIZATION_STRATEGY = NormalizationStrategy.CASE_INSENSITIVE 201 202 TIME_MAPPING = { 203 "y": "%Y", 204 "Y": "%Y", 205 "YYYY": "%Y", 206 "yyyy": "%Y", 207 "YY": "%y", 208 "yy": "%y", 209 "MMMM": "%B", 210 "MMM": "%b", 211 "MM": "%m", 212 "M": "%-m", 213 "dd": "%d", 214 "d": "%-d", 215 "HH": "%H", 216 "H": "%-H", 217 "hh": "%I", 218 "h": "%-I", 219 "mm": "%M", 220 "m": "%-M", 221 "ss": "%S", 222 "s": "%-S", 223 "SSSSSS": "%f", 224 "a": "%p", 225 "DD": "%j", 226 "D": "%-j", 227 "E": "%a", 228 "EE": "%a", 229 "EEE": "%a", 230 "EEEE": "%A", 231 } 232 233 DATE_FORMAT = "'yyyy-MM-dd'" 234 DATEINT_FORMAT = "'yyyyMMdd'" 235 TIME_FORMAT = "'yyyy-MM-dd HH:mm:ss'" 236 237 class Tokenizer(tokens.Tokenizer): 238 QUOTES = ["'", '"'] 239 IDENTIFIERS = ["`"] 240 STRING_ESCAPES = ["\\"] 241 242 SINGLE_TOKENS = { 243 **tokens.Tokenizer.SINGLE_TOKENS, 244 "$": TokenType.PARAMETER, 245 } 246 247 KEYWORDS = { 248 **tokens.Tokenizer.KEYWORDS, 249 "ADD ARCHIVE": TokenType.COMMAND, 250 "ADD ARCHIVES": TokenType.COMMAND, 251 "ADD FILE": TokenType.COMMAND, 252 "ADD FILES": TokenType.COMMAND, 253 "ADD JAR": TokenType.COMMAND, 254 "ADD JARS": TokenType.COMMAND, 255 "MSCK REPAIR": TokenType.COMMAND, 256 "REFRESH": TokenType.REFRESH, 257 "TIMESTAMP AS OF": TokenType.TIMESTAMP_SNAPSHOT, 258 "VERSION AS OF": TokenType.VERSION_SNAPSHOT, 259 "SERDEPROPERTIES": TokenType.SERDE_PROPERTIES, 260 } 261 262 NUMERIC_LITERALS = { 263 "L": "BIGINT", 264 "S": "SMALLINT", 265 "Y": "TINYINT", 266 "D": "DOUBLE", 267 "F": "FLOAT", 268 "BD": "DECIMAL", 269 } 270 271 class Parser(parser.Parser): 272 LOG_DEFAULTS_TO_LN = True 273 STRICT_CAST = False 274 VALUES_FOLLOWED_BY_PAREN = False 275 276 FUNCTIONS = { 277 **parser.Parser.FUNCTIONS, 278 "BASE64": exp.ToBase64.from_arg_list, 279 "COLLECT_LIST": exp.ArrayAgg.from_arg_list, 280 "COLLECT_SET": exp.ArrayUniqueAgg.from_arg_list, 281 "DATE_ADD": lambda args: exp.TsOrDsAdd( 282 this=seq_get(args, 0), expression=seq_get(args, 1), unit=exp.Literal.string("DAY") 283 ), 284 "DATE_FORMAT": lambda args: build_formatted_time(exp.TimeToStr, "hive")( 285 [ 286 exp.TimeStrToTime(this=seq_get(args, 0)), 287 seq_get(args, 1), 288 ] 289 ), 290 "DATE_SUB": lambda args: exp.TsOrDsAdd( 291 this=seq_get(args, 0), 292 expression=exp.Mul(this=seq_get(args, 1), expression=exp.Literal.number(-1)), 293 unit=exp.Literal.string("DAY"), 294 ), 295 "DATEDIFF": lambda args: exp.DateDiff( 296 this=exp.TsOrDsToDate(this=seq_get(args, 0)), 297 expression=exp.TsOrDsToDate(this=seq_get(args, 1)), 298 ), 299 "DAY": lambda args: exp.Day(this=exp.TsOrDsToDate(this=seq_get(args, 0))), 300 "FIRST": _build_with_ignore_nulls(exp.First), 301 "FIRST_VALUE": _build_with_ignore_nulls(exp.FirstValue), 302 "FROM_UNIXTIME": build_formatted_time(exp.UnixToStr, "hive", True), 303 "GET_JSON_OBJECT": exp.JSONExtractScalar.from_arg_list, 304 "LAST": _build_with_ignore_nulls(exp.Last), 305 "LAST_VALUE": _build_with_ignore_nulls(exp.LastValue), 306 "LOCATE": locate_to_strposition, 307 "MAP": parser.build_var_map, 308 "MONTH": lambda args: exp.Month(this=exp.TsOrDsToDate.from_arg_list(args)), 309 "PERCENTILE": exp.Quantile.from_arg_list, 310 "PERCENTILE_APPROX": exp.ApproxQuantile.from_arg_list, 311 "REGEXP_EXTRACT": lambda args: exp.RegexpExtract( 312 this=seq_get(args, 0), expression=seq_get(args, 1), group=seq_get(args, 2) 313 ), 314 "SEQUENCE": exp.GenerateSeries.from_arg_list, 315 "SIZE": exp.ArraySize.from_arg_list, 316 "SPLIT": exp.RegexpSplit.from_arg_list, 317 "STR_TO_MAP": lambda args: exp.StrToMap( 318 this=seq_get(args, 0), 319 pair_delim=seq_get(args, 1) or exp.Literal.string(","), 320 key_value_delim=seq_get(args, 2) or exp.Literal.string(":"), 321 ), 322 "TO_DATE": build_formatted_time(exp.TsOrDsToDate, "hive"), 323 "TO_JSON": exp.JSONFormat.from_arg_list, 324 "TRUNC": exp.TimestampTrunc.from_arg_list, 325 "UNBASE64": exp.FromBase64.from_arg_list, 326 "UNIX_TIMESTAMP": lambda args: build_formatted_time(exp.StrToUnix, "hive", True)( 327 args or [exp.CurrentTimestamp()] 328 ), 329 "YEAR": lambda args: exp.Year(this=exp.TsOrDsToDate.from_arg_list(args)), 330 } 331 332 NO_PAREN_FUNCTION_PARSERS = { 333 **parser.Parser.NO_PAREN_FUNCTION_PARSERS, 334 "TRANSFORM": lambda self: self._parse_transform(), 335 } 336 337 PROPERTY_PARSERS = { 338 **parser.Parser.PROPERTY_PARSERS, 339 "SERDEPROPERTIES": lambda self: exp.SerdeProperties( 340 expressions=self._parse_wrapped_csv(self._parse_property) 341 ), 342 } 343 344 def _parse_transform(self) -> t.Optional[exp.Transform | exp.QueryTransform]: 345 if not self._match(TokenType.L_PAREN, advance=False): 346 self._retreat(self._index - 1) 347 return None 348 349 args = self._parse_wrapped_csv(self._parse_lambda) 350 row_format_before = self._parse_row_format(match_row=True) 351 352 record_writer = None 353 if self._match_text_seq("RECORDWRITER"): 354 record_writer = self._parse_string() 355 356 if not self._match(TokenType.USING): 357 return exp.Transform.from_arg_list(args) 358 359 command_script = self._parse_string() 360 361 self._match(TokenType.ALIAS) 362 schema = self._parse_schema() 363 364 row_format_after = self._parse_row_format(match_row=True) 365 record_reader = None 366 if self._match_text_seq("RECORDREADER"): 367 record_reader = self._parse_string() 368 369 return self.expression( 370 exp.QueryTransform, 371 expressions=args, 372 command_script=command_script, 373 schema=schema, 374 row_format_before=row_format_before, 375 record_writer=record_writer, 376 row_format_after=row_format_after, 377 record_reader=record_reader, 378 ) 379 380 def _parse_types( 381 self, check_func: bool = False, schema: bool = False, allow_identifiers: bool = True 382 ) -> t.Optional[exp.Expression]: 383 """ 384 Spark (and most likely Hive) treats casts to CHAR(length) and VARCHAR(length) as casts to 385 STRING in all contexts except for schema definitions. For example, this is in Spark v3.4.0: 386 387 spark-sql (default)> select cast(1234 as varchar(2)); 388 23/06/06 15:51:18 WARN CharVarcharUtils: The Spark cast operator does not support 389 char/varchar type and simply treats them as string type. Please use string type 390 directly to avoid confusion. Otherwise, you can set spark.sql.legacy.charVarcharAsString 391 to true, so that Spark treat them as string type as same as Spark 3.0 and earlier 392 393 1234 394 Time taken: 4.265 seconds, Fetched 1 row(s) 395 396 This shows that Spark doesn't truncate the value into '12', which is inconsistent with 397 what other dialects (e.g. postgres) do, so we need to drop the length to transpile correctly. 398 399 Reference: https://spark.apache.org/docs/latest/sql-ref-datatypes.html 400 """ 401 this = super()._parse_types( 402 check_func=check_func, schema=schema, allow_identifiers=allow_identifiers 403 ) 404 405 if this and not schema: 406 return this.transform( 407 lambda node: ( 408 node.replace(exp.DataType.build("text")) 409 if isinstance(node, exp.DataType) and node.is_type("char", "varchar") 410 else node 411 ), 412 copy=False, 413 ) 414 415 return this 416 417 def _parse_partition_and_order( 418 self, 419 ) -> t.Tuple[t.List[exp.Expression], t.Optional[exp.Expression]]: 420 return ( 421 ( 422 self._parse_csv(self._parse_assignment) 423 if self._match_set({TokenType.PARTITION_BY, TokenType.DISTRIBUTE_BY}) 424 else [] 425 ), 426 super()._parse_order(skip_order_token=self._match(TokenType.SORT_BY)), 427 ) 428 429 def _parse_parameter(self) -> exp.Parameter: 430 self._match(TokenType.L_BRACE) 431 this = self._parse_identifier() or self._parse_primary_or_var() 432 expression = self._match(TokenType.COLON) and ( 433 self._parse_identifier() or self._parse_primary_or_var() 434 ) 435 self._match(TokenType.R_BRACE) 436 return self.expression(exp.Parameter, this=this, expression=expression) 437 438 class Generator(generator.Generator): 439 LIMIT_FETCH = "LIMIT" 440 TABLESAMPLE_WITH_METHOD = False 441 JOIN_HINTS = False 442 TABLE_HINTS = False 443 QUERY_HINTS = False 444 INDEX_ON = "ON TABLE" 445 EXTRACT_ALLOWS_QUOTES = False 446 NVL2_SUPPORTED = False 447 LAST_DAY_SUPPORTS_DATE_PART = False 448 JSON_PATH_SINGLE_QUOTE_ESCAPE = True 449 SUPPORTS_TO_NUMBER = False 450 WITH_PROPERTIES_PREFIX = "TBLPROPERTIES" 451 PARSE_JSON_NAME = None 452 PAD_FILL_PATTERN_IS_REQUIRED = True 453 454 EXPRESSIONS_WITHOUT_NESTED_CTES = { 455 exp.Insert, 456 exp.Select, 457 exp.Subquery, 458 exp.SetOperation, 459 } 460 461 SUPPORTED_JSON_PATH_PARTS = { 462 exp.JSONPathKey, 463 exp.JSONPathRoot, 464 exp.JSONPathSubscript, 465 exp.JSONPathWildcard, 466 } 467 468 TYPE_MAPPING = { 469 **generator.Generator.TYPE_MAPPING, 470 exp.DataType.Type.BIT: "BOOLEAN", 471 exp.DataType.Type.DATETIME: "TIMESTAMP", 472 exp.DataType.Type.ROWVERSION: "BINARY", 473 exp.DataType.Type.TEXT: "STRING", 474 exp.DataType.Type.TIME: "TIMESTAMP", 475 exp.DataType.Type.TIMESTAMPTZ: "TIMESTAMP", 476 exp.DataType.Type.UTINYINT: "SMALLINT", 477 exp.DataType.Type.VARBINARY: "BINARY", 478 } 479 480 TRANSFORMS = { 481 **generator.Generator.TRANSFORMS, 482 exp.Group: transforms.preprocess([transforms.unalias_group]), 483 exp.Select: transforms.preprocess( 484 [ 485 transforms.eliminate_qualify, 486 transforms.eliminate_distinct_on, 487 transforms.unnest_to_explode, 488 ] 489 ), 490 exp.Property: _property_sql, 491 exp.AnyValue: rename_func("FIRST"), 492 exp.ApproxDistinct: approx_count_distinct_sql, 493 exp.ArgMax: arg_max_or_min_no_count("MAX_BY"), 494 exp.ArgMin: arg_max_or_min_no_count("MIN_BY"), 495 exp.ArrayConcat: rename_func("CONCAT"), 496 exp.ArrayToString: lambda self, e: self.func("CONCAT_WS", e.expression, e.this), 497 exp.ArraySize: rename_func("SIZE"), 498 exp.ArraySort: _array_sort_sql, 499 exp.With: no_recursive_cte_sql, 500 exp.DateAdd: _add_date_sql, 501 exp.DateDiff: _date_diff_sql, 502 exp.DateStrToDate: datestrtodate_sql, 503 exp.DateSub: _add_date_sql, 504 exp.DateToDi: lambda self, 505 e: f"CAST(DATE_FORMAT({self.sql(e, 'this')}, {Hive.DATEINT_FORMAT}) AS INT)", 506 exp.DiToDate: lambda self, 507 e: f"TO_DATE(CAST({self.sql(e, 'this')} AS STRING), {Hive.DATEINT_FORMAT})", 508 exp.FileFormatProperty: lambda self, 509 e: f"STORED AS {self.sql(e, 'this') if isinstance(e.this, exp.InputOutputFormat) else e.name.upper()}", 510 exp.FromBase64: rename_func("UNBASE64"), 511 exp.GenerateSeries: sequence_sql, 512 exp.If: if_sql(), 513 exp.ILike: no_ilike_sql, 514 exp.IsNan: rename_func("ISNAN"), 515 exp.JSONExtract: lambda self, e: self.func("GET_JSON_OBJECT", e.this, e.expression), 516 exp.JSONExtractScalar: lambda self, e: self.func( 517 "GET_JSON_OBJECT", e.this, e.expression 518 ), 519 exp.JSONFormat: _json_format_sql, 520 exp.Left: left_to_substring_sql, 521 exp.Map: var_map_sql, 522 exp.Max: max_or_greatest, 523 exp.MD5Digest: lambda self, e: self.func("UNHEX", self.func("MD5", e.this)), 524 exp.Min: min_or_least, 525 exp.MonthsBetween: lambda self, e: self.func("MONTHS_BETWEEN", e.this, e.expression), 526 exp.NotNullColumnConstraint: lambda _, e: ( 527 "" if e.args.get("allow_null") else "NOT NULL" 528 ), 529 exp.VarMap: var_map_sql, 530 exp.Create: preprocess( 531 [ 532 remove_unique_constraints, 533 ctas_with_tmp_tables_to_create_tmp_view, 534 move_schema_columns_to_partitioned_by, 535 ] 536 ), 537 exp.Quantile: rename_func("PERCENTILE"), 538 exp.ApproxQuantile: rename_func("PERCENTILE_APPROX"), 539 exp.RegexpExtract: regexp_extract_sql, 540 exp.RegexpReplace: regexp_replace_sql, 541 exp.RegexpLike: lambda self, e: self.binary(e, "RLIKE"), 542 exp.RegexpSplit: rename_func("SPLIT"), 543 exp.Right: right_to_substring_sql, 544 exp.SafeDivide: no_safe_divide_sql, 545 exp.SchemaCommentProperty: lambda self, e: self.naked_property(e), 546 exp.ArrayUniqueAgg: rename_func("COLLECT_SET"), 547 exp.Split: lambda self, e: self.func( 548 "SPLIT", e.this, self.func("CONCAT", "'\\\\Q'", e.expression) 549 ), 550 exp.StrPosition: strposition_to_locate_sql, 551 exp.StrToDate: _str_to_date_sql, 552 exp.StrToTime: _str_to_time_sql, 553 exp.StrToUnix: _str_to_unix_sql, 554 exp.StructExtract: struct_extract_sql, 555 exp.TimeStrToDate: rename_func("TO_DATE"), 556 exp.TimeStrToTime: timestrtotime_sql, 557 exp.TimeStrToUnix: rename_func("UNIX_TIMESTAMP"), 558 exp.TimestampTrunc: lambda self, e: self.func("TRUNC", e.this, unit_to_str(e)), 559 exp.TimeToStr: lambda self, e: self.func("DATE_FORMAT", e.this, self.format_time(e)), 560 exp.TimeToUnix: rename_func("UNIX_TIMESTAMP"), 561 exp.ToBase64: rename_func("BASE64"), 562 exp.TsOrDiToDi: lambda self, 563 e: f"CAST(SUBSTR(REPLACE(CAST({self.sql(e, 'this')} AS STRING), '-', ''), 1, 8) AS INT)", 564 exp.TsOrDsAdd: _add_date_sql, 565 exp.TsOrDsDiff: _date_diff_sql, 566 exp.TsOrDsToDate: _to_date_sql, 567 exp.TryCast: no_trycast_sql, 568 exp.UnixToStr: lambda self, e: self.func( 569 "FROM_UNIXTIME", e.this, time_format("hive")(self, e) 570 ), 571 exp.UnixToTime: _unix_to_time_sql, 572 exp.UnixToTimeStr: rename_func("FROM_UNIXTIME"), 573 exp.PartitionedByProperty: lambda self, e: f"PARTITIONED BY {self.sql(e, 'this')}", 574 exp.NumberToStr: rename_func("FORMAT_NUMBER"), 575 exp.National: lambda self, e: self.national_sql(e, prefix=""), 576 exp.ClusteredColumnConstraint: lambda self, 577 e: f"({self.expressions(e, 'this', indent=False)})", 578 exp.NonClusteredColumnConstraint: lambda self, 579 e: f"({self.expressions(e, 'this', indent=False)})", 580 exp.NotForReplicationColumnConstraint: lambda *_: "", 581 exp.OnProperty: lambda *_: "", 582 exp.PrimaryKeyColumnConstraint: lambda *_: "PRIMARY KEY", 583 exp.WeekOfYear: rename_func("WEEKOFYEAR"), 584 exp.DayOfMonth: rename_func("DAYOFMONTH"), 585 exp.DayOfWeek: rename_func("DAYOFWEEK"), 586 } 587 588 PROPERTIES_LOCATION = { 589 **generator.Generator.PROPERTIES_LOCATION, 590 exp.FileFormatProperty: exp.Properties.Location.POST_SCHEMA, 591 exp.PartitionedByProperty: exp.Properties.Location.POST_SCHEMA, 592 exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED, 593 exp.WithDataProperty: exp.Properties.Location.UNSUPPORTED, 594 } 595 596 def _jsonpathkey_sql(self, expression: exp.JSONPathKey) -> str: 597 if isinstance(expression.this, exp.JSONPathWildcard): 598 self.unsupported("Unsupported wildcard in JSONPathKey expression") 599 return "" 600 601 return super()._jsonpathkey_sql(expression) 602 603 def parameter_sql(self, expression: exp.Parameter) -> str: 604 this = self.sql(expression, "this") 605 expression_sql = self.sql(expression, "expression") 606 607 parent = expression.parent 608 this = f"{this}:{expression_sql}" if expression_sql else this 609 610 if isinstance(parent, exp.EQ) and isinstance(parent.parent, exp.SetItem): 611 # We need to produce SET key = value instead of SET ${key} = value 612 return this 613 614 return f"${{{this}}}" 615 616 def schema_sql(self, expression: exp.Schema) -> str: 617 for ordered in expression.find_all(exp.Ordered): 618 if ordered.args.get("desc") is False: 619 ordered.set("desc", None) 620 621 return super().schema_sql(expression) 622 623 def constraint_sql(self, expression: exp.Constraint) -> str: 624 for prop in list(expression.find_all(exp.Properties)): 625 prop.pop() 626 627 this = self.sql(expression, "this") 628 expressions = self.expressions(expression, sep=" ", flat=True) 629 return f"CONSTRAINT {this} {expressions}" 630 631 def rowformatserdeproperty_sql(self, expression: exp.RowFormatSerdeProperty) -> str: 632 serde_props = self.sql(expression, "serde_properties") 633 serde_props = f" {serde_props}" if serde_props else "" 634 return f"ROW FORMAT SERDE {self.sql(expression, 'this')}{serde_props}" 635 636 def arrayagg_sql(self, expression: exp.ArrayAgg) -> str: 637 return self.func( 638 "COLLECT_LIST", 639 expression.this.this if isinstance(expression.this, exp.Order) else expression.this, 640 ) 641 642 def datatype_sql(self, expression: exp.DataType) -> str: 643 if expression.this in self.PARAMETERIZABLE_TEXT_TYPES and ( 644 not expression.expressions or expression.expressions[0].name == "MAX" 645 ): 646 expression = exp.DataType.build("text") 647 elif expression.is_type(exp.DataType.Type.TEXT) and expression.expressions: 648 expression.set("this", exp.DataType.Type.VARCHAR) 649 elif expression.this in exp.DataType.TEMPORAL_TYPES: 650 expression = exp.DataType.build(expression.this) 651 elif expression.is_type("float"): 652 size_expression = expression.find(exp.DataTypeParam) 653 if size_expression: 654 size = int(size_expression.name) 655 expression = ( 656 exp.DataType.build("float") if size <= 32 else exp.DataType.build("double") 657 ) 658 659 return super().datatype_sql(expression) 660 661 def version_sql(self, expression: exp.Version) -> str: 662 sql = super().version_sql(expression) 663 return sql.replace("FOR ", "", 1) 664 665 def struct_sql(self, expression: exp.Struct) -> str: 666 values = [] 667 668 for i, e in enumerate(expression.expressions): 669 if isinstance(e, exp.PropertyEQ): 670 self.unsupported("Hive does not support named structs.") 671 values.append(e.expression) 672 else: 673 values.append(e) 674 675 return self.func("STRUCT", *values) 676 677 def alterset_sql(self, expression: exp.AlterSet) -> str: 678 exprs = self.expressions(expression, flat=True) 679 exprs = f" {exprs}" if exprs else "" 680 location = self.sql(expression, "location") 681 location = f" LOCATION {location}" if location else "" 682 file_format = self.expressions(expression, key="file_format", flat=True, sep=" ") 683 file_format = f" FILEFORMAT {file_format}" if file_format else "" 684 serde = self.sql(expression, "serde") 685 serde = f" SERDE {serde}" if serde else "" 686 tags = self.expressions(expression, key="tag", flat=True, sep="") 687 tags = f" TAGS {tags}" if tags else "" 688 689 return f"SET{serde}{exprs}{location}{file_format}{tags}" 690 691 def serdeproperties_sql(self, expression: exp.SerdeProperties) -> str: 692 prefix = "WITH " if expression.args.get("with") else "" 693 exprs = self.expressions(expression, flat=True) 694 695 return f"{prefix}SERDEPROPERTIES ({exprs})"
DATE_DELTA_INTERVAL =
{'YEAR': ('ADD_MONTHS', 12), 'MONTH': ('ADD_MONTHS', 1), 'QUARTER': ('ADD_MONTHS', 3), 'WEEK': ('DATE_ADD', 7), 'DAY': ('DATE_ADD', 1)}
TIME_DIFF_FACTOR =
{'MILLISECOND': ' * 1000', 'SECOND': '', 'MINUTE': ' / 60', 'HOUR': ' / 3600'}
DIFF_MONTH_SWITCH =
('YEAR', 'QUARTER', 'MONTH')
194class Hive(Dialect): 195 ALIAS_POST_TABLESAMPLE = True 196 IDENTIFIERS_CAN_START_WITH_DIGIT = True 197 SUPPORTS_USER_DEFINED_TYPES = False 198 SAFE_DIVISION = True 199 200 # https://spark.apache.org/docs/latest/sql-ref-identifier.html#description 201 NORMALIZATION_STRATEGY = NormalizationStrategy.CASE_INSENSITIVE 202 203 TIME_MAPPING = { 204 "y": "%Y", 205 "Y": "%Y", 206 "YYYY": "%Y", 207 "yyyy": "%Y", 208 "YY": "%y", 209 "yy": "%y", 210 "MMMM": "%B", 211 "MMM": "%b", 212 "MM": "%m", 213 "M": "%-m", 214 "dd": "%d", 215 "d": "%-d", 216 "HH": "%H", 217 "H": "%-H", 218 "hh": "%I", 219 "h": "%-I", 220 "mm": "%M", 221 "m": "%-M", 222 "ss": "%S", 223 "s": "%-S", 224 "SSSSSS": "%f", 225 "a": "%p", 226 "DD": "%j", 227 "D": "%-j", 228 "E": "%a", 229 "EE": "%a", 230 "EEE": "%a", 231 "EEEE": "%A", 232 } 233 234 DATE_FORMAT = "'yyyy-MM-dd'" 235 DATEINT_FORMAT = "'yyyyMMdd'" 236 TIME_FORMAT = "'yyyy-MM-dd HH:mm:ss'" 237 238 class Tokenizer(tokens.Tokenizer): 239 QUOTES = ["'", '"'] 240 IDENTIFIERS = ["`"] 241 STRING_ESCAPES = ["\\"] 242 243 SINGLE_TOKENS = { 244 **tokens.Tokenizer.SINGLE_TOKENS, 245 "$": TokenType.PARAMETER, 246 } 247 248 KEYWORDS = { 249 **tokens.Tokenizer.KEYWORDS, 250 "ADD ARCHIVE": TokenType.COMMAND, 251 "ADD ARCHIVES": TokenType.COMMAND, 252 "ADD FILE": TokenType.COMMAND, 253 "ADD FILES": TokenType.COMMAND, 254 "ADD JAR": TokenType.COMMAND, 255 "ADD JARS": TokenType.COMMAND, 256 "MSCK REPAIR": TokenType.COMMAND, 257 "REFRESH": TokenType.REFRESH, 258 "TIMESTAMP AS OF": TokenType.TIMESTAMP_SNAPSHOT, 259 "VERSION AS OF": TokenType.VERSION_SNAPSHOT, 260 "SERDEPROPERTIES": TokenType.SERDE_PROPERTIES, 261 } 262 263 NUMERIC_LITERALS = { 264 "L": "BIGINT", 265 "S": "SMALLINT", 266 "Y": "TINYINT", 267 "D": "DOUBLE", 268 "F": "FLOAT", 269 "BD": "DECIMAL", 270 } 271 272 class Parser(parser.Parser): 273 LOG_DEFAULTS_TO_LN = True 274 STRICT_CAST = False 275 VALUES_FOLLOWED_BY_PAREN = False 276 277 FUNCTIONS = { 278 **parser.Parser.FUNCTIONS, 279 "BASE64": exp.ToBase64.from_arg_list, 280 "COLLECT_LIST": exp.ArrayAgg.from_arg_list, 281 "COLLECT_SET": exp.ArrayUniqueAgg.from_arg_list, 282 "DATE_ADD": lambda args: exp.TsOrDsAdd( 283 this=seq_get(args, 0), expression=seq_get(args, 1), unit=exp.Literal.string("DAY") 284 ), 285 "DATE_FORMAT": lambda args: build_formatted_time(exp.TimeToStr, "hive")( 286 [ 287 exp.TimeStrToTime(this=seq_get(args, 0)), 288 seq_get(args, 1), 289 ] 290 ), 291 "DATE_SUB": lambda args: exp.TsOrDsAdd( 292 this=seq_get(args, 0), 293 expression=exp.Mul(this=seq_get(args, 1), expression=exp.Literal.number(-1)), 294 unit=exp.Literal.string("DAY"), 295 ), 296 "DATEDIFF": lambda args: exp.DateDiff( 297 this=exp.TsOrDsToDate(this=seq_get(args, 0)), 298 expression=exp.TsOrDsToDate(this=seq_get(args, 1)), 299 ), 300 "DAY": lambda args: exp.Day(this=exp.TsOrDsToDate(this=seq_get(args, 0))), 301 "FIRST": _build_with_ignore_nulls(exp.First), 302 "FIRST_VALUE": _build_with_ignore_nulls(exp.FirstValue), 303 "FROM_UNIXTIME": build_formatted_time(exp.UnixToStr, "hive", True), 304 "GET_JSON_OBJECT": exp.JSONExtractScalar.from_arg_list, 305 "LAST": _build_with_ignore_nulls(exp.Last), 306 "LAST_VALUE": _build_with_ignore_nulls(exp.LastValue), 307 "LOCATE": locate_to_strposition, 308 "MAP": parser.build_var_map, 309 "MONTH": lambda args: exp.Month(this=exp.TsOrDsToDate.from_arg_list(args)), 310 "PERCENTILE": exp.Quantile.from_arg_list, 311 "PERCENTILE_APPROX": exp.ApproxQuantile.from_arg_list, 312 "REGEXP_EXTRACT": lambda args: exp.RegexpExtract( 313 this=seq_get(args, 0), expression=seq_get(args, 1), group=seq_get(args, 2) 314 ), 315 "SEQUENCE": exp.GenerateSeries.from_arg_list, 316 "SIZE": exp.ArraySize.from_arg_list, 317 "SPLIT": exp.RegexpSplit.from_arg_list, 318 "STR_TO_MAP": lambda args: exp.StrToMap( 319 this=seq_get(args, 0), 320 pair_delim=seq_get(args, 1) or exp.Literal.string(","), 321 key_value_delim=seq_get(args, 2) or exp.Literal.string(":"), 322 ), 323 "TO_DATE": build_formatted_time(exp.TsOrDsToDate, "hive"), 324 "TO_JSON": exp.JSONFormat.from_arg_list, 325 "TRUNC": exp.TimestampTrunc.from_arg_list, 326 "UNBASE64": exp.FromBase64.from_arg_list, 327 "UNIX_TIMESTAMP": lambda args: build_formatted_time(exp.StrToUnix, "hive", True)( 328 args or [exp.CurrentTimestamp()] 329 ), 330 "YEAR": lambda args: exp.Year(this=exp.TsOrDsToDate.from_arg_list(args)), 331 } 332 333 NO_PAREN_FUNCTION_PARSERS = { 334 **parser.Parser.NO_PAREN_FUNCTION_PARSERS, 335 "TRANSFORM": lambda self: self._parse_transform(), 336 } 337 338 PROPERTY_PARSERS = { 339 **parser.Parser.PROPERTY_PARSERS, 340 "SERDEPROPERTIES": lambda self: exp.SerdeProperties( 341 expressions=self._parse_wrapped_csv(self._parse_property) 342 ), 343 } 344 345 def _parse_transform(self) -> t.Optional[exp.Transform | exp.QueryTransform]: 346 if not self._match(TokenType.L_PAREN, advance=False): 347 self._retreat(self._index - 1) 348 return None 349 350 args = self._parse_wrapped_csv(self._parse_lambda) 351 row_format_before = self._parse_row_format(match_row=True) 352 353 record_writer = None 354 if self._match_text_seq("RECORDWRITER"): 355 record_writer = self._parse_string() 356 357 if not self._match(TokenType.USING): 358 return exp.Transform.from_arg_list(args) 359 360 command_script = self._parse_string() 361 362 self._match(TokenType.ALIAS) 363 schema = self._parse_schema() 364 365 row_format_after = self._parse_row_format(match_row=True) 366 record_reader = None 367 if self._match_text_seq("RECORDREADER"): 368 record_reader = self._parse_string() 369 370 return self.expression( 371 exp.QueryTransform, 372 expressions=args, 373 command_script=command_script, 374 schema=schema, 375 row_format_before=row_format_before, 376 record_writer=record_writer, 377 row_format_after=row_format_after, 378 record_reader=record_reader, 379 ) 380 381 def _parse_types( 382 self, check_func: bool = False, schema: bool = False, allow_identifiers: bool = True 383 ) -> t.Optional[exp.Expression]: 384 """ 385 Spark (and most likely Hive) treats casts to CHAR(length) and VARCHAR(length) as casts to 386 STRING in all contexts except for schema definitions. For example, this is in Spark v3.4.0: 387 388 spark-sql (default)> select cast(1234 as varchar(2)); 389 23/06/06 15:51:18 WARN CharVarcharUtils: The Spark cast operator does not support 390 char/varchar type and simply treats them as string type. Please use string type 391 directly to avoid confusion. Otherwise, you can set spark.sql.legacy.charVarcharAsString 392 to true, so that Spark treat them as string type as same as Spark 3.0 and earlier 393 394 1234 395 Time taken: 4.265 seconds, Fetched 1 row(s) 396 397 This shows that Spark doesn't truncate the value into '12', which is inconsistent with 398 what other dialects (e.g. postgres) do, so we need to drop the length to transpile correctly. 399 400 Reference: https://spark.apache.org/docs/latest/sql-ref-datatypes.html 401 """ 402 this = super()._parse_types( 403 check_func=check_func, schema=schema, allow_identifiers=allow_identifiers 404 ) 405 406 if this and not schema: 407 return this.transform( 408 lambda node: ( 409 node.replace(exp.DataType.build("text")) 410 if isinstance(node, exp.DataType) and node.is_type("char", "varchar") 411 else node 412 ), 413 copy=False, 414 ) 415 416 return this 417 418 def _parse_partition_and_order( 419 self, 420 ) -> t.Tuple[t.List[exp.Expression], t.Optional[exp.Expression]]: 421 return ( 422 ( 423 self._parse_csv(self._parse_assignment) 424 if self._match_set({TokenType.PARTITION_BY, TokenType.DISTRIBUTE_BY}) 425 else [] 426 ), 427 super()._parse_order(skip_order_token=self._match(TokenType.SORT_BY)), 428 ) 429 430 def _parse_parameter(self) -> exp.Parameter: 431 self._match(TokenType.L_BRACE) 432 this = self._parse_identifier() or self._parse_primary_or_var() 433 expression = self._match(TokenType.COLON) and ( 434 self._parse_identifier() or self._parse_primary_or_var() 435 ) 436 self._match(TokenType.R_BRACE) 437 return self.expression(exp.Parameter, this=this, expression=expression) 438 439 class Generator(generator.Generator): 440 LIMIT_FETCH = "LIMIT" 441 TABLESAMPLE_WITH_METHOD = False 442 JOIN_HINTS = False 443 TABLE_HINTS = False 444 QUERY_HINTS = False 445 INDEX_ON = "ON TABLE" 446 EXTRACT_ALLOWS_QUOTES = False 447 NVL2_SUPPORTED = False 448 LAST_DAY_SUPPORTS_DATE_PART = False 449 JSON_PATH_SINGLE_QUOTE_ESCAPE = True 450 SUPPORTS_TO_NUMBER = False 451 WITH_PROPERTIES_PREFIX = "TBLPROPERTIES" 452 PARSE_JSON_NAME = None 453 PAD_FILL_PATTERN_IS_REQUIRED = True 454 455 EXPRESSIONS_WITHOUT_NESTED_CTES = { 456 exp.Insert, 457 exp.Select, 458 exp.Subquery, 459 exp.SetOperation, 460 } 461 462 SUPPORTED_JSON_PATH_PARTS = { 463 exp.JSONPathKey, 464 exp.JSONPathRoot, 465 exp.JSONPathSubscript, 466 exp.JSONPathWildcard, 467 } 468 469 TYPE_MAPPING = { 470 **generator.Generator.TYPE_MAPPING, 471 exp.DataType.Type.BIT: "BOOLEAN", 472 exp.DataType.Type.DATETIME: "TIMESTAMP", 473 exp.DataType.Type.ROWVERSION: "BINARY", 474 exp.DataType.Type.TEXT: "STRING", 475 exp.DataType.Type.TIME: "TIMESTAMP", 476 exp.DataType.Type.TIMESTAMPTZ: "TIMESTAMP", 477 exp.DataType.Type.UTINYINT: "SMALLINT", 478 exp.DataType.Type.VARBINARY: "BINARY", 479 } 480 481 TRANSFORMS = { 482 **generator.Generator.TRANSFORMS, 483 exp.Group: transforms.preprocess([transforms.unalias_group]), 484 exp.Select: transforms.preprocess( 485 [ 486 transforms.eliminate_qualify, 487 transforms.eliminate_distinct_on, 488 transforms.unnest_to_explode, 489 ] 490 ), 491 exp.Property: _property_sql, 492 exp.AnyValue: rename_func("FIRST"), 493 exp.ApproxDistinct: approx_count_distinct_sql, 494 exp.ArgMax: arg_max_or_min_no_count("MAX_BY"), 495 exp.ArgMin: arg_max_or_min_no_count("MIN_BY"), 496 exp.ArrayConcat: rename_func("CONCAT"), 497 exp.ArrayToString: lambda self, e: self.func("CONCAT_WS", e.expression, e.this), 498 exp.ArraySize: rename_func("SIZE"), 499 exp.ArraySort: _array_sort_sql, 500 exp.With: no_recursive_cte_sql, 501 exp.DateAdd: _add_date_sql, 502 exp.DateDiff: _date_diff_sql, 503 exp.DateStrToDate: datestrtodate_sql, 504 exp.DateSub: _add_date_sql, 505 exp.DateToDi: lambda self, 506 e: f"CAST(DATE_FORMAT({self.sql(e, 'this')}, {Hive.DATEINT_FORMAT}) AS INT)", 507 exp.DiToDate: lambda self, 508 e: f"TO_DATE(CAST({self.sql(e, 'this')} AS STRING), {Hive.DATEINT_FORMAT})", 509 exp.FileFormatProperty: lambda self, 510 e: f"STORED AS {self.sql(e, 'this') if isinstance(e.this, exp.InputOutputFormat) else e.name.upper()}", 511 exp.FromBase64: rename_func("UNBASE64"), 512 exp.GenerateSeries: sequence_sql, 513 exp.If: if_sql(), 514 exp.ILike: no_ilike_sql, 515 exp.IsNan: rename_func("ISNAN"), 516 exp.JSONExtract: lambda self, e: self.func("GET_JSON_OBJECT", e.this, e.expression), 517 exp.JSONExtractScalar: lambda self, e: self.func( 518 "GET_JSON_OBJECT", e.this, e.expression 519 ), 520 exp.JSONFormat: _json_format_sql, 521 exp.Left: left_to_substring_sql, 522 exp.Map: var_map_sql, 523 exp.Max: max_or_greatest, 524 exp.MD5Digest: lambda self, e: self.func("UNHEX", self.func("MD5", e.this)), 525 exp.Min: min_or_least, 526 exp.MonthsBetween: lambda self, e: self.func("MONTHS_BETWEEN", e.this, e.expression), 527 exp.NotNullColumnConstraint: lambda _, e: ( 528 "" if e.args.get("allow_null") else "NOT NULL" 529 ), 530 exp.VarMap: var_map_sql, 531 exp.Create: preprocess( 532 [ 533 remove_unique_constraints, 534 ctas_with_tmp_tables_to_create_tmp_view, 535 move_schema_columns_to_partitioned_by, 536 ] 537 ), 538 exp.Quantile: rename_func("PERCENTILE"), 539 exp.ApproxQuantile: rename_func("PERCENTILE_APPROX"), 540 exp.RegexpExtract: regexp_extract_sql, 541 exp.RegexpReplace: regexp_replace_sql, 542 exp.RegexpLike: lambda self, e: self.binary(e, "RLIKE"), 543 exp.RegexpSplit: rename_func("SPLIT"), 544 exp.Right: right_to_substring_sql, 545 exp.SafeDivide: no_safe_divide_sql, 546 exp.SchemaCommentProperty: lambda self, e: self.naked_property(e), 547 exp.ArrayUniqueAgg: rename_func("COLLECT_SET"), 548 exp.Split: lambda self, e: self.func( 549 "SPLIT", e.this, self.func("CONCAT", "'\\\\Q'", e.expression) 550 ), 551 exp.StrPosition: strposition_to_locate_sql, 552 exp.StrToDate: _str_to_date_sql, 553 exp.StrToTime: _str_to_time_sql, 554 exp.StrToUnix: _str_to_unix_sql, 555 exp.StructExtract: struct_extract_sql, 556 exp.TimeStrToDate: rename_func("TO_DATE"), 557 exp.TimeStrToTime: timestrtotime_sql, 558 exp.TimeStrToUnix: rename_func("UNIX_TIMESTAMP"), 559 exp.TimestampTrunc: lambda self, e: self.func("TRUNC", e.this, unit_to_str(e)), 560 exp.TimeToStr: lambda self, e: self.func("DATE_FORMAT", e.this, self.format_time(e)), 561 exp.TimeToUnix: rename_func("UNIX_TIMESTAMP"), 562 exp.ToBase64: rename_func("BASE64"), 563 exp.TsOrDiToDi: lambda self, 564 e: f"CAST(SUBSTR(REPLACE(CAST({self.sql(e, 'this')} AS STRING), '-', ''), 1, 8) AS INT)", 565 exp.TsOrDsAdd: _add_date_sql, 566 exp.TsOrDsDiff: _date_diff_sql, 567 exp.TsOrDsToDate: _to_date_sql, 568 exp.TryCast: no_trycast_sql, 569 exp.UnixToStr: lambda self, e: self.func( 570 "FROM_UNIXTIME", e.this, time_format("hive")(self, e) 571 ), 572 exp.UnixToTime: _unix_to_time_sql, 573 exp.UnixToTimeStr: rename_func("FROM_UNIXTIME"), 574 exp.PartitionedByProperty: lambda self, e: f"PARTITIONED BY {self.sql(e, 'this')}", 575 exp.NumberToStr: rename_func("FORMAT_NUMBER"), 576 exp.National: lambda self, e: self.national_sql(e, prefix=""), 577 exp.ClusteredColumnConstraint: lambda self, 578 e: f"({self.expressions(e, 'this', indent=False)})", 579 exp.NonClusteredColumnConstraint: lambda self, 580 e: f"({self.expressions(e, 'this', indent=False)})", 581 exp.NotForReplicationColumnConstraint: lambda *_: "", 582 exp.OnProperty: lambda *_: "", 583 exp.PrimaryKeyColumnConstraint: lambda *_: "PRIMARY KEY", 584 exp.WeekOfYear: rename_func("WEEKOFYEAR"), 585 exp.DayOfMonth: rename_func("DAYOFMONTH"), 586 exp.DayOfWeek: rename_func("DAYOFWEEK"), 587 } 588 589 PROPERTIES_LOCATION = { 590 **generator.Generator.PROPERTIES_LOCATION, 591 exp.FileFormatProperty: exp.Properties.Location.POST_SCHEMA, 592 exp.PartitionedByProperty: exp.Properties.Location.POST_SCHEMA, 593 exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED, 594 exp.WithDataProperty: exp.Properties.Location.UNSUPPORTED, 595 } 596 597 def _jsonpathkey_sql(self, expression: exp.JSONPathKey) -> str: 598 if isinstance(expression.this, exp.JSONPathWildcard): 599 self.unsupported("Unsupported wildcard in JSONPathKey expression") 600 return "" 601 602 return super()._jsonpathkey_sql(expression) 603 604 def parameter_sql(self, expression: exp.Parameter) -> str: 605 this = self.sql(expression, "this") 606 expression_sql = self.sql(expression, "expression") 607 608 parent = expression.parent 609 this = f"{this}:{expression_sql}" if expression_sql else this 610 611 if isinstance(parent, exp.EQ) and isinstance(parent.parent, exp.SetItem): 612 # We need to produce SET key = value instead of SET ${key} = value 613 return this 614 615 return f"${{{this}}}" 616 617 def schema_sql(self, expression: exp.Schema) -> str: 618 for ordered in expression.find_all(exp.Ordered): 619 if ordered.args.get("desc") is False: 620 ordered.set("desc", None) 621 622 return super().schema_sql(expression) 623 624 def constraint_sql(self, expression: exp.Constraint) -> str: 625 for prop in list(expression.find_all(exp.Properties)): 626 prop.pop() 627 628 this = self.sql(expression, "this") 629 expressions = self.expressions(expression, sep=" ", flat=True) 630 return f"CONSTRAINT {this} {expressions}" 631 632 def rowformatserdeproperty_sql(self, expression: exp.RowFormatSerdeProperty) -> str: 633 serde_props = self.sql(expression, "serde_properties") 634 serde_props = f" {serde_props}" if serde_props else "" 635 return f"ROW FORMAT SERDE {self.sql(expression, 'this')}{serde_props}" 636 637 def arrayagg_sql(self, expression: exp.ArrayAgg) -> str: 638 return self.func( 639 "COLLECT_LIST", 640 expression.this.this if isinstance(expression.this, exp.Order) else expression.this, 641 ) 642 643 def datatype_sql(self, expression: exp.DataType) -> str: 644 if expression.this in self.PARAMETERIZABLE_TEXT_TYPES and ( 645 not expression.expressions or expression.expressions[0].name == "MAX" 646 ): 647 expression = exp.DataType.build("text") 648 elif expression.is_type(exp.DataType.Type.TEXT) and expression.expressions: 649 expression.set("this", exp.DataType.Type.VARCHAR) 650 elif expression.this in exp.DataType.TEMPORAL_TYPES: 651 expression = exp.DataType.build(expression.this) 652 elif expression.is_type("float"): 653 size_expression = expression.find(exp.DataTypeParam) 654 if size_expression: 655 size = int(size_expression.name) 656 expression = ( 657 exp.DataType.build("float") if size <= 32 else exp.DataType.build("double") 658 ) 659 660 return super().datatype_sql(expression) 661 662 def version_sql(self, expression: exp.Version) -> str: 663 sql = super().version_sql(expression) 664 return sql.replace("FOR ", "", 1) 665 666 def struct_sql(self, expression: exp.Struct) -> str: 667 values = [] 668 669 for i, e in enumerate(expression.expressions): 670 if isinstance(e, exp.PropertyEQ): 671 self.unsupported("Hive does not support named structs.") 672 values.append(e.expression) 673 else: 674 values.append(e) 675 676 return self.func("STRUCT", *values) 677 678 def alterset_sql(self, expression: exp.AlterSet) -> str: 679 exprs = self.expressions(expression, flat=True) 680 exprs = f" {exprs}" if exprs else "" 681 location = self.sql(expression, "location") 682 location = f" LOCATION {location}" if location else "" 683 file_format = self.expressions(expression, key="file_format", flat=True, sep=" ") 684 file_format = f" FILEFORMAT {file_format}" if file_format else "" 685 serde = self.sql(expression, "serde") 686 serde = f" SERDE {serde}" if serde else "" 687 tags = self.expressions(expression, key="tag", flat=True, sep="") 688 tags = f" TAGS {tags}" if tags else "" 689 690 return f"SET{serde}{exprs}{location}{file_format}{tags}" 691 692 def serdeproperties_sql(self, expression: exp.SerdeProperties) -> str: 693 prefix = "WITH " if expression.args.get("with") else "" 694 exprs = self.expressions(expression, flat=True) 695 696 return f"{prefix}SERDEPROPERTIES ({exprs})"
NORMALIZATION_STRATEGY =
<NormalizationStrategy.CASE_INSENSITIVE: 'CASE_INSENSITIVE'>
Specifies the strategy according to which identifiers should be normalized.
TIME_MAPPING: Dict[str, str] =
{'y': '%Y', 'Y': '%Y', 'YYYY': '%Y', 'yyyy': '%Y', 'YY': '%y', 'yy': '%y', 'MMMM': '%B', 'MMM': '%b', 'MM': '%m', 'M': '%-m', 'dd': '%d', 'd': '%-d', 'HH': '%H', 'H': '%-H', 'hh': '%I', 'h': '%-I', 'mm': '%M', 'm': '%-M', 'ss': '%S', 's': '%-S', 'SSSSSS': '%f', 'a': '%p', 'DD': '%j', 'D': '%-j', 'E': '%a', 'EE': '%a', 'EEE': '%a', 'EEEE': '%A'}
Associates this dialect's time formats with their equivalent Python strftime
formats.
UNESCAPED_SEQUENCES: Dict[str, str] =
{'\\a': '\x07', '\\b': '\x08', '\\f': '\x0c', '\\n': '\n', '\\r': '\r', '\\t': '\t', '\\v': '\x0b', '\\\\': '\\'}
Mapping of an escaped sequence (\n
) to its unescaped version (
).
tokenizer_class =
<class 'Hive.Tokenizer'>
parser_class =
<class 'Hive.Parser'>
generator_class =
<class 'Hive.Generator'>
TIME_TRIE: Dict =
{'y': {0: True, 'y': {'y': {'y': {0: True}}, 0: True}}, 'Y': {0: True, 'Y': {'Y': {'Y': {0: True}}, 0: True}}, 'M': {'M': {'M': {'M': {0: True}, 0: True}, 0: True}, 0: True}, 'd': {'d': {0: True}, 0: True}, 'H': {'H': {0: True}, 0: True}, 'h': {'h': {0: True}, 0: True}, 'm': {'m': {0: True}, 0: True}, 's': {'s': {0: True}, 0: True}, 'S': {'S': {'S': {'S': {'S': {'S': {0: True}}}}}}, 'a': {0: True}, 'D': {'D': {0: True}, 0: True}, 'E': {0: True, 'E': {0: True, 'E': {0: True, 'E': {0: True}}}}}
FORMAT_TRIE: Dict =
{'y': {0: True, 'y': {'y': {'y': {0: True}}, 0: True}}, 'Y': {0: True, 'Y': {'Y': {'Y': {0: True}}, 0: True}}, 'M': {'M': {'M': {'M': {0: True}, 0: True}, 0: True}, 0: True}, 'd': {'d': {0: True}, 0: True}, 'H': {'H': {0: True}, 0: True}, 'h': {'h': {0: True}, 0: True}, 'm': {'m': {0: True}, 0: True}, 's': {'s': {0: True}, 0: True}, 'S': {'S': {'S': {'S': {'S': {'S': {0: True}}}}}}, 'a': {0: True}, 'D': {'D': {0: True}, 0: True}, 'E': {0: True, 'E': {0: True, 'E': {0: True, 'E': {0: True}}}}}
INVERSE_TIME_MAPPING: Dict[str, str] =
{'%Y': 'yyyy', '%y': 'yy', '%B': 'MMMM', '%b': 'MMM', '%m': 'MM', '%-m': 'M', '%d': 'dd', '%-d': 'd', '%H': 'HH', '%-H': 'H', '%I': 'hh', '%-I': 'h', '%M': 'mm', '%-M': 'm', '%S': 'ss', '%-S': 's', '%f': 'SSSSSS', '%p': 'a', '%j': 'DD', '%-j': 'D', '%a': 'EEE', '%A': 'EEEE'}
INVERSE_TIME_TRIE: Dict =
{'%': {'Y': {0: True}, 'y': {0: True}, 'B': {0: True}, 'b': {0: True}, 'm': {0: True}, '-': {'m': {0: True}, 'd': {0: True}, 'H': {0: True}, 'I': {0: True}, 'M': {0: True}, 'S': {0: True}, 'j': {0: True}}, 'd': {0: True}, 'H': {0: True}, 'I': {0: True}, 'M': {0: True}, 'S': {0: True}, 'f': {0: True}, 'p': {0: True}, 'j': {0: True}, 'a': {0: True}, 'A': {0: True}}}
ESCAPED_SEQUENCES: Dict[str, str] =
{'\x07': '\\a', '\x08': '\\b', '\x0c': '\\f', '\n': '\\n', '\r': '\\r', '\t': '\\t', '\x0b': '\\v', '\\': '\\\\'}
Inherited Members
- sqlglot.dialects.dialect.Dialect
- Dialect
- INDEX_OFFSET
- WEEK_OFFSET
- UNNEST_COLUMN_ONLY
- TABLESAMPLE_SIZE_IS_PERCENT
- DPIPE_IS_STRING_CONCAT
- STRICT_STRING_CONCAT
- SUPPORTS_SEMI_ANTI_JOIN
- COPY_PARAMS_ARE_CSV
- NORMALIZE_FUNCTIONS
- LOG_BASE_FIRST
- NULL_ORDERING
- TYPED_DIVISION
- CONCAT_COALESCE
- HEX_LOWERCASE
- FORMAT_MAPPING
- PSEUDOCOLUMNS
- PREFER_CTE_ALIAS_COLUMN
- FORCE_EARLY_ALIAS_REF_EXPANSION
- EXPAND_ALIAS_REFS_EARLY_ONLY_IN_GROUP_BY
- SUPPORTS_ORDER_BY_ALL
- DATE_PART_MAPPING
- TYPE_TO_EXPRESSIONS
- ANNOTATORS
- get_or_raise
- format_time
- settings
- normalize_identifier
- case_sensitive
- can_identify
- quote_identifier
- to_json_path
- parse
- parse_into
- generate
- transpile
- tokenize
- tokenizer
- jsonpath_tokenizer
- parser
- generator
238 class Tokenizer(tokens.Tokenizer): 239 QUOTES = ["'", '"'] 240 IDENTIFIERS = ["`"] 241 STRING_ESCAPES = ["\\"] 242 243 SINGLE_TOKENS = { 244 **tokens.Tokenizer.SINGLE_TOKENS, 245 "$": TokenType.PARAMETER, 246 } 247 248 KEYWORDS = { 249 **tokens.Tokenizer.KEYWORDS, 250 "ADD ARCHIVE": TokenType.COMMAND, 251 "ADD ARCHIVES": TokenType.COMMAND, 252 "ADD FILE": TokenType.COMMAND, 253 "ADD FILES": TokenType.COMMAND, 254 "ADD JAR": TokenType.COMMAND, 255 "ADD JARS": TokenType.COMMAND, 256 "MSCK REPAIR": TokenType.COMMAND, 257 "REFRESH": TokenType.REFRESH, 258 "TIMESTAMP AS OF": TokenType.TIMESTAMP_SNAPSHOT, 259 "VERSION AS OF": TokenType.VERSION_SNAPSHOT, 260 "SERDEPROPERTIES": TokenType.SERDE_PROPERTIES, 261 } 262 263 NUMERIC_LITERALS = { 264 "L": "BIGINT", 265 "S": "SMALLINT", 266 "Y": "TINYINT", 267 "D": "DOUBLE", 268 "F": "FLOAT", 269 "BD": "DECIMAL", 270 }
SINGLE_TOKENS =
{'(': <TokenType.L_PAREN: 'L_PAREN'>, ')': <TokenType.R_PAREN: 'R_PAREN'>, '[': <TokenType.L_BRACKET: 'L_BRACKET'>, ']': <TokenType.R_BRACKET: 'R_BRACKET'>, '{': <TokenType.L_BRACE: 'L_BRACE'>, '}': <TokenType.R_BRACE: 'R_BRACE'>, '&': <TokenType.AMP: 'AMP'>, '^': <TokenType.CARET: 'CARET'>, ':': <TokenType.COLON: 'COLON'>, ',': <TokenType.COMMA: 'COMMA'>, '.': <TokenType.DOT: 'DOT'>, '-': <TokenType.DASH: 'DASH'>, '=': <TokenType.EQ: 'EQ'>, '>': <TokenType.GT: 'GT'>, '<': <TokenType.LT: 'LT'>, '%': <TokenType.MOD: 'MOD'>, '!': <TokenType.NOT: 'NOT'>, '|': <TokenType.PIPE: 'PIPE'>, '+': <TokenType.PLUS: 'PLUS'>, ';': <TokenType.SEMICOLON: 'SEMICOLON'>, '/': <TokenType.SLASH: 'SLASH'>, '\\': <TokenType.BACKSLASH: 'BACKSLASH'>, '*': <TokenType.STAR: 'STAR'>, '~': <TokenType.TILDA: 'TILDA'>, '?': <TokenType.PLACEHOLDER: 'PLACEHOLDER'>, '@': <TokenType.PARAMETER: 'PARAMETER'>, '#': <TokenType.HASH: 'HASH'>, "'": <TokenType.UNKNOWN: 'UNKNOWN'>, '`': <TokenType.UNKNOWN: 'UNKNOWN'>, '"': <TokenType.UNKNOWN: 'UNKNOWN'>, '$': <TokenType.PARAMETER: 'PARAMETER'>}
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.COLON_EQ: 'COLON_EQ'>, '<=>': <TokenType.NULLSAFE_EQ: 'NULLSAFE_EQ'>, '->': <TokenType.ARROW: 'ARROW'>, '->>': <TokenType.DARROW: 'DARROW'>, '=>': <TokenType.FARROW: 'FARROW'>, '#>': <TokenType.HASH_ARROW: 'HASH_ARROW'>, '#>>': <TokenType.DHASH_ARROW: 'DHASH_ARROW'>, '<->': <TokenType.LR_ARROW: 'LR_ARROW'>, '&&': <TokenType.DAMP: 'DAMP'>, '??': <TokenType.DQMARK: 'DQMARK'>, 'ALL': <TokenType.ALL: 'ALL'>, 'ALWAYS': <TokenType.ALWAYS: 'ALWAYS'>, 'AND': <TokenType.AND: 'AND'>, 'ANTI': <TokenType.ANTI: 'ANTI'>, 'ANY': <TokenType.ANY: 'ANY'>, 'ASC': <TokenType.ASC: 'ASC'>, 'AS': <TokenType.ALIAS: 'ALIAS'>, 'ASOF': <TokenType.ASOF: 'ASOF'>, 'AUTOINCREMENT': <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, 'AUTO_INCREMENT': <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, 'BEGIN': <TokenType.BEGIN: 'BEGIN'>, 'BETWEEN': <TokenType.BETWEEN: 'BETWEEN'>, 'CACHE': <TokenType.CACHE: 'CACHE'>, 'UNCACHE': <TokenType.UNCACHE: 'UNCACHE'>, 'CASE': <TokenType.CASE: 'CASE'>, 'CHARACTER SET': <TokenType.CHARACTER_SET: 'CHARACTER_SET'>, 'CLUSTER BY': <TokenType.CLUSTER_BY: 'CLUSTER_BY'>, 'COLLATE': <TokenType.COLLATE: 'COLLATE'>, 'COLUMN': <TokenType.COLUMN: 'COLUMN'>, 'COMMIT': <TokenType.COMMIT: 'COMMIT'>, 'CONNECT BY': <TokenType.CONNECT_BY: 'CONNECT_BY'>, 'CONSTRAINT': <TokenType.CONSTRAINT: 'CONSTRAINT'>, 'COPY': <TokenType.COPY: 'COPY'>, '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'>, 'ENUM': <TokenType.ENUM: 'ENUM'>, 'ESCAPE': <TokenType.ESCAPE: 'ESCAPE'>, 'EXCEPT': <TokenType.EXCEPT: 'EXCEPT'>, 'EXECUTE': <TokenType.EXECUTE: 'EXECUTE'>, 'EXISTS': <TokenType.EXISTS: 'EXISTS'>, 'FALSE': <TokenType.FALSE: 'FALSE'>, 'FETCH': <TokenType.FETCH: 'FETCH'>, 'FILTER': <TokenType.FILTER: 'FILTER'>, 'FIRST': <TokenType.FIRST: 'FIRST'>, 'FULL': <TokenType.FULL: 'FULL'>, 'FUNCTION': <TokenType.FUNCTION: 'FUNCTION'>, 'FOR': <TokenType.FOR: 'FOR'>, 'FOREIGN KEY': <TokenType.FOREIGN_KEY: 'FOREIGN_KEY'>, 'FORMAT': <TokenType.FORMAT: 'FORMAT'>, 'FROM': <TokenType.FROM: 'FROM'>, 'GEOGRAPHY': <TokenType.GEOGRAPHY: 'GEOGRAPHY'>, 'GEOMETRY': <TokenType.GEOMETRY: 'GEOMETRY'>, 'GLOB': <TokenType.GLOB: 'GLOB'>, 'GROUP BY': <TokenType.GROUP_BY: 'GROUP_BY'>, 'GROUPING SETS': <TokenType.GROUPING_SETS: 'GROUPING_SETS'>, 'HAVING': <TokenType.HAVING: 'HAVING'>, 'ILIKE': <TokenType.ILIKE: 'ILIKE'>, 'IN': <TokenType.IN: 'IN'>, 'INDEX': <TokenType.INDEX: 'INDEX'>, 'INET': <TokenType.INET: 'INET'>, 'INNER': <TokenType.INNER: 'INNER'>, 'INSERT': <TokenType.INSERT: 'INSERT'>, 'INTERVAL': <TokenType.INTERVAL: 'INTERVAL'>, 'INTERSECT': <TokenType.INTERSECT: 'INTERSECT'>, 'INTO': <TokenType.INTO: 'INTO'>, 'IS': <TokenType.IS: 'IS'>, 'ISNULL': <TokenType.ISNULL: 'ISNULL'>, 'JOIN': <TokenType.JOIN: 'JOIN'>, 'KEEP': <TokenType.KEEP: 'KEEP'>, 'KILL': <TokenType.KILL: 'KILL'>, 'LATERAL': <TokenType.LATERAL: 'LATERAL'>, 'LEFT': <TokenType.LEFT: 'LEFT'>, 'LIKE': <TokenType.LIKE: 'LIKE'>, 'LIMIT': <TokenType.LIMIT: 'LIMIT'>, 'LOAD': <TokenType.LOAD: 'LOAD'>, 'LOCK': <TokenType.LOCK: 'LOCK'>, 'MERGE': <TokenType.MERGE: 'MERGE'>, 'NATURAL': <TokenType.NATURAL: 'NATURAL'>, 'NEXT': <TokenType.NEXT: 'NEXT'>, 'NOT': <TokenType.NOT: 'NOT'>, 'NOTNULL': <TokenType.NOTNULL: 'NOTNULL'>, 'NULL': <TokenType.NULL: 'NULL'>, 'OBJECT': <TokenType.OBJECT: 'OBJECT'>, 'OFFSET': <TokenType.OFFSET: 'OFFSET'>, 'ON': <TokenType.ON: 'ON'>, 'OR': <TokenType.OR: 'OR'>, 'XOR': <TokenType.XOR: 'XOR'>, 'ORDER BY': <TokenType.ORDER_BY: 'ORDER_BY'>, 'ORDINALITY': <TokenType.ORDINALITY: 'ORDINALITY'>, 'OUTER': <TokenType.OUTER: 'OUTER'>, 'OVER': <TokenType.OVER: 'OVER'>, 'OVERLAPS': <TokenType.OVERLAPS: 'OVERLAPS'>, 'OVERWRITE': <TokenType.OVERWRITE: 'OVERWRITE'>, 'PARTITION': <TokenType.PARTITION: 'PARTITION'>, 'PARTITION BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PARTITIONED BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PARTITIONED_BY': <TokenType.PARTITION_BY: 'PARTITION_BY'>, 'PERCENT': <TokenType.PERCENT: 'PERCENT'>, 'PIVOT': <TokenType.PIVOT: 'PIVOT'>, 'PRAGMA': <TokenType.PRAGMA: 'PRAGMA'>, 'PRIMARY KEY': <TokenType.PRIMARY_KEY: 'PRIMARY_KEY'>, 'PROCEDURE': <TokenType.PROCEDURE: 'PROCEDURE'>, 'QUALIFY': <TokenType.QUALIFY: 'QUALIFY'>, 'RANGE': <TokenType.RANGE: 'RANGE'>, 'RECURSIVE': <TokenType.RECURSIVE: 'RECURSIVE'>, 'REGEXP': <TokenType.RLIKE: 'RLIKE'>, 'REPLACE': <TokenType.REPLACE: 'REPLACE'>, 'RETURNING': <TokenType.RETURNING: 'RETURNING'>, 'REFERENCES': <TokenType.REFERENCES: 'REFERENCES'>, 'RIGHT': <TokenType.RIGHT: 'RIGHT'>, 'RLIKE': <TokenType.RLIKE: 'RLIKE'>, 'ROLLBACK': <TokenType.ROLLBACK: 'ROLLBACK'>, 'ROLLUP': <TokenType.ROLLUP: 'ROLLUP'>, 'ROW': <TokenType.ROW: 'ROW'>, 'ROWS': <TokenType.ROWS: 'ROWS'>, 'SCHEMA': <TokenType.SCHEMA: 'SCHEMA'>, 'SELECT': <TokenType.SELECT: 'SELECT'>, 'SEMI': <TokenType.SEMI: 'SEMI'>, 'SET': <TokenType.SET: 'SET'>, 'SETTINGS': <TokenType.SETTINGS: 'SETTINGS'>, 'SHOW': <TokenType.SHOW: 'SHOW'>, 'SIMILAR TO': <TokenType.SIMILAR_TO: 'SIMILAR_TO'>, 'SOME': <TokenType.SOME: 'SOME'>, 'SORT BY': <TokenType.SORT_BY: 'SORT_BY'>, 'START WITH': <TokenType.START_WITH: 'START_WITH'>, 'STRAIGHT_JOIN': <TokenType.STRAIGHT_JOIN: 'STRAIGHT_JOIN'>, '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'>, 'TRUNCATE': <TokenType.TRUNCATE: 'TRUNCATE'>, 'UNION': <TokenType.UNION: 'UNION'>, 'UNKNOWN': <TokenType.UNKNOWN: 'UNKNOWN'>, 'UNNEST': <TokenType.UNNEST: 'UNNEST'>, 'UNPIVOT': <TokenType.UNPIVOT: 'UNPIVOT'>, 'UPDATE': <TokenType.UPDATE: 'UPDATE'>, 'USE': <TokenType.USE: 'USE'>, 'USING': <TokenType.USING: 'USING'>, 'UUID': <TokenType.UUID: 'UUID'>, 'VALUES': <TokenType.VALUES: 'VALUES'>, 'VIEW': <TokenType.VIEW: 'VIEW'>, 'VOLATILE': <TokenType.VOLATILE: 'VOLATILE'>, 'WHEN': <TokenType.WHEN: 'WHEN'>, 'WHERE': <TokenType.WHERE: 'WHERE'>, 'WINDOW': <TokenType.WINDOW: 'WINDOW'>, 'WITH': <TokenType.WITH: 'WITH'>, 'APPLY': <TokenType.APPLY: 'APPLY'>, 'ARRAY': <TokenType.ARRAY: 'ARRAY'>, 'BIT': <TokenType.BIT: 'BIT'>, 'BOOL': <TokenType.BOOLEAN: 'BOOLEAN'>, 'BOOLEAN': <TokenType.BOOLEAN: 'BOOLEAN'>, 'BYTE': <TokenType.TINYINT: 'TINYINT'>, 'MEDIUMINT': <TokenType.MEDIUMINT: 'MEDIUMINT'>, 'INT1': <TokenType.TINYINT: 'TINYINT'>, 'TINYINT': <TokenType.TINYINT: 'TINYINT'>, 'INT16': <TokenType.SMALLINT: 'SMALLINT'>, 'SHORT': <TokenType.SMALLINT: 'SMALLINT'>, 'SMALLINT': <TokenType.SMALLINT: 'SMALLINT'>, 'INT128': <TokenType.INT128: 'INT128'>, 'HUGEINT': <TokenType.INT128: 'INT128'>, 'INT2': <TokenType.SMALLINT: 'SMALLINT'>, 'INTEGER': <TokenType.INT: 'INT'>, 'INT': <TokenType.INT: 'INT'>, 'INT4': <TokenType.INT: 'INT'>, 'INT32': <TokenType.INT: 'INT'>, 'INT64': <TokenType.BIGINT: 'BIGINT'>, 'LONG': <TokenType.BIGINT: 'BIGINT'>, 'BIGINT': <TokenType.BIGINT: 'BIGINT'>, 'INT8': <TokenType.TINYINT: 'TINYINT'>, 'UINT': <TokenType.UINT: 'UINT'>, 'DEC': <TokenType.DECIMAL: 'DECIMAL'>, 'DECIMAL': <TokenType.DECIMAL: 'DECIMAL'>, 'BIGDECIMAL': <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, 'BIGNUMERIC': <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, 'LIST': <TokenType.LIST: 'LIST'>, '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'>, 'JSONB': <TokenType.JSONB: 'JSONB'>, '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'>, 'BPCHAR': <TokenType.BPCHAR: 'BPCHAR'>, 'STR': <TokenType.TEXT: 'TEXT'>, 'STRING': <TokenType.TEXT: 'TEXT'>, 'TEXT': <TokenType.TEXT: 'TEXT'>, 'LONGTEXT': <TokenType.LONGTEXT: 'LONGTEXT'>, 'MEDIUMTEXT': <TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>, 'TINYTEXT': <TokenType.TINYTEXT: 'TINYTEXT'>, 'CLOB': <TokenType.TEXT: 'TEXT'>, 'LONGVARCHAR': <TokenType.TEXT: 'TEXT'>, 'BINARY': <TokenType.BINARY: 'BINARY'>, 'BLOB': <TokenType.VARBINARY: 'VARBINARY'>, 'LONGBLOB': <TokenType.LONGBLOB: 'LONGBLOB'>, 'MEDIUMBLOB': <TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>, 'TINYBLOB': <TokenType.TINYBLOB: 'TINYBLOB'>, 'BYTEA': <TokenType.VARBINARY: 'VARBINARY'>, 'VARBINARY': <TokenType.VARBINARY: 'VARBINARY'>, 'TIME': <TokenType.TIME: 'TIME'>, 'TIMETZ': <TokenType.TIMETZ: 'TIMETZ'>, 'TIMESTAMP': <TokenType.TIMESTAMP: 'TIMESTAMP'>, 'TIMESTAMPTZ': <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>, 'TIMESTAMPLTZ': <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>, 'TIMESTAMP_LTZ': <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>, 'TIMESTAMPNTZ': <TokenType.TIMESTAMPNTZ: 'TIMESTAMPNTZ'>, 'TIMESTAMP_NTZ': <TokenType.TIMESTAMPNTZ: 'TIMESTAMPNTZ'>, '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'>, 'VECTOR': <TokenType.VECTOR: 'VECTOR'>, 'STRUCT': <TokenType.STRUCT: 'STRUCT'>, 'SEQUENCE': <TokenType.SEQUENCE: 'SEQUENCE'>, 'VARIANT': <TokenType.VARIANT: 'VARIANT'>, 'ALTER': <TokenType.ALTER: 'ALTER'>, 'ANALYZE': <TokenType.COMMAND: 'COMMAND'>, 'CALL': <TokenType.COMMAND: 'COMMAND'>, 'COMMENT': <TokenType.COMMENT: 'COMMENT'>, 'EXPLAIN': <TokenType.COMMAND: 'COMMAND'>, 'GRANT': <TokenType.COMMAND: 'COMMAND'>, 'OPTIMIZE': <TokenType.COMMAND: 'COMMAND'>, 'PREPARE': <TokenType.COMMAND: 'COMMAND'>, 'VACUUM': <TokenType.COMMAND: 'COMMAND'>, 'USER-DEFINED': <TokenType.USERDEFINED: 'USERDEFINED'>, 'FOR VERSION': <TokenType.VERSION_SNAPSHOT: 'VERSION_SNAPSHOT'>, 'FOR TIMESTAMP': <TokenType.TIMESTAMP_SNAPSHOT: 'TIMESTAMP_SNAPSHOT'>, 'ADD ARCHIVE': <TokenType.COMMAND: 'COMMAND'>, 'ADD ARCHIVES': <TokenType.COMMAND: 'COMMAND'>, 'ADD FILE': <TokenType.COMMAND: 'COMMAND'>, 'ADD FILES': <TokenType.COMMAND: 'COMMAND'>, 'ADD JAR': <TokenType.COMMAND: 'COMMAND'>, 'ADD JARS': <TokenType.COMMAND: 'COMMAND'>, 'MSCK REPAIR': <TokenType.COMMAND: 'COMMAND'>, 'REFRESH': <TokenType.REFRESH: 'REFRESH'>, 'TIMESTAMP AS OF': <TokenType.TIMESTAMP_SNAPSHOT: 'TIMESTAMP_SNAPSHOT'>, 'VERSION AS OF': <TokenType.VERSION_SNAPSHOT: 'VERSION_SNAPSHOT'>, 'SERDEPROPERTIES': <TokenType.SERDE_PROPERTIES: 'SERDE_PROPERTIES'>}
NUMERIC_LITERALS =
{'L': 'BIGINT', 'S': 'SMALLINT', 'Y': 'TINYINT', 'D': 'DOUBLE', 'F': 'FLOAT', 'BD': 'DECIMAL'}
Inherited Members
- sqlglot.tokens.Tokenizer
- Tokenizer
- BIT_STRINGS
- BYTE_STRINGS
- HEX_STRINGS
- RAW_STRINGS
- HEREDOC_STRINGS
- UNICODE_STRINGS
- IDENTIFIER_ESCAPES
- VAR_SINGLE_TOKENS
- HEREDOC_TAG_IS_IDENTIFIER
- HEREDOC_STRING_ALTERNATIVE
- STRING_ESCAPES_ALLOWED_IN_RAW_STRINGS
- WHITE_SPACE
- COMMANDS
- COMMAND_PREFIX_TOKENS
- COMMENTS
- dialect
- reset
- tokenize
- tokenize_rs
- size
- sql
- tokens
272 class Parser(parser.Parser): 273 LOG_DEFAULTS_TO_LN = True 274 STRICT_CAST = False 275 VALUES_FOLLOWED_BY_PAREN = False 276 277 FUNCTIONS = { 278 **parser.Parser.FUNCTIONS, 279 "BASE64": exp.ToBase64.from_arg_list, 280 "COLLECT_LIST": exp.ArrayAgg.from_arg_list, 281 "COLLECT_SET": exp.ArrayUniqueAgg.from_arg_list, 282 "DATE_ADD": lambda args: exp.TsOrDsAdd( 283 this=seq_get(args, 0), expression=seq_get(args, 1), unit=exp.Literal.string("DAY") 284 ), 285 "DATE_FORMAT": lambda args: build_formatted_time(exp.TimeToStr, "hive")( 286 [ 287 exp.TimeStrToTime(this=seq_get(args, 0)), 288 seq_get(args, 1), 289 ] 290 ), 291 "DATE_SUB": lambda args: exp.TsOrDsAdd( 292 this=seq_get(args, 0), 293 expression=exp.Mul(this=seq_get(args, 1), expression=exp.Literal.number(-1)), 294 unit=exp.Literal.string("DAY"), 295 ), 296 "DATEDIFF": lambda args: exp.DateDiff( 297 this=exp.TsOrDsToDate(this=seq_get(args, 0)), 298 expression=exp.TsOrDsToDate(this=seq_get(args, 1)), 299 ), 300 "DAY": lambda args: exp.Day(this=exp.TsOrDsToDate(this=seq_get(args, 0))), 301 "FIRST": _build_with_ignore_nulls(exp.First), 302 "FIRST_VALUE": _build_with_ignore_nulls(exp.FirstValue), 303 "FROM_UNIXTIME": build_formatted_time(exp.UnixToStr, "hive", True), 304 "GET_JSON_OBJECT": exp.JSONExtractScalar.from_arg_list, 305 "LAST": _build_with_ignore_nulls(exp.Last), 306 "LAST_VALUE": _build_with_ignore_nulls(exp.LastValue), 307 "LOCATE": locate_to_strposition, 308 "MAP": parser.build_var_map, 309 "MONTH": lambda args: exp.Month(this=exp.TsOrDsToDate.from_arg_list(args)), 310 "PERCENTILE": exp.Quantile.from_arg_list, 311 "PERCENTILE_APPROX": exp.ApproxQuantile.from_arg_list, 312 "REGEXP_EXTRACT": lambda args: exp.RegexpExtract( 313 this=seq_get(args, 0), expression=seq_get(args, 1), group=seq_get(args, 2) 314 ), 315 "SEQUENCE": exp.GenerateSeries.from_arg_list, 316 "SIZE": exp.ArraySize.from_arg_list, 317 "SPLIT": exp.RegexpSplit.from_arg_list, 318 "STR_TO_MAP": lambda args: exp.StrToMap( 319 this=seq_get(args, 0), 320 pair_delim=seq_get(args, 1) or exp.Literal.string(","), 321 key_value_delim=seq_get(args, 2) or exp.Literal.string(":"), 322 ), 323 "TO_DATE": build_formatted_time(exp.TsOrDsToDate, "hive"), 324 "TO_JSON": exp.JSONFormat.from_arg_list, 325 "TRUNC": exp.TimestampTrunc.from_arg_list, 326 "UNBASE64": exp.FromBase64.from_arg_list, 327 "UNIX_TIMESTAMP": lambda args: build_formatted_time(exp.StrToUnix, "hive", True)( 328 args or [exp.CurrentTimestamp()] 329 ), 330 "YEAR": lambda args: exp.Year(this=exp.TsOrDsToDate.from_arg_list(args)), 331 } 332 333 NO_PAREN_FUNCTION_PARSERS = { 334 **parser.Parser.NO_PAREN_FUNCTION_PARSERS, 335 "TRANSFORM": lambda self: self._parse_transform(), 336 } 337 338 PROPERTY_PARSERS = { 339 **parser.Parser.PROPERTY_PARSERS, 340 "SERDEPROPERTIES": lambda self: exp.SerdeProperties( 341 expressions=self._parse_wrapped_csv(self._parse_property) 342 ), 343 } 344 345 def _parse_transform(self) -> t.Optional[exp.Transform | exp.QueryTransform]: 346 if not self._match(TokenType.L_PAREN, advance=False): 347 self._retreat(self._index - 1) 348 return None 349 350 args = self._parse_wrapped_csv(self._parse_lambda) 351 row_format_before = self._parse_row_format(match_row=True) 352 353 record_writer = None 354 if self._match_text_seq("RECORDWRITER"): 355 record_writer = self._parse_string() 356 357 if not self._match(TokenType.USING): 358 return exp.Transform.from_arg_list(args) 359 360 command_script = self._parse_string() 361 362 self._match(TokenType.ALIAS) 363 schema = self._parse_schema() 364 365 row_format_after = self._parse_row_format(match_row=True) 366 record_reader = None 367 if self._match_text_seq("RECORDREADER"): 368 record_reader = self._parse_string() 369 370 return self.expression( 371 exp.QueryTransform, 372 expressions=args, 373 command_script=command_script, 374 schema=schema, 375 row_format_before=row_format_before, 376 record_writer=record_writer, 377 row_format_after=row_format_after, 378 record_reader=record_reader, 379 ) 380 381 def _parse_types( 382 self, check_func: bool = False, schema: bool = False, allow_identifiers: bool = True 383 ) -> t.Optional[exp.Expression]: 384 """ 385 Spark (and most likely Hive) treats casts to CHAR(length) and VARCHAR(length) as casts to 386 STRING in all contexts except for schema definitions. For example, this is in Spark v3.4.0: 387 388 spark-sql (default)> select cast(1234 as varchar(2)); 389 23/06/06 15:51:18 WARN CharVarcharUtils: The Spark cast operator does not support 390 char/varchar type and simply treats them as string type. Please use string type 391 directly to avoid confusion. Otherwise, you can set spark.sql.legacy.charVarcharAsString 392 to true, so that Spark treat them as string type as same as Spark 3.0 and earlier 393 394 1234 395 Time taken: 4.265 seconds, Fetched 1 row(s) 396 397 This shows that Spark doesn't truncate the value into '12', which is inconsistent with 398 what other dialects (e.g. postgres) do, so we need to drop the length to transpile correctly. 399 400 Reference: https://spark.apache.org/docs/latest/sql-ref-datatypes.html 401 """ 402 this = super()._parse_types( 403 check_func=check_func, schema=schema, allow_identifiers=allow_identifiers 404 ) 405 406 if this and not schema: 407 return this.transform( 408 lambda node: ( 409 node.replace(exp.DataType.build("text")) 410 if isinstance(node, exp.DataType) and node.is_type("char", "varchar") 411 else node 412 ), 413 copy=False, 414 ) 415 416 return this 417 418 def _parse_partition_and_order( 419 self, 420 ) -> t.Tuple[t.List[exp.Expression], t.Optional[exp.Expression]]: 421 return ( 422 ( 423 self._parse_csv(self._parse_assignment) 424 if self._match_set({TokenType.PARTITION_BY, TokenType.DISTRIBUTE_BY}) 425 else [] 426 ), 427 super()._parse_order(skip_order_token=self._match(TokenType.SORT_BY)), 428 ) 429 430 def _parse_parameter(self) -> exp.Parameter: 431 self._match(TokenType.L_BRACE) 432 this = self._parse_identifier() or self._parse_primary_or_var() 433 expression = self._match(TokenType.COLON) and ( 434 self._parse_identifier() or self._parse_primary_or_var() 435 ) 436 self._match(TokenType.R_BRACE) 437 return self.expression(exp.Parameter, this=this, expression=expression)
Parser consumes a list of tokens produced by the Tokenizer and produces a parsed syntax tree.
Arguments:
- error_level: The desired error level. Default: ErrorLevel.IMMEDIATE
- error_message_context: The amount of context to capture from a query string when displaying the error message (in number of characters). Default: 100
- max_errors: Maximum number of error messages to include in a raised ParseError. This is only relevant if error_level is ErrorLevel.RAISE. Default: 3
FUNCTIONS =
{'ABS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Abs'>>, 'ADD_MONTHS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.AddMonths'>>, 'ANONYMOUS_AGG_FUNC': <bound method Func.from_arg_list of <class 'sqlglot.expressions.AnonymousAggFunc'>>, 'ANY_VALUE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.AnyValue'>>, 'APPROX_DISTINCT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ApproxDistinct'>>, 'APPROX_COUNT_DISTINCT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ApproxDistinct'>>, 'APPROX_QUANTILE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ApproxQuantile'>>, 'APPROX_TOP_K': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ApproxTopK'>>, 'ARG_MAX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArgMax'>>, 'ARGMAX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArgMax'>>, 'MAX_BY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArgMax'>>, 'ARG_MIN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArgMin'>>, 'ARGMIN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArgMin'>>, 'MIN_BY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArgMin'>>, 'ARRAY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Array'>>, 'ARRAY_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayAgg'>>, 'ARRAY_ALL': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayAll'>>, 'ARRAY_ANY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayAny'>>, 'ARRAY_CONCAT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayConcat'>>, 'ARRAY_CAT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayConcat'>>, 'ARRAY_CONSTRUCT_COMPACT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayConstructCompact'>>, 'ARRAY_CONTAINS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayContains'>>, 'ARRAY_HAS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayContains'>>, 'ARRAY_CONTAINS_ALL': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayContainsAll'>>, 'ARRAY_HAS_ALL': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayContainsAll'>>, 'FILTER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayFilter'>>, 'ARRAY_FILTER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayFilter'>>, 'ARRAY_OVERLAPS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayOverlaps'>>, 'ARRAY_SIZE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArraySize'>>, 'ARRAY_LENGTH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArraySize'>>, 'ARRAY_SORT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArraySort'>>, 'ARRAY_SUM': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArraySum'>>, 'ARRAY_TO_STRING': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayToString'>>, 'ARRAY_JOIN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayToString'>>, 'ARRAY_UNION_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayUnionAgg'>>, 'ARRAY_UNIQUE_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayUniqueAgg'>>, 'AVG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Avg'>>, 'CASE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Case'>>, 'CAST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Cast'>>, 'CAST_TO_STR_TYPE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CastToStrType'>>, 'CBRT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Cbrt'>>, 'CEIL': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Ceil'>>, 'CEILING': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Ceil'>>, 'CHR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Chr'>>, 'CHAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Chr'>>, 'COALESCE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Coalesce'>>, 'IFNULL': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Coalesce'>>, 'NVL': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Coalesce'>>, 'COLLATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Collate'>>, 'COMBINED_AGG_FUNC': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CombinedAggFunc'>>, 'COMBINED_PARAMETERIZED_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CombinedParameterizedAgg'>>, 'CONCAT': <function Parser.<lambda>>, 'CONCAT_WS': <function Parser.<lambda>>, 'CONNECT_BY_ROOT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ConnectByRoot'>>, 'CONVERT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Convert'>>, 'CORR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Corr'>>, 'COUNT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Count'>>, 'COUNT_IF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CountIf'>>, 'COUNTIF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CountIf'>>, 'COVAR_POP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CovarPop'>>, 'COVAR_SAMP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CovarSamp'>>, 'CURRENT_DATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CurrentDate'>>, 'CURRENT_DATETIME': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CurrentDatetime'>>, 'CURRENT_TIME': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CurrentTime'>>, 'CURRENT_TIMESTAMP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CurrentTimestamp'>>, 'CURRENT_USER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.CurrentUser'>>, 'DATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Date'>>, 'DATE_ADD': <function Hive.Parser.<lambda>>, 'DATEDIFF': <function Hive.Parser.<lambda>>, 'DATE_DIFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateDiff'>>, 'DATE_FROM_PARTS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateFromParts'>>, 'DATEFROMPARTS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateFromParts'>>, 'DATE_STR_TO_DATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateStrToDate'>>, 'DATE_SUB': <function Hive.Parser.<lambda>>, 'DATE_TO_DATE_STR': <function Parser.<lambda>>, 'DATE_TO_DI': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateToDi'>>, 'DATE_TRUNC': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DateTrunc'>>, 'DATETIME': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Datetime'>>, 'DATETIME_ADD': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DatetimeAdd'>>, 'DATETIME_DIFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DatetimeDiff'>>, 'DATETIME_SUB': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DatetimeSub'>>, 'DATETIME_TRUNC': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DatetimeTrunc'>>, 'DAY': <function Hive.Parser.<lambda>>, 'DAY_OF_MONTH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DayOfMonth'>>, 'DAYOFMONTH': <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'>>, 'EXPLODE_OUTER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ExplodeOuter'>>, 'EXTRACT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Extract'>>, 'FIRST': <function _build_with_ignore_nulls.<locals>._parse>, 'FIRST_VALUE': <function _build_with_ignore_nulls.<locals>._parse>, 'FLATTEN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Flatten'>>, 'FLOOR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Floor'>>, 'FROM_BASE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.FromBase'>>, 'FROM_BASE64': <bound method Func.from_arg_list of <class 'sqlglot.expressions.FromBase64'>>, 'GAP_FILL': <bound method Func.from_arg_list of <class 'sqlglot.expressions.GapFill'>>, 'GENERATE_DATE_ARRAY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.GenerateDateArray'>>, 'GENERATE_SERIES': <bound method Func.from_arg_list of <class 'sqlglot.expressions.GenerateSeries'>>, 'GREATEST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Greatest'>>, 'GROUP_CONCAT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.GroupConcat'>>, 'HEX': <function build_hex>, 'HLL': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Hll'>>, 'IF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.If'>>, 'IIF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.If'>>, 'INITCAP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Initcap'>>, 'IS_INF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.IsInf'>>, 'ISINF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.IsInf'>>, 'IS_NAN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.IsNan'>>, 'ISNAN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.IsNan'>>, 'J_S_O_N_ARRAY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONArray'>>, 'J_S_O_N_ARRAY_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONArrayAgg'>>, 'JSON_ARRAY_CONTAINS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONArrayContains'>>, 'JSONB_CONTAINS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONBContains'>>, 'JSONB_EXTRACT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONBExtract'>>, 'JSONB_EXTRACT_SCALAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONBExtractScalar'>>, 'JSON_EXTRACT': <function build_extract_json_with_path.<locals>._builder>, 'JSON_EXTRACT_SCALAR': <function build_extract_json_with_path.<locals>._builder>, 'JSON_FORMAT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONFormat'>>, 'J_S_O_N_OBJECT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONObject'>>, 'J_S_O_N_OBJECT_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONObjectAgg'>>, 'J_S_O_N_TABLE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONTable'>>, 'LAG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Lag'>>, 'LAST': <function _build_with_ignore_nulls.<locals>._parse>, 'LAST_DAY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LastDay'>>, 'LAST_DAY_OF_MONTH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LastDay'>>, 'LAST_VALUE': <function _build_with_ignore_nulls.<locals>._parse>, 'LEAD': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Lead'>>, 'LEAST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Least'>>, 'LEFT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Left'>>, 'LENGTH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Length'>>, 'LEN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Length'>>, 'LEVENSHTEIN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Levenshtein'>>, 'LIST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.List'>>, 'LN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Ln'>>, 'LOG': <function build_logarithm>, 'LOGICAL_AND': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LogicalAnd'>>, 'BOOL_AND': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LogicalAnd'>>, 'BOOLAND_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LogicalAnd'>>, 'LOGICAL_OR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LogicalOr'>>, 'BOOL_OR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LogicalOr'>>, 'BOOLOR_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LogicalOr'>>, 'LOWER': <function build_lower>, 'LCASE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Lower'>>, 'LOWER_HEX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.LowerHex'>>, 'MD5': <bound method Func.from_arg_list of <class 'sqlglot.expressions.MD5'>>, 'MD5_DIGEST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.MD5Digest'>>, 'MAP': <function build_var_map>, 'MAP_FROM_ENTRIES': <bound method Func.from_arg_list of <class 'sqlglot.expressions.MapFromEntries'>>, 'MATCH_AGAINST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.MatchAgainst'>>, 'MAX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Max'>>, 'MIN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Min'>>, 'MONTH': <function Hive.Parser.<lambda>>, 'MONTHS_BETWEEN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.MonthsBetween'>>, 'NEXT_VALUE_FOR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.NextValueFor'>>, 'NTH_VALUE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.NthValue'>>, 'NULLIF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Nullif'>>, 'NUMBER_TO_STR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.NumberToStr'>>, 'NVL2': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Nvl2'>>, 'OBJECT_INSERT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ObjectInsert'>>, 'OPEN_J_S_O_N': <bound method Func.from_arg_list of <class 'sqlglot.expressions.OpenJSON'>>, 'PAD': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Pad'>>, 'PARAMETERIZED_AGG': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ParameterizedAgg'>>, 'PARSE_JSON': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ParseJSON'>>, 'JSON_PARSE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ParseJSON'>>, 'PERCENTILE_CONT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.PercentileCont'>>, 'PERCENTILE_DISC': <bound method Func.from_arg_list of <class 'sqlglot.expressions.PercentileDisc'>>, 'POSEXPLODE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Posexplode'>>, 'POSEXPLODE_OUTER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.PosexplodeOuter'>>, 'POWER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Pow'>>, 'POW': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Pow'>>, 'PREDICT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Predict'>>, 'QUANTILE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Quantile'>>, 'QUARTER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Quarter'>>, 'RAND': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Rand'>>, 'RANDOM': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Rand'>>, 'RANDN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Randn'>>, 'RANGE_N': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RangeN'>>, 'READ_CSV': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ReadCSV'>>, 'REDUCE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Reduce'>>, 'REGEXP_EXTRACT': <function Hive.Parser.<lambda>>, 'REGEXP_I_LIKE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RegexpILike'>>, 'REGEXP_LIKE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RegexpLike'>>, 'REGEXP_REPLACE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RegexpReplace'>>, 'REGEXP_SPLIT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RegexpSplit'>>, 'REPEAT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Repeat'>>, 'RIGHT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Right'>>, 'ROUND': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Round'>>, 'ROW_NUMBER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RowNumber'>>, 'SHA': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SHA'>>, 'SHA1': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SHA'>>, 'SHA2': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SHA2'>>, 'SAFE_DIVIDE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SafeDivide'>>, 'SIGN': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Sign'>>, 'SIGNUM': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Sign'>>, 'SORT_ARRAY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.SortArray'>>, 'SPLIT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.RegexpSplit'>>, 'SQRT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Sqrt'>>, 'STANDARD_HASH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StandardHash'>>, 'STAR_MAP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StarMap'>>, 'STARTS_WITH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StartsWith'>>, 'STARTSWITH': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StartsWith'>>, 'STDDEV': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Stddev'>>, 'STDEV': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Stddev'>>, 'STDDEV_POP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StddevPop'>>, 'STDDEV_SAMP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StddevSamp'>>, 'STR_POSITION': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StrPosition'>>, 'STR_TO_DATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StrToDate'>>, 'STR_TO_MAP': <function Hive.Parser.<lambda>>, 'STR_TO_TIME': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StrToTime'>>, 'STR_TO_UNIX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StrToUnix'>>, 'STRING_TO_ARRAY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StringToArray'>>, 'SPLIT_BY_STRING': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StringToArray'>>, 'STRUCT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Struct'>>, 'STRUCT_EXTRACT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.StructExtract'>>, 'STUFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Stuff'>>, 'INSERT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Stuff'>>, 'SUBSTRING': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Substring'>>, 'SUM': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Sum'>>, 'TIME': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Time'>>, 'TIME_ADD': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeAdd'>>, 'TIME_DIFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeDiff'>>, 'TIME_FROM_PARTS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeFromParts'>>, 'TIMEFROMPARTS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeFromParts'>>, 'TIME_STR_TO_DATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeStrToDate'>>, 'TIME_STR_TO_TIME': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeStrToTime'>>, 'TIME_STR_TO_UNIX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeStrToUnix'>>, 'TIME_SUB': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeSub'>>, 'TIME_TO_STR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeToStr'>>, 'TIME_TO_TIME_STR': <function Parser.<lambda>>, 'TIME_TO_UNIX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeToUnix'>>, 'TIME_TRUNC': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimeTrunc'>>, 'TIMESTAMP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Timestamp'>>, 'TIMESTAMP_ADD': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimestampAdd'>>, 'TIMESTAMPDIFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimestampDiff'>>, 'TIMESTAMP_DIFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimestampDiff'>>, 'TIMESTAMP_FROM_PARTS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimestampFromParts'>>, 'TIMESTAMPFROMPARTS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimestampFromParts'>>, 'TIMESTAMP_SUB': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimestampSub'>>, 'TIMESTAMP_TRUNC': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimestampTrunc'>>, 'TO_ARRAY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ToArray'>>, 'TO_BASE64': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ToBase64'>>, 'TO_CHAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ToChar'>>, 'TO_DAYS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ToDays'>>, 'TO_MAP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ToMap'>>, 'TO_NUMBER': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ToNumber'>>, 'TRANSFORM': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Transform'>>, 'TRIM': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Trim'>>, 'TRY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Try'>>, 'TRY_CAST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TryCast'>>, 'TS_OR_DI_TO_DI': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TsOrDiToDi'>>, 'TS_OR_DS_ADD': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TsOrDsAdd'>>, 'TS_OR_DS_DIFF': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TsOrDsDiff'>>, 'TS_OR_DS_TO_DATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TsOrDsToDate'>>, 'TS_OR_DS_TO_DATE_STR': <function Parser.<lambda>>, 'TS_OR_DS_TO_TIME': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TsOrDsToTime'>>, 'TS_OR_DS_TO_TIMESTAMP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TsOrDsToTimestamp'>>, 'UNHEX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Unhex'>>, 'UNIX_DATE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.UnixDate'>>, 'UNIX_TO_STR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.UnixToStr'>>, 'UNIX_TO_TIME': <bound method Func.from_arg_list of <class 'sqlglot.expressions.UnixToTime'>>, 'UNIX_TO_TIME_STR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.UnixToTimeStr'>>, 'UNNEST': <function Parser.<lambda>>, 'UPPER': <function build_upper>, 'UCASE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Upper'>>, 'VAR_MAP': <function build_var_map>, 'VARIANCE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Variance'>>, 'VARIANCE_SAMP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Variance'>>, 'VAR_SAMP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Variance'>>, 'VARIANCE_POP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.VariancePop'>>, 'VAR_POP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.VariancePop'>>, 'WEEK': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Week'>>, 'WEEK_OF_YEAR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.WeekOfYear'>>, 'WEEKOFYEAR': <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': <function Hive.Parser.<lambda>>, 'GLOB': <function Parser.<lambda>>, 'JSON_EXTRACT_PATH_TEXT': <function build_extract_json_with_path.<locals>._builder>, 'LIKE': <function build_like>, 'LOG2': <function Parser.<lambda>>, 'LOG10': <function Parser.<lambda>>, 'LPAD': <function Parser.<lambda>>, 'LEFTPAD': <function Parser.<lambda>>, 'MOD': <function build_mod>, 'RPAD': <function Parser.<lambda>>, 'RIGHTPAD': <function Parser.<lambda>>, 'SCOPE_RESOLUTION': <function Parser.<lambda>>, 'TO_HEX': <function build_hex>, 'BASE64': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ToBase64'>>, 'COLLECT_LIST': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayAgg'>>, 'COLLECT_SET': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArrayUniqueAgg'>>, 'DATE_FORMAT': <function Hive.Parser.<lambda>>, 'FROM_UNIXTIME': <function build_formatted_time.<locals>._builder>, 'GET_JSON_OBJECT': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONExtractScalar'>>, 'LOCATE': <function locate_to_strposition>, 'PERCENTILE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Quantile'>>, 'PERCENTILE_APPROX': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ApproxQuantile'>>, 'SEQUENCE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.GenerateSeries'>>, 'SIZE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ArraySize'>>, 'TO_DATE': <function build_formatted_time.<locals>._builder>, 'TO_JSON': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONFormat'>>, 'TRUNC': <bound method Func.from_arg_list of <class 'sqlglot.expressions.TimestampTrunc'>>, 'UNBASE64': <bound method Func.from_arg_list of <class 'sqlglot.expressions.FromBase64'>>, 'UNIX_TIMESTAMP': <function Hive.Parser.<lambda>>}
NO_PAREN_FUNCTION_PARSERS =
{'ANY': <function Parser.<lambda>>, 'CASE': <function Parser.<lambda>>, 'CONNECT_BY_ROOT': <function Parser.<lambda>>, 'IF': <function Parser.<lambda>>, 'NEXT': <function Parser.<lambda>>, 'TRANSFORM': <function Hive.Parser.<lambda>>}
PROPERTY_PARSERS =
{'ALLOWED_VALUES': <function Parser.<lambda>>, 'ALGORITHM': <function Parser.<lambda>>, 'AUTO': <function Parser.<lambda>>, 'AUTO_INCREMENT': <function Parser.<lambda>>, 'BACKUP': <function Parser.<lambda>>, 'BLOCKCOMPRESSION': <function Parser.<lambda>>, 'CHARSET': <function Parser.<lambda>>, 'CHARACTER SET': <function Parser.<lambda>>, 'CHECKSUM': <function Parser.<lambda>>, 'CLUSTER BY': <function Parser.<lambda>>, 'CLUSTERED': <function Parser.<lambda>>, 'COLLATE': <function Parser.<lambda>>, 'COMMENT': <function Parser.<lambda>>, 'CONTAINS': <function Parser.<lambda>>, 'COPY': <function Parser.<lambda>>, 'DATABLOCKSIZE': <function Parser.<lambda>>, 'DATA_DELETION': <function Parser.<lambda>>, 'DEFINER': <function Parser.<lambda>>, 'DETERMINISTIC': <function Parser.<lambda>>, 'DYNAMIC': <function Parser.<lambda>>, 'DISTKEY': <function Parser.<lambda>>, 'DISTSTYLE': <function Parser.<lambda>>, 'ENGINE': <function Parser.<lambda>>, 'EXECUTE': <function Parser.<lambda>>, 'EXTERNAL': <function Parser.<lambda>>, 'FALLBACK': <function Parser.<lambda>>, 'FORMAT': <function Parser.<lambda>>, 'FREESPACE': <function Parser.<lambda>>, 'GLOBAL': <function Parser.<lambda>>, 'HEAP': <function Parser.<lambda>>, 'ICEBERG': <function Parser.<lambda>>, 'IMMUTABLE': <function Parser.<lambda>>, 'INHERITS': <function Parser.<lambda>>, 'INPUT': <function Parser.<lambda>>, 'JOURNAL': <function Parser.<lambda>>, 'LANGUAGE': <function Parser.<lambda>>, 'LAYOUT': <function Parser.<lambda>>, 'LIFETIME': <function Parser.<lambda>>, 'LIKE': <function Parser.<lambda>>, 'LOCATION': <function Parser.<lambda>>, 'LOCK': <function Parser.<lambda>>, 'LOCKING': <function Parser.<lambda>>, 'LOG': <function Parser.<lambda>>, 'MATERIALIZED': <function Parser.<lambda>>, 'MERGEBLOCKRATIO': <function Parser.<lambda>>, 'MODIFIES': <function Parser.<lambda>>, 'MULTISET': <function Parser.<lambda>>, 'NO': <function Parser.<lambda>>, 'ON': <function Parser.<lambda>>, 'ORDER BY': <function Parser.<lambda>>, 'OUTPUT': <function Parser.<lambda>>, 'PARTITION': <function Parser.<lambda>>, 'PARTITION BY': <function Parser.<lambda>>, 'PARTITIONED BY': <function Parser.<lambda>>, 'PARTITIONED_BY': <function Parser.<lambda>>, 'PRIMARY KEY': <function Parser.<lambda>>, 'RANGE': <function Parser.<lambda>>, 'READS': <function Parser.<lambda>>, 'REMOTE': <function Parser.<lambda>>, 'RETURNS': <function Parser.<lambda>>, 'STRICT': <function Parser.<lambda>>, 'ROW': <function Parser.<lambda>>, 'ROW_FORMAT': <function Parser.<lambda>>, 'SAMPLE': <function Parser.<lambda>>, 'SECURE': <function Parser.<lambda>>, 'SET': <function Parser.<lambda>>, 'SETTINGS': <function Parser.<lambda>>, 'SHARING': <function Parser.<lambda>>, 'SORTKEY': <function Parser.<lambda>>, 'SOURCE': <function Parser.<lambda>>, 'STABLE': <function Parser.<lambda>>, 'STORED': <function Parser.<lambda>>, 'SYSTEM_VERSIONING': <function Parser.<lambda>>, 'TBLPROPERTIES': <function Parser.<lambda>>, 'TEMP': <function Parser.<lambda>>, 'TEMPORARY': <function Parser.<lambda>>, 'TO': <function Parser.<lambda>>, 'TRANSIENT': <function Parser.<lambda>>, 'TRANSFORM': <function Parser.<lambda>>, 'TTL': <function Parser.<lambda>>, 'USING': <function Parser.<lambda>>, 'UNLOGGED': <function Parser.<lambda>>, 'VOLATILE': <function Parser.<lambda>>, 'WITH': <function Parser.<lambda>>, 'SERDEPROPERTIES': <function Hive.Parser.<lambda>>}
ID_VAR_TOKENS =
{<TokenType.TIMESTAMPNTZ: 'TIMESTAMPNTZ'>, <TokenType.FINAL: 'FINAL'>, <TokenType.MEDIUMINT: 'MEDIUMINT'>, <TokenType.DATERANGE: 'DATERANGE'>, <TokenType.TAG: 'TAG'>, <TokenType.GEOGRAPHY: 'GEOGRAPHY'>, <TokenType.TIME: 'TIME'>, <TokenType.COPY: 'COPY'>, <TokenType.DELETE: 'DELETE'>, <TokenType.ASOF: 'ASOF'>, <TokenType.INT256: 'INT256'>, <TokenType.TRUE: 'TRUE'>, <TokenType.FLOAT: 'FLOAT'>, <TokenType.ANTI: 'ANTI'>, <TokenType.TINYINT: 'TINYINT'>, <TokenType.TIMESTAMP_S: 'TIMESTAMP_S'>, <TokenType.FILTER: 'FILTER'>, <TokenType.CACHE: 'CACHE'>, <TokenType.VECTOR: 'VECTOR'>, <TokenType.OBJECT_IDENTIFIER: 'OBJECT_IDENTIFIER'>, <TokenType.ROWS: 'ROWS'>, <TokenType.NESTED: 'NESTED'>, <TokenType.CURRENT_DATETIME: 'CURRENT_DATETIME'>, <TokenType.KEEP: 'KEEP'>, <TokenType.CASE: 'CASE'>, <TokenType.KILL: 'KILL'>, <TokenType.TEMPORARY: 'TEMPORARY'>, <TokenType.UINT128: 'UINT128'>, <TokenType.COMMIT: 'COMMIT'>, <TokenType.ROWVERSION: 'ROWVERSION'>, <TokenType.IDENTIFIER: 'IDENTIFIER'>, <TokenType.STREAMLIT: 'STREAMLIT'>, <TokenType.IPV6: 'IPV6'>, <TokenType.GEOMETRY: 'GEOMETRY'>, <TokenType.COLUMN: 'COLUMN'>, <TokenType.TINYTEXT: 'TINYTEXT'>, <TokenType.WINDOW: 'WINDOW'>, <TokenType.BINARY: 'BINARY'>, <TokenType.BOOLEAN: 'BOOLEAN'>, <TokenType.ROW: 'ROW'>, <TokenType.TEXT: 'TEXT'>, <TokenType.IPPREFIX: 'IPPREFIX'>, <TokenType.DICTIONARY: 'DICTIONARY'>, <TokenType.ISNULL: 'ISNULL'>, <TokenType.PERCENT: 'PERCENT'>, <TokenType.SCHEMA: 'SCHEMA'>, <TokenType.ENUM16: 'ENUM16'>, <TokenType.UTINYINT: 'UTINYINT'>, <TokenType.CURRENT_TIME: 'CURRENT_TIME'>, <TokenType.USE: 'USE'>, <TokenType.INDEX: 'INDEX'>, <TokenType.IPV4: 'IPV4'>, <TokenType.INT128: 'INT128'>, <TokenType.EXECUTE: 'EXECUTE'>, <TokenType.TABLE: 'TABLE'>, <TokenType.UNPIVOT: 'UNPIVOT'>, <TokenType.DECIMAL: 'DECIMAL'>, <TokenType.LONGTEXT: 'LONGTEXT'>, <TokenType.TIMESTAMP_MS: 'TIMESTAMP_MS'>, <TokenType.TINYBLOB: 'TINYBLOB'>, <TokenType.CONSTRAINT: 'CONSTRAINT'>, <TokenType.NUMRANGE: 'NUMRANGE'>, <TokenType.SETTINGS: 'SETTINGS'>, <TokenType.NULLABLE: 'NULLABLE'>, <TokenType.STRAIGHT_JOIN: 'STRAIGHT_JOIN'>, <TokenType.IMAGE: 'IMAGE'>, <TokenType.TSTZMULTIRANGE: 'TSTZMULTIRANGE'>, <TokenType.LIST: 'LIST'>, <TokenType.INT4MULTIRANGE: 'INT4MULTIRANGE'>, <TokenType.SEQUENCE: 'SEQUENCE'>, <TokenType.ALL: 'ALL'>, <TokenType.MAP: 'MAP'>, <TokenType.OPERATOR: 'OPERATOR'>, <TokenType.LOWCARDINALITY: 'LOWCARDINALITY'>, <TokenType.UNKNOWN: 'UNKNOWN'>, <TokenType.NULL: 'NULL'>, <TokenType.LEFT: 'LEFT'>, <TokenType.SEMI: 'SEMI'>, <TokenType.ROLLUP: 'ROLLUP'>, <TokenType.INT4RANGE: 'INT4RANGE'>, <TokenType.TDIGEST: 'TDIGEST'>, <TokenType.CURRENT_TIMESTAMP: 'CURRENT_TIMESTAMP'>, <TokenType.MONEY: 'MONEY'>, <TokenType.TIMESTAMP_NS: 'TIMESTAMP_NS'>, <TokenType.STRUCT: 'STRUCT'>, <TokenType.NATURAL: 'NATURAL'>, <TokenType.SMALLINT: 'SMALLINT'>, <TokenType.VIEW: 'VIEW'>, <TokenType.SMALLMONEY: 'SMALLMONEY'>, <TokenType.SIMPLEAGGREGATEFUNCTION: 'SIMPLEAGGREGATEFUNCTION'>, <TokenType.VARCHAR: 'VARCHAR'>, <TokenType.COLLATE: 'COLLATE'>, <TokenType.NEXT: 'NEXT'>, <TokenType.PARTITION: 'PARTITION'>, <TokenType.OVERLAPS: 'OVERLAPS'>, <TokenType.NCHAR: 'NCHAR'>, <TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>, <TokenType.OFFSET: 'OFFSET'>, <TokenType.ORDINALITY: 'ORDINALITY'>, <TokenType.BPCHAR: 'BPCHAR'>, <TokenType.SUPER: 'SUPER'>, <TokenType.END: 'END'>, <TokenType.USMALLINT: 'USMALLINT'>, <TokenType.TSTZRANGE: 'TSTZRANGE'>, <TokenType.COMMENT: 'COMMENT'>, <TokenType.UPDATE: 'UPDATE'>, <TokenType.EXISTS: 'EXISTS'>, <TokenType.CHAR: 'CHAR'>, <TokenType.WAREHOUSE: 'WAREHOUSE'>, <TokenType.ESCAPE: 'ESCAPE'>, <TokenType.LONGBLOB: 'LONGBLOB'>, <TokenType.CURRENT_USER: 'CURRENT_USER'>, <TokenType.UINT: 'UINT'>, <TokenType.VARIANT: 'VARIANT'>, <TokenType.ENUM8: 'ENUM8'>, <TokenType.BIGINT: 'BIGINT'>, <TokenType.TOP: 'TOP'>, <TokenType.TIMESTAMP: 'TIMESTAMP'>, <TokenType.SOME: 'SOME'>, <TokenType.UMEDIUMINT: 'UMEDIUMINT'>, <TokenType.DATEMULTIRANGE: 'DATEMULTIRANGE'>, <TokenType.USERDEFINED: 'USERDEFINED'>, <TokenType.DESC: 'DESC'>, <TokenType.NUMMULTIRANGE: 'NUMMULTIRANGE'>, <TokenType.RANGE: 'RANGE'>, <TokenType.FIRST: 'FIRST'>, <TokenType.UUID: 'UUID'>, <TokenType.DESCRIBE: 'DESCRIBE'>, <TokenType.MODEL: 'MODEL'>, <TokenType.AGGREGATEFUNCTION: 'AGGREGATEFUNCTION'>, <TokenType.MERGE: 'MERGE'>, <TokenType.INT8MULTIRANGE: 'INT8MULTIRANGE'>, <TokenType.RECURSIVE: 'RECURSIVE'>, <TokenType.VAR: 'VAR'>, <TokenType.NVARCHAR: 'NVARCHAR'>, <TokenType.NAME: 'NAME'>, <TokenType.JSON: 'JSON'>, <TokenType.FULL: 'FULL'>, <TokenType.BEGIN: 'BEGIN'>, <TokenType.IS: 'IS'>, <TokenType.TSMULTIRANGE: 'TSMULTIRANGE'>, <TokenType.YEAR: 'YEAR'>, <TokenType.XML: 'XML'>, <TokenType.OBJECT: 'OBJECT'>, <TokenType.DATE32: 'DATE32'>, <TokenType.DATETIME64: 'DATETIME64'>, <TokenType.DATETIME: 'DATETIME'>, <TokenType.JSONB: 'JSONB'>, <TokenType.PIVOT: 'PIVOT'>, <TokenType.BIT: 'BIT'>, <TokenType.FORMAT: 'FORMAT'>, <TokenType.PRAGMA: 'PRAGMA'>, <TokenType.FOREIGN_KEY: 'FOREIGN_KEY'>, <TokenType.UNIQUEIDENTIFIER: 'UNIQUEIDENTIFIER'>, <TokenType.APPLY: 'APPLY'>, <TokenType.TSRANGE: 'TSRANGE'>, <TokenType.LOAD: 'LOAD'>, <TokenType.RIGHT: 'RIGHT'>, <TokenType.BIGSERIAL: 'BIGSERIAL'>, <TokenType.VARBINARY: 'VARBINARY'>, <TokenType.UINT256: 'UINT256'>, <TokenType.DIV: 'DIV'>, <TokenType.ARRAY: 'ARRAY'>, <TokenType.SHOW: 'SHOW'>, <TokenType.ASC: 'ASC'>, <TokenType.INT: 'INT'>, <TokenType.IPADDRESS: 'IPADDRESS'>, <TokenType.INET: 'INET'>, <TokenType.INT8RANGE: 'INT8RANGE'>, <TokenType.SMALLSERIAL: 'SMALLSERIAL'>, <TokenType.DEFAULT: 'DEFAULT'>, <TokenType.ANY: 'ANY'>, <TokenType.HLLSKETCH: 'HLLSKETCH'>, <TokenType.VOLATILE: 'VOLATILE'>, <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>, <TokenType.FIXEDSTRING: 'FIXEDSTRING'>, <TokenType.TRUNCATE: 'TRUNCATE'>, <TokenType.DOUBLE: 'DOUBLE'>, <TokenType.UBIGINT: 'UBIGINT'>, <TokenType.FUNCTION: 'FUNCTION'>, <TokenType.UDECIMAL: 'UDECIMAL'>, <TokenType.REPLACE: 'REPLACE'>, <TokenType.OVERWRITE: 'OVERWRITE'>, <TokenType.REFERENCES: 'REFERENCES'>, <TokenType.HSTORE: 'HSTORE'>, <TokenType.DATABASE: 'DATABASE'>, <TokenType.FALSE: 'FALSE'>, <TokenType.UNNEST: 'UNNEST'>, <TokenType.ENUM: 'ENUM'>, <TokenType.REFRESH: 'REFRESH'>, <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>, <TokenType.COMMAND: 'COMMAND'>, <TokenType.INTERVAL: 'INTERVAL'>, <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, <TokenType.CURRENT_DATE: 'CURRENT_DATE'>, <TokenType.UNIQUE: 'UNIQUE'>, <TokenType.PSEUDO_TYPE: 'PSEUDO_TYPE'>, <TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>, <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, <TokenType.TIMETZ: 'TIMETZ'>, <TokenType.SET: 'SET'>, <TokenType.SERIAL: 'SERIAL'>, <TokenType.DATE: 'DATE'>, <TokenType.STORAGE_INTEGRATION: 'STORAGE_INTEGRATION'>, <TokenType.PROCEDURE: 'PROCEDURE'>}
TABLE_ALIAS_TOKENS =
{<TokenType.TIMESTAMPNTZ: 'TIMESTAMPNTZ'>, <TokenType.FINAL: 'FINAL'>, <TokenType.MEDIUMINT: 'MEDIUMINT'>, <TokenType.DATERANGE: 'DATERANGE'>, <TokenType.TAG: 'TAG'>, <TokenType.GEOGRAPHY: 'GEOGRAPHY'>, <TokenType.TIME: 'TIME'>, <TokenType.COPY: 'COPY'>, <TokenType.DELETE: 'DELETE'>, <TokenType.INT256: 'INT256'>, <TokenType.TRUE: 'TRUE'>, <TokenType.FLOAT: 'FLOAT'>, <TokenType.TINYINT: 'TINYINT'>, <TokenType.TIMESTAMP_S: 'TIMESTAMP_S'>, <TokenType.FILTER: 'FILTER'>, <TokenType.CACHE: 'CACHE'>, <TokenType.VECTOR: 'VECTOR'>, <TokenType.OBJECT_IDENTIFIER: 'OBJECT_IDENTIFIER'>, <TokenType.ROWS: 'ROWS'>, <TokenType.NESTED: 'NESTED'>, <TokenType.CURRENT_DATETIME: 'CURRENT_DATETIME'>, <TokenType.KEEP: 'KEEP'>, <TokenType.CASE: 'CASE'>, <TokenType.KILL: 'KILL'>, <TokenType.TEMPORARY: 'TEMPORARY'>, <TokenType.UINT128: 'UINT128'>, <TokenType.COMMIT: 'COMMIT'>, <TokenType.ROWVERSION: 'ROWVERSION'>, <TokenType.IDENTIFIER: 'IDENTIFIER'>, <TokenType.STREAMLIT: 'STREAMLIT'>, <TokenType.IPV6: 'IPV6'>, <TokenType.GEOMETRY: 'GEOMETRY'>, <TokenType.COLUMN: 'COLUMN'>, <TokenType.TINYTEXT: 'TINYTEXT'>, <TokenType.BINARY: 'BINARY'>, <TokenType.BOOLEAN: 'BOOLEAN'>, <TokenType.ROW: 'ROW'>, <TokenType.TEXT: 'TEXT'>, <TokenType.IPPREFIX: 'IPPREFIX'>, <TokenType.DICTIONARY: 'DICTIONARY'>, <TokenType.ISNULL: 'ISNULL'>, <TokenType.PERCENT: 'PERCENT'>, <TokenType.SCHEMA: 'SCHEMA'>, <TokenType.ENUM16: 'ENUM16'>, <TokenType.UTINYINT: 'UTINYINT'>, <TokenType.CURRENT_TIME: 'CURRENT_TIME'>, <TokenType.USE: 'USE'>, <TokenType.INDEX: 'INDEX'>, <TokenType.IPV4: 'IPV4'>, <TokenType.INT128: 'INT128'>, <TokenType.EXECUTE: 'EXECUTE'>, <TokenType.TABLE: 'TABLE'>, <TokenType.UNPIVOT: 'UNPIVOT'>, <TokenType.DECIMAL: 'DECIMAL'>, <TokenType.LONGTEXT: 'LONGTEXT'>, <TokenType.TIMESTAMP_MS: 'TIMESTAMP_MS'>, <TokenType.TINYBLOB: 'TINYBLOB'>, <TokenType.CONSTRAINT: 'CONSTRAINT'>, <TokenType.NUMRANGE: 'NUMRANGE'>, <TokenType.SETTINGS: 'SETTINGS'>, <TokenType.NULLABLE: 'NULLABLE'>, <TokenType.STRAIGHT_JOIN: 'STRAIGHT_JOIN'>, <TokenType.IMAGE: 'IMAGE'>, <TokenType.TSTZMULTIRANGE: 'TSTZMULTIRANGE'>, <TokenType.LIST: 'LIST'>, <TokenType.INT4MULTIRANGE: 'INT4MULTIRANGE'>, <TokenType.SEQUENCE: 'SEQUENCE'>, <TokenType.ALL: 'ALL'>, <TokenType.MAP: 'MAP'>, <TokenType.OPERATOR: 'OPERATOR'>, <TokenType.LOWCARDINALITY: 'LOWCARDINALITY'>, <TokenType.UNKNOWN: 'UNKNOWN'>, <TokenType.NULL: 'NULL'>, <TokenType.ROLLUP: 'ROLLUP'>, <TokenType.INT4RANGE: 'INT4RANGE'>, <TokenType.TDIGEST: 'TDIGEST'>, <TokenType.CURRENT_TIMESTAMP: 'CURRENT_TIMESTAMP'>, <TokenType.MONEY: 'MONEY'>, <TokenType.TIMESTAMP_NS: 'TIMESTAMP_NS'>, <TokenType.STRUCT: 'STRUCT'>, <TokenType.SMALLINT: 'SMALLINT'>, <TokenType.VIEW: 'VIEW'>, <TokenType.SMALLMONEY: 'SMALLMONEY'>, <TokenType.SIMPLEAGGREGATEFUNCTION: 'SIMPLEAGGREGATEFUNCTION'>, <TokenType.VARCHAR: 'VARCHAR'>, <TokenType.COLLATE: 'COLLATE'>, <TokenType.NEXT: 'NEXT'>, <TokenType.PARTITION: 'PARTITION'>, <TokenType.OVERLAPS: 'OVERLAPS'>, <TokenType.NCHAR: 'NCHAR'>, <TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>, <TokenType.ORDINALITY: 'ORDINALITY'>, <TokenType.BPCHAR: 'BPCHAR'>, <TokenType.SUPER: 'SUPER'>, <TokenType.END: 'END'>, <TokenType.USMALLINT: 'USMALLINT'>, <TokenType.TSTZRANGE: 'TSTZRANGE'>, <TokenType.COMMENT: 'COMMENT'>, <TokenType.UPDATE: 'UPDATE'>, <TokenType.EXISTS: 'EXISTS'>, <TokenType.CHAR: 'CHAR'>, <TokenType.WAREHOUSE: 'WAREHOUSE'>, <TokenType.ESCAPE: 'ESCAPE'>, <TokenType.LONGBLOB: 'LONGBLOB'>, <TokenType.CURRENT_USER: 'CURRENT_USER'>, <TokenType.UINT: 'UINT'>, <TokenType.VARIANT: 'VARIANT'>, <TokenType.ENUM8: 'ENUM8'>, <TokenType.BIGINT: 'BIGINT'>, <TokenType.TOP: 'TOP'>, <TokenType.TIMESTAMP: 'TIMESTAMP'>, <TokenType.SOME: 'SOME'>, <TokenType.UMEDIUMINT: 'UMEDIUMINT'>, <TokenType.DATEMULTIRANGE: 'DATEMULTIRANGE'>, <TokenType.USERDEFINED: 'USERDEFINED'>, <TokenType.DESC: 'DESC'>, <TokenType.NUMMULTIRANGE: 'NUMMULTIRANGE'>, <TokenType.RANGE: 'RANGE'>, <TokenType.FIRST: 'FIRST'>, <TokenType.UUID: 'UUID'>, <TokenType.DESCRIBE: 'DESCRIBE'>, <TokenType.MODEL: 'MODEL'>, <TokenType.AGGREGATEFUNCTION: 'AGGREGATEFUNCTION'>, <TokenType.MERGE: 'MERGE'>, <TokenType.INT8MULTIRANGE: 'INT8MULTIRANGE'>, <TokenType.RECURSIVE: 'RECURSIVE'>, <TokenType.VAR: 'VAR'>, <TokenType.NVARCHAR: 'NVARCHAR'>, <TokenType.NAME: 'NAME'>, <TokenType.JSON: 'JSON'>, <TokenType.BEGIN: 'BEGIN'>, <TokenType.IS: 'IS'>, <TokenType.TSMULTIRANGE: 'TSMULTIRANGE'>, <TokenType.YEAR: 'YEAR'>, <TokenType.XML: 'XML'>, <TokenType.OBJECT: 'OBJECT'>, <TokenType.DATE32: 'DATE32'>, <TokenType.DATETIME64: 'DATETIME64'>, <TokenType.DATETIME: 'DATETIME'>, <TokenType.JSONB: 'JSONB'>, <TokenType.PIVOT: 'PIVOT'>, <TokenType.BIT: 'BIT'>, <TokenType.FORMAT: 'FORMAT'>, <TokenType.PRAGMA: 'PRAGMA'>, <TokenType.FOREIGN_KEY: 'FOREIGN_KEY'>, <TokenType.UNIQUEIDENTIFIER: 'UNIQUEIDENTIFIER'>, <TokenType.TSRANGE: 'TSRANGE'>, <TokenType.LOAD: 'LOAD'>, <TokenType.BIGSERIAL: 'BIGSERIAL'>, <TokenType.VARBINARY: 'VARBINARY'>, <TokenType.UINT256: 'UINT256'>, <TokenType.DIV: 'DIV'>, <TokenType.ARRAY: 'ARRAY'>, <TokenType.SHOW: 'SHOW'>, <TokenType.ASC: 'ASC'>, <TokenType.INT: 'INT'>, <TokenType.IPADDRESS: 'IPADDRESS'>, <TokenType.INET: 'INET'>, <TokenType.INT8RANGE: 'INT8RANGE'>, <TokenType.SMALLSERIAL: 'SMALLSERIAL'>, <TokenType.PROCEDURE: 'PROCEDURE'>, <TokenType.DEFAULT: 'DEFAULT'>, <TokenType.ANY: 'ANY'>, <TokenType.HLLSKETCH: 'HLLSKETCH'>, <TokenType.VOLATILE: 'VOLATILE'>, <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>, <TokenType.FIXEDSTRING: 'FIXEDSTRING'>, <TokenType.TRUNCATE: 'TRUNCATE'>, <TokenType.DOUBLE: 'DOUBLE'>, <TokenType.UBIGINT: 'UBIGINT'>, <TokenType.FUNCTION: 'FUNCTION'>, <TokenType.UDECIMAL: 'UDECIMAL'>, <TokenType.REPLACE: 'REPLACE'>, <TokenType.OVERWRITE: 'OVERWRITE'>, <TokenType.REFERENCES: 'REFERENCES'>, <TokenType.HSTORE: 'HSTORE'>, <TokenType.DATABASE: 'DATABASE'>, <TokenType.FALSE: 'FALSE'>, <TokenType.UNNEST: 'UNNEST'>, <TokenType.ENUM: 'ENUM'>, <TokenType.REFRESH: 'REFRESH'>, <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>, <TokenType.COMMAND: 'COMMAND'>, <TokenType.INTERVAL: 'INTERVAL'>, <TokenType.CURRENT_DATE: 'CURRENT_DATE'>, <TokenType.UNIQUE: 'UNIQUE'>, <TokenType.PSEUDO_TYPE: 'PSEUDO_TYPE'>, <TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>, <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, <TokenType.TIMETZ: 'TIMETZ'>, <TokenType.SET: 'SET'>, <TokenType.SERIAL: 'SERIAL'>, <TokenType.DATE: 'DATE'>, <TokenType.STORAGE_INTEGRATION: 'STORAGE_INTEGRATION'>, <TokenType.BIGDECIMAL: 'BIGDECIMAL'>}
SET_TRIE: Dict =
{'GLOBAL': {0: True}, 'LOCAL': {0: True}, 'SESSION': {0: True}, 'TRANSACTION': {0: True}}
Inherited Members
- sqlglot.parser.Parser
- Parser
- NO_PAREN_FUNCTIONS
- STRUCT_TYPE_TOKENS
- NESTED_TYPE_TOKENS
- ENUM_TYPE_TOKENS
- AGGREGATE_TYPE_TOKENS
- TYPE_TOKENS
- SIGNED_TO_UNSIGNED_TYPE_TOKEN
- SUBQUERY_PREDICATES
- RESERVED_TOKENS
- DB_CREATABLES
- CREATABLES
- INTERVAL_VARS
- ALIAS_TOKENS
- ARRAY_CONSTRUCTORS
- COMMENT_TABLE_ALIAS_TOKENS
- UPDATE_ALIAS_TOKENS
- TRIM_TYPES
- FUNC_TOKENS
- CONJUNCTION
- ASSIGNMENT
- DISJUNCTION
- EQUALITY
- COMPARISON
- BITWISE
- TERM
- FACTOR
- EXPONENT
- TIMES
- TIMESTAMPS
- SET_OPERATIONS
- JOIN_METHODS
- JOIN_SIDES
- JOIN_KINDS
- JOIN_HINTS
- LAMBDAS
- COLUMN_OPERATORS
- EXPRESSION_PARSERS
- STATEMENT_PARSERS
- UNARY_PARSERS
- STRING_PARSERS
- NUMERIC_PARSERS
- PRIMARY_PARSERS
- PLACEHOLDER_PARSERS
- RANGE_PARSERS
- CONSTRAINT_PARSERS
- ALTER_PARSERS
- ALTER_ALTER_PARSERS
- SCHEMA_UNNAMED_CONSTRAINTS
- INVALID_FUNC_NAME_TOKENS
- FUNCTIONS_WITH_ALIASED_ARGS
- KEY_VALUE_DEFINITIONS
- FUNCTION_PARSERS
- QUERY_MODIFIER_PARSERS
- SET_PARSERS
- SHOW_PARSERS
- TYPE_LITERAL_PARSERS
- TYPE_CONVERTERS
- DDL_SELECT_TOKENS
- PRE_VOLATILE_TOKENS
- TRANSACTION_KIND
- TRANSACTION_CHARACTERISTICS
- CONFLICT_ACTIONS
- CREATE_SEQUENCE
- ISOLATED_LOADING_OPTIONS
- USABLES
- CAST_ACTIONS
- SCHEMA_BINDING_OPTIONS
- KEY_CONSTRAINT_OPTIONS
- INSERT_ALTERNATIVES
- CLONE_KEYWORDS
- HISTORICAL_DATA_PREFIX
- HISTORICAL_DATA_KIND
- OPCLASS_FOLLOW_KEYWORDS
- OPTYPE_FOLLOW_TOKENS
- TABLE_INDEX_HINT_TOKENS
- VIEW_ATTRIBUTES
- WINDOW_ALIAS_TOKENS
- WINDOW_BEFORE_PAREN_TOKENS
- WINDOW_SIDES
- JSON_KEY_VALUE_SEPARATOR_TOKENS
- FETCH_TOKENS
- ADD_CONSTRAINT_TOKENS
- DISTINCT_TOKENS
- NULL_TOKENS
- UNNEST_OFFSET_ALIAS_TOKENS
- SELECT_START_TOKENS
- COPY_INTO_VARLEN_OPTIONS
- PREFIXED_PIVOT_COLUMNS
- IDENTIFY_PIVOT_STRINGS
- ALTER_TABLE_ADD_REQUIRED_FOR_EACH_COLUMN
- TABLESAMPLE_CSV
- DEFAULT_SAMPLING_METHOD
- SET_REQUIRES_ASSIGNMENT_DELIMITER
- TRIM_PATTERN_FIRST
- STRING_ALIASES
- MODIFIERS_ATTACHED_TO_SET_OP
- SET_OP_MODIFIERS
- NO_PAREN_IF_COMMANDS
- JSON_ARROWS_REQUIRE_JSON_TYPE
- COLON_IS_VARIANT_EXTRACT
- SUPPORTS_IMPLICIT_UNNEST
- INTERVAL_SPANS
- SUPPORTS_PARTITION_SELECTION
- error_level
- error_message_context
- max_errors
- dialect
- reset
- parse
- parse_into
- check_errors
- raise_error
- expression
- validate_expression
- errors
- sql
439 class Generator(generator.Generator): 440 LIMIT_FETCH = "LIMIT" 441 TABLESAMPLE_WITH_METHOD = False 442 JOIN_HINTS = False 443 TABLE_HINTS = False 444 QUERY_HINTS = False 445 INDEX_ON = "ON TABLE" 446 EXTRACT_ALLOWS_QUOTES = False 447 NVL2_SUPPORTED = False 448 LAST_DAY_SUPPORTS_DATE_PART = False 449 JSON_PATH_SINGLE_QUOTE_ESCAPE = True 450 SUPPORTS_TO_NUMBER = False 451 WITH_PROPERTIES_PREFIX = "TBLPROPERTIES" 452 PARSE_JSON_NAME = None 453 PAD_FILL_PATTERN_IS_REQUIRED = True 454 455 EXPRESSIONS_WITHOUT_NESTED_CTES = { 456 exp.Insert, 457 exp.Select, 458 exp.Subquery, 459 exp.SetOperation, 460 } 461 462 SUPPORTED_JSON_PATH_PARTS = { 463 exp.JSONPathKey, 464 exp.JSONPathRoot, 465 exp.JSONPathSubscript, 466 exp.JSONPathWildcard, 467 } 468 469 TYPE_MAPPING = { 470 **generator.Generator.TYPE_MAPPING, 471 exp.DataType.Type.BIT: "BOOLEAN", 472 exp.DataType.Type.DATETIME: "TIMESTAMP", 473 exp.DataType.Type.ROWVERSION: "BINARY", 474 exp.DataType.Type.TEXT: "STRING", 475 exp.DataType.Type.TIME: "TIMESTAMP", 476 exp.DataType.Type.TIMESTAMPTZ: "TIMESTAMP", 477 exp.DataType.Type.UTINYINT: "SMALLINT", 478 exp.DataType.Type.VARBINARY: "BINARY", 479 } 480 481 TRANSFORMS = { 482 **generator.Generator.TRANSFORMS, 483 exp.Group: transforms.preprocess([transforms.unalias_group]), 484 exp.Select: transforms.preprocess( 485 [ 486 transforms.eliminate_qualify, 487 transforms.eliminate_distinct_on, 488 transforms.unnest_to_explode, 489 ] 490 ), 491 exp.Property: _property_sql, 492 exp.AnyValue: rename_func("FIRST"), 493 exp.ApproxDistinct: approx_count_distinct_sql, 494 exp.ArgMax: arg_max_or_min_no_count("MAX_BY"), 495 exp.ArgMin: arg_max_or_min_no_count("MIN_BY"), 496 exp.ArrayConcat: rename_func("CONCAT"), 497 exp.ArrayToString: lambda self, e: self.func("CONCAT_WS", e.expression, e.this), 498 exp.ArraySize: rename_func("SIZE"), 499 exp.ArraySort: _array_sort_sql, 500 exp.With: no_recursive_cte_sql, 501 exp.DateAdd: _add_date_sql, 502 exp.DateDiff: _date_diff_sql, 503 exp.DateStrToDate: datestrtodate_sql, 504 exp.DateSub: _add_date_sql, 505 exp.DateToDi: lambda self, 506 e: f"CAST(DATE_FORMAT({self.sql(e, 'this')}, {Hive.DATEINT_FORMAT}) AS INT)", 507 exp.DiToDate: lambda self, 508 e: f"TO_DATE(CAST({self.sql(e, 'this')} AS STRING), {Hive.DATEINT_FORMAT})", 509 exp.FileFormatProperty: lambda self, 510 e: f"STORED AS {self.sql(e, 'this') if isinstance(e.this, exp.InputOutputFormat) else e.name.upper()}", 511 exp.FromBase64: rename_func("UNBASE64"), 512 exp.GenerateSeries: sequence_sql, 513 exp.If: if_sql(), 514 exp.ILike: no_ilike_sql, 515 exp.IsNan: rename_func("ISNAN"), 516 exp.JSONExtract: lambda self, e: self.func("GET_JSON_OBJECT", e.this, e.expression), 517 exp.JSONExtractScalar: lambda self, e: self.func( 518 "GET_JSON_OBJECT", e.this, e.expression 519 ), 520 exp.JSONFormat: _json_format_sql, 521 exp.Left: left_to_substring_sql, 522 exp.Map: var_map_sql, 523 exp.Max: max_or_greatest, 524 exp.MD5Digest: lambda self, e: self.func("UNHEX", self.func("MD5", e.this)), 525 exp.Min: min_or_least, 526 exp.MonthsBetween: lambda self, e: self.func("MONTHS_BETWEEN", e.this, e.expression), 527 exp.NotNullColumnConstraint: lambda _, e: ( 528 "" if e.args.get("allow_null") else "NOT NULL" 529 ), 530 exp.VarMap: var_map_sql, 531 exp.Create: preprocess( 532 [ 533 remove_unique_constraints, 534 ctas_with_tmp_tables_to_create_tmp_view, 535 move_schema_columns_to_partitioned_by, 536 ] 537 ), 538 exp.Quantile: rename_func("PERCENTILE"), 539 exp.ApproxQuantile: rename_func("PERCENTILE_APPROX"), 540 exp.RegexpExtract: regexp_extract_sql, 541 exp.RegexpReplace: regexp_replace_sql, 542 exp.RegexpLike: lambda self, e: self.binary(e, "RLIKE"), 543 exp.RegexpSplit: rename_func("SPLIT"), 544 exp.Right: right_to_substring_sql, 545 exp.SafeDivide: no_safe_divide_sql, 546 exp.SchemaCommentProperty: lambda self, e: self.naked_property(e), 547 exp.ArrayUniqueAgg: rename_func("COLLECT_SET"), 548 exp.Split: lambda self, e: self.func( 549 "SPLIT", e.this, self.func("CONCAT", "'\\\\Q'", e.expression) 550 ), 551 exp.StrPosition: strposition_to_locate_sql, 552 exp.StrToDate: _str_to_date_sql, 553 exp.StrToTime: _str_to_time_sql, 554 exp.StrToUnix: _str_to_unix_sql, 555 exp.StructExtract: struct_extract_sql, 556 exp.TimeStrToDate: rename_func("TO_DATE"), 557 exp.TimeStrToTime: timestrtotime_sql, 558 exp.TimeStrToUnix: rename_func("UNIX_TIMESTAMP"), 559 exp.TimestampTrunc: lambda self, e: self.func("TRUNC", e.this, unit_to_str(e)), 560 exp.TimeToStr: lambda self, e: self.func("DATE_FORMAT", e.this, self.format_time(e)), 561 exp.TimeToUnix: rename_func("UNIX_TIMESTAMP"), 562 exp.ToBase64: rename_func("BASE64"), 563 exp.TsOrDiToDi: lambda self, 564 e: f"CAST(SUBSTR(REPLACE(CAST({self.sql(e, 'this')} AS STRING), '-', ''), 1, 8) AS INT)", 565 exp.TsOrDsAdd: _add_date_sql, 566 exp.TsOrDsDiff: _date_diff_sql, 567 exp.TsOrDsToDate: _to_date_sql, 568 exp.TryCast: no_trycast_sql, 569 exp.UnixToStr: lambda self, e: self.func( 570 "FROM_UNIXTIME", e.this, time_format("hive")(self, e) 571 ), 572 exp.UnixToTime: _unix_to_time_sql, 573 exp.UnixToTimeStr: rename_func("FROM_UNIXTIME"), 574 exp.PartitionedByProperty: lambda self, e: f"PARTITIONED BY {self.sql(e, 'this')}", 575 exp.NumberToStr: rename_func("FORMAT_NUMBER"), 576 exp.National: lambda self, e: self.national_sql(e, prefix=""), 577 exp.ClusteredColumnConstraint: lambda self, 578 e: f"({self.expressions(e, 'this', indent=False)})", 579 exp.NonClusteredColumnConstraint: lambda self, 580 e: f"({self.expressions(e, 'this', indent=False)})", 581 exp.NotForReplicationColumnConstraint: lambda *_: "", 582 exp.OnProperty: lambda *_: "", 583 exp.PrimaryKeyColumnConstraint: lambda *_: "PRIMARY KEY", 584 exp.WeekOfYear: rename_func("WEEKOFYEAR"), 585 exp.DayOfMonth: rename_func("DAYOFMONTH"), 586 exp.DayOfWeek: rename_func("DAYOFWEEK"), 587 } 588 589 PROPERTIES_LOCATION = { 590 **generator.Generator.PROPERTIES_LOCATION, 591 exp.FileFormatProperty: exp.Properties.Location.POST_SCHEMA, 592 exp.PartitionedByProperty: exp.Properties.Location.POST_SCHEMA, 593 exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED, 594 exp.WithDataProperty: exp.Properties.Location.UNSUPPORTED, 595 } 596 597 def _jsonpathkey_sql(self, expression: exp.JSONPathKey) -> str: 598 if isinstance(expression.this, exp.JSONPathWildcard): 599 self.unsupported("Unsupported wildcard in JSONPathKey expression") 600 return "" 601 602 return super()._jsonpathkey_sql(expression) 603 604 def parameter_sql(self, expression: exp.Parameter) -> str: 605 this = self.sql(expression, "this") 606 expression_sql = self.sql(expression, "expression") 607 608 parent = expression.parent 609 this = f"{this}:{expression_sql}" if expression_sql else this 610 611 if isinstance(parent, exp.EQ) and isinstance(parent.parent, exp.SetItem): 612 # We need to produce SET key = value instead of SET ${key} = value 613 return this 614 615 return f"${{{this}}}" 616 617 def schema_sql(self, expression: exp.Schema) -> str: 618 for ordered in expression.find_all(exp.Ordered): 619 if ordered.args.get("desc") is False: 620 ordered.set("desc", None) 621 622 return super().schema_sql(expression) 623 624 def constraint_sql(self, expression: exp.Constraint) -> str: 625 for prop in list(expression.find_all(exp.Properties)): 626 prop.pop() 627 628 this = self.sql(expression, "this") 629 expressions = self.expressions(expression, sep=" ", flat=True) 630 return f"CONSTRAINT {this} {expressions}" 631 632 def rowformatserdeproperty_sql(self, expression: exp.RowFormatSerdeProperty) -> str: 633 serde_props = self.sql(expression, "serde_properties") 634 serde_props = f" {serde_props}" if serde_props else "" 635 return f"ROW FORMAT SERDE {self.sql(expression, 'this')}{serde_props}" 636 637 def arrayagg_sql(self, expression: exp.ArrayAgg) -> str: 638 return self.func( 639 "COLLECT_LIST", 640 expression.this.this if isinstance(expression.this, exp.Order) else expression.this, 641 ) 642 643 def datatype_sql(self, expression: exp.DataType) -> str: 644 if expression.this in self.PARAMETERIZABLE_TEXT_TYPES and ( 645 not expression.expressions or expression.expressions[0].name == "MAX" 646 ): 647 expression = exp.DataType.build("text") 648 elif expression.is_type(exp.DataType.Type.TEXT) and expression.expressions: 649 expression.set("this", exp.DataType.Type.VARCHAR) 650 elif expression.this in exp.DataType.TEMPORAL_TYPES: 651 expression = exp.DataType.build(expression.this) 652 elif expression.is_type("float"): 653 size_expression = expression.find(exp.DataTypeParam) 654 if size_expression: 655 size = int(size_expression.name) 656 expression = ( 657 exp.DataType.build("float") if size <= 32 else exp.DataType.build("double") 658 ) 659 660 return super().datatype_sql(expression) 661 662 def version_sql(self, expression: exp.Version) -> str: 663 sql = super().version_sql(expression) 664 return sql.replace("FOR ", "", 1) 665 666 def struct_sql(self, expression: exp.Struct) -> str: 667 values = [] 668 669 for i, e in enumerate(expression.expressions): 670 if isinstance(e, exp.PropertyEQ): 671 self.unsupported("Hive does not support named structs.") 672 values.append(e.expression) 673 else: 674 values.append(e) 675 676 return self.func("STRUCT", *values) 677 678 def alterset_sql(self, expression: exp.AlterSet) -> str: 679 exprs = self.expressions(expression, flat=True) 680 exprs = f" {exprs}" if exprs else "" 681 location = self.sql(expression, "location") 682 location = f" LOCATION {location}" if location else "" 683 file_format = self.expressions(expression, key="file_format", flat=True, sep=" ") 684 file_format = f" FILEFORMAT {file_format}" if file_format else "" 685 serde = self.sql(expression, "serde") 686 serde = f" SERDE {serde}" if serde else "" 687 tags = self.expressions(expression, key="tag", flat=True, sep="") 688 tags = f" TAGS {tags}" if tags else "" 689 690 return f"SET{serde}{exprs}{location}{file_format}{tags}" 691 692 def serdeproperties_sql(self, expression: exp.SerdeProperties) -> str: 693 prefix = "WITH " if expression.args.get("with") else "" 694 exprs = self.expressions(expression, flat=True) 695 696 return f"{prefix}SERDEPROPERTIES ({exprs})"
Generator converts a given syntax tree to the corresponding SQL string.
Arguments:
- pretty: Whether to format the produced SQL string. Default: False.
- identify: Determines when an identifier should be quoted. Possible values are: False (default): Never quote, except in cases where it's mandatory by the dialect. True or 'always': Always quote. 'safe': Only quote identifiers that are case insensitive.
- normalize: Whether to normalize identifiers to lowercase. Default: False.
- pad: The pad size in a formatted string. For example, this affects the indentation of a projection in a query, relative to its nesting level. Default: 2.
- indent: The indentation size in a formatted string. For example, this affects the
indentation of subqueries and filters under a
WHERE
clause. Default: 2. - normalize_functions: How to normalize function names. Possible values are: "upper" or True (default): Convert names to uppercase. "lower": Convert names to lowercase. False: Disables function name normalization.
- unsupported_level: Determines the generator's behavior when it encounters unsupported expressions. Default ErrorLevel.WARN.
- max_unsupported: Maximum number of unsupported messages to include in a raised UnsupportedError. This is only relevant if unsupported_level is ErrorLevel.RAISE. Default: 3
- leading_comma: Whether the comma is leading or trailing in select expressions. This is only relevant when generating in pretty mode. Default: False
- max_text_width: The max number of characters in a segment before creating new lines in pretty mode. The default is on the smaller end because the length only represents a segment and not the true line length. Default: 80
- comments: Whether to preserve comments in the output SQL code. Default: True
EXPRESSIONS_WITHOUT_NESTED_CTES =
{<class 'sqlglot.expressions.SetOperation'>, <class 'sqlglot.expressions.Insert'>, <class 'sqlglot.expressions.Subquery'>, <class 'sqlglot.expressions.Select'>}
SUPPORTED_JSON_PATH_PARTS =
{<class 'sqlglot.expressions.JSONPathSubscript'>, <class 'sqlglot.expressions.JSONPathRoot'>, <class 'sqlglot.expressions.JSONPathKey'>, <class 'sqlglot.expressions.JSONPathWildcard'>}
TYPE_MAPPING =
{<Type.NCHAR: 'NCHAR'>: 'CHAR', <Type.NVARCHAR: 'NVARCHAR'>: 'VARCHAR', <Type.MEDIUMTEXT: 'MEDIUMTEXT'>: 'TEXT', <Type.LONGTEXT: 'LONGTEXT'>: 'TEXT', <Type.TINYTEXT: 'TINYTEXT'>: 'TEXT', <Type.MEDIUMBLOB: 'MEDIUMBLOB'>: 'BLOB', <Type.LONGBLOB: 'LONGBLOB'>: 'BLOB', <Type.TINYBLOB: 'TINYBLOB'>: 'BLOB', <Type.INET: 'INET'>: 'INET', <Type.ROWVERSION: 'ROWVERSION'>: 'BINARY', <Type.BIT: 'BIT'>: 'BOOLEAN', <Type.DATETIME: 'DATETIME'>: 'TIMESTAMP', <Type.TEXT: 'TEXT'>: 'STRING', <Type.TIME: 'TIME'>: 'TIMESTAMP', <Type.TIMESTAMPTZ: 'TIMESTAMPTZ'>: 'TIMESTAMP', <Type.UTINYINT: 'UTINYINT'>: 'SMALLINT', <Type.VARBINARY: 'VARBINARY'>: 'BINARY'}
TRANSFORMS =
{<class 'sqlglot.expressions.JSONPathKey'>: <function <lambda>>, <class 'sqlglot.expressions.JSONPathRoot'>: <function <lambda>>, <class 'sqlglot.expressions.JSONPathSubscript'>: <function <lambda>>, <class 'sqlglot.expressions.JSONPathWildcard'>: <function <lambda>>, <class 'sqlglot.expressions.AllowedValuesProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.AutoRefreshProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.BackupProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CaseSpecificColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CharacterSetColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CharacterSetProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ClusteredColumnConstraint'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.CollateColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CommentColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ConnectByRoot'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.CopyGrantsProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.DateFormatColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.DefaultColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.DynamicProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.EncodeColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.EphemeralColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ExcludeColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ExecuteAsProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ExternalProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.GlobalProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.HeapProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.IcebergProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.InheritsProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.InlineLengthColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.InputModelProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.IntervalSpan'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.JSONExtract'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.JSONExtractScalar'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.LanguageProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.LocationProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.LogProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.MaterializedProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.NonClusteredColumnConstraint'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.NoPrimaryIndexProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.NotForReplicationColumnConstraint'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.OnCommitProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.OnProperty'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.OnUpdateColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.OutputModelProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.PathColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ProjectionPolicyColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.RemoteWithConnectionModelProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ReturnsProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SampleProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SecureProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SetConfigProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SetProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SettingsProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SharingProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SqlReadWriteProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.SqlSecurityProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.StabilityProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.StrictProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.TemporaryProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.TagColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.TitleColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.Timestamp'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ToMap'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.ToTableProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.TransformModelProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.TransientProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.UppercaseColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.UnloggedProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.VarMap'>: <function var_map_sql>, <class 'sqlglot.expressions.ViewAttributeProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.VolatileProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.WithJournalTableProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.WithSchemaBindingProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.WithOperator'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.Group'>: <function preprocess.<locals>._to_sql>, <class 'sqlglot.expressions.Select'>: <function preprocess.<locals>._to_sql>, <class 'sqlglot.expressions.Property'>: <function _property_sql>, <class 'sqlglot.expressions.AnyValue'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.ApproxDistinct'>: <function approx_count_distinct_sql>, <class 'sqlglot.expressions.ArgMax'>: <function arg_max_or_min_no_count.<locals>._arg_max_or_min_sql>, <class 'sqlglot.expressions.ArgMin'>: <function arg_max_or_min_no_count.<locals>._arg_max_or_min_sql>, <class 'sqlglot.expressions.ArrayConcat'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.ArrayToString'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.ArraySize'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.ArraySort'>: <function _array_sort_sql>, <class 'sqlglot.expressions.With'>: <function no_recursive_cte_sql>, <class 'sqlglot.expressions.DateAdd'>: <function _add_date_sql>, <class 'sqlglot.expressions.DateDiff'>: <function _date_diff_sql>, <class 'sqlglot.expressions.DateStrToDate'>: <function datestrtodate_sql>, <class 'sqlglot.expressions.DateSub'>: <function _add_date_sql>, <class 'sqlglot.expressions.DateToDi'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.DiToDate'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.FileFormatProperty'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.FromBase64'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.GenerateSeries'>: <function sequence_sql>, <class 'sqlglot.expressions.If'>: <function if_sql.<locals>._if_sql>, <class 'sqlglot.expressions.ILike'>: <function no_ilike_sql>, <class 'sqlglot.expressions.IsNan'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.JSONFormat'>: <function _json_format_sql>, <class 'sqlglot.expressions.Left'>: <function left_to_substring_sql>, <class 'sqlglot.expressions.Map'>: <function var_map_sql>, <class 'sqlglot.expressions.Max'>: <function max_or_greatest>, <class 'sqlglot.expressions.MD5Digest'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.Min'>: <function min_or_least>, <class 'sqlglot.expressions.MonthsBetween'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.NotNullColumnConstraint'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.Create'>: <function preprocess.<locals>._to_sql>, <class 'sqlglot.expressions.Quantile'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.ApproxQuantile'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.RegexpExtract'>: <function regexp_extract_sql>, <class 'sqlglot.expressions.RegexpReplace'>: <function regexp_replace_sql>, <class 'sqlglot.expressions.RegexpLike'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.RegexpSplit'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.Right'>: <function right_to_substring_sql>, <class 'sqlglot.expressions.SafeDivide'>: <function no_safe_divide_sql>, <class 'sqlglot.expressions.SchemaCommentProperty'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.ArrayUniqueAgg'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.Split'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.StrPosition'>: <function strposition_to_locate_sql>, <class 'sqlglot.expressions.StrToDate'>: <function _str_to_date_sql>, <class 'sqlglot.expressions.StrToTime'>: <function _str_to_time_sql>, <class 'sqlglot.expressions.StrToUnix'>: <function _str_to_unix_sql>, <class 'sqlglot.expressions.StructExtract'>: <function struct_extract_sql>, <class 'sqlglot.expressions.TimeStrToDate'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.TimeStrToTime'>: <function timestrtotime_sql>, <class 'sqlglot.expressions.TimeStrToUnix'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.TimestampTrunc'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.TimeToStr'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.TimeToUnix'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.ToBase64'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.TsOrDiToDi'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.TsOrDsAdd'>: <function _add_date_sql>, <class 'sqlglot.expressions.TsOrDsDiff'>: <function _date_diff_sql>, <class 'sqlglot.expressions.TsOrDsToDate'>: <function _to_date_sql>, <class 'sqlglot.expressions.TryCast'>: <function no_trycast_sql>, <class 'sqlglot.expressions.UnixToStr'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.UnixToTime'>: <function _unix_to_time_sql>, <class 'sqlglot.expressions.UnixToTimeStr'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.PartitionedByProperty'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.NumberToStr'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.National'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.PrimaryKeyColumnConstraint'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.WeekOfYear'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.DayOfMonth'>: <function rename_func.<locals>.<lambda>>, <class 'sqlglot.expressions.DayOfWeek'>: <function rename_func.<locals>.<lambda>>}
PROPERTIES_LOCATION =
{<class 'sqlglot.expressions.AllowedValuesProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.AlgorithmProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.AutoIncrementProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.AutoRefreshProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.BackupProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.BlockCompressionProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.CharacterSetProperty'>: <Location.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.DataDeletionProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.DefinerProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.DictRange'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.DictProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.DynamicProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <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_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.FreespaceProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.GlobalProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.HeapProperty'>: <Location.POST_WITH: 'POST_WITH'>, <class 'sqlglot.expressions.InheritsProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.IcebergProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.InputModelProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.IsolatedLoadingProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.JournalProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.LanguageProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.LikeProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.LocationProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.LockProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.LockingProperty'>: <Location.POST_ALIAS: 'POST_ALIAS'>, <class 'sqlglot.expressions.LogProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.MaterializedProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.MergeBlockRatioProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.NoPrimaryIndexProperty'>: <Location.POST_EXPRESSION: 'POST_EXPRESSION'>, <class 'sqlglot.expressions.OnProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.OnCommitProperty'>: <Location.POST_EXPRESSION: 'POST_EXPRESSION'>, <class 'sqlglot.expressions.Order'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.OutputModelProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.PartitionedByProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.PartitionedOfProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.PrimaryKey'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.Property'>: <Location.POST_WITH: 'POST_WITH'>, <class 'sqlglot.expressions.RemoteWithConnectionModelProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.ReturnsProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.RowFormatProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.RowFormatDelimitedProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.RowFormatSerdeProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SampleProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SchemaCommentProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SecureProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.SerdeProperties'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.Set'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SettingsProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SetProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.SetConfigProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SharingProperty'>: <Location.POST_EXPRESSION: 'POST_EXPRESSION'>, <class 'sqlglot.expressions.SequenceProperties'>: <Location.POST_EXPRESSION: 'POST_EXPRESSION'>, <class 'sqlglot.expressions.SortKeyProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SqlReadWriteProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SqlSecurityProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.StabilityProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.StrictProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.TemporaryProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.ToTableProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.TransientProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.TransformModelProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.MergeTreeTTL'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.UnloggedProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.ViewAttributeProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.VolatileProperty'>: <Location.UNSUPPORTED: 'UNSUPPORTED'>, <class 'sqlglot.expressions.WithDataProperty'>: <Location.UNSUPPORTED: 'UNSUPPORTED'>, <class 'sqlglot.expressions.WithJournalTableProperty'>: <Location.POST_NAME: 'POST_NAME'>, <class 'sqlglot.expressions.WithSchemaBindingProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.WithSystemVersioningProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>}
604 def parameter_sql(self, expression: exp.Parameter) -> str: 605 this = self.sql(expression, "this") 606 expression_sql = self.sql(expression, "expression") 607 608 parent = expression.parent 609 this = f"{this}:{expression_sql}" if expression_sql else this 610 611 if isinstance(parent, exp.EQ) and isinstance(parent.parent, exp.SetItem): 612 # We need to produce SET key = value instead of SET ${key} = value 613 return this 614 615 return f"${{{this}}}"
def
rowformatserdeproperty_sql(self, expression: sqlglot.expressions.RowFormatSerdeProperty) -> str:
643 def datatype_sql(self, expression: exp.DataType) -> str: 644 if expression.this in self.PARAMETERIZABLE_TEXT_TYPES and ( 645 not expression.expressions or expression.expressions[0].name == "MAX" 646 ): 647 expression = exp.DataType.build("text") 648 elif expression.is_type(exp.DataType.Type.TEXT) and expression.expressions: 649 expression.set("this", exp.DataType.Type.VARCHAR) 650 elif expression.this in exp.DataType.TEMPORAL_TYPES: 651 expression = exp.DataType.build(expression.this) 652 elif expression.is_type("float"): 653 size_expression = expression.find(exp.DataTypeParam) 654 if size_expression: 655 size = int(size_expression.name) 656 expression = ( 657 exp.DataType.build("float") if size <= 32 else exp.DataType.build("double") 658 ) 659 660 return super().datatype_sql(expression)
666 def struct_sql(self, expression: exp.Struct) -> str: 667 values = [] 668 669 for i, e in enumerate(expression.expressions): 670 if isinstance(e, exp.PropertyEQ): 671 self.unsupported("Hive does not support named structs.") 672 values.append(e.expression) 673 else: 674 values.append(e) 675 676 return self.func("STRUCT", *values)
678 def alterset_sql(self, expression: exp.AlterSet) -> str: 679 exprs = self.expressions(expression, flat=True) 680 exprs = f" {exprs}" if exprs else "" 681 location = self.sql(expression, "location") 682 location = f" LOCATION {location}" if location else "" 683 file_format = self.expressions(expression, key="file_format", flat=True, sep=" ") 684 file_format = f" FILEFORMAT {file_format}" if file_format else "" 685 serde = self.sql(expression, "serde") 686 serde = f" SERDE {serde}" if serde else "" 687 tags = self.expressions(expression, key="tag", flat=True, sep="") 688 tags = f" TAGS {tags}" if tags else "" 689 690 return f"SET{serde}{exprs}{location}{file_format}{tags}"
Inherited Members
- sqlglot.generator.Generator
- Generator
- NULL_ORDERING_SUPPORTED
- IGNORE_NULLS_IN_FUNC
- LOCKING_READS_SUPPORTED
- EXPLICIT_SET_OP
- WRAP_DERIVED_VALUES
- CREATE_FUNCTION_RETURN_AS
- MATCHED_BY_SOURCE
- SINGLE_STRING_INTERVAL
- INTERVAL_ALLOWS_PLURAL_FORM
- LIMIT_ONLY_LITERALS
- RENAME_TABLE_WITH_DB
- GROUPINGS_SEP
- QUERY_HINT_SEP
- IS_BOOL_ALLOWED
- DUPLICATE_KEY_UPDATE_WITH_SET
- LIMIT_IS_TOP
- RETURNING_END
- TZ_TO_WITH_TIME_ZONE
- VALUES_AS_TABLE
- ALTER_TABLE_INCLUDE_COLUMN_KEYWORD
- UNNEST_WITH_ORDINALITY
- AGGREGATE_FILTER_SUPPORTED
- SEMI_ANTI_JOIN_WITH_SIDE
- COMPUTED_COLUMN_WITH_TYPE
- SUPPORTS_TABLE_COPY
- TABLESAMPLE_REQUIRES_PARENS
- TABLESAMPLE_SIZE_IS_ROWS
- TABLESAMPLE_KEYWORDS
- TABLESAMPLE_SEED_KEYWORD
- COLLATE_IS_FUNC
- DATA_TYPE_SPECIFIERS_ALLOWED
- ENSURE_BOOLS
- CTE_RECURSIVE_KEYWORD_REQUIRED
- SUPPORTS_SINGLE_ARG_CONCAT
- SUPPORTS_TABLE_ALIAS_COLUMNS
- UNPIVOT_ALIASES_ARE_IDENTIFIERS
- JSON_KEY_VALUE_PAIR_SEP
- INSERT_OVERWRITE
- SUPPORTS_SELECT_INTO
- SUPPORTS_UNLOGGED_TABLES
- SUPPORTS_CREATE_TABLE_LIKE
- LIKE_PROPERTY_INSIDE_SCHEMA
- MULTI_ARG_DISTINCT
- JSON_TYPE_REQUIRED_FOR_EXTRACTION
- JSON_PATH_BRACKETED_KEY_SUPPORTED
- CAN_IMPLEMENT_ARRAY_ANY
- SET_OP_MODIFIERS
- COPY_PARAMS_ARE_WRAPPED
- COPY_PARAMS_EQ_REQUIRED
- COPY_HAS_INTO_KEYWORD
- STAR_EXCEPT
- HEX_FUNC
- QUOTE_JSON_PATH
- TIME_PART_SINGULARS
- AFTER_HAVING_MODIFIER_TRANSFORMS
- TOKEN_MAPPING
- STRUCT_DELIMITER
- PARAMETER_TOKEN
- NAMED_PLACEHOLDER_TOKEN
- RESERVED_KEYWORDS
- WITH_SEPARATED_COMMENTS
- EXCLUDE_COMMENTS
- UNWRAPPED_INTERVAL_VALUES
- PARAMETERIZABLE_TEXT_TYPES
- SENTINEL_LINE_BREAK
- pretty
- identify
- normalize
- pad
- unsupported_level
- max_unsupported
- leading_comma
- max_text_width
- comments
- dialect
- normalize_functions
- unsupported_messages
- generate
- preprocess
- unsupported
- sep
- seg
- pad_comment
- maybe_comment
- wrap
- no_identify
- normalize_func
- indent
- sql
- uncache_sql
- cache_sql
- characterset_sql
- column_parts
- column_sql
- columnposition_sql
- columndef_sql
- columnconstraint_sql
- computedcolumnconstraint_sql
- autoincrementcolumnconstraint_sql
- compresscolumnconstraint_sql
- generatedasidentitycolumnconstraint_sql
- generatedasrowcolumnconstraint_sql
- periodforsystemtimeconstraint_sql
- notnullcolumnconstraint_sql
- transformcolumnconstraint_sql
- primarykeycolumnconstraint_sql
- uniquecolumnconstraint_sql
- createable_sql
- create_sql
- sequenceproperties_sql
- clone_sql
- describe_sql
- heredoc_sql
- prepend_ctes
- with_sql
- cte_sql
- tablealias_sql
- bitstring_sql
- hexstring_sql
- bytestring_sql
- unicodestring_sql
- rawstring_sql
- datatypeparam_sql
- directory_sql
- delete_sql
- drop_sql
- except_sql
- except_op
- fetch_sql
- filter_sql
- hint_sql
- indexparameters_sql
- index_sql
- identifier_sql
- hex_sql
- lowerhex_sql
- inputoutputformat_sql
- national_sql
- partition_sql
- properties_sql
- root_properties
- properties
- with_properties
- locate_properties
- property_name
- property_sql
- likeproperty_sql
- fallbackproperty_sql
- journalproperty_sql
- freespaceproperty_sql
- checksumproperty_sql
- mergeblockratioproperty_sql
- datablocksizeproperty_sql
- blockcompressionproperty_sql
- isolatedloadingproperty_sql
- partitionboundspec_sql
- partitionedofproperty_sql
- lockingproperty_sql
- withdataproperty_sql
- withsystemversioningproperty_sql
- insert_sql
- intersect_sql
- intersect_op
- introducer_sql
- kill_sql
- pseudotype_sql
- objectidentifier_sql
- onconflict_sql
- returning_sql
- rowformatdelimitedproperty_sql
- withtablehint_sql
- indextablehint_sql
- historicaldata_sql
- table_parts
- table_sql
- tablesample_sql
- pivot_sql
- tuple_sql
- update_sql
- values_sql
- var_sql
- into_sql
- from_sql
- group_sql
- having_sql
- connect_sql
- prior_sql
- join_sql
- lambda_sql
- lateral_op
- lateral_sql
- limit_sql
- offset_sql
- setitem_sql
- set_sql
- pragma_sql
- lock_sql
- literal_sql
- escape_str
- loaddata_sql
- null_sql
- boolean_sql
- order_sql
- withfill_sql
- cluster_sql
- distribute_sql
- sort_sql
- ordered_sql
- matchrecognizemeasure_sql
- matchrecognize_sql
- query_modifiers
- options_modifier
- queryoption_sql
- offset_limit_modifiers
- after_limit_modifiers
- select_sql
- schema_columns_sql
- star_sql
- sessionparameter_sql
- placeholder_sql
- subquery_sql
- qualify_sql
- set_operations
- union_sql
- union_op
- unnest_sql
- prewhere_sql
- where_sql
- window_sql
- partition_by_sql
- windowspec_sql
- withingroup_sql
- between_sql
- bracket_offset_expressions
- bracket_sql
- all_sql
- any_sql
- exists_sql
- case_sql
- nextvaluefor_sql
- extract_sql
- trim_sql
- convert_concat_args
- concat_sql
- concatws_sql
- check_sql
- foreignkey_sql
- primarykey_sql
- if_sql
- matchagainst_sql
- jsonkeyvalue_sql
- jsonpath_sql
- json_path_part
- formatjson_sql
- jsonobject_sql
- jsonobjectagg_sql
- jsonarray_sql
- jsonarrayagg_sql
- jsoncolumndef_sql
- jsonschema_sql
- jsontable_sql
- openjsoncolumndef_sql
- openjson_sql
- in_sql
- in_unnest_op
- interval_sql
- return_sql
- reference_sql
- anonymous_sql
- paren_sql
- neg_sql
- not_sql
- alias_sql
- pivotalias_sql
- aliases_sql
- atindex_sql
- attimezone_sql
- fromtimezone_sql
- add_sql
- and_sql
- or_sql
- xor_sql
- connector_sql
- bitwiseand_sql
- bitwiseleftshift_sql
- bitwisenot_sql
- bitwiseor_sql
- bitwiserightshift_sql
- bitwisexor_sql
- cast_sql
- currentdate_sql
- currenttimestamp_sql
- collate_sql
- command_sql
- comment_sql
- mergetreettlaction_sql
- mergetreettl_sql
- transaction_sql
- commit_sql
- rollback_sql
- altercolumn_sql
- alterdiststyle_sql
- altersortkey_sql
- renametable_sql
- renamecolumn_sql
- altertable_sql
- add_column_sql
- droppartition_sql
- addconstraint_sql
- distinct_sql
- ignorenulls_sql
- respectnulls_sql
- havingmax_sql
- intdiv_sql
- dpipe_sql
- div_sql
- overlaps_sql
- distance_sql
- dot_sql
- eq_sql
- propertyeq_sql
- escape_sql
- glob_sql
- gt_sql
- gte_sql
- ilike_sql
- ilikeany_sql
- is_sql
- like_sql
- likeany_sql
- similarto_sql
- lt_sql
- lte_sql
- mod_sql
- mul_sql
- neq_sql
- nullsafeeq_sql
- nullsafeneq_sql
- slice_sql
- sub_sql
- trycast_sql
- try_sql
- log_sql
- use_sql
- binary
- function_fallback_sql
- func
- format_args
- too_wide
- format_time
- expressions
- op_expressions
- naked_property
- tag_sql
- token_sql
- userdefinedfunction_sql
- joinhint_sql
- kwarg_sql
- when_sql
- merge_sql
- tochar_sql
- tonumber_sql
- dictproperty_sql
- dictrange_sql
- dictsubproperty_sql
- oncluster_sql
- clusteredbyproperty_sql
- anyvalue_sql
- querytransform_sql
- indexconstraintoption_sql
- checkcolumnconstraint_sql
- indexcolumnconstraint_sql
- nvl2_sql
- comprehension_sql
- columnprefix_sql
- opclass_sql
- predict_sql
- forin_sql
- refresh_sql
- operator_sql
- toarray_sql
- tsordstotime_sql
- tsordstotimestamp_sql
- tsordstodate_sql
- unixdate_sql
- lastday_sql
- dateadd_sql
- arrayany_sql
- generateseries_sql
- partitionrange_sql
- truncatetable_sql
- convert_sql
- copyparameter_sql
- credentials_sql
- copy_sql
- semicolon_sql
- datadeletionproperty_sql
- maskingpolicycolumnconstraint_sql
- gapfill_sql
- scope_resolution
- scoperesolution_sql
- parsejson_sql
- length_sql
- rand_sql
- strtodate_sql
- strtotime_sql
- changes_sql
- pad_sql