sqlglot.dialects.hive
1from __future__ import annotations 2 3import typing as t 4from functools import partial 5 6from sqlglot import exp, generator, parser, tokens, transforms 7from sqlglot.dialects.dialect import ( 8 DATE_ADD_OR_SUB, 9 Dialect, 10 NormalizationStrategy, 11 approx_count_distinct_sql, 12 arg_max_or_min_no_count, 13 datestrtodate_sql, 14 build_formatted_time, 15 if_sql, 16 is_parse_json, 17 left_to_substring_sql, 18 locate_to_strposition, 19 max_or_greatest, 20 min_or_least, 21 no_ilike_sql, 22 no_recursive_cte_sql, 23 no_safe_divide_sql, 24 no_trycast_sql, 25 regexp_extract_sql, 26 regexp_replace_sql, 27 rename_func, 28 right_to_substring_sql, 29 strposition_to_locate_sql, 30 struct_extract_sql, 31 time_format, 32 timestrtotime_sql, 33 unit_to_str, 34 var_map_sql, 35 sequence_sql, 36 property_sql, 37 build_regexp_extract, 38) 39from sqlglot.transforms import ( 40 remove_unique_constraints, 41 ctas_with_tmp_tables_to_create_tmp_view, 42 preprocess, 43 move_schema_columns_to_partitioned_by, 44) 45from sqlglot.helper import seq_get 46from sqlglot.tokens import TokenType 47 48# (FuncType, Multiplier) 49DATE_DELTA_INTERVAL = { 50 "YEAR": ("ADD_MONTHS", 12), 51 "MONTH": ("ADD_MONTHS", 1), 52 "QUARTER": ("ADD_MONTHS", 3), 53 "WEEK": ("DATE_ADD", 7), 54 "DAY": ("DATE_ADD", 1), 55} 56 57TIME_DIFF_FACTOR = { 58 "MILLISECOND": " * 1000", 59 "SECOND": "", 60 "MINUTE": " / 60", 61 "HOUR": " / 3600", 62} 63 64DIFF_MONTH_SWITCH = ("YEAR", "QUARTER", "MONTH") 65 66 67def _add_date_sql(self: Hive.Generator, expression: DATE_ADD_OR_SUB) -> str: 68 if isinstance(expression, exp.TsOrDsAdd) and not expression.unit: 69 return self.func("DATE_ADD", expression.this, expression.expression) 70 71 unit = expression.text("unit").upper() 72 func, multiplier = DATE_DELTA_INTERVAL.get(unit, ("DATE_ADD", 1)) 73 74 if isinstance(expression, exp.DateSub): 75 multiplier *= -1 76 77 if expression.expression.is_number: 78 modified_increment = exp.Literal.number(expression.expression.to_py() * multiplier) 79 else: 80 modified_increment = expression.expression 81 if multiplier != 1: 82 modified_increment = exp.Mul( # type: ignore 83 this=modified_increment, expression=exp.Literal.number(multiplier) 84 ) 85 86 return self.func(func, expression.this, modified_increment) 87 88 89def _date_diff_sql(self: Hive.Generator, expression: exp.DateDiff | exp.TsOrDsDiff) -> str: 90 unit = expression.text("unit").upper() 91 92 factor = TIME_DIFF_FACTOR.get(unit) 93 if factor is not None: 94 left = self.sql(expression, "this") 95 right = self.sql(expression, "expression") 96 sec_diff = f"UNIX_TIMESTAMP({left}) - UNIX_TIMESTAMP({right})" 97 return f"({sec_diff}){factor}" if factor else sec_diff 98 99 months_between = unit in DIFF_MONTH_SWITCH 100 sql_func = "MONTHS_BETWEEN" if months_between else "DATEDIFF" 101 _, multiplier = DATE_DELTA_INTERVAL.get(unit, ("", 1)) 102 multiplier_sql = f" / {multiplier}" if multiplier > 1 else "" 103 diff_sql = f"{sql_func}({self.format_args(expression.this, expression.expression)})" 104 105 if months_between or multiplier_sql: 106 # MONTHS_BETWEEN returns a float, so we need to truncate the fractional part. 107 # For the same reason, we want to truncate if there's a divisor present. 108 diff_sql = f"CAST({diff_sql}{multiplier_sql} AS INT)" 109 110 return diff_sql 111 112 113def _json_format_sql(self: Hive.Generator, expression: exp.JSONFormat) -> str: 114 this = expression.this 115 116 if is_parse_json(this): 117 if this.this.is_string: 118 # Since FROM_JSON requires a nested type, we always wrap the json string with 119 # an array to ensure that "naked" strings like "'a'" will be handled correctly 120 wrapped_json = exp.Literal.string(f"[{this.this.name}]") 121 122 from_json = self.func( 123 "FROM_JSON", wrapped_json, self.func("SCHEMA_OF_JSON", wrapped_json) 124 ) 125 to_json = self.func("TO_JSON", from_json) 126 127 # This strips the [, ] delimiters of the dummy array printed by TO_JSON 128 return self.func("REGEXP_EXTRACT", to_json, "'^.(.*).$'", "1") 129 return self.sql(this) 130 131 return self.func("TO_JSON", this, expression.args.get("options")) 132 133 134def _array_sort_sql(self: Hive.Generator, expression: exp.ArraySort) -> str: 135 if expression.expression: 136 self.unsupported("Hive SORT_ARRAY does not support a comparator") 137 return self.func("SORT_ARRAY", expression.this) 138 139 140def _str_to_unix_sql(self: Hive.Generator, expression: exp.StrToUnix) -> str: 141 return self.func("UNIX_TIMESTAMP", expression.this, time_format("hive")(self, expression)) 142 143 144def _unix_to_time_sql(self: Hive.Generator, expression: exp.UnixToTime) -> str: 145 timestamp = self.sql(expression, "this") 146 scale = expression.args.get("scale") 147 if scale in (None, exp.UnixToTime.SECONDS): 148 return rename_func("FROM_UNIXTIME")(self, expression) 149 150 return f"FROM_UNIXTIME({timestamp} / POW(10, {scale}))" 151 152 153def _str_to_date_sql(self: Hive.Generator, expression: exp.StrToDate) -> str: 154 this = self.sql(expression, "this") 155 time_format = self.format_time(expression) 156 if time_format not in (Hive.TIME_FORMAT, Hive.DATE_FORMAT): 157 this = f"FROM_UNIXTIME(UNIX_TIMESTAMP({this}, {time_format}))" 158 return f"CAST({this} AS DATE)" 159 160 161def _str_to_time_sql(self: Hive.Generator, expression: exp.StrToTime) -> str: 162 this = self.sql(expression, "this") 163 time_format = self.format_time(expression) 164 if time_format not in (Hive.TIME_FORMAT, Hive.DATE_FORMAT): 165 this = f"FROM_UNIXTIME(UNIX_TIMESTAMP({this}, {time_format}))" 166 return f"CAST({this} AS TIMESTAMP)" 167 168 169def _to_date_sql(self: Hive.Generator, expression: exp.TsOrDsToDate) -> str: 170 time_format = self.format_time(expression) 171 if time_format and time_format not in (Hive.TIME_FORMAT, Hive.DATE_FORMAT): 172 return self.func("TO_DATE", expression.this, time_format) 173 174 if isinstance(expression.this, exp.TsOrDsToDate): 175 return self.sql(expression, "this") 176 177 return self.func("TO_DATE", expression.this) 178 179 180def _build_with_ignore_nulls( 181 exp_class: t.Type[exp.Expression], 182) -> t.Callable[[t.List[exp.Expression]], exp.Expression]: 183 def _parse(args: t.List[exp.Expression]) -> exp.Expression: 184 this = exp_class(this=seq_get(args, 0)) 185 if seq_get(args, 1) == exp.true(): 186 return exp.IgnoreNulls(this=this) 187 return this 188 189 return _parse 190 191 192class Hive(Dialect): 193 ALIAS_POST_TABLESAMPLE = True 194 IDENTIFIERS_CAN_START_WITH_DIGIT = True 195 SUPPORTS_USER_DEFINED_TYPES = False 196 SAFE_DIVISION = True 197 ARRAY_AGG_INCLUDES_NULLS = None 198 REGEXP_EXTRACT_DEFAULT_GROUP = 1 199 200 # 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 "MINUS": TokenType.EXCEPT, 257 "MSCK REPAIR": TokenType.COMMAND, 258 "REFRESH": TokenType.REFRESH, 259 "TIMESTAMP AS OF": TokenType.TIMESTAMP_SNAPSHOT, 260 "VERSION AS OF": TokenType.VERSION_SNAPSHOT, 261 "SERDEPROPERTIES": TokenType.SERDE_PROPERTIES, 262 } 263 264 NUMERIC_LITERALS = { 265 "L": "BIGINT", 266 "S": "SMALLINT", 267 "Y": "TINYINT", 268 "D": "DOUBLE", 269 "F": "FLOAT", 270 "BD": "DECIMAL", 271 } 272 273 class Parser(parser.Parser): 274 LOG_DEFAULTS_TO_LN = True 275 STRICT_CAST = False 276 VALUES_FOLLOWED_BY_PAREN = False 277 278 FUNCTIONS = { 279 **parser.Parser.FUNCTIONS, 280 "BASE64": exp.ToBase64.from_arg_list, 281 "COLLECT_LIST": lambda args: exp.ArrayAgg(this=seq_get(args, 0), nulls_excluded=True), 282 "COLLECT_SET": exp.ArrayUniqueAgg.from_arg_list, 283 "DATE_ADD": lambda args: exp.TsOrDsAdd( 284 this=seq_get(args, 0), expression=seq_get(args, 1), unit=exp.Literal.string("DAY") 285 ), 286 "DATE_FORMAT": lambda args: build_formatted_time(exp.TimeToStr, "hive")( 287 [ 288 exp.TimeStrToTime(this=seq_get(args, 0)), 289 seq_get(args, 1), 290 ] 291 ), 292 "DATE_SUB": lambda args: exp.TsOrDsAdd( 293 this=seq_get(args, 0), 294 expression=exp.Mul(this=seq_get(args, 1), expression=exp.Literal.number(-1)), 295 unit=exp.Literal.string("DAY"), 296 ), 297 "DATEDIFF": lambda args: exp.DateDiff( 298 this=exp.TsOrDsToDate(this=seq_get(args, 0)), 299 expression=exp.TsOrDsToDate(this=seq_get(args, 1)), 300 ), 301 "DAY": lambda args: exp.Day(this=exp.TsOrDsToDate(this=seq_get(args, 0))), 302 "FIRST": _build_with_ignore_nulls(exp.First), 303 "FIRST_VALUE": _build_with_ignore_nulls(exp.FirstValue), 304 "FROM_UNIXTIME": build_formatted_time(exp.UnixToStr, "hive", True), 305 "GET_JSON_OBJECT": exp.JSONExtractScalar.from_arg_list, 306 "LAST": _build_with_ignore_nulls(exp.Last), 307 "LAST_VALUE": _build_with_ignore_nulls(exp.LastValue), 308 "LOCATE": locate_to_strposition, 309 "MAP": parser.build_var_map, 310 "MONTH": lambda args: exp.Month(this=exp.TsOrDsToDate.from_arg_list(args)), 311 "PERCENTILE": exp.Quantile.from_arg_list, 312 "PERCENTILE_APPROX": exp.ApproxQuantile.from_arg_list, 313 "REGEXP_EXTRACT": build_regexp_extract, 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 def _to_prop_eq(self, expression: exp.Expression, index: int) -> exp.Expression: 439 if isinstance(expression, exp.Column): 440 key = expression.this 441 else: 442 key = exp.to_identifier(f"col{index + 1}") 443 444 return self.expression(exp.PropertyEQ, this=key, expression=expression) 445 446 class Generator(generator.Generator): 447 LIMIT_FETCH = "LIMIT" 448 TABLESAMPLE_WITH_METHOD = False 449 JOIN_HINTS = False 450 TABLE_HINTS = False 451 QUERY_HINTS = False 452 INDEX_ON = "ON TABLE" 453 EXTRACT_ALLOWS_QUOTES = False 454 NVL2_SUPPORTED = False 455 LAST_DAY_SUPPORTS_DATE_PART = False 456 JSON_PATH_SINGLE_QUOTE_ESCAPE = True 457 SUPPORTS_TO_NUMBER = False 458 WITH_PROPERTIES_PREFIX = "TBLPROPERTIES" 459 PARSE_JSON_NAME = None 460 PAD_FILL_PATTERN_IS_REQUIRED = True 461 462 EXPRESSIONS_WITHOUT_NESTED_CTES = { 463 exp.Insert, 464 exp.Select, 465 exp.Subquery, 466 exp.SetOperation, 467 } 468 469 SUPPORTED_JSON_PATH_PARTS = { 470 exp.JSONPathKey, 471 exp.JSONPathRoot, 472 exp.JSONPathSubscript, 473 exp.JSONPathWildcard, 474 } 475 476 TYPE_MAPPING = { 477 **generator.Generator.TYPE_MAPPING, 478 exp.DataType.Type.BIT: "BOOLEAN", 479 exp.DataType.Type.DATETIME: "TIMESTAMP", 480 exp.DataType.Type.ROWVERSION: "BINARY", 481 exp.DataType.Type.TEXT: "STRING", 482 exp.DataType.Type.TIME: "TIMESTAMP", 483 exp.DataType.Type.TIMESTAMPTZ: "TIMESTAMP", 484 exp.DataType.Type.UTINYINT: "SMALLINT", 485 exp.DataType.Type.VARBINARY: "BINARY", 486 } 487 488 TRANSFORMS = { 489 **generator.Generator.TRANSFORMS, 490 exp.Group: transforms.preprocess([transforms.unalias_group]), 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.GenerateDateArray: sequence_sql, 514 exp.If: if_sql(), 515 exp.ILike: no_ilike_sql, 516 exp.IsNan: rename_func("ISNAN"), 517 exp.JSONExtract: lambda self, e: self.func("GET_JSON_OBJECT", e.this, e.expression), 518 exp.JSONExtractScalar: lambda self, e: self.func( 519 "GET_JSON_OBJECT", e.this, e.expression 520 ), 521 exp.JSONFormat: _json_format_sql, 522 exp.Left: left_to_substring_sql, 523 exp.Map: var_map_sql, 524 exp.Max: max_or_greatest, 525 exp.MD5Digest: lambda self, e: self.func("UNHEX", self.func("MD5", e.this)), 526 exp.Min: min_or_least, 527 exp.MonthsBetween: lambda self, e: self.func("MONTHS_BETWEEN", e.this, e.expression), 528 exp.NotNullColumnConstraint: lambda _, e: ( 529 "" if e.args.get("allow_null") else "NOT NULL" 530 ), 531 exp.VarMap: var_map_sql, 532 exp.Create: preprocess( 533 [ 534 remove_unique_constraints, 535 ctas_with_tmp_tables_to_create_tmp_view, 536 move_schema_columns_to_partitioned_by, 537 ] 538 ), 539 exp.Quantile: rename_func("PERCENTILE"), 540 exp.ApproxQuantile: rename_func("PERCENTILE_APPROX"), 541 exp.RegexpExtract: regexp_extract_sql, 542 exp.RegexpReplace: regexp_replace_sql, 543 exp.RegexpLike: lambda self, e: self.binary(e, "RLIKE"), 544 exp.RegexpSplit: rename_func("SPLIT"), 545 exp.Right: right_to_substring_sql, 546 exp.SafeDivide: no_safe_divide_sql, 547 exp.SchemaCommentProperty: lambda self, e: self.naked_property(e), 548 exp.ArrayUniqueAgg: rename_func("COLLECT_SET"), 549 exp.Split: lambda self, e: self.func( 550 "SPLIT", e.this, self.func("CONCAT", "'\\\\Q'", e.expression) 551 ), 552 exp.Select: transforms.preprocess( 553 [ 554 transforms.eliminate_qualify, 555 transforms.eliminate_distinct_on, 556 partial(transforms.unnest_to_explode, unnest_using_arrays_zip=False), 557 ] 558 ), 559 exp.StrPosition: strposition_to_locate_sql, 560 exp.StrToDate: _str_to_date_sql, 561 exp.StrToTime: _str_to_time_sql, 562 exp.StrToUnix: _str_to_unix_sql, 563 exp.StructExtract: struct_extract_sql, 564 exp.Table: transforms.preprocess([transforms.unnest_generate_series]), 565 exp.TimeStrToDate: rename_func("TO_DATE"), 566 exp.TimeStrToTime: timestrtotime_sql, 567 exp.TimeStrToUnix: rename_func("UNIX_TIMESTAMP"), 568 exp.TimestampTrunc: lambda self, e: self.func("TRUNC", e.this, unit_to_str(e)), 569 exp.TimeToStr: lambda self, e: self.func("DATE_FORMAT", e.this, self.format_time(e)), 570 exp.TimeToUnix: rename_func("UNIX_TIMESTAMP"), 571 exp.ToBase64: rename_func("BASE64"), 572 exp.TsOrDiToDi: lambda self, 573 e: f"CAST(SUBSTR(REPLACE(CAST({self.sql(e, 'this')} AS STRING), '-', ''), 1, 8) AS INT)", 574 exp.TsOrDsAdd: _add_date_sql, 575 exp.TsOrDsDiff: _date_diff_sql, 576 exp.TsOrDsToDate: _to_date_sql, 577 exp.TryCast: no_trycast_sql, 578 exp.UnixToStr: lambda self, e: self.func( 579 "FROM_UNIXTIME", e.this, time_format("hive")(self, e) 580 ), 581 exp.UnixToTime: _unix_to_time_sql, 582 exp.UnixToTimeStr: rename_func("FROM_UNIXTIME"), 583 exp.Unnest: rename_func("EXPLODE"), 584 exp.PartitionedByProperty: lambda self, e: f"PARTITIONED BY {self.sql(e, 'this')}", 585 exp.NumberToStr: rename_func("FORMAT_NUMBER"), 586 exp.National: lambda self, e: self.national_sql(e, prefix=""), 587 exp.ClusteredColumnConstraint: lambda self, 588 e: f"({self.expressions(e, 'this', indent=False)})", 589 exp.NonClusteredColumnConstraint: lambda self, 590 e: f"({self.expressions(e, 'this', indent=False)})", 591 exp.NotForReplicationColumnConstraint: lambda *_: "", 592 exp.OnProperty: lambda *_: "", 593 exp.PrimaryKeyColumnConstraint: lambda *_: "PRIMARY KEY", 594 exp.WeekOfYear: rename_func("WEEKOFYEAR"), 595 exp.DayOfMonth: rename_func("DAYOFMONTH"), 596 exp.DayOfWeek: rename_func("DAYOFWEEK"), 597 } 598 599 PROPERTIES_LOCATION = { 600 **generator.Generator.PROPERTIES_LOCATION, 601 exp.FileFormatProperty: exp.Properties.Location.POST_SCHEMA, 602 exp.PartitionedByProperty: exp.Properties.Location.POST_SCHEMA, 603 exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED, 604 exp.WithDataProperty: exp.Properties.Location.UNSUPPORTED, 605 } 606 607 def unnest_sql(self, expression: exp.Unnest) -> str: 608 return rename_func("EXPLODE")(self, expression) 609 610 def _jsonpathkey_sql(self, expression: exp.JSONPathKey) -> str: 611 if isinstance(expression.this, exp.JSONPathWildcard): 612 self.unsupported("Unsupported wildcard in JSONPathKey expression") 613 return "" 614 615 return super()._jsonpathkey_sql(expression) 616 617 def parameter_sql(self, expression: exp.Parameter) -> str: 618 this = self.sql(expression, "this") 619 expression_sql = self.sql(expression, "expression") 620 621 parent = expression.parent 622 this = f"{this}:{expression_sql}" if expression_sql else this 623 624 if isinstance(parent, exp.EQ) and isinstance(parent.parent, exp.SetItem): 625 # We need to produce SET key = value instead of SET ${key} = value 626 return this 627 628 return f"${{{this}}}" 629 630 def schema_sql(self, expression: exp.Schema) -> str: 631 for ordered in expression.find_all(exp.Ordered): 632 if ordered.args.get("desc") is False: 633 ordered.set("desc", None) 634 635 return super().schema_sql(expression) 636 637 def constraint_sql(self, expression: exp.Constraint) -> str: 638 for prop in list(expression.find_all(exp.Properties)): 639 prop.pop() 640 641 this = self.sql(expression, "this") 642 expressions = self.expressions(expression, sep=" ", flat=True) 643 return f"CONSTRAINT {this} {expressions}" 644 645 def rowformatserdeproperty_sql(self, expression: exp.RowFormatSerdeProperty) -> str: 646 serde_props = self.sql(expression, "serde_properties") 647 serde_props = f" {serde_props}" if serde_props else "" 648 return f"ROW FORMAT SERDE {self.sql(expression, 'this')}{serde_props}" 649 650 def arrayagg_sql(self, expression: exp.ArrayAgg) -> str: 651 return self.func( 652 "COLLECT_LIST", 653 expression.this.this if isinstance(expression.this, exp.Order) else expression.this, 654 ) 655 656 def datatype_sql(self, expression: exp.DataType) -> str: 657 if expression.this in self.PARAMETERIZABLE_TEXT_TYPES and ( 658 not expression.expressions or expression.expressions[0].name == "MAX" 659 ): 660 expression = exp.DataType.build("text") 661 elif expression.is_type(exp.DataType.Type.TEXT) and expression.expressions: 662 expression.set("this", exp.DataType.Type.VARCHAR) 663 elif expression.this in exp.DataType.TEMPORAL_TYPES: 664 expression = exp.DataType.build(expression.this) 665 elif expression.is_type("float"): 666 size_expression = expression.find(exp.DataTypeParam) 667 if size_expression: 668 size = int(size_expression.name) 669 expression = ( 670 exp.DataType.build("float") if size <= 32 else exp.DataType.build("double") 671 ) 672 673 return super().datatype_sql(expression) 674 675 def version_sql(self, expression: exp.Version) -> str: 676 sql = super().version_sql(expression) 677 return sql.replace("FOR ", "", 1) 678 679 def struct_sql(self, expression: exp.Struct) -> str: 680 values = [] 681 682 for i, e in enumerate(expression.expressions): 683 if isinstance(e, exp.PropertyEQ): 684 self.unsupported("Hive does not support named structs.") 685 values.append(e.expression) 686 else: 687 values.append(e) 688 689 return self.func("STRUCT", *values) 690 691 def alterset_sql(self, expression: exp.AlterSet) -> str: 692 exprs = self.expressions(expression, flat=True) 693 exprs = f" {exprs}" if exprs else "" 694 location = self.sql(expression, "location") 695 location = f" LOCATION {location}" if location else "" 696 file_format = self.expressions(expression, key="file_format", flat=True, sep=" ") 697 file_format = f" FILEFORMAT {file_format}" if file_format else "" 698 serde = self.sql(expression, "serde") 699 serde = f" SERDE {serde}" if serde else "" 700 tags = self.expressions(expression, key="tag", flat=True, sep="") 701 tags = f" TAGS {tags}" if tags else "" 702 703 return f"SET{serde}{exprs}{location}{file_format}{tags}" 704 705 def serdeproperties_sql(self, expression: exp.SerdeProperties) -> str: 706 prefix = "WITH " if expression.args.get("with") else "" 707 exprs = self.expressions(expression, flat=True) 708 709 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')
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 ARRAY_AGG_INCLUDES_NULLS = None 199 REGEXP_EXTRACT_DEFAULT_GROUP = 1 200 201 # https://spark.apache.org/docs/latest/sql-ref-identifier.html#description 202 NORMALIZATION_STRATEGY = NormalizationStrategy.CASE_INSENSITIVE 203 204 TIME_MAPPING = { 205 "y": "%Y", 206 "Y": "%Y", 207 "YYYY": "%Y", 208 "yyyy": "%Y", 209 "YY": "%y", 210 "yy": "%y", 211 "MMMM": "%B", 212 "MMM": "%b", 213 "MM": "%m", 214 "M": "%-m", 215 "dd": "%d", 216 "d": "%-d", 217 "HH": "%H", 218 "H": "%-H", 219 "hh": "%I", 220 "h": "%-I", 221 "mm": "%M", 222 "m": "%-M", 223 "ss": "%S", 224 "s": "%-S", 225 "SSSSSS": "%f", 226 "a": "%p", 227 "DD": "%j", 228 "D": "%-j", 229 "E": "%a", 230 "EE": "%a", 231 "EEE": "%a", 232 "EEEE": "%A", 233 } 234 235 DATE_FORMAT = "'yyyy-MM-dd'" 236 DATEINT_FORMAT = "'yyyyMMdd'" 237 TIME_FORMAT = "'yyyy-MM-dd HH:mm:ss'" 238 239 class Tokenizer(tokens.Tokenizer): 240 QUOTES = ["'", '"'] 241 IDENTIFIERS = ["`"] 242 STRING_ESCAPES = ["\\"] 243 244 SINGLE_TOKENS = { 245 **tokens.Tokenizer.SINGLE_TOKENS, 246 "$": TokenType.PARAMETER, 247 } 248 249 KEYWORDS = { 250 **tokens.Tokenizer.KEYWORDS, 251 "ADD ARCHIVE": TokenType.COMMAND, 252 "ADD ARCHIVES": TokenType.COMMAND, 253 "ADD FILE": TokenType.COMMAND, 254 "ADD FILES": TokenType.COMMAND, 255 "ADD JAR": TokenType.COMMAND, 256 "ADD JARS": TokenType.COMMAND, 257 "MINUS": TokenType.EXCEPT, 258 "MSCK REPAIR": TokenType.COMMAND, 259 "REFRESH": TokenType.REFRESH, 260 "TIMESTAMP AS OF": TokenType.TIMESTAMP_SNAPSHOT, 261 "VERSION AS OF": TokenType.VERSION_SNAPSHOT, 262 "SERDEPROPERTIES": TokenType.SERDE_PROPERTIES, 263 } 264 265 NUMERIC_LITERALS = { 266 "L": "BIGINT", 267 "S": "SMALLINT", 268 "Y": "TINYINT", 269 "D": "DOUBLE", 270 "F": "FLOAT", 271 "BD": "DECIMAL", 272 } 273 274 class Parser(parser.Parser): 275 LOG_DEFAULTS_TO_LN = True 276 STRICT_CAST = False 277 VALUES_FOLLOWED_BY_PAREN = False 278 279 FUNCTIONS = { 280 **parser.Parser.FUNCTIONS, 281 "BASE64": exp.ToBase64.from_arg_list, 282 "COLLECT_LIST": lambda args: exp.ArrayAgg(this=seq_get(args, 0), nulls_excluded=True), 283 "COLLECT_SET": exp.ArrayUniqueAgg.from_arg_list, 284 "DATE_ADD": lambda args: exp.TsOrDsAdd( 285 this=seq_get(args, 0), expression=seq_get(args, 1), unit=exp.Literal.string("DAY") 286 ), 287 "DATE_FORMAT": lambda args: build_formatted_time(exp.TimeToStr, "hive")( 288 [ 289 exp.TimeStrToTime(this=seq_get(args, 0)), 290 seq_get(args, 1), 291 ] 292 ), 293 "DATE_SUB": lambda args: exp.TsOrDsAdd( 294 this=seq_get(args, 0), 295 expression=exp.Mul(this=seq_get(args, 1), expression=exp.Literal.number(-1)), 296 unit=exp.Literal.string("DAY"), 297 ), 298 "DATEDIFF": lambda args: exp.DateDiff( 299 this=exp.TsOrDsToDate(this=seq_get(args, 0)), 300 expression=exp.TsOrDsToDate(this=seq_get(args, 1)), 301 ), 302 "DAY": lambda args: exp.Day(this=exp.TsOrDsToDate(this=seq_get(args, 0))), 303 "FIRST": _build_with_ignore_nulls(exp.First), 304 "FIRST_VALUE": _build_with_ignore_nulls(exp.FirstValue), 305 "FROM_UNIXTIME": build_formatted_time(exp.UnixToStr, "hive", True), 306 "GET_JSON_OBJECT": exp.JSONExtractScalar.from_arg_list, 307 "LAST": _build_with_ignore_nulls(exp.Last), 308 "LAST_VALUE": _build_with_ignore_nulls(exp.LastValue), 309 "LOCATE": locate_to_strposition, 310 "MAP": parser.build_var_map, 311 "MONTH": lambda args: exp.Month(this=exp.TsOrDsToDate.from_arg_list(args)), 312 "PERCENTILE": exp.Quantile.from_arg_list, 313 "PERCENTILE_APPROX": exp.ApproxQuantile.from_arg_list, 314 "REGEXP_EXTRACT": build_regexp_extract, 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 def _to_prop_eq(self, expression: exp.Expression, index: int) -> exp.Expression: 440 if isinstance(expression, exp.Column): 441 key = expression.this 442 else: 443 key = exp.to_identifier(f"col{index + 1}") 444 445 return self.expression(exp.PropertyEQ, this=key, expression=expression) 446 447 class Generator(generator.Generator): 448 LIMIT_FETCH = "LIMIT" 449 TABLESAMPLE_WITH_METHOD = False 450 JOIN_HINTS = False 451 TABLE_HINTS = False 452 QUERY_HINTS = False 453 INDEX_ON = "ON TABLE" 454 EXTRACT_ALLOWS_QUOTES = False 455 NVL2_SUPPORTED = False 456 LAST_DAY_SUPPORTS_DATE_PART = False 457 JSON_PATH_SINGLE_QUOTE_ESCAPE = True 458 SUPPORTS_TO_NUMBER = False 459 WITH_PROPERTIES_PREFIX = "TBLPROPERTIES" 460 PARSE_JSON_NAME = None 461 PAD_FILL_PATTERN_IS_REQUIRED = True 462 463 EXPRESSIONS_WITHOUT_NESTED_CTES = { 464 exp.Insert, 465 exp.Select, 466 exp.Subquery, 467 exp.SetOperation, 468 } 469 470 SUPPORTED_JSON_PATH_PARTS = { 471 exp.JSONPathKey, 472 exp.JSONPathRoot, 473 exp.JSONPathSubscript, 474 exp.JSONPathWildcard, 475 } 476 477 TYPE_MAPPING = { 478 **generator.Generator.TYPE_MAPPING, 479 exp.DataType.Type.BIT: "BOOLEAN", 480 exp.DataType.Type.DATETIME: "TIMESTAMP", 481 exp.DataType.Type.ROWVERSION: "BINARY", 482 exp.DataType.Type.TEXT: "STRING", 483 exp.DataType.Type.TIME: "TIMESTAMP", 484 exp.DataType.Type.TIMESTAMPTZ: "TIMESTAMP", 485 exp.DataType.Type.UTINYINT: "SMALLINT", 486 exp.DataType.Type.VARBINARY: "BINARY", 487 } 488 489 TRANSFORMS = { 490 **generator.Generator.TRANSFORMS, 491 exp.Group: transforms.preprocess([transforms.unalias_group]), 492 exp.Property: property_sql, 493 exp.AnyValue: rename_func("FIRST"), 494 exp.ApproxDistinct: approx_count_distinct_sql, 495 exp.ArgMax: arg_max_or_min_no_count("MAX_BY"), 496 exp.ArgMin: arg_max_or_min_no_count("MIN_BY"), 497 exp.ArrayConcat: rename_func("CONCAT"), 498 exp.ArrayToString: lambda self, e: self.func("CONCAT_WS", e.expression, e.this), 499 exp.ArraySize: rename_func("SIZE"), 500 exp.ArraySort: _array_sort_sql, 501 exp.With: no_recursive_cte_sql, 502 exp.DateAdd: _add_date_sql, 503 exp.DateDiff: _date_diff_sql, 504 exp.DateStrToDate: datestrtodate_sql, 505 exp.DateSub: _add_date_sql, 506 exp.DateToDi: lambda self, 507 e: f"CAST(DATE_FORMAT({self.sql(e, 'this')}, {Hive.DATEINT_FORMAT}) AS INT)", 508 exp.DiToDate: lambda self, 509 e: f"TO_DATE(CAST({self.sql(e, 'this')} AS STRING), {Hive.DATEINT_FORMAT})", 510 exp.FileFormatProperty: lambda self, 511 e: f"STORED AS {self.sql(e, 'this') if isinstance(e.this, exp.InputOutputFormat) else e.name.upper()}", 512 exp.FromBase64: rename_func("UNBASE64"), 513 exp.GenerateSeries: sequence_sql, 514 exp.GenerateDateArray: sequence_sql, 515 exp.If: if_sql(), 516 exp.ILike: no_ilike_sql, 517 exp.IsNan: rename_func("ISNAN"), 518 exp.JSONExtract: lambda self, e: self.func("GET_JSON_OBJECT", e.this, e.expression), 519 exp.JSONExtractScalar: lambda self, e: self.func( 520 "GET_JSON_OBJECT", e.this, e.expression 521 ), 522 exp.JSONFormat: _json_format_sql, 523 exp.Left: left_to_substring_sql, 524 exp.Map: var_map_sql, 525 exp.Max: max_or_greatest, 526 exp.MD5Digest: lambda self, e: self.func("UNHEX", self.func("MD5", e.this)), 527 exp.Min: min_or_least, 528 exp.MonthsBetween: lambda self, e: self.func("MONTHS_BETWEEN", e.this, e.expression), 529 exp.NotNullColumnConstraint: lambda _, e: ( 530 "" if e.args.get("allow_null") else "NOT NULL" 531 ), 532 exp.VarMap: var_map_sql, 533 exp.Create: preprocess( 534 [ 535 remove_unique_constraints, 536 ctas_with_tmp_tables_to_create_tmp_view, 537 move_schema_columns_to_partitioned_by, 538 ] 539 ), 540 exp.Quantile: rename_func("PERCENTILE"), 541 exp.ApproxQuantile: rename_func("PERCENTILE_APPROX"), 542 exp.RegexpExtract: regexp_extract_sql, 543 exp.RegexpReplace: regexp_replace_sql, 544 exp.RegexpLike: lambda self, e: self.binary(e, "RLIKE"), 545 exp.RegexpSplit: rename_func("SPLIT"), 546 exp.Right: right_to_substring_sql, 547 exp.SafeDivide: no_safe_divide_sql, 548 exp.SchemaCommentProperty: lambda self, e: self.naked_property(e), 549 exp.ArrayUniqueAgg: rename_func("COLLECT_SET"), 550 exp.Split: lambda self, e: self.func( 551 "SPLIT", e.this, self.func("CONCAT", "'\\\\Q'", e.expression) 552 ), 553 exp.Select: transforms.preprocess( 554 [ 555 transforms.eliminate_qualify, 556 transforms.eliminate_distinct_on, 557 partial(transforms.unnest_to_explode, unnest_using_arrays_zip=False), 558 ] 559 ), 560 exp.StrPosition: strposition_to_locate_sql, 561 exp.StrToDate: _str_to_date_sql, 562 exp.StrToTime: _str_to_time_sql, 563 exp.StrToUnix: _str_to_unix_sql, 564 exp.StructExtract: struct_extract_sql, 565 exp.Table: transforms.preprocess([transforms.unnest_generate_series]), 566 exp.TimeStrToDate: rename_func("TO_DATE"), 567 exp.TimeStrToTime: timestrtotime_sql, 568 exp.TimeStrToUnix: rename_func("UNIX_TIMESTAMP"), 569 exp.TimestampTrunc: lambda self, e: self.func("TRUNC", e.this, unit_to_str(e)), 570 exp.TimeToStr: lambda self, e: self.func("DATE_FORMAT", e.this, self.format_time(e)), 571 exp.TimeToUnix: rename_func("UNIX_TIMESTAMP"), 572 exp.ToBase64: rename_func("BASE64"), 573 exp.TsOrDiToDi: lambda self, 574 e: f"CAST(SUBSTR(REPLACE(CAST({self.sql(e, 'this')} AS STRING), '-', ''), 1, 8) AS INT)", 575 exp.TsOrDsAdd: _add_date_sql, 576 exp.TsOrDsDiff: _date_diff_sql, 577 exp.TsOrDsToDate: _to_date_sql, 578 exp.TryCast: no_trycast_sql, 579 exp.UnixToStr: lambda self, e: self.func( 580 "FROM_UNIXTIME", e.this, time_format("hive")(self, e) 581 ), 582 exp.UnixToTime: _unix_to_time_sql, 583 exp.UnixToTimeStr: rename_func("FROM_UNIXTIME"), 584 exp.Unnest: rename_func("EXPLODE"), 585 exp.PartitionedByProperty: lambda self, e: f"PARTITIONED BY {self.sql(e, 'this')}", 586 exp.NumberToStr: rename_func("FORMAT_NUMBER"), 587 exp.National: lambda self, e: self.national_sql(e, prefix=""), 588 exp.ClusteredColumnConstraint: lambda self, 589 e: f"({self.expressions(e, 'this', indent=False)})", 590 exp.NonClusteredColumnConstraint: lambda self, 591 e: f"({self.expressions(e, 'this', indent=False)})", 592 exp.NotForReplicationColumnConstraint: lambda *_: "", 593 exp.OnProperty: lambda *_: "", 594 exp.PrimaryKeyColumnConstraint: lambda *_: "PRIMARY KEY", 595 exp.WeekOfYear: rename_func("WEEKOFYEAR"), 596 exp.DayOfMonth: rename_func("DAYOFMONTH"), 597 exp.DayOfWeek: rename_func("DAYOFWEEK"), 598 } 599 600 PROPERTIES_LOCATION = { 601 **generator.Generator.PROPERTIES_LOCATION, 602 exp.FileFormatProperty: exp.Properties.Location.POST_SCHEMA, 603 exp.PartitionedByProperty: exp.Properties.Location.POST_SCHEMA, 604 exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED, 605 exp.WithDataProperty: exp.Properties.Location.UNSUPPORTED, 606 } 607 608 def unnest_sql(self, expression: exp.Unnest) -> str: 609 return rename_func("EXPLODE")(self, expression) 610 611 def _jsonpathkey_sql(self, expression: exp.JSONPathKey) -> str: 612 if isinstance(expression.this, exp.JSONPathWildcard): 613 self.unsupported("Unsupported wildcard in JSONPathKey expression") 614 return "" 615 616 return super()._jsonpathkey_sql(expression) 617 618 def parameter_sql(self, expression: exp.Parameter) -> str: 619 this = self.sql(expression, "this") 620 expression_sql = self.sql(expression, "expression") 621 622 parent = expression.parent 623 this = f"{this}:{expression_sql}" if expression_sql else this 624 625 if isinstance(parent, exp.EQ) and isinstance(parent.parent, exp.SetItem): 626 # We need to produce SET key = value instead of SET ${key} = value 627 return this 628 629 return f"${{{this}}}" 630 631 def schema_sql(self, expression: exp.Schema) -> str: 632 for ordered in expression.find_all(exp.Ordered): 633 if ordered.args.get("desc") is False: 634 ordered.set("desc", None) 635 636 return super().schema_sql(expression) 637 638 def constraint_sql(self, expression: exp.Constraint) -> str: 639 for prop in list(expression.find_all(exp.Properties)): 640 prop.pop() 641 642 this = self.sql(expression, "this") 643 expressions = self.expressions(expression, sep=" ", flat=True) 644 return f"CONSTRAINT {this} {expressions}" 645 646 def rowformatserdeproperty_sql(self, expression: exp.RowFormatSerdeProperty) -> str: 647 serde_props = self.sql(expression, "serde_properties") 648 serde_props = f" {serde_props}" if serde_props else "" 649 return f"ROW FORMAT SERDE {self.sql(expression, 'this')}{serde_props}" 650 651 def arrayagg_sql(self, expression: exp.ArrayAgg) -> str: 652 return self.func( 653 "COLLECT_LIST", 654 expression.this.this if isinstance(expression.this, exp.Order) else expression.this, 655 ) 656 657 def datatype_sql(self, expression: exp.DataType) -> str: 658 if expression.this in self.PARAMETERIZABLE_TEXT_TYPES and ( 659 not expression.expressions or expression.expressions[0].name == "MAX" 660 ): 661 expression = exp.DataType.build("text") 662 elif expression.is_type(exp.DataType.Type.TEXT) and expression.expressions: 663 expression.set("this", exp.DataType.Type.VARCHAR) 664 elif expression.this in exp.DataType.TEMPORAL_TYPES: 665 expression = exp.DataType.build(expression.this) 666 elif expression.is_type("float"): 667 size_expression = expression.find(exp.DataTypeParam) 668 if size_expression: 669 size = int(size_expression.name) 670 expression = ( 671 exp.DataType.build("float") if size <= 32 else exp.DataType.build("double") 672 ) 673 674 return super().datatype_sql(expression) 675 676 def version_sql(self, expression: exp.Version) -> str: 677 sql = super().version_sql(expression) 678 return sql.replace("FOR ", "", 1) 679 680 def struct_sql(self, expression: exp.Struct) -> str: 681 values = [] 682 683 for i, e in enumerate(expression.expressions): 684 if isinstance(e, exp.PropertyEQ): 685 self.unsupported("Hive does not support named structs.") 686 values.append(e.expression) 687 else: 688 values.append(e) 689 690 return self.func("STRUCT", *values) 691 692 def alterset_sql(self, expression: exp.AlterSet) -> str: 693 exprs = self.expressions(expression, flat=True) 694 exprs = f" {exprs}" if exprs else "" 695 location = self.sql(expression, "location") 696 location = f" LOCATION {location}" if location else "" 697 file_format = self.expressions(expression, key="file_format", flat=True, sep=" ") 698 file_format = f" FILEFORMAT {file_format}" if file_format else "" 699 serde = self.sql(expression, "serde") 700 serde = f" SERDE {serde}" if serde else "" 701 tags = self.expressions(expression, key="tag", flat=True, sep="") 702 tags = f" TAGS {tags}" if tags else "" 703 704 return f"SET{serde}{exprs}{location}{file_format}{tags}" 705 706 def serdeproperties_sql(self, expression: exp.SerdeProperties) -> str: 707 prefix = "WITH " if expression.args.get("with") else "" 708 exprs = self.expressions(expression, flat=True) 709 710 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
- HAS_DISTINCT_ARRAY_CONSTRUCTORS
- SUPPORTS_FIXED_SIZE_ARRAYS
- STRICT_JSON_PATH_SYNTAX
- ON_CONDITION_EMPTY_BEFORE_ERROR
- SET_OP_DISTINCT_BY_DEFAULT
- CREATABLE_KIND_MAPPING
- 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
239 class Tokenizer(tokens.Tokenizer): 240 QUOTES = ["'", '"'] 241 IDENTIFIERS = ["`"] 242 STRING_ESCAPES = ["\\"] 243 244 SINGLE_TOKENS = { 245 **tokens.Tokenizer.SINGLE_TOKENS, 246 "$": TokenType.PARAMETER, 247 } 248 249 KEYWORDS = { 250 **tokens.Tokenizer.KEYWORDS, 251 "ADD ARCHIVE": TokenType.COMMAND, 252 "ADD ARCHIVES": TokenType.COMMAND, 253 "ADD FILE": TokenType.COMMAND, 254 "ADD FILES": TokenType.COMMAND, 255 "ADD JAR": TokenType.COMMAND, 256 "ADD JARS": TokenType.COMMAND, 257 "MINUS": TokenType.EXCEPT, 258 "MSCK REPAIR": TokenType.COMMAND, 259 "REFRESH": TokenType.REFRESH, 260 "TIMESTAMP AS OF": TokenType.TIMESTAMP_SNAPSHOT, 261 "VERSION AS OF": TokenType.VERSION_SNAPSHOT, 262 "SERDEPROPERTIES": TokenType.SERDE_PROPERTIES, 263 } 264 265 NUMERIC_LITERALS = { 266 "L": "BIGINT", 267 "S": "SMALLINT", 268 "Y": "TINYINT", 269 "D": "DOUBLE", 270 "F": "FLOAT", 271 "BD": "DECIMAL", 272 }
SINGLE_TOKENS =
{'(': <TokenType.L_PAREN: 'L_PAREN'>, ')': <TokenType.R_PAREN: 'R_PAREN'>, '[': <TokenType.L_BRACKET: 'L_BRACKET'>, ']': <TokenType.R_BRACKET: 'R_BRACKET'>, '{': <TokenType.L_BRACE: 'L_BRACE'>, '}': <TokenType.R_BRACE: 'R_BRACE'>, '&': <TokenType.AMP: 'AMP'>, '^': <TokenType.CARET: 'CARET'>, ':': <TokenType.COLON: 'COLON'>, ',': <TokenType.COMMA: 'COMMA'>, '.': <TokenType.DOT: 'DOT'>, '-': <TokenType.DASH: 'DASH'>, '=': <TokenType.EQ: 'EQ'>, '>': <TokenType.GT: 'GT'>, '<': <TokenType.LT: 'LT'>, '%': <TokenType.MOD: 'MOD'>, '!': <TokenType.NOT: 'NOT'>, '|': <TokenType.PIPE: 'PIPE'>, '+': <TokenType.PLUS: 'PLUS'>, ';': <TokenType.SEMICOLON: 'SEMICOLON'>, '/': <TokenType.SLASH: 'SLASH'>, '\\': <TokenType.BACKSLASH: 'BACKSLASH'>, '*': <TokenType.STAR: 'STAR'>, '~': <TokenType.TILDA: 'TILDA'>, '?': <TokenType.PLACEHOLDER: 'PLACEHOLDER'>, '@': <TokenType.PARAMETER: 'PARAMETER'>, '#': <TokenType.HASH: 'HASH'>, "'": <TokenType.UNKNOWN: 'UNKNOWN'>, '`': <TokenType.UNKNOWN: 'UNKNOWN'>, '"': <TokenType.UNKNOWN: 'UNKNOWN'>, '$': <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'>, 'RENAME': <TokenType.RENAME: 'RENAME'>, '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'>, 'DECIMAL32': <TokenType.DECIMAL32: 'DECIMAL32'>, 'DECIMAL64': <TokenType.DECIMAL64: 'DECIMAL64'>, 'DECIMAL128': <TokenType.DECIMAL128: 'DECIMAL128'>, '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'>, 'MINUS': <TokenType.EXCEPT: 'EXCEPT'>, '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
- NESTED_COMMENTS
- WHITE_SPACE
- COMMANDS
- COMMAND_PREFIX_TOKENS
- COMMENTS
- dialect
- reset
- tokenize
- tokenize_rs
- size
- sql
- tokens
274 class Parser(parser.Parser): 275 LOG_DEFAULTS_TO_LN = True 276 STRICT_CAST = False 277 VALUES_FOLLOWED_BY_PAREN = False 278 279 FUNCTIONS = { 280 **parser.Parser.FUNCTIONS, 281 "BASE64": exp.ToBase64.from_arg_list, 282 "COLLECT_LIST": lambda args: exp.ArrayAgg(this=seq_get(args, 0), nulls_excluded=True), 283 "COLLECT_SET": exp.ArrayUniqueAgg.from_arg_list, 284 "DATE_ADD": lambda args: exp.TsOrDsAdd( 285 this=seq_get(args, 0), expression=seq_get(args, 1), unit=exp.Literal.string("DAY") 286 ), 287 "DATE_FORMAT": lambda args: build_formatted_time(exp.TimeToStr, "hive")( 288 [ 289 exp.TimeStrToTime(this=seq_get(args, 0)), 290 seq_get(args, 1), 291 ] 292 ), 293 "DATE_SUB": lambda args: exp.TsOrDsAdd( 294 this=seq_get(args, 0), 295 expression=exp.Mul(this=seq_get(args, 1), expression=exp.Literal.number(-1)), 296 unit=exp.Literal.string("DAY"), 297 ), 298 "DATEDIFF": lambda args: exp.DateDiff( 299 this=exp.TsOrDsToDate(this=seq_get(args, 0)), 300 expression=exp.TsOrDsToDate(this=seq_get(args, 1)), 301 ), 302 "DAY": lambda args: exp.Day(this=exp.TsOrDsToDate(this=seq_get(args, 0))), 303 "FIRST": _build_with_ignore_nulls(exp.First), 304 "FIRST_VALUE": _build_with_ignore_nulls(exp.FirstValue), 305 "FROM_UNIXTIME": build_formatted_time(exp.UnixToStr, "hive", True), 306 "GET_JSON_OBJECT": exp.JSONExtractScalar.from_arg_list, 307 "LAST": _build_with_ignore_nulls(exp.Last), 308 "LAST_VALUE": _build_with_ignore_nulls(exp.LastValue), 309 "LOCATE": locate_to_strposition, 310 "MAP": parser.build_var_map, 311 "MONTH": lambda args: exp.Month(this=exp.TsOrDsToDate.from_arg_list(args)), 312 "PERCENTILE": exp.Quantile.from_arg_list, 313 "PERCENTILE_APPROX": exp.ApproxQuantile.from_arg_list, 314 "REGEXP_EXTRACT": build_regexp_extract, 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 def _to_prop_eq(self, expression: exp.Expression, index: int) -> exp.Expression: 440 if isinstance(expression, exp.Column): 441 key = expression.this 442 else: 443 key = exp.to_identifier(f"col{index + 1}") 444 445 return self.expression(exp.PropertyEQ, this=key, 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': <function Parser.<lambda>>, 'ARRAY_AGG': <function Parser.<lambda>>, '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': <function build_coalesce>, 'IFNULL': <function build_coalesce>, 'NVL': <function build_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'>>, 'CONVERT_TIMEZONE': <function build_convert_timezone>, 'CORR': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Corr'>>, 'COUNT': <function Parser.<lambda>>, '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'>>, 'DAYOFWEEK_ISO': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DayOfWeekIso'>>, 'ISODOW': <bound method Func.from_arg_list of <class 'sqlglot.expressions.DayOfWeekIso'>>, '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'>>, 'EXPLODING_GENERATE_SERIES': <bound method Func.from_arg_list of <class 'sqlglot.expressions.ExplodingGenerateSeries'>>, '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'>>, 'FROM_ISO8601_TIMESTAMP': <bound method Func.from_arg_list of <class 'sqlglot.expressions.FromISO8601Timestamp'>>, 'GAP_FILL': <bound method Func.from_arg_list of <class 'sqlglot.expressions.GapFill'>>, 'GENERATE_DATE_ARRAY': <function Parser.<lambda>>, 'GENERATE_SERIES': <bound method Func.from_arg_list of <class 'sqlglot.expressions.GenerateSeries'>>, 'GENERATE_TIMESTAMP_ARRAY': <bound method Func.from_arg_list of <class 'sqlglot.expressions.GenerateTimestampArray'>>, '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'>>, 'INLINE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Inline'>>, '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'>>, 'J_S_O_N_EXISTS': <bound method Func.from_arg_list of <class 'sqlglot.expressions.JSONExists'>>, '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'>>, 'NORMALIZE': <bound method Func.from_arg_list of <class 'sqlglot.expressions.Normalize'>>, '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 build_regexp_extract>, '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>>, 'ARRAYAGG': <function 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>>, 'LTRIM': <function Parser.<lambda>>, 'MOD': <function build_mod>, 'RIGHTPAD': <function Parser.<lambda>>, 'RPAD': <function Parser.<lambda>>, 'RTRIM': <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': <function Hive.Parser.<lambda>>, '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>>, 'DISTRIBUTED': <function Parser.<lambda>>, 'DUPLICATE': <function Parser.<lambda>>, 'DYNAMIC': <function Parser.<lambda>>, 'DISTKEY': <function Parser.<lambda>>, 'DISTSTYLE': <function Parser.<lambda>>, 'EMPTY': <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>>, 'STREAMING': <function Parser.<lambda>>, 'ROW': <function Parser.<lambda>>, 'ROW_FORMAT': <function Parser.<lambda>>, 'SAMPLE': <function Parser.<lambda>>, 'SECURE': <function Parser.<lambda>>, 'SECURITY': <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.NULLABLE: 'NULLABLE'>, <TokenType.DIV: 'DIV'>, <TokenType.WINDOW: 'WINDOW'>, <TokenType.INT256: 'INT256'>, <TokenType.RANGE: 'RANGE'>, <TokenType.BINARY: 'BINARY'>, <TokenType.ENUM8: 'ENUM8'>, <TokenType.TSRANGE: 'TSRANGE'>, <TokenType.DATERANGE: 'DATERANGE'>, <TokenType.DATE: 'DATE'>, <TokenType.GEOGRAPHY: 'GEOGRAPHY'>, <TokenType.STREAMLIT: 'STREAMLIT'>, <TokenType.INTERVAL: 'INTERVAL'>, <TokenType.RENAME: 'RENAME'>, <TokenType.UNKNOWN: 'UNKNOWN'>, <TokenType.VARCHAR: 'VARCHAR'>, <TokenType.INT: 'INT'>, <TokenType.CURRENT_TIME: 'CURRENT_TIME'>, <TokenType.MAP: 'MAP'>, <TokenType.SETTINGS: 'SETTINGS'>, <TokenType.SMALLMONEY: 'SMALLMONEY'>, <TokenType.VARBINARY: 'VARBINARY'>, <TokenType.UDECIMAL: 'UDECIMAL'>, <TokenType.UUID: 'UUID'>, <TokenType.PERCENT: 'PERCENT'>, <TokenType.GEOMETRY: 'GEOMETRY'>, <TokenType.ARRAY: 'ARRAY'>, <TokenType.INT8MULTIRANGE: 'INT8MULTIRANGE'>, <TokenType.PARTITION: 'PARTITION'>, <TokenType.RECURSIVE: 'RECURSIVE'>, <TokenType.VOLATILE: 'VOLATILE'>, <TokenType.NUMMULTIRANGE: 'NUMMULTIRANGE'>, <TokenType.WAREHOUSE: 'WAREHOUSE'>, <TokenType.TINYTEXT: 'TINYTEXT'>, <TokenType.CURRENT_TIMESTAMP: 'CURRENT_TIMESTAMP'>, <TokenType.DATETIME64: 'DATETIME64'>, <TokenType.FOREIGN_KEY: 'FOREIGN_KEY'>, <TokenType.LEFT: 'LEFT'>, <TokenType.NEXT: 'NEXT'>, <TokenType.INDEX: 'INDEX'>, <TokenType.DECIMAL32: 'DECIMAL32'>, <TokenType.UNNEST: 'UNNEST'>, <TokenType.UNPIVOT: 'UNPIVOT'>, <TokenType.RIGHT: 'RIGHT'>, <TokenType.INET: 'INET'>, <TokenType.COMMAND: 'COMMAND'>, <TokenType.DELETE: 'DELETE'>, <TokenType.UINT: 'UINT'>, <TokenType.JSON: 'JSON'>, <TokenType.TIMESTAMP_S: 'TIMESTAMP_S'>, <TokenType.CURRENT_USER: 'CURRENT_USER'>, <TokenType.ASOF: 'ASOF'>, <TokenType.KILL: 'KILL'>, <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>, <TokenType.NAME: 'NAME'>, <TokenType.BIT: 'BIT'>, <TokenType.LOWCARDINALITY: 'LOWCARDINALITY'>, <TokenType.BPCHAR: 'BPCHAR'>, <TokenType.TINYBLOB: 'TINYBLOB'>, <TokenType.LIST: 'LIST'>, <TokenType.TIMESTAMP: 'TIMESTAMP'>, <TokenType.LONGTEXT: 'LONGTEXT'>, <TokenType.TDIGEST: 'TDIGEST'>, <TokenType.OPERATOR: 'OPERATOR'>, <TokenType.SERIAL: 'SERIAL'>, <TokenType.PIVOT: 'PIVOT'>, <TokenType.DICTIONARY: 'DICTIONARY'>, <TokenType.UINT128: 'UINT128'>, <TokenType.CURRENT_DATE: 'CURRENT_DATE'>, <TokenType.TABLE: 'TABLE'>, <TokenType.SET: 'SET'>, <TokenType.ANY: 'ANY'>, <TokenType.FULL: 'FULL'>, <TokenType.ANTI: 'ANTI'>, <TokenType.ASC: 'ASC'>, <TokenType.PRAGMA: 'PRAGMA'>, <TokenType.CHAR: 'CHAR'>, <TokenType.BOOLEAN: 'BOOLEAN'>, <TokenType.ISNULL: 'ISNULL'>, <TokenType.PROCEDURE: 'PROCEDURE'>, <TokenType.DATEMULTIRANGE: 'DATEMULTIRANGE'>, <TokenType.FINAL: 'FINAL'>, <TokenType.USE: 'USE'>, <TokenType.DESC: 'DESC'>, <TokenType.UNIQUE: 'UNIQUE'>, <TokenType.CASE: 'CASE'>, <TokenType.ORDINALITY: 'ORDINALITY'>, <TokenType.ENUM16: 'ENUM16'>, <TokenType.DESCRIBE: 'DESCRIBE'>, <TokenType.MEDIUMINT: 'MEDIUMINT'>, <TokenType.UTINYINT: 'UTINYINT'>, <TokenType.TEMPORARY: 'TEMPORARY'>, <TokenType.TIMETZ: 'TIMETZ'>, <TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>, <TokenType.XML: 'XML'>, <TokenType.IPV4: 'IPV4'>, <TokenType.BIGINT: 'BIGINT'>, <TokenType.NESTED: 'NESTED'>, <TokenType.DECIMAL64: 'DECIMAL64'>, <TokenType.ENUM: 'ENUM'>, <TokenType.BEGIN: 'BEGIN'>, <TokenType.ESCAPE: 'ESCAPE'>, <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>, <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, <TokenType.SOME: 'SOME'>, <TokenType.FORMAT: 'FORMAT'>, <TokenType.INT128: 'INT128'>, <TokenType.TSTZRANGE: 'TSTZRANGE'>, <TokenType.SHOW: 'SHOW'>, <TokenType.OVERWRITE: 'OVERWRITE'>, <TokenType.TIME: 'TIME'>, <TokenType.IS: 'IS'>, <TokenType.DATE32: 'DATE32'>, <TokenType.TIMESTAMP_MS: 'TIMESTAMP_MS'>, <TokenType.CACHE: 'CACHE'>, <TokenType.HSTORE: 'HSTORE'>, <TokenType.TSTZMULTIRANGE: 'TSTZMULTIRANGE'>, <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, <TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>, <TokenType.BIGSERIAL: 'BIGSERIAL'>, <TokenType.YEAR: 'YEAR'>, <TokenType.CUBE: 'CUBE'>, <TokenType.VIEW: 'VIEW'>, <TokenType.DECIMAL: 'DECIMAL'>, <TokenType.ALL: 'ALL'>, <TokenType.NCHAR: 'NCHAR'>, <TokenType.OVERLAPS: 'OVERLAPS'>, <TokenType.OBJECT: 'OBJECT'>, <TokenType.COMMENT: 'COMMENT'>, <TokenType.USMALLINT: 'USMALLINT'>, <TokenType.UINT256: 'UINT256'>, <TokenType.COMMIT: 'COMMIT'>, <TokenType.TINYINT: 'TINYINT'>, <TokenType.TIMESTAMP_NS: 'TIMESTAMP_NS'>, <TokenType.COPY: 'COPY'>, <TokenType.EXECUTE: 'EXECUTE'>, <TokenType.REFERENCES: 'REFERENCES'>, <TokenType.UPDATE: 'UPDATE'>, <TokenType.SEMI: 'SEMI'>, <TokenType.TAG: 'TAG'>, <TokenType.DOUBLE: 'DOUBLE'>, <TokenType.VECTOR: 'VECTOR'>, <TokenType.OFFSET: 'OFFSET'>, <TokenType.TRUNCATE: 'TRUNCATE'>, <TokenType.FALSE: 'FALSE'>, <TokenType.STRUCT: 'STRUCT'>, <TokenType.REFRESH: 'REFRESH'>, <TokenType.UBIGINT: 'UBIGINT'>, <TokenType.SCHEMA: 'SCHEMA'>, <TokenType.UMEDIUMINT: 'UMEDIUMINT'>, <TokenType.PSEUDO_TYPE: 'PSEUDO_TYPE'>, <TokenType.CONSTRAINT: 'CONSTRAINT'>, <TokenType.INT4RANGE: 'INT4RANGE'>, <TokenType.STRAIGHT_JOIN: 'STRAIGHT_JOIN'>, <TokenType.INT8RANGE: 'INT8RANGE'>, <TokenType.KEEP: 'KEEP'>, <TokenType.DATETIME: 'DATETIME'>, <TokenType.UNIQUEIDENTIFIER: 'UNIQUEIDENTIFIER'>, <TokenType.SMALLSERIAL: 'SMALLSERIAL'>, <TokenType.APPLY: 'APPLY'>, <TokenType.FLOAT: 'FLOAT'>, <TokenType.SUPER: 'SUPER'>, <TokenType.NATURAL: 'NATURAL'>, <TokenType.STORAGE_INTEGRATION: 'STORAGE_INTEGRATION'>, <TokenType.VARIANT: 'VARIANT'>, <TokenType.TSMULTIRANGE: 'TSMULTIRANGE'>, <TokenType.INT4MULTIRANGE: 'INT4MULTIRANGE'>, <TokenType.FILTER: 'FILTER'>, <TokenType.COLLATE: 'COLLATE'>, <TokenType.FUNCTION: 'FUNCTION'>, <TokenType.REPLACE: 'REPLACE'>, <TokenType.JSONB: 'JSONB'>, <TokenType.ROW: 'ROW'>, <TokenType.TOP: 'TOP'>, <TokenType.NULL: 'NULL'>, <TokenType.IDENTIFIER: 'IDENTIFIER'>, <TokenType.SIMPLEAGGREGATEFUNCTION: 'SIMPLEAGGREGATEFUNCTION'>, <TokenType.ROLLUP: 'ROLLUP'>, <TokenType.NUMRANGE: 'NUMRANGE'>, <TokenType.END: 'END'>, <TokenType.MERGE: 'MERGE'>, <TokenType.CURRENT_DATETIME: 'CURRENT_DATETIME'>, <TokenType.DATABASE: 'DATABASE'>, <TokenType.IPV6: 'IPV6'>, <TokenType.IPADDRESS: 'IPADDRESS'>, <TokenType.ROWVERSION: 'ROWVERSION'>, <TokenType.ROWS: 'ROWS'>, <TokenType.VAR: 'VAR'>, <TokenType.EXISTS: 'EXISTS'>, <TokenType.IPPREFIX: 'IPPREFIX'>, <TokenType.USERDEFINED: 'USERDEFINED'>, <TokenType.OBJECT_IDENTIFIER: 'OBJECT_IDENTIFIER'>, <TokenType.SEQUENCE: 'SEQUENCE'>, <TokenType.FIXEDSTRING: 'FIXEDSTRING'>, <TokenType.NVARCHAR: 'NVARCHAR'>, <TokenType.TEXT: 'TEXT'>, <TokenType.AGGREGATEFUNCTION: 'AGGREGATEFUNCTION'>, <TokenType.MODEL: 'MODEL'>, <TokenType.FIRST: 'FIRST'>, <TokenType.LONGBLOB: 'LONGBLOB'>, <TokenType.HLLSKETCH: 'HLLSKETCH'>, <TokenType.SMALLINT: 'SMALLINT'>, <TokenType.TIMESTAMPNTZ: 'TIMESTAMPNTZ'>, <TokenType.COLUMN: 'COLUMN'>, <TokenType.DECIMAL128: 'DECIMAL128'>, <TokenType.MONEY: 'MONEY'>, <TokenType.LOAD: 'LOAD'>, <TokenType.TRUE: 'TRUE'>, <TokenType.DEFAULT: 'DEFAULT'>, <TokenType.IMAGE: 'IMAGE'>}
TABLE_ALIAS_TOKENS =
{<TokenType.NULLABLE: 'NULLABLE'>, <TokenType.DIV: 'DIV'>, <TokenType.INT256: 'INT256'>, <TokenType.BINARY: 'BINARY'>, <TokenType.RANGE: 'RANGE'>, <TokenType.ENUM8: 'ENUM8'>, <TokenType.TSRANGE: 'TSRANGE'>, <TokenType.DATERANGE: 'DATERANGE'>, <TokenType.DATE: 'DATE'>, <TokenType.GEOGRAPHY: 'GEOGRAPHY'>, <TokenType.STREAMLIT: 'STREAMLIT'>, <TokenType.INTERVAL: 'INTERVAL'>, <TokenType.RENAME: 'RENAME'>, <TokenType.UNKNOWN: 'UNKNOWN'>, <TokenType.VARCHAR: 'VARCHAR'>, <TokenType.INT: 'INT'>, <TokenType.CURRENT_TIME: 'CURRENT_TIME'>, <TokenType.MAP: 'MAP'>, <TokenType.SETTINGS: 'SETTINGS'>, <TokenType.SMALLMONEY: 'SMALLMONEY'>, <TokenType.VARBINARY: 'VARBINARY'>, <TokenType.UDECIMAL: 'UDECIMAL'>, <TokenType.UUID: 'UUID'>, <TokenType.PERCENT: 'PERCENT'>, <TokenType.GEOMETRY: 'GEOMETRY'>, <TokenType.ARRAY: 'ARRAY'>, <TokenType.INT8MULTIRANGE: 'INT8MULTIRANGE'>, <TokenType.PARTITION: 'PARTITION'>, <TokenType.RECURSIVE: 'RECURSIVE'>, <TokenType.VOLATILE: 'VOLATILE'>, <TokenType.NUMMULTIRANGE: 'NUMMULTIRANGE'>, <TokenType.WAREHOUSE: 'WAREHOUSE'>, <TokenType.TINYTEXT: 'TINYTEXT'>, <TokenType.CURRENT_TIMESTAMP: 'CURRENT_TIMESTAMP'>, <TokenType.DATETIME64: 'DATETIME64'>, <TokenType.FOREIGN_KEY: 'FOREIGN_KEY'>, <TokenType.NEXT: 'NEXT'>, <TokenType.INDEX: 'INDEX'>, <TokenType.DECIMAL32: 'DECIMAL32'>, <TokenType.UNNEST: 'UNNEST'>, <TokenType.UNPIVOT: 'UNPIVOT'>, <TokenType.INET: 'INET'>, <TokenType.COMMAND: 'COMMAND'>, <TokenType.DELETE: 'DELETE'>, <TokenType.UINT: 'UINT'>, <TokenType.JSON: 'JSON'>, <TokenType.TIMESTAMP_S: 'TIMESTAMP_S'>, <TokenType.CURRENT_USER: 'CURRENT_USER'>, <TokenType.KILL: 'KILL'>, <TokenType.TIMESTAMPTZ: 'TIMESTAMPTZ'>, <TokenType.NAME: 'NAME'>, <TokenType.BIT: 'BIT'>, <TokenType.LOWCARDINALITY: 'LOWCARDINALITY'>, <TokenType.BPCHAR: 'BPCHAR'>, <TokenType.TINYBLOB: 'TINYBLOB'>, <TokenType.LIST: 'LIST'>, <TokenType.TIMESTAMP: 'TIMESTAMP'>, <TokenType.LONGTEXT: 'LONGTEXT'>, <TokenType.TDIGEST: 'TDIGEST'>, <TokenType.OPERATOR: 'OPERATOR'>, <TokenType.SERIAL: 'SERIAL'>, <TokenType.PIVOT: 'PIVOT'>, <TokenType.DICTIONARY: 'DICTIONARY'>, <TokenType.UINT128: 'UINT128'>, <TokenType.CURRENT_DATE: 'CURRENT_DATE'>, <TokenType.TABLE: 'TABLE'>, <TokenType.SET: 'SET'>, <TokenType.ANY: 'ANY'>, <TokenType.ASC: 'ASC'>, <TokenType.PRAGMA: 'PRAGMA'>, <TokenType.CHAR: 'CHAR'>, <TokenType.BOOLEAN: 'BOOLEAN'>, <TokenType.ISNULL: 'ISNULL'>, <TokenType.PROCEDURE: 'PROCEDURE'>, <TokenType.DATEMULTIRANGE: 'DATEMULTIRANGE'>, <TokenType.FINAL: 'FINAL'>, <TokenType.USE: 'USE'>, <TokenType.DESC: 'DESC'>, <TokenType.UNIQUE: 'UNIQUE'>, <TokenType.CASE: 'CASE'>, <TokenType.ORDINALITY: 'ORDINALITY'>, <TokenType.ENUM16: 'ENUM16'>, <TokenType.DESCRIBE: 'DESCRIBE'>, <TokenType.MEDIUMINT: 'MEDIUMINT'>, <TokenType.UTINYINT: 'UTINYINT'>, <TokenType.TEMPORARY: 'TEMPORARY'>, <TokenType.TIMETZ: 'TIMETZ'>, <TokenType.MEDIUMTEXT: 'MEDIUMTEXT'>, <TokenType.XML: 'XML'>, <TokenType.IPV4: 'IPV4'>, <TokenType.BIGINT: 'BIGINT'>, <TokenType.NESTED: 'NESTED'>, <TokenType.DECIMAL64: 'DECIMAL64'>, <TokenType.ENUM: 'ENUM'>, <TokenType.BEGIN: 'BEGIN'>, <TokenType.ESCAPE: 'ESCAPE'>, <TokenType.TIMESTAMPLTZ: 'TIMESTAMPLTZ'>, <TokenType.BIGDECIMAL: 'BIGDECIMAL'>, <TokenType.SOME: 'SOME'>, <TokenType.FORMAT: 'FORMAT'>, <TokenType.INT128: 'INT128'>, <TokenType.TSTZRANGE: 'TSTZRANGE'>, <TokenType.SHOW: 'SHOW'>, <TokenType.OVERWRITE: 'OVERWRITE'>, <TokenType.TIME: 'TIME'>, <TokenType.IS: 'IS'>, <TokenType.DATE32: 'DATE32'>, <TokenType.TIMESTAMP_MS: 'TIMESTAMP_MS'>, <TokenType.CACHE: 'CACHE'>, <TokenType.HSTORE: 'HSTORE'>, <TokenType.TSTZMULTIRANGE: 'TSTZMULTIRANGE'>, <TokenType.AUTO_INCREMENT: 'AUTO_INCREMENT'>, <TokenType.MEDIUMBLOB: 'MEDIUMBLOB'>, <TokenType.BIGSERIAL: 'BIGSERIAL'>, <TokenType.YEAR: 'YEAR'>, <TokenType.CUBE: 'CUBE'>, <TokenType.VIEW: 'VIEW'>, <TokenType.DECIMAL: 'DECIMAL'>, <TokenType.ALL: 'ALL'>, <TokenType.NCHAR: 'NCHAR'>, <TokenType.OVERLAPS: 'OVERLAPS'>, <TokenType.OBJECT: 'OBJECT'>, <TokenType.COMMENT: 'COMMENT'>, <TokenType.USMALLINT: 'USMALLINT'>, <TokenType.UINT256: 'UINT256'>, <TokenType.COMMIT: 'COMMIT'>, <TokenType.TINYINT: 'TINYINT'>, <TokenType.TIMESTAMP_NS: 'TIMESTAMP_NS'>, <TokenType.COPY: 'COPY'>, <TokenType.EXECUTE: 'EXECUTE'>, <TokenType.REFERENCES: 'REFERENCES'>, <TokenType.UPDATE: 'UPDATE'>, <TokenType.TAG: 'TAG'>, <TokenType.DOUBLE: 'DOUBLE'>, <TokenType.VECTOR: 'VECTOR'>, <TokenType.TRUNCATE: 'TRUNCATE'>, <TokenType.FALSE: 'FALSE'>, <TokenType.STRUCT: 'STRUCT'>, <TokenType.REFRESH: 'REFRESH'>, <TokenType.UBIGINT: 'UBIGINT'>, <TokenType.SCHEMA: 'SCHEMA'>, <TokenType.UMEDIUMINT: 'UMEDIUMINT'>, <TokenType.PSEUDO_TYPE: 'PSEUDO_TYPE'>, <TokenType.CONSTRAINT: 'CONSTRAINT'>, <TokenType.INT4RANGE: 'INT4RANGE'>, <TokenType.STRAIGHT_JOIN: 'STRAIGHT_JOIN'>, <TokenType.INT8RANGE: 'INT8RANGE'>, <TokenType.KEEP: 'KEEP'>, <TokenType.DATETIME: 'DATETIME'>, <TokenType.UNIQUEIDENTIFIER: 'UNIQUEIDENTIFIER'>, <TokenType.SMALLSERIAL: 'SMALLSERIAL'>, <TokenType.FLOAT: 'FLOAT'>, <TokenType.SUPER: 'SUPER'>, <TokenType.STORAGE_INTEGRATION: 'STORAGE_INTEGRATION'>, <TokenType.VARIANT: 'VARIANT'>, <TokenType.TSMULTIRANGE: 'TSMULTIRANGE'>, <TokenType.INT4MULTIRANGE: 'INT4MULTIRANGE'>, <TokenType.FILTER: 'FILTER'>, <TokenType.COLLATE: 'COLLATE'>, <TokenType.FUNCTION: 'FUNCTION'>, <TokenType.REPLACE: 'REPLACE'>, <TokenType.JSONB: 'JSONB'>, <TokenType.ROW: 'ROW'>, <TokenType.TOP: 'TOP'>, <TokenType.NULL: 'NULL'>, <TokenType.IDENTIFIER: 'IDENTIFIER'>, <TokenType.SIMPLEAGGREGATEFUNCTION: 'SIMPLEAGGREGATEFUNCTION'>, <TokenType.ROLLUP: 'ROLLUP'>, <TokenType.NUMRANGE: 'NUMRANGE'>, <TokenType.END: 'END'>, <TokenType.MERGE: 'MERGE'>, <TokenType.CURRENT_DATETIME: 'CURRENT_DATETIME'>, <TokenType.DATABASE: 'DATABASE'>, <TokenType.IPV6: 'IPV6'>, <TokenType.IPADDRESS: 'IPADDRESS'>, <TokenType.ROWVERSION: 'ROWVERSION'>, <TokenType.ROWS: 'ROWS'>, <TokenType.VAR: 'VAR'>, <TokenType.EXISTS: 'EXISTS'>, <TokenType.IPPREFIX: 'IPPREFIX'>, <TokenType.USERDEFINED: 'USERDEFINED'>, <TokenType.OBJECT_IDENTIFIER: 'OBJECT_IDENTIFIER'>, <TokenType.SEQUENCE: 'SEQUENCE'>, <TokenType.FIXEDSTRING: 'FIXEDSTRING'>, <TokenType.NVARCHAR: 'NVARCHAR'>, <TokenType.TEXT: 'TEXT'>, <TokenType.AGGREGATEFUNCTION: 'AGGREGATEFUNCTION'>, <TokenType.MODEL: 'MODEL'>, <TokenType.FIRST: 'FIRST'>, <TokenType.LONGBLOB: 'LONGBLOB'>, <TokenType.HLLSKETCH: 'HLLSKETCH'>, <TokenType.SMALLINT: 'SMALLINT'>, <TokenType.TIMESTAMPNTZ: 'TIMESTAMPNTZ'>, <TokenType.COLUMN: 'COLUMN'>, <TokenType.DECIMAL128: 'DECIMAL128'>, <TokenType.MONEY: 'MONEY'>, <TokenType.LOAD: 'LOAD'>, <TokenType.TRUE: 'TRUE'>, <TokenType.DEFAULT: 'DEFAULT'>, <TokenType.IMAGE: 'IMAGE'>}
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
- ALTERABLES
- 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
- IS_JSON_PREDICATE_KIND
- ODBC_DATETIME_LITERALS
- ON_CONDITION_TOKENS
- 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
447 class Generator(generator.Generator): 448 LIMIT_FETCH = "LIMIT" 449 TABLESAMPLE_WITH_METHOD = False 450 JOIN_HINTS = False 451 TABLE_HINTS = False 452 QUERY_HINTS = False 453 INDEX_ON = "ON TABLE" 454 EXTRACT_ALLOWS_QUOTES = False 455 NVL2_SUPPORTED = False 456 LAST_DAY_SUPPORTS_DATE_PART = False 457 JSON_PATH_SINGLE_QUOTE_ESCAPE = True 458 SUPPORTS_TO_NUMBER = False 459 WITH_PROPERTIES_PREFIX = "TBLPROPERTIES" 460 PARSE_JSON_NAME = None 461 PAD_FILL_PATTERN_IS_REQUIRED = True 462 463 EXPRESSIONS_WITHOUT_NESTED_CTES = { 464 exp.Insert, 465 exp.Select, 466 exp.Subquery, 467 exp.SetOperation, 468 } 469 470 SUPPORTED_JSON_PATH_PARTS = { 471 exp.JSONPathKey, 472 exp.JSONPathRoot, 473 exp.JSONPathSubscript, 474 exp.JSONPathWildcard, 475 } 476 477 TYPE_MAPPING = { 478 **generator.Generator.TYPE_MAPPING, 479 exp.DataType.Type.BIT: "BOOLEAN", 480 exp.DataType.Type.DATETIME: "TIMESTAMP", 481 exp.DataType.Type.ROWVERSION: "BINARY", 482 exp.DataType.Type.TEXT: "STRING", 483 exp.DataType.Type.TIME: "TIMESTAMP", 484 exp.DataType.Type.TIMESTAMPTZ: "TIMESTAMP", 485 exp.DataType.Type.UTINYINT: "SMALLINT", 486 exp.DataType.Type.VARBINARY: "BINARY", 487 } 488 489 TRANSFORMS = { 490 **generator.Generator.TRANSFORMS, 491 exp.Group: transforms.preprocess([transforms.unalias_group]), 492 exp.Property: property_sql, 493 exp.AnyValue: rename_func("FIRST"), 494 exp.ApproxDistinct: approx_count_distinct_sql, 495 exp.ArgMax: arg_max_or_min_no_count("MAX_BY"), 496 exp.ArgMin: arg_max_or_min_no_count("MIN_BY"), 497 exp.ArrayConcat: rename_func("CONCAT"), 498 exp.ArrayToString: lambda self, e: self.func("CONCAT_WS", e.expression, e.this), 499 exp.ArraySize: rename_func("SIZE"), 500 exp.ArraySort: _array_sort_sql, 501 exp.With: no_recursive_cte_sql, 502 exp.DateAdd: _add_date_sql, 503 exp.DateDiff: _date_diff_sql, 504 exp.DateStrToDate: datestrtodate_sql, 505 exp.DateSub: _add_date_sql, 506 exp.DateToDi: lambda self, 507 e: f"CAST(DATE_FORMAT({self.sql(e, 'this')}, {Hive.DATEINT_FORMAT}) AS INT)", 508 exp.DiToDate: lambda self, 509 e: f"TO_DATE(CAST({self.sql(e, 'this')} AS STRING), {Hive.DATEINT_FORMAT})", 510 exp.FileFormatProperty: lambda self, 511 e: f"STORED AS {self.sql(e, 'this') if isinstance(e.this, exp.InputOutputFormat) else e.name.upper()}", 512 exp.FromBase64: rename_func("UNBASE64"), 513 exp.GenerateSeries: sequence_sql, 514 exp.GenerateDateArray: sequence_sql, 515 exp.If: if_sql(), 516 exp.ILike: no_ilike_sql, 517 exp.IsNan: rename_func("ISNAN"), 518 exp.JSONExtract: lambda self, e: self.func("GET_JSON_OBJECT", e.this, e.expression), 519 exp.JSONExtractScalar: lambda self, e: self.func( 520 "GET_JSON_OBJECT", e.this, e.expression 521 ), 522 exp.JSONFormat: _json_format_sql, 523 exp.Left: left_to_substring_sql, 524 exp.Map: var_map_sql, 525 exp.Max: max_or_greatest, 526 exp.MD5Digest: lambda self, e: self.func("UNHEX", self.func("MD5", e.this)), 527 exp.Min: min_or_least, 528 exp.MonthsBetween: lambda self, e: self.func("MONTHS_BETWEEN", e.this, e.expression), 529 exp.NotNullColumnConstraint: lambda _, e: ( 530 "" if e.args.get("allow_null") else "NOT NULL" 531 ), 532 exp.VarMap: var_map_sql, 533 exp.Create: preprocess( 534 [ 535 remove_unique_constraints, 536 ctas_with_tmp_tables_to_create_tmp_view, 537 move_schema_columns_to_partitioned_by, 538 ] 539 ), 540 exp.Quantile: rename_func("PERCENTILE"), 541 exp.ApproxQuantile: rename_func("PERCENTILE_APPROX"), 542 exp.RegexpExtract: regexp_extract_sql, 543 exp.RegexpReplace: regexp_replace_sql, 544 exp.RegexpLike: lambda self, e: self.binary(e, "RLIKE"), 545 exp.RegexpSplit: rename_func("SPLIT"), 546 exp.Right: right_to_substring_sql, 547 exp.SafeDivide: no_safe_divide_sql, 548 exp.SchemaCommentProperty: lambda self, e: self.naked_property(e), 549 exp.ArrayUniqueAgg: rename_func("COLLECT_SET"), 550 exp.Split: lambda self, e: self.func( 551 "SPLIT", e.this, self.func("CONCAT", "'\\\\Q'", e.expression) 552 ), 553 exp.Select: transforms.preprocess( 554 [ 555 transforms.eliminate_qualify, 556 transforms.eliminate_distinct_on, 557 partial(transforms.unnest_to_explode, unnest_using_arrays_zip=False), 558 ] 559 ), 560 exp.StrPosition: strposition_to_locate_sql, 561 exp.StrToDate: _str_to_date_sql, 562 exp.StrToTime: _str_to_time_sql, 563 exp.StrToUnix: _str_to_unix_sql, 564 exp.StructExtract: struct_extract_sql, 565 exp.Table: transforms.preprocess([transforms.unnest_generate_series]), 566 exp.TimeStrToDate: rename_func("TO_DATE"), 567 exp.TimeStrToTime: timestrtotime_sql, 568 exp.TimeStrToUnix: rename_func("UNIX_TIMESTAMP"), 569 exp.TimestampTrunc: lambda self, e: self.func("TRUNC", e.this, unit_to_str(e)), 570 exp.TimeToStr: lambda self, e: self.func("DATE_FORMAT", e.this, self.format_time(e)), 571 exp.TimeToUnix: rename_func("UNIX_TIMESTAMP"), 572 exp.ToBase64: rename_func("BASE64"), 573 exp.TsOrDiToDi: lambda self, 574 e: f"CAST(SUBSTR(REPLACE(CAST({self.sql(e, 'this')} AS STRING), '-', ''), 1, 8) AS INT)", 575 exp.TsOrDsAdd: _add_date_sql, 576 exp.TsOrDsDiff: _date_diff_sql, 577 exp.TsOrDsToDate: _to_date_sql, 578 exp.TryCast: no_trycast_sql, 579 exp.UnixToStr: lambda self, e: self.func( 580 "FROM_UNIXTIME", e.this, time_format("hive")(self, e) 581 ), 582 exp.UnixToTime: _unix_to_time_sql, 583 exp.UnixToTimeStr: rename_func("FROM_UNIXTIME"), 584 exp.Unnest: rename_func("EXPLODE"), 585 exp.PartitionedByProperty: lambda self, e: f"PARTITIONED BY {self.sql(e, 'this')}", 586 exp.NumberToStr: rename_func("FORMAT_NUMBER"), 587 exp.National: lambda self, e: self.national_sql(e, prefix=""), 588 exp.ClusteredColumnConstraint: lambda self, 589 e: f"({self.expressions(e, 'this', indent=False)})", 590 exp.NonClusteredColumnConstraint: lambda self, 591 e: f"({self.expressions(e, 'this', indent=False)})", 592 exp.NotForReplicationColumnConstraint: lambda *_: "", 593 exp.OnProperty: lambda *_: "", 594 exp.PrimaryKeyColumnConstraint: lambda *_: "PRIMARY KEY", 595 exp.WeekOfYear: rename_func("WEEKOFYEAR"), 596 exp.DayOfMonth: rename_func("DAYOFMONTH"), 597 exp.DayOfWeek: rename_func("DAYOFWEEK"), 598 } 599 600 PROPERTIES_LOCATION = { 601 **generator.Generator.PROPERTIES_LOCATION, 602 exp.FileFormatProperty: exp.Properties.Location.POST_SCHEMA, 603 exp.PartitionedByProperty: exp.Properties.Location.POST_SCHEMA, 604 exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED, 605 exp.WithDataProperty: exp.Properties.Location.UNSUPPORTED, 606 } 607 608 def unnest_sql(self, expression: exp.Unnest) -> str: 609 return rename_func("EXPLODE")(self, expression) 610 611 def _jsonpathkey_sql(self, expression: exp.JSONPathKey) -> str: 612 if isinstance(expression.this, exp.JSONPathWildcard): 613 self.unsupported("Unsupported wildcard in JSONPathKey expression") 614 return "" 615 616 return super()._jsonpathkey_sql(expression) 617 618 def parameter_sql(self, expression: exp.Parameter) -> str: 619 this = self.sql(expression, "this") 620 expression_sql = self.sql(expression, "expression") 621 622 parent = expression.parent 623 this = f"{this}:{expression_sql}" if expression_sql else this 624 625 if isinstance(parent, exp.EQ) and isinstance(parent.parent, exp.SetItem): 626 # We need to produce SET key = value instead of SET ${key} = value 627 return this 628 629 return f"${{{this}}}" 630 631 def schema_sql(self, expression: exp.Schema) -> str: 632 for ordered in expression.find_all(exp.Ordered): 633 if ordered.args.get("desc") is False: 634 ordered.set("desc", None) 635 636 return super().schema_sql(expression) 637 638 def constraint_sql(self, expression: exp.Constraint) -> str: 639 for prop in list(expression.find_all(exp.Properties)): 640 prop.pop() 641 642 this = self.sql(expression, "this") 643 expressions = self.expressions(expression, sep=" ", flat=True) 644 return f"CONSTRAINT {this} {expressions}" 645 646 def rowformatserdeproperty_sql(self, expression: exp.RowFormatSerdeProperty) -> str: 647 serde_props = self.sql(expression, "serde_properties") 648 serde_props = f" {serde_props}" if serde_props else "" 649 return f"ROW FORMAT SERDE {self.sql(expression, 'this')}{serde_props}" 650 651 def arrayagg_sql(self, expression: exp.ArrayAgg) -> str: 652 return self.func( 653 "COLLECT_LIST", 654 expression.this.this if isinstance(expression.this, exp.Order) else expression.this, 655 ) 656 657 def datatype_sql(self, expression: exp.DataType) -> str: 658 if expression.this in self.PARAMETERIZABLE_TEXT_TYPES and ( 659 not expression.expressions or expression.expressions[0].name == "MAX" 660 ): 661 expression = exp.DataType.build("text") 662 elif expression.is_type(exp.DataType.Type.TEXT) and expression.expressions: 663 expression.set("this", exp.DataType.Type.VARCHAR) 664 elif expression.this in exp.DataType.TEMPORAL_TYPES: 665 expression = exp.DataType.build(expression.this) 666 elif expression.is_type("float"): 667 size_expression = expression.find(exp.DataTypeParam) 668 if size_expression: 669 size = int(size_expression.name) 670 expression = ( 671 exp.DataType.build("float") if size <= 32 else exp.DataType.build("double") 672 ) 673 674 return super().datatype_sql(expression) 675 676 def version_sql(self, expression: exp.Version) -> str: 677 sql = super().version_sql(expression) 678 return sql.replace("FOR ", "", 1) 679 680 def struct_sql(self, expression: exp.Struct) -> str: 681 values = [] 682 683 for i, e in enumerate(expression.expressions): 684 if isinstance(e, exp.PropertyEQ): 685 self.unsupported("Hive does not support named structs.") 686 values.append(e.expression) 687 else: 688 values.append(e) 689 690 return self.func("STRUCT", *values) 691 692 def alterset_sql(self, expression: exp.AlterSet) -> str: 693 exprs = self.expressions(expression, flat=True) 694 exprs = f" {exprs}" if exprs else "" 695 location = self.sql(expression, "location") 696 location = f" LOCATION {location}" if location else "" 697 file_format = self.expressions(expression, key="file_format", flat=True, sep=" ") 698 file_format = f" FILEFORMAT {file_format}" if file_format else "" 699 serde = self.sql(expression, "serde") 700 serde = f" SERDE {serde}" if serde else "" 701 tags = self.expressions(expression, key="tag", flat=True, sep="") 702 tags = f" TAGS {tags}" if tags else "" 703 704 return f"SET{serde}{exprs}{location}{file_format}{tags}" 705 706 def serdeproperties_sql(self, expression: exp.SerdeProperties) -> str: 707 prefix = "WITH " if expression.args.get("with") else "" 708 exprs = self.expressions(expression, flat=True) 709 710 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
WHEREclause. 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.Subquery'>, <class 'sqlglot.expressions.Select'>, <class 'sqlglot.expressions.Insert'>, <class 'sqlglot.expressions.SetOperation'>}
SUPPORTED_JSON_PATH_PARTS =
{<class 'sqlglot.expressions.JSONPathWildcard'>, <class 'sqlglot.expressions.JSONPathKey'>, <class 'sqlglot.expressions.JSONPathRoot'>, <class 'sqlglot.expressions.JSONPathSubscript'>}
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.EmptyProperty'>: <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.Except'>: <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.Intersect'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.IntervalSpan'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.LanguageProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.LocationProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.LogProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.MaterializedProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.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.Operator'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.OutputModelProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.PathColumnConstraint'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.PivotAny'>: <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.SecurityProperty'>: <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.Stream'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.StreamingTableProperty'>: <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.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.Union'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.UnloggedProperty'>: <function Generator.<lambda>>, <class 'sqlglot.expressions.UppercaseColumnConstraint'>: <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.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.GenerateDateArray'>: <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.JSONExtract'>: <function Hive.Generator.<lambda>>, <class 'sqlglot.expressions.JSONExtractScalar'>: <function Hive.Generator.<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.Select'>: <function preprocess.<locals>._to_sql>, <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.Table'>: <function preprocess.<locals>._to_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.Unnest'>: <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.DistributedByProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.DuplicateKeyProperty'>: <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.EmptyProperty'>: <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.SecurityProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SerdeProperties'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.Set'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SettingsProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SetProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.SetConfigProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SharingProperty'>: <Location.POST_EXPRESSION: 'POST_EXPRESSION'>, <class 'sqlglot.expressions.SequenceProperties'>: <Location.POST_EXPRESSION: 'POST_EXPRESSION'>, <class 'sqlglot.expressions.SortKeyProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SqlReadWriteProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.SqlSecurityProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <class 'sqlglot.expressions.StabilityProperty'>: <Location.POST_SCHEMA: 'POST_SCHEMA'>, <class 'sqlglot.expressions.StreamingTableProperty'>: <Location.POST_CREATE: 'POST_CREATE'>, <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'>}
618 def parameter_sql(self, expression: exp.Parameter) -> str: 619 this = self.sql(expression, "this") 620 expression_sql = self.sql(expression, "expression") 621 622 parent = expression.parent 623 this = f"{this}:{expression_sql}" if expression_sql else this 624 625 if isinstance(parent, exp.EQ) and isinstance(parent.parent, exp.SetItem): 626 # We need to produce SET key = value instead of SET ${key} = value 627 return this 628 629 return f"${{{this}}}"
def
rowformatserdeproperty_sql(self, expression: sqlglot.expressions.RowFormatSerdeProperty) -> str:
657 def datatype_sql(self, expression: exp.DataType) -> str: 658 if expression.this in self.PARAMETERIZABLE_TEXT_TYPES and ( 659 not expression.expressions or expression.expressions[0].name == "MAX" 660 ): 661 expression = exp.DataType.build("text") 662 elif expression.is_type(exp.DataType.Type.TEXT) and expression.expressions: 663 expression.set("this", exp.DataType.Type.VARCHAR) 664 elif expression.this in exp.DataType.TEMPORAL_TYPES: 665 expression = exp.DataType.build(expression.this) 666 elif expression.is_type("float"): 667 size_expression = expression.find(exp.DataTypeParam) 668 if size_expression: 669 size = int(size_expression.name) 670 expression = ( 671 exp.DataType.build("float") if size <= 32 else exp.DataType.build("double") 672 ) 673 674 return super().datatype_sql(expression)
680 def struct_sql(self, expression: exp.Struct) -> str: 681 values = [] 682 683 for i, e in enumerate(expression.expressions): 684 if isinstance(e, exp.PropertyEQ): 685 self.unsupported("Hive does not support named structs.") 686 values.append(e.expression) 687 else: 688 values.append(e) 689 690 return self.func("STRUCT", *values)
692 def alterset_sql(self, expression: exp.AlterSet) -> str: 693 exprs = self.expressions(expression, flat=True) 694 exprs = f" {exprs}" if exprs else "" 695 location = self.sql(expression, "location") 696 location = f" LOCATION {location}" if location else "" 697 file_format = self.expressions(expression, key="file_format", flat=True, sep=" ") 698 file_format = f" FILEFORMAT {file_format}" if file_format else "" 699 serde = self.sql(expression, "serde") 700 serde = f" SERDE {serde}" if serde else "" 701 tags = self.expressions(expression, key="tag", flat=True, sep="") 702 tags = f" TAGS {tags}" if tags else "" 703 704 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
- EXCEPT_INTERSECT_SUPPORT_ALL_CLAUSE
- 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
- SUPPORTS_EXPLODING_PROJECTIONS
- ARRAY_CONCAT_IS_VAR_LEN
- SUPPORTS_CONVERT_TIMEZONE
- 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
- set_operation
- set_operations
- 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
- 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
- groupingsets_sql
- rollup_sql
- cube_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
- 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
- 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
- alter_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
- duplicatekeyproperty_sql
- distributedbyproperty_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
- toarray_sql
- tsordstotime_sql
- tsordstotimestamp_sql
- tsordstodate_sql
- unixdate_sql
- lastday_sql
- dateadd_sql
- arrayany_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
- rand_sql
- changes_sql
- pad_sql
- summarize_sql
- explodinggenerateseries_sql
- arrayconcat_sql
- converttimezone_sql
- json_sql
- jsonvalue_sql
- conditionalinsert_sql
- multitableinserts_sql
- oncondition_sql
- jsonexists_sql