sqlglot.dialects.mysql
1from __future__ import annotations 2 3import typing as t 4 5from sqlglot import exp, generator, parser, tokens, transforms 6from sqlglot.dialects.dialect import ( 7 Dialect, 8 arrow_json_extract_scalar_sql, 9 datestrtodate_sql, 10 format_time_lambda, 11 locate_to_strposition, 12 max_or_greatest, 13 min_or_least, 14 no_ilike_sql, 15 no_paren_current_date_sql, 16 no_pivot_sql, 17 no_tablesample_sql, 18 no_trycast_sql, 19 parse_date_delta_with_interval, 20 rename_func, 21 strposition_to_locate_sql, 22) 23from sqlglot.helper import seq_get 24from sqlglot.tokens import TokenType 25 26 27def _show_parser(*args: t.Any, **kwargs: t.Any) -> t.Callable[[MySQL.Parser], exp.Show]: 28 def _parse(self: MySQL.Parser) -> exp.Show: 29 return self._parse_show_mysql(*args, **kwargs) 30 31 return _parse 32 33 34def _date_trunc_sql(self: generator.Generator, expression: exp.DateTrunc) -> str: 35 expr = self.sql(expression, "this") 36 unit = expression.text("unit") 37 38 if unit == "day": 39 return f"DATE({expr})" 40 41 if unit == "week": 42 concat = f"CONCAT(YEAR({expr}), ' ', WEEK({expr}, 1), ' 1')" 43 date_format = "%Y %u %w" 44 elif unit == "month": 45 concat = f"CONCAT(YEAR({expr}), ' ', MONTH({expr}), ' 1')" 46 date_format = "%Y %c %e" 47 elif unit == "quarter": 48 concat = f"CONCAT(YEAR({expr}), ' ', QUARTER({expr}) * 3 - 2, ' 1')" 49 date_format = "%Y %c %e" 50 elif unit == "year": 51 concat = f"CONCAT(YEAR({expr}), ' 1 1')" 52 date_format = "%Y %c %e" 53 else: 54 self.unsupported(f"Unexpected interval unit: {unit}") 55 return f"DATE({expr})" 56 57 return f"STR_TO_DATE({concat}, '{date_format}')" 58 59 60def _str_to_date(args: t.List) -> exp.StrToDate: 61 date_format = MySQL.format_time(seq_get(args, 1)) 62 return exp.StrToDate(this=seq_get(args, 0), format=date_format) 63 64 65def _str_to_date_sql(self: generator.Generator, expression: exp.StrToDate | exp.StrToTime) -> str: 66 date_format = self.format_time(expression) 67 return f"STR_TO_DATE({self.sql(expression.this)}, {date_format})" 68 69 70def _trim_sql(self: generator.Generator, expression: exp.Trim) -> str: 71 target = self.sql(expression, "this") 72 trim_type = self.sql(expression, "position") 73 remove_chars = self.sql(expression, "expression") 74 75 # Use TRIM/LTRIM/RTRIM syntax if the expression isn't mysql-specific 76 if not remove_chars: 77 return self.trim_sql(expression) 78 79 trim_type = f"{trim_type} " if trim_type else "" 80 remove_chars = f"{remove_chars} " if remove_chars else "" 81 from_part = "FROM " if trim_type or remove_chars else "" 82 return f"TRIM({trim_type}{remove_chars}{from_part}{target})" 83 84 85def _date_add_sql(kind: str) -> t.Callable[[generator.Generator, exp.DateAdd | exp.DateSub], str]: 86 def func(self: generator.Generator, expression: exp.DateAdd | exp.DateSub) -> str: 87 this = self.sql(expression, "this") 88 unit = expression.text("unit").upper() or "DAY" 89 return ( 90 f"DATE_{kind}({this}, {self.sql(exp.Interval(this=expression.expression, unit=unit))})" 91 ) 92 93 return func 94 95 96class MySQL(Dialect): 97 TIME_FORMAT = "'%Y-%m-%d %T'" 98 99 # https://prestodb.io/docs/current/functions/datetime.html#mysql-date-functions 100 TIME_MAPPING = { 101 "%M": "%B", 102 "%c": "%-m", 103 "%e": "%-d", 104 "%h": "%I", 105 "%i": "%M", 106 "%s": "%S", 107 "%S": "%S", 108 "%u": "%W", 109 "%k": "%-H", 110 "%l": "%-I", 111 "%T": "%H:%M:%S", 112 "%W": "%a", 113 } 114 115 class Tokenizer(tokens.Tokenizer): 116 QUOTES = ["'", '"'] 117 COMMENTS = ["--", "#", ("/*", "*/")] 118 IDENTIFIERS = ["`"] 119 STRING_ESCAPES = ["'", "\\"] 120 BIT_STRINGS = [("b'", "'"), ("B'", "'"), ("0b", "")] 121 HEX_STRINGS = [("x'", "'"), ("X'", "'"), ("0x", "")] 122 123 KEYWORDS = { 124 **tokens.Tokenizer.KEYWORDS, 125 "CHARSET": TokenType.CHARACTER_SET, 126 "LONGBLOB": TokenType.LONGBLOB, 127 "LONGTEXT": TokenType.LONGTEXT, 128 "MEDIUMBLOB": TokenType.MEDIUMBLOB, 129 "MEDIUMTEXT": TokenType.MEDIUMTEXT, 130 "SEPARATOR": TokenType.SEPARATOR, 131 "ENUM": TokenType.ENUM, 132 "START": TokenType.BEGIN, 133 "_ARMSCII8": TokenType.INTRODUCER, 134 "_ASCII": TokenType.INTRODUCER, 135 "_BIG5": TokenType.INTRODUCER, 136 "_BINARY": TokenType.INTRODUCER, 137 "_CP1250": TokenType.INTRODUCER, 138 "_CP1251": TokenType.INTRODUCER, 139 "_CP1256": TokenType.INTRODUCER, 140 "_CP1257": TokenType.INTRODUCER, 141 "_CP850": TokenType.INTRODUCER, 142 "_CP852": TokenType.INTRODUCER, 143 "_CP866": TokenType.INTRODUCER, 144 "_CP932": TokenType.INTRODUCER, 145 "_DEC8": TokenType.INTRODUCER, 146 "_EUCJPMS": TokenType.INTRODUCER, 147 "_EUCKR": TokenType.INTRODUCER, 148 "_GB18030": TokenType.INTRODUCER, 149 "_GB2312": TokenType.INTRODUCER, 150 "_GBK": TokenType.INTRODUCER, 151 "_GEOSTD8": TokenType.INTRODUCER, 152 "_GREEK": TokenType.INTRODUCER, 153 "_HEBREW": TokenType.INTRODUCER, 154 "_HP8": TokenType.INTRODUCER, 155 "_KEYBCS2": TokenType.INTRODUCER, 156 "_KOI8R": TokenType.INTRODUCER, 157 "_KOI8U": TokenType.INTRODUCER, 158 "_LATIN1": TokenType.INTRODUCER, 159 "_LATIN2": TokenType.INTRODUCER, 160 "_LATIN5": TokenType.INTRODUCER, 161 "_LATIN7": TokenType.INTRODUCER, 162 "_MACCE": TokenType.INTRODUCER, 163 "_MACROMAN": TokenType.INTRODUCER, 164 "_SJIS": TokenType.INTRODUCER, 165 "_SWE7": TokenType.INTRODUCER, 166 "_TIS620": TokenType.INTRODUCER, 167 "_UCS2": TokenType.INTRODUCER, 168 "_UJIS": TokenType.INTRODUCER, 169 # https://dev.mysql.com/doc/refman/8.0/en/string-literals.html 170 "_UTF8": TokenType.INTRODUCER, 171 "_UTF16": TokenType.INTRODUCER, 172 "_UTF16LE": TokenType.INTRODUCER, 173 "_UTF32": TokenType.INTRODUCER, 174 "_UTF8MB3": TokenType.INTRODUCER, 175 "_UTF8MB4": TokenType.INTRODUCER, 176 "@@": TokenType.SESSION_PARAMETER, 177 } 178 179 COMMANDS = tokens.Tokenizer.COMMANDS - {TokenType.SHOW} 180 181 class Parser(parser.Parser): 182 FUNC_TOKENS = {*parser.Parser.FUNC_TOKENS, TokenType.SCHEMA, TokenType.DATABASE} 183 184 FUNCTIONS = { 185 **parser.Parser.FUNCTIONS, 186 "DATE_ADD": parse_date_delta_with_interval(exp.DateAdd), 187 "DATE_FORMAT": format_time_lambda(exp.TimeToStr, "mysql"), 188 "DATE_SUB": parse_date_delta_with_interval(exp.DateSub), 189 "INSTR": lambda args: exp.StrPosition(substr=seq_get(args, 1), this=seq_get(args, 0)), 190 "LOCATE": locate_to_strposition, 191 "STR_TO_DATE": _str_to_date, 192 } 193 194 FUNCTION_PARSERS = { 195 **parser.Parser.FUNCTION_PARSERS, 196 "GROUP_CONCAT": lambda self: self.expression( 197 exp.GroupConcat, 198 this=self._parse_lambda(), 199 separator=self._match(TokenType.SEPARATOR) and self._parse_field(), 200 ), 201 } 202 203 STATEMENT_PARSERS = { 204 **parser.Parser.STATEMENT_PARSERS, 205 TokenType.SHOW: lambda self: self._parse_show(), 206 } 207 208 SHOW_PARSERS = { 209 "BINARY LOGS": _show_parser("BINARY LOGS"), 210 "MASTER LOGS": _show_parser("BINARY LOGS"), 211 "BINLOG EVENTS": _show_parser("BINLOG EVENTS"), 212 "CHARACTER SET": _show_parser("CHARACTER SET"), 213 "CHARSET": _show_parser("CHARACTER SET"), 214 "COLLATION": _show_parser("COLLATION"), 215 "FULL COLUMNS": _show_parser("COLUMNS", target="FROM", full=True), 216 "COLUMNS": _show_parser("COLUMNS", target="FROM"), 217 "CREATE DATABASE": _show_parser("CREATE DATABASE", target=True), 218 "CREATE EVENT": _show_parser("CREATE EVENT", target=True), 219 "CREATE FUNCTION": _show_parser("CREATE FUNCTION", target=True), 220 "CREATE PROCEDURE": _show_parser("CREATE PROCEDURE", target=True), 221 "CREATE TABLE": _show_parser("CREATE TABLE", target=True), 222 "CREATE TRIGGER": _show_parser("CREATE TRIGGER", target=True), 223 "CREATE VIEW": _show_parser("CREATE VIEW", target=True), 224 "DATABASES": _show_parser("DATABASES"), 225 "ENGINE": _show_parser("ENGINE", target=True), 226 "STORAGE ENGINES": _show_parser("ENGINES"), 227 "ENGINES": _show_parser("ENGINES"), 228 "ERRORS": _show_parser("ERRORS"), 229 "EVENTS": _show_parser("EVENTS"), 230 "FUNCTION CODE": _show_parser("FUNCTION CODE", target=True), 231 "FUNCTION STATUS": _show_parser("FUNCTION STATUS"), 232 "GRANTS": _show_parser("GRANTS", target="FOR"), 233 "INDEX": _show_parser("INDEX", target="FROM"), 234 "MASTER STATUS": _show_parser("MASTER STATUS"), 235 "OPEN TABLES": _show_parser("OPEN TABLES"), 236 "PLUGINS": _show_parser("PLUGINS"), 237 "PROCEDURE CODE": _show_parser("PROCEDURE CODE", target=True), 238 "PROCEDURE STATUS": _show_parser("PROCEDURE STATUS"), 239 "PRIVILEGES": _show_parser("PRIVILEGES"), 240 "FULL PROCESSLIST": _show_parser("PROCESSLIST", full=True), 241 "PROCESSLIST": _show_parser("PROCESSLIST"), 242 "PROFILE": _show_parser("PROFILE"), 243 "PROFILES": _show_parser("PROFILES"), 244 "RELAYLOG EVENTS": _show_parser("RELAYLOG EVENTS"), 245 "REPLICAS": _show_parser("REPLICAS"), 246 "SLAVE HOSTS": _show_parser("REPLICAS"), 247 "REPLICA STATUS": _show_parser("REPLICA STATUS"), 248 "SLAVE STATUS": _show_parser("REPLICA STATUS"), 249 "GLOBAL STATUS": _show_parser("STATUS", global_=True), 250 "SESSION STATUS": _show_parser("STATUS"), 251 "STATUS": _show_parser("STATUS"), 252 "TABLE STATUS": _show_parser("TABLE STATUS"), 253 "FULL TABLES": _show_parser("TABLES", full=True), 254 "TABLES": _show_parser("TABLES"), 255 "TRIGGERS": _show_parser("TRIGGERS"), 256 "GLOBAL VARIABLES": _show_parser("VARIABLES", global_=True), 257 "SESSION VARIABLES": _show_parser("VARIABLES"), 258 "VARIABLES": _show_parser("VARIABLES"), 259 "WARNINGS": _show_parser("WARNINGS"), 260 } 261 262 SET_PARSERS = { 263 **parser.Parser.SET_PARSERS, 264 "PERSIST": lambda self: self._parse_set_item_assignment("PERSIST"), 265 "PERSIST_ONLY": lambda self: self._parse_set_item_assignment("PERSIST_ONLY"), 266 "CHARACTER SET": lambda self: self._parse_set_item_charset("CHARACTER SET"), 267 "CHARSET": lambda self: self._parse_set_item_charset("CHARACTER SET"), 268 "NAMES": lambda self: self._parse_set_item_names(), 269 } 270 271 PROFILE_TYPES = { 272 "ALL", 273 "BLOCK IO", 274 "CONTEXT SWITCHES", 275 "CPU", 276 "IPC", 277 "MEMORY", 278 "PAGE FAULTS", 279 "SOURCE", 280 "SWAPS", 281 } 282 283 TYPE_TOKENS = { 284 *parser.Parser.TYPE_TOKENS, 285 TokenType.SET, 286 } 287 288 ENUM_TYPE_TOKENS = { 289 *parser.Parser.ENUM_TYPE_TOKENS, 290 TokenType.SET, 291 } 292 293 LOG_DEFAULTS_TO_LN = True 294 295 def _parse_show_mysql( 296 self, 297 this: str, 298 target: bool | str = False, 299 full: t.Optional[bool] = None, 300 global_: t.Optional[bool] = None, 301 ) -> exp.Show: 302 if target: 303 if isinstance(target, str): 304 self._match_text_seq(target) 305 target_id = self._parse_id_var() 306 else: 307 target_id = None 308 309 log = self._parse_string() if self._match_text_seq("IN") else None 310 311 if this in {"BINLOG EVENTS", "RELAYLOG EVENTS"}: 312 position = self._parse_number() if self._match_text_seq("FROM") else None 313 db = None 314 else: 315 position = None 316 db = None 317 318 if self._match(TokenType.FROM): 319 db = self._parse_id_var() 320 elif self._match(TokenType.DOT): 321 db = target_id 322 target_id = self._parse_id_var() 323 324 channel = self._parse_id_var() if self._match_text_seq("FOR", "CHANNEL") else None 325 326 like = self._parse_string() if self._match_text_seq("LIKE") else None 327 where = self._parse_where() 328 329 if this == "PROFILE": 330 types = self._parse_csv(lambda: self._parse_var_from_options(self.PROFILE_TYPES)) 331 query = self._parse_number() if self._match_text_seq("FOR", "QUERY") else None 332 offset = self._parse_number() if self._match_text_seq("OFFSET") else None 333 limit = self._parse_number() if self._match_text_seq("LIMIT") else None 334 else: 335 types, query = None, None 336 offset, limit = self._parse_oldstyle_limit() 337 338 mutex = True if self._match_text_seq("MUTEX") else None 339 mutex = False if self._match_text_seq("STATUS") else mutex 340 341 return self.expression( 342 exp.Show, 343 this=this, 344 target=target_id, 345 full=full, 346 log=log, 347 position=position, 348 db=db, 349 channel=channel, 350 like=like, 351 where=where, 352 types=types, 353 query=query, 354 offset=offset, 355 limit=limit, 356 mutex=mutex, 357 **{"global": global_}, # type: ignore 358 ) 359 360 def _parse_oldstyle_limit( 361 self, 362 ) -> t.Tuple[t.Optional[exp.Expression], t.Optional[exp.Expression]]: 363 limit = None 364 offset = None 365 if self._match_text_seq("LIMIT"): 366 parts = self._parse_csv(self._parse_number) 367 if len(parts) == 1: 368 limit = parts[0] 369 elif len(parts) == 2: 370 limit = parts[1] 371 offset = parts[0] 372 373 return offset, limit 374 375 def _parse_set_item_charset(self, kind: str) -> exp.Expression: 376 this = self._parse_string() or self._parse_id_var() 377 return self.expression(exp.SetItem, this=this, kind=kind) 378 379 def _parse_set_item_names(self) -> exp.Expression: 380 charset = self._parse_string() or self._parse_id_var() 381 if self._match_text_seq("COLLATE"): 382 collate = self._parse_string() or self._parse_id_var() 383 else: 384 collate = None 385 386 return self.expression(exp.SetItem, this=charset, collate=collate, kind="NAMES") 387 388 class Generator(generator.Generator): 389 LOCKING_READS_SUPPORTED = True 390 NULL_ORDERING_SUPPORTED = False 391 JOIN_HINTS = False 392 TABLE_HINTS = False 393 394 TRANSFORMS = { 395 **generator.Generator.TRANSFORMS, 396 exp.CurrentDate: no_paren_current_date_sql, 397 exp.DateDiff: lambda self, e: self.func("DATEDIFF", e.this, e.expression), 398 exp.DateAdd: _date_add_sql("ADD"), 399 exp.DateStrToDate: datestrtodate_sql, 400 exp.DateSub: _date_add_sql("SUB"), 401 exp.DateTrunc: _date_trunc_sql, 402 exp.DayOfMonth: rename_func("DAYOFMONTH"), 403 exp.DayOfWeek: rename_func("DAYOFWEEK"), 404 exp.DayOfYear: rename_func("DAYOFYEAR"), 405 exp.GroupConcat: lambda self, e: f"""GROUP_CONCAT({self.sql(e, "this")} SEPARATOR {self.sql(e, "separator") or "','"})""", 406 exp.ILike: no_ilike_sql, 407 exp.JSONExtractScalar: arrow_json_extract_scalar_sql, 408 exp.Max: max_or_greatest, 409 exp.Min: min_or_least, 410 exp.NullSafeEQ: lambda self, e: self.binary(e, "<=>"), 411 exp.NullSafeNEQ: lambda self, e: self.not_sql(self.binary(e, "<=>")), 412 exp.Pivot: no_pivot_sql, 413 exp.Select: transforms.preprocess([transforms.eliminate_distinct_on]), 414 exp.StrPosition: strposition_to_locate_sql, 415 exp.StrToDate: _str_to_date_sql, 416 exp.StrToTime: _str_to_date_sql, 417 exp.TableSample: no_tablesample_sql, 418 exp.TimeStrToUnix: rename_func("UNIX_TIMESTAMP"), 419 exp.TimeToStr: lambda self, e: self.func("DATE_FORMAT", e.this, self.format_time(e)), 420 exp.Trim: _trim_sql, 421 exp.TryCast: no_trycast_sql, 422 exp.WeekOfYear: rename_func("WEEKOFYEAR"), 423 } 424 425 TYPE_MAPPING = generator.Generator.TYPE_MAPPING.copy() 426 TYPE_MAPPING.pop(exp.DataType.Type.MEDIUMTEXT) 427 TYPE_MAPPING.pop(exp.DataType.Type.LONGTEXT) 428 TYPE_MAPPING.pop(exp.DataType.Type.MEDIUMBLOB) 429 TYPE_MAPPING.pop(exp.DataType.Type.LONGBLOB) 430 431 PROPERTIES_LOCATION = { 432 **generator.Generator.PROPERTIES_LOCATION, 433 exp.TransientProperty: exp.Properties.Location.UNSUPPORTED, 434 exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED, 435 } 436 437 LIMIT_FETCH = "LIMIT" 438 439 def show_sql(self, expression: exp.Show) -> str: 440 this = f" {expression.name}" 441 full = " FULL" if expression.args.get("full") else "" 442 global_ = " GLOBAL" if expression.args.get("global") else "" 443 444 target = self.sql(expression, "target") 445 target = f" {target}" if target else "" 446 if expression.name in {"COLUMNS", "INDEX"}: 447 target = f" FROM{target}" 448 elif expression.name == "GRANTS": 449 target = f" FOR{target}" 450 451 db = self._prefixed_sql("FROM", expression, "db") 452 453 like = self._prefixed_sql("LIKE", expression, "like") 454 where = self.sql(expression, "where") 455 456 types = self.expressions(expression, key="types") 457 types = f" {types}" if types else types 458 query = self._prefixed_sql("FOR QUERY", expression, "query") 459 460 if expression.name == "PROFILE": 461 offset = self._prefixed_sql("OFFSET", expression, "offset") 462 limit = self._prefixed_sql("LIMIT", expression, "limit") 463 else: 464 offset = "" 465 limit = self._oldstyle_limit_sql(expression) 466 467 log = self._prefixed_sql("IN", expression, "log") 468 position = self._prefixed_sql("FROM", expression, "position") 469 470 channel = self._prefixed_sql("FOR CHANNEL", expression, "channel") 471 472 if expression.name == "ENGINE": 473 mutex_or_status = " MUTEX" if expression.args.get("mutex") else " STATUS" 474 else: 475 mutex_or_status = "" 476 477 return f"SHOW{full}{global_}{this}{target}{types}{db}{query}{log}{position}{channel}{mutex_or_status}{like}{where}{offset}{limit}" 478 479 def _prefixed_sql(self, prefix: str, expression: exp.Expression, arg: str) -> str: 480 sql = self.sql(expression, arg) 481 return f" {prefix} {sql}" if sql else "" 482 483 def _oldstyle_limit_sql(self, expression: exp.Show) -> str: 484 limit = self.sql(expression, "limit") 485 offset = self.sql(expression, "offset") 486 if limit: 487 limit_offset = f"{offset}, {limit}" if offset else limit 488 return f" LIMIT {limit_offset}" 489 return ""
97class MySQL(Dialect): 98 TIME_FORMAT = "'%Y-%m-%d %T'" 99 100 # https://prestodb.io/docs/current/functions/datetime.html#mysql-date-functions 101 TIME_MAPPING = { 102 "%M": "%B", 103 "%c": "%-m", 104 "%e": "%-d", 105 "%h": "%I", 106 "%i": "%M", 107 "%s": "%S", 108 "%S": "%S", 109 "%u": "%W", 110 "%k": "%-H", 111 "%l": "%-I", 112 "%T": "%H:%M:%S", 113 "%W": "%a", 114 } 115 116 class Tokenizer(tokens.Tokenizer): 117 QUOTES = ["'", '"'] 118 COMMENTS = ["--", "#", ("/*", "*/")] 119 IDENTIFIERS = ["`"] 120 STRING_ESCAPES = ["'", "\\"] 121 BIT_STRINGS = [("b'", "'"), ("B'", "'"), ("0b", "")] 122 HEX_STRINGS = [("x'", "'"), ("X'", "'"), ("0x", "")] 123 124 KEYWORDS = { 125 **tokens.Tokenizer.KEYWORDS, 126 "CHARSET": TokenType.CHARACTER_SET, 127 "LONGBLOB": TokenType.LONGBLOB, 128 "LONGTEXT": TokenType.LONGTEXT, 129 "MEDIUMBLOB": TokenType.MEDIUMBLOB, 130 "MEDIUMTEXT": TokenType.MEDIUMTEXT, 131 "SEPARATOR": TokenType.SEPARATOR, 132 "ENUM": TokenType.ENUM, 133 "START": TokenType.BEGIN, 134 "_ARMSCII8": TokenType.INTRODUCER, 135 "_ASCII": TokenType.INTRODUCER, 136 "_BIG5": TokenType.INTRODUCER, 137 "_BINARY": TokenType.INTRODUCER, 138 "_CP1250": TokenType.INTRODUCER, 139 "_CP1251": TokenType.INTRODUCER, 140 "_CP1256": TokenType.INTRODUCER, 141 "_CP1257": TokenType.INTRODUCER, 142 "_CP850": TokenType.INTRODUCER, 143 "_CP852": TokenType.INTRODUCER, 144 "_CP866": TokenType.INTRODUCER, 145 "_CP932": TokenType.INTRODUCER, 146 "_DEC8": TokenType.INTRODUCER, 147 "_EUCJPMS": TokenType.INTRODUCER, 148 "_EUCKR": TokenType.INTRODUCER, 149 "_GB18030": TokenType.INTRODUCER, 150 "_GB2312": TokenType.INTRODUCER, 151 "_GBK": TokenType.INTRODUCER, 152 "_GEOSTD8": TokenType.INTRODUCER, 153 "_GREEK": TokenType.INTRODUCER, 154 "_HEBREW": TokenType.INTRODUCER, 155 "_HP8": TokenType.INTRODUCER, 156 "_KEYBCS2": TokenType.INTRODUCER, 157 "_KOI8R": TokenType.INTRODUCER, 158 "_KOI8U": TokenType.INTRODUCER, 159 "_LATIN1": TokenType.INTRODUCER, 160 "_LATIN2": TokenType.INTRODUCER, 161 "_LATIN5": TokenType.INTRODUCER, 162 "_LATIN7": TokenType.INTRODUCER, 163 "_MACCE": TokenType.INTRODUCER, 164 "_MACROMAN": TokenType.INTRODUCER, 165 "_SJIS": TokenType.INTRODUCER, 166 "_SWE7": TokenType.INTRODUCER, 167 "_TIS620": TokenType.INTRODUCER, 168 "_UCS2": TokenType.INTRODUCER, 169 "_UJIS": TokenType.INTRODUCER, 170 # https://dev.mysql.com/doc/refman/8.0/en/string-literals.html 171 "_UTF8": TokenType.INTRODUCER, 172 "_UTF16": TokenType.INTRODUCER, 173 "_UTF16LE": TokenType.INTRODUCER, 174 "_UTF32": TokenType.INTRODUCER, 175 "_UTF8MB3": TokenType.INTRODUCER, 176 "_UTF8MB4": TokenType.INTRODUCER, 177 "@@": TokenType.SESSION_PARAMETER, 178 } 179 180 COMMANDS = tokens.Tokenizer.COMMANDS - {TokenType.SHOW} 181 182 class Parser(parser.Parser): 183 FUNC_TOKENS = {*parser.Parser.FUNC_TOKENS, TokenType.SCHEMA, TokenType.DATABASE} 184 185 FUNCTIONS = { 186 **parser.Parser.FUNCTIONS, 187 "DATE_ADD": parse_date_delta_with_interval(exp.DateAdd), 188 "DATE_FORMAT": format_time_lambda(exp.TimeToStr, "mysql"), 189 "DATE_SUB": parse_date_delta_with_interval(exp.DateSub), 190 "INSTR": lambda args: exp.StrPosition(substr=seq_get(args, 1), this=seq_get(args, 0)), 191 "LOCATE": locate_to_strposition, 192 "STR_TO_DATE": _str_to_date, 193 } 194 195 FUNCTION_PARSERS = { 196 **parser.Parser.FUNCTION_PARSERS, 197 "GROUP_CONCAT": lambda self: self.expression( 198 exp.GroupConcat, 199 this=self._parse_lambda(), 200 separator=self._match(TokenType.SEPARATOR) and self._parse_field(), 201 ), 202 } 203 204 STATEMENT_PARSERS = { 205 **parser.Parser.STATEMENT_PARSERS, 206 TokenType.SHOW: lambda self: self._parse_show(), 207 } 208 209 SHOW_PARSERS = { 210 "BINARY LOGS": _show_parser("BINARY LOGS"), 211 "MASTER LOGS": _show_parser("BINARY LOGS"), 212 "BINLOG EVENTS": _show_parser("BINLOG EVENTS"), 213 "CHARACTER SET": _show_parser("CHARACTER SET"), 214 "CHARSET": _show_parser("CHARACTER SET"), 215 "COLLATION": _show_parser("COLLATION"), 216 "FULL COLUMNS": _show_parser("COLUMNS", target="FROM", full=True), 217 "COLUMNS": _show_parser("COLUMNS", target="FROM"), 218 "CREATE DATABASE": _show_parser("CREATE DATABASE", target=True), 219 "CREATE EVENT": _show_parser("CREATE EVENT", target=True), 220 "CREATE FUNCTION": _show_parser("CREATE FUNCTION", target=True), 221 "CREATE PROCEDURE": _show_parser("CREATE PROCEDURE", target=True), 222 "CREATE TABLE": _show_parser("CREATE TABLE", target=True), 223 "CREATE TRIGGER": _show_parser("CREATE TRIGGER", target=True), 224 "CREATE VIEW": _show_parser("CREATE VIEW", target=True), 225 "DATABASES": _show_parser("DATABASES"), 226 "ENGINE": _show_parser("ENGINE", target=True), 227 "STORAGE ENGINES": _show_parser("ENGINES"), 228 "ENGINES": _show_parser("ENGINES"), 229 "ERRORS": _show_parser("ERRORS"), 230 "EVENTS": _show_parser("EVENTS"), 231 "FUNCTION CODE": _show_parser("FUNCTION CODE", target=True), 232 "FUNCTION STATUS": _show_parser("FUNCTION STATUS"), 233 "GRANTS": _show_parser("GRANTS", target="FOR"), 234 "INDEX": _show_parser("INDEX", target="FROM"), 235 "MASTER STATUS": _show_parser("MASTER STATUS"), 236 "OPEN TABLES": _show_parser("OPEN TABLES"), 237 "PLUGINS": _show_parser("PLUGINS"), 238 "PROCEDURE CODE": _show_parser("PROCEDURE CODE", target=True), 239 "PROCEDURE STATUS": _show_parser("PROCEDURE STATUS"), 240 "PRIVILEGES": _show_parser("PRIVILEGES"), 241 "FULL PROCESSLIST": _show_parser("PROCESSLIST", full=True), 242 "PROCESSLIST": _show_parser("PROCESSLIST"), 243 "PROFILE": _show_parser("PROFILE"), 244 "PROFILES": _show_parser("PROFILES"), 245 "RELAYLOG EVENTS": _show_parser("RELAYLOG EVENTS"), 246 "REPLICAS": _show_parser("REPLICAS"), 247 "SLAVE HOSTS": _show_parser("REPLICAS"), 248 "REPLICA STATUS": _show_parser("REPLICA STATUS"), 249 "SLAVE STATUS": _show_parser("REPLICA STATUS"), 250 "GLOBAL STATUS": _show_parser("STATUS", global_=True), 251 "SESSION STATUS": _show_parser("STATUS"), 252 "STATUS": _show_parser("STATUS"), 253 "TABLE STATUS": _show_parser("TABLE STATUS"), 254 "FULL TABLES": _show_parser("TABLES", full=True), 255 "TABLES": _show_parser("TABLES"), 256 "TRIGGERS": _show_parser("TRIGGERS"), 257 "GLOBAL VARIABLES": _show_parser("VARIABLES", global_=True), 258 "SESSION VARIABLES": _show_parser("VARIABLES"), 259 "VARIABLES": _show_parser("VARIABLES"), 260 "WARNINGS": _show_parser("WARNINGS"), 261 } 262 263 SET_PARSERS = { 264 **parser.Parser.SET_PARSERS, 265 "PERSIST": lambda self: self._parse_set_item_assignment("PERSIST"), 266 "PERSIST_ONLY": lambda self: self._parse_set_item_assignment("PERSIST_ONLY"), 267 "CHARACTER SET": lambda self: self._parse_set_item_charset("CHARACTER SET"), 268 "CHARSET": lambda self: self._parse_set_item_charset("CHARACTER SET"), 269 "NAMES": lambda self: self._parse_set_item_names(), 270 } 271 272 PROFILE_TYPES = { 273 "ALL", 274 "BLOCK IO", 275 "CONTEXT SWITCHES", 276 "CPU", 277 "IPC", 278 "MEMORY", 279 "PAGE FAULTS", 280 "SOURCE", 281 "SWAPS", 282 } 283 284 TYPE_TOKENS = { 285 *parser.Parser.TYPE_TOKENS, 286 TokenType.SET, 287 } 288 289 ENUM_TYPE_TOKENS = { 290 *parser.Parser.ENUM_TYPE_TOKENS, 291 TokenType.SET, 292 } 293 294 LOG_DEFAULTS_TO_LN = True 295 296 def _parse_show_mysql( 297 self, 298 this: str, 299 target: bool | str = False, 300 full: t.Optional[bool] = None, 301 global_: t.Optional[bool] = None, 302 ) -> exp.Show: 303 if target: 304 if isinstance(target, str): 305 self._match_text_seq(target) 306 target_id = self._parse_id_var() 307 else: 308 target_id = None 309 310 log = self._parse_string() if self._match_text_seq("IN") else None 311 312 if this in {"BINLOG EVENTS", "RELAYLOG EVENTS"}: 313 position = self._parse_number() if self._match_text_seq("FROM") else None 314 db = None 315 else: 316 position = None 317 db = None 318 319 if self._match(TokenType.FROM): 320 db = self._parse_id_var() 321 elif self._match(TokenType.DOT): 322 db = target_id 323 target_id = self._parse_id_var() 324 325 channel = self._parse_id_var() if self._match_text_seq("FOR", "CHANNEL") else None 326 327 like = self._parse_string() if self._match_text_seq("LIKE") else None 328 where = self._parse_where() 329 330 if this == "PROFILE": 331 types = self._parse_csv(lambda: self._parse_var_from_options(self.PROFILE_TYPES)) 332 query = self._parse_number() if self._match_text_seq("FOR", "QUERY") else None 333 offset = self._parse_number() if self._match_text_seq("OFFSET") else None 334 limit = self._parse_number() if self._match_text_seq("LIMIT") else None 335 else: 336 types, query = None, None 337 offset, limit = self._parse_oldstyle_limit() 338 339 mutex = True if self._match_text_seq("MUTEX") else None 340 mutex = False if self._match_text_seq("STATUS") else mutex 341 342 return self.expression( 343 exp.Show, 344 this=this, 345 target=target_id, 346 full=full, 347 log=log, 348 position=position, 349 db=db, 350 channel=channel, 351 like=like, 352 where=where, 353 types=types, 354 query=query, 355 offset=offset, 356 limit=limit, 357 mutex=mutex, 358 **{"global": global_}, # type: ignore 359 ) 360 361 def _parse_oldstyle_limit( 362 self, 363 ) -> t.Tuple[t.Optional[exp.Expression], t.Optional[exp.Expression]]: 364 limit = None 365 offset = None 366 if self._match_text_seq("LIMIT"): 367 parts = self._parse_csv(self._parse_number) 368 if len(parts) == 1: 369 limit = parts[0] 370 elif len(parts) == 2: 371 limit = parts[1] 372 offset = parts[0] 373 374 return offset, limit 375 376 def _parse_set_item_charset(self, kind: str) -> exp.Expression: 377 this = self._parse_string() or self._parse_id_var() 378 return self.expression(exp.SetItem, this=this, kind=kind) 379 380 def _parse_set_item_names(self) -> exp.Expression: 381 charset = self._parse_string() or self._parse_id_var() 382 if self._match_text_seq("COLLATE"): 383 collate = self._parse_string() or self._parse_id_var() 384 else: 385 collate = None 386 387 return self.expression(exp.SetItem, this=charset, collate=collate, kind="NAMES") 388 389 class Generator(generator.Generator): 390 LOCKING_READS_SUPPORTED = True 391 NULL_ORDERING_SUPPORTED = False 392 JOIN_HINTS = False 393 TABLE_HINTS = False 394 395 TRANSFORMS = { 396 **generator.Generator.TRANSFORMS, 397 exp.CurrentDate: no_paren_current_date_sql, 398 exp.DateDiff: lambda self, e: self.func("DATEDIFF", e.this, e.expression), 399 exp.DateAdd: _date_add_sql("ADD"), 400 exp.DateStrToDate: datestrtodate_sql, 401 exp.DateSub: _date_add_sql("SUB"), 402 exp.DateTrunc: _date_trunc_sql, 403 exp.DayOfMonth: rename_func("DAYOFMONTH"), 404 exp.DayOfWeek: rename_func("DAYOFWEEK"), 405 exp.DayOfYear: rename_func("DAYOFYEAR"), 406 exp.GroupConcat: lambda self, e: f"""GROUP_CONCAT({self.sql(e, "this")} SEPARATOR {self.sql(e, "separator") or "','"})""", 407 exp.ILike: no_ilike_sql, 408 exp.JSONExtractScalar: arrow_json_extract_scalar_sql, 409 exp.Max: max_or_greatest, 410 exp.Min: min_or_least, 411 exp.NullSafeEQ: lambda self, e: self.binary(e, "<=>"), 412 exp.NullSafeNEQ: lambda self, e: self.not_sql(self.binary(e, "<=>")), 413 exp.Pivot: no_pivot_sql, 414 exp.Select: transforms.preprocess([transforms.eliminate_distinct_on]), 415 exp.StrPosition: strposition_to_locate_sql, 416 exp.StrToDate: _str_to_date_sql, 417 exp.StrToTime: _str_to_date_sql, 418 exp.TableSample: no_tablesample_sql, 419 exp.TimeStrToUnix: rename_func("UNIX_TIMESTAMP"), 420 exp.TimeToStr: lambda self, e: self.func("DATE_FORMAT", e.this, self.format_time(e)), 421 exp.Trim: _trim_sql, 422 exp.TryCast: no_trycast_sql, 423 exp.WeekOfYear: rename_func("WEEKOFYEAR"), 424 } 425 426 TYPE_MAPPING = generator.Generator.TYPE_MAPPING.copy() 427 TYPE_MAPPING.pop(exp.DataType.Type.MEDIUMTEXT) 428 TYPE_MAPPING.pop(exp.DataType.Type.LONGTEXT) 429 TYPE_MAPPING.pop(exp.DataType.Type.MEDIUMBLOB) 430 TYPE_MAPPING.pop(exp.DataType.Type.LONGBLOB) 431 432 PROPERTIES_LOCATION = { 433 **generator.Generator.PROPERTIES_LOCATION, 434 exp.TransientProperty: exp.Properties.Location.UNSUPPORTED, 435 exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED, 436 } 437 438 LIMIT_FETCH = "LIMIT" 439 440 def show_sql(self, expression: exp.Show) -> str: 441 this = f" {expression.name}" 442 full = " FULL" if expression.args.get("full") else "" 443 global_ = " GLOBAL" if expression.args.get("global") else "" 444 445 target = self.sql(expression, "target") 446 target = f" {target}" if target else "" 447 if expression.name in {"COLUMNS", "INDEX"}: 448 target = f" FROM{target}" 449 elif expression.name == "GRANTS": 450 target = f" FOR{target}" 451 452 db = self._prefixed_sql("FROM", expression, "db") 453 454 like = self._prefixed_sql("LIKE", expression, "like") 455 where = self.sql(expression, "where") 456 457 types = self.expressions(expression, key="types") 458 types = f" {types}" if types else types 459 query = self._prefixed_sql("FOR QUERY", expression, "query") 460 461 if expression.name == "PROFILE": 462 offset = self._prefixed_sql("OFFSET", expression, "offset") 463 limit = self._prefixed_sql("LIMIT", expression, "limit") 464 else: 465 offset = "" 466 limit = self._oldstyle_limit_sql(expression) 467 468 log = self._prefixed_sql("IN", expression, "log") 469 position = self._prefixed_sql("FROM", expression, "position") 470 471 channel = self._prefixed_sql("FOR CHANNEL", expression, "channel") 472 473 if expression.name == "ENGINE": 474 mutex_or_status = " MUTEX" if expression.args.get("mutex") else " STATUS" 475 else: 476 mutex_or_status = "" 477 478 return f"SHOW{full}{global_}{this}{target}{types}{db}{query}{log}{position}{channel}{mutex_or_status}{like}{where}{offset}{limit}" 479 480 def _prefixed_sql(self, prefix: str, expression: exp.Expression, arg: str) -> str: 481 sql = self.sql(expression, arg) 482 return f" {prefix} {sql}" if sql else "" 483 484 def _oldstyle_limit_sql(self, expression: exp.Show) -> str: 485 limit = self.sql(expression, "limit") 486 offset = self.sql(expression, "offset") 487 if limit: 488 limit_offset = f"{offset}, {limit}" if offset else limit 489 return f" LIMIT {limit_offset}" 490 return ""
116 class Tokenizer(tokens.Tokenizer): 117 QUOTES = ["'", '"'] 118 COMMENTS = ["--", "#", ("/*", "*/")] 119 IDENTIFIERS = ["`"] 120 STRING_ESCAPES = ["'", "\\"] 121 BIT_STRINGS = [("b'", "'"), ("B'", "'"), ("0b", "")] 122 HEX_STRINGS = [("x'", "'"), ("X'", "'"), ("0x", "")] 123 124 KEYWORDS = { 125 **tokens.Tokenizer.KEYWORDS, 126 "CHARSET": TokenType.CHARACTER_SET, 127 "LONGBLOB": TokenType.LONGBLOB, 128 "LONGTEXT": TokenType.LONGTEXT, 129 "MEDIUMBLOB": TokenType.MEDIUMBLOB, 130 "MEDIUMTEXT": TokenType.MEDIUMTEXT, 131 "SEPARATOR": TokenType.SEPARATOR, 132 "ENUM": TokenType.ENUM, 133 "START": TokenType.BEGIN, 134 "_ARMSCII8": TokenType.INTRODUCER, 135 "_ASCII": TokenType.INTRODUCER, 136 "_BIG5": TokenType.INTRODUCER, 137 "_BINARY": TokenType.INTRODUCER, 138 "_CP1250": TokenType.INTRODUCER, 139 "_CP1251": TokenType.INTRODUCER, 140 "_CP1256": TokenType.INTRODUCER, 141 "_CP1257": TokenType.INTRODUCER, 142 "_CP850": TokenType.INTRODUCER, 143 "_CP852": TokenType.INTRODUCER, 144 "_CP866": TokenType.INTRODUCER, 145 "_CP932": TokenType.INTRODUCER, 146 "_DEC8": TokenType.INTRODUCER, 147 "_EUCJPMS": TokenType.INTRODUCER, 148 "_EUCKR": TokenType.INTRODUCER, 149 "_GB18030": TokenType.INTRODUCER, 150 "_GB2312": TokenType.INTRODUCER, 151 "_GBK": TokenType.INTRODUCER, 152 "_GEOSTD8": TokenType.INTRODUCER, 153 "_GREEK": TokenType.INTRODUCER, 154 "_HEBREW": TokenType.INTRODUCER, 155 "_HP8": TokenType.INTRODUCER, 156 "_KEYBCS2": TokenType.INTRODUCER, 157 "_KOI8R": TokenType.INTRODUCER, 158 "_KOI8U": TokenType.INTRODUCER, 159 "_LATIN1": TokenType.INTRODUCER, 160 "_LATIN2": TokenType.INTRODUCER, 161 "_LATIN5": TokenType.INTRODUCER, 162 "_LATIN7": TokenType.INTRODUCER, 163 "_MACCE": TokenType.INTRODUCER, 164 "_MACROMAN": TokenType.INTRODUCER, 165 "_SJIS": TokenType.INTRODUCER, 166 "_SWE7": TokenType.INTRODUCER, 167 "_TIS620": TokenType.INTRODUCER, 168 "_UCS2": TokenType.INTRODUCER, 169 "_UJIS": TokenType.INTRODUCER, 170 # https://dev.mysql.com/doc/refman/8.0/en/string-literals.html 171 "_UTF8": TokenType.INTRODUCER, 172 "_UTF16": TokenType.INTRODUCER, 173 "_UTF16LE": TokenType.INTRODUCER, 174 "_UTF32": TokenType.INTRODUCER, 175 "_UTF8MB3": TokenType.INTRODUCER, 176 "_UTF8MB4": TokenType.INTRODUCER, 177 "@@": TokenType.SESSION_PARAMETER, 178 } 179 180 COMMANDS = tokens.Tokenizer.COMMANDS - {TokenType.SHOW}
Inherited Members
182 class Parser(parser.Parser): 183 FUNC_TOKENS = {*parser.Parser.FUNC_TOKENS, TokenType.SCHEMA, TokenType.DATABASE} 184 185 FUNCTIONS = { 186 **parser.Parser.FUNCTIONS, 187 "DATE_ADD": parse_date_delta_with_interval(exp.DateAdd), 188 "DATE_FORMAT": format_time_lambda(exp.TimeToStr, "mysql"), 189 "DATE_SUB": parse_date_delta_with_interval(exp.DateSub), 190 "INSTR": lambda args: exp.StrPosition(substr=seq_get(args, 1), this=seq_get(args, 0)), 191 "LOCATE": locate_to_strposition, 192 "STR_TO_DATE": _str_to_date, 193 } 194 195 FUNCTION_PARSERS = { 196 **parser.Parser.FUNCTION_PARSERS, 197 "GROUP_CONCAT": lambda self: self.expression( 198 exp.GroupConcat, 199 this=self._parse_lambda(), 200 separator=self._match(TokenType.SEPARATOR) and self._parse_field(), 201 ), 202 } 203 204 STATEMENT_PARSERS = { 205 **parser.Parser.STATEMENT_PARSERS, 206 TokenType.SHOW: lambda self: self._parse_show(), 207 } 208 209 SHOW_PARSERS = { 210 "BINARY LOGS": _show_parser("BINARY LOGS"), 211 "MASTER LOGS": _show_parser("BINARY LOGS"), 212 "BINLOG EVENTS": _show_parser("BINLOG EVENTS"), 213 "CHARACTER SET": _show_parser("CHARACTER SET"), 214 "CHARSET": _show_parser("CHARACTER SET"), 215 "COLLATION": _show_parser("COLLATION"), 216 "FULL COLUMNS": _show_parser("COLUMNS", target="FROM", full=True), 217 "COLUMNS": _show_parser("COLUMNS", target="FROM"), 218 "CREATE DATABASE": _show_parser("CREATE DATABASE", target=True), 219 "CREATE EVENT": _show_parser("CREATE EVENT", target=True), 220 "CREATE FUNCTION": _show_parser("CREATE FUNCTION", target=True), 221 "CREATE PROCEDURE": _show_parser("CREATE PROCEDURE", target=True), 222 "CREATE TABLE": _show_parser("CREATE TABLE", target=True), 223 "CREATE TRIGGER": _show_parser("CREATE TRIGGER", target=True), 224 "CREATE VIEW": _show_parser("CREATE VIEW", target=True), 225 "DATABASES": _show_parser("DATABASES"), 226 "ENGINE": _show_parser("ENGINE", target=True), 227 "STORAGE ENGINES": _show_parser("ENGINES"), 228 "ENGINES": _show_parser("ENGINES"), 229 "ERRORS": _show_parser("ERRORS"), 230 "EVENTS": _show_parser("EVENTS"), 231 "FUNCTION CODE": _show_parser("FUNCTION CODE", target=True), 232 "FUNCTION STATUS": _show_parser("FUNCTION STATUS"), 233 "GRANTS": _show_parser("GRANTS", target="FOR"), 234 "INDEX": _show_parser("INDEX", target="FROM"), 235 "MASTER STATUS": _show_parser("MASTER STATUS"), 236 "OPEN TABLES": _show_parser("OPEN TABLES"), 237 "PLUGINS": _show_parser("PLUGINS"), 238 "PROCEDURE CODE": _show_parser("PROCEDURE CODE", target=True), 239 "PROCEDURE STATUS": _show_parser("PROCEDURE STATUS"), 240 "PRIVILEGES": _show_parser("PRIVILEGES"), 241 "FULL PROCESSLIST": _show_parser("PROCESSLIST", full=True), 242 "PROCESSLIST": _show_parser("PROCESSLIST"), 243 "PROFILE": _show_parser("PROFILE"), 244 "PROFILES": _show_parser("PROFILES"), 245 "RELAYLOG EVENTS": _show_parser("RELAYLOG EVENTS"), 246 "REPLICAS": _show_parser("REPLICAS"), 247 "SLAVE HOSTS": _show_parser("REPLICAS"), 248 "REPLICA STATUS": _show_parser("REPLICA STATUS"), 249 "SLAVE STATUS": _show_parser("REPLICA STATUS"), 250 "GLOBAL STATUS": _show_parser("STATUS", global_=True), 251 "SESSION STATUS": _show_parser("STATUS"), 252 "STATUS": _show_parser("STATUS"), 253 "TABLE STATUS": _show_parser("TABLE STATUS"), 254 "FULL TABLES": _show_parser("TABLES", full=True), 255 "TABLES": _show_parser("TABLES"), 256 "TRIGGERS": _show_parser("TRIGGERS"), 257 "GLOBAL VARIABLES": _show_parser("VARIABLES", global_=True), 258 "SESSION VARIABLES": _show_parser("VARIABLES"), 259 "VARIABLES": _show_parser("VARIABLES"), 260 "WARNINGS": _show_parser("WARNINGS"), 261 } 262 263 SET_PARSERS = { 264 **parser.Parser.SET_PARSERS, 265 "PERSIST": lambda self: self._parse_set_item_assignment("PERSIST"), 266 "PERSIST_ONLY": lambda self: self._parse_set_item_assignment("PERSIST_ONLY"), 267 "CHARACTER SET": lambda self: self._parse_set_item_charset("CHARACTER SET"), 268 "CHARSET": lambda self: self._parse_set_item_charset("CHARACTER SET"), 269 "NAMES": lambda self: self._parse_set_item_names(), 270 } 271 272 PROFILE_TYPES = { 273 "ALL", 274 "BLOCK IO", 275 "CONTEXT SWITCHES", 276 "CPU", 277 "IPC", 278 "MEMORY", 279 "PAGE FAULTS", 280 "SOURCE", 281 "SWAPS", 282 } 283 284 TYPE_TOKENS = { 285 *parser.Parser.TYPE_TOKENS, 286 TokenType.SET, 287 } 288 289 ENUM_TYPE_TOKENS = { 290 *parser.Parser.ENUM_TYPE_TOKENS, 291 TokenType.SET, 292 } 293 294 LOG_DEFAULTS_TO_LN = True 295 296 def _parse_show_mysql( 297 self, 298 this: str, 299 target: bool | str = False, 300 full: t.Optional[bool] = None, 301 global_: t.Optional[bool] = None, 302 ) -> exp.Show: 303 if target: 304 if isinstance(target, str): 305 self._match_text_seq(target) 306 target_id = self._parse_id_var() 307 else: 308 target_id = None 309 310 log = self._parse_string() if self._match_text_seq("IN") else None 311 312 if this in {"BINLOG EVENTS", "RELAYLOG EVENTS"}: 313 position = self._parse_number() if self._match_text_seq("FROM") else None 314 db = None 315 else: 316 position = None 317 db = None 318 319 if self._match(TokenType.FROM): 320 db = self._parse_id_var() 321 elif self._match(TokenType.DOT): 322 db = target_id 323 target_id = self._parse_id_var() 324 325 channel = self._parse_id_var() if self._match_text_seq("FOR", "CHANNEL") else None 326 327 like = self._parse_string() if self._match_text_seq("LIKE") else None 328 where = self._parse_where() 329 330 if this == "PROFILE": 331 types = self._parse_csv(lambda: self._parse_var_from_options(self.PROFILE_TYPES)) 332 query = self._parse_number() if self._match_text_seq("FOR", "QUERY") else None 333 offset = self._parse_number() if self._match_text_seq("OFFSET") else None 334 limit = self._parse_number() if self._match_text_seq("LIMIT") else None 335 else: 336 types, query = None, None 337 offset, limit = self._parse_oldstyle_limit() 338 339 mutex = True if self._match_text_seq("MUTEX") else None 340 mutex = False if self._match_text_seq("STATUS") else mutex 341 342 return self.expression( 343 exp.Show, 344 this=this, 345 target=target_id, 346 full=full, 347 log=log, 348 position=position, 349 db=db, 350 channel=channel, 351 like=like, 352 where=where, 353 types=types, 354 query=query, 355 offset=offset, 356 limit=limit, 357 mutex=mutex, 358 **{"global": global_}, # type: ignore 359 ) 360 361 def _parse_oldstyle_limit( 362 self, 363 ) -> t.Tuple[t.Optional[exp.Expression], t.Optional[exp.Expression]]: 364 limit = None 365 offset = None 366 if self._match_text_seq("LIMIT"): 367 parts = self._parse_csv(self._parse_number) 368 if len(parts) == 1: 369 limit = parts[0] 370 elif len(parts) == 2: 371 limit = parts[1] 372 offset = parts[0] 373 374 return offset, limit 375 376 def _parse_set_item_charset(self, kind: str) -> exp.Expression: 377 this = self._parse_string() or self._parse_id_var() 378 return self.expression(exp.SetItem, this=this, kind=kind) 379 380 def _parse_set_item_names(self) -> exp.Expression: 381 charset = self._parse_string() or self._parse_id_var() 382 if self._match_text_seq("COLLATE"): 383 collate = self._parse_string() or self._parse_id_var() 384 else: 385 collate = None 386 387 return self.expression(exp.SetItem, this=charset, collate=collate, kind="NAMES")
Parser consumes a list of tokens produced by the Tokenizer and produces a parsed syntax tree.
Arguments:
- error_level: The desired error level. Default: ErrorLevel.IMMEDIATE
- error_message_context: Determines the amount of context to capture from a query string when displaying the error message (in number of characters). Default: 100
- max_errors: Maximum number of error messages to include in a raised ParseError. This is only relevant if error_level is ErrorLevel.RAISE. Default: 3
Inherited Members
389 class Generator(generator.Generator): 390 LOCKING_READS_SUPPORTED = True 391 NULL_ORDERING_SUPPORTED = False 392 JOIN_HINTS = False 393 TABLE_HINTS = False 394 395 TRANSFORMS = { 396 **generator.Generator.TRANSFORMS, 397 exp.CurrentDate: no_paren_current_date_sql, 398 exp.DateDiff: lambda self, e: self.func("DATEDIFF", e.this, e.expression), 399 exp.DateAdd: _date_add_sql("ADD"), 400 exp.DateStrToDate: datestrtodate_sql, 401 exp.DateSub: _date_add_sql("SUB"), 402 exp.DateTrunc: _date_trunc_sql, 403 exp.DayOfMonth: rename_func("DAYOFMONTH"), 404 exp.DayOfWeek: rename_func("DAYOFWEEK"), 405 exp.DayOfYear: rename_func("DAYOFYEAR"), 406 exp.GroupConcat: lambda self, e: f"""GROUP_CONCAT({self.sql(e, "this")} SEPARATOR {self.sql(e, "separator") or "','"})""", 407 exp.ILike: no_ilike_sql, 408 exp.JSONExtractScalar: arrow_json_extract_scalar_sql, 409 exp.Max: max_or_greatest, 410 exp.Min: min_or_least, 411 exp.NullSafeEQ: lambda self, e: self.binary(e, "<=>"), 412 exp.NullSafeNEQ: lambda self, e: self.not_sql(self.binary(e, "<=>")), 413 exp.Pivot: no_pivot_sql, 414 exp.Select: transforms.preprocess([transforms.eliminate_distinct_on]), 415 exp.StrPosition: strposition_to_locate_sql, 416 exp.StrToDate: _str_to_date_sql, 417 exp.StrToTime: _str_to_date_sql, 418 exp.TableSample: no_tablesample_sql, 419 exp.TimeStrToUnix: rename_func("UNIX_TIMESTAMP"), 420 exp.TimeToStr: lambda self, e: self.func("DATE_FORMAT", e.this, self.format_time(e)), 421 exp.Trim: _trim_sql, 422 exp.TryCast: no_trycast_sql, 423 exp.WeekOfYear: rename_func("WEEKOFYEAR"), 424 } 425 426 TYPE_MAPPING = generator.Generator.TYPE_MAPPING.copy() 427 TYPE_MAPPING.pop(exp.DataType.Type.MEDIUMTEXT) 428 TYPE_MAPPING.pop(exp.DataType.Type.LONGTEXT) 429 TYPE_MAPPING.pop(exp.DataType.Type.MEDIUMBLOB) 430 TYPE_MAPPING.pop(exp.DataType.Type.LONGBLOB) 431 432 PROPERTIES_LOCATION = { 433 **generator.Generator.PROPERTIES_LOCATION, 434 exp.TransientProperty: exp.Properties.Location.UNSUPPORTED, 435 exp.VolatileProperty: exp.Properties.Location.UNSUPPORTED, 436 } 437 438 LIMIT_FETCH = "LIMIT" 439 440 def show_sql(self, expression: exp.Show) -> str: 441 this = f" {expression.name}" 442 full = " FULL" if expression.args.get("full") else "" 443 global_ = " GLOBAL" if expression.args.get("global") else "" 444 445 target = self.sql(expression, "target") 446 target = f" {target}" if target else "" 447 if expression.name in {"COLUMNS", "INDEX"}: 448 target = f" FROM{target}" 449 elif expression.name == "GRANTS": 450 target = f" FOR{target}" 451 452 db = self._prefixed_sql("FROM", expression, "db") 453 454 like = self._prefixed_sql("LIKE", expression, "like") 455 where = self.sql(expression, "where") 456 457 types = self.expressions(expression, key="types") 458 types = f" {types}" if types else types 459 query = self._prefixed_sql("FOR QUERY", expression, "query") 460 461 if expression.name == "PROFILE": 462 offset = self._prefixed_sql("OFFSET", expression, "offset") 463 limit = self._prefixed_sql("LIMIT", expression, "limit") 464 else: 465 offset = "" 466 limit = self._oldstyle_limit_sql(expression) 467 468 log = self._prefixed_sql("IN", expression, "log") 469 position = self._prefixed_sql("FROM", expression, "position") 470 471 channel = self._prefixed_sql("FOR CHANNEL", expression, "channel") 472 473 if expression.name == "ENGINE": 474 mutex_or_status = " MUTEX" if expression.args.get("mutex") else " STATUS" 475 else: 476 mutex_or_status = "" 477 478 return f"SHOW{full}{global_}{this}{target}{types}{db}{query}{log}{position}{channel}{mutex_or_status}{like}{where}{offset}{limit}" 479 480 def _prefixed_sql(self, prefix: str, expression: exp.Expression, arg: str) -> str: 481 sql = self.sql(expression, arg) 482 return f" {prefix} {sql}" if sql else "" 483 484 def _oldstyle_limit_sql(self, expression: exp.Show) -> str: 485 limit = self.sql(expression, "limit") 486 offset = self.sql(expression, "offset") 487 if limit: 488 limit_offset = f"{offset}, {limit}" if offset else limit 489 return f" LIMIT {limit_offset}" 490 return ""
Generator converts a given syntax tree to the corresponding SQL string.
Arguments:
- pretty: Whether or not to format the produced SQL string. Default: False.
- identify: Determines when an identifier should be quoted. Possible values are: False (default): Never quote, except in cases where it's mandatory by the dialect. True or 'always': Always quote. 'safe': Only quote identifiers that are case insensitive.
- normalize: Whether or not to normalize identifiers to lowercase. Default: False.
- pad: Determines the pad size in a formatted string. Default: 2.
- indent: Determines the indentation size in a formatted string. Default: 2.
- normalize_functions: Whether or not to normalize all function names. Possible values are: "upper" or True (default): Convert names to uppercase. "lower": Convert names to lowercase. False: Disables function name normalization.
- unsupported_level: Determines the generator's behavior when it encounters unsupported expressions. Default ErrorLevel.WARN.
- max_unsupported: Maximum number of unsupported messages to include in a raised UnsupportedError. This is only relevant if unsupported_level is ErrorLevel.RAISE. Default: 3
- leading_comma: Determines whether or not the comma is leading or trailing in select expressions. This is only relevant when generating in pretty mode. Default: False
- max_text_width: The max number of characters in a segment before creating new lines in pretty mode. The default is on the smaller end because the length only represents a segment and not the true line length. Default: 80
- comments: Whether or not to preserve comments in the output SQL code. Default: True
440 def show_sql(self, expression: exp.Show) -> str: 441 this = f" {expression.name}" 442 full = " FULL" if expression.args.get("full") else "" 443 global_ = " GLOBAL" if expression.args.get("global") else "" 444 445 target = self.sql(expression, "target") 446 target = f" {target}" if target else "" 447 if expression.name in {"COLUMNS", "INDEX"}: 448 target = f" FROM{target}" 449 elif expression.name == "GRANTS": 450 target = f" FOR{target}" 451 452 db = self._prefixed_sql("FROM", expression, "db") 453 454 like = self._prefixed_sql("LIKE", expression, "like") 455 where = self.sql(expression, "where") 456 457 types = self.expressions(expression, key="types") 458 types = f" {types}" if types else types 459 query = self._prefixed_sql("FOR QUERY", expression, "query") 460 461 if expression.name == "PROFILE": 462 offset = self._prefixed_sql("OFFSET", expression, "offset") 463 limit = self._prefixed_sql("LIMIT", expression, "limit") 464 else: 465 offset = "" 466 limit = self._oldstyle_limit_sql(expression) 467 468 log = self._prefixed_sql("IN", expression, "log") 469 position = self._prefixed_sql("FROM", expression, "position") 470 471 channel = self._prefixed_sql("FOR CHANNEL", expression, "channel") 472 473 if expression.name == "ENGINE": 474 mutex_or_status = " MUTEX" if expression.args.get("mutex") else " STATUS" 475 else: 476 mutex_or_status = "" 477 478 return f"SHOW{full}{global_}{this}{target}{types}{db}{query}{log}{position}{channel}{mutex_or_status}{like}{where}{offset}{limit}"
Inherited Members
- sqlglot.generator.Generator
- Generator
- generate
- unsupported
- sep
- seg
- pad_comment
- maybe_comment
- wrap
- no_identify
- normalize_func
- indent
- sql
- uncache_sql
- cache_sql
- characterset_sql
- column_sql
- columnposition_sql
- columndef_sql
- columnconstraint_sql
- autoincrementcolumnconstraint_sql
- compresscolumnconstraint_sql
- generatedasidentitycolumnconstraint_sql
- notnullcolumnconstraint_sql
- primarykeycolumnconstraint_sql
- uniquecolumnconstraint_sql
- createable_sql
- create_sql
- clone_sql
- describe_sql
- prepend_ctes
- with_sql
- cte_sql
- tablealias_sql
- bitstring_sql
- hexstring_sql
- bytestring_sql
- rawstring_sql
- datatypesize_sql
- datatype_sql
- directory_sql
- delete_sql
- drop_sql
- except_sql
- except_op
- fetch_sql
- filter_sql
- hint_sql
- index_sql
- identifier_sql
- inputoutputformat_sql
- national_sql
- partition_sql
- properties_sql
- root_properties
- properties
- with_properties
- locate_properties
- property_sql
- likeproperty_sql
- fallbackproperty_sql
- journalproperty_sql
- freespaceproperty_sql
- checksumproperty_sql
- mergeblockratioproperty_sql
- datablocksizeproperty_sql
- blockcompressionproperty_sql
- isolatedloadingproperty_sql
- lockingproperty_sql
- withdataproperty_sql
- insert_sql
- intersect_sql
- intersect_op
- introducer_sql
- pseudotype_sql
- onconflict_sql
- returning_sql
- rowformatdelimitedproperty_sql
- table_sql
- tablesample_sql
- pivot_sql
- tuple_sql
- update_sql
- values_sql
- var_sql
- into_sql
- from_sql
- group_sql
- having_sql
- join_sql
- lambda_sql
- lateral_sql
- limit_sql
- offset_sql
- setitem_sql
- set_sql
- pragma_sql
- lock_sql
- literal_sql
- loaddata_sql
- null_sql
- boolean_sql
- order_sql
- cluster_sql
- distribute_sql
- sort_sql
- ordered_sql
- matchrecognize_sql
- query_modifiers
- offset_limit_modifiers
- after_having_modifiers
- after_limit_modifiers
- select_sql
- schema_sql
- schema_columns_sql
- star_sql
- parameter_sql
- sessionparameter_sql
- placeholder_sql
- subquery_sql
- qualify_sql
- union_sql
- union_op
- unnest_sql
- where_sql
- window_sql
- partition_by_sql
- windowspec_sql
- withingroup_sql
- between_sql
- bracket_sql
- all_sql
- any_sql
- exists_sql
- case_sql
- constraint_sql
- nextvaluefor_sql
- extract_sql
- trim_sql
- safeconcat_sql
- check_sql
- foreignkey_sql
- primarykey_sql
- if_sql
- matchagainst_sql
- jsonkeyvalue_sql
- jsonobject_sql
- openjsoncolumndef_sql
- openjson_sql
- in_sql
- in_unnest_op
- interval_sql
- return_sql
- reference_sql
- anonymous_sql
- paren_sql
- neg_sql
- not_sql
- alias_sql
- aliases_sql
- attimezone_sql
- add_sql
- and_sql
- connector_sql
- bitwiseand_sql
- bitwiseleftshift_sql
- bitwisenot_sql
- bitwiseor_sql
- bitwiserightshift_sql
- bitwisexor_sql
- cast_sql
- currentdate_sql
- collate_sql
- command_sql
- comment_sql
- mergetreettlaction_sql
- mergetreettl_sql
- transaction_sql
- commit_sql
- rollback_sql
- altercolumn_sql
- renametable_sql
- altertable_sql
- droppartition_sql
- addconstraint_sql
- distinct_sql
- ignorenulls_sql
- respectnulls_sql
- intdiv_sql
- dpipe_sql
- safedpipe_sql
- div_sql
- overlaps_sql
- distance_sql
- dot_sql
- eq_sql
- escape_sql
- glob_sql
- gt_sql
- gte_sql
- ilike_sql
- ilikeany_sql
- is_sql
- like_sql
- likeany_sql
- similarto_sql
- lt_sql
- lte_sql
- mod_sql
- mul_sql
- neq_sql
- nullsafeeq_sql
- nullsafeneq_sql
- or_sql
- slice_sql
- sub_sql
- trycast_sql
- use_sql
- binary
- function_fallback_sql
- func
- format_args
- text_width
- format_time
- expressions
- op_expressions
- naked_property
- set_operation
- tag_sql
- token_sql
- userdefinedfunction_sql
- joinhint_sql
- kwarg_sql
- when_sql
- merge_sql
- tochar_sql
- dictproperty_sql
- dictrange_sql
- dictsubproperty_sql
- oncluster_sql