feat: generic sql based on spark sql

CHANGELOG.md

@@ -2,6 +2,34 @@
 
 All notable changes to this project will be documented in this file. See [standard-version](https://github.com/conventional-changelog/standard-version) for commit guidelines.
 
+## [4.1.0-beta.0](https://github.com/DTStack/dt-sql-parser/compare/v4.0.1...v4.1.0-beta.0) (2024-08-27)
+
+
+### Features
+
+* add alter table stmt ([#312](https://github.com/DTStack/dt-sql-parser/issues/312)) ([5aade9e](https://github.com/DTStack/dt-sql-parser/commit/5aade9e6daafc2c6e70c5202d7ef06572ec37f6e))
+* add benchmark test suite ([#273](https://github.com/DTStack/dt-sql-parser/issues/273)) ([de1bd9d](https://github.com/DTStack/dt-sql-parser/commit/de1bd9de4cb7c3b42d51bedd79635eb91afba9ed))
+* **basicSql:** remove judge splitListener/collectListener, all sqlParser implements it ([#316](https://github.com/DTStack/dt-sql-parser/issues/316)) ([eb2e920](https://github.com/DTStack/dt-sql-parser/commit/eb2e920e345aef98285ba261c2060db61d1d56b8))
+* collect entity's attribute([#333](https://github.com/DTStack/dt-sql-parser/issues/333)) ([a3b6b7e](https://github.com/DTStack/dt-sql-parser/commit/a3b6b7eb8bad2444b16481985278461c35360570))
+* **flinksql:** collect comment, type attribute for entity ([#319](https://github.com/DTStack/dt-sql-parser/issues/319)) ([ae52ebd](https://github.com/DTStack/dt-sql-parser/commit/ae52ebdd6b6d1511cf92eb09521b06bdec66ba0d)), closes [#305](https://github.com/DTStack/dt-sql-parser/issues/305)
+* improve errorListener msg ([#281](https://github.com/DTStack/dt-sql-parser/issues/281)) ([deef123](https://github.com/DTStack/dt-sql-parser/commit/deef1238bb25d5bfee80ddaf1fea5ad48178d17b))
+* sync some useful syntax from antlr/grammars-v4 ([95a1087](https://github.com/DTStack/dt-sql-parser/commit/95a108744bb40e418056faaf86bd97b85dd191f8))
+* upgrade trino to 450 ([#323](https://github.com/DTStack/dt-sql-parser/issues/323)) ([2b0de6a](https://github.com/DTStack/dt-sql-parser/commit/2b0de6a3da16561ec52b0c69d4e052226d54a553))
+* use common sql to run benchmark ([#326](https://github.com/DTStack/dt-sql-parser/issues/326)) ([76d0900](https://github.com/DTStack/dt-sql-parser/commit/76d090040e7af26227727673a82f77cda08b3f9e))
+
+
+### Bug Fixes
+
+* alert to alterView ([#346](https://github.com/DTStack/dt-sql-parser/issues/346)) ([9ba5100](https://github.com/DTStack/dt-sql-parser/commit/9ba51007e2f21ab8bc42623596ee281801904cfa))
+* **benchmark:** add reports dir judge and remove plsql and include pgsql ([9c534c2](https://github.com/DTStack/dt-sql-parser/commit/9c534c25cacba3cfba6bd234c68e8f27bd90b2e2))
+* build mysql ([5d6ff46](https://github.com/DTStack/dt-sql-parser/commit/5d6ff4662a11acf9f16b1f18c41c204922890df9))
+* createFunction and createFunctionLoadable ([e83449a](https://github.com/DTStack/dt-sql-parser/commit/e83449a0cc0a50be510c7b4a3337597b1890fc92))
+* flinksql function params add more time functions ([#347](https://github.com/DTStack/dt-sql-parser/issues/347)) ([b835c4b](https://github.com/DTStack/dt-sql-parser/commit/b835c4b5b506c8e4bf0bd9c99fe66c15e53a179b))
+* **impala:** fix alter table change statement ([#332](https://github.com/DTStack/dt-sql-parser/issues/332)) ([4a9681e](https://github.com/DTStack/dt-sql-parser/commit/4a9681ed3bd188e41c30a6d7be39d6e77df7f61b))
+* mysql case when ([#317](https://github.com/DTStack/dt-sql-parser/issues/317)) ([fea1ad1](https://github.com/DTStack/dt-sql-parser/commit/fea1ad1a357b70291a240eca6d2058bab9b49469))
+* **postgresql:** combine plsql_unreserved_keyword to unreserved_keyword and remove unused rules ([7884cbe](https://github.com/DTStack/dt-sql-parser/commit/7884cbe37844c057fa41fde4d0716af43c4023af))
+* spell check ([#337](https://github.com/DTStack/dt-sql-parser/issues/337)) ([694b0cd](https://github.com/DTStack/dt-sql-parser/commit/694b0cdf15943d02a9402a748155a1b06508af95))
+
 ### [4.0.2](https://github.com/DTStack/dt-sql-parser/compare/v4.0.1...v4.0.2) (2024-06-19)
 
 
@@ -61,7 +89,7 @@ All notable changes to this project will be documented in this file. See [standa
 
 ### Features
 
-* add toMatchUnorderedArrary matcher and apply it ([#271](https://github.com/DTStack/dt-sql-parser/issues/271)) ([a05f099](https://github.com/DTStack/dt-sql-parser/commit/a05f099aa1ad555c408bc2018240fb4611ec09b8))
+* add toMatchUnorderedArray matcher and apply it ([#271](https://github.com/DTStack/dt-sql-parser/issues/271)) ([a05f099](https://github.com/DTStack/dt-sql-parser/commit/a05f099aa1ad555c408bc2018240fb4611ec09b8))
 * collect entity ([#265](https://github.com/DTStack/dt-sql-parser/issues/265)) ([a997211](https://github.com/DTStack/dt-sql-parser/commit/a99721162be0d463b513f53bb13ada6d10168548)), closes [#256](https://github.com/DTStack/dt-sql-parser/issues/256) [#263](https://github.com/DTStack/dt-sql-parser/issues/263) [#268](https://github.com/DTStack/dt-sql-parser/issues/268)
 * migrate to antlr4ng ([#267](https://github.com/DTStack/dt-sql-parser/issues/267)) ([195878d](https://github.com/DTStack/dt-sql-parser/commit/195878da9bb1ff8011b5d60c02389fa66d2bc0b8))
 * **spark:** support materialized view for spark sql ([#262](https://github.com/DTStack/dt-sql-parser/issues/262)) ([5ce89cb](https://github.com/DTStack/dt-sql-parser/commit/5ce89cb421de18330d56e23a4ab5b658b2130a0b))

package.json

@@ -1,6 +1,6 @@
 {
   "name": "dt-sql-parser",
-  "version": "4.0.2",
+  "version": "4.1.0-beta.0",
   "authors": "DTStack Corporation",
   "description": "SQL Parsers for BigData, built with antlr4",
   "keywords": [
@@ -70,7 +70,7 @@
   },
   "repository": {
     "type": "git",
-		"url": "https://github.com/DTStack/dt-sql-parser.git"
+    "url": "https://github.com/DTStack/dt-sql-parser.git"
   },
   "publishConfig": {
     "registry": "https://registry.npmjs.org/"
@@ -89,6 +89,8 @@
     "*": [
       "prettier --write --ignore-unknown"
     ],
-    "*.g4": ["antlr-format -c ./antlr.format.json -v"]
+    "*.g4": [
+      "antlr-format -c ./antlr.format.json -v"
+    ]
   }
 }

src/grammar/flink/FlinkSqlParser.g4

@@ -156,8 +156,9 @@ createTable
 simpleCreateTable
     : KW_CREATE KW_TEMPORARY? KW_TABLE ifNotExists? tablePathCreate LR_BRACKET columnOptionDefinition (
         COMMA columnOptionDefinition
-    )* (COMMA watermarkDefinition)? (COMMA tableConstraint)? (COMMA selfDefinitionClause)? RR_BRACKET commentSpec? partitionDefinition? withOption
-        likeDefinition?
+    )* (COMMA watermarkDefinition)? (COMMA tableConstraint)? (COMMA selfDefinitionClause)? RR_BRACKET (
+        KW_COMMENT comment=STRING_LITERAL
+    )? partitionDefinition? withOption likeDefinition?
     ;
 
 /*
@@ -175,7 +176,7 @@ columnOptionDefinition
     ;
 
 physicalColumnDefinition
-    : columnNameCreate columnType columnConstraint? commentSpec?
+    : columnNameCreate columnType columnConstraint? (KW_COMMENT comment=STRING_LITERAL)?
     ;
 
 columnNameCreate
@@ -193,8 +194,8 @@ columnNameList
     ;
 
 columnType
-    : typeName=(KW_DATE | KW_BOOLEAN | KW_NULL)
-    | typeName=(
+    : colType=(KW_DATE | KW_BOOLEAN | KW_NULL)
+    | colType=(
         KW_CHAR
         | KW_VARCHAR
         | KW_STRING
@@ -210,12 +211,12 @@ columnType
         | KW_TIMESTAMP_LTZ
         | KW_DATETIME
     ) lengthOneDimension?
-    | typeName=KW_TIMESTAMP lengthOneDimension? ((KW_WITHOUT | KW_WITH) KW_LOCAL? KW_TIME KW_ZONE)?
-    | typeName=(KW_DECIMAL | KW_DEC | KW_NUMERIC | KW_FLOAT | KW_DOUBLE) lengthTwoOptionalDimension?
-    | type=(KW_ARRAY | KW_MULTISET) lengthOneTypeDimension?
-    | type=KW_MAP mapTypeDimension?
-    | type=KW_ROW rowTypeDimension?
-    | type=KW_RAW lengthTwoStringDimension?
+    | colType=KW_TIMESTAMP lengthOneDimension? ((KW_WITHOUT | KW_WITH) KW_LOCAL? KW_TIME KW_ZONE)?
+    | colType=(KW_DECIMAL | KW_DEC | KW_NUMERIC | KW_FLOAT | KW_DOUBLE) lengthTwoOptionalDimension?
+    | colType=(KW_ARRAY | KW_MULTISET) lengthOneTypeDimension?
+    | colType=KW_MAP mapTypeDimension?
+    | colType=KW_ROW rowTypeDimension?
+    | colType=KW_RAW lengthTwoStringDimension?
     ;
 
 lengthOneDimension
@@ -247,10 +248,6 @@ columnConstraint
     | KW_NOT? KW_NULL
     ;
 
-commentSpec
-    : KW_COMMENT STRING_LITERAL
-    ;
-
 metadataColumnDefinition
     : columnNameCreate columnType KW_METADATA (KW_FROM metadataKey)? KW_VIRTUAL?
     ;
@@ -260,7 +257,7 @@ metadataKey
     ;
 
 computedColumnDefinition
-    : columnNameCreate KW_AS computedColumnExpression commentSpec?
+    : columnNameCreate KW_AS computedColumnExpression (KW_COMMENT comment=STRING_LITERAL)?
     ;
 
 // 计算表达式
@@ -316,11 +313,13 @@ createCatalog
     ;
 
 createDatabase
-    : KW_CREATE KW_DATABASE ifNotExists? databasePathCreate commentSpec? withOption
+    : KW_CREATE KW_DATABASE ifNotExists? databasePathCreate (KW_COMMENT comment=STRING_LITERAL)? withOption
     ;
 
 createView
-    : KW_CREATE KW_TEMPORARY? KW_VIEW ifNotExists? viewPathCreate columnNameList? commentSpec? KW_AS queryStatement
+    : KW_CREATE KW_TEMPORARY? KW_VIEW ifNotExists? viewPathCreate columnNameList? (
+        KW_COMMENT comment=STRING_LITERAL
+    )? KW_AS queryStatement
     ;
 
 createFunction
@@ -513,8 +512,8 @@ tableReference
     ;
 
 tablePrimary
-    : KW_TABLE? tablePath systemTimePeriod? (KW_AS? correlationName)?
-    | viewPath systemTimePeriod? (KW_AS? correlationName)?
+    : KW_TABLE? tablePath systemTimePeriod?
+    | viewPath systemTimePeriod?
     | KW_LATERAL KW_TABLE LR_BRACKET functionName LR_BRACKET functionParam (COMMA functionParam)* RR_BRACKET RR_BRACKET
     | KW_LATERAL? LR_BRACKET queryStatement RR_BRACKET
     | KW_UNNEST LR_BRACKET expression RR_BRACKET
@@ -834,7 +833,7 @@ intervalValue
     ;
 
 tableAlias
-    : KW_AS? identifier identifierList?
+    : KW_AS? alias=identifier identifierList?
     ;
 
 errorCapturingIdentifier

src/grammar/hive/HiveSqlParser.g4

@@ -887,7 +887,9 @@ tableConstraint
     ;
 
 columnNameTypeConstraint
-    : colName=columnNameCreate columnType columnConstraint? (KW_COMMENT comment=StringLiteral)?
+    : colName=columnNameCreate colType=columnType columnConstraint? (
+        KW_COMMENT comment=StringLiteral
+    )?
     ;
 
 columnConstraint
@@ -1363,10 +1365,12 @@ joinToken
     ;
 
 lateralView
-    : KW_LATERAL KW_VIEW KW_OUTER function_ tableAlias (KW_AS id_ (COMMA id_)*)?
+    : KW_LATERAL KW_VIEW KW_OUTER function_ alias=tableAlias (KW_AS id_ (COMMA id_)*)?
     | COMMA? KW_LATERAL (
-        KW_VIEW function_ tableAlias (KW_AS id_ (COMMA id_)*)?
-        | KW_TABLE LPAREN valuesClause RPAREN KW_AS? tableAlias (LPAREN id_ (COMMA id_)* RPAREN)?
+        KW_VIEW function_ alias=tableAlias (KW_AS id_ (COMMA id_)*)?
+        | KW_TABLE LPAREN valuesClause RPAREN KW_AS? alias=tableAlias (
+            LPAREN id_ (COMMA id_)* RPAREN
+        )?
     )
     ;
 

src/grammar/impala/ImpalaSqlParser.g4

@@ -96,20 +96,20 @@ createKuduTableAsSelect
     : KW_CREATE KW_EXTERNAL? KW_TABLE ifNotExists? tableNameCreate (
         LPAREN kuduTableElement (COMMA kuduTableElement)* (COMMA KW_PRIMARY KW_KEY columnAliases)? RPAREN
     )? (KW_PRIMARY KW_KEY columnAliases?)? (KW_PARTITION KW_BY kuduPartitionClause)? (
-        KW_COMMENT stringLiteral
+        commentClause
     )? KW_STORED KW_AS KW_KUDU (KW_TBLPROPERTIES tblProp=properties)? (KW_AS queryStatement)?
     ;
 
 createView
-    : KW_CREATE KW_VIEW ifNotExists? viewNameCreate viewColumns? (KW_COMMENT stringLiteral)? (
+    : KW_CREATE KW_VIEW ifNotExists? viewNameCreate viewColumns? commentClause? (
         KW_TBLPROPERTIES tblProp=properties
     )? KW_AS queryStatement
     ;
 
 createSchema
-    : KW_CREATE (KW_SCHEMA | KW_DATABASE) ifNotExists? databaseNameCreate (
-        KW_COMMENT comment=stringLiteral
-    )? (KW_LOCATION location=stringLiteral)?
+    : KW_CREATE (KW_SCHEMA | KW_DATABASE) ifNotExists? databaseNameCreate (commentClause)? (
+        KW_LOCATION location=stringLiteral
+    )?
     ;
 
 createRole
@@ -119,14 +119,14 @@ createRole
 createAggregateFunction
     : KW_CREATE KW_AGGREGATE? KW_FUNCTION ifNotExists? functionNameCreate (
         LPAREN (type (COMMA type)*)? RPAREN
-    )? KW_RETURNS type (KW_INTERMEDIATE type)? KW_LOCATION STRING (KW_INIT_FN EQ STRING)? KW_UPDATE_FN EQ STRING KW_MERGE_FN EQ STRING (
+    )? KW_RETURNS returnType=type (KW_INTERMEDIATE type)? KW_LOCATION STRING (KW_INIT_FN EQ STRING)? KW_UPDATE_FN EQ STRING KW_MERGE_FN EQ STRING (
         KW_PREPARE_FN EQ STRING
     )? (KW_CLOSEFN EQ STRING)? (KW_SERIALIZE_FN EQ STRING)? (KW_FINALIZE_FN EQ STRING)?
     ;
 
 createFunction
     : KW_CREATE KW_FUNCTION ifNotExists? functionNameCreate (LPAREN (type (COMMA type)*)? RPAREN)? (
-        KW_RETURNS type
+        KW_RETURNS returnType=type
     )? KW_LOCATION STRING KW_SYMBOL EQ symbol=stringLiteral
     ;
 
@@ -569,11 +569,9 @@ tableOrViewPath
     ;
 
 createCommonItem
-    : (KW_SORT KW_BY columnAliases)? (KW_COMMENT comment=stringLiteral)? (
-        KW_ROW KW_FORMAT rowFormat
-    )? (KW_WITH KW_SERDEPROPERTIES serdProp=properties)? (KW_STORED KW_AS fileFormat)? (
-        KW_LOCATION location=stringLiteral
-    )? (
+    : (KW_SORT KW_BY columnAliases)? commentClause? (KW_ROW KW_FORMAT rowFormat)? (
+        KW_WITH KW_SERDEPROPERTIES serdProp=properties
+    )? (KW_STORED KW_AS fileFormat)? (KW_LOCATION location=stringLiteral)? (
         KW_CACHED KW_IN cacheName=qualifiedName (KW_WITH KW_REPLICATION EQ INTEGER_VALUE)?
         | KW_UNCACHED
     )? (KW_TBLPROPERTIES tblProp=properties)?
@@ -588,9 +586,11 @@ assignmentItem
     ;
 
 viewColumns
-    : LPAREN columnNamePathCreate (KW_COMMENT stringLiteral)? (
-        COMMA columnNamePathCreate (KW_COMMENT stringLiteral)?
-    )* RPAREN
+    : LPAREN viewColumnItem? (COMMA viewColumnItem?)* RPAREN
+    ;
+
+viewColumnItem
+    : columnNamePathCreate commentClause?
     ;
 
 queryStatement
@@ -621,19 +621,23 @@ columnSpec
     ;
 
 columnDefinition
-    : columnNamePathCreate type (KW_COMMENT stringLiteral)?
+    : columnNamePathCreate colType=type commentClause?
     ;
 
 kuduTableElement
     : kuduColumnDefinition
     ;
 
 kuduColumnDefinition
-    : columnNamePathCreate type (kuduAttributes kuduAttributes*?)? (KW_COMMENT stringLiteral)? (
+    : columnNamePathCreate colType=type (kuduAttributes kuduAttributes*?)? commentClause? (
         KW_PRIMARY KW_KEY
     )?
     ;
 
+commentClause
+    : KW_COMMENT comment=stringLiteral
+    ;
+
 columnSpecWithKudu
     : columnSpec (kuduAttributes kuduAttributes*?)?
     ;
@@ -838,7 +842,7 @@ sampleType
     ;
 
 aliasedRelation
-    : relationPrimary (KW_AS? identifier columnAliases?)?
+    : relationPrimary (KW_AS? alias=identifier columnAliases?)?
     ;
 
 columnAliases

src/grammar/mysql/MySqlParser.g4

@@ -442,7 +442,7 @@ functionParameter
     ;
 
 routineOption
-    : KW_COMMENT STRING_LITERAL                                                                  # routineComment
+    : KW_COMMENT comment=STRING_LITERAL                                                          # routineComment
     | KW_LANGUAGE KW_SQL                                                                         # routineLanguage
     | KW_NOT? KW_DETERMINISTIC                                                                   # routineBehavior
     | (KW_CONTAINS KW_SQL | KW_NO KW_SQL | KW_READS KW_SQL KW_DATA | KW_MODIFIES KW_SQL KW_DATA) # routineData
@@ -483,7 +483,7 @@ constraintSymbol
     ;
 
 columnDefinition
-    : dataType columnConstraint*
+    : colType=dataType columnConstraint*
     ;
 
 columnConstraint
@@ -494,7 +494,7 @@ columnConstraint
     | (KW_AUTO_INCREMENT | KW_ON KW_UPDATE currentTimestamp)                       # autoIncrementColumnConstraint
     | KW_PRIMARY? KW_KEY                                                           # primaryKeyColumnConstraint
     | KW_UNIQUE KW_KEY?                                                            # uniqueKeyColumnConstraint
-    | KW_COMMENT STRING_LITERAL                                                    # commentColumnConstraint
+    | KW_COMMENT comment=STRING_LITERAL                                            # commentColumnConstraint
     | KW_COLUMN_FORMAT colformat=(KW_FIXED | KW_DYNAMIC | KW_DEFAULT)              # formatColumnConstraint
     | KW_STORAGE storageval=(KW_DISK | KW_MEMORY | KW_DEFAULT)                     # storageColumnConstraint
     | referenceDefinition                                                          # referenceColumnConstraint
@@ -536,7 +536,7 @@ tableOption
     | KW_DEFAULT? charSet '='? (charsetName | KW_DEFAULT)              # tableOptionCharset
     | (KW_CHECKSUM | KW_PAGE_CHECKSUM) '='? boolValue=('0' | '1')      # tableOptionChecksum
     | KW_DEFAULT? KW_COLLATE '='? collationName                        # tableOptionCollate
-    | KW_COMMENT '='? STRING_LITERAL                                   # tableOptionComment
+    | KW_COMMENT '='? comment=STRING_LITERAL                           # tableOptionComment
     | KW_COMPRESSION '='? (STRING_LITERAL | ID)                        # tableOptionCompression
     | KW_CONNECTION '='? STRING_LITERAL                                # tableOptionConnection
     | (KW_DATA | KW_INDEX) KW_DIRECTORY '='? STRING_LITERAL            # tableOptionDataDirectory

src/grammar/postgresql/PostgreSqlParser.g4

@@ -620,7 +620,7 @@ typedtableelement
     ;
 
 column_def
-    : column_name_create typename create_generic_options? (
+    : column_name_create colType=typename create_generic_options? (
         KW_STORAGE (KW_PLAIN | KW_EXTERNAL | KW_EXTENDED | KW_MAIN | KW_DEFAULT | colid)
     )? (KW_COMPRESSION colid)? (opt_collate_clause)? (KW_WITH KW_OPTIONS)? colconstraint*
     ;
@@ -2163,12 +2163,12 @@ table_ref
     ;
 
 alias_clause
-    : KW_AS? colid (OPEN_PAREN name_list CLOSE_PAREN)?
+    : KW_AS? alias=colid (OPEN_PAREN name_list CLOSE_PAREN)?
     ;
 
 func_alias_clause
     : alias_clause
-    | (KW_AS colid? | colid) OPEN_PAREN tablefuncelementlist CLOSE_PAREN
+    | (KW_AS alias=colid? | alias=colid) OPEN_PAREN tablefuncelementlist CLOSE_PAREN
     ;
 
 join_type
@@ -2598,7 +2598,7 @@ func_arg_list
 func_arg_expr
     : column_name
     | expression
-    | type_function_name (COLON_EQUALS | EQUALS_GREATER) expression
+    | type_function_name ((COLON_EQUALS | EQUALS_GREATER) expression)?
     ;
 
 array_expr