feat: unify variables in lexer

DTStack · Nov 11, 2024 · e1dde71 · e1dde71
1 parent 2358d95
commit e1dde71
Show file tree

Hide file tree

Showing 43 changed files with 2,472 additions and 2,505 deletions.
diff --git a/src/grammar/flink/FlinkSqlLexer.g4 b/src/grammar/flink/FlinkSqlLexer.g4
@@ -11,8 +11,8 @@ options {
 
 // SKIP
 
-SPACE         : [ \t\r\n]+                                                         -> channel(HIDDEN);
-COMMENT_INPUT : '/*' .*? '*/'                                                      -> channel(HIDDEN);
+WHITE_SPACE       : [ \t\r\n]+                                                     -> channel(HIDDEN);
+BRACKETED_COMMENT : '/*' .*? '*/'                                                  -> channel(HIDDEN);
 LINE_COMMENT: (('--' | '#') ~[\r\n]* ('\r'? '\n' | EOF) | '--' ('\r'? '\n' | EOF)) -> channel(HIDDEN);
 
 /**

diff --git a/src/grammar/impala/ImpalaSqlLexer.g4 b/src/grammar/impala/ImpalaSqlLexer.g4
@@ -334,20 +334,20 @@ QUOTED_IDENTIFIER: '"' ( ~'"' | '""')* '"';
 
 BACKQUOTED_IDENTIFIER: '`' ( ~'`' | '``')* '`';
 
-TIME_WITH_TIME_ZONE: 'TIME' WS 'WITH' WS 'TIME' WS 'ZONE';
+TIME_WITH_TIME_ZONE: 'TIME' WHITE_SPACE 'WITH' WHITE_SPACE 'TIME' WHITE_SPACE 'ZONE';
 
-TIMESTAMP_WITH_TIME_ZONE: 'TIMESTAMP' WS 'WITH' WS 'TIME' WS 'ZONE';
+TIMESTAMP_WITH_TIME_ZONE: 'TIMESTAMP' WHITE_SPACE 'WITH' WHITE_SPACE 'TIME' WHITE_SPACE 'ZONE';
 
-DOUBLE_PRECISION: 'DOUBLE' WS 'PRECISION';
+DOUBLE_PRECISION: 'DOUBLE' WHITE_SPACE 'PRECISION';
 
 fragment EXPONENT: 'E' [+-]? DIGIT+;
 
 fragment DIGIT: [0-9];
 
 fragment LETTER: [A-Z];
 
-SIMPLE_COMMENT: '--' ~[\r\n]* '\r'? '\n'? -> channel(HIDDEN);
+LINE_COMMENT: '--' ~[\r\n]* '\r'? '\n'? -> channel(HIDDEN);
 
 BRACKETED_COMMENT: '/*' .*? '*/' -> channel(HIDDEN);
 
-WS: [ \r\n\t]+ -> channel(HIDDEN);
+WHITE_SPACE: [ \r\n\t]+ -> channel(HIDDEN);
diff --git a/src/grammar/mysql/MySqlLexer.g4 b/src/grammar/mysql/MySqlLexer.g4
@@ -1,27 +1,23 @@
 /*
-MySQL (Positive Technologies) grammar
-The MIT License (MIT).
-Copyright (c) 2015-2017, Ivan Kochurkin ([email protected]), Positive Technologies.
-Copyright (c) 2017, Ivan Khudyashev ([email protected])
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in
-all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
-THE SOFTWARE.
-*/
+ MySQL (Positive Technologies) grammar The MIT License (MIT). Copyright (c) 2015-2017, Ivan
+ Kochurkin ([email protected]), Positive Technologies. Copyright (c) 2017, Ivan Khudyashev
+ ([email protected])
+ 
+ Permission is hereby granted, free of charge, to any person obtaining a copy of this software and
+ associated documentation files (the "Software"), to deal in the Software without restriction,
+ including without limitation the rights to use, copy, modify, merge, publish, distribute,
+ sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is
+ furnished to do so, subject to the following conditions:
+ 
+ The above copyright notice and this permission notice shall be included in all copies or
+ substantial portions of the Software.
+ 
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT
+ NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT
+ OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
 
 // https://github.com/antlr/grammars-v4/blob/master/sql/mysql/Positive-Technologies/MySqlLexer.g4
 
@@ -41,9 +37,9 @@ channels {
     ERRORCHANNEL
 }
 
-SPACE              : [ \t\r\n]+                                                           -> channel(HIDDEN);
+WHITE_SPACE        : [ \t\r\n]+                                                           -> channel(HIDDEN);
 SPEC_MYSQL_COMMENT : '/*!' .+? '*/'                                                       -> channel(MYSQLCOMMENT);
-COMMENT_INPUT      : '/*' .*? '*/'                                                        -> channel(HIDDEN);
+BRACKETED_COMMENT  : '/*' .*? '*/'                                                        -> channel(HIDDEN);
 LINE_COMMENT: (('--' [ \t]* | '#') ~[\r\n]* ('\r'? '\n' | EOF) | '--' ('\r'? '\n' | EOF)) -> channel(HIDDEN);
 
 // Keywords

diff --git a/src/grammar/postgresql/PostgreSqlLexer.g4 b/src/grammar/postgresql/PostgreSqlLexer.g4
@@ -804,22 +804,19 @@ PLSQLIDENTIFIER: ':"' ('\\' . | '""' | ~ ('"' | '\\'))* '"';
 
 //
 
-Whitespace: [ \t]+ -> channel (HIDDEN);
-
-Newline: ('\r' '\n'? | '\n') -> channel (HIDDEN);
-//
+WHITE_SPACE: (' ' | '\r' | '\t' | '\n') -> channel(HIDDEN);
 
 // COMMENTS (4.1.5)
 
 //
 
-LineComment: '--' ~ [\r\n]* -> channel (HIDDEN);
+LINE_COMMENT: '--' ~ [\r\n]* -> channel (HIDDEN);
 
-BlockComment: ('/*' ( '/'* BlockComment | ~ [/*] | '/'+ ~ [/*] | '*'+ ~ [/*])* '*'* '*/') -> channel (HIDDEN);
+BRACKETED_COMMENT: ('/*' ( '/'* BRACKETED_COMMENT | ~ [/*] | '/'+ ~ [/*] | '*'+ ~ [/*])* '*'* '*/') -> channel (HIDDEN);
 
 UnterminatedBlockComment:
     '/*' (
-        '/'* BlockComment
+        '/'* BRACKETED_COMMENT
         | // these characters are not part of special sequences in a block comment
         ~ [/*]
         |
@@ -886,18 +883,14 @@ InvalidUnterminatedEscapeStringConstant:
 fragment InvalidEscapeStringText: ('\'\'' | '\\' . | ~ ['\\])*;
 
 mode AfterEscapeStringConstantMode;
-AfterEscapeStringConstantMode_Whitespace: Whitespace -> type (Whitespace), channel (HIDDEN);
+AfterEscapeStringConstantMode_Whitespace: WHITE_SPACE -> type (WHITE_SPACE), channel (HIDDEN);
 
-AfterEscapeStringConstantMode_Newline:
-    Newline -> type (Newline), channel (HIDDEN), mode (AfterEscapeStringConstantWithNewlineMode);
 //
 // AfterEscapeStringConstantMode_NotContinued: '\\' ~[\r\n] -> skip, popMode;
 
 mode AfterEscapeStringConstantWithNewlineMode;
 AfterEscapeStringConstantWithNewlineMode_Whitespace:
-    Whitespace -> type (Whitespace), channel (HIDDEN);
-
-AfterEscapeStringConstantWithNewlineMode_Newline: Newline -> type (Newline), channel (HIDDEN);
+    WHITE_SPACE -> type (WHITE_SPACE), channel (HIDDEN);
 
 AfterEscapeStringConstantWithNewlineMode_Continued:
     '\'' -> more, mode (EscapeStringConstantMode);

diff --git a/src/grammar/spark/SparkSqlLexer.g4 b/src/grammar/spark/SparkSqlLexer.g4
@@ -476,12 +476,12 @@ fragment DIGIT: [0-9];
 
 fragment LETTER: [A-Z];
 
-SIMPLE_COMMENT: '--' ('\\\n' | ~[\r\n])* '\r'? '\n'? -> channel(HIDDEN);
+LINE_COMMENT: '--' ('\\\n' | ~[\r\n])* '\r'? '\n'? -> channel(HIDDEN);
 
 BRACKETED_COMMENT:
     '/*' (BRACKETED_COMMENT | .)*? ('*/' | {this.markUnclosedComment();} EOF) -> channel(HIDDEN);
 
-WS: [ \r\n\t]+ -> channel(HIDDEN);
+WHITE_SPACE: [ \r\n\t]+ -> channel(HIDDEN);
 
 // Catch-all for anything we can't recognize.
 // We use this to be able to ignore and recover all the text

diff --git a/src/grammar/trino/TrinoSql.g4 b/src/grammar/trino/TrinoSql.g4
@@ -1646,11 +1646,11 @@ fragment DIGIT: [0-9];
 
 fragment LETTER: [A-Z];
 
-SIMPLE_COMMENT: '--' ~[\r\n]* '\r'? '\n'? -> channel(HIDDEN);
+LINE_COMMENT: '--' ~[\r\n]* '\r'? '\n'? -> channel(HIDDEN);
 
 BRACKETED_COMMENT: '/*' .*? '*/' -> channel(HIDDEN);
 
-WS: [ \r\n\t]+ -> channel(HIDDEN);
+WHITE_SPACE: [ \r\n\t]+ -> channel(HIDDEN);
 
 // Catch-all for anything we can't recognize.
 // We use this to be able to ignore and recover all the text

diff --git a/src/lib/flink/FlinkSqlLexer.interp b/src/lib/flink/FlinkSqlLexer.interp
@@ -544,8 +544,8 @@ null
 
 token symbolic names:
 null
-SPACE
-COMMENT_INPUT
+WHITE_SPACE
+BRACKETED_COMMENT
 LINE_COMMENT
 KW_ABS
 KW_ALL
@@ -1087,8 +1087,8 @@ BIT_STRING
 ID_LITERAL
 
 rule names:
-SPACE
-COMMENT_INPUT
+WHITE_SPACE
+BRACKETED_COMMENT
 LINE_COMMENT
 KW_ABS
 KW_ALL

diff --git a/src/lib/flink/FlinkSqlLexer.tokens b/src/lib/flink/FlinkSqlLexer.tokens
@@ -1,5 +1,5 @@
-SPACE=1
-COMMENT_INPUT=2
+WHITE_SPACE=1
+BRACKETED_COMMENT=2
 LINE_COMMENT=3
 KW_ABS=4
 KW_ALL=5

diff --git a/src/lib/flink/FlinkSqlLexer.ts b/src/lib/flink/FlinkSqlLexer.ts
@@ -7,8 +7,8 @@ import { Token } from "antlr4ng";
 
 
 export class FlinkSqlLexer extends antlr.Lexer {
-    public static readonly SPACE = 1;
-    public static readonly COMMENT_INPUT = 2;
+    public static readonly WHITE_SPACE = 1;
+    public static readonly BRACKETED_COMMENT = 2;
     public static readonly LINE_COMMENT = 3;
     public static readonly KW_ABS = 4;
     public static readonly KW_ALL = 5;
@@ -655,21 +655,22 @@ export class FlinkSqlLexer extends antlr.Lexer {
     ];
 
     public static readonly symbolicNames = [
-        null, "SPACE", "COMMENT_INPUT", "LINE_COMMENT", "KW_ABS", "KW_ALL", 
-        "KW_ALLOCATE", "KW_ALLOW", "KW_ALTER", "KW_ANALYZE", "KW_AND", "KW_ANY", 
-        "KW_ARE", "KW_ARRAY", "KW_ARRAY_AGG", "KW_ARRAY_CONCAT_AGG", "KW_ARRAY_MAX_CARDINALITY", 
-        "KW_AS", "KW_ASENSITIVE", "KW_ASYMMETRIC", "KW_AT", "KW_ATOMIC", 
-        "KW_AUTHORIZATION", "KW_AVG", "KW_BEGIN", "KW_BEGIN_FRAME", "KW_BEGIN_PARTITION", 
-        "KW_BETWEEN", "KW_BIGINT", "KW_BINARY", "KW_BIT", "KW_BLOB", "KW_BOOLEAN", 
-        "KW_BOTH", "KW_BY", "KW_BYTES", "KW_CALL", "KW_CALLED", "KW_CARDINALITY", 
-        "KW_CASCADED", "KW_CASE", "KW_CAST", "KW_CATALOGS", "KW_CEIL", "KW_CEILING", 
-        "KW_CHANGELOG_MODE", "KW_CHAR", "KW_CHARACTER", "KW_CHARACTER_LENGTH", 
-        "KW_CHAR_LENGTH", "KW_CHECK", "KW_CLASSIFIER", "KW_CLOB", "KW_CLOSE", 
-        "KW_COALESCE", "KW_COLLATE", "KW_COLLECT", "KW_COLUMN", "KW_COLUMNS", 
-        "KW_COMMENT", "KW_COMMIT", "KW_COMPUTE", "KW_CONDITION", "KW_CONNECT", 
-        "KW_CONSTRAINT", "KW_CONTAINS", "KW_CONVERT", "KW_CORR", "KW_CORRESPONDING", 
-        "KW_COUNT", "KW_COVAR_POP", "KW_COVAR_SAMP", "KW_CREATE", "KW_CROSS", 
-        "KW_CUBE", "KW_CUME_DIST", "KW_CURRENT", "KW_CURRENT_CATALOG", "KW_CURRENT_DATE", 
+        null, "WHITE_SPACE", "BRACKETED_COMMENT", "LINE_COMMENT", "KW_ABS", 
+        "KW_ALL", "KW_ALLOCATE", "KW_ALLOW", "KW_ALTER", "KW_ANALYZE", "KW_AND", 
+        "KW_ANY", "KW_ARE", "KW_ARRAY", "KW_ARRAY_AGG", "KW_ARRAY_CONCAT_AGG", 
+        "KW_ARRAY_MAX_CARDINALITY", "KW_AS", "KW_ASENSITIVE", "KW_ASYMMETRIC", 
+        "KW_AT", "KW_ATOMIC", "KW_AUTHORIZATION", "KW_AVG", "KW_BEGIN", 
+        "KW_BEGIN_FRAME", "KW_BEGIN_PARTITION", "KW_BETWEEN", "KW_BIGINT", 
+        "KW_BINARY", "KW_BIT", "KW_BLOB", "KW_BOOLEAN", "KW_BOTH", "KW_BY", 
+        "KW_BYTES", "KW_CALL", "KW_CALLED", "KW_CARDINALITY", "KW_CASCADED", 
+        "KW_CASE", "KW_CAST", "KW_CATALOGS", "KW_CEIL", "KW_CEILING", "KW_CHANGELOG_MODE", 
+        "KW_CHAR", "KW_CHARACTER", "KW_CHARACTER_LENGTH", "KW_CHAR_LENGTH", 
+        "KW_CHECK", "KW_CLASSIFIER", "KW_CLOB", "KW_CLOSE", "KW_COALESCE", 
+        "KW_COLLATE", "KW_COLLECT", "KW_COLUMN", "KW_COLUMNS", "KW_COMMENT", 
+        "KW_COMMIT", "KW_COMPUTE", "KW_CONDITION", "KW_CONNECT", "KW_CONSTRAINT", 
+        "KW_CONTAINS", "KW_CONVERT", "KW_CORR", "KW_CORRESPONDING", "KW_COUNT", 
+        "KW_COVAR_POP", "KW_COVAR_SAMP", "KW_CREATE", "KW_CROSS", "KW_CUBE", 
+        "KW_CUME_DIST", "KW_CURRENT", "KW_CURRENT_CATALOG", "KW_CURRENT_DATE", 
         "KW_CURRENT_DEFAULT_TRANSFORM_GROUP", "KW_CURRENT_PATH", "KW_CURRENT_ROLE", 
         "KW_CURRENT_ROW", "KW_CURRENT_SCHEMA", "KW_CURRENT_TIME", "KW_CURRENT_TIMESTAMP", 
         "KW_CURRENT_TRANSFORM_GROUP_FOR_TYPE", "KW_CURRENT_USER", "KW_CURSOR", 
@@ -770,9 +771,9 @@ export class FlinkSqlLexer extends antlr.Lexer {
     ];
 
     public static readonly ruleNames = [
-        "SPACE", "COMMENT_INPUT", "LINE_COMMENT", "KW_ABS", "KW_ALL", "KW_ALLOCATE", 
-        "KW_ALLOW", "KW_ALTER", "KW_ANALYZE", "KW_AND", "KW_ANY", "KW_ARE", 
-        "KW_ARRAY", "KW_ARRAY_AGG", "KW_ARRAY_CONCAT_AGG", "KW_ARRAY_MAX_CARDINALITY", 
+        "WHITE_SPACE", "BRACKETED_COMMENT", "LINE_COMMENT", "KW_ABS", "KW_ALL", 
+        "KW_ALLOCATE", "KW_ALLOW", "KW_ALTER", "KW_ANALYZE", "KW_AND", "KW_ANY", 
+        "KW_ARE", "KW_ARRAY", "KW_ARRAY_AGG", "KW_ARRAY_CONCAT_AGG", "KW_ARRAY_MAX_CARDINALITY", 
         "KW_AS", "KW_ASENSITIVE", "KW_ASYMMETRIC", "KW_AT", "KW_ATOMIC", 
         "KW_AUTHORIZATION", "KW_AVG", "KW_BEGIN", "KW_BEGIN_FRAME", "KW_BEGIN_PARTITION", 
         "KW_BETWEEN", "KW_BIGINT", "KW_BINARY", "KW_BIT", "KW_BLOB", "KW_BOOLEAN", 

diff --git a/src/lib/flink/FlinkSqlParser.interp b/src/lib/flink/FlinkSqlParser.interp
@@ -544,8 +544,8 @@ null
 
 token symbolic names:
 null
-SPACE
-COMMENT_INPUT
+WHITE_SPACE
+BRACKETED_COMMENT
 LINE_COMMENT
 KW_ABS
 KW_ALL

diff --git a/src/lib/flink/FlinkSqlParser.tokens b/src/lib/flink/FlinkSqlParser.tokens
@@ -1,5 +1,5 @@
-SPACE=1
-COMMENT_INPUT=2
+WHITE_SPACE=1
+BRACKETED_COMMENT=2
 LINE_COMMENT=3
 KW_ABS=4
 KW_ALL=5

diff --git a/src/lib/flink/FlinkSqlParser.ts b/src/lib/flink/FlinkSqlParser.ts
@@ -17,8 +17,8 @@ import { SQLParserBase } from '../SQLParserBase';
 
 
 export class FlinkSqlParser extends SQLParserBase {
-    public static readonly SPACE = 1;
-    public static readonly COMMENT_INPUT = 2;
+    public static readonly WHITE_SPACE = 1;
+    public static readonly BRACKETED_COMMENT = 2;
     public static readonly LINE_COMMENT = 3;
     public static readonly KW_ABS = 4;
     public static readonly KW_ALL = 5;
@@ -848,21 +848,22 @@ export class FlinkSqlParser extends SQLParserBase {
     ];
 
     public static readonly symbolicNames = [
-        null, "SPACE", "COMMENT_INPUT", "LINE_COMMENT", "KW_ABS", "KW_ALL", 
-        "KW_ALLOCATE", "KW_ALLOW", "KW_ALTER", "KW_ANALYZE", "KW_AND", "KW_ANY", 
-        "KW_ARE", "KW_ARRAY", "KW_ARRAY_AGG", "KW_ARRAY_CONCAT_AGG", "KW_ARRAY_MAX_CARDINALITY", 
-        "KW_AS", "KW_ASENSITIVE", "KW_ASYMMETRIC", "KW_AT", "KW_ATOMIC", 
-        "KW_AUTHORIZATION", "KW_AVG", "KW_BEGIN", "KW_BEGIN_FRAME", "KW_BEGIN_PARTITION", 
-        "KW_BETWEEN", "KW_BIGINT", "KW_BINARY", "KW_BIT", "KW_BLOB", "KW_BOOLEAN", 
-        "KW_BOTH", "KW_BY", "KW_BYTES", "KW_CALL", "KW_CALLED", "KW_CARDINALITY", 
-        "KW_CASCADED", "KW_CASE", "KW_CAST", "KW_CATALOGS", "KW_CEIL", "KW_CEILING", 
-        "KW_CHANGELOG_MODE", "KW_CHAR", "KW_CHARACTER", "KW_CHARACTER_LENGTH", 
-        "KW_CHAR_LENGTH", "KW_CHECK", "KW_CLASSIFIER", "KW_CLOB", "KW_CLOSE", 
-        "KW_COALESCE", "KW_COLLATE", "KW_COLLECT", "KW_COLUMN", "KW_COLUMNS", 
-        "KW_COMMENT", "KW_COMMIT", "KW_COMPUTE", "KW_CONDITION", "KW_CONNECT", 
-        "KW_CONSTRAINT", "KW_CONTAINS", "KW_CONVERT", "KW_CORR", "KW_CORRESPONDING", 
-        "KW_COUNT", "KW_COVAR_POP", "KW_COVAR_SAMP", "KW_CREATE", "KW_CROSS", 
-        "KW_CUBE", "KW_CUME_DIST", "KW_CURRENT", "KW_CURRENT_CATALOG", "KW_CURRENT_DATE", 
+        null, "WHITE_SPACE", "BRACKETED_COMMENT", "LINE_COMMENT", "KW_ABS", 
+        "KW_ALL", "KW_ALLOCATE", "KW_ALLOW", "KW_ALTER", "KW_ANALYZE", "KW_AND", 
+        "KW_ANY", "KW_ARE", "KW_ARRAY", "KW_ARRAY_AGG", "KW_ARRAY_CONCAT_AGG", 
+        "KW_ARRAY_MAX_CARDINALITY", "KW_AS", "KW_ASENSITIVE", "KW_ASYMMETRIC", 
+        "KW_AT", "KW_ATOMIC", "KW_AUTHORIZATION", "KW_AVG", "KW_BEGIN", 
+        "KW_BEGIN_FRAME", "KW_BEGIN_PARTITION", "KW_BETWEEN", "KW_BIGINT", 
+        "KW_BINARY", "KW_BIT", "KW_BLOB", "KW_BOOLEAN", "KW_BOTH", "KW_BY", 
+        "KW_BYTES", "KW_CALL", "KW_CALLED", "KW_CARDINALITY", "KW_CASCADED", 
+        "KW_CASE", "KW_CAST", "KW_CATALOGS", "KW_CEIL", "KW_CEILING", "KW_CHANGELOG_MODE", 
+        "KW_CHAR", "KW_CHARACTER", "KW_CHARACTER_LENGTH", "KW_CHAR_LENGTH", 
+        "KW_CHECK", "KW_CLASSIFIER", "KW_CLOB", "KW_CLOSE", "KW_COALESCE", 
+        "KW_COLLATE", "KW_COLLECT", "KW_COLUMN", "KW_COLUMNS", "KW_COMMENT", 
+        "KW_COMMIT", "KW_COMPUTE", "KW_CONDITION", "KW_CONNECT", "KW_CONSTRAINT", 
+        "KW_CONTAINS", "KW_CONVERT", "KW_CORR", "KW_CORRESPONDING", "KW_COUNT", 
+        "KW_COVAR_POP", "KW_COVAR_SAMP", "KW_CREATE", "KW_CROSS", "KW_CUBE", 
+        "KW_CUME_DIST", "KW_CURRENT", "KW_CURRENT_CATALOG", "KW_CURRENT_DATE", 
         "KW_CURRENT_DEFAULT_TRANSFORM_GROUP", "KW_CURRENT_PATH", "KW_CURRENT_ROLE", 
         "KW_CURRENT_ROW", "KW_CURRENT_SCHEMA", "KW_CURRENT_TIME", "KW_CURRENT_TIMESTAMP", 
         "KW_CURRENT_TRANSFORM_GROUP_FOR_TYPE", "KW_CURRENT_USER", "KW_CURSOR", 

diff --git a/src/lib/impala/ImpalaSqlLexer.interp b/src/lib/impala/ImpalaSqlLexer.interp
@@ -578,9 +578,9 @@ BACKQUOTED_IDENTIFIER
 TIME_WITH_TIME_ZONE
 TIMESTAMP_WITH_TIME_ZONE
 DOUBLE_PRECISION
-SIMPLE_COMMENT
+LINE_COMMENT
 BRACKETED_COMMENT
-WS
+WHITE_SPACE
 
 rule names:
 KW_ADD
@@ -872,9 +872,9 @@ DOUBLE_PRECISION
 EXPONENT
 DIGIT
 LETTER
-SIMPLE_COMMENT
+LINE_COMMENT
 BRACKETED_COMMENT
-WS
+WHITE_SPACE
 
 channel names:
 DEFAULT_TOKEN_CHANNEL

diff --git a/src/lib/impala/ImpalaSqlLexer.tokens b/src/lib/impala/ImpalaSqlLexer.tokens
@@ -284,9 +284,9 @@ BACKQUOTED_IDENTIFIER=283
 TIME_WITH_TIME_ZONE=284
 TIMESTAMP_WITH_TIME_ZONE=285
 DOUBLE_PRECISION=286
-SIMPLE_COMMENT=287
+LINE_COMMENT=287
 BRACKETED_COMMENT=288
-WS=289
+WHITE_SPACE=289
 'ADD'=1
 'ALL'=2
 'ANALYTIC'=3