From 6f1d34b6fe3e9c1fb98db7b21a6debc03baa55ec Mon Sep 17 00:00:00 2001
From: Nick Mancuso <nicholas.mancuso13@gmail.com>
Date: Fri, 2 Feb 2024 14:27:04 -0500
Subject: [PATCH] minor: clean up token test and generation

---
 .../grammar/java/JavaLanguageLexer.g4         |  2 -
 .../grammar/GeneratedJavaTokenTypesTest.java  | 50 ++++++++++++-------
 2 files changed, 32 insertions(+), 20 deletions(-)

diff --git a/src/main/resources/com/puppycrawl/tools/checkstyle/grammar/java/JavaLanguageLexer.g4 b/src/main/resources/com/puppycrawl/tools/checkstyle/grammar/java/JavaLanguageLexer.g4
index c40df529504..6acaec69dd1 100644
--- a/src/main/resources/com/puppycrawl/tools/checkstyle/grammar/java/JavaLanguageLexer.g4
+++ b/src/main/resources/com/puppycrawl/tools/checkstyle/grammar/java/JavaLanguageLexer.g4
@@ -168,7 +168,6 @@ LITERAL_CASE:            'case';
 LITERAL_CATCH:           'catch';
 LITERAL_CHAR:            'char';
 LITERAL_CLASS:           'class';
-LITERAL_CONST:           'const';
 LITERAL_CONTINUE:        'continue';
 LITERAL_DEFAULT:         'default';
 LITERAL_DO:              'do';
@@ -181,7 +180,6 @@ LITERAL_FINALLY:         'finally';
 LITERAL_FLOAT:           'float';
 LITERAL_FOR:             'for';
 LITERAL_IF:              'if';
-LITERAL_GOTO:            'goto';
 LITERAL_IMPLEMENTS:      'implements';
 IMPORT:                  'import';
 LITERAL_INSTANCEOF:      'instanceof';
diff --git a/src/test/java/com/puppycrawl/tools/checkstyle/grammar/GeneratedJavaTokenTypesTest.java b/src/test/java/com/puppycrawl/tools/checkstyle/grammar/GeneratedJavaTokenTypesTest.java
index c67efbdbd4c..f0bc432cc45 100644
--- a/src/test/java/com/puppycrawl/tools/checkstyle/grammar/GeneratedJavaTokenTypesTest.java
+++ b/src/test/java/com/puppycrawl/tools/checkstyle/grammar/GeneratedJavaTokenTypesTest.java
@@ -27,6 +27,7 @@
 import java.util.Collections;
 import java.util.List;
 import java.util.Objects;
+import java.util.Set;
 import java.util.stream.Collectors;
 
 import org.antlr.v4.runtime.VocabularyImpl;
@@ -43,6 +44,23 @@
  */
 public class GeneratedJavaTokenTypesTest {
 
+    /**
+     * The following tokens are not declared in the lexer's 'tokens' block,
+     * they will always appear last in the list of symbolic names provided
+     * by the vocabulary. They are not part of the public API and are only
+     * used as components of parser rules.
+     */
+    private static final List<String> INTERNAL_TOKENS = List.of(
+            "DECIMAL_LITERAL_LONG",
+            "DECIMAL_LITERAL",
+            "HEX_LITERAL_LONG",
+            "HEX_LITERAL",
+            "OCT_LITERAL_LONG",
+            "OCT_LITERAL",
+            "BINARY_LITERAL_LONG",
+            "BINARY_LITERAL"
+    );
+
     /**
      * <p>
      * New tokens must be added onto the end of the list with new numbers, and
@@ -73,6 +91,9 @@ public void testTokenNumbering() {
         assertWithMessage(message)
             .that(JavaLanguageLexer.COMPILATION_UNIT)
             .isEqualTo(1);
+        assertWithMessage(message)
+            .that(JavaLanguageLexer.PLACEHOLDER1)
+            .isEqualTo(2);
         assertWithMessage(message)
             .that(JavaLanguageLexer.NULL_TREE_LOOKAHEAD)
             .isEqualTo(3);
@@ -743,16 +764,23 @@ public void testTokenNumbering() {
             .that(JavaLanguageLexer.UNNAMED_PATTERN_DEF)
             .isEqualTo(225);
 
+        final Set<String> modeNames = Set.of(JavaLanguageLexer.modeNames);
+        final Set<String> channelNames = Set.of(JavaLanguageLexer.channelNames);
+
         final int tokenCount = (int) Arrays.stream(JavaLanguageLexer.class.getDeclaredFields())
                 .filter(GeneratedJavaTokenTypesTest::isPublicStaticFinalInt)
+                .filter(field -> !modeNames.contains(field.getName()))
+                .filter(field -> !channelNames.contains(field.getName()))
+                .filter(field -> !INTERNAL_TOKENS.contains(field.getName()))
                 .count();
 
-        // Read JavaDoc before changing count below
+        // Read JavaDoc before changing count below, the count should be equal to
+        // the number of the last token asserted above.
         assertWithMessage("all tokens must be added to list in"
                         + " 'GeneratedJavaTokenTypesTest' and verified"
                         + " that their old numbering didn't change")
             .that(tokenCount)
-            .isEqualTo(237);
+            .isEqualTo(225);
     }
 
     /**
@@ -769,25 +797,11 @@ public void testTokenHasBeenAddedToTokensBlockInLexerGrammar() {
                 .filter(Objects::nonNull)
                 .collect(Collectors.toUnmodifiableList());
 
-        // Since the following tokens are not declared in the 'tokens' block,
-        // they will always appear last in the list of symbolic names provided
-        // by the vocabulary.
-        final List<String> unusedTokenNames = List.of(
-                // reserved keywords that are not part of the language
-                "LITERAL_CONST", "LITERAL_GOTO",
-
-                // Lexer tokens that are not part of our API (they are used as components of
-                // parser rules, but the token name is changed).
-                "DECIMAL_LITERAL_LONG", "DECIMAL_LITERAL", "HEX_LITERAL_LONG",
-                "HEX_LITERAL", "OCT_LITERAL_LONG", "OCT_LITERAL", "BINARY_LITERAL_LONG",
-                "BINARY_LITERAL"
-        );
-
         // Get the starting index of the sublist of tokens, or -1 if sublist
         // is not present.
         final int lastIndexOfSublist =
-                Collections.lastIndexOfSubList(allTokenNames, unusedTokenNames);
-        final int expectedNumberOfUsedTokens = allTokenNames.size() - unusedTokenNames.size();
+                Collections.lastIndexOfSubList(allTokenNames, INTERNAL_TOKENS);
+        final int expectedNumberOfUsedTokens = allTokenNames.size() - INTERNAL_TOKENS.size();
         final String message = "New tokens must be added to the 'tokens' block in the"
                 + " lexer grammar.";