Expanded error message for GreedyStringTiling out of bounds

core/src/main/java/de/jplag/GreedyStringTiling.java

@@ -9,6 +9,7 @@
 import java.util.Set;
 import java.util.concurrent.ConcurrentHashMap;
 import java.util.concurrent.ConcurrentMap;
+import java.util.stream.Collectors;
 
 import de.jplag.options.JPlagOptions;
 
@@ -30,7 +31,12 @@ public class GreedyStringTiling {
     private final Map<Submission, int[]> cachedTokenValueLists = new IdentityHashMap<>();
     private final Map<Submission, SubsequenceHashLookupTable> cachedHashLookupTables = new IdentityHashMap<>();
 
-    private static final String ERROR_INDEX_OUT_OF_BOUNDS = "GST index out of bounds. This is probably a random issue caused by multithreading issues. Length: %s, Index: %s";
+    private static final String ERROR_INDEX_OUT_OF_BOUNDS = """
+                GST index out of bounds. This is probably a random issue caused by multithreading issues.
+                Length: %s, Index: %s
+                TokenCount: %s, TokenList: %s
+                CachedTokenCount: %s
+            """.trim().stripIndent();
 
     public GreedyStringTiling(JPlagOptions options) {
         this.options = options;
@@ -117,14 +123,14 @@ private JPlagComparison compareInternal(Submission leftSubmission, Submission ri
             List<Match> iterationMatches = new ArrayList<>();
             for (int leftStartIndex = 0; leftStartIndex < leftValues.length - maximumMatchLength; leftStartIndex++) {
                 int leftSubsequenceHash = leftLookupTable.subsequenceHashForStartIndex(leftStartIndex);
-                if (checkMark(leftMarked, leftStartIndex) || leftSubsequenceHash == SubsequenceHashLookupTable.NO_HASH) {
+                if (checkMark(leftMarked, leftStartIndex, leftSubmission) || leftSubsequenceHash == SubsequenceHashLookupTable.NO_HASH) {
                     continue;
                 }
                 List<Integer> possiblyMatchingRightStartIndexes = rightLookupTable
                         .startIndexesOfPossiblyMatchingSubsequencesForSubsequenceHash(leftSubsequenceHash);
                 for (Integer rightStartIndex : possiblyMatchingRightStartIndexes) {
                     // comparison uses >= because it is assumed that the last token is a pivot (FILE_END)
-                    if (checkMark(rightMarked, rightStartIndex) || maximumMatchLength >= rightValues.length - rightStartIndex) {
+                    if (checkMark(rightMarked, rightStartIndex, rightSubmission) || maximumMatchLength >= rightValues.length - rightStartIndex) {
                         continue;
                     }
 
@@ -231,9 +237,11 @@ private int[] tokenValueListFromSubmission(Submission submission) {
         }));
     }
 
-    private boolean checkMark(boolean[] marks, int index) {
+    private boolean checkMark(boolean[] marks, int index, Submission submission) {
         if (index >= marks.length) {
-            throw new IllegalStateException(String.format(ERROR_INDEX_OUT_OF_BOUNDS, marks.length, index));
+            throw new IllegalStateException(String.format(ERROR_INDEX_OUT_OF_BOUNDS, marks.length, index, submission.getTokenList().size(),
+                    submission.getTokenList().stream().map(it -> it.getType().getDescription()).collect(Collectors.joining(", ")),
+                    cachedTokenValueLists.get(submission).length));
         }
 
         return marks[index];