Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Implemented GreedyStringTiling workaround #2076

Open
wants to merge 2 commits into
base: develop
Choose a base branch
from
Open

Implemented GreedyStringTiling workaround #2076

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
87030d1
Implemented GreedyStringTiling workaround
TwoOfTwelve Nov 20, 2024
217f8b8
Expanded error message for GreedyStringTiling out of bounds
TwoOfTwelve Nov 28, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 20 additions & 2 deletions core/src/main/java/de/jplag/GreedyStringTiling.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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;

Expand All @@ -30,6 +31,13 @@ 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 = """
Copy link
Member

@Kr0nox Kr0nox Nov 28, 2024 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Elaborate what index and length is printed.
Add information what two submissions are being compared (names)
Also print which of the two had the error

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I would second that.

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;
// Ensures 1 <= neighborLength <= minimumTokenMatch
Expand Down Expand Up @@ -115,14 +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 (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 (rightMarked[rightStartIndex] || maximumMatchLength >= rightValues.length - rightStartIndex) {
if (checkMark(rightMarked, rightStartIndex, rightSubmission) || maximumMatchLength >= rightValues.length - rightStartIndex) {
continue;
}

Expand Down Expand Up @@ -228,4 +236,14 @@ private int[] tokenValueListFromSubmission(Submission submission) {
return tokenValueList;
}));
}

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, submission.getTokenList().size(),
submission.getTokenList().stream().map(it -> it.getType().getDescription()).collect(Collectors.joining(", ")),
cachedTokenValueLists.get(submission).length));
}

return marks[index];
}
}
Loading