Skip to content

Fix NPE when disambiguator is null in DatasetParser #18

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

Merged
lfoppiano merged 1 commit into from
Apr 14, 2026
Merged

Fix NPE when disambiguator is null in DatasetParser #18

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
42 changes: 28 additions & 14 deletions src/main/java/org/grobid/core/engines/DatasetParser.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,6 +79,10 @@ public class DatasetParser extends AbstractParser {
private static final java.util.concurrent.atomic.AtomicBoolean gluttonWarningLogged =
new java.util.concurrent.atomic.AtomicBoolean(false);

// guard to warn only once about the disambiguator not being available
private static final java.util.concurrent.atomic.AtomicBoolean disambiguatorWarningLogged =
new java.util.concurrent.atomic.AtomicBoolean(false);

private EngineParsers parsers;
private DatastetServiceConfiguration datastetConfiguration;
private DataTypeClassifier dataTypeClassifier;
Expand All @@ -91,6 +95,12 @@ private static void warnGluttonNotConfiguredOnce() {
}
}

private static void warnDisambiguatorNotAvailableOnce() {
if (disambiguatorWarningLogged.compareAndSet(false, true)) {
LOGGER.warn("Dataset disambiguator is not available, dataset disambiguation will be skipped");
}
}

public static DatasetParser getInstance(
DatastetServiceConfiguration configuration,
DataTypeClassifier dataTypeClassifier,
Expand Down Expand Up @@ -122,7 +132,7 @@ private DatasetParser(DatastetServiceConfiguration configuration) {
DatastetLexicon.getInstance();
this.parsers = new EngineParsers();
this.datastetConfiguration = configuration;
this.disambiguator = disambiguator;
this.disambiguator = DatasetDisambiguator.getInstance(configuration.getDatastetConfiguration());
this.datasetContextClassifier = datasetContextClassifier;
}

Expand Down Expand Up @@ -273,22 +283,26 @@ public List<List<Dataset>> processing(List<DatasetDocumentSequence> datasetDocum

// disambiguation
if (disambiguate) {
localDatasets = disambiguator.disambiguate(localDatasets, tokens);

// apply existing filtering
indexToBeFiltered = new ArrayList<>();
k = 0;
for (Dataset entity : localDatasets) {
if (entity.isFiltered()) {
indexToBeFiltered.add(Integer.valueOf(k));
if (disambiguator != null) {
localDatasets = disambiguator.disambiguate(localDatasets, tokens);

// apply existing filtering
indexToBeFiltered = new ArrayList<>();
k = 0;
for (Dataset entity : localDatasets) {
if (entity.isFiltered()) {
indexToBeFiltered.add(Integer.valueOf(k));
}
k++;
}
k++;
}

if (indexToBeFiltered.size() > 0) {
for (int j = indexToBeFiltered.size() - 1; j >= 0; j--) {
localDatasets.remove(indexToBeFiltered.get(j).intValue());
if (indexToBeFiltered.size() > 0) {
for (int j = indexToBeFiltered.size() - 1; j >= 0; j--) {
localDatasets.remove(indexToBeFiltered.get(j).intValue());
}
}
} else {
warnDisambiguatorNotAvailableOnce();
}
}

Expand Down
Loading