Fix generic wildcards

.github/workflows/build-and-publish.yaml

@@ -10,9 +10,7 @@ on:
 jobs:
   build-and-publish:
     name: Java Gradle
-    uses: bakdata/ci-templates/.github/workflows/java-gradle-library.yaml@1.75.0
-    with:
-      java-version: 17
+    uses: bakdata/ci-templates/.github/workflows/java-gradle-library.yaml@1.81.2
     secrets:
       sonar-token: ${{ secrets.SONARCLOUD_TOKEN }}
       sonar-organization: ${{ secrets.SONARCLOUD_ORGANIZATION }}

.github/workflows/release.yaml

@@ -16,9 +16,8 @@ on:
 jobs:
   java-gradle-release:
     name: Java Gradle
-    uses: bakdata/ci-templates/.github/workflows/java-gradle-release.yaml@1.75.0
+    uses: bakdata/ci-templates/.github/workflows/java-gradle-release.yaml@1.81.2
     with:
-      java-version: 17
       release-type: "${{ inputs.release-type }}"
     secrets:
       github-email: "${{ secrets.GH_EMAIL }}"

common/src/main/java/com/bakdata/dedupe/clustering/ClusterIdGenerators.java

@@ -37,23 +37,23 @@ public class ClusterIdGenerators {
     /**
      * Returns an id generator that generates ints starting from 0.
      */
-    public static <T> Function<? super Iterable<? extends T>, Integer> intGenerator() {
+    public static <T> Function<Iterable<T>, Integer> intGenerator() {
         final AtomicInteger nextId = new AtomicInteger();
         return objects -> nextId.getAndIncrement();
     }
 
     /**
      * Returns an id generator that generates longs starting from 0.
      */
-    public static <T> Function<? super Iterable<? extends T>, Long> longGenerator() {
+    public static <T> Function<Iterable<T>, Long> longGenerator() {
         final AtomicLong nextId = new AtomicLong();
         return objects -> nextId.getAndIncrement();
     }
 
     /**
      * Returns an id generator that generates strings with a given prefix starting from 0.
      */
-    public static <T> Function<? super Iterable<? extends T>, String> stringGenerator(final String prefix) {
+    public static <T> Function<Iterable<T>, String> stringGenerator(final String prefix) {
         final AtomicLong nextId = new AtomicLong();
         return objects -> prefix + nextId.getAndIncrement();
     }

common/src/main/java/com/bakdata/dedupe/clustering/ConsistentClustering.java

@@ -90,7 +90,7 @@ public class ConsistentClustering<C extends Comparable<C>, T, I extends Comparab
         final T firstElement = clusters.get(0).get(0);
         final List<Candidate<T>> candidates = clusters.stream()
                 .flatMap(cluster -> cluster.getElements().stream()
-                        .map(record -> new OnlineCandidate<>(firstElement, record)))
+                        .map(element -> new OnlineCandidate<>(firstElement, element)))
                 .collect(Collectors.toList());
         final List<Cluster<C, T>> transitiveClusters = this.getInternalClosure().clusterDuplicates(candidates);
         if (transitiveClusters.size() != 1) {
@@ -104,13 +104,13 @@ public class ConsistentClustering<C extends Comparable<C>, T, I extends Comparab
     }
 
     @Override
-    public @NonNull Function<? super Iterable<? extends I>, C> getClusterIdGenerator() {
+    public @NonNull Function<Iterable<I>, C> getClusterIdGenerator() {
         return this.clustering.getClusterIdGenerator();
     }
 
     private boolean noRecordInIndex(final Collection<? extends Cluster<C, T>> clusters) {
         final Map<I, Cluster<C, T>> clusterIndex = this.getInternalClosure().getClusterIndex();
         return clusters.stream().flatMap(cluster -> cluster.getElements().stream())
-                .allMatch(record -> clusterIndex.get(this.idExtractor.apply(record)) == null);
+                .allMatch(element -> clusterIndex.get(this.idExtractor.apply(element)) == null);
     }
 }

common/src/main/java/com/bakdata/dedupe/clustering/OracleClustering.java

@@ -87,8 +87,8 @@ public class OracleClustering<C extends Comparable<C>, T, I> implements Clusteri
     }
 
     @Override
-    public @NonNull Function<Iterable<? extends I>, C> getClusterIdGenerator() {
-        final Map<@NonNull Iterable<? extends I>, C> elementsToClusterId =
+    public @NonNull Function<Iterable<I>, C> getClusterIdGenerator() {
+        final Map<@NonNull Iterable<I>, C> elementsToClusterId =
                 this.goldClusters.stream()
                         .collect(Collectors.toMap(this::getElementIds, Cluster::getId));
         return elementsToClusterId::get;

common/src/main/java/com/bakdata/dedupe/clustering/RefineCluster.java

@@ -43,11 +43,11 @@ Stream<Cluster<C, T>> refine(final Stream<? extends Cluster<C, T>> clusters,
      * A function to generate the id for newly split clusters.
      */
     @NonNull
-    Function<? super Iterable<? extends I>, C> getClusterIdGenerator();
+    Function<Iterable<I>, C> getClusterIdGenerator();
 
     /**
      * A function to extract the id of a record.
      */
     @NonNull
-    Function<? super T, I> getIdExtractor();
+    Function<T, I> getIdExtractor();
 }

common/src/main/java/com/bakdata/dedupe/clustering/RefineClusterImpl.java

@@ -56,7 +56,6 @@
 import lombok.Value;
 import lombok.With;
 import lombok.experimental.FieldDefaults;
-import lombok.experimental.Wither;
 import org.apache.commons.lang3.tuple.Pair;
 
 
@@ -95,12 +94,12 @@ public class RefineClusterImpl<C extends Comparable<C>, T, I> implements RefineC
      * A function to generate the id for newly split clusters.
      */
     @NonNull
-    Function<? super Iterable<? extends I>, C> clusterIdGenerator;
+    Function<Iterable<I>, C> clusterIdGenerator;
     /**
      * A function to extract the id of a record.
      */
     @NonNull
-    Function<? super T, I> idExtractor;
+    Function<T, I> idExtractor;
 
     private static double getWeight(final ClassificationResult classificationResult) {
         switch (classificationResult.getClassification()) {
@@ -167,7 +166,7 @@ static int triangularNumber(final int n) {
     private List<ClassifiedCandidate<T>> getRelevantClassifications(final Cluster<C, ? super T> cluster,
             final @NonNull Map<T, List<ClassifiedCandidate<T>>> relevantClassificationIndex) {
         return cluster.getElements().stream()
-                .flatMap(record -> relevantClassificationIndex.getOrDefault(record, List.of()).stream()
+                .flatMap(element -> relevantClassificationIndex.getOrDefault(element, List.of()).stream()
                         .filter(classifiedCandidate -> cluster
                                 .contains(classifiedCandidate.getCandidate().getRecord2())))
                 .collect(Collectors.toList());
@@ -297,7 +296,7 @@ private List<I> getElementIds(final Collection<? extends T> records) {
                 .collect(Collectors.toList());
     }
 
-    private List<WeightedEdge> addRandomEdges(final @NonNull List<? extends WeightedEdge> edges,
+    private List<WeightedEdge> addRandomEdges(final @NonNull List<WeightedEdge> edges,
             final int desiredNumEdges) {
         final Set<WeightedEdge> weightedEdges = new LinkedHashSet<>(edges);
         for (int distance = 2; distance < this.maxSmallClusterSize && weightedEdges.size() < desiredNumEdges;
@@ -318,7 +317,7 @@ private List<WeightedEdge> addRandomEdges(final @NonNull List<? extends Weighted
     }
 
     private List<WeightedEdge> getWeightedEdges(final @NonNull Cluster<C, ? extends T> cluster,
-            final List<? extends WeightedEdge> duplicates,
+            final List<WeightedEdge> duplicates,
             final int desiredNumEdges) {
         final List<WeightedEdge> edges = this.getEdges(cluster, duplicates, desiredNumEdges);
 
@@ -328,7 +327,7 @@ private List<WeightedEdge> getWeightedEdges(final @NonNull Cluster<C, ? extends
     }
 
     private List<WeightedEdge> getEdges(final @NonNull Cluster<C, ? extends T> cluster,
-            final List<? extends WeightedEdge> duplicates, final int desiredNumEdges) {
+            final List<WeightedEdge> duplicates, final int desiredNumEdges) {
         if (duplicates.isEmpty()) {
             final int n = cluster.size();
             return getRandomEdges(triangularNumber(n), desiredNumEdges);
@@ -427,7 +426,7 @@ private boolean overlaps(final @NonNull WeightedEdge e) {
 
     static class GreedyClustering<C extends Comparable<C>, T> {
 
-        int[] greedyCluster(final Cluster<C, T> cluster, final @NonNull Collection<? extends WeightedEdge> edges) {
+        int[] greedyCluster(final Cluster<C, T> cluster, final @NonNull Collection<WeightedEdge> edges) {
 
             final Collection<WeightedEdge> queue = new PriorityQueue<>(Comparator.comparing(WeightedEdge::getWeight));
             queue.addAll(edges);

common/src/main/java/com/bakdata/dedupe/clustering/RefinedTransitiveClosure.java

@@ -121,7 +121,7 @@ private I getClusterId(final Cluster<C, ? extends T> cluster) {
     }
 
     @Override
-    public @NonNull Function<? super Iterable<? extends I>, C> getClusterIdGenerator() {
+    public @NonNull Function<Iterable<I>, C> getClusterIdGenerator() {
         return this.closure.getClusterIdGenerator();
     }
 

common/src/main/java/com/bakdata/dedupe/clustering/TransitiveClosure.java

@@ -60,7 +60,7 @@ public class TransitiveClosure<C extends Comparable<C>, T, I extends Comparable<
      * A function to generate the id for newly formed clusters.
      */
     @NonNull
-    Function<? super Iterable<? extends I>, C> clusterIdGenerator;
+    Function<Iterable<I>, C> clusterIdGenerator;
     /**
      * A backing map for old clusters. Defaults to an in-memory map if null during construction.
      */

common/src/main/java/com/bakdata/dedupe/similarity/AggregatingSimilarityMeasure.java

@@ -46,7 +46,7 @@ public class AggregatingSimilarityMeasure<T> implements SimilarityMeasure<T> {
      */
     @NonNull ToDoubleFunction<? super DoubleStream> aggregator;
     /**
-     * The similarity measures that will successively applied on the input values.
+     * The similarity measures that will successively apply on the input values.
      */
     @NonNull List<SimilarityMeasure<? super T>> similarityMeasures;
 

core/src/main/java/com/bakdata/dedupe/clustering/Cluster.java

@@ -66,8 +66,8 @@ public Cluster(final @NonNull C id) {
         this(id, new ArrayList<>());
     }
 
-    public void add(final @NonNull T record) {
-        this.elements.add(record);
+    public void add(final @NonNull T element) {
+        this.elements.add(element);
     }
 
     public int size() {
@@ -78,8 +78,8 @@ public int size() {
         return this.elements.get(index);
     }
 
-    public boolean contains(final @NonNull T record) {
-        return this.elements.contains(record);
+    public boolean contains(final @NonNull T element) {
+        return this.elements.contains(element);
     }
 
     /**
@@ -91,7 +91,7 @@ public boolean contains(final @NonNull T record) {
      * @return the newly created merged cluster or this iff {@code other == this}.
      */
     public @NonNull <I> Cluster<C, T> merge(
-            final @NonNull Function<? super Iterable<? extends I>, ? extends C> idGenerator,
+            final @NonNull Function<? super Iterable<I>, ? extends C> idGenerator,
             final @NonNull Function<? super T, ? extends I> idExtractor,
             final @NonNull Cluster<C, ? extends T> other) {
         if (other == this) {

core/src/main/java/com/bakdata/dedupe/clustering/Clustering.java

@@ -51,5 +51,6 @@ public interface Clustering<C extends Comparable<C>, T, I> {
      *
      * @return the cluster id generator.
      */
-    @NonNull Function<? super Iterable<? extends I>, C> getClusterIdGenerator();
+    @NonNull
+    Function<Iterable<I>, C> getClusterIdGenerator();
 }

core/src/main/java/com/bakdata/dedupe/clustering/Clusters.java

@@ -48,11 +48,11 @@ public class Clusters {
      * @throws IllegalArgumentException when there is not exactly one cluster
      */
     public static <C extends Comparable<C>, T> @NonNull Cluster<C, T> getContainingCluster(
-            final @NonNull Iterator<? extends Cluster<C, T>> clusterIterator, final @NonNull T record) {
+            final @NonNull Iterator<? extends Cluster<C, T>> clusterIterator, final @NonNull T element) {
         final Spliterator<Cluster<C, T>> spliterator =
                 Spliterators.spliteratorUnknownSize(clusterIterator, ORDERED | NONNULL);
         final List<? extends Cluster<C, T>> mainClusters = StreamSupport.stream(spliterator, false)
-                .filter(c -> c.contains(record))
+                .filter(c -> c.contains(element))
                 .collect(Collectors.toList());
         if (mainClusters.size() != 1) {
             throw new IllegalArgumentException(

examples/src/test/java/com/bakdata/dedupe/person/PersonDeduplicationTest.java

@@ -43,18 +43,23 @@ class PersonDeduplicationTest {
     private static final DateTimeFormatter BDAY_FORMAT = DateTimeFormatter.ofPattern("dd.MM.yy");
 
     private static List<Person> parseCsv(final String resourceName) throws IOException {
-        final CSVFormat format = CSVFormat.newFormat('\t').withFirstRecordAsHeader().withQuote('"');
+        final CSVFormat format = CSVFormat.DEFAULT.builder()
+                .setDelimiter('\t')
+                .setQuote('"')
+                .setHeader()
+                .setSkipHeaderRecord(true)
+                .get();
         try (final CSVParser parser = CSVParser
                 .parse(PersonDeduplicationTest.class.getResourceAsStream(resourceName), StandardCharsets.UTF_8,
                         format)) {
             return parser.getRecords()
                     .stream()
-                    .map(record -> Person.builder()
-                            .id(record.get("id"))
-                            .firstName(record.get("firstname_full"))
-                            .lastName(record.get("lastname"))
-                            .birthDate(LocalDate.parse(record.get("birthdate"), BDAY_FORMAT))
-                            .gender(Gender.valueOf(record.get("gender").toUpperCase()))
+                    .map(csvRecord -> Person.builder()
+                            .id(csvRecord.get("id"))
+                            .firstName(csvRecord.get("firstname_full"))
+                            .lastName(csvRecord.get("lastname"))
+                            .birthDate(LocalDate.parse(csvRecord.get("birthdate"), BDAY_FORMAT))
+                            .gender(Gender.valueOf(csvRecord.get("gender").toUpperCase()))
                             .lastModified(LocalDateTime.now())
                             .build())
                     .collect(Collectors.toList());

gradle/libs.versions.toml

@@ -13,7 +13,7 @@ junit-jupiter = { group = "org.junit.jupiter", name = "junit-jupiter", version.r
 assertj = { group = "org.assertj", name = "assertj-core", version = "3.27.7" }
 
 [plugins]
-release = { id = "com.bakdata.release", version = "2.1.0" }
-sonar = { id = "com.bakdata.sonar", version = "2.1.0" }
-sonatype = { id = "com.bakdata.sonatype", version = "2.1.0" }
+release = { id = "com.bakdata.release", version = "2.2.0" }
+sonar = { id = "com.bakdata.sonar", version = "2.2.0" }
+sonatype = { id = "com.bakdata.sonatype", version = "2.2.0" }
 lombok = { id = "io.freefair.lombok", version = "9.2.0" }