OAK-11801 : removed Guava's fluent iterable with Apache's (#2408)

rishabhdaim · web-flow · commit 00b103fb3c68 · 2025-07-30T11:10:04.000+05:30
diff --git a/oak-blob-plugins/src/main/java/org/apache/jackrabbit/oak/plugins/blob/datastore/SharedDataStoreUtils.java b/oak-blob-plugins/src/main/java/org/apache/jackrabbit/oak/plugins/blob/datastore/SharedDataStoreUtils.java
@@ -19,13 +19,15 @@
 import java.util.Arrays;
 import java.util.Collections;
 import java.util.Comparator;
+import java.util.LinkedHashMap;
 import java.util.List;
 import java.util.Set;
 import java.util.stream.Collectors;
 
-import org.apache.jackrabbit.guava.common.collect.FluentIterable;
+import org.apache.commons.collections4.FluentIterable;
 import org.apache.jackrabbit.core.data.DataRecord;
 import org.apache.jackrabbit.oak.commons.collections.SetUtils;
+import org.apache.jackrabbit.oak.commons.collections.StreamUtils;
 import org.apache.jackrabbit.oak.plugins.blob.SharedDataStore;
 import org.apache.jackrabbit.oak.spi.blob.BlobStore;
 
@@ -63,10 +65,24 @@ public static DataRecord getEarliestRecord(List<DataRecord> recs) {
      */
     public static Set<String> refsNotAvailableFromRepos(List<DataRecord> repos,
             List<DataRecord> refs) {
-        return SetUtils.difference(FluentIterable.from(repos)
-                .uniqueIndex(input -> SharedStoreRecordType.REPOSITORY.getIdFromName(input.getIdentifier().toString())).keySet(),
-                FluentIterable.from(refs)
-                        .index(input -> SharedStoreRecordType.REFERENCES.getIdFromName(input.getIdentifier().toString())).keySet());
+        return SetUtils.difference(
+                StreamUtils.toStream(
+                        FluentIterable.of(repos)).collect(
+                                Collectors.toMap(
+                                        input -> SharedStoreRecordType.REPOSITORY.getIdFromName(input.getIdentifier().toString()),
+                                        e -> e,
+                                        (oldValue, newValue) -> {
+                                            throw new IllegalArgumentException("Duplicate key found: " + SharedStoreRecordType.REPOSITORY.getIdFromName(newValue.getIdentifier().toString()));
+                                            },
+                                        LinkedHashMap::new))
+                        .keySet(),
+                StreamUtils.toStream(
+                        FluentIterable.of(refs)).collect(
+                                Collectors.groupingBy(
+                                        input -> SharedStoreRecordType.REFERENCES.getIdFromName(input.getIdentifier().toString()),
+                                        LinkedHashMap::new,
+                                        Collectors.toList()))
+                        .keySet());
     }
 
     /**
diff --git a/oak-lucene/src/main/java/org/apache/jackrabbit/oak/plugins/index/lucene/LucenePropertyIndex.java b/oak-lucene/src/main/java/org/apache/jackrabbit/oak/plugins/index/lucene/LucenePropertyIndex.java
@@ -32,13 +32,14 @@
 import java.util.LinkedList;
 import java.util.List;
 import java.util.Map;
+import java.util.Objects;
 import java.util.Set;
 import java.util.concurrent.atomic.AtomicBoolean;
 import java.util.concurrent.atomic.AtomicReference;
 import java.util.function.Predicate;
 
+import org.apache.commons.collections4.FluentIterable;
 import org.apache.jackrabbit.guava.common.collect.AbstractIterator;
-import org.apache.jackrabbit.guava.common.collect.FluentIterable;
 import org.apache.jackrabbit.oak.api.PropertyValue;
 import org.apache.jackrabbit.oak.api.Type;
 import org.apache.jackrabbit.oak.commons.PathUtils;
@@ -1610,13 +1611,13 @@ private static Iterator<FulltextResultRow> mergePropertyIndexResult(IndexPlan pl
         FluentIterable<String> paths;
         if (pir != null) {
             Iterable<String> queryResult = lookup.query(plan.getFilter(), pir.propertyName, pir.pr);
-            paths = FluentIterable.from(queryResult)
+            paths = FluentIterable.of(queryResult)
                     .transform(path -> pr.isPathTransformed() ? pr.transformPath(path) : path)
-                    .filter(x -> x != null);
+                    .filter(Objects::nonNull);
         } else {
             Validate.checkState(pr.evaluateSyncNodeTypeRestriction()); //Either of property or nodetype should not be null
             Filter filter = plan.getFilter();
-            paths = FluentIterable.from(IterableUtils.chainedIterable(
+            paths = FluentIterable.of(IterableUtils.chainedIterable(
                     lookup.query(filter, JCR_PRIMARYTYPE, newName(filter.getPrimaryTypes())),
                     lookup.query(filter, JCR_MIXINTYPES, newName(filter.getMixinTypes()))));
         }
diff --git a/oak-run-commons/pom.xml b/oak-run-commons/pom.xml
@@ -123,6 +123,10 @@
             <groupId>commons-io</groupId>
             <artifactId>commons-io</artifactId>
         </dependency>
+        <dependency>
+            <groupId>org.apache.commons</groupId>
+            <artifactId>commons-collections4</artifactId>
+        </dependency>
         <dependency>
             <groupId>org.apache.felix</groupId>
             <artifactId>org.apache.felix.configadmin</artifactId>
diff --git a/oak-run-commons/src/main/java/org/apache/jackrabbit/oak/index/indexer/document/NodeStateEntryTraverser.java b/oak-run-commons/src/main/java/org/apache/jackrabbit/oak/index/indexer/document/NodeStateEntryTraverser.java
@@ -19,7 +19,7 @@
 
 package org.apache.jackrabbit.oak.index.indexer.document;
 
-import org.apache.jackrabbit.guava.common.collect.FluentIterable;
+import org.apache.commons.collections4.FluentIterable;
 import org.apache.jackrabbit.oak.commons.collections.IterableUtils;
 import org.apache.jackrabbit.oak.commons.pio.Closer;
 import org.apache.jackrabbit.oak.plugins.document.Collection;
@@ -94,9 +94,8 @@ public void close() throws IOException {
 
     @SuppressWarnings("Guava")
     private Iterable<NodeStateEntry> getIncludedDocs() {
-        return FluentIterable.from(getDocsFilteredByPath())
-                .filter(doc -> includeDoc(doc))
-                .transformAndConcat(doc -> getEntries(doc));
+        return IterableUtils.chainedIterable(
+                FluentIterable.of(getDocsFilteredByPath()).filter(this::includeDoc).transform(this::getEntries));
     }
 
     private boolean includeDoc(NodeDocument doc) {
diff --git a/oak-run-commons/src/main/java/org/apache/jackrabbit/oak/plugins/document/mongo/MongoDocumentTraverser.java b/oak-run-commons/src/main/java/org/apache/jackrabbit/oak/plugins/document/mongo/MongoDocumentTraverser.java
@@ -22,7 +22,7 @@
 import com.mongodb.BasicDBObject;
 import com.mongodb.ReadPreference;
 import com.mongodb.client.MongoCollection;
-import org.apache.jackrabbit.guava.common.collect.FluentIterable;
+import org.apache.commons.collections4.FluentIterable;
 import org.apache.jackrabbit.oak.commons.conditions.Validate;
 import org.apache.jackrabbit.oak.plugins.document.Collection;
 import org.apache.jackrabbit.oak.plugins.document.Document;
@@ -73,7 +73,7 @@ public <T extends Document> CloseableIterable<T> getAllDocuments(Collection<T> c
         cursor = closeableCursor;
 
         @SuppressWarnings("Guava")
-        Iterable<T> result = FluentIterable.from(cursor)
+        Iterable<T> result = FluentIterable.of(cursor)
                 .filter(o -> filter.test((String) o.get(Document.ID)))
                 .transform(o -> {
                     T doc = mongoStore.convertFromDBObject(collection, o);
diff --git a/oak-run/pom.xml b/oak-run/pom.xml
@@ -336,6 +336,10 @@
       <groupId>org.apache.commons</groupId>
       <artifactId>commons-lang3</artifactId>
     </dependency>
+    <dependency>
+      <groupId>org.apache.commons</groupId>
+      <artifactId>commons-collections4</artifactId>
+    </dependency>
     <dependency>
        <groupId>org.apache.commons</groupId>
        <artifactId>commons-text</artifactId>
diff --git a/oak-run/src/main/java/org/apache/jackrabbit/oak/plugins/tika/BinaryResourceProvider.java b/oak-run/src/main/java/org/apache/jackrabbit/oak/plugins/tika/BinaryResourceProvider.java
@@ -19,9 +19,9 @@
 
 package org.apache.jackrabbit.oak.plugins.tika;
 
-import java.io.IOException;
+import org.apache.commons.collections4.FluentIterable;
 
-import org.apache.jackrabbit.guava.common.collect.FluentIterable;
+import java.io.IOException;
 
 /**
  * Provides an iterator for binaries present under given path
diff --git a/oak-run/src/main/java/org/apache/jackrabbit/oak/plugins/tika/CSVFileBinaryResourceProvider.java b/oak-run/src/main/java/org/apache/jackrabbit/oak/plugins/tika/CSVFileBinaryResourceProvider.java
@@ -24,7 +24,7 @@
 import java.nio.charset.StandardCharsets;
 import java.util.function.Function;
 
-import org.apache.jackrabbit.guava.common.collect.FluentIterable;
+import org.apache.commons.collections4.FluentIterable;
 import org.apache.commons.csv.CSVFormat;
 import org.apache.commons.csv.CSVParser;
 import org.apache.commons.csv.CSVRecord;
@@ -72,7 +72,7 @@ public CSVFileBinaryResourceProvider(File dataFile, @Nullable BlobStore blobStor
     public FluentIterable<BinaryResource> getBinaries(final String path) throws IOException {
         CSVParser parser = CSVParser.parse(dataFile, StandardCharsets.UTF_8, FORMAT);
         closer.register(parser);
-        return FluentIterable.from(parser)
+        return FluentIterable.of(parser)
                 .transform(new RecordTransformer()::apply)
                 .filter(input -> input != null && PathUtils.isAncestor(path, input.getPath()));
     }
diff --git a/oak-run/src/main/java/org/apache/jackrabbit/oak/plugins/tika/CSVFileGenerator.java b/oak-run/src/main/java/org/apache/jackrabbit/oak/plugins/tika/CSVFileGenerator.java
@@ -25,7 +25,7 @@
 import java.io.IOException;
 import java.nio.charset.StandardCharsets;
 
-import org.apache.jackrabbit.guava.common.collect.FluentIterable;
+import org.apache.commons.collections4.FluentIterable;
 import org.apache.commons.csv.CSVPrinter;
 import org.apache.jackrabbit.oak.commons.pio.Closer;
 import org.slf4j.Logger;
diff --git a/oak-run/src/main/java/org/apache/jackrabbit/oak/plugins/tika/NodeStoreBinaryResourceProvider.java b/oak-run/src/main/java/org/apache/jackrabbit/oak/plugins/tika/NodeStoreBinaryResourceProvider.java
@@ -18,7 +18,7 @@
  */
 package org.apache.jackrabbit.oak.plugins.tika;
 
-import org.apache.jackrabbit.guava.common.collect.FluentIterable;
+import org.apache.commons.collections4.FluentIterable;
 import org.apache.jackrabbit.guava.common.collect.TreeTraverser;
 import org.apache.jackrabbit.JcrConstants;
 import org.apache.jackrabbit.oak.api.Blob;
@@ -34,6 +34,7 @@
 import static org.apache.jackrabbit.oak.plugins.tree.factories.TreeFactory.createReadOnlyTree;
 import static org.apache.jackrabbit.oak.spi.state.NodeStateUtils.getNode;
 
+import java.util.Objects;
 import java.util.function.Function;
 
 class NodeStoreBinaryResourceProvider implements BinaryResourceProvider {
@@ -47,10 +48,12 @@ public NodeStoreBinaryResourceProvider(NodeStore nodeStore, BlobStore blobStore)
     }
 
     public FluentIterable<BinaryResource> getBinaries(String path) {
-        return new OakTreeTraverser()
+        // had to convert Guava's FluentIterable to Apache Commons Collections FluentIterable
+        // TODO once we remove preOrderTraversal() of Guava, we can use Apache FluentIterable directly
+        return FluentIterable.of(new OakTreeTraverser()
                 .preOrderTraversal(createReadOnlyTree(getNode(nodeStore.getRoot(), path)))
                 .transform(new TreeToBinarySource()::apply)
-                .filter(x -> x != null);
+                .filter(Objects::nonNull));
     }
 
     private class TreeToBinarySource implements Function<Tree, BinaryResource> {
diff --git a/oak-run/src/test/java/org/apache/jackrabbit/oak/plugins/tika/BinaryStatsTest.java b/oak-run/src/test/java/org/apache/jackrabbit/oak/plugins/tika/BinaryStatsTest.java
@@ -18,7 +18,7 @@
  */
 package org.apache.jackrabbit.oak.plugins.tika;
 
-import org.apache.jackrabbit.guava.common.collect.FluentIterable;
+import org.apache.commons.collections4.FluentIterable;
 import org.apache.jackrabbit.oak.plugins.tika.BinaryStats.MimeTypeStats;
 import org.junit.Assert;
 import org.junit.Test;
diff --git a/oak-run/src/test/java/org/apache/jackrabbit/oak/plugins/tika/CSVFileBinaryResourceProviderTest.java b/oak-run/src/test/java/org/apache/jackrabbit/oak/plugins/tika/CSVFileBinaryResourceProviderTest.java
@@ -21,8 +21,10 @@
 import java.io.File;
 import java.nio.file.Files;
 import java.util.Map;
+import java.util.stream.Collectors;
 
 import org.apache.commons.csv.CSVPrinter;
+import org.apache.jackrabbit.oak.commons.collections.StreamUtils;
 import org.apache.jackrabbit.oak.spi.blob.MemoryBlobStore;
 import org.junit.Rule;
 import org.junit.Test;
@@ -50,12 +52,24 @@ public void testGetBinaries() throws Exception {
 
         CSVFileBinaryResourceProvider provider = new CSVFileBinaryResourceProvider(dataFile, new MemoryBlobStore());
 
-        Map<String, BinaryResource> binaries = provider.getBinaries("/").uniqueIndex(BinarySourceMapper.BY_BLOBID::apply);
+        Map<String, BinaryResource> binaries = StreamUtils.toStream(provider.getBinaries("/")).collect(Collectors.toMap(
+                BinarySourceMapper.BY_BLOBID,
+                element -> element,
+                (oldValue, newValue) -> {
+                    throw new IllegalArgumentException("Duplicate key found: " + BinarySourceMapper.BY_BLOBID.apply(newValue));
+                } // This handles the duplicate key scenario similar to uniqueIndex
+        ));
         assertEquals(3, binaries.size());
         assertEquals("a", binaries.get("a").getBlobId());
         assertEquals("/a", binaries.get("a").getPath());
 
-        binaries = provider.getBinaries("/a").uniqueIndex(BinarySourceMapper.BY_BLOBID::apply);
+        binaries = StreamUtils.toStream(provider.getBinaries("/a")).collect(Collectors.toMap(
+                BinarySourceMapper.BY_BLOBID,
+                element -> element,
+                (oldValue, newValue) -> {
+                    throw new IllegalArgumentException("Duplicate key found: " + BinarySourceMapper.BY_BLOBID.apply(newValue));
+                } // This handles the duplicate key scenario similar to uniqueIndex
+        ));
         assertEquals(1, binaries.size());
 
         provider.close();
diff --git a/oak-run/src/test/java/org/apache/jackrabbit/oak/plugins/tika/NodeStoreBinaryResourceProviderTest.java b/oak-run/src/test/java/org/apache/jackrabbit/oak/plugins/tika/NodeStoreBinaryResourceProviderTest.java
@@ -25,6 +25,7 @@
 
 import org.apache.jackrabbit.JcrConstants;
 import org.apache.jackrabbit.oak.api.Blob;
+import org.apache.jackrabbit.oak.commons.collections.IterableUtils;
 import org.apache.jackrabbit.oak.plugins.blob.BlobStoreBlob;
 import org.apache.jackrabbit.oak.plugins.memory.ArrayBasedBlob;
 import org.apache.jackrabbit.oak.plugins.memory.MemoryNodeStore;
@@ -60,7 +61,7 @@ public void countBinaries() throws Exception {
         assertEquals(2, extractor.getBinaries("/").size());
         assertEquals(1, extractor.getBinaries("/a2").size());
 
-        BinaryResource bs = extractor.getBinaries("/a2").first().get();
+        BinaryResource bs = IterableUtils.getFirst(extractor.getBinaries("/a2"), null);
         assertEquals("text/foo", bs.getMimeType());
         assertEquals("bar", bs.getEncoding());
         assertEquals("id2", bs.getBlobId());
diff --git a/oak-run/src/test/java/org/apache/jackrabbit/oak/plugins/tika/TextPopulatorTest.java b/oak-run/src/test/java/org/apache/jackrabbit/oak/plugins/tika/TextPopulatorTest.java
@@ -18,7 +18,7 @@
  */
 package org.apache.jackrabbit.oak.plugins.tika;
 
-import org.apache.jackrabbit.guava.common.collect.FluentIterable;
+import org.apache.commons.collections4.FluentIterable;
 import org.apache.jackrabbit.oak.plugins.blob.datastore.TextWriter;
 import org.apache.jackrabbit.oak.plugins.index.lucene.FieldFactory;
 import org.apache.jackrabbit.oak.plugins.index.lucene.OakAnalyzer;
@@ -277,13 +277,7 @@ static String getBlobId(String path) {
 
         @Override
         public FluentIterable<BinaryResource> getBinaries(String path) {
-            return new FluentIterable<BinaryResource>() {
-                @NotNull
-                @Override
-                public Iterator<BinaryResource> iterator() {
-                    return binaries.iterator();
-                }
-            };
+            return FluentIterable.of(binaries);
         }
     }
 }
diff --git a/oak-security-spi/src/main/java/org/apache/jackrabbit/oak/spi/security/privilege/PrivilegeBitsProvider.java b/oak-security-spi/src/main/java/org/apache/jackrabbit/oak/spi/security/privilege/PrivilegeBitsProvider.java
@@ -28,7 +28,7 @@
 import javax.jcr.security.AccessControlException;
 import javax.jcr.security.Privilege;
 
-import org.apache.jackrabbit.guava.common.collect.FluentIterable;
+import org.apache.commons.collections4.FluentIterable;
 import org.apache.jackrabbit.oak.api.PropertyState;
 import org.apache.jackrabbit.oak.api.Root;
 import org.apache.jackrabbit.oak.api.Tree;
@@ -263,7 +263,7 @@ public Iterable<String> getAggregatedPrivilegeNames(@NotNull String... privilege
 
     @NotNull
     private Iterable<String> extractAggregatedPrivileges(@NotNull Iterable<String> privilegeNames) {
-        return FluentIterable.from(privilegeNames).transformAndConcat(new ExtractAggregatedPrivileges()::apply);
+        return IterableUtils.chainedIterable(FluentIterable.of(privilegeNames).transform(new ExtractAggregatedPrivileges()::apply));
     }
 
     @NotNull
diff --git a/oak-store-composite/src/main/java/org/apache/jackrabbit/oak/composite/CompositeNodeBuilder.java b/oak-store-composite/src/main/java/org/apache/jackrabbit/oak/composite/CompositeNodeBuilder.java
@@ -16,13 +16,13 @@
  */
 package org.apache.jackrabbit.oak.composite;
 
-import org.apache.jackrabbit.guava.common.collect.FluentIterable;
+import org.apache.commons.collections4.FluentIterable;
 import org.apache.jackrabbit.oak.api.Blob;
 import org.apache.jackrabbit.oak.api.PropertyState;
 import org.apache.jackrabbit.oak.api.Type;
 import org.apache.jackrabbit.oak.commons.PathUtils;
+import org.apache.jackrabbit.oak.commons.collections.IterableUtils;
 import org.apache.jackrabbit.oak.plugins.memory.EmptyNodeState;
-import org.apache.jackrabbit.oak.plugins.memory.MemoryNodeBuilder;
 import org.apache.jackrabbit.oak.spi.state.NodeBuilder;
 import org.apache.jackrabbit.oak.spi.state.NodeState;
 import org.slf4j.Logger;
@@ -175,24 +175,24 @@ public long getChildNodeCount(final long max) {
             return getWrappedNodeBuilder().getChildNodeCount(max);
         } else {
             // Count the children in each contributing store.
-            return accumulateChildSizes(FluentIterable.from(contributingStores)
-                    .transformAndConcat(mns -> {
+            return accumulateChildSizes(IterableUtils.chainedIterable(
+                    FluentIterable.of(contributingStores).transform(mns -> {
                         NodeBuilder node = nodeBuilders.get(mns);
                         if (node.getChildNodeCount(max) == MAX_VALUE) {
                             return singleton(STOP_COUNTING_CHILDREN);
                         } else {
-                            return FluentIterable.from(node.getChildNodeNames()).filter(e -> belongsToStore(mns, e));
+                            return FluentIterable.of(node.getChildNodeNames()).filter(e -> belongsToStore(mns, e));
                         }
-                    }), max);
+                    })), max);
         }
     }
 
     @Override
     public Iterable<String> getChildNodeNames() {
-        return FluentIterable.from(ctx.getContributingStoresForBuilders(getPath(), nodeBuilders))
-                .transformAndConcat(mns -> FluentIterable
-                        .from(nodeBuilders.get(mns).getChildNodeNames())
-                        .filter(e -> belongsToStore(mns, e)));
+        return IterableUtils.chainedIterable(
+                FluentIterable.of(ctx.getContributingStoresForBuilders(getPath(), nodeBuilders)).
+                        transform(mns -> FluentIterable.of(nodeBuilders.get(mns).getChildNodeNames()).
+                                filter(e -> belongsToStore(mns, e))));
     }
 
     @Override
diff --git a/oak-store-composite/src/main/java/org/apache/jackrabbit/oak/composite/CompositeNodeState.java b/oak-store-composite/src/main/java/org/apache/jackrabbit/oak/composite/CompositeNodeState.java
