mikemccand commented on a change in pull request #2246: URL: https://github.com/apache/lucene-solr/pull/2246#discussion_r566271500
########## File path: lucene/misc/src/java/org/apache/lucene/misc/index/BinaryDocValueSelector.java ########## @@ -0,0 +1,84 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.lucene.misc.index; + +import java.io.IOException; +import java.io.Serializable; +import java.util.ArrayList; +import java.util.HashSet; +import java.util.List; +import org.apache.lucene.index.BinaryDocValues; +import org.apache.lucene.index.CodecReader; +import org.apache.lucene.index.DirectoryReader; +import org.apache.lucene.index.IndexReader; +import org.apache.lucene.index.LeafReaderContext; +import org.apache.lucene.store.Directory; +import org.apache.lucene.util.BitSet; +import org.apache.lucene.util.Bits; +import org.apache.lucene.util.FixedBitSet; + +/** Select documents using binary doc values */ +public class BinaryDocValueSelector implements IndexRearranger.DocumentSelector, Serializable { + + private final String field; + private final HashSet<String> keySet; + + public BinaryDocValueSelector(String field, HashSet<String> keySet) { Review comment: We could later (in follow-on issue) switch to Lucene's `CharArraySet` if heap usage of this possibly large set ever becomes a problem ... but it is not urgent since this tool need not be optimized. ########## File path: lucene/misc/src/java/org/apache/lucene/misc/index/BinaryDocValueSelector.java ########## @@ -0,0 +1,84 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.lucene.misc.index; + +import java.io.IOException; +import java.io.Serializable; +import java.util.ArrayList; +import java.util.HashSet; +import java.util.List; +import org.apache.lucene.index.BinaryDocValues; +import org.apache.lucene.index.CodecReader; +import org.apache.lucene.index.DirectoryReader; +import org.apache.lucene.index.IndexReader; +import org.apache.lucene.index.LeafReaderContext; +import org.apache.lucene.store.Directory; +import org.apache.lucene.util.BitSet; +import org.apache.lucene.util.Bits; +import org.apache.lucene.util.FixedBitSet; + +/** Select documents using binary doc values */ +public class BinaryDocValueSelector implements IndexRearranger.DocumentSelector, Serializable { + + private final String field; + private final HashSet<String> keySet; + + public BinaryDocValueSelector(String field, HashSet<String> keySet) { + this.field = field; + this.keySet = keySet; + } + + @Override + public BitSet getFilteredLiveDocs(CodecReader reader) throws IOException { + BinaryDocValues binaryDocValues = reader.getBinaryDocValues(field); + Bits oldLiveDocs = reader.getLiveDocs(); + FixedBitSet bits = new FixedBitSet(reader.maxDoc()); + for (int i = 0; i < reader.maxDoc(); i++) { + if (oldLiveDocs != null && oldLiveDocs.get(i) == false) { + continue; + } + if (binaryDocValues.advanceExact(i) + && keySet.contains(binaryDocValues.binaryValue().utf8ToString())) { + bits.set(i); + } + } + return bits; + } + + public static List<IndexRearranger.DocumentSelector> createFromExistIndex( Review comment: Maybe `createFromExistingIndex`? ########## File path: lucene/misc/src/java/org/apache/lucene/misc/index/BinaryDocValueSelector.java ########## @@ -0,0 +1,84 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.lucene.misc.index; + +import java.io.IOException; +import java.io.Serializable; +import java.util.ArrayList; +import java.util.HashSet; +import java.util.List; +import org.apache.lucene.index.BinaryDocValues; +import org.apache.lucene.index.CodecReader; +import org.apache.lucene.index.DirectoryReader; +import org.apache.lucene.index.IndexReader; +import org.apache.lucene.index.LeafReaderContext; +import org.apache.lucene.store.Directory; +import org.apache.lucene.util.BitSet; +import org.apache.lucene.util.Bits; +import org.apache.lucene.util.FixedBitSet; + +/** Select documents using binary doc values */ +public class BinaryDocValueSelector implements IndexRearranger.DocumentSelector, Serializable { + + private final String field; + private final HashSet<String> keySet; + + public BinaryDocValueSelector(String field, HashSet<String> keySet) { + this.field = field; + this.keySet = keySet; + } + + @Override + public BitSet getFilteredLiveDocs(CodecReader reader) throws IOException { + BinaryDocValues binaryDocValues = reader.getBinaryDocValues(field); + Bits oldLiveDocs = reader.getLiveDocs(); + FixedBitSet bits = new FixedBitSet(reader.maxDoc()); + for (int i = 0; i < reader.maxDoc(); i++) { + if (oldLiveDocs != null && oldLiveDocs.get(i) == false) { + continue; + } + if (binaryDocValues.advanceExact(i) + && keySet.contains(binaryDocValues.binaryValue().utf8ToString())) { + bits.set(i); + } + } + return bits; + } + + public static List<IndexRearranger.DocumentSelector> createFromExistIndex( + String field, Directory directory) throws IOException { + List<IndexRearranger.DocumentSelector> selectors = new ArrayList<>(); + try (IndexReader reader = DirectoryReader.open(directory)) { + for (LeafReaderContext context : reader.leaves()) { + HashSet<String> keySet = new HashSet<>(); + Bits liveDocs = context.reader().getLiveDocs(); + BinaryDocValues binaryDocValues = context.reader().getBinaryDocValues(field); + for (int i = 0; i < context.reader().maxDoc(); i++) { + if (liveDocs != null && liveDocs.get(i) == false) { + continue; + } + if (binaryDocValues.advanceExact(i)) { + keySet.add(binaryDocValues.binaryValue().utf8ToString()); + } Review comment: Maybe add `else throw exception`? ########## File path: lucene/CHANGES.txt ########## @@ -247,6 +247,13 @@ Other * LUCENE-9627: Remove unused Lucene50FieldInfosFormat codec and small refactor some codecs to separate reading header/footer from reading content of the file. (Ignacio Vera) +======================= Lucene 8.9.0 ======================= + +New Features +--------------------- + +* LUCENE-9694: New tool for creating a deterministic index (Haoyu Zhai) Review comment: Thanks for adding `CHANGES` entry! Could we beef it up a bit, e.g.: ``` LUCENE-9694: New tool for creating a deterministic index to enabling benchmarking changes on a consistent multi-segment index even when they require re-indexing. ``` Or so? ########## File path: lucene/misc/src/java/org/apache/lucene/misc/index/IndexRearranger.java ########## @@ -0,0 +1,132 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.lucene.misc.index; + +import java.io.IOException; +import java.util.ArrayList; +import java.util.List; +import java.util.concurrent.Callable; +import java.util.concurrent.ExecutorService; +import java.util.concurrent.Executors; +import java.util.concurrent.Future; +import org.apache.lucene.index.CodecReader; +import org.apache.lucene.index.DirectoryReader; +import org.apache.lucene.index.FilterCodecReader; +import org.apache.lucene.index.IndexReader; +import org.apache.lucene.index.IndexWriter; +import org.apache.lucene.index.IndexWriterConfig; +import org.apache.lucene.index.LeafReaderContext; +import org.apache.lucene.index.NoMergePolicy; +import org.apache.lucene.store.Directory; +import org.apache.lucene.util.BitSet; +import org.apache.lucene.util.Bits; +import org.apache.lucene.util.NamedThreadFactory; + +/** + * Copy and rearrange index according to document selectors, from input dir to output dir Length of + * documentSelectors determines how many segments there will be + */ +public class IndexRearranger { + protected final Directory input, output; + protected final IndexWriterConfig config; + protected final List<DocumentSelector> documentSelectors; + + public IndexRearranger( + Directory input, + Directory output, + IndexWriterConfig config, + List<DocumentSelector> documentSelectors) { Review comment: Awesome, thanks for adding this! ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org
