dungba88 commented on code in PR #12624: URL: https://github.com/apache/lucene/pull/12624#discussion_r1416403950
########## lucene/core/src/java/org/apache/lucene/util/fst/ReadWriteDataOutput.java: ########## @@ -0,0 +1,82 @@ +/* + * 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.util.fst; + +import java.io.IOException; +import java.nio.ByteBuffer; +import java.util.List; +import org.apache.lucene.store.ByteBuffersDataInput; +import org.apache.lucene.store.ByteBuffersDataOutput; +import org.apache.lucene.store.DataOutput; + +/** + * An adapter class to use {@link ByteBuffersDataOutput} as a {@link FSTReader}. It allows the FST + * to be readable immediately after writing + */ +final class ReadWriteDataOutput extends DataOutput implements FSTReader, Freezable { + + private final ByteBuffersDataOutput dataOutput; + // the DataInput to read from in case the DataOutput has multiple blocks + private ByteBuffersDataInput dataInput; + // the ByteBuffers to read from in case the DataOutput has a single block + private ByteBuffer byteBuffer; + + public ReadWriteDataOutput(ByteBuffersDataOutput dataOutput) { + this.dataOutput = dataOutput; + } + + @Override + public void writeByte(byte b) { + dataOutput.writeByte(b); + } + + @Override + public void writeBytes(byte[] b, int offset, int length) { + dataOutput.writeBytes(b, offset, length); + } + + @Override + public long ramBytesUsed() { + return dataOutput.ramBytesUsed(); + } + + @Override + public void freeze() { + // these operations are costly, so we want to compute it once and cache + List<ByteBuffer> byteBuffers = dataOutput.toWriteableBufferList(); + if (byteBuffers.size() == 1) { Review Comment: Even for ByteBuffersDataInput in multi-block cases, there's a slight regression over the BytesStore implementation (note that we already called `freeze()`). The diff is https://github.com/dungba88/lucene/pull/13/files. ### ReverseRandomBytesReader with ByteBuffersDataInput ``` 1> TEST: now verify [fst size=4621076364; nodeCount=2252341486; arcCount=2264078585] 1> 0...: took 0 seconds 1> 1000000...: took 27 seconds 1> 2000000...: took 54 seconds 1> 3000000...: took 82 seconds 1> 4000000...: took 109 seconds 1> 5000000...: took 137 seconds 1> 6000000...: took 165 seconds 1> 7000000...: took 192 seconds 1> 8000000...: took 219 seconds 1> 9000000...: took 247 seconds 1> 10000000...: took 275 seconds 1> 11000000...: took 300 seconds ``` ### BytesStore-like BytesReader ``` 1> TEST: now verify [fst size=4621076364; nodeCount=2252341486; arcCount=2264078585] 1> 0...: took 0 seconds 1> 1000000...: took 22 seconds 1> 2000000...: took 44 seconds 1> 3000000...: took 66 seconds 1> 4000000...: took 89 seconds 1> 5000000...: took 111 seconds 1> 6000000...: took 133 seconds 1> 7000000...: took 155 seconds 1> 8000000...: took 178 seconds 1> 9000000...: took 200 seconds 1> 10000000...: took 222 seconds 1> 11000000...: took 245 seconds ``` As this PR is already rather long, I can make the first implementation simple by solely using ByteBuffersDataInput, then open an issue to benchmark different alternatives thoroughly. WDYT? -- 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. To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org 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
