jpountz commented on a change in pull request #1234: Add compression for Binary doc value fields URL: https://github.com/apache/lucene-solr/pull/1234#discussion_r375252907
########## File path: lucene/core/src/java/org/apache/lucene/codecs/lucene80/Lucene80DocValuesConsumer.java ########## @@ -353,67 +360,168 @@ private void writeBlock(long[] values, int length, long gcd, ByteBuffersDataOutp } } - @Override - public void addBinaryField(FieldInfo field, DocValuesProducer valuesProducer) throws IOException { - meta.writeInt(field.number); - meta.writeByte(Lucene80DocValuesFormat.BINARY); - - BinaryDocValues values = valuesProducer.getBinary(field); - long start = data.getFilePointer(); - meta.writeLong(start); // dataOffset - int numDocsWithField = 0; - int minLength = Integer.MAX_VALUE; - int maxLength = 0; - for (int doc = values.nextDoc(); doc != DocIdSetIterator.NO_MORE_DOCS; doc = values.nextDoc()) { - numDocsWithField++; - BytesRef v = values.binaryValue(); - int length = v.length; - data.writeBytes(v.bytes, v.offset, v.length); - minLength = Math.min(length, minLength); - maxLength = Math.max(length, maxLength); + class CompressedBinaryBlockWriter implements Closeable { + FastCompressionHashTable ht = new LZ4.FastCompressionHashTable(); + int uncompressedBlockLength = 0; + int maxUncompressedBlockLength = 0; + int numDocsInCurrentBlock = 0; + int [] docLengths = new int[Lucene80DocValuesFormat.BINARY_DOCS_PER_COMPRESSED_BLOCK]; + byte [] block = new byte [1024 * 16]; Review comment: ```suggestion byte[] block = new byte [1024 * 16]; ``` ---------------------------------------------------------------- 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 With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org