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_r376527753
##########
File path:
lucene/core/src/java/org/apache/lucene/codecs/lucene80/Lucene80DocValuesProducer.java
##########
@@ -742,6 +755,131 @@ public BytesRef binaryValue() throws IOException {
};
}
}
+ }
+
+ // Decompresses blocks of binary values to retrieve content
+ class BinaryDecoder {
+
+ private final LongValues addresses;
+ private final IndexInput compressedData;
+ // Cache of last uncompressed block
+ private long lastBlockId = -1;
+ private int []uncompressedDocEnds = new
int[Lucene80DocValuesFormat.BINARY_DOCS_PER_COMPRESSED_BLOCK];
+ private int uncompressedBlockLength = 0;
+ private int numDocsInBlock = 0;
+ private final byte[] uncompressedBlock;
+ private final BytesRef uncompressedBytesRef;
+
+ public BinaryDecoder(LongValues addresses, IndexInput compressedData, int
biggestUncompressedBlockSize) {
+ super();
+ this.addresses = addresses;
+ this.compressedData = compressedData;
+ // pre-allocate a byte array large enough for the biggest uncompressed
block needed.
+ this.uncompressedBlock = new byte[biggestUncompressedBlockSize];
+ uncompressedBytesRef = new BytesRef(uncompressedBlock);
+
+ }
+
+ BytesRef decode(int docNumber) throws IOException {
+ int blockId = docNumber >> Lucene80DocValuesFormat.BINARY_BLOCK_SHIFT;
+ int docInBlockId = docNumber %
Lucene80DocValuesFormat.BINARY_DOCS_PER_COMPRESSED_BLOCK;
+ assert docInBlockId <
Lucene80DocValuesFormat.BINARY_DOCS_PER_COMPRESSED_BLOCK;
+
+
+ // already read and uncompressed?
+ if (blockId != lastBlockId) {
+ lastBlockId = blockId;
+ long blockStartOffset = addresses.get(blockId);
+ compressedData.seek(blockStartOffset);
+
+ numDocsInBlock = compressedData.readVInt();
+ assert numDocsInBlock <=
Lucene80DocValuesFormat.BINARY_DOCS_PER_COMPRESSED_BLOCK;
+ uncompressedDocEnds = new int[numDocsInBlock];
+ uncompressedBlockLength = 0;
+
+ int onlyLength = -1;
+ for (int i = 0; i < numDocsInBlock; i++) {
+ if (i == 0) {
+ // The first length value is special. It is shifted and has a bit
to denote if
+ // all other values are the same length
+ int lengthPlusSameInd = compressedData.readVInt();
+ int sameIndicator = lengthPlusSameInd & 1;
+ int firstValLength = lengthPlusSameInd >>1;
+ if (sameIndicator == 1) {
+ onlyLength = firstValLength;
+ }
+ uncompressedBlockLength += firstValLength;
+ } else {
+ if (onlyLength == -1) {
+ // Various lengths are stored - read each from disk
+ uncompressedBlockLength += compressedData.readVInt();
+ } else {
+ // Only one length
+ uncompressedBlockLength += onlyLength;
+ }
+ }
+ uncompressedDocEnds[i] = uncompressedBlockLength;
Review comment:
maybe we could call it `uncompressedDocStarts` and set the index at `i+1`
which would then help below to remove the else block of the `docInBlockId > 0`
condition below?
----------------------------------------------------------------
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
