vsop-479 commented on code in PR #16245:
URL: https://github.com/apache/lucene/pull/16245#discussion_r3563068643
##########
lucene/core/src/java/org/apache/lucene/codecs/lucene103/blocktree/IntersectTermsEnumFrame.java:
##########
@@ -190,18 +197,32 @@ void load(TrieReader.Node node) throws IOException {
suffixesReader.reset(suffixBytes, 0, numSuffixBytes);
int numSuffixLengthBytes = ite.in.readVInt();
- final boolean allEqual = (numSuffixLengthBytes & 0x01) != 0;
+ allEqual = (numSuffixLengthBytes & 0x01) != 0;
numSuffixLengthBytes >>>= 1;
- if (suffixLengthBytes.length < numSuffixLengthBytes) {
- suffixLengthBytes = new byte[ArrayUtil.oversize(numSuffixLengthBytes,
1)];
- }
- if (allEqual) {
- Arrays.fill(suffixLengthBytes, 0, numSuffixLengthBytes,
ite.in.readByte());
+ if (isLeafBlock) {
+ if (allEqual) {
+ suffixLength = numSuffixLengthBytes;
+ } else {
+ final int numLongs = numSuffixLengthBytes;
+ suffixLengths = new int[entCount];
+ long[] longs = new long[numLongs];
+ for (int i = 0; i < numLongs; i++) {
+ longs[i] = ite.in.readLong();
+ }
+ // TODO: read and decode one long only when it is needed.
+ Simple64.decodeAll(longs, 0, suffixLengths, 0, entCount);
Review Comment:
> So this means we pre-decode all term suffix lengths for the terms in the
block, up front?
> We could later decode one long only when we need to scan its corresponding
suffixLengths.
This has already been implemented.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
