pvary commented on a change in pull request #1251:
URL: https://github.com/apache/hive/pull/1251#discussion_r454603042
##########
File path:
ql/src/java/org/apache/hadoop/hive/ql/io/orc/VectorizedOrcAcidRowBatchReader.java
##########
@@ -1562,20 +1580,31 @@ public int compareTo(CompressedOwid other) {
try {
final Path[] deleteDeltaDirs = getDeleteDeltaDirsFromSplit(orcSplit);
if (deleteDeltaDirs.length > 0) {
+ FileSystem fs = orcSplit.getPath().getFileSystem(conf);
+ AcidOutputFormat.Options orcSplitMinMaxWriteIds =
+ AcidUtils.parseBaseOrDeltaBucketFilename(orcSplit.getPath(),
conf);
int totalDeleteEventCount = 0;
for (Path deleteDeltaDir : deleteDeltaDirs) {
- FileSystem fs = deleteDeltaDir.getFileSystem(conf);
+ if (!isQualifiedDeleteDeltaForSplit(orcSplitMinMaxWriteIds,
deleteDeltaDir)) {
+ continue;
+ }
Path[] deleteDeltaFiles =
OrcRawRecordMerger.getDeltaFiles(deleteDeltaDir, bucket,
new OrcRawRecordMerger.Options().isCompacting(false), null);
for (Path deleteDeltaFile : deleteDeltaFiles) {
try {
- /**
- * todo: we have OrcSplit.orcTail so we should be able to get
stats from there
- */
- Reader deleteDeltaReader =
OrcFile.createReader(deleteDeltaFile, OrcFile.readerOptions(conf));
- if (deleteDeltaReader.getNumberOfRows() <= 0) {
+ ReaderData readerData = getOrcTail(deleteDeltaFile, conf,
cacheTag);
+ OrcTail orcTail = readerData.orcTail;
+ if (orcTail.getFooter().getNumberOfRows() <= 0) {
continue; // just a safe check to ensure that we are not
reading empty delete files.
}
+ OrcRawRecordMerger.KeyInterval deleteKeyInterval =
findDeleteMinMaxKeys(orcTail, deleteDeltaFile);
+ if (!deleteKeyInterval.isIntersects(keyInterval)) {
+ // If there is no intersection between data and delete
delta, do not read delete file
+ continue;
+ }
+ // Create the reader if we got the OrcTail from cache
Review comment:
Added more comment
----------------------------------------------------------------
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:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
