danny0405 commented on code in PR #12269:
URL: https://github.com/apache/hudi/pull/12269#discussion_r1847730424
##########
hudi-common/src/main/java/org/apache/hudi/metadata/HoodieTableMetadataUtil.java:
##########
@@ -759,6 +769,77 @@ public static HoodieData<HoodieRecord>
convertMetadataToColumnStatsRecords(Hoodi
});
}
+ static HoodieData<HoodieRecord>
convertMetadataToRecordIndexRecords(HoodieEngineContext engineContext,
+
HoodieCommitMetadata commitMetadata,
+
HoodieMetadataConfig metadataConfig,
+
HoodieTableMetaClient dataTableMetaClient,
+ int
writesFileIdEncoding,
+ String
instantTime) {
+
+ List<HoodieWriteStat> allWriteStats =
commitMetadata.getPartitionToWriteStats().values().stream()
+ .flatMap(Collection::stream).collect(Collectors.toList());
+
+ if (allWriteStats.isEmpty()) {
+ return engineContext.emptyHoodieData();
+ }
+
+ try {
+ int parallelism = Math.max(Math.min(allWriteStats.size(),
metadataConfig.getRecordIndexMaxParallelism()), 1);
+ String basePath = dataTableMetaClient.getBasePath().toString();
+ // we might need to set some additional variables if we need to process
log files.
+ boolean anyLogFilesWithDeleteBlocks =
allWriteStats.stream().anyMatch(writeStat -> {
+ String fileName = FSUtils.getFileName(writeStat.getPath(),
writeStat.getPartitionPath());
+ return FSUtils.isLogFile(fileName) && writeStat.getNumInserts() == 0
&& writeStat.getNumUpdateWrites() == 0 && writeStat.getNumDeletes() > 0;
+ });
+ Option<String> latestCommitTimestamp = Option.empty();
+ Option<Schema> writerSchemaOpt = Option.empty();
+ if (anyLogFilesWithDeleteBlocks) { // if we have a log file w/ pure
deletes.
+ latestCommitTimestamp =
Option.of(dataTableMetaClient.getActiveTimeline().getCommitsTimeline().lastInstant().get().requestedTime());
+ writerSchemaOpt = tryResolveSchemaForTable(dataTableMetaClient);
+ }
+ int maxBufferSize = metadataConfig.getMaxReaderBufferSize();
+ StorageConfiguration storageConfiguration =
dataTableMetaClient.getStorageConf();
+ Option<Schema> finalWriterSchemaOpt = writerSchemaOpt;
+ Option<String> finalLatestCommitTimestamp = latestCommitTimestamp;
+ HoodieData<HoodieRecord> recordIndexRecords =
engineContext.parallelize(allWriteStats, parallelism)
+ .flatMap(writeStat -> {
+ HoodieStorage storage = HoodieStorageUtils.getStorage(new
StoragePath(writeStat.getPath()), storageConfiguration);
+ // handle base files
+ if
(writeStat.getPath().endsWith(HoodieFileFormat.PARQUET.getFileExtension())) {
+ return
BaseFileUtils.generateRLIMetadataHoodieRecordsForBaseFile(basePath, writeStat,
writesFileIdEncoding, instantTime, storage);
+ } else {
+ // for logs, we only need to process delete blocks for RLI
+ if (writeStat.getNumInserts() == 0 &&
writeStat.getNumUpdateWrites() == 0 && writeStat.getNumDeletes() > 0) {
+ Set<String> deletedRecordKeys =
getDeletedRecordKeys(dataTableMetaClient.getBasePath().toString() + "/" +
writeStat.getPath(), dataTableMetaClient,
Review Comment:
Let's try to use `FSUtils` to have the full path:
`dataTableMetaClient.getBasePath().toString() + "/" + writeStat.getPath()`
--
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]
