danny0405 commented on code in PR #7767:
URL: https://github.com/apache/hudi/pull/7767#discussion_r1089604222
##########
hudi-client/hudi-client-common/src/main/java/org/apache/hudi/table/action/clean/CleanPlanner.java:
##########
@@ -436,23 +433,12 @@ private List<CleanFileInfo>
getCleanFileInfoForSlice(FileSlice nextSlice) {
cleanPaths.add(new
CleanFileInfo(dataFile.getBootstrapBaseFile().get().getPath(), true));
}
}
- if (hoodieTable.getMetaClient().getTableType() ==
HoodieTableType.MERGE_ON_READ) {
- // If merge on read, then clean the log files for the commits as well
- Predicate<HoodieLogFile> notCDCLogFile =
- hoodieLogFile ->
!hoodieLogFile.getFileName().endsWith(HoodieCDCUtils.CDC_LOGFILE_SUFFIX);
- cleanPaths.addAll(
- nextSlice.getLogFiles().filter(notCDCLogFile).map(lf -> new
CleanFileInfo(lf.getPath().toString(), false))
- .collect(Collectors.toList()));
- }
- if (hoodieTable.getMetaClient().getTableConfig().isCDCEnabled()) {
- // The cdc log files will be written out in cdc scenario, no matter the
table type is mor or cow.
- // Here we need to clean uo these cdc log files.
- Predicate<HoodieLogFile> isCDCLogFile =
- hoodieLogFile ->
hoodieLogFile.getFileName().endsWith(HoodieCDCUtils.CDC_LOGFILE_SUFFIX);
- cleanPaths.addAll(
- nextSlice.getLogFiles().filter(isCDCLogFile).map(lf -> new
CleanFileInfo(lf.getPath().toString(), false))
- .collect(Collectors.toList()));
- }
+
+ // clean the log files for the commits, which contain cdc log files in cdc
scenario
+ // and normal log files for mor tables.
+ cleanPaths.addAll(
+ nextSlice.getLogFiles().map(lf -> new
CleanFileInfo(lf.getPath().toString(), false))
+ .collect(Collectors.toList()));
return cleanPaths;
Review Comment:
Should pre-condition `hoodieTable.getMetaClient().getTableType() ==
HoodieTableType.MERGE_ON_READ` be kept for efficiency?
--
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]
