ajantha-bhat commented on code in PR #6090:
URL: https://github.com/apache/iceberg/pull/6090#discussion_r1047957805
##########
core/src/main/java/org/apache/iceberg/IncrementalFileCleanup.java:
##########
@@ -264,6 +264,14 @@ public void cleanFiles(TableMetadata beforeExpiration,
TableMetadata afterExpira
LOG.warn("Manifests Lists to delete: {}", Joiner.on(",
").join(manifestListsToDelete));
deleteFiles(manifestsToDelete, "manifest");
deleteFiles(manifestListsToDelete, "manifest list");
+
+ if (!beforeExpiration.statisticsFiles().isEmpty()) {
+ Set<String> expiredStatisticsFilesLocations =
+ expiredStatisticsFilesLocations(beforeExpiration, afterExpiration);
+ LOG.warn(
+ "Statistics files to delete: {}", Joiner.on(",
").join(expiredStatisticsFilesLocations));
Review Comment:
I made it to debug and other places too I have changed to debug log.
##########
core/src/main/java/org/apache/iceberg/FileCleanupStrategy.java:
##########
@@ -83,4 +85,25 @@ protected void deleteFiles(Set<String> pathsToDelete, String
fileType) {
(file, thrown) -> LOG.warn("Delete failed for {} file: {}",
fileType, file, thrown))
.run(deleteFunc::accept);
}
+
+ protected Set<String> expiredStatisticsFilesLocations(
+ TableMetadata beforeExpiration, TableMetadata afterExpiration) {
+ Set<String> statisticsFilesLocationBeforeExpiry =
allStatisticsFilesLocation(beforeExpiration);
+ Set<String> statisticsFilesLocationAfterExpiry =
allStatisticsFilesLocation(afterExpiration);
+
statisticsFilesLocationBeforeExpiry.removeAll(statisticsFilesLocationAfterExpiry);
+ return statisticsFilesLocationBeforeExpiry;
+ }
+
+ private Set<String> allStatisticsFilesLocation(TableMetadata tableMetadata) {
+ Set<String> allStatisticsFilesLocation;
+ if (tableMetadata.statisticsFiles() != null) {
+ allStatisticsFilesLocation =
+ tableMetadata.statisticsFiles().stream()
+ .map(StatisticsFile::path)
+ .collect(Collectors.toSet());
+ } else {
+ allStatisticsFilesLocation = Sets.newHashSet();
+ }
+ return allStatisticsFilesLocation;
Review Comment:
done
--
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]
