aokolnychyi commented on code in PR #5495:
URL: https://github.com/apache/iceberg/pull/5495#discussion_r948400468
##########
spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/actions/DeleteOrphanFilesSparkAction.java:
##########
@@ -426,65 +405,159 @@ private static Map<String, String>
flattenMap(Map<String, String> map) {
if (map != null) {
for (String key : map.keySet()) {
String value = map.get(key);
- for (String splitKey : COMMA.split(key)) {
+ for (String splitKey : COMMA_SPLITTER.split(key)) {
flattenedMap.put(splitKey.trim(), value.trim());
}
}
}
return flattenedMap;
}
- private static MapPartitionsFunction<Tuple2<FileMetadata, FileMetadata>,
String> findOrphanFiles(
- PrefixMismatchMode mode, SetAccumulator<Pair<String, String>> conflicts)
{
- return rows -> {
- Iterator<String> transformed =
- Iterators.transform(
- rows,
- row -> {
- FileMetadata actual = row._1;
- FileMetadata valid = row._2;
-
- if (valid == null) {
- return actual.location;
- }
-
- boolean schemeMatch =
- Strings.isNullOrEmpty(valid.scheme)
- || valid.scheme.equalsIgnoreCase(actual.scheme);
- boolean authorityMatch =
- Strings.isNullOrEmpty(valid.authority)
- || valid.authority.equalsIgnoreCase(actual.authority);
-
- if ((!schemeMatch || !authorityMatch) && mode ==
PrefixMismatchMode.DELETE) {
- return actual.location;
- } else {
- if (!schemeMatch) {
- conflicts.add(Pair.of(valid.scheme, actual.scheme));
- }
- if (!authorityMatch) {
- conflicts.add(Pair.of(valid.authority, actual.authority));
- }
- }
-
- return null;
- });
- return Iterators.filter(transformed, Objects::nonNull);
- };
+ private static class ListDirsRecursively implements
FlatMapFunction<Iterator<String>, String> {
+
+ private final Broadcast<SerializableConfiguration> hadoopConf;
+ private final long olderThanTimestamp;
+ private final PathFilter pathFilter;
+
+ ListDirsRecursively(
+ Broadcast<SerializableConfiguration> hadoopConf,
+ long olderThanTimestamp,
+ PathFilter pathFilter) {
+
+ this.hadoopConf = hadoopConf;
+ this.olderThanTimestamp = olderThanTimestamp;
+ this.pathFilter = pathFilter;
+ }
+
+ @Override
+ public Iterator<String> call(Iterator<String> dirs) throws Exception {
+ List<String> subDirs = Lists.newArrayList();
+ List<String> files = Lists.newArrayList();
+
+ Predicate<FileStatus> predicate = file -> file.getModificationTime() <
olderThanTimestamp;
+
+ dirs.forEachRemaining(
+ dir -> {
Review Comment:
It got formatted a little bit weirdly after removing `{`. I switched to a
`while` loop and got rid of `{` after.
--
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]
