aokolnychyi commented on code in PR #5495:
URL: https://github.com/apache/iceberg/pull/5495#discussion_r943794410
##########
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> {
Review Comment:
I think having separate classes for Spark functions is more readable with
new formatting so I am switching those for consistency. That's what @karuppayya
suggested earlier but we did not do cause of the existing code. I think it is
worth converting after a closer look.
--
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]
