vinothchandar commented on code in PR #6661:
URL: https://github.com/apache/hudi/pull/6661#discussion_r1178763050
##########
hudi-utilities/src/main/java/org/apache/hudi/utilities/sources/S3EventsHoodieIncrSource.java:
##########
@@ -213,15 +216,27 @@ public Pair<Option<Dataset<Row>>, String>
fetchNextBatch(Option<String> lastCkpt
}
});
return cloudFilesPerPartition.iterator();
- }, Encoders.STRING()).collectAsList();
+ }, Encoders.STRING());
Option<Dataset<Row>> dataset = Option.empty();
+ cloudFiles.cache();
if (!cloudFiles.isEmpty()) {
- DataFrameReader dataFrameReader = getDataFrameReader(fileFormat);
- dataset = Option.of(dataFrameReader.load(cloudFiles.toArray(new
String[0])));
+ JavaRDD<Dataset<Row>> datasetIterator = cloudFiles.javaRDD().flatMap(new
FlatMapFunction<String, Dataset<Row>>() {
+ @Override
+ public Iterator<Dataset<Row>> call(String cloudFile) throws Exception {
+ return Collections.singletonList(getDataFromFile(cloudFile,
fileFormat)).iterator();
+ }
+ });
+ Dataset<Row> finalDataset =
datasetIterator.fold(sparkSession.emptyDataFrame(), (Function2<Dataset<Row>,
Dataset<Row>, Dataset<Row>>) (v1, v2) -> v1.union(v2));
+ dataset = Option.of(finalDataset);
}
- LOG.debug("Extracted distinct files " + cloudFiles.size()
- + " and some samples " +
cloudFiles.stream().limit(10).collect(Collectors.toList()));
+ LOG.debug("Extracted distinct files " + cloudFiles.count()
Review Comment:
+1
--
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]
