danielxjd commented on a change in pull request #12223:
URL: https://github.com/apache/beam/pull/12223#discussion_r467200308
##########
File path:
sdks/java/io/parquet/src/main/java/org/apache/beam/sdk/io/parquet/ParquetIO.java
##########
@@ -230,14 +281,284 @@ public ReadFiles withAvroDataModel(GenericData model) {
return toBuilder().setAvroDataModel(model).build();
}
+ public ReadFiles withSplit() {
+ return toBuilder().setSplit(true).build();
+ }
+
@Override
public PCollection<GenericRecord> expand(PCollection<FileIO.ReadableFile>
input) {
checkNotNull(getSchema(), "Schema can not be null");
+ if (getSplit()) {
+ return input
+ .apply(ParDo.of(new SplitReadFn(getAvroDataModel())))
+ .setCoder(AvroCoder.of(getSchema()));
+ }
return input
.apply(ParDo.of(new ReadFn(getAvroDataModel())))
.setCoder(AvroCoder.of(getSchema()));
}
+ @DoFn.BoundedPerElement
+ static class SplitReadFn extends DoFn<FileIO.ReadableFile, GenericRecord> {
+ private Class<? extends GenericData> modelClass;
+ private static final Logger LOG =
LoggerFactory.getLogger(SplitReadFn.class);
+ private static final long SPLIT_LIMIT = 64000000;
Review comment:
Comment added. the unit is bytes.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
