jonvex commented on code in PR #10278:
URL: https://github.com/apache/hudi/pull/10278#discussion_r1437722062
##########
hudi-common/src/main/java/org/apache/hudi/common/table/read/HoodieFileGroupReader.java:
##########
@@ -227,23 +249,34 @@ private ClosableIterator<T>
makeBootstrapBaseFileIterator(HoodieBaseFile baseFil
BaseFile dataFile = baseFile.getBootstrapBaseFile().get();
Pair<List<Schema.Field>,List<Schema.Field>> requiredFields =
getDataAndMetaCols(requiredSchema);
Pair<List<Schema.Field>,List<Schema.Field>> allFields =
getDataAndMetaCols(dataSchema);
-
- Option<ClosableIterator<T>> dataFileIterator =
requiredFields.getRight().isEmpty() ? Option.empty() :
-
Option.of(readerContext.getFileRecordIterator(dataFile.getHadoopPath(), 0,
dataFile.getFileLen(),
- createSchemaFromFields(allFields.getRight()),
createSchemaFromFields(requiredFields.getRight()), hadoopConf));
-
- Option<ClosableIterator<T>> skeletonFileIterator =
requiredFields.getLeft().isEmpty() ? Option.empty() :
-
Option.of(readerContext.getFileRecordIterator(baseFile.getHadoopPath(), 0,
baseFile.getFileLen(),
- createSchemaFromFields(allFields.getLeft()),
createSchemaFromFields(requiredFields.getLeft()), hadoopConf));
+ Option<Pair<ClosableIterator<T>,Schema>> dataFileIterator =
+ makeBootstrapBaseFileIteratorHelper(requiredFields.getRight(),
allFields.getRight(), dataFile);
+ Option<Pair<ClosableIterator<T>,Schema>> skeletonFileIterator =
+ makeBootstrapBaseFileIteratorHelper(requiredFields.getLeft(),
allFields.getLeft(), baseFile);
if (!dataFileIterator.isPresent() && !skeletonFileIterator.isPresent()) {
throw new IllegalStateException("should not be here if only partition
cols are required");
} else if (!dataFileIterator.isPresent()) {
- return skeletonFileIterator.get();
+ return skeletonFileIterator.get().getLeft();
} else if (!skeletonFileIterator.isPresent()) {
- return dataFileIterator.get();
+ return dataFileIterator.get().getLeft();
} else {
- return readerContext.mergeBootstrapReaders(skeletonFileIterator.get(),
dataFileIterator.get());
+ return
readerContext.mergeBootstrapReaders(skeletonFileIterator.get().getLeft(),
skeletonFileIterator.get().getRight(),
+ dataFileIterator.get().getLeft(), dataFileIterator.get().getRight());
+ }
+ }
+
+ private Option<Pair<ClosableIterator<T>,Schema>>
makeBootstrapBaseFileIteratorHelper(List<Schema.Field> requiredFields,
+
List<Schema.Field> allFields,
+
BaseFile file) throws IOException {
+ if (requiredFields.isEmpty()) {
+ return Option.empty();
+ }
+ if (needMerge && shouldMergeWithPosition) {
+ requiredFields.add(getPositionalMergeField());
}
+ Schema requiredSchema = createSchemaFromFields(requiredFields);
+ return
Option.of(Pair.of(readerContext.getFileRecordIterator(file.getHadoopPath(), 0,
file.getFileLen(),
+ requiredSchema, createSchemaFromFields(allFields), hadoopConf,
this.needMerge), requiredSchema));
Review Comment:
requiredSchema and data schema are flipped
--
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]
