danny0405 commented on code in PR #8955:
URL: https://github.com/apache/hudi/pull/8955#discussion_r1227903585
##########
hudi-hadoop-mr/src/main/java/org/apache/hudi/hadoop/avro/HoodieAvroParquetReader.java:
##########
@@ -50,24 +51,20 @@ public class HoodieAvroParquetReader extends
RecordReader<Void, ArrayWritable> {
private Schema baseSchema;
public HoodieAvroParquetReader(InputSplit inputSplit, Configuration conf)
throws IOException {
+ // get base schema
+ ParquetMetadata fileFooter =
+ ParquetFileReader.readFooter(conf, ((ParquetInputSplit)
inputSplit).getPath(), ParquetMetadataConverter.NO_FILTER);
+ MessageType messageType = fileFooter.getFileMetaData().getSchema();
+ baseSchema = new AvroSchemaConverter(conf).convert(messageType);
+
// if exists read columns, we need to filter columns.
List<String> readColNames =
Arrays.asList(HoodieColumnProjectionUtils.getReadColumnNames(conf));
if (!readColNames.isEmpty()) {
- // get base schema
- ParquetMetadata fileFooter =
- ParquetFileReader.readFooter(conf, ((ParquetInputSplit)
inputSplit).getPath(), ParquetMetadataConverter.NO_FILTER);
- MessageType messageType = fileFooter.getFileMetaData().getSchema();
- baseSchema = new AvroSchemaConverter(conf).convert(messageType);
- // filter schema for reading
- final Schema filterSchema = Schema.createRecord(baseSchema.getName(),
- baseSchema.getDoc(), baseSchema.getNamespace(), baseSchema.isError(),
- baseSchema.getFields().stream()
- .filter(f -> readColNames.contains(f.name()))
- .map(f -> new Schema.Field(f.name(), f.schema(), f.doc(),
f.defaultVal()))
- .collect(Collectors.toList()));
+ Schema filterSchema =
HoodieAvroUtils.generateProjectionSchema(baseSchema, readColNames);
Review Comment:
Can we write a test case for it.
--
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]
