Github user mattyb149 commented on a diff in the pull request: https://github.com/apache/nifi/pull/2718#discussion_r194589636 --- Diff: nifi-nar-bundles/nifi-standard-services/nifi-record-serialization-services-bundle/nifi-record-serialization-services/src/main/java/org/apache/nifi/avro/AvroReaderWithExplicitSchema.java --- @@ -17,33 +17,61 @@ package org.apache.nifi.avro; +import java.io.ByteArrayInputStream; +import java.io.ByteArrayOutputStream; import java.io.EOFException; import java.io.IOException; import java.io.InputStream; +import java.io.SequenceInputStream; import org.apache.avro.Schema; +import org.apache.avro.file.DataFileStream; import org.apache.avro.generic.GenericDatumReader; import org.apache.avro.generic.GenericRecord; import org.apache.avro.io.BinaryDecoder; import org.apache.avro.io.DatumReader; import org.apache.avro.io.DecoderFactory; -import org.apache.nifi.schema.access.SchemaNotFoundException; +import org.apache.commons.io.input.TeeInputStream; import org.apache.nifi.serialization.MalformedRecordException; import org.apache.nifi.serialization.record.RecordSchema; public class AvroReaderWithExplicitSchema extends AvroRecordReader { private final InputStream in; private final RecordSchema recordSchema; private final DatumReader<GenericRecord> datumReader; - private final BinaryDecoder decoder; + private BinaryDecoder decoder; private GenericRecord genericRecord; + private DataFileStream<GenericRecord> dataFileStream; - public AvroReaderWithExplicitSchema(final InputStream in, final RecordSchema recordSchema, final Schema avroSchema) throws IOException, SchemaNotFoundException { + public AvroReaderWithExplicitSchema(final InputStream in, final RecordSchema recordSchema, final Schema avroSchema) throws IOException { this.in = in; this.recordSchema = recordSchema; - datumReader = new GenericDatumReader<GenericRecord>(avroSchema); - decoder = DecoderFactory.get().binaryDecoder(in, null); + datumReader = new GenericDatumReader<>(avroSchema); + ByteArrayOutputStream baos = new ByteArrayOutputStream(); + TeeInputStream teeInputStream = new TeeInputStream(in, baos); + // Try to parse as a DataFileStream, if it works, glue the streams back together and delegate calls to the DataFileStream + try { + dataFileStream = new DataFileStream<>(teeInputStream, new GenericDatumReader<>()); --- End diff -- Sounds about right :) I was playing around with gluing these together and as soon as it "worked" I stopped touching it. Will take a closer look, thanks!
---