paul-rogers commented on a change in pull request #1862: DRILL-7385: Convert PCAP Format Plugin to EVF URL: https://github.com/apache/drill/pull/1862#discussion_r331764799
########## File path: exec/java-exec/src/main/java/org/apache/drill/exec/store/pcap/PcapBatchReader.java ########## @@ -0,0 +1,295 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.drill.exec.store.pcap; + +import org.apache.drill.common.exceptions.UserException; +import org.apache.drill.common.types.TypeProtos; +import org.apache.drill.exec.physical.impl.scan.file.FileScanFramework.FileSchemaNegotiator; +import org.apache.drill.exec.physical.impl.scan.framework.ManagedReader; +import org.apache.drill.exec.physical.resultSet.ResultSetLoader; +import org.apache.drill.exec.physical.resultSet.RowSetLoader; +import org.apache.drill.exec.record.metadata.ColumnMetadata; +import org.apache.drill.exec.record.metadata.MetadataUtils; +import org.apache.drill.exec.record.metadata.SchemaBuilder; +import org.apache.drill.exec.record.metadata.TupleMetadata; +import org.apache.drill.exec.store.pcap.decoder.Packet; +import org.apache.drill.exec.store.pcap.decoder.PacketDecoder; +import org.apache.drill.exec.store.pcap.schema.Schema; +import org.apache.drill.exec.vector.accessor.ScalarWriter; +import org.apache.drill.exec.vector.accessor.TupleWriter; +import org.apache.hadoop.fs.FSDataInputStream; +import org.apache.hadoop.mapred.FileSplit; +import org.joda.time.Instant; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.io.IOException; +import org.apache.hadoop.fs.Path; + +import static org.apache.drill.exec.store.pcap.PcapFormatUtils.parseBytesToASCII; + +public class PcapBatchReader implements ManagedReader<FileSchemaNegotiator> { + + private FileSplit split; + + private PcapReaderConfig readerConfig; + + private PacketDecoder decoder; + + private ResultSetLoader loader; + + private FSDataInputStream fsStream; + + private Schema pcapSchema; + + private int validBytes; + + private byte[] buffer; + + private int offset = 0; + + static final int BUFFER_SIZE = 500_000; + + private static final Logger logger = LoggerFactory.getLogger(PcapBatchReader.class); + + public static class PcapReaderConfig { + + protected final PcapFormatPlugin plugin; + public PcapReaderConfig(PcapFormatPlugin plugin) { + this.plugin = plugin; + } + } + + public PcapBatchReader(PcapReaderConfig readerConfig) { + this.readerConfig = readerConfig; + } + + @Override + public boolean open(FileSchemaNegotiator negotiator) { + split = negotiator.split(); + openFile(negotiator); + SchemaBuilder builder = new SchemaBuilder(); + this.pcapSchema = new Schema(); + TupleMetadata schema = pcapSchema.buildSchema(builder); + negotiator.setTableSchema(schema, false); + this.loader = negotiator.build(); + return true; + } + + @Override + public boolean next() { + RowSetLoader rowWriter = loader.writer(); + while (!rowWriter.isFull()) { + if (!parseNextPacket(rowWriter)) { + return false; + } + } + return true; + } + + @Override + public void close() { + try { + fsStream.close(); + } catch (IOException e) { + throw UserException. + dataReadError() + .addContext("Error closing InputStream: " + e.getMessage()) + .build(logger); + } + fsStream = null; + this.buffer = null; + this.decoder = null; + } + + private void openFile(FileSchemaNegotiator negotiator) { + String filePath = null; + try { + filePath = split.getPath().toString(); + this.fsStream = negotiator.fileSystem().open(new Path(filePath)); + this.decoder = new PacketDecoder(fsStream); + this.buffer = new byte[BUFFER_SIZE + decoder.getMaxLength()]; + this.validBytes = fsStream.read(buffer); Review comment: Nit: The this. prefix is not needed. ---------------------------------------------------------------- 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 With regards, Apache Git Services
