[GitHub] drill pull request #831: DRILL-5432: Added pcap-format support

[paul-rogers <gi...@git.apache.org>]

Github user paul-rogers commented on a diff in the pull request:

    https://github.com/apache/drill/pull/831#discussion_r123397439
  
    --- Diff: exec/java-exec/src/main/java/org/apache/drill/exec/store/pcap/PcapRecordReader.java ---
    @@ -0,0 +1,307 @@
    +/*
    + * 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
    + * <p>
    + * http://www.apache.org/licenses/LICENSE-2.0
    + * <p>
    + * 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 com.google.common.collect.ImmutableList;
    +import com.google.common.collect.ImmutableMap;
    +import org.apache.drill.common.exceptions.ExecutionSetupException;
    +import org.apache.drill.common.exceptions.UserException;
    +import org.apache.drill.common.expression.SchemaPath;
    +import org.apache.drill.common.types.TypeProtos;
    +import org.apache.drill.common.types.TypeProtos.MajorType;
    +import org.apache.drill.common.types.TypeProtos.MinorType;
    +import org.apache.drill.common.types.Types;
    +import org.apache.drill.exec.exception.SchemaChangeException;
    +import org.apache.drill.exec.expr.TypeHelper;
    +import org.apache.drill.exec.ops.OperatorContext;
    +import org.apache.drill.exec.physical.impl.OutputMutator;
    +import org.apache.drill.exec.record.MaterializedField;
    +import org.apache.drill.exec.store.AbstractRecordReader;
    +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.dto.ColumnDto;
    +import org.apache.drill.exec.store.pcap.schema.PcapTypes;
    +import org.apache.drill.exec.store.pcap.schema.Schema;
    +import org.apache.drill.exec.vector.NullableBigIntVector;
    +import org.apache.drill.exec.vector.NullableIntVector;
    +import org.apache.drill.exec.vector.NullableTimeStampVector;
    +import org.apache.drill.exec.vector.NullableVarCharVector;
    +import org.apache.drill.exec.vector.ValueVector;
    +import org.slf4j.Logger;
    +import org.slf4j.LoggerFactory;
    +
    +import java.io.FileInputStream;
    +import java.io.IOException;
    +import java.io.InputStream;
    +import java.nio.ByteBuffer;
    +import java.util.List;
    +import java.util.Map;
    +
    +import static java.nio.charset.StandardCharsets.UTF_8;
    +import static org.apache.drill.exec.store.pcap.Utils.parseBytesToASCII;
    +
    +public class PcapRecordReader extends AbstractRecordReader {
    +  private static final Logger logger = LoggerFactory.getLogger(PcapRecordReader.class);
    +
    +  private static final int BATCH_SIZE = 40_000;
    +
    +  private OutputMutator output;
    +
    +  private PacketDecoder decoder;
    +  private ImmutableList<ProjectedColumnInfo> projectedCols;
    +
    +  private byte[] buffer;
    +  private int offset = 0;
    +  private InputStream in;
    +  private int validBytes;
    +
    +  private String inputPath;
    +  private List<SchemaPath> projectedColumns;
    +
    +  private static final Map<PcapTypes, MinorType> TYPES;
    +
    +  private static class ProjectedColumnInfo {
    +    ValueVector vv;
    +    ColumnDto pcapColumn;
    +  }
    +
    +  static {
    +    TYPES = ImmutableMap.<PcapTypes, TypeProtos.MinorType>builder()
    +        .put(PcapTypes.STRING, MinorType.VARCHAR)
    +        .put(PcapTypes.INTEGER, MinorType.INT)
    +        .put(PcapTypes.LONG, MinorType.BIGINT)
    +        .put(PcapTypes.TIMESTAMP, MinorType.TIMESTAMP)
    +        .build();
    +  }
    +
    +  public PcapRecordReader(final String inputPath,
    +                          final List<SchemaPath> projectedColumns) {
    +    this.inputPath = inputPath;
    +    this.projectedColumns = projectedColumns;
    +  }
    +
    +  @Override
    +  public void setup(final OperatorContext context, final OutputMutator output) throws ExecutionSetupException {
    +    try {
    +
    +      this.output = output;
    +      this.buffer = new byte[100000];
    +      this.in = new FileInputStream(inputPath);
    +      this.decoder = new PacketDecoder(in);
    +      this.validBytes = in.read(buffer);
    +      this.projectedCols = getProjectedColsIfItNull();
    +      setColumns(projectedColumns);
    +    } catch (IOException io) {
    +      throw UserException.dataReadError(io)
    +          .addContext("File name:", inputPath)
    +          .build(logger);
    +    }
    +  }
    +
    +  @Override
    +  public int next() {
    +    try {
    +      return parsePcapFilesAndPutItToTable();
    +    } catch (IOException io) {
    +      throw UserException.dataReadError(io)
    +          .addContext("Trouble with reading packets in file!")
    +          .build(logger);
    +    }
    +  }
    +
    +  @Override
    +  public void close() throws Exception {
    +//    buffer = null;
    +//    in.close();
    +  }
    +
    +  private ImmutableList<ProjectedColumnInfo> getProjectedColsIfItNull() {
    +    return projectedCols != null ? projectedCols : initCols(new Schema());
    +  }
    +
    +  private ImmutableList<ProjectedColumnInfo> initCols(final Schema schema) {
    +    ImmutableList.Builder<ProjectedColumnInfo> pciBuilder = ImmutableList.builder();
    +    ColumnDto column;
    +
    +    for (int i = 0; i < schema.getNumberOfColumns(); i++) {
    +      column = schema.getColumnByIndex(i);
    +
    +      final String name = column.getColumnName();
    --- End diff --
    
    The column name passed in from Drill will have the case that the user typed. For example:
    
    ```
    SELECT DST_IP ...
    SELECT DsT_iP ...
    SELECT dst_ip ...
    ```
    
    Drill is supposed to be case insensitive: all the above should match the same "dst_ip" column.
    
    But, the code later code a case-insensitive switch. So, a simple solution here is to do:
    ```
    final String name = column.getColumnName().toLowerCase();
    ```


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---