apex-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From amberarrow <...@git.apache.org>
Subject [GitHub] apex-malhar pull request #326: APEXMALHAR-2116 Added FS record reader operat...
Date Tue, 21 Jun 2016 23:22:06 GMT
Github user amberarrow commented on a diff in the pull request:

    https://github.com/apache/apex-malhar/pull/326#discussion_r67970457
  
    --- Diff: library/src/main/java/org/apache/apex/malhar/lib/fs/FSRecordReader.java ---
    @@ -0,0 +1,175 @@
    +/**
    + * 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.apex.malhar.lib.fs;
    +
    +import java.io.IOException;
    +
    +import org.apache.commons.beanutils.ConvertUtils;
    +import org.apache.commons.beanutils.converters.AbstractConverter;
    +import org.apache.hadoop.fs.FSDataInputStream;
    +
    +import com.datatorrent.api.Context.OperatorContext;
    +import com.datatorrent.api.DefaultOutputPort;
    +import com.datatorrent.lib.io.block.BlockMetadata;
    +import com.datatorrent.lib.io.block.FSSliceReader;
    +import com.datatorrent.lib.io.block.ReaderContext;
    +
    +/**
    + * This operator can be used for reading records/tuples from Filesystem 
    + * in parallel (without ordering guarantees between tuples).
    + * Records can be delimited (e.g. newline) or fixed with records.
    + * Output tuples are byte[]. 
    + * 
    + * Typically, this operator will be connected to output of FileSplitterInput 
    + * to read records in parallel.
    + */
    +@org.apache.hadoop.classification.InterfaceStability.Evolving
    +public class FSRecordReader extends FSSliceReader
    +{
    +  /**
    +   * Record reader mode decides how to split the records.
    +   */
    +  public static enum RECORD_READER_MODE
    +  {
    +    DELIMITED_RECORD, FIXED_WIDTH_RECORD;
    +  }
    +
    +  /**
    +   * Criteria for record split
    +   */
    +  private RECORD_READER_MODE mode = RECORD_READER_MODE.DELIMITED_RECORD;
    +  
    +  /**
    +   * Length for fixed width record
    +   */
    +  private int recordLength;
    +  
    +  /**
    +   * Port to emit individual records/tuples as byte[]
    +   */
    +  public final transient DefaultOutputPort<byte[]> records = new DefaultOutputPort<byte[]>();
    +
    +  /**
    +   * Initialize appropriate reader context based on mode selection
    +   */
    +  @Override
    +  public void setup(OperatorContext context)
    +  {
    +    super.setup(context);
    +    if (mode == RECORD_READER_MODE.FIXED_WIDTH_RECORD) {
    +      ReaderContext.FixedBytesReaderContext<FSDataInputStream> fixedBytesReaderContext
= new ReaderContext.FixedBytesReaderContext<FSDataInputStream>();
    +      fixedBytesReaderContext.setLength(recordLength);
    +      readerContext = fixedBytesReaderContext;
    +    } else {
    +      readerContext = new ReaderContext.ReadAheadLineReaderContext<FSDataInputStream>();
    +    }
    +  }
    +  
    +  /**
    +   * Read the block data and emit records based on reader context
    +   *
    +   * @param blockMetadata block
    +   * @throws IOException
    +   */
    +  protected void readBlock(BlockMetadata blockMetadata) throws IOException
    +  {
    +    readerContext.initialize(stream, blockMetadata, consecutiveBlock);
    +    ReaderContext.Entity entity;
    +    while ((entity = readerContext.next()) != null) {
    +
    +      counters.getCounter(ReaderCounterKeys.BYTES).add(entity.getUsedBytes());
    +
    +      byte[] record = entity.getRecord();
    +
    +      //If the record is partial then ignore the record.
    --- End diff --
    
    why 'partial' rather than 'null' ?


---
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.
---

Mime
View raw message