Mailing-List: contact dev-help@apex.incubator.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@apex.incubator.apache.org
From: DT-Priyanka <git@git.apache.org>
To: dev@apex.incubator.apache.org
Reply-To: dev@apex.incubator.apache.org
References: <git-pr-216-incubator-apex-malhar@git.apache.org>
In-Reply-To: <git-pr-216-incubator-apex-malhar@git.apache.org>
Subject: [GitHub] incubator-apex-malhar pull request: APEXMALHAR-2013 : HDFS
 output ...
Content-Type: text/plain
Message-Id: <20160318083915.D97E2DFBA0@git1-us-west.apache.org>
Date: Fri, 18 Mar 2016 08:39:15 +0000 (UTC)

Github user DT-Priyanka commented on a diff in the pull request:

    https://github.com/apache/incubator-apex-malhar/pull/216#discussion_r56625652
  
    --- Diff: library/src/main/java/com/datatorrent/lib/io/fs/FileMerger.java ---
    @@ -0,0 +1,161 @@
    +/**
    + * 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 com.datatorrent.lib.io.fs;
    +
    +import java.io.IOException;
    +import java.io.OutputStream;
    +
    +import org.slf4j.Logger;
    +import org.slf4j.LoggerFactory;
    +
    +import org.apache.hadoop.fs.Path;
    +
    +import com.datatorrent.api.AutoMetric;
    +import com.datatorrent.api.Context;
    +import com.datatorrent.api.Context.OperatorContext;
    +import com.datatorrent.lib.io.fs.Synchronizer.OutputFileMetadata;
    +
    +/**
    + * This operator merges the blocks into a file. The list of blocks is obtained
    + * from the OutputFileMetadata. The implementation extends FileStitcher (which
    + * uses reconciler), hence the file merging operation is carried out in a
    + * separate thread.
    + *
    + */
    +public class FileMerger extends FileStitcher<OutputFileMetadata>
    +{
    +  /**
    +   * Flag to control if existing file with same name should be overwritten
    +   */
    +  private boolean overwriteOnConflict = true;
    +
    +  private static final Logger LOG = LoggerFactory.getLogger(FileMerger.class);
    +
    +  @AutoMetric
    +  private long bytesWrittenPerSec;
    +
    +  private long bytesWritten;
    +  private double windowTimeSec;
    +
    +  @Override
    +  public void setup(OperatorContext context)
    +  {
    +    super.setup(context);
    +    windowTimeSec = (context.getValue(Context.OperatorContext.APPLICATION_WINDOW_COUNT)
    +        * context.getValue(Context.DAGContext.STREAMING_WINDOW_SIZE_MILLIS) * 1.0) / 1000.0;
    +  }
    +
    +  @Override
    +  public void beginWindow(long windowId)
    +  {
    +    super.beginWindow(windowId);
    +    bytesWrittenPerSec = 0;
    +    bytesWritten = 0;
    +  }
    +
    +  /* 
    +   * Calls super.endWindow() and sets counters 
    +   * @see com.datatorrent.api.BaseOperator#endWindow()
    +   */
    +  @Override
    +  public void endWindow()
    +  {
    +    OutputFileMetadata outputFileMetadata;
    +    int size = doneTuples.size();
    +    for (int i = 0; i < size; i++) {
    +      outputFileMetadata = doneTuples.peek();
    +      // If a tuple is present in doneTuples, it has to be also present in successful/failed/skipped
    +      // as processCommittedData adds tuple in successful/failed/skipped
    +      // and then reconciler thread add that in doneTuples 
    +      if (successfulFiles.contains(outputFileMetadata)) {
    +        successfulFiles.remove(outputFileMetadata);
    +        LOG.debug("File copy successful: {}", outputFileMetadata.getStitchedFileRelativePath());
    +      } else if (skippedFiles.contains(outputFileMetadata)) {
    +        skippedFiles.remove(outputFileMetadata);
    +        LOG.debug("File copy skipped: {}", outputFileMetadata.getStitchedFileRelativePath());
    +      } else if (failedFiles.contains(outputFileMetadata)) {
    +        failedFiles.remove(outputFileMetadata);
    +        LOG.debug("File copy failed: {}", outputFileMetadata.getStitchedFileRelativePath());
    +      } else {
    +        throw new RuntimeException("Tuple present in doneTuples but not in successfulFiles: "
    --- End diff --
    
    minor: message cannot say "but not in successfulFiles" it can be sucess/skip/error.


---
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.
---