apex-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From ishark <...@git.apache.org>
Subject [GitHub] incubator-apex-malhar pull request: APEXMALHAR-2008: Create HDFS F...
Date Mon, 14 Mar 2016 23:53:15 GMT
Github user ishark commented on a diff in the pull request:

    https://github.com/apache/incubator-apex-malhar/pull/207#discussion_r56096295
  
    --- Diff: library/src/main/java/com/datatorrent/lib/io/fs/HDFSFileSplitter.java ---
    @@ -0,0 +1,184 @@
    +/**
    + * 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.File;
    +import java.io.IOException;
    +import java.util.regex.Matcher;
    +import java.util.regex.Pattern;
    +
    +import javax.validation.constraints.NotNull;
    +
    +import org.apache.hadoop.fs.FileStatus;
    +import org.apache.hadoop.fs.Path;
    +
    +import com.datatorrent.api.Context.OperatorContext;
    +import com.datatorrent.lib.io.block.BlockMetadata.FileBlockMetadata;
    +
    +/**
    + * HDFSFileSplitter extends {@link FileSplitterInput} to,
    + * 1. Add relative path to file metadata.
    + * 2. Ignore HDFS temp files (files with extensions _COPYING_).
    + * 3. Set sequencial read option on readers.
    + */
    +public class HDFSFileSplitter extends FileSplitterInput
    +{
    +  private boolean sequencialFileRead;
    +
    +  public HDFSFileSplitter()
    +  {
    +    super();
    +    super.setScanner(new HDFSScanner());
    +  }
    +
    +  @Override
    +  protected FileMetadata createFileMetadata(FileInfo fileInfo)
    +  {
    +    return new HDFSFileMetaData(fileInfo.getFilePath());
    +  }
    +
    +  @Override
    +  protected HDFSFileMetaData buildFileMetadata(FileInfo fileInfo) throws IOException
    +  {
    +    FileMetadata metadata = super.buildFileMetadata(fileInfo);
    +    HDFSFileMetaData hdfsFileMetaData = (HDFSFileMetaData)metadata;
    +
    +    Path path = new Path(fileInfo.getFilePath());
    +    FileStatus status = getFileStatus(path);
    +    if (fileInfo.getDirectoryPath() == null) { // Direct filename is given as input.
    +      hdfsFileMetaData.setRelativePath(status.getPath().getName());
    +    } else {
    +      String relativePath = getRelativePathWithFolderName(fileInfo);
    +      hdfsFileMetaData.setRelativePath(relativePath);
    +    }
    +    return hdfsFileMetaData;
    +  }
    +
    +  /*
    +   * As folder name was given to input for copy, prefix folder name to the sub items
to copy.
    +   */
    +  private String getRelativePathWithFolderName(FileInfo fileInfo)
    +  {
    +    String parentDir = new Path(fileInfo.getDirectoryPath()).getName();
    +    return parentDir + File.separator + fileInfo.getRelativeFilePath();
    +  }
    +
    +  @Override
    +  protected FileBlockMetadata createBlockMetadata(FileMetadata fileMetadata)
    +  {
    +    FileBlockMetadata blockMetadta = new FileBlockMetadata(fileMetadata.getFilePath());
    +    blockMetadta.setReadBlockInSequence(sequencialFileRead);
    +    return blockMetadta;
    +  }
    +
    +  public boolean isSequencialFileRead()
    +  {
    +    return sequencialFileRead;
    +  }
    +
    +  public void setSequencialFileRead(boolean sequencialFileRead)
    +  {
    +    this.sequencialFileRead = sequencialFileRead;
    +  }
    +
    +  /**
    +   * HDFSScanner extends {@link TimeBasedDirectoryScanner} to ignore HDFS temporary files
    +   * and files containing unsupported characters. 
    +   */
    +  public static class HDFSScanner extends TimeBasedDirectoryScanner
    +  {
    +    protected static final String HDFS_TEMP_FILE = ".*._COPYING_";
    +    protected static final String UNSUPPORTED_CHARACTOR = ":";
    +    private transient Pattern ignoreRegex;
    --- End diff --
    
    I think ignoreFileRegex could be useful for non-hdfs file inputs as well.


---
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