001    /**
002     * Licensed to the Apache Software Foundation (ASF) under one
003     * or more contributor license agreements.  See the NOTICE file
004     * distributed with this work for additional information
005     * regarding copyright ownership.  The ASF licenses this file
006     * to you under the Apache License, Version 2.0 (the
007     * "License"); you may not use this file except in compliance
008     * with the License.  You may obtain a copy of the License at
009     *
010     *     http://www.apache.org/licenses/LICENSE-2.0
011     *
012     * Unless required by applicable law or agreed to in writing, software
013     * distributed under the License is distributed on an "AS IS" BASIS,
014     * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
015     * See the License for the specific language governing permissions and
016     * limitations under the License.
017     */
018    
019    package org.apache.hadoop.mapred;
020    
021    import org.apache.hadoop.classification.InterfaceAudience;
022    import org.apache.hadoop.classification.InterfaceStability;
023    import org.apache.hadoop.fs.Path;
024    import org.apache.hadoop.fs.PathFilter;
025    
026    /**
027     * A utility class. It provides
028     *   A path filter utility to filter out output/part files in the output dir
029     */
030    @InterfaceAudience.Public
031    @InterfaceStability.Stable
032    public class Utils {
033      public static class OutputFileUtils {
034        /**
035         * This class filters output(part) files from the given directory
036         * It does not accept files with filenames _logs and _SUCCESS.
037         * This can be used to list paths of output directory as follows:
038         *   Path[] fileList = FileUtil.stat2Paths(fs.listStatus(outDir,
039         *                                         new OutputFilesFilter()));
040         */
041        public static class OutputFilesFilter extends OutputLogFilter {
042          public boolean accept(Path path) {
043            return super.accept(path) 
044                   && !FileOutputCommitter.SUCCEEDED_FILE_NAME
045                       .equals(path.getName());
046          }
047        }
048        
049        /**
050         * This class filters log files from directory given
051         * It doesnt accept paths having _logs.
052         * This can be used to list paths of output directory as follows:
053         *   Path[] fileList = FileUtil.stat2Paths(fs.listStatus(outDir,
054         *                                   new OutputLogFilter()));
055         */
056        public static class OutputLogFilter implements PathFilter {
057          public boolean accept(Path path) {
058            return !"_logs".equals(path.getName());
059          }
060        }
061      }
062    }