[120] | 1 | /** |
---|
| 2 | * Licensed to the Apache Software Foundation (ASF) under one |
---|
| 3 | * or more contributor license agreements. See the NOTICE file |
---|
| 4 | * distributed with this work for additional information |
---|
| 5 | * regarding copyright ownership. The ASF licenses this file |
---|
| 6 | * to you under the Apache License, Version 2.0 (the |
---|
| 7 | * "License"); you may not use this file except in compliance |
---|
| 8 | * with the License. You may obtain a copy of the License at |
---|
| 9 | * |
---|
| 10 | * http://www.apache.org/licenses/LICENSE-2.0 |
---|
| 11 | * |
---|
| 12 | * Unless required by applicable law or agreed to in writing, software |
---|
| 13 | * distributed under the License is distributed on an "AS IS" BASIS, |
---|
| 14 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
---|
| 15 | * See the License for the specific language governing permissions and |
---|
| 16 | * limitations under the License. |
---|
| 17 | */ |
---|
| 18 | |
---|
| 19 | package org.apache.hadoop.mapreduce.lib.output; |
---|
| 20 | |
---|
| 21 | import java.io.IOException; |
---|
| 22 | |
---|
| 23 | import org.apache.hadoop.fs.FileSystem; |
---|
| 24 | import org.apache.hadoop.fs.Path; |
---|
| 25 | |
---|
| 26 | import org.apache.hadoop.io.SequenceFile; |
---|
| 27 | import org.apache.hadoop.io.SequenceFile.CompressionType; |
---|
| 28 | import org.apache.hadoop.io.compress.CompressionCodec; |
---|
| 29 | import org.apache.hadoop.io.compress.DefaultCodec; |
---|
| 30 | import org.apache.hadoop.mapreduce.Job; |
---|
| 31 | import org.apache.hadoop.mapreduce.JobContext; |
---|
| 32 | import org.apache.hadoop.mapreduce.OutputFormat; |
---|
| 33 | import org.apache.hadoop.mapreduce.RecordWriter; |
---|
| 34 | import org.apache.hadoop.mapreduce.TaskAttemptContext; |
---|
| 35 | import org.apache.hadoop.util.ReflectionUtils; |
---|
| 36 | import org.apache.hadoop.conf.Configuration; |
---|
| 37 | |
---|
| 38 | /** An {@link OutputFormat} that writes {@link SequenceFile}s. */ |
---|
| 39 | public class SequenceFileOutputFormat <K,V> extends FileOutputFormat<K, V> { |
---|
| 40 | |
---|
| 41 | public RecordWriter<K, V> |
---|
| 42 | getRecordWriter(TaskAttemptContext context |
---|
| 43 | ) throws IOException, InterruptedException { |
---|
| 44 | Configuration conf = context.getConfiguration(); |
---|
| 45 | |
---|
| 46 | CompressionCodec codec = null; |
---|
| 47 | CompressionType compressionType = CompressionType.NONE; |
---|
| 48 | if (getCompressOutput(context)) { |
---|
| 49 | // find the kind of compression to do |
---|
| 50 | compressionType = getOutputCompressionType(context); |
---|
| 51 | |
---|
| 52 | // find the right codec |
---|
| 53 | Class<?> codecClass = getOutputCompressorClass(context, |
---|
| 54 | DefaultCodec.class); |
---|
| 55 | codec = (CompressionCodec) |
---|
| 56 | ReflectionUtils.newInstance(codecClass, conf); |
---|
| 57 | } |
---|
| 58 | // get the path of the temporary output file |
---|
| 59 | Path file = getDefaultWorkFile(context, ""); |
---|
| 60 | FileSystem fs = file.getFileSystem(conf); |
---|
| 61 | final SequenceFile.Writer out = |
---|
| 62 | SequenceFile.createWriter(fs, conf, file, |
---|
| 63 | context.getOutputKeyClass(), |
---|
| 64 | context.getOutputValueClass(), |
---|
| 65 | compressionType, |
---|
| 66 | codec, |
---|
| 67 | context); |
---|
| 68 | |
---|
| 69 | return new RecordWriter<K, V>() { |
---|
| 70 | |
---|
| 71 | public void write(K key, V value) |
---|
| 72 | throws IOException { |
---|
| 73 | |
---|
| 74 | out.append(key, value); |
---|
| 75 | } |
---|
| 76 | |
---|
| 77 | public void close(TaskAttemptContext context) throws IOException { |
---|
| 78 | out.close(); |
---|
| 79 | } |
---|
| 80 | }; |
---|
| 81 | } |
---|
| 82 | |
---|
| 83 | /** |
---|
| 84 | * Get the {@link CompressionType} for the output {@link SequenceFile}. |
---|
| 85 | * @param job the {@link Job} |
---|
| 86 | * @return the {@link CompressionType} for the output {@link SequenceFile}, |
---|
| 87 | * defaulting to {@link CompressionType#RECORD} |
---|
| 88 | */ |
---|
| 89 | public static CompressionType getOutputCompressionType(JobContext job) { |
---|
| 90 | String val = job.getConfiguration().get("mapred.output.compression.type", |
---|
| 91 | CompressionType.RECORD.toString()); |
---|
| 92 | return CompressionType.valueOf(val); |
---|
| 93 | } |
---|
| 94 | |
---|
| 95 | /** |
---|
| 96 | * Set the {@link CompressionType} for the output {@link SequenceFile}. |
---|
| 97 | * @param job the {@link Job} to modify |
---|
| 98 | * @param style the {@link CompressionType} for the output |
---|
| 99 | * {@link SequenceFile} |
---|
| 100 | */ |
---|
| 101 | public static void setOutputCompressionType(Job job, |
---|
| 102 | CompressionType style) { |
---|
| 103 | setCompressOutput(job, true); |
---|
| 104 | job.getConfiguration().set("mapred.output.compression.type", |
---|
| 105 | style.toString()); |
---|
| 106 | } |
---|
| 107 | |
---|
| 108 | } |
---|
| 109 | |
---|