Created
September 29, 2013 18:34
-
-
Save chriswhite199/6755242 to your computer and use it in GitHub Desktop.
Gist for Stack Overflow Q: http://stackoverflow.com/questions/19080287/whats-the-difference-between-mapred-and-mapreduce-packages-in-apache-avro
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/** | |
* 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 csw; | |
import java.io.IOException; | |
import java.util.StringTokenizer; | |
import org.apache.avro.mapred.AvroKey; | |
import org.apache.avro.mapreduce.AvroJob; | |
import org.apache.avro.mapreduce.AvroKeyOutputFormat; | |
import org.apache.hadoop.conf.Configuration; | |
import org.apache.hadoop.conf.Configured; | |
import org.apache.hadoop.fs.Path; | |
import org.apache.hadoop.io.IntWritable; | |
import org.apache.hadoop.io.LongWritable; | |
import org.apache.hadoop.io.NullWritable; | |
import org.apache.hadoop.io.Text; | |
import org.apache.hadoop.mapreduce.Job; | |
import org.apache.hadoop.mapreduce.Mapper; | |
import org.apache.hadoop.mapreduce.Reducer; | |
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; | |
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat; | |
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; | |
import org.apache.hadoop.util.Tool; | |
import org.apache.hadoop.util.ToolRunner; | |
import csw.avro.WordCount; | |
/** | |
* The classic WordCount example modified to output Avro Pair<CharSequence, | |
* Integer> records instead of text | |
* <p> | |
* Adapted from | |
* http://svn.apache.org/viewvc/avro/trunk/doc/examples/mr-example/src | |
* /main/java/example/AvroWordCount.java?view=co and modified to use the new | |
* Hadoop mapreduce API | |
*/ | |
public class AvroWordCountNewAPI extends Configured implements Tool { | |
public static class Map extends | |
Mapper<LongWritable, Text, Text, IntWritable> { | |
private final static IntWritable one = new IntWritable(1); | |
private Text word = new Text(); | |
@Override | |
public void map(LongWritable key, Text value, Context context) | |
throws IOException, InterruptedException { | |
String line = value.toString(); | |
StringTokenizer tokenizer = new StringTokenizer(line); | |
while (tokenizer.hasMoreTokens()) { | |
word.set(tokenizer.nextToken()); | |
context.write(word, one); | |
} | |
} | |
} | |
public static class Reduce extends | |
Reducer<Text, IntWritable, AvroKey<WordCount>, NullWritable> { | |
AvroKey<WordCount> outputKey = new AvroKey<WordCount>(new WordCount()); | |
@Override | |
protected void reduce(Text key, Iterable<IntWritable> values, | |
Context context) throws IOException, InterruptedException { | |
int sum = 0; | |
for (IntWritable value : values) { | |
sum += value.get(); | |
} | |
outputKey.datum().setWord(key.toString()); | |
outputKey.datum().setCount(sum); | |
context.write(outputKey, null); | |
} | |
} | |
public int run(String[] args) throws Exception { | |
if (args.length != 2) { | |
System.err | |
.println("Usage: AvroWordCountNewAPI <input path> <output path>"); | |
return -1; | |
} | |
Job conf = new Job(getConf()); | |
conf.setJobName("wordcount"); | |
conf.setJarByClass(AvroWordCountNewAPI.class); | |
AvroJob.setOutputKeySchema(conf, WordCount.getClassSchema()); | |
conf.setMapperClass(Map.class); | |
conf.setReducerClass(Reduce.class); | |
conf.setInputFormatClass(TextInputFormat.class); | |
conf.setOutputFormatClass(AvroKeyOutputFormat.class); | |
conf.setMapOutputKeyClass(Text.class); | |
conf.setMapOutputValueClass(IntWritable.class); | |
conf.setOutputKeyClass(AvroKey.class); | |
conf.setOutputValueClass(NullWritable.class); | |
FileInputFormat.setInputPaths(conf, new Path(args[0])); | |
FileOutputFormat.setOutputPath(conf, new Path(args[1])); | |
return conf.waitForCompletion(true) ? 0 : 1; | |
} | |
public static void main(String[] args) throws Exception { | |
int res = ToolRunner.run(new Configuration(), | |
new AvroWordCountNewAPI(), args); | |
System.exit(res); | |
} | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{"namespace": "csw.avro", | |
"type": "record", | |
"name": "WordCount", | |
"fields": [ | |
{"name": "word", "type": "string"}, | |
{"name": "count", "type": "int"} | |
] | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment