Java tutorial
/* * 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 fire.util.fileformats.tika; import java.io.IOException; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; public class TikaDriver { public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(); @SuppressWarnings("deprecation") Job job = new Job(conf, "TikaParser"); job.setJarByClass(TikaDriver.class); job.setJobName("TikaDriver"); job.setInputFormatClass(TikaFileInputFormat.class); FileInputFormat.addInputPath(job, new Path(args[0])); job.setMapperClass(TikaMapper.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setNumReduceTasks(0); // job.setOutputFormatClass(TikaOutPutFormt.class); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.waitForCompletion(true); } }