org.jacky.hadoop.examples.ExtractData.java Source code

Java tutorial

Introduction

Here is the source code for org.jacky.hadoop.examples.ExtractData.java

Source

/**
 * 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 org.jacky.hadoop.examples;

import java.io.IOException;
import java.net.URI;
import java.util.ArrayList;
import java.util.Collection;
import java.util.Collections;
import java.util.HashMap;
import java.util.LinkedList;
import java.util.List;
import java.util.Map;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Counter;
import org.apache.hadoop.mapreduce.InputSplit;
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.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class ExtractData {

    private static final Log log = LogFactory.getLog(ExtractData.class);
    private static Long primaryDataTime = Long.MAX_VALUE;

    private static enum DataStatus {
        Add, Update, Delete;
    }

    // private static final String inputPath =
    // "hdfs://192.168.2.248:9000/usr/input/out";
    // private static final String outPath =
    // "hdfs://192.168.2.248:9000/usr/outPut";
    private static URI uri;
    static {
        uri = URI.create("hdfs://192.168.50.70:9000");
    }

    public static class TokenizerMapper extends Mapper<Object, Text, Text, Text> {
        private Text word = new Text();

        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            InputSplit inputSplit = context.getInputSplit();
            String fileName = ((FileSplit) inputSplit).getPath().getName();
            fileName = fileName.substring(0, fileName.lastIndexOf(".")); //remove file postfix
            String[] params = fileName.split("[_]");
            if (params.length != 3)
                return;

            String tableSignature = params[0];
            String tableName = params[1];
            String dataTime = params[2];

            if (!dataTime.matches("[0-9]+"))
                throw new IllegalArgumentException("123 " + dataTime + " is not digit!");

            if (/*primaryDataTime == 0 || */primaryDataTime > Long.valueOf(dataTime))
                primaryDataTime = Long.valueOf(dataTime);

            Text valueText = new Text();

            valueText.set(value.toString() + "|" + dataTime);

            Text keyText = new Text();
            keyText.set(value.toString().split("[|]")[2]);

            Counter count = context.getCounter("map value: ", value.toString());
            count.increment(1l);

            word.set(tableSignature + "_" + keyText);
            context.write(word, valueText);
        }
    }

    public static class IntSumReducer extends Reducer<Text, Text, Text, Text> {

        public void reduce(Text key, Iterable<Text> values, Context context)
                throws IOException, InterruptedException {
            Map<Long, String> dataMap = new HashMap<Long, String>();
            List<Long> timeList = new LinkedList<Long>();
            for (Text text : values) {
                String[] textTmp = text.toString().split("[|]");
                String dataTime = textTmp[textTmp.length - 1];
                if (!dataTime.matches("[0-9]+"))
                    throw new IllegalArgumentException("321 " + dataTime + " is not digit!");
                timeList.add(Long.valueOf(dataTime));
                dataMap.put(Long.valueOf(dataTime), text.toString().substring(0, text.toString().lastIndexOf("|")));
            }

            List<Long> arrayDataList = new ArrayList<Long>(timeList);
            Collections.sort(arrayDataList);
            String primaryData = dataMap.get(arrayDataList.get(0));
            Long primaryTime = arrayDataList.get(0);

            Text keyText = new Text();
            keyText.set(primaryData);

            if (dataMap.size() == 1) {
                if (primaryTime <= primaryDataTime)
                    context.write(keyText, new Text(DataStatus.Delete.toString()));
                else
                    context.write(keyText, new Text(DataStatus.Add.toString()));
            } else {
                for (int i = 1; i < arrayDataList.size(); i++) {
                    String data = dataMap.get(arrayDataList.get(i));
                    if (!data.trim().equals(primaryData.trim()))
                        context.write(keyText, new Text(DataStatus.Update.toString()));
                }
            }
        }
    }

    /**
     * delete a dir in the hdfs. dir may like /tmp/testdir.
     * 
     * @param dir
     * @throws IOException
     */
    public static void deleteDir(String dir) throws IOException {

        log.info("delete path");

        Configuration conf = new Configuration();
        FileSystem fs = FileSystem.get(uri, conf);
        /*
         * for method delete(Path f, boolean recursive)we need notice:if path
         * is a directory or is a empty directory and set recursive to true, the
         * directory is deleted else throws an exception. In case of a file the
         * recursive can be set to either true or false
         */
        fs.delete(new Path(dir), true);
        fs.close();
    }

    public static void main(String[] args) throws Exception {
        long startTime = System.currentTimeMillis();
        Configuration conf = new Configuration();
        // conf.setQuietMode(false);

        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        if (otherArgs.length != 2) {
            System.err.println("Usage: extract <in> <out>");
            System.exit(2);
        }

        Job job = new Job(conf, "word count");
        job.setJarByClass(ExtractData.class);
        job.setMapperClass(TokenizerMapper.class);
        //job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
        // delete out path first
        deleteDir(otherArgs[1]);
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
        if (job.waitForCompletion(true)) {
            long endTime = System.currentTimeMillis();
            log.info("useTime: " + formatLongToTimeStr((endTime - startTime)));
            log.info("primary time: " + primaryDataTime);
            System.exit(0);
        }
    }

    public static String formatLongToTimeStr(Long useTime) {
        int hour = 0;
        int minute = 0;
        int second = 0;
        second = useTime.intValue() / 1000;
        if (second > 60) {
            minute = second / 60;
            second = second % 60;
        }
        if (minute > 60) {
            hour = minute / 60;
            minute = minute % 60;
        }
        String strtime = hour + "H " + minute + "M " + second + "S";
        return strtime;
    }
}