1.模拟数据：
[hadoop@h71 q1]$ vi file1.txt
mapreduce is simple
[hadoop@h71 q1]$ vi file2.txt
mapreduce is powerful is simple
[hadoop@h71 q1]$ vi file3.txt
hello mapreduce bye mapreduce
补充：
(1)这里存在两个问题：第一，<key,value>对只能有两个值，在不使用Hadoop自定义数据类型的情况下，需要根据情况将其中两个值合并成一个值，作为key或value值；第二，通过一个Reduce过程无法同时完成词频统计和生成文档列表，所以必须增加一个Combine过程完成词频统计。
(2)这里讲单词和URL组成key值（如"MapReduce：file1.txt"），将词频作为value，这样做的好处是可以利用MapReduce框架自带的Map端排序，将同一文档的相同单词的词频组成列表，传递给Combine过程，实现类似于WordCount的功能。
(3)Combine过程：经过map方法处理后，Combine过程将key值相同的value值累加，得到一个单词在文档在文档中的词频，如果直接输出作为Reduce过程的输入，在Shuffle过程时将面临一个问题：所有具有相同单词的记录（由单词、URL和词频组成）应该交由同一个Reducer处理，但当前的key值无法保证这一点，所以必须修改key值和value值。这次将单词作为key值，URL和词频组成value值（如"file1.txt：1"）。这样做的好处是可以利用MapReduce框架默认的HashPartitioner类完成Shuffle过程，将相同单词的所有记录发送给同一个Reducer进行处理。
2.将数据上传到hdfs上：
[hadoop@h71 q1]$ hadoop fs -mkdir /user/hadoop/index_in
[hadoop@h71 q1]$ hadoop fs -put file1.txt /user/hadoop/index_in
[hadoop@h71 q1]$ hadoop fs -put file2.txt /user/hadoop/index_in
[hadoop@h71 q1]$ hadoop fs -put file3.txt /user/hadoop/index_in
3.[hadoop@h71 q1]$ vi InvertedIndex.java
import java.io.IOException;
import java.util.StringTokenizer;
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.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 InvertedIndex {
public static class Map extends Mapper<Object, Text, Text, Text> {
private Text keyInfo = new Text(); // 存储单词和URL组合
private Text valueInfo = new Text(); // 存储词频
private FileSplit split; // 存储Split对象
// 实现map函数
public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
// 获得<key,value>对所属的FileSplit对象
split = (FileSplit) context.getInputSplit();
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
// key值由单词和URL组成，如"MapReduce：file1.txt"
// 获取文件的完整路径
// keyInfo.set(itr.nextToken()+":"+split.getPath().toString());
// 这里为了好看，只获取文件的名称。
int splitIndex = split.getPath().toString().indexOf("file");
keyInfo.set(itr.nextToken() + ":" + split.getPath().toString().substring(splitIndex));
// 词频初始化为1
valueInfo.set("1");
context.write(keyInfo, valueInfo);
}
}
}
public static class Combine extends Reducer<Text, Text, Text, Text> {
private Text info = new Text();
// 实现reduce函数
public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
// 统计词频
int sum = 0;
for (Text value : values) {
sum += Integer.parseInt(value.toString());
}
int splitIndex = key.toString().indexOf(":");
// 重新设置value值由URL和词频组成
info.set(key.toString().substring(splitIndex + 1) + ":" + sum);
// 重新设置key值为单词
key.set(key.toString().substring(0, splitIndex));
context.write(key, info);
}
}
public static class Reduce extends Reducer<Text, Text, Text, Text> {
private Text result = new Text();
// 实现reduce函数
public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
// 生成文档列表
String fileList = new String();
for (Text value : values) {
fileList += value.toString() + ";";
}
result.set(fileList);
context.write(key, result);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
conf.set("mapred.jar", "ii.jar");
String[] ioArgs = new String[] { "index_in", "index_out" };
String[] otherArgs = new GenericOptionsParser(conf, ioArgs).getRemainingArgs();
if (otherArgs.length != 2) {
System.err.println("Usage: Inverted Index <in> <out>");
System.exit(2);
}
Job job = new Job(conf, "Inverted Index");
job.setJarByClass(InvertedIndex.class);
// 设置Map、Combine和Reduce处理类
job.setMapperClass(Map.class);
job.setCombinerClass(Combine.class);
job.setReducerClass(Reduce.class);
// 设置Map输出类型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
// 设置Reduce输出类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
// 设置输入和输出目录
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
4.知识点延伸：
(1)int indexOf(String str) ：返回第一次出现的指定子字符串在此字符串中的索引。
(2)int indexOf(String str, int startIndex)：从指定的索引处开始，返回第一次出现的指定子字符串在此字符串中的索引。
(3)int lastIndexOf(String str) ：返回在此字符串中最右边出现的指定子字符串的索引。
(4)int lastIndexOf(String str, int startIndex) ：从指定的索引处开始向后搜索，返回在此字符串中最后一次出现的指定子字符串的索引。
(5)indexOf("a")是从字符串的0个位置开始查找的。比如你的字符串："abca"，那么程序将会输出0，之后的a是不判断的。
(6)str＝str.substring(int beginIndex);截取掉str从首字母起长度为beginIndex的字符串，将剩余字符串赋值给str
(7)str＝str.substring(int beginIndex，int endIndex);截取str中从beginIndex开始至endIndex结束时的字符串，并将其赋值给str
5.执行：
[hadoop@h71 q1]$ /usr/jdk1.7.0_25/bin/javac InvertedIndex.java
[hadoop@h71 q1]$ /usr/jdk1.7.0_25/bin/jar cvf xx.jar InvertedIndex*class
[hadoop@h71 q1]$ hadoop jar xx.jar InvertedIndex
6.查看结果：
[hadoop@h71 q1]$ hadoop fs -cat /user/hadoop/index_out/part-r-00000
bye file3.txt:1;
hello file3.txt:1;
is file1.txt:1;file2.txt:2;
mapreduce file2.txt:1;file3.txt:2;file1.txt:1;
powerful file2.txt:1;
simple file2.txt:1;file1.txt:1;
号外：有一网友给我发私信说遇到了个问题，让我帮一下他
题目：将数据源文件上传到HDFS系统进行存储，然后基于MapReduce编程进行数据分析，测试数据来源于美国专利文献数据
数据源：
5855015,1998,14242,1995,"US","CA",715526,2,38,707,2,22,5,4,1,0.5,0.32,2,3.8,0,0,0,0
5855016,1998,14242,1995,"US","CA",147695,2,2,707,2,22,8,0,1,,0.5938,,12.375,0,0,,
5855018,1998,14242,1996,"IL","",636865,3,18,707,2,22,5,0,1,,0.72,,2.6,0,0,,
5855019,1998,14242,1997,"US","CA",280070,2,18,707,2,22,7,0,1,,0,,5.4286,0.1429,0.1429,,
5855020,1998,14242,1996,"US","CA",732759,2,10,707,2,22,5,1,1,0,0.48,1,0.4,0.25,0.2,0,0
5855021,1999,14249,1996,"US","MI",,1,,2,6,63,9,0,0.5556,,0,,40.5556,,,,
5855022,1999,14249,1998,"US","IL",,1,,2,6,63,9,0,0.8889,,0.375,,18.8889,,,,
5855023,1999,14249,1996,"US","PA",,1,,2,6,63,13,0,0.1538,,0,,63.6154,,,,
5855024,1999,14249,1997,"US","NJ",749658,2,,4,6,65,2,0,0,,,,94.5,0,0,,
5855025,1999,14249,1997,"US","CA",,1,,4,6,65,9,0,0.8889,,0.2188,,18.4444,,,,
5855026,1999,14249,1997,"US","KS",,1,,2,6,63,5,0,0.4,,0,,30.6,,,,
5855027,1999,14249,1998,"GB","",,1,,4,6,65,10,0,0.4,,0.625,,33,,,,
解答代码：
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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class InvertedIndex {
public static class Map extends Mapper<Object, Text, Text, Text> {
private final static Text one = new Text("1");
private Text word = new Text();
public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
String line[] = value.toString().split(",");
word.set(line[4].substring(1, line[4].length()-1)+":"+line[1]);
context.write(word, one);
}
}
public static class Combine extends Reducer<Text, Text, Text, Text> {
private Text info = new Text();
// 实现reduce函数
public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
// 统计词频
int sum = 0;
for (Text value : values) {
sum += Integer.parseInt(value.toString());
}
int splitIndex = key.toString().indexOf(":");
// 重新设置value值由URL和词频组成
info.set("<"+key.toString().substring(splitIndex + 1) + ":" + sum+">");
// 重新设置key值为单词
key.set(key.toString().substring(0, splitIndex));
context.write(key, info);
}
}
public static class Reduce extends Reducer<Text, Text, Text, Text> {
private Text result = new Text();
// 实现reduce函数
public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
// 生成文档列表
String fileList = new String();
for (Text value : values) {
fileList += value.toString() + ",";
}
result.set(fileList.substring(0,fileList.length()-1));
context.write(key, result);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
conf.set("mapred.jar", "ii.jar");
String[] ioArgs = new String[] { "index_in", "index_out" };
String[] otherArgs = new GenericOptionsParser(conf, ioArgs).getRemainingArgs();
if (otherArgs.length != 2) {
System.err.println("Usage: Inverted Index <in> <out>");
System.exit(2);
}
Job job = new Job(conf, "Inverted Index");
job.setJarByClass(InvertedIndex.class);
// 设置Map、Combine和Reduce处理类
job.setMapperClass(Map.class);
job.setCombinerClass(Combine.class);
job.setReducerClass(Reduce.class);
// 设置Map输出类型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
// 设置Reduce输出类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
// 设置输入和输出目录
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
运行结果：[hadoop@h40 hui]$ hadoop fs -cat /user/hadoop/index_out/part-r-00000
GB <1999:1>
IL <1998:1>
US <1998:4>,<1999:6>
