import org.apache.hadoop.io.Text;
import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.ContextFactory;
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.mapreduce.lib.output.MapFileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.MultipleOutputs;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
import org.apache.hadoop.util.Progressable;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import net.sourceforge.pinyin4j.PinyinHelper;
import net.sourceforge.pinyin4j.format.HanyuPinyinCaseType;
import net.sourceforge.pinyin4j.format.HanyuPinyinOutputFormat;
import net.sourceforge.pinyin4j.format.HanyuPinyinToneType;
import net.sourceforge.pinyin4j.format.HanyuPinyinVCharType;
import net.sourceforge.pinyin4j.format.exception.BadHanyuPinyinOutputFormatCombination;
public class MultiFileOut extends Configured implements Tool {
private final static String[] Shengarry = { "北京", "天津", "山西", "内蒙古", "辽宁",
"吉林", "黑龙江", "上海", "江苏", "浙江", "安徽", "福建", "江西", "山东", "河南", "湖北",
"湖南", "广东", "广西", "海南", "重庆", "四川", "贵州", "云南", "西藏", "陕西省", "甘肃",
"青海", "宁夏", "新疆", "河北" };
private final static String[] sexary = { "M", "F" };
public static String getPinYin(String src) {
char[] srcary = null;
srcary = src.toCharArray();
String[] strtmp = new String[srcary.length];
// 设置汉字拼音输出的格式
HanyuPinyinOutputFormat formatstr = new HanyuPinyinOutputFormat();
formatstr.setCaseType(HanyuPinyinCaseType.LOWERCASE);
formatstr.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
formatstr.setVCharType(HanyuPinyinVCharType.WITH_V);
String resultstr = "";
int t0 = srcary.length;
try {
for (int i = 0; i < t0; i++) {
// 判断能否为汉字字符
if (Character.toString(srcary[i]).matches("[\\u4E00-\\u9FA5]+")) {
strtmp = PinyinHelper.toHanyuPinyinStringArray(srcary[i],
formatstr);// 将汉字的几种全拼都存到t2数组中
resultstr += strtmp[0];// +" ";// 取出该汉字全拼的第一种读音并连接到字符串t4后
} else {
// 如果不是汉字字符，间接取出字符并连接到字符串t4后
resultstr += Character.toString(srcary[i]);
}
}
} catch (BadHanyuPinyinOutputFormatCombination e) {
e.printStackTrace();
}
return resultstr;
}
private static class ProvinceMapper extends
Mapper<Object, Text, Text, Text> {
@Override
protected void map(Object key, Text value, Context context)
throws IOException, InterruptedException {
String str = value.toString();
String outkey = "";
Boolean isfind = false;
if (str.indexOf("name") >= 0)
return;
String[] strArray = str.split(",");
if (strArray.length != 33)
return;
String sex = strArray[5];
String addr = strArray[7];
for (int i = 0; i < Shengarry.length; i++) {
for (int j = 0; j < sexary.length; j++) {
int index = addr.indexOf(Shengarry[i]);
if ((index >= 0) && (index <= 3)
&& (sex.indexOf(sexary[j]) >= 0)) {
isfind = true;
outkey = getPinYin(Shengarry[i]) + sexary[j];
break;
}
}
if (isfind)
break;
}
if (isfind) {
context.write(new Text(outkey), value);
} else {
System.out.println("Error Data" + value.toString());
}
}
}
private static class ProvinceReducer extends
Reducer<Text, Text, NullWritable, Text> {
private MultipleOutputs mos = null;
@Override
protected void setup(Context context) throws IOException,
InterruptedException {
mos = new MultipleOutputs(context);
}
@Override
protected void cleanup(Context context) throws IOException,
InterruptedException {
mos.close();
}
@Override
protected void reduce(Text key, Iterable<Text> values, Context context)
throws IOException, InterruptedException {
Text value = new Text("");
String valuetmp = "";
for (Text va : values) {
value.set(va.toString());
try {
mos.write(key.toString(), NullWritable.get(), value);
} catch (Exception e) {
//System.out.println("Exception" + key);
}
}
}
}
public static void main(String[] args) throws Exception {
ToolRunner.run(new Configuration(), new MultiFileOut(), args);
}
@Override
public int run(String[] args) throws Exception {
int result = 0;
Configuration conf = new Configuration();
String[] argArray = new GenericOptionsParser(conf, args)
.getRemainingArgs();
if (argArray.length != 2) {
System.err.println("Usage: MultiFileOut <in> <out>");
System.exit(1);
}
Job job = new Job(conf, "MultiFileOut");
job.setJarByClass(MultiFileOut.class);
job.setMapperClass(ProvinceMapper.class);
job.setReducerClass(ProvinceReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setOutputKeyClass(NullWritable.class);
job.setOutputValueClass(Text.class);
// job.setOutputFormatClass(WordCountOutputFormat.class);
FileInputFormat.addInputPath(job, new Path(argArray[0]));
FileOutputFormat.setOutputPath(job, new Path(argArray[1]));
for (int i = 0; i < Shengarry.length; i++) {
for (int j = 0; j < sexary.length; j++) {
MultipleOutputs.addNamedOutput(job, getPinYin(Shengarry[i])
+ sexary[j], TextOutputFormat.class, Text.class,
Text.class);
}
}
try {
result = job.waitForCompletion(true) ? 0 : 1;
} catch (ClassNotFoundException | InterruptedException e) {
e.printStackTrace();
}
return result;
}
}
原文地址：http://www.cnblogs.com/chengxin1982/p/3832902.html
