hadoop涉及輸出文本的默認輸出編碼統一用沒有BOM的UTF-8的形式,但是對於中文的輸出window系統默認的是GBK,有些格式文件例如CSV格式的文件用excel打開輸出編碼爲沒有BOM的UTF-8文件時,輸出的結果爲亂碼,只能由UE或者記事本打開才能正常顯示。因此將hadoop默認輸出編碼更改爲GBK成爲非常常見的需求。
自定義 TextOutputFormat.class 子類
TextOutputFormat.class 類代碼展示:
package main.java.util;
import java.io.DataOutputStream;
import java.io.IOException;
import java.io.UnsupportedEncodingException;
import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.hadoop.mapreduce.RecordWriter;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.ReflectionUtils;
/**
*
* <p>Title:hadoop MapReduce 輸出結果中文亂碼解決</p>
* <p> 功能描述:: </p>
* <p>Company: adteach </p>
* @version 1.0
*/
@InterfaceAudience.Public
@InterfaceStability.Stable
public class TextOutputFormat<K, V> extends FileOutputFormat<K, V> {
public static String SEPERATOR = "mapreduce.output.textoutputformat.separator";
protected static class LineRecordWriter<K, V>
extends RecordWriter<K, V> {
private static final String utf8 = "UTF-8"; // 將UTF-8轉換成GBK
private static final byte[] newline;
static {
try {
newline = "\n".getBytes(utf8);
} catch (UnsupportedEncodingException uee) {
throw new IllegalArgumentException("can't find " + utf8 + " encoding");
}
}
protected DataOutputStream out;
private final byte[] keyValueSeparator;
public LineRecordWriter(DataOutputStream out, String keyValueSeparator) {
this.out = out;
try {
this.keyValueSeparator = keyValueSeparator.getBytes(utf8);
} catch (UnsupportedEncodingException uee) {
throw new IllegalArgumentException("can't find " + utf8 + " encoding");
}
}
public LineRecordWriter(DataOutputStream out) {
this(out, "\t");
}
/**
* Write the object to the byte stream, handling Text as a special
* case.
* @param o the object to print
* @throws IOException if the write throws, we pass it on
*/
private void writeObject(Object o) throws IOException {
if (o instanceof Text) {
Text to = (Text) o; // 將此行代碼註釋掉
out.write(to.getBytes(), 0, to.getLength()); // 將此行代碼註釋掉
} else { // 將此行代碼註釋掉
out.write(o.toString().getBytes(utf8));
}
}
public synchronized void write(K key, V value)
throws IOException {
boolean nullKey = key == null || key instanceof NullWritable;
boolean nullValue = value == null || value instanceof NullWritable;
if (nullKey && nullValue) {
return;
}
if (!nullKey) {
writeObject(key);
}
if (!(nullKey || nullValue)) {
out.write(keyValueSeparator);
}
if (!nullValue) {
writeObject(value);
}
out.write(newline);
}
public synchronized
void close(TaskAttemptContext context) throws IOException {
out.close();
}
}
public RecordWriter<K, V>
getRecordWriter(TaskAttemptContext job
) throws IOException, InterruptedException {
Configuration conf = job.getConfiguration();
boolean isCompressed = getCompressOutput(job);
String keyValueSeparator= conf.get(SEPERATOR, "\t");
CompressionCodec codec = null;
String extension = "";
if (isCompressed) {
Class<? extends CompressionCodec> codecClass =
getOutputCompressorClass(job, GzipCodec.class);
codec = (CompressionCodec) ReflectionUtils.newInstance(codecClass, conf);
extension = codec.getDefaultExtension();
}
Path file = getDefaultWorkFile(job, extension);
FileSystem fs = file.getFileSystem(conf);
if (!isCompressed) {
FSDataOutputStream fileOut = fs.create(file, false);
return new LineRecordWriter<K, V>(fileOut, keyValueSeparator);
} else {
FSDataOutputStream fileOut = fs.create(file, false);
return new LineRecordWriter<K, V>(new DataOutputStream
(codec.createOutputStream(fileOut)),
keyValueSeparator);
}
}
}
默認的情況下MR主程序中,設定輸出編碼的設置語句爲:
job.setOutputFormatClass(TextOutputFormat.class);
但是注意:
上述代碼的第48行可以看出hadoop已經限定此輸出格式統一爲UTF-8,因此爲了改變hadoop的輸出代碼的文本編碼只需定義一個和TextOutputFormat相同的類GbkOutputFormat同樣繼承FileOutputFormat
(注意是
org.apache.hadoop.mapreduce.lib.output.FileOutputFormat)
即可,如下代碼
package main.java.util;
import java.io.DataOutputStream;
import java.io.IOException;
import java.io.UnsupportedEncodingException;
import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.hadoop.mapreduce.RecordWriter;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.ReflectionUtils;
/**
*
* <p>
* Title: GbkOutputFormat
* </p>
* <p>
* 功能描述::
* hadoop已經限定此輸出格式統一爲UTF-8,因此爲了改變hadoop的輸出代碼的文本編碼只需定義一個和TextOutputFormat相同的類GbkOutputFormat同樣繼承FileOutputFormat
* (注意是 org.apache.hadoop.mapreduce.lib.output.FileOutputFormat)
* </p>
* <p>
* Company: adteach
* </p>
* @version 1.0
*/
@InterfaceAudience.Public
@InterfaceStability.Stable
public class GbkOutputFormat<K, V> extends FileOutputFormat<K, V> {
public static String SEPERATOR = "mapreduce.output.textoutputformat.separator";
protected static class LineRecordWriter<K, V>
extends RecordWriter<K, V> {
private static final String utf8 = "GBK";
private static final byte[] newline;
static {
try {
newline = "\n".getBytes(utf8);
} catch (UnsupportedEncodingException uee) {
throw new IllegalArgumentException("can't find " + utf8 + " encoding");
}
}
protected DataOutputStream out;
private final byte[] keyValueSeparator;
public LineRecordWriter(DataOutputStream out, String keyValueSeparator) {
this.out = out;
try {
this.keyValueSeparator = keyValueSeparator.getBytes(utf8);
} catch (UnsupportedEncodingException uee) {
throw new IllegalArgumentException("can't find " + utf8 + " encoding");
}
}
public LineRecordWriter(DataOutputStream out) {
this(out, "\t");
}
/**
* Write the object to the byte stream, handling Text as a special
* case.
* @param o the object to print
* @throws IOException if the write throws, we pass it on
*/
private void writeObject(Object o) throws IOException {
if (o instanceof Text) {
// Text to = (Text) o;
// out.write(to.getBytes(), 0, to.getLength());
// } else {
out.write(o.toString().getBytes(utf8));
}
}
public synchronized void write(K key, V value)
throws IOException {
boolean nullKey = key == null || key instanceof NullWritable;
boolean nullValue = value == null || value instanceof NullWritable;
if (nullKey && nullValue) {
return;
}
if (!nullKey) {
writeObject(key);
}
if (!(nullKey || nullValue)) {
out.write(keyValueSeparator);
}
if (!nullValue) {
writeObject(value);
}
out.write(newline);
}
public synchronized
void close(TaskAttemptContext context) throws IOException {
out.close();
}
}
public RecordWriter<K, V>
getRecordWriter(TaskAttemptContext job
) throws IOException, InterruptedException {
Configuration conf = job.getConfiguration();
boolean isCompressed = getCompressOutput(job);
String keyValueSeparator= conf.get(SEPERATOR, "\t");
CompressionCodec codec = null;
String extension = "";
if (isCompressed) {
Class<? extends CompressionCodec> codecClass =
getOutputCompressorClass(job, GzipCodec.class);
codec = (CompressionCodec) ReflectionUtils.newInstance(codecClass, conf);
extension = codec.getDefaultExtension();
}
Path file = getDefaultWorkFile(job, extension);
FileSystem fs = file.getFileSystem(conf);
if (!isCompressed) {
FSDataOutputStream fileOut = fs.create(file, false);
return new LineRecordWriter<K, V>(fileOut, keyValueSeparator);
} else {
FSDataOutputStream fileOut = fs.create(file, false);
return new LineRecordWriter<K, V>(new DataOutputStream
(codec.createOutputStream(fileOut)),
keyValueSeparator);
}
}
}
最後將輸出編碼類型設置成GbkOutputFormat.class,如:
job.setOutputFormatClass(GbkOutputFormat.class);
代碼示例:
package main.java.demo;
import main.java.util.GbkOutputFormat;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;
public class DemoLogETL {
//使用LongWritable而不是Long是因爲map讀文件寫文件都要序列化分序列化,map處理完結果寫到磁盤,而reduce讀map的結果需要反序列化,所以使用**Writable
//數據類型使用Writable接口,以便於這些類型定義的數據可以被序列化用於網絡傳輸和文件存儲。
//靜態內部類(靜態內部類只能訪問外部類的靜態成員)
public static class WordCountMapper extends Mapper<LongWritable, Text, LongWritable,Text>{ //前兩個輸入參數 後兩個定義輸出
@Override
protected void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
if(null != value){
// String row = value.toString(); //直接toString()會亂碼
// String row=new String(value.getBytes(),0,value.getLength(),"GBK");//讀取gbk編碼格式的文件input\jsonLog1.txt
String row=new String(value.getBytes(),0,value.getLength(),"utf-8");//讀取UTF-8編碼格式的文件input\jsonLog.txt
String sub = row.substring(20, row.length() - 20);
context.write(key,new Text(sub));
}
}
}
//dirver(將dirver提出來了)
public int run(String[] args) throws Exception {
//1.get configuration
Configuration conf = new Configuration();
// conf.set("mapreduce.framework.name", "local");
//2.create job
Job job = Job.getInstance(conf,this.getClass().getSimpleName());
// run jar
job.setJarByClass(DemoLogETL.class);
//3.set job (input -> map -> reduce -> output)
//3.1 map
job.setMapperClass(WordCountMapper.class);
//設置Map端輸出key類和輸出value類
job.setMapOutputKeyClass(LongWritable.class);
job.setMapOutputValueClass(Text.class);
job.setOutputFormatClass(GbkOutputFormat.class);
//3.3
//input path
FileInputFormat.addInputPath(job,new Path("input\\jsonLog.txt"));
//output path
FileOutputFormat.setOutputPath(job,new Path("DemoLogETL1"));
//submit job 提交任務
boolean isSuccess = job.waitForCompletion(true);//表示打印日誌信息
System.out.println(isSuccess);
return isSuccess ? 0 : 1;
}
// run program 運行整個工程
public static void main(String[] args) throws Exception{
int status = new DemoLogETL().run(args);
// 結束程序
System.exit(status);
}
}
參考:https://blog.csdn.net/u014033218/article/details/75413332