【发布时间】:2018-04-02 00:34:13
【问题描述】:
我不是 Java 专家,但我了解 Java 的基础知识,并且我总是尝试深入了解 Java 代码,无论何时遇到它。
这可能是一个非常愚蠢的疑问,但我很想在我心中清楚地理解它。
我在 Java 社区发帖,因为我的怀疑只是关于 Java。
自从最近几个月我开始使用 hadoop 以来,我发现 hadoop 使用自己的类型,这些类型围绕 Java 的原始类型进行包装,以便在序列化和反序列化的基础上提高通过网络发送数据的效率。
我的困惑从这里开始,假设我们在 HDFS 中有一些数据要使用在 hadoop 代码中运行的以下 Java 代码进行处理
org.apache.hadoop.io.IntWritable;
org.apache.hadoop.io.LongWritable;
org.apache.hadoop.io.Text;
org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
public class WordCountMapper
{
extends Mapper<LongWritable,Text,Text,IntWritable>
@Override
public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException{
}
}
String line = value.toString();
for (String word : line.split(" ")){
if(word.length()>0){
context.write(new Text(word),new IntWritable(1));
}
在这段代码中,hadoop 的类型有 LongWritable、Text、IntWritable。
让我们选择包裹在 Java 的 String 类型周围的 Text 类型(如果我错了,请纠正我)。
我的疑问是,当我们在上面的代码中将这些参数传递给我们的方法映射时,这些参数如何与import package i.e org.apache.hadoop.io.Text;中的代码交互
下面是Text类代码
package org.apache.hadoop.io;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import java.nio.ByteBuffer;
import java.nio.CharBuffer;
import java.nio.charset.CharacterCodingException;
import java.nio.charset.Charset;
import java.nio.charset.CharsetDecoder;
import java.nio.charset.CharsetEncoder;
import java.nio.charset.CodingErrorAction;
import java.nio.charset.MalformedInputException;
import java.text.CharacterIterator;
import java.text.StringCharacterIterator;
import java.util.Arrays;
import org.apache.avro.reflect.Stringable;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.classification.InterfaceAudience.Public;
import org.apache.hadoop.classification.InterfaceStability.Stable;
@Stringable
@InterfaceAudience.Public
@InterfaceStability.Stable
public class Text
extends BinaryComparable
implements WritableComparable<BinaryComparable>
{
private static final Log LOG = LogFactory.getLog(Text.class);
private static ThreadLocal<CharsetEncoder> ENCODER_FACTORY = new ThreadLocal()
{
protected CharsetEncoder initialValue() {
return Charset.forName("UTF-8").newEncoder().onMalformedInput(CodingErrorAction.REPORT).onUnmappableCharacter(CodingErrorAction.REPORT);
}
};
private static ThreadLocal<CharsetDecoder> DECODER_FACTORY = new ThreadLocal()
{
protected CharsetDecoder initialValue() {
return Charset.forName("UTF-8").newDecoder().onMalformedInput(CodingErrorAction.REPORT).onUnmappableCharacter(CodingErrorAction.REPORT);
}
};
private static final byte[] EMPTY_BYTES = new byte[0];
private byte[] bytes;
private int length;
public Text()
{
bytes = EMPTY_BYTES;
}
public Text(String string)
{
set(string);
}
public Text(Text utf8)
{
set(utf8);
}
public Text(byte[] utf8)
{
set(utf8);
}
public byte[] getBytes()
{
return bytes;
}
public int getLength()
{
return length;
}
public int charAt(int position)
{
if (position > length) return -1;
if (position < 0) { return -1;
}
ByteBuffer bb = (ByteBuffer)ByteBuffer.wrap(bytes).position(position);
return bytesToCodePoint(bb.slice());
}
public int find(String what) {
return find(what, 0);
}
public int find(String what, int start)
{
try
{
ByteBuffer src = ByteBuffer.wrap(bytes, 0, length);
ByteBuffer tgt = encode(what);
byte b = tgt.get();
src.position(start);
while (src.hasRemaining()) {
if (b == src.get()) {
src.mark();
tgt.mark();
boolean found = true;
int pos = src.position() - 1;
while (tgt.hasRemaining()) {
if (!src.hasRemaining()) {
tgt.reset();
src.reset();
found = false;
}
else if (tgt.get() != src.get()) {
tgt.reset();
src.reset();
found = false;
}
}
if (found) return pos;
}
}
return -1;
}
catch (CharacterCodingException e) {
e.printStackTrace(); }
return -1;
}
public void set(String string)
{
try
{
ByteBuffer bb = encode(string, true);
bytes = bb.array();
length = bb.limit();
} catch (CharacterCodingException e) {
throw new RuntimeException("Should not have happened " + e.toString());
}
}
public void set(byte[] utf8)
{
set(utf8, 0, utf8.length);
}
public void set(Text other)
{
set(other.getBytes(), 0, other.getLength());
}
public void set(byte[] utf8, int start, int len)
{
setCapacity(len, false);
System.arraycopy(utf8, start, bytes, 0, len);
length = len;
}
public void append(byte[] utf8, int start, int len)
{
setCapacity(length + len, true);
System.arraycopy(utf8, start, bytes, length, len);
length += len;
}
public void clear()
{
length = 0;
}
private void setCapacity(int len, boolean keepData)
{
if ((bytes == null) || (bytes.length < len)) {
if ((bytes != null) && (keepData)) {
bytes = Arrays.copyOf(bytes, Math.max(len, length << 1));
} else {
bytes = new byte[len];
}
}
}
public String toString()
{
try
{
return decode(bytes, 0, length);
} catch (CharacterCodingException e) {
throw new RuntimeException("Should not have happened " + e.toString());
}
}
public void readFields(DataInput in)
throws IOException
{
int newLength = WritableUtils.readVInt(in);
setCapacity(newLength, false);
in.readFully(bytes, 0, newLength);
length = newLength;
}
public static void skip(DataInput in) throws IOException
{
int length = WritableUtils.readVInt(in);
WritableUtils.skipFully(in, length);
}
public void write(DataOutput out)
throws IOException
{
WritableUtils.writeVInt(out, length);
out.write(bytes, 0, length);
}
public boolean equals(Object o)
{
if ((o instanceof Text))
return super.equals(o);
return false;
}
请问,当我们运行上述 hadoop 的代码时,HDFS 中的数据会流经我们在 map 方法中提到的参数。
一旦来自 HDFS 的第一个数据集达到 Text 参数,它如何在 org.apache.hadoop.io.Text 类中流动?
我的意思是它从哪里开始(我假设它从类中的 set 方法开始,因为它具有与提到的 map 方法相同的参数,对吗?)
代码中从普通字符串类型变为Text类型在哪里?
我的第二个疑问是:当数据以 Text 类型存储时,谁来开始进行序列化?我的意思是,一旦数据到达网络上的目的地,谁调用这个 write(DataOutput out),谁调用 readFields(DataInput in)?
它是如何工作的,我需要在哪里查看?
我希望我问的很清楚。
【问题讨论】:
标签: java hadoop serialization mapreduce deserialization