以下为TextPair类

public class TextPair implements WritableComparable {
?private Text first;
?private Text second;

?public TextPair() {
? set(new Text(), new Text());
?}

?public TextPair(String first, String second) {
? set(new Text(first), new Text(second));
?}

?public TextPair(Text first, Text second) {
? set(first, second);
?}

?public void set(Text first, Text second) {
? this.first = first;
? this.second = second;
?}

?public Text getFirst() {
? return first;
?}

?public Text getSecond() {
? return second;
?}

?@Override
?public void write(DataOutput out) throws IOException {
? first.write(out);
? second.write(out);
?}

?@Override
?public void readFields(DataInput in) throws IOException {
? first.readFields(in);
? second.readFields(in);
?}

?@Override
?public int hashCode() {
? return first.hashCode() * 163 + second.hashCode();
?}

?@Override
?public boolean equals(Object o) {
? if (o instanceof TextPair) {
? ?TextPair tp = (TextPair) o;
? ?return first.equals(tp.first) && second.equals(tp.second);
? }
? return false;
?}

?@Override
?public String toString() {
? return first + "\t" + second;
?}
?
?@Override
?/**A.compareTo(B)
? * 如果比较相同，则比较结果为0
? * 如果A大于B，则比较结果为1
? * 如果A小于B，则比较结果为-1
? *
? */
?public int compareTo(TextPair tp) {
? int cmp = first.compareTo(tp.first);
? if (cmp != 0) {
? ?return cmp;
? }
? //此时实现的是升序排列
? return second.compareTo(tp.second);
?}
}

以下为WholeFileInputFormat，其控制数据在mapreduce过程中不被切分

package web.hadoop;

import java.io.IOException;?

import org.apache.hadoop.fs.Path;?
import org.apache.hadoop.io.BytesWritable;?
import org.apache.hadoop.io.Text;?
import org.apache.hadoop.mapreduce.InputSplit;?
import org.apache.hadoop.mapreduce.JobContext;?
import org.apache.hadoop.mapreduce.RecordReader;?
import org.apache.hadoop.mapreduce.TaskAttemptContext;?
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

public class WholeFileInputFormat extends FileInputFormat {?
?
? ? @Override?
? ? public RecordReader createRecordReader(?
? ? ? ? ? ? InputSplit arg0, TaskAttemptContext arg1) throws IOException,?
? ? ? ? ? ? InterruptedException {?
? ? ? ? // TODO Auto-generated method stub?
? ? ? ? return new WholeFileRecordReader();?
? ? }?
?
? ? @Override?
? ? protected boolean isSplitable(JobContext context, Path filename) {?
? ? ? ? // TODO Auto-generated method stub?
? ? ? ? return false;?
? ? }?
}?

以下为WholeFileRecordReader类

package web.hadoop;

import java.io.IOException;