自定义 hadoop MapReduce InputFormat 切分输入文件
在上一篇中,我们实现了按 cookieId 和 time 进行二次排序,现在又有新问题:假如我需要按 cookieId 和 cookieId&time 的组合进行分析呢?此时最好的办法是自定义 InputFormat,让 mapreduce 一次读取一个 cookieId 下的所有记录,然后再按 time 进行切分 session,逻辑伪码如下:
for OneSplit in MyInputFormat.getSplit() // OneSplit 是某个 cookieId 下的所有记录
for session in OneSplit // session 是按 time 把 OneSplit 进行了二次分割
for line in session // line 是 session 中的每条记录,对应原始日志的某条记录
1、原理:
public interface InputFormat<K, V> {
InputSplit[] getSplits(JobConf job, int numSplits) throws IOException;
RecordReader<K, V> createRecordReader(InputSplit split,
TaskAttemptContext context) throws IOException;
}
K createKey();
V createValue();
long getPos() throws IOException;
public void close() throws IOException;
float getProgress() throws IOException;
}
2、代码:
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
|
package MyInputFormat;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.CompressionCodecFactory;
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 TrackInputFormat extends FileInputFormat<LongWritable, Text> {
@SuppressWarnings ( "deprecation" )
@Override
public RecordReader<LongWritable, Text> createRecordReader(
InputSplit split, TaskAttemptContext context) {
return new TrackRecordReader();
}
@Override
protected boolean isSplitable(JobContext context, Path file) {
CompressionCodec codec = new CompressionCodecFactory(
context.getConfiguration()).getCodec(file);
return codec == null ;
}
} |
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
|
package MyInputFormat;
import java.io.IOException;
import java.io.InputStream;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.CompressionCodecFactory;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
/** * Treats keys as offset in file and value as line.
*
* @deprecated Use
* {@link org.apache.hadoop.mapreduce.lib.input.LineRecordReader}
* instead.
*/
public class TrackRecordReader extends RecordReader<LongWritable, Text> {
private static final Log LOG = LogFactory.getLog(TrackRecordReader. class );
private CompressionCodecFactory compressionCodecs = null ;
private long start;
private long pos;
private long end;
private NewLineReader in;
private int maxLineLength;
private LongWritable key = null ;
private Text value = null ;
// ----------------------
// 行分隔符,即一条记录的分隔符
private byte [] separator = "END\n" .getBytes();
// --------------------
public void initialize(InputSplit genericSplit, TaskAttemptContext context)
throws IOException {
FileSplit split = (FileSplit) genericSplit;
Configuration job = context.getConfiguration();
this .maxLineLength = job.getInt( "mapred.linerecordreader.maxlength" ,
Integer.MAX_VALUE);
start = split.getStart();
end = start + split.getLength();
final Path file = split.getPath();
compressionCodecs = new CompressionCodecFactory(job);
final CompressionCodec codec = compressionCodecs.getCodec(file);
FileSystem fs = file.getFileSystem(job);
FSDataInputStream fileIn = fs.open(split.getPath());
boolean skipFirstLine = false ;
if (codec != null ) {
in = new NewLineReader(codec.createInputStream(fileIn), job);
end = Long.MAX_VALUE;
} else {
if (start != 0 ) {
skipFirstLine = true ;
this .start -= separator.length; //
// --start;
fileIn.seek(start);
}
in = new NewLineReader(fileIn, job);
}
if (skipFirstLine) { // skip first line and re-establish "start".
start += in.readLine( new Text(), 0 ,
( int ) Math.min(( long ) Integer.MAX_VALUE, end - start));
}
this .pos = start;
}
public boolean nextKeyValue() throws IOException {
if (key == null ) {
key = new LongWritable();
}
key.set(pos);
if (value == null ) {
value = new Text();
}
int newSize = 0 ;
while (pos < end) {
newSize = in.readLine(value, maxLineLength,
Math.max(( int ) Math.min(Integer.MAX_VALUE, end - pos),
maxLineLength));
if (newSize == 0 ) {
break ;
}
pos += newSize;
if (newSize < maxLineLength) {
break ;
}
LOG.info( "Skipped line of size " + newSize + " at pos "
+ (pos - newSize));
}
if (newSize == 0 ) {
key = null ;
value = null ;
return false ;
} else {
return true ;
}
}
@Override
public LongWritable getCurrentKey() {
return key;
}
@Override
public Text getCurrentValue() {
return value;
}
/**
* Get the progress within the split
*/
public float getProgress() {
if (start == end) {
return 0 .0f;
} else {
return Math.min( 1 .0f, (pos - start) / ( float ) (end - start));
}
}
public synchronized void close() throws IOException {
if (in != null ) {
in.close();
}
}
public class NewLineReader {
private static final int DEFAULT_BUFFER_SIZE = 64 * 1024 ;
private int bufferSize = DEFAULT_BUFFER_SIZE;
private InputStream in;
private byte [] buffer;
private int bufferLength = 0 ;
private int bufferPosn = 0 ;
public NewLineReader(InputStream in) {
this (in, DEFAULT_BUFFER_SIZE);
}
public NewLineReader(InputStream in, int bufferSize) {
this .in = in;
this .bufferSize = bufferSize;
this .buffer = new byte [ this .bufferSize];
}
public NewLineReader(InputStream in, Configuration conf)
throws IOException {
this (in, conf.getInt( "io.file.buffer.size" , DEFAULT_BUFFER_SIZE));
}
public void close() throws IOException {
in.close();
}
public int readLine(Text str, int maxLineLength, int maxBytesToConsume)
throws IOException {
str.clear();
Text record = new Text();
int txtLength = 0 ;
long bytesConsumed = 0L;
boolean newline = false ;
int sepPosn = 0 ;
do {
// 已经读到buffer的末尾了,读下一个buffer
if ( this .bufferPosn >= this .bufferLength) {
bufferPosn = 0 ;
bufferLength = in.read(buffer);
// 读到文件末尾了,则跳出,进行下一个文件的读取
if (bufferLength <= 0 ) {
break ;
}
}
int startPosn = this .bufferPosn;
for (; bufferPosn < bufferLength; bufferPosn++) {
// 处理上一个buffer的尾巴被切成了两半的分隔符(如果分隔符中重复字符过多在这里会有问题)
if (sepPosn > 0 && buffer[bufferPosn] != separator[sepPosn]) {
sepPosn = 0 ;
}
// 遇到行分隔符的第一个字符
if (buffer[bufferPosn] == separator[sepPosn]) {
bufferPosn++;
int i = 0 ;
// 判断接下来的字符是否也是行分隔符中的字符
for (++sepPosn; sepPosn < separator.length; i++, sepPosn++) {
// buffer的最后刚好是分隔符,且分隔符被不幸地切成了两半
if (bufferPosn + i >= bufferLength) {
bufferPosn += i - 1 ;
break ;
}
// 一旦其中有一个字符不相同,就判定为不是分隔符
if ( this .buffer[ this .bufferPosn + i] != separator[sepPosn]) {
sepPosn = 0 ;
break ;
}
}
// 的确遇到了行分隔符
if (sepPosn == separator.length) {
bufferPosn += i;
newline = true ;
sepPosn = 0 ;
break ;
}
}
}
int readLength = this .bufferPosn - startPosn;
bytesConsumed += readLength;
// 行分隔符不放入块中
if (readLength > maxLineLength - txtLength) {
readLength = maxLineLength - txtLength;
}
if (readLength > 0 ) {
record.append( this .buffer, startPosn, readLength);
txtLength += readLength;
// 去掉记录的分隔符
if (newline) {
str.set(record.getBytes(), 0 , record.getLength()
- separator.length);
}
}
} while (!newline && (bytesConsumed < maxBytesToConsume));
if (bytesConsumed > ( long ) Integer.MAX_VALUE) {
throw new IOException( "Too many bytes before newline: "
+ bytesConsumed);
}
return ( int ) bytesConsumed;
}
public int readLine(Text str, int maxLineLength) throws IOException {
return readLine(str, maxLineLength, Integer.MAX_VALUE);
}
public int readLine(Text str) throws IOException {
return readLine(str, Integer.MAX_VALUE, Integer.MAX_VALUE);
}
}
} |
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
|
package MyInputFormat;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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;
public class TestMyInputFormat {
public static class MapperClass extends Mapper<LongWritable, Text, Text, Text> {
public void map(LongWritable key, Text value, Context context) throws IOException,
InterruptedException {
System.out.println( "key:\t " + key);
System.out.println( "value:\t " + value);
System.out.println( "-------------------------" );
}
}
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
Configuration conf = new Configuration();
Path outPath = new Path( "/hive/11" );
FileSystem.get(conf).delete(outPath, true );
Job job = new Job(conf, "TestMyInputFormat" );
job.setInputFormatClass(TrackInputFormat. class );
job.setJarByClass(TestMyInputFormat. class );
job.setMapperClass(TestMyInputFormat.MapperClass. class );
job.setNumReduceTasks( 0 );
job.setMapOutputKeyClass(Text. class );
job.setMapOutputValueClass(Text. class );
FileInputFormat.addInputPath(job, new Path(args[ 0 ]));
org.apache.hadoop.mapreduce.lib.output.FileOutputFormat.setOutputPath(job, outPath);
System.exit(job.waitForCompletion( true ) ? 0 : 1 );
}
} |
3、测试数据:
cookieId time url cookieOverFlag
1
2
3
4
5
6
7
8
9
|
1 a 1_hao123
1 a 1_baidu
1 b 1_google 2END
2 c 2_google
2 c 2_hao123
2 c 2_google 1END
3 a 3_baidu
3 a 3_sougou
3 b 3_soso 2END
|
4、结果:
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
|
key: 0
value: 1 a 1_hao123
1 a 1_baidu
1 b 1_google 2
------------------------- key: 47
value: 2 c 2_google
2 c 2_hao123
2 c 2_google 1
------------------------- key: 96
value: 3 a 3_baidu
3 a 3_sougou
3 b 3_soso 2
------------------------- |
REF:
自定义hadoop map/reduce输入文件切割InputFormat
http://hi.baidu.com/lzpsky/item/0d9d84c05afb43ba0c0a7b27
MapReduce高级编程之自定义InputFormat
http://datamining.xmu.edu.cn/bbs/home.php?mod=space&uid=91&do=blog&id=190
http://irwenqiang.iteye.com/blog/1448164
http://my.oschina.net/leejun2005/blog/133424