1 | package ro.pub.cs.pp.pdad; |
---|
2 | |
---|
3 | import java.io.IOException; |
---|
4 | |
---|
5 | import org.apache.hadoop.fs.Path; |
---|
6 | import org.apache.hadoop.conf.Configuration; |
---|
7 | import org.apache.hadoop.io.Text; |
---|
8 | import org.apache.hadoop.io.IntWritable; |
---|
9 | import org.apache.hadoop.mapreduce.Job; |
---|
10 | import org.apache.hadoop.mapreduce.Mapper; |
---|
11 | import org.apache.hadoop.mapreduce.Reducer; |
---|
12 | import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; |
---|
13 | import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; |
---|
14 | |
---|
15 | public class EndReason { |
---|
16 | |
---|
17 | private static int[] domains = {-1, 0, 1, 1000, 2000, 3000, 4000, 5000, 6000, 7000}; |
---|
18 | private static String[] reasonName = {"not reported", "undetermined", "infrastructure", "hardware", "IO", "network", "software", "human error", "user"}; |
---|
19 | |
---|
20 | public static class Map extends Mapper<Object, Text, IntWritable, IntWritable> { |
---|
21 | |
---|
22 | private static String null_reason = "NULL"; |
---|
23 | |
---|
24 | private final static IntWritable one = new IntWritable(1); |
---|
25 | private final static IntWritable zero = new IntWritable(0); |
---|
26 | private final static int fieldNo = 9; |
---|
27 | |
---|
28 | private int findDomainCode(int reasonCode) { |
---|
29 | for (int domainCode = 0; domainCode < domains.length - 1; domainCode++) { |
---|
30 | if (domains[domainCode] <= reasonCode && reasonCode < domains[domainCode + 1]) |
---|
31 | return domainCode; |
---|
32 | } |
---|
33 | return 0; |
---|
34 | } |
---|
35 | |
---|
36 | private int extractReasonDomainCode(String line) { |
---|
37 | String[] pieces = line.split("\\s+"); |
---|
38 | if (pieces.length < fieldNo + 1) { |
---|
39 | return 0; |
---|
40 | } |
---|
41 | String reason = pieces[fieldNo]; |
---|
42 | if (reason.equals(null_reason)) { |
---|
43 | return 0; |
---|
44 | } else { |
---|
45 | int reasonCode = Integer.parseInt(reason); |
---|
46 | return findDomainCode(reasonCode); |
---|
47 | } |
---|
48 | } |
---|
49 | |
---|
50 | public void map(Object key, Text value, Context context) throws IOException, InterruptedException { |
---|
51 | String line = value.toString(); |
---|
52 | try { |
---|
53 | int reasonDomain = extractReasonDomainCode(line); |
---|
54 | context.write(new IntWritable(reasonDomain), one); |
---|
55 | } catch (NumberFormatException ex) { |
---|
56 | context.write(zero, zero); |
---|
57 | } |
---|
58 | |
---|
59 | } |
---|
60 | } |
---|
61 | |
---|
62 | public static class Reduce extends Reducer <IntWritable, IntWritable, Text, IntWritable> { |
---|
63 | |
---|
64 | private Text reasonDomain = new Text(); |
---|
65 | |
---|
66 | public void reduce(IntWritable key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { |
---|
67 | int sum = 0; |
---|
68 | for (IntWritable cnt : values) { |
---|
69 | sum += cnt.get(); |
---|
70 | } |
---|
71 | reasonDomain.set(reasonName[key.get()]); |
---|
72 | context.write(reasonDomain, new IntWritable(sum)); |
---|
73 | } |
---|
74 | } |
---|
75 | |
---|
76 | public static void main(String[] args) throws Exception { |
---|
77 | Configuration conf = new Configuration(); |
---|
78 | Job job = new Job(conf, "EndReason"); |
---|
79 | job.setNumReduceTasks(5); |
---|
80 | job.setJarByClass(EndReason.class); |
---|
81 | |
---|
82 | /* set map output key/value classes */ |
---|
83 | job.setMapOutputKeyClass(IntWritable.class); |
---|
84 | job.setMapOutputValueClass(IntWritable.class); |
---|
85 | |
---|
86 | /* set application output key/value classes */ |
---|
87 | job.setOutputKeyClass(Text.class); |
---|
88 | job.setOutputValueClass(IntWritable.class); |
---|
89 | |
---|
90 | job.setMapperClass(Map.class); |
---|
91 | job.setReducerClass(Reduce.class); |
---|
92 | /* don't set any combiner class */ |
---|
93 | |
---|
94 | FileInputFormat.addInputPath(job, new Path(args[0])); |
---|
95 | FileOutputFormat.setOutputPath(job, new Path(args[1])); |
---|
96 | System.exit(job.waitForCompletion(true) ? 0 : 1); |
---|
97 | } |
---|
98 | |
---|
99 | } |
---|