| 1 | {{{ |
| 2 | public void map(LongWritable key, Text value, |
| 3 | OutputCollector<Text, IntWritable> output, Reporter reporter) |
| 4 | throws IOException { |
| 5 | String line = (caseSensitive) ? value.toString() : value.toString() |
| 6 | .toLowerCase(); |
| 7 | |
| 8 | for (String pattern : patternsToSkip) { |
| 9 | line = line.replaceAll(pattern, ""); |
| 10 | } |
| 11 | |
| 12 | StringTokenizer tokenizer = new StringTokenizer(line); |
| 13 | while (tokenizer.hasMoreTokens()) { |
| 14 | word.set(tokenizer.nextToken()); |
| 15 | output.collect(word, one); |
| 16 | reporter.incrCounter(Counters.INPUT_WORDS, 1); |
| 17 | } |
| 18 | |
| 19 | if ((++numRecords % 100) == 0) { |
| 20 | reporter.setStatus("Finished processing " + numRecords |
| 21 | + " records " + "from the input file: " + inputFile); |
| 22 | } |
| 23 | } |
| 24 | } |
| 25 | |
| 26 | public static class Reduce extends MapReduceBase implements |
| 27 | Reducer<Text, IntWritable, Text, IntWritable> { |
| 28 | public void reduce(Text key, Iterator<IntWritable> values, |
| 29 | OutputCollector<Text, IntWritable> output, Reporter reporter) |
| 30 | throws IOException { |
| 31 | int sum = 0; |
| 32 | while (values.hasNext()) { |
| 33 | sum += values.next().get(); |
| 34 | } |
| 35 | output.collect(key, new IntWritable(sum)); |
| 36 | } |
| 37 | } |
| 38 | }}} |