Created
May 29, 2013 22:27
-
-
Save esammer/5674345 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| // The MR contract says we're guaranteed to get: | |
| // 1. each key exactly once. | |
| // 2. keys in sorted order. | |
| // 3. all values for each key. | |
| // | |
| // We are not guaranteed to get values in any particular order, however. | |
| // Let's fix that. | |
| void reduce(Text key, Iterator<LongWritable> values, Context<Text, LongWritable> context) { | |
| // Create a copy buffer and slurp all values out of the iterator. | |
| List<Long> bufferedValues = new ArrayList<Long>(); | |
| for (LongWritable value : values) { | |
| bufferedValues.add(value.get()); | |
| } | |
| // Sort the values (if you want) and iterator over them. | |
| for (Long value : Collections.sort(bufferedValues)) { | |
| context.output(key, value); | |
| } | |
| } | |
| Assuming the input is: | |
| reduce("a", [ 4, 3, 2 ]); | |
| reduce("b", [ 1, 2 ]); | |
| The output is: | |
| "a", 2 | |
| "a", 3 | |
| "a", 4 | |
| "b", 1 | |
| "b", 2 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment