List of usage examples for org.apache.mahout.common.iterator.sequencefile SequenceFileDirIterable iterator
@Override
public Iterator<Pair<K, V>> iterator()
From source file:org.conan.mymahout.clustering.streaming.tools.ResplitSequenceFiles.java
License:Apache License
private void run(PrintWriter printWriter) throws IOException { conf = new Configuration(); SequenceFileDirIterable<Writable, Writable> inputIterable = new SequenceFileDirIterable<Writable, Writable>( new Path(inputFile), PathType.LIST, conf); fs = FileSystem.get(conf);// w w w .ja v a2s . com int numEntries = Iterables.size(inputIterable); int numEntriesPerSplit = numEntries / numSplits; int numEntriesLastSplit = numEntriesPerSplit + numEntries - numEntriesPerSplit * numSplits; Iterator<Pair<Writable, Writable>> inputIterator = inputIterable.iterator(); printWriter.printf("Writing %d splits\n", numSplits); for (int i = 0; i < numSplits - 1; ++i) { printWriter.printf("Writing split %d\n", i); writeSplit(inputIterator, i, numEntriesPerSplit); } printWriter.printf("Writing split %d\n", numSplits - 1); writeSplit(inputIterator, numSplits - 1, numEntriesLastSplit); }