/**
* Write out a SequenceFile that can be read by TotalOrderPartitioner that contains the split
* points in startKeys.
*
* <p>This method was copied from HFileOutputFormat in hbase-0.90.1-cdh3u0. I had to copy it
* because it's private.
*
* @param conf The job configuration.
* @param partitionsPath output path for SequenceFile.
* @param startKeys the region start keys to use as the partitions.
* @throws IOException If there is an error.
*/
private static void writePartitionFile(
Configuration conf, Path partitionsPath, List<HFileKeyValue> startKeys) throws IOException {
if (startKeys.isEmpty()) {
throw new IllegalArgumentException("No regions passed");
}
// We're generating a list of split points, and we don't ever
// have keys < the first region (which has an empty start key)
// so we need to remove it. Otherwise we would end up with an
// empty reducer with index 0.
TreeSet<HFileKeyValue> sorted = new TreeSet<HFileKeyValue>();
sorted.addAll(startKeys);
HFileKeyValue first = sorted.first();
if (0 != first.getRowKey().length) {
throw new IllegalArgumentException(
"First region of table should have empty start row key. Instead has: "
+ Bytes.toStringBinary(first.getRowKey()));
}
sorted.remove(first);
// Write the actual file
final SequenceFile.Writer writer =
KijiMRPlatformBridge.get()
.newSeqFileWriter(conf, partitionsPath, HFileKeyValue.class, NullWritable.class);
try {
for (HFileKeyValue startKey : sorted) {
writer.append(startKey, NullWritable.get());
}
} finally {
writer.close();
}
}
