Author: brandonwilliams Date: Wed Oct 12 16:25:00 2011 New Revision: 1182463
URL: http://svn.apache.org/viewvc?rev=1182463&view=rev Log: Skip empty rows when slicing the entire row. Patch by Jeremy Hanna and brandonwilliams, reviewed by Jeremy Hanna for CASSANDRA-2855 Modified: cassandra/branches/cassandra-0.8/CHANGES.txt cassandra/branches/cassandra-0.8/src/java/org/apache/cassandra/hadoop/ColumnFamilyRecordReader.java Modified: cassandra/branches/cassandra-0.8/CHANGES.txt URL: http://svn.apache.org/viewvc/cassandra/branches/cassandra-0.8/CHANGES.txt?rev=1182463&r1=1182462&r2=1182463&view=diff ============================================================================== --- cassandra/branches/cassandra-0.8/CHANGES.txt (original) +++ cassandra/branches/cassandra-0.8/CHANGES.txt Wed Oct 12 16:25:00 2011 @@ -4,6 +4,7 @@ * (CQL) update grammar to require key clause in DELETE statement (CASSANDRA-3349) * (CQL) allow numeric keyspace names in USE statement (CASSANDRA-3350) + * (Hadoop) skip empty rows when slicing the entire row (CASSANDRA-2855) 0.8.7 Modified: cassandra/branches/cassandra-0.8/src/java/org/apache/cassandra/hadoop/ColumnFamilyRecordReader.java URL: http://svn.apache.org/viewvc/cassandra/branches/cassandra-0.8/src/java/org/apache/cassandra/hadoop/ColumnFamilyRecordReader.java?rev=1182463&r1=1182462&r2=1182463&view=diff ============================================================================== --- cassandra/branches/cassandra-0.8/src/java/org/apache/cassandra/hadoop/ColumnFamilyRecordReader.java (original) +++ cassandra/branches/cassandra-0.8/src/java/org/apache/cassandra/hadoop/ColumnFamilyRecordReader.java Wed Oct 12 16:25:00 2011 @@ -98,7 +98,7 @@ public class ColumnFamilyRecordReader ex batchRowCount = ConfigHelper.getRangeBatchSize(conf); cfName = ConfigHelper.getInputColumnFamily(conf); consistencyLevel = ConsistencyLevel.valueOf(ConfigHelper.getReadConsistencyLevel(conf)); - + keyspace = ConfigHelper.getInputKeyspace(conf); @@ -257,14 +257,24 @@ public class ColumnFamilyRecordReader ex rows = null; return; } - - // reset to iterate through this new batch - i = 0; + + // Pre-compute the last row key, before removing empty rows + ByteBuffer lastRowKey = rows.get(rows.size() - 1).key; + + // only remove empty rows if the slice predicate is empty + if (isPredicateEmpty(predicate)) + { + Iterator<KeySlice> rowsIterator = rows.iterator(); + while (rowsIterator.hasNext()) + if (rowsIterator.next().columns.isEmpty()) + rowsIterator.remove(); + } + // reset to iterate through the new batch + i = 0; + // prepare for the next slice to be read - KeySlice lastRow = rows.get(rows.size() - 1); - ByteBuffer rowkey = lastRow.key; - startToken = partitioner.getTokenFactory().toString(partitioner.getToken(rowkey)); + startToken = partitioner.getTokenFactory().toString(partitioner.getToken(lastRowKey)); } catch (Exception e) { @@ -339,4 +349,16 @@ public class ColumnFamilyRecordReader ex return sc; } } + + private boolean isPredicateEmpty(SlicePredicate predicate) + { + if (predicate != null) + if (predicate.isSetSlice_range()) + if (predicate.getSlice_range().getStart() != null && predicate.getSlice_range().getFinish() != null) + return false; + else if (predicate.isSetColumn_names()) + return false; + + return true; + } }
