NUTCH-1446 Port NUTCH-1444 to trunk (Indexing should not create tempo…

src/java/org/apache/nutch/indexer/IndexerOutputFormat.java

@@ -14,24 +14,27 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
+
 package org.apache.nutch.indexer;
 
 import java.io.IOException;
 import java.lang.invoke.MethodHandles;
 
 import org.apache.hadoop.io.Text;
-import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
-import org.apache.hadoop.mapreduce.RecordWriter;
 import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.mapreduce.JobContext;
+import org.apache.hadoop.mapreduce.OutputCommitter;
+import org.apache.hadoop.mapreduce.OutputFormat;
+import org.apache.hadoop.mapreduce.RecordWriter;
 import org.apache.hadoop.mapreduce.TaskAttemptContext;
+
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
-public class IndexerOutputFormat
-    extends FileOutputFormat<Text, NutchIndexAction> {
+public class IndexerOutputFormat extends OutputFormat<Text, NutchIndexAction> {
 
-  private static final Logger LOG = LoggerFactory
-      .getLogger(MethodHandles.lookup().lookupClass());
+  private static final Logger LOG =
+      LoggerFactory.getLogger(MethodHandles.lookup().lookupClass());
 
   @Override
   public RecordWriter<Text, NutchIndexAction> getRecordWriter(
@@ -40,32 +43,69 @@ public RecordWriter<Text, NutchIndexAction> getRecordWriter(
     Configuration conf = context.getConfiguration();
     final IndexWriters writers = IndexWriters.get(conf);
 
-    String name = getUniqueFile(context, "part", "");
-    writers.open(conf, name);
+    // open writers (no temporary file output anymore)
+    String indexName = "index-" + context.getTaskAttemptID().toString();
+    writers.open(conf, indexName);
     LOG.info(writers.describe());
 
     return new RecordWriter<Text, NutchIndexAction>() {
 
       @Override
       public void close(TaskAttemptContext context) throws IOException {
+
         // do the commits once and for all the reducers in one go
-        boolean noCommit = conf
-            .getBoolean(IndexerMapReduce.INDEXER_NO_COMMIT, false);
+      boolean noCommit =
+        conf.getBoolean(IndexerMapReduce.INDEXER_NO_COMMIT, false);
+
         if (!noCommit) {
           writers.commit();
         }
+
         writers.close();
       }
 
       @Override
       public void write(Text key, NutchIndexAction indexAction)
           throws IOException {
+
         if (indexAction.action == NutchIndexAction.ADD) {
           writers.write(indexAction.doc);
+
         } else if (indexAction.action == NutchIndexAction.DELETE) {
           writers.delete(key.toString());
         }
       }
     };
   }
-}
+
+  @Override
+  public void checkOutputSpecs(JobContext context)
+      throws IOException, InterruptedException {
+    // No output specs required since we don't write files
+  }
+
+  @Override
+  public OutputCommitter getOutputCommitter(TaskAttemptContext context)
+      throws IOException, InterruptedException {
+
+    return new OutputCommitter() {
+
+      @Override
+      public void setupJob(JobContext jobContext) {}
+
+      @Override
+      public void setupTask(TaskAttemptContext taskContext) {}
+
+      @Override
+      public boolean needsTaskCommit(TaskAttemptContext taskContext) {
+        return false;
+      }
+
+      @Override
+      public void commitTask(TaskAttemptContext taskContext) {}
+
+      @Override
+      public void abortTask(TaskAttemptContext taskContext) {}
+    };
+  }
+}