summaryrefslogtreecommitdiffstats
path: root/sandbox/ctrezzo/src/services/WordCountImpl.java
diff options
context:
space:
mode:
Diffstat (limited to 'sandbox/ctrezzo/src/services/WordCountImpl.java')
-rw-r--r--sandbox/ctrezzo/src/services/WordCountImpl.java69
1 files changed, 69 insertions, 0 deletions
diff --git a/sandbox/ctrezzo/src/services/WordCountImpl.java b/sandbox/ctrezzo/src/services/WordCountImpl.java
new file mode 100644
index 0000000000..0575506cc4
--- /dev/null
+++ b/sandbox/ctrezzo/src/services/WordCountImpl.java
@@ -0,0 +1,69 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package services;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.io.IntWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapred.JobClient;
+import org.apache.hadoop.mapred.JobConf;
+import org.osoa.sca.annotations.Property;
+
+public class WordCountImpl implements services.WordCount {
+
+ //this path is a HDFS path
+ @Property
+ Path inputPath = new Path("/file01.txt");
+
+ //this path is a HDFS path
+ @Property
+ Path outputPath = new Path("/output1");
+
+ public void runJob() {
+
+ org.apache.hadoop.examples.WordCount myCount = new org.apache.hadoop.examples.WordCount();
+ Configuration conf = new Configuration();
+
+ myCount.setConf(conf);
+
+ JobConf mapredConf = new JobConf(myCount.getConf(), org.apache.hadoop.examples.WordCount.class);
+ mapredConf.setJobName("wordcount");
+
+ // the keys are words (strings)
+ mapredConf.setOutputKeyClass(Text.class);
+ // the values are counts (ints)
+ mapredConf.setOutputValueClass(IntWritable.class);
+
+ mapredConf.setMapperClass(org.apache.hadoop.examples.WordCount.MapClass.class);
+ mapredConf.setCombinerClass(org.apache.hadoop.examples.WordCount.Reduce.class);
+ mapredConf.setReducerClass(org.apache.hadoop.examples.WordCount.Reduce.class);
+
+ mapredConf.setInputPath(inputPath);
+ mapredConf.setOutputPath(outputPath);
+
+ try {
+ JobClient.runJob(mapredConf);
+ }
+ catch(Exception e) {
+ System.out.println("ERROR: " + e);
+ }
+ }
+}