cleanup to prep RC

pom.xml

@@ -4,7 +4,7 @@
   <artifactId>crunchTS</artifactId>
   <packaging>jar</packaging>
   <version>0.0.2-SNAPSHOT</version>
-  <name>crunchTS</name>
+  <name>crunch.TS</name>
   <url>http://maven.apache.org</url>
   <properties>
     <!--hadoopclient.version>2.0.0-cdh4.5.0</hadoopclient.version-->

src/main/java/de/bitocean/crunchts/simple/ImportClickCountData.java

@@ -114,7 +114,7 @@ public void initialize() {
                         fileName = ((CombineFileSplit) inputSplit).getPaths()[0].getName();
                     }
 
-                    timestamp = wikipedia.TimeStampTool.getTimeInMillis(fileName);
+                    timestamp = de.bitocean.util.wikipedia.TimeStampTool.getTimeInMillis(fileName);
                 } 
                 catch (ClassCastException e) {
                     e.printStackTrace();

src/main/java/org/apache/crunchts/TSData.java → src/main/java/de/bitocean/data/TSData.java

@@ -1,4 +1,4 @@
-package org.apache.crunchts;
+package de.bitocean.data;
 import java.io.BufferedReader;
 import java.io.DataInput;
 import java.io.DataOutput;

src/main/java/de/bitocean/relevance/WebResourceBucketNodeDegree.java

@@ -113,7 +113,7 @@ public void initialize() {
                         fileName = ((CombineFileSplit) inputSplit).getPaths()[0].getName();
                     }
 
-                    timestamp = wikipedia.TimeStampTool.getTimeInMillis(fileName);
+                    timestamp = de.bitocean.util.wikipedia.TimeStampTool.getTimeInMillis(fileName);
                 } 
                 catch (ClassCastException e) {
                     e.printStackTrace();

src/main/java/wikipedia/TimeStampTool.java → src/main/java/de/bitocean/util/wikipedia/TimeStampTool.java

@@ -1,17 +1,35 @@
-package wikipedia;
+package de.bitocean.util.wikipedia;
 
 import java.util.Calendar;
 import java.util.Date;
 import java.util.GregorianCalendar;
 
 /**
- * Based on a filename like "pagecounts-20071210-010000.gz"
- * the time in millis is calculated.
+ * Wikipedia Click-Count data is public available.
+ * 
+ * Each file contains aggregated hourly click-counts for all 
+ * Wikipedia pages.
+ * 
+ * Based on the filename like "pagecounts-20071210-010000.gz"
+ * the time stamp in milli seconds is calculated.
+ * 
+ * The timestamp represents the beginning of the hour for which data 
+ * is provided. Due to inqaccuracy one can not relay on all digits.
+ * 
+ * This implementation does not do any kind of correction.
+ * More advanced testing is required for future releases. 
  *
- * @author root
+ * @author Mirko Kämpf
+ * 
  */
 public class TimeStampTool {
 
+    /**
+     * Extract time stamp from click-count file name.
+     * 
+     * @param filename
+     * @return timestamp in ms
+     */
     static public long getTimeInMillis(String filename) {
         // System.out.println( filename );
         String[] s = filename.split("-");