JobHistory related clean-up

hraven-etl/src/main/java/com/twitter/hraven/etl/JobHistoryFileParserFactory.java

@@ -32,9 +32,7 @@ public class JobHistoryFileParserFactory {
    * VERSION variable there becomes package-level visible and hence we need a replica
    */
   public static final String HADOOP2_VERSION_STRING = "Avro-Json";
-  public static final String HADOOP1_VERSION_STRING = "Meta VERSION=\"1\" .";
   private static final int HADOOP2_VERSION_LENGTH = 9;
-  private static final int HADOOP1_VERSION_LENGTH = 18;
 
   /**
    * determines the verison of hadoop that the history file belongs to
@@ -55,26 +53,17 @@ public static HadoopVersion getVersion(byte[] historyFileContents) {
       String version2Part =  new String(historyFileContents, 0, HADOOP2_VERSION_LENGTH);
       if (StringUtils.equalsIgnoreCase(version2Part, HADOOP2_VERSION_STRING)) {
         return HadoopVersion.TWO;
-      } else {
-        if(historyFileContents.length > HADOOP1_VERSION_LENGTH) {
-          // the first 18 bytes in a hadoop1.0 history file contain Meta VERSION="1" .
-          String version1Part =  new String(historyFileContents, 0, HADOOP1_VERSION_LENGTH);
-          if (StringUtils.equalsIgnoreCase(version1Part, HADOOP1_VERSION_STRING)) {
-            return HadoopVersion.ONE;
-          }
-        }
       }
     }
     // throw an exception if we did not find any matching version
     throw new IllegalArgumentException(" Unknown format of job history file: " + historyFileContents);
   }
 
   /**
-   * creates an instance of {@link JobHistoryParseHadoop1}
-   * or
-   * {@link JobHistoryParseHadoop2} that can parse post MAPREDUCE-1016 job history files
+   * creates an instance of
+   * {@link JobHistoryFileParserHadoop2} that can parse post MAPREDUCE-1016 job history files
    *
-   * @param historyFile: history file contents
+   * @param historyFileContents: history file contents
    *
    * @return an object that can parse job history files
    * Or return null if either input is null
@@ -90,9 +79,6 @@ public static JobHistoryFileParser createJobHistoryFileParser(
     HadoopVersion version = getVersion(historyFileContents);
 
     switch (version) {
-    case ONE:
-      return new JobHistoryFileParserHadoop1(jobConf);
-
     case TWO:
       return new JobHistoryFileParserHadoop2(jobConf);
 
@@ -102,13 +88,6 @@ public static JobHistoryFileParser createJobHistoryFileParser(
     }
   }
 
-  /**
-   * @return HISTORY_FILE_VERSION1
-   */
-  public static HadoopVersion getHistoryFileVersion1() {
-    return HadoopVersion.ONE;
-  }
-
   /**
    * @return HISTORY_FILE_VERSION2
    */

hraven-etl/src/main/java/com/twitter/hraven/etl/JobHistoryFileParserHadoop2.java

@@ -26,22 +26,19 @@
 import org.apache.avro.io.Decoder;
 import org.apache.avro.io.DecoderFactory;
 import org.apache.commons.configuration.ConversionException;
-import org.apache.commons.lang.StringUtils;
 import org.apache.commons.logging.Log;
 import org.apache.commons.logging.LogFactory;
 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.fs.FSDataInputStream;
 import org.apache.hadoop.hbase.KeyValue;
 import org.apache.hadoop.hbase.client.Put;
 import org.apache.hadoop.hbase.util.Bytes;
-import org.apache.hadoop.mapred.JobHistoryCopy.RecordTypes;
+import com.twitter.hraven.mapreduce.RecordTypes;
 import org.codehaus.jettison.json.JSONArray;
 import org.codehaus.jettison.json.JSONException;
 import org.codehaus.jettison.json.JSONObject;
 
 import com.google.common.collect.Maps;
-import com.twitter.hraven.AppKey;
-import com.twitter.hraven.AppSummary;
 import com.twitter.hraven.Constants;
 import com.twitter.hraven.JobDetails;
 import com.twitter.hraven.JobHistoryKeys;