add test suite case for removetip/removebridge/pathmerge
diff --git a/genomix/genomix-hadoop/src/test/java/edu/uci/ics/genomix/hadoop/graphclean/mergepaths/h3/TestPathMergeH3.java b/genomix/genomix-hadoop/src/test/java/edu/uci/ics/genomix/hadoop/graphclean/mergepaths/h3/TestPathMergeH3.java
index 7db3db5..bac2a45 100644
--- a/genomix/genomix-hadoop/src/test/java/edu/uci/ics/genomix/hadoop/graphclean/mergepaths/h3/TestPathMergeH3.java
+++ b/genomix/genomix-hadoop/src/test/java/edu/uci/ics/genomix/hadoop/graphclean/mergepaths/h3/TestPathMergeH3.java
@@ -27,7 +27,7 @@
protected String PATHMERGE_FILE = "mergepath.result";
protected boolean regenerateGraph = true;
- {
+ {w
KMER_LENGTH = 5;
READ_LENGTH = 8;
HDFS_PATHS = new ArrayList<String>(Arrays.asList(HDFS_SEQUENCE, HDFS_GRAPHBUILD, HDFS_MARKPATHS, HDFS_MERGED));
diff --git a/genomix/genomix-pregelix/data/bridgeremove/txt/.bridgeremove.crc b/genomix/genomix-pregelix/data/bridgeremove/txt/.bridgeremove.crc
deleted file mode 100644
index e69de29..0000000
--- a/genomix/genomix-pregelix/data/bridgeremove/txt/.bridgeremove.crc
+++ /dev/null
diff --git a/genomix/genomix-pregelix/data/bridgeremove/txt/bridgeremove b/genomix/genomix-pregelix/data/bridgeremove/txt/bridgeremove
deleted file mode 100755
index e5fb406..0000000
--- a/genomix/genomix-pregelix/data/bridgeremove/txt/bridgeremove
+++ /dev/null
@@ -1,7 +0,0 @@
-(2,1)([(2,2)] [] [] [] GCC)
-(1,1)([(1,2)] [] [] [] AAT)
-(2,2)([(2,3)] [] [] [(2,1),(3,1)] CCT)
-(1,2)([(1,3),(3,1)] [] [] [(1,1)] ATA)
-(2,3)([] [] [] [(2,2)] CTAGCA)
-(1,3)([] [] [] [(1,2)] TAGAAC)
-(3,1)([(2,2)] [] [] [(1,2)] TAGCCT)
diff --git a/genomix/genomix-pregelix/data/bubble_merge/txt/.bubble_merge.crc b/genomix/genomix-pregelix/data/bubble_merge/txt/.bubble_merge.crc
deleted file mode 100644
index e69de29..0000000
--- a/genomix/genomix-pregelix/data/bubble_merge/txt/.bubble_merge.crc
+++ /dev/null
diff --git a/genomix/genomix-pregelix/data/bubble_merge/txt/bubble_merge b/genomix/genomix-pregelix/data/bubble_merge/txt/bubble_merge
deleted file mode 100755
index 22d58bf..0000000
--- a/genomix/genomix-pregelix/data/bubble_merge/txt/bubble_merge
+++ /dev/null
@@ -1,6 +0,0 @@
-(1,5)([] [] [] [(1,4)] GAAC)
-(2,1)([(1,4)] [] [] [(1,2)] TAGCCAG)
-(1,1)([(1,2)] [] [] [] AAT)
-(1,2)([(1,3),(2,1)] [] [] [(1,1)] ATA)
-(1,4)([(1,5)] [] [] [(1,3),(2,1)] AGA)
-(1,3)([(1,4)] [] [] [(1,2)] TAG)
diff --git a/genomix/genomix-pregelix/data/bubble_remove/txt/.bubble.crc b/genomix/genomix-pregelix/data/bubble_remove/txt/.bubble.crc
deleted file mode 100644
index e69de29..0000000
--- a/genomix/genomix-pregelix/data/bubble_remove/txt/.bubble.crc
+++ /dev/null
diff --git a/genomix/genomix-pregelix/data/bubble_remove/txt/bubble b/genomix/genomix-pregelix/data/bubble_remove/txt/bubble
deleted file mode 100755
index d250792..0000000
--- a/genomix/genomix-pregelix/data/bubble_remove/txt/bubble
+++ /dev/null
@@ -1,6 +0,0 @@
-(1,5)([] [] [] [(1,4)] GAAC)
-(2,1)([(1,4)] [] [] [(1,2)] TAG)
-(1,1)([(1,2)] [] [] [] AAT)
-(1,2)([(1,3),(2,1)] [] [] [(1,1)] ATA)
-(1,4)([(1,5)] [] [] [(1,3),(2,1)] AGA)
-(1,3)([(1,4)] [] [] [(1,2)] TAG)
diff --git a/genomix/genomix-pregelix/data/graphbuild.test/read.txt b/genomix/genomix-pregelix/data/graphbuild.test/read.txt
deleted file mode 100755
index 37f02de..0000000
--- a/genomix/genomix-pregelix/data/graphbuild.test/read.txt
+++ /dev/null
@@ -1 +0,0 @@
-1 AATAGAA
diff --git a/genomix/genomix-pregelix/data/graphbuild.test/repeat.txt b/genomix/genomix-pregelix/data/graphbuild.test/repeat.txt
deleted file mode 100755
index 64e3de8..0000000
--- a/genomix/genomix-pregelix/data/graphbuild.test/repeat.txt
+++ /dev/null
@@ -1,2 +0,0 @@
-1 AATAGAAC
-2 TAGAACTG
diff --git a/genomix/genomix-pregelix/data/graphbuild.test/repeat2.txt b/genomix/genomix-pregelix/data/graphbuild.test/repeat2.txt
deleted file mode 100755
index c065d06..0000000
--- a/genomix/genomix-pregelix/data/graphbuild.test/repeat2.txt
+++ /dev/null
@@ -1,2 +0,0 @@
-1 AATAGAAC
-2 TAGAAGAT
diff --git a/genomix/genomix-pregelix/data/graphbuild.test/text.txt b/genomix/genomix-pregelix/data/graphbuild.test/text.txt
deleted file mode 100755
index f9e7e07..0000000
--- a/genomix/genomix-pregelix/data/graphbuild.test/text.txt
+++ /dev/null
@@ -1,2 +0,0 @@
-1 AATAGAAGG
-2 ATAGAAACC
diff --git a/genomix/genomix-pregelix/data/graphbuild.test/text.txt~ b/genomix/genomix-pregelix/data/graphbuild.test/text.txt~
deleted file mode 100755
index ba651ae..0000000
--- a/genomix/genomix-pregelix/data/graphbuild.test/text.txt~
+++ /dev/null
@@ -1,2 +0,0 @@
-1 AATAGAA
-2 ATAGAAA
diff --git a/genomix/genomix-pregelix/data/graphbuild.test/tip.txt b/genomix/genomix-pregelix/data/graphbuild.test/tip.txt
deleted file mode 100755
index 62a6fd7..0000000
--- a/genomix/genomix-pregelix/data/graphbuild.test/tip.txt
+++ /dev/null
@@ -1,2 +0,0 @@
-1 AATAGAAC
-2 GAAGGTCC
diff --git a/genomix/genomix-pregelix/data/graphbuild.test/tworeads.txt b/genomix/genomix-pregelix/data/graphbuild.test/tworeads.txt
deleted file mode 100755
index 62a6fd7..0000000
--- a/genomix/genomix-pregelix/data/graphbuild.test/tworeads.txt
+++ /dev/null
@@ -1,2 +0,0 @@
-1 AATAGAAC
-2 GAAGGTCC
diff --git a/genomix/genomix-pregelix/data/input/pathmerge/part-0 b/genomix/genomix-pregelix/data/input/pathmerge/part-0
deleted file mode 100755
index 56056ab..0000000
--- a/genomix/genomix-pregelix/data/input/pathmerge/part-0
+++ /dev/null
Binary files differ
diff --git a/genomix/genomix-pregelix/data/input/pathmerge/part-1 b/genomix/genomix-pregelix/data/input/pathmerge/part-1
deleted file mode 100755
index 95701ce..0000000
--- a/genomix/genomix-pregelix/data/input/pathmerge/part-1
+++ /dev/null
Binary files differ
diff --git a/genomix/genomix-pregelix/data/input/pathmerge/part-2 b/genomix/genomix-pregelix/data/input/pathmerge/part-2
deleted file mode 100755
index 6bb6633..0000000
--- a/genomix/genomix-pregelix/data/input/pathmerge/part-2
+++ /dev/null
Binary files differ
diff --git a/genomix/genomix-pregelix/data/input/test/part-2 b/genomix/genomix-pregelix/data/input/test/part-2
deleted file mode 100755
index 9098ad0..0000000
--- a/genomix/genomix-pregelix/data/input/test/part-2
+++ /dev/null
Binary files differ
diff --git a/genomix/genomix-pregelix/data/input/test/part-3 b/genomix/genomix-pregelix/data/input/test/part-3
deleted file mode 100755
index 9cfb024..0000000
--- a/genomix/genomix-pregelix/data/input/test/part-3
+++ /dev/null
Binary files differ
diff --git a/genomix/genomix-pregelix/data/input/tipremove/part-0 b/genomix/genomix-pregelix/data/input/tipremove/part-0
deleted file mode 100755
index d45f051..0000000
--- a/genomix/genomix-pregelix/data/input/tipremove/part-0
+++ /dev/null
Binary files differ
diff --git a/genomix/genomix-pregelix/data/input/tipremove/part-1 b/genomix/genomix-pregelix/data/input/tipremove/part-1
deleted file mode 100755
index d50e98a..0000000
--- a/genomix/genomix-pregelix/data/input/tipremove/part-1
+++ /dev/null
Binary files differ
diff --git a/genomix/genomix-pregelix/data/input/tipremove/part-2 b/genomix/genomix-pregelix/data/input/tipremove/part-2
deleted file mode 100755
index 6ed28d6..0000000
--- a/genomix/genomix-pregelix/data/input/tipremove/part-2
+++ /dev/null
Binary files differ
diff --git a/genomix/genomix-pregelix/data/input/tipremove/part-3 b/genomix/genomix-pregelix/data/input/tipremove/part-3
deleted file mode 100755
index 4734cf2..0000000
--- a/genomix/genomix-pregelix/data/input/tipremove/part-3
+++ /dev/null
Binary files differ
diff --git a/genomix/genomix-pregelix/data/input/tipremove/part-4 b/genomix/genomix-pregelix/data/input/tipremove/part-4
deleted file mode 100755
index 84cd77d..0000000
--- a/genomix/genomix-pregelix/data/input/tipremove/part-4
+++ /dev/null
Binary files differ
diff --git a/genomix/genomix-pregelix/data/input/tipremove/part-5 b/genomix/genomix-pregelix/data/input/tipremove/part-5
deleted file mode 100755
index 9143122..0000000
--- a/genomix/genomix-pregelix/data/input/tipremove/part-5
+++ /dev/null
Binary files differ
diff --git a/genomix/genomix-pregelix/data/input/tipremove/part-6 b/genomix/genomix-pregelix/data/input/tipremove/part-6
deleted file mode 100755
index 14c675c..0000000
--- a/genomix/genomix-pregelix/data/input/tipremove/part-6
+++ /dev/null
Binary files differ
diff --git a/genomix/genomix-pregelix/data/input/tipremove/part-7 b/genomix/genomix-pregelix/data/input/tipremove/part-7
deleted file mode 100755
index 0c9ca53..0000000
--- a/genomix/genomix-pregelix/data/input/tipremove/part-7
+++ /dev/null
Binary files differ
diff --git a/genomix/genomix-pregelix/data/input/test/part-0 b/genomix/genomix-pregelix/data/input/tworeads/part-0
similarity index 65%
rename from genomix/genomix-pregelix/data/input/test/part-0
rename to genomix/genomix-pregelix/data/input/tworeads/part-0
index 0b15880..271cd2b 100755
--- a/genomix/genomix-pregelix/data/input/test/part-0
+++ b/genomix/genomix-pregelix/data/input/tworeads/part-0
Binary files differ
diff --git a/genomix/genomix-pregelix/data/input/test/part-1 b/genomix/genomix-pregelix/data/input/tworeads/part-1
similarity index 81%
rename from genomix/genomix-pregelix/data/input/test/part-1
rename to genomix/genomix-pregelix/data/input/tworeads/part-1
index b68421a..30c05e6 100755
--- a/genomix/genomix-pregelix/data/input/test/part-1
+++ b/genomix/genomix-pregelix/data/input/tworeads/part-1
Binary files differ
diff --git a/genomix/genomix-pregelix/data/input/tworeads/part-2 b/genomix/genomix-pregelix/data/input/tworeads/part-2
new file mode 100755
index 0000000..4b8e2c4
--- /dev/null
+++ b/genomix/genomix-pregelix/data/input/tworeads/part-2
Binary files differ
diff --git a/genomix/genomix-pregelix/data/input/pathmerge/part-3 b/genomix/genomix-pregelix/data/input/tworeads/part-3
similarity index 65%
rename from genomix/genomix-pregelix/data/input/pathmerge/part-3
rename to genomix/genomix-pregelix/data/input/tworeads/part-3
index caa63de..9fa10d6 100755
--- a/genomix/genomix-pregelix/data/input/pathmerge/part-3
+++ b/genomix/genomix-pregelix/data/input/tworeads/part-3
Binary files differ
diff --git a/genomix/genomix-pregelix/data/test/result.graphbuild.bidirectional.txt b/genomix/genomix-pregelix/data/test/result.graphbuild.bidirectional.txt
deleted file mode 100644
index a41ce56..0000000
--- a/genomix/genomix-pregelix/data/test/result.graphbuild.bidirectional.txt
+++ /dev/null
@@ -1,18 +0,0 @@
-((2,1) [(2,3)] [] [] [] AATAGA) (null)
-((2,3) [(6,1),(2,4)] [] [] [(2,1)] TAGAA) (null)
-((2,4) [(6,2)] [] [] [(2,3)] AGAAG) (null)
-((4,1) [(4,3)] [] [] [] AATAGA) (null)
-((4,3) [(6,1),(4,4)] [] [] [(4,1)] TAGAA) (null)
-((4,4) [(6,2)] [] [] [(4,3)] AGAAG) (null)
-((6,1) [(6,2)] [] [] [(2,3),(1,3),(3,3),(4,3),(5,3)] AGAAG) (null)
-((6,2) [(6,3)] [] [] [(2,4),(3,4),(1,4),(4,4),(5,4),(6,1)] GAAGA) (null)
-((6,3) [] [] [] [(6,2)] AAGAAG) (null)
-((1,1) [(1,3)] [] [] [] AATAGA) (null)
-((1,3) [(6,1),(1,4)] [] [] [(1,1)] TAGAA) (null)
-((1,4) [(6,2)] [] [] [(1,3)] AGAAG) (null)
-((3,1) [(3,3)] [] [] [] AATAGA) (null)
-((3,3) [(6,1),(3,4)] [] [] [(3,1)] TAGAA) (null)
-((3,4) [(6,2)] [] [] [(3,3)] AGAAG) (null)
-((5,1) [(5,3)] [] [] [] AATAGA) (null)
-((5,3) [(6,1),(5,4)] [] [] [(5,1)] TAGAA) (null)
-((5,4) [(6,2)] [] [] [(5,3)] AGAAG) (null)
diff --git a/genomix/genomix-pregelix/data/test/result.graphbuild.txt.bin b/genomix/genomix-pregelix/data/test/result.graphbuild.txt.bin
deleted file mode 100644
index 4865aeb..0000000
--- a/genomix/genomix-pregelix/data/test/result.graphbuild.txt.bin
+++ /dev/null
Binary files differ
diff --git a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/format/DataCleanOutputFormat.java b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/format/DataCleanOutputFormat.java
index 9e2e5f0..1a961d8 100644
--- a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/format/DataCleanOutputFormat.java
+++ b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/format/DataCleanOutputFormat.java
@@ -36,8 +36,8 @@
@Override
public void writeVertex(Vertex<PositionWritable, VertexValueWritable, NullWritable, ?> vertex)
throws IOException, InterruptedException {
- if(vertex.getVertexValue().getState() != MessageFlag.IS_OLDHEAD)
- getRecordWriter().write(vertex.getVertexId(), vertex.getVertexValue());
+ //if(vertex.getVertexValue().getState() != MessageFlag.IS_OLDHEAD)
+ getRecordWriter().write(vertex.getVertexId(), vertex.getVertexValue());
}
}
}
diff --git a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/io/MessageWritable.java b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/io/MessageWritable.java
index 314dff6..979f5f2 100644
--- a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/io/MessageWritable.java
+++ b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/io/MessageWritable.java
@@ -6,7 +6,6 @@
import org.apache.hadoop.io.WritableComparable;
-import edu.uci.ics.genomix.pregelix.type.AdjMessage;
import edu.uci.ics.genomix.pregelix.type.CheckMessage;
import edu.uci.ics.genomix.pregelix.type.Message;
import edu.uci.ics.genomix.type.KmerBytesWritable;
diff --git a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bridgeremove/BridgeRemoveVertex.java b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bridgeremove/BridgeRemoveVertex.java
index cf312db..91bb9cb 100644
--- a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bridgeremove/BridgeRemoveVertex.java
+++ b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bridgeremove/BridgeRemoveVertex.java
@@ -2,16 +2,15 @@
import java.util.ArrayList;
import java.util.Iterator;
-import org.apache.hadoop.io.NullWritable;
import edu.uci.ics.genomix.type.PositionWritable;
-import edu.uci.ics.pregelix.api.graph.Vertex;
import edu.uci.ics.pregelix.api.job.PregelixJob;
import edu.uci.ics.genomix.pregelix.client.Client;
import edu.uci.ics.genomix.pregelix.format.DataCleanInputFormat;
import edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat;
import edu.uci.ics.genomix.pregelix.io.MessageWritable;
import edu.uci.ics.genomix.pregelix.io.VertexValueWritable;
+import edu.uci.ics.genomix.pregelix.operator.pathmerge.BasicPathMergeVertex;
import edu.uci.ics.genomix.pregelix.type.AdjMessage;
import edu.uci.ics.genomix.pregelix.util.VertexUtil;
@@ -47,20 +46,12 @@
* Naive Algorithm for path merge graph
*/
public class BridgeRemoveVertex extends
- Vertex<PositionWritable, VertexValueWritable, NullWritable, MessageWritable> {
- public static final String KMER_SIZE = "BridgeRemoveVertex.kmerSize";
+ BasicPathMergeVertex {
public static final String LENGTH = "BridgeRemoveVertex.length";
- public static int kmerSize = -1;
private int length = -1;
- private MessageWritable incomingMsg = new MessageWritable();
- private MessageWritable outgoingMsg = new MessageWritable();
private ArrayList<MessageWritable> receivedMsgList = new ArrayList<MessageWritable>();
-
- private Iterator<PositionWritable> iterator;
- private PositionWritable pos = new PositionWritable();
- private PositionWritable destVertexId = new PositionWritable();
- private Iterator<PositionWritable> posIterator;
+
/**
* initiate kmerSize, maxIteration
*/
@@ -74,46 +65,6 @@
}
/**
- * head send message to all next nodes
- */
- public void sendMsgToAllNextNodes(VertexValueWritable value) {
- posIterator = value.getFFList().iterator(); // FFList
- while(posIterator.hasNext()){
- outgoingMsg.setFlag(AdjMessage.FROMFF);
- outgoingMsg.setSourceVertexId(getVertexId());
- destVertexId.set(posIterator.next());
- sendMsg(destVertexId, outgoingMsg);
- }
- posIterator = value.getFRList().iterator(); // FRList
- while(posIterator.hasNext()){
- outgoingMsg.setFlag(AdjMessage.FROMFR);
- outgoingMsg.setSourceVertexId(getVertexId());
- destVertexId.set(posIterator.next());
- sendMsg(destVertexId, outgoingMsg);
- }
- }
-
- /**
- * head send message to all previous nodes
- */
- public void sendMsgToAllPreviousNodes(VertexValueWritable value) {
- posIterator = value.getRFList().iterator(); // RFList
- while(posIterator.hasNext()){
- outgoingMsg.setFlag(AdjMessage.FROMRF);
- outgoingMsg.setSourceVertexId(getVertexId());
- destVertexId.set(posIterator.next());
- sendMsg(destVertexId, outgoingMsg);
- }
- posIterator = value.getRRList().iterator(); // RRList
- while(posIterator.hasNext()){
- outgoingMsg.setFlag(AdjMessage.FROMRR);
- outgoingMsg.setSourceVertexId(getVertexId());
- destVertexId.set(posIterator.next());
- sendMsg(destVertexId, outgoingMsg);
- }
- }
-
- /**
* broadcast kill self to all neighbers
*/
public void broadcaseKillself(){
@@ -129,21 +80,21 @@
&& receivedMsgList.get(1).getFlag() == AdjMessage.FROMRF) {
outgoingMsg.setFlag(AdjMessage.FROMRR);
sendMsg(receivedMsgList.get(0).getSourceVertexId(), outgoingMsg);
- outgoingMsg.setFlag(AdjMessage.FROMFR);
+ outgoingMsg.setFlag(AdjMessage.FROMRF);
sendMsg(receivedMsgList.get(1).getSourceVertexId(), outgoingMsg);
deleteVertex(getVertexId());
} else if (receivedMsgList.get(0).getFlag() == AdjMessage.FROMFR
&& receivedMsgList.get(1).getFlag() == AdjMessage.FROMRR) {
- outgoingMsg.setFlag(AdjMessage.FROMRF);
+ outgoingMsg.setFlag(AdjMessage.FROMFR);
sendMsg(receivedMsgList.get(0).getSourceVertexId(), outgoingMsg);
outgoingMsg.setFlag(AdjMessage.FROMFF);
sendMsg(receivedMsgList.get(1).getSourceVertexId(), outgoingMsg);
deleteVertex(getVertexId());
} else if (receivedMsgList.get(0).getFlag() == AdjMessage.FROMFR
&& receivedMsgList.get(1).getFlag() == AdjMessage.FROMRF) {
- outgoingMsg.setFlag(AdjMessage.FROMRF);
- sendMsg(receivedMsgList.get(0).getSourceVertexId(), outgoingMsg);
outgoingMsg.setFlag(AdjMessage.FROMFR);
+ sendMsg(receivedMsgList.get(0).getSourceVertexId(), outgoingMsg);
+ outgoingMsg.setFlag(AdjMessage.FROMRF);
sendMsg(receivedMsgList.get(1).getSourceVertexId(), outgoingMsg);
deleteVertex(getVertexId());
} // RR
@@ -158,74 +109,25 @@
&& receivedMsgList.get(0).getFlag() == AdjMessage.FROMRF) {
outgoingMsg.setFlag(AdjMessage.FROMRR);
sendMsg(receivedMsgList.get(1).getSourceVertexId(), outgoingMsg);
- outgoingMsg.setFlag(AdjMessage.FROMFR);
+ outgoingMsg.setFlag(AdjMessage.FROMRF);
sendMsg(receivedMsgList.get(0).getSourceVertexId(), outgoingMsg);
deleteVertex(getVertexId());
} else if (receivedMsgList.get(1).getFlag() == AdjMessage.FROMFR
&& receivedMsgList.get(0).getFlag() == AdjMessage.FROMRR) {
- outgoingMsg.setFlag(AdjMessage.FROMRF);
+ outgoingMsg.setFlag(AdjMessage.FROMFR);
sendMsg(receivedMsgList.get(1).getSourceVertexId(), outgoingMsg);
outgoingMsg.setFlag(AdjMessage.FROMFF);
sendMsg(receivedMsgList.get(0).getSourceVertexId(), outgoingMsg);
deleteVertex(getVertexId());
} else if (receivedMsgList.get(1).getFlag() == AdjMessage.FROMFR
&& receivedMsgList.get(0).getFlag() == AdjMessage.FROMRF) {
- outgoingMsg.setFlag(AdjMessage.FROMRF);
- sendMsg(receivedMsgList.get(1).getSourceVertexId(), outgoingMsg);
outgoingMsg.setFlag(AdjMessage.FROMFR);
+ sendMsg(receivedMsgList.get(1).getSourceVertexId(), outgoingMsg);
+ outgoingMsg.setFlag(AdjMessage.FROMRF);
sendMsg(receivedMsgList.get(0).getSourceVertexId(), outgoingMsg);
deleteVertex(getVertexId());
- }
- }
-
- /**
- * do some remove operations on adjMap after receiving the info about dead Vertex
- */
- public void responseToDeadVertex(Iterator<MessageWritable> msgIterator){
- while (msgIterator.hasNext()) {
- incomingMsg = msgIterator.next();
- if(incomingMsg.getFlag() == AdjMessage.FROMFF){
- //remove incomingMsg.getSourceId from RR positionList
- iterator = getVertexValue().getRRList().iterator();
- while(iterator.hasNext()){
- pos = iterator.next();
- if(pos.equals(incomingMsg.getSourceVertexId())){
- iterator.remove();
- break;
- }
- }
- } else if(incomingMsg.getFlag() == AdjMessage.FROMFR){
- //remove incomingMsg.getSourceId from RF positionList
- iterator = getVertexValue().getRFList().iterator();
- while(iterator.hasNext()){
- pos = iterator.next();
- if(pos.equals(incomingMsg.getSourceVertexId())){
- iterator.remove();
- break;
- }
- }
- } else if(incomingMsg.getFlag() == AdjMessage.FROMRF){
- //remove incomingMsg.getSourceId from FR positionList
- iterator = getVertexValue().getFRList().iterator();
- while(iterator.hasNext()){
- pos = iterator.next();
- if(pos.equals(incomingMsg.getSourceVertexId())){
- iterator.remove();
- break;
- }
- }
- } else{ //incomingMsg.getFlag() == AdjMessage.FROMRR
- //remove incomingMsg.getSourceId from FF positionList
- iterator = getVertexValue().getFFList().iterator();
- while(iterator.hasNext()){
- pos = iterator.next();
- if(pos.equals(incomingMsg.getSourceVertexId())){
- iterator.remove();
- break;
- }
- }
- }
- }
+ } else
+ voteToHalt();
}
@Override
@@ -233,11 +135,11 @@
initVertex();
if (getSuperstep() == 1) {
if(VertexUtil.isUpBridgeVertex(getVertexValue())){
- sendMsgToAllNextNodes(getVertexValue());
+ sendSettledMsgToAllNextNodes(getVertexValue());
}
- else if(VertexUtil.isDownBridgeVertex(getVertexValue())){
- sendMsgToAllPreviousNodes(getVertexValue());
- }
+ else if(VertexUtil.isDownBridgeVertex(getVertexValue())){
+ sendSettledMsgToAllPreviousNodes(getVertexValue());
+ }
}
else if (getSuperstep() == 2){
int i = 0;
diff --git a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bubblemerge/BubbleMergeVertex.java b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bubblemerge/BubbleMergeVertex.java
index cd449b5..4cb6b39 100644
--- a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bubblemerge/BubbleMergeVertex.java
+++ b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bubblemerge/BubbleMergeVertex.java
@@ -144,7 +144,7 @@
}
} else if(incomingMsg.getMessage() == AdjMessage.FROMFR){
//remove incomingMsg.getSourceId from RF positionList
- iterator = getVertexValue().getRFList().iterator();
+ iterator = getVertexValue().getFRList().iterator();
while(iterator.hasNext()){
pos = iterator.next();
if(pos.equals(incomingMsg.getSourceVertexId())){
@@ -154,7 +154,7 @@
}
} else if(incomingMsg.getMessage() == AdjMessage.FROMRF){
//remove incomingMsg.getSourceId from FR positionList
- iterator = getVertexValue().getFRList().iterator();
+ iterator = getVertexValue().getRFList().iterator();
while(iterator.hasNext()){
pos = iterator.next();
if(pos.equals(incomingMsg.getSourceVertexId())){
diff --git a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/pathmerge/BasicPathMergeVertex.java b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/pathmerge/BasicPathMergeVertex.java
index c8d1852..05716fe 100644
--- a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/pathmerge/BasicPathMergeVertex.java
+++ b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/pathmerge/BasicPathMergeVertex.java
@@ -10,6 +10,7 @@
import edu.uci.ics.pregelix.api.graph.Vertex;
import edu.uci.ics.genomix.pregelix.io.MessageWritable;
import edu.uci.ics.genomix.pregelix.io.VertexValueWritable;
+import edu.uci.ics.genomix.pregelix.type.AdjMessage;
import edu.uci.ics.genomix.pregelix.type.MessageFlag;
import edu.uci.ics.genomix.pregelix.util.VertexUtil;
@@ -27,6 +28,7 @@
protected MessageWritable outgoingMsg = new MessageWritable();
protected PositionWritable destVertexId = new PositionWritable();
protected Iterator<PositionWritable> posIterator;
+ private PositionWritable pos = new PositionWritable();
byte headFlag;
protected byte outFlag;
protected byte inFlag;
@@ -140,6 +142,47 @@
sendMsg(destVertexId, outgoingMsg);
}
}
+
+ /**
+ * head send message to all next nodes
+ */
+ public void sendSettledMsgToAllNextNodes(VertexValueWritable value) {
+ posIterator = value.getFFList().iterator(); // FFList
+ while(posIterator.hasNext()){
+ outgoingMsg.setFlag(AdjMessage.FROMFF);
+ outgoingMsg.setSourceVertexId(getVertexId());
+ destVertexId.set(posIterator.next());
+ sendMsg(destVertexId, outgoingMsg);
+ }
+ posIterator = value.getFRList().iterator(); // FRList
+ while(posIterator.hasNext()){
+ outgoingMsg.setFlag(AdjMessage.FROMFR);
+ outgoingMsg.setSourceVertexId(getVertexId());
+ destVertexId.set(posIterator.next());
+ sendMsg(destVertexId, outgoingMsg);
+ }
+ }
+
+ /**
+ * head send message to all previous nodes
+ */
+ public void sendSettledMsgToAllPreviousNodes(VertexValueWritable value) {
+ posIterator = value.getRFList().iterator(); // RFList
+ while(posIterator.hasNext()){
+ outgoingMsg.setFlag(AdjMessage.FROMRF);
+ outgoingMsg.setSourceVertexId(getVertexId());
+ destVertexId.set(posIterator.next());
+ sendMsg(destVertexId, outgoingMsg);
+ }
+ posIterator = value.getRRList().iterator(); // RRList
+ while(posIterator.hasNext()){
+ outgoingMsg.setFlag(AdjMessage.FROMRR);
+ outgoingMsg.setSourceVertexId(getVertexId());
+ destVertexId.set(posIterator.next());
+ sendMsg(destVertexId, outgoingMsg);
+ }
+ }
+
/**
* start sending message
*/
@@ -511,6 +554,56 @@
selfFlag =(byte)(getVertexValue().getState() & MessageFlag.VERTEX_MASK);
}
+ /**
+ * do some remove operations on adjMap after receiving the info about dead Vertex
+ */
+ public void responseToDeadVertex(Iterator<MessageWritable> msgIterator){
+ while (msgIterator.hasNext()) {
+ incomingMsg = msgIterator.next();
+ if(incomingMsg.getFlag() == AdjMessage.FROMFF){
+ //remove incomingMsg.getSourceId from RR positionList
+ posIterator = getVertexValue().getRRList().iterator();
+ while(posIterator.hasNext()){
+ pos = posIterator.next();
+ if(pos.equals(incomingMsg.getSourceVertexId())){
+ posIterator.remove();
+ break;
+ }
+ }
+ } else if(incomingMsg.getFlag() == AdjMessage.FROMFR){
+ //remove incomingMsg.getSourceId from FR positionList
+ posIterator = getVertexValue().getFRList().iterator();
+ while(posIterator.hasNext()){
+ pos = posIterator.next();
+ if(pos.equals(incomingMsg.getSourceVertexId())){
+ posIterator.remove();
+ break;
+ }
+ }
+ } else if(incomingMsg.getFlag() == AdjMessage.FROMRF){
+ //remove incomingMsg.getSourceId from RF positionList
+ posIterator = getVertexValue().getRFList().iterator();
+ while(posIterator.hasNext()){
+ pos = posIterator.next();
+ if(pos.equals(incomingMsg.getSourceVertexId())){
+ posIterator.remove();
+ break;
+ }
+ }
+ } else{ //incomingMsg.getFlag() == AdjMessage.FROMRR
+ //remove incomingMsg.getSourceId from FF positionList
+ posIterator = getVertexValue().getFFList().iterator();
+ while(posIterator.hasNext()){
+ pos = posIterator.next();
+ if(pos.equals(incomingMsg.getSourceVertexId())){
+ posIterator.remove();
+ break;
+ }
+ }
+ }
+ }
+ }
+
@Override
public void compute(Iterator<MessageWritable> msgIterator) {
}
diff --git a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/tipremove/TipRemoveVertex.java b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/tipremove/TipRemoveVertex.java
index dec2d48..26a66e8 100644
--- a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/tipremove/TipRemoveVertex.java
+++ b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/tipremove/TipRemoveVertex.java
@@ -1,16 +1,15 @@
package edu.uci.ics.genomix.pregelix.operator.tipremove;
import java.util.Iterator;
-import org.apache.hadoop.io.NullWritable;
import edu.uci.ics.genomix.type.PositionWritable;
-import edu.uci.ics.pregelix.api.graph.Vertex;
import edu.uci.ics.pregelix.api.job.PregelixJob;
import edu.uci.ics.genomix.pregelix.client.Client;
import edu.uci.ics.genomix.pregelix.format.DataCleanInputFormat;
import edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat;
import edu.uci.ics.genomix.pregelix.io.MessageWritable;
import edu.uci.ics.genomix.pregelix.io.VertexValueWritable;
+import edu.uci.ics.genomix.pregelix.operator.pathmerge.BasicPathMergeVertex;
import edu.uci.ics.genomix.pregelix.type.AdjMessage;
import edu.uci.ics.genomix.pregelix.util.VertexUtil;
@@ -46,19 +45,9 @@
* Remove tip or single node when l > constant
*/
public class TipRemoveVertex extends
- Vertex<PositionWritable, VertexValueWritable, NullWritable, MessageWritable> {
- public static final String KMER_SIZE = "TipRemoveVertex.kmerSize";
+ BasicPathMergeVertex {
public static final String LENGTH = "TipRemoveVertex.length";
- public static int kmerSize = -1;
private int length = -1;
-
- private MessageWritable incomingMsg = new MessageWritable();
- private MessageWritable outgoingMsg = new MessageWritable();
-
- private Iterator<PositionWritable> iterator;
- private PositionWritable pos = new PositionWritable();
- private PositionWritable destVertexId = new PositionWritable();
- private Iterator<PositionWritable> posIterator;
/**
* initiate kmerSize, length
@@ -70,25 +59,6 @@
length = getContext().getConfiguration().getInt(LENGTH, kmerSize); //kmerSize + 5
outgoingMsg.reset();
}
-
- /**
- * get destination vertex
- */
- public PositionWritable getNextDestVertexId(VertexValueWritable value) {
- if(value.getFFList().getCountOfPosition() > 0) // #FFList() > 0
- posIterator = value.getFFList().iterator();
- else // #FRList() > 0
- posIterator = value.getFRList().iterator();
- return posIterator.next();
- }
-
- public PositionWritable getPreDestVertexId(VertexValueWritable value) {
- if(value.getRFList().getCountOfPosition() > 0) // #RFList() > 0
- posIterator = value.getRFList().iterator();
- else // #RRList() > 0
- posIterator = value.getRRList().iterator();
- return posIterator.next();
- }
@Override
public void compute(Iterator<MessageWritable> msgIterator) {
@@ -124,50 +94,7 @@
}
}
else if(getSuperstep() == 2){
- while (msgIterator.hasNext()) {
- incomingMsg = msgIterator.next();
- if(incomingMsg.getFlag() == AdjMessage.FROMFF){
- //remove incomingMsg.getSourceId from RR positionList
- iterator = getVertexValue().getRRList().iterator();
- while(iterator.hasNext()){
- pos = iterator.next();
- if(pos.equals(incomingMsg.getSourceVertexId())){
- iterator.remove();
- break;
- }
- }
- } else if(incomingMsg.getFlag() == AdjMessage.FROMFR){
- //remove incomingMsg.getSourceId from RF positionList
- iterator = getVertexValue().getRFList().iterator();
- while(iterator.hasNext()){
- pos = iterator.next();
- if(pos.equals(incomingMsg.getSourceVertexId())){
- iterator.remove();
- break;
- }
- }
- } else if(incomingMsg.getFlag() == AdjMessage.FROMRF){
- //remove incomingMsg.getSourceId from FR positionList
- iterator = getVertexValue().getFRList().iterator();
- while(iterator.hasNext()){
- pos = iterator.next();
- if(pos.equals(incomingMsg.getSourceVertexId())){
- iterator.remove();
- break;
- }
- }
- } else{ //incomingMsg.getFlag() == AdjMessage.FROMRR
- //remove incomingMsg.getSourceId from FF positionList
- iterator = getVertexValue().getFFList().iterator();
- while(iterator.hasNext()){
- pos = iterator.next();
- if(pos.equals(incomingMsg.getSourceVertexId())){
- iterator.remove();
- break;
- }
- }
- }
- }
+ responseToDeadVertex(msgIterator);
}
voteToHalt();
}
diff --git a/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobGen/JobGenerator.java b/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobGen/JobGenerator.java
index 0a366db..62e5725 100644
--- a/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobGen/JobGenerator.java
+++ b/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobGen/JobGenerator.java
@@ -83,7 +83,7 @@
private static void generateP4ForMergeGraphJob(String jobName, String outputPath) throws IOException {
PregelixJob job = new PregelixJob(jobName);
job.setVertexClass(P4ForPathMergeVertex.class);
- job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class);
+ job.setVertexInputFormatClass(DataCleanInputFormat.class);
job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
job.setDynamicVertexValueSize(true);
job.setOutputKeyClass(PositionWritable.class);
@@ -201,15 +201,15 @@
public static void main(String[] args) throws IOException {
//genNaiveAlgorithmForMergeGraph();
- genLogAlgorithmForMergeGraph();
+ //genLogAlgorithmForMergeGraph();
//genP3ForMergeGraph();
- //genTipAddGraph();
- //genTipRemoveGraph();
- //genBridgeAddGraph();
- //genBridgeRemoveGraph();
- //genBubbleAddGraph();
- //genBubbleMergeGraph();
- //genP4ForMergeGraph();
+ genTipAddGraph();
+ genTipRemoveGraph();
+ genBridgeAddGraph();
+ genBridgeRemoveGraph();
+ genBubbleAddGraph();
+ genBubbleMergeGraph();
+ genP4ForMergeGraph();
}
}
diff --git a/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/PathMergeSmallTestCase.java b/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/BasicSmallTestCase.java
similarity index 94%
rename from genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/PathMergeSmallTestCase.java
rename to genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/BasicSmallTestCase.java
index 4405134..e138348 100644
--- a/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/PathMergeSmallTestCase.java
+++ b/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/BasicSmallTestCase.java
@@ -29,7 +29,7 @@
import edu.uci.ics.pregelix.core.driver.Driver;
import edu.uci.ics.pregelix.core.util.PregelixHyracksIntegrationUtil;
-public class PathMergeSmallTestCase extends TestCase {
+public class BasicSmallTestCase extends TestCase {
private final PregelixJob job;
private final String resultFileDir;
private final String textFileDir;
@@ -37,7 +37,7 @@
private final Driver driver = new Driver(this.getClass());
private final FileSystem dfs;
- public PathMergeSmallTestCase(String hadoopConfPath, String jobName, String jobFile, FileSystem dfs,
+ public BasicSmallTestCase(String hadoopConfPath, String jobName, String jobFile, FileSystem dfs,
String hdfsInput, String resultFile, String textFile) throws Exception {
super("test");
this.jobFile = jobFile;
diff --git a/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/BridgeRemoveSmallTestSuite.java b/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/BridgeRemoveSmallTestSuite.java
new file mode 100644
index 0000000..eee495c
--- /dev/null
+++ b/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/BridgeRemoveSmallTestSuite.java
@@ -0,0 +1,210 @@
+/*
+ * Copyright 2009-2010 by The Regents of the University of California
+ * Licensed 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 from
+ *
+ * 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 edu.uci.ics.genomix.pregelix.JobRun;
+
+import java.io.BufferedReader;
+import java.io.DataOutputStream;
+import java.io.File;
+import java.io.FileNotFoundException;
+import java.io.FileOutputStream;
+import java.io.FileReader;
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.logging.Logger;
+
+import junit.framework.Test;
+import junit.framework.TestResult;
+import junit.framework.TestSuite;
+
+import org.apache.commons.io.FileUtils;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hdfs.MiniDFSCluster;
+import org.apache.hadoop.mapred.JobConf;
+
+import edu.uci.ics.pregelix.core.jobgen.clusterconfig.ClusterConfig;
+import edu.uci.ics.pregelix.core.util.PregelixHyracksIntegrationUtil;
+
+@SuppressWarnings("deprecation")
+public class BridgeRemoveSmallTestSuite extends TestSuite {
+ private static final Logger LOGGER = Logger.getLogger(BridgeRemoveSmallTestSuite.class.getName());
+
+ public static final String PreFix = "data/input"; //"graphbuildresult";
+ public static final String[] TestDir = { PreFix + File.separator
+ + "pathmerge"};/*, PreFix + File.separator
+ /*+ "CyclePath"};, PreFix + File.separator
+ + "SimplePath", PreFix + File.separator
+ + "SinglePath", PreFix + File.separator
+ + "TreePath"};*/
+ /* + "2", PreFix + File.separator + "3", PreFix + File.separator + "4", PreFix + File.separator + "5",
+ PreFix + File.separator + "6", PreFix + File.separator + "7", PreFix + File.separator + "8",
+ PreFix + File.separator + "9", PreFix + File.separator + "TwoKmer", PreFix + File.separator + "ThreeKmer",
+ PreFix + File.separator + "SinglePath", PreFix + File.separator + "SimplePath",
+ PreFix + File.separator + "Path", PreFix + File.separator + "BridgePath",
+ PreFix + File.separator + "CyclePath", PreFix + File.separator + "RingPath",
+ PreFix + File.separator + "LongPath", PreFix + File.separator + "TreePath" };*/
+ private static final String ACTUAL_RESULT_DIR = "actual";
+ private static final String PATH_TO_HADOOP_CONF = "src/test/resources/hadoop/conf";
+ private static final String PATH_TO_CLUSTER_STORE = "src/test/resources/cluster/stores.properties";
+ private static final String PATH_TO_CLUSTER_PROPERTIES = "src/test/resources/cluster/cluster.properties";
+ private static final String PATH_TO_JOBS = "src/test/resources/jobs/";
+ private static final String PATH_TO_ONLY = "src/test/resources/only.txt";
+
+ public static final String HDFS_INPUTPATH = "/PathTestSet";
+
+ private static final String HADOOP_CONF_PATH = ACTUAL_RESULT_DIR + File.separator + "conf.xml";
+ private MiniDFSCluster dfsCluster;
+
+ private JobConf conf = new JobConf();
+ private int numberOfNC = 2;
+
+ public void setUp() throws Exception {
+ ClusterConfig.setStorePath(PATH_TO_CLUSTER_STORE);
+ ClusterConfig.setClusterPropertiesPath(PATH_TO_CLUSTER_PROPERTIES);
+ cleanupStores();
+ PregelixHyracksIntegrationUtil.init("src/test/resources/topology.xml");
+ LOGGER.info("Hyracks mini-cluster started");
+ FileUtils.forceMkdir(new File(ACTUAL_RESULT_DIR));
+ FileUtils.cleanDirectory(new File(ACTUAL_RESULT_DIR));
+ startHDFS();
+ }
+
+ private void startHDFS() throws IOException {
+ conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/core-site.xml"));
+ conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/mapred-site.xml"));
+ conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/hdfs-site.xml"));
+ FileSystem lfs = FileSystem.getLocal(new Configuration());
+ lfs.delete(new Path("build"), true);
+ System.setProperty("hadoop.log.dir", "logs");
+ dfsCluster = new MiniDFSCluster(conf, numberOfNC, true, null);
+ FileSystem dfs = FileSystem.get(conf);
+
+ for (String testDir : TestDir) {
+ File src = new File(testDir);
+ Path dest = new Path(HDFS_INPUTPATH + File.separator + src.getName());
+ dfs.mkdirs(dest);
+ //src.listFiles()
+ //src.listFiles((FilenameFilter)(new WildcardFileFilter("part*")))
+ for (File f : src.listFiles()) {
+ dfs.copyFromLocalFile(new Path(f.getAbsolutePath()), dest);
+ }
+ }
+
+ DataOutputStream confOutput = new DataOutputStream(new FileOutputStream(new File(HADOOP_CONF_PATH)));
+ conf.writeXml(confOutput);
+ confOutput.flush();
+ confOutput.close();
+ }
+
+ private void cleanupStores() throws IOException {
+ FileUtils.forceMkdir(new File("teststore"));
+ FileUtils.forceMkdir(new File("build"));
+ FileUtils.cleanDirectory(new File("teststore"));
+ FileUtils.cleanDirectory(new File("build"));
+ }
+
+ /**
+ * cleanup hdfs cluster
+ */
+ private void cleanupHDFS() throws Exception {
+ dfsCluster.shutdown();
+ }
+
+ public void tearDown() throws Exception {
+ PregelixHyracksIntegrationUtil.deinit();
+ LOGGER.info("Hyracks mini-cluster shut down");
+ cleanupHDFS();
+ }
+
+ public static Test suite() throws Exception {
+ List<String> onlys = getFileList(PATH_TO_ONLY);
+ File testData = new File(PATH_TO_JOBS);
+ File[] queries = testData.listFiles();
+ BridgeRemoveSmallTestSuite testSuite = new BridgeRemoveSmallTestSuite();
+ testSuite.setUp();
+ boolean onlyEnabled = false;
+ FileSystem dfs = FileSystem.get(testSuite.conf);
+
+ if (onlys.size() > 0) {
+ onlyEnabled = true;
+ }
+
+ for (File qFile : queries) {
+ if (qFile.isFile()) {
+ if (onlyEnabled && !isInList(onlys, qFile.getName())) {
+ continue;
+ } else {
+ for (String testPathStr : TestDir) {
+ File testDir = new File(testPathStr);
+ String resultFileName = ACTUAL_RESULT_DIR + File.separator + jobExtToResExt(qFile.getName())
+ + File.separator + "bin" + File.separator + testDir.getName();
+ String textFileName = ACTUAL_RESULT_DIR + File.separator + jobExtToResExt(qFile.getName())
+ + File.separator + "txt" + File.separator + testDir.getName();
+ testSuite.addTest(new BasicSmallTestCase(HADOOP_CONF_PATH, qFile.getName(), qFile
+ .getAbsolutePath().toString(), dfs,
+ HDFS_INPUTPATH + File.separator + testDir.getName(), resultFileName, textFileName));
+ }
+ }
+ }
+ }
+ return testSuite;
+ }
+
+ /**
+ * Runs the tests and collects their result in a TestResult.
+ */
+ @Override
+ public void run(TestResult result) {
+ try {
+ int testCount = countTestCases();
+ for (int i = 0; i < testCount; i++) {
+ // cleanupStores();
+ Test each = this.testAt(i);
+ if (result.shouldStop())
+ break;
+ runTest(each, result);
+ }
+ tearDown();
+ } catch (Exception e) {
+ throw new IllegalStateException(e);
+ }
+ }
+
+ protected static List<String> getFileList(String ignorePath) throws FileNotFoundException, IOException {
+ BufferedReader reader = new BufferedReader(new FileReader(ignorePath));
+ String s = null;
+ List<String> ignores = new ArrayList<String>();
+ while ((s = reader.readLine()) != null) {
+ ignores.add(s);
+ }
+ reader.close();
+ return ignores;
+ }
+
+ private static String jobExtToResExt(String fname) {
+ int dot = fname.lastIndexOf('.');
+ return fname.substring(0, dot);
+ }
+
+ private static boolean isInList(List<String> onlys, String name) {
+ for (String only : onlys)
+ if (name.indexOf(only) >= 0)
+ return true;
+ return false;
+ }
+
+}
diff --git a/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/BubbleMergeSmallTestSuite.java b/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/BubbleMergeSmallTestSuite.java
new file mode 100644
index 0000000..9e98cb6
--- /dev/null
+++ b/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/BubbleMergeSmallTestSuite.java
@@ -0,0 +1,210 @@
+/*
+ * Copyright 2009-2010 by The Regents of the University of California
+ * Licensed 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 from
+ *
+ * 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 edu.uci.ics.genomix.pregelix.JobRun;
+
+import java.io.BufferedReader;
+import java.io.DataOutputStream;
+import java.io.File;
+import java.io.FileNotFoundException;
+import java.io.FileOutputStream;
+import java.io.FileReader;
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.logging.Logger;
+
+import junit.framework.Test;
+import junit.framework.TestResult;
+import junit.framework.TestSuite;
+
+import org.apache.commons.io.FileUtils;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hdfs.MiniDFSCluster;
+import org.apache.hadoop.mapred.JobConf;
+
+import edu.uci.ics.pregelix.core.jobgen.clusterconfig.ClusterConfig;
+import edu.uci.ics.pregelix.core.util.PregelixHyracksIntegrationUtil;
+
+@SuppressWarnings("deprecation")
+public class BubbleMergeSmallTestSuite extends TestSuite {
+ private static final Logger LOGGER = Logger.getLogger(BubbleMergeSmallTestSuite.class.getName());
+
+ public static final String PreFix = "data/input"; //"graphbuildresult";
+ public static final String[] TestDir = { PreFix + File.separator
+ + "pathmerge"};/*, PreFix + File.separator
+ /*+ "CyclePath"};, PreFix + File.separator
+ + "SimplePath", PreFix + File.separator
+ + "SinglePath", PreFix + File.separator
+ + "TreePath"};*/
+ /* + "2", PreFix + File.separator + "3", PreFix + File.separator + "4", PreFix + File.separator + "5",
+ PreFix + File.separator + "6", PreFix + File.separator + "7", PreFix + File.separator + "8",
+ PreFix + File.separator + "9", PreFix + File.separator + "TwoKmer", PreFix + File.separator + "ThreeKmer",
+ PreFix + File.separator + "SinglePath", PreFix + File.separator + "SimplePath",
+ PreFix + File.separator + "Path", PreFix + File.separator + "BridgePath",
+ PreFix + File.separator + "CyclePath", PreFix + File.separator + "RingPath",
+ PreFix + File.separator + "LongPath", PreFix + File.separator + "TreePath" };*/
+ private static final String ACTUAL_RESULT_DIR = "actual";
+ private static final String PATH_TO_HADOOP_CONF = "src/test/resources/hadoop/conf";
+ private static final String PATH_TO_CLUSTER_STORE = "src/test/resources/cluster/stores.properties";
+ private static final String PATH_TO_CLUSTER_PROPERTIES = "src/test/resources/cluster/cluster.properties";
+ private static final String PATH_TO_JOBS = "src/test/resources/jobs/";
+ private static final String PATH_TO_ONLY = "src/test/resources/only.txt";
+
+ public static final String HDFS_INPUTPATH = "/PathTestSet";
+
+ private static final String HADOOP_CONF_PATH = ACTUAL_RESULT_DIR + File.separator + "conf.xml";
+ private MiniDFSCluster dfsCluster;
+
+ private JobConf conf = new JobConf();
+ private int numberOfNC = 2;
+
+ public void setUp() throws Exception {
+ ClusterConfig.setStorePath(PATH_TO_CLUSTER_STORE);
+ ClusterConfig.setClusterPropertiesPath(PATH_TO_CLUSTER_PROPERTIES);
+ cleanupStores();
+ PregelixHyracksIntegrationUtil.init("src/test/resources/topology.xml");
+ LOGGER.info("Hyracks mini-cluster started");
+ FileUtils.forceMkdir(new File(ACTUAL_RESULT_DIR));
+ FileUtils.cleanDirectory(new File(ACTUAL_RESULT_DIR));
+ startHDFS();
+ }
+
+ private void startHDFS() throws IOException {
+ conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/core-site.xml"));
+ conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/mapred-site.xml"));
+ conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/hdfs-site.xml"));
+ FileSystem lfs = FileSystem.getLocal(new Configuration());
+ lfs.delete(new Path("build"), true);
+ System.setProperty("hadoop.log.dir", "logs");
+ dfsCluster = new MiniDFSCluster(conf, numberOfNC, true, null);
+ FileSystem dfs = FileSystem.get(conf);
+
+ for (String testDir : TestDir) {
+ File src = new File(testDir);
+ Path dest = new Path(HDFS_INPUTPATH + File.separator + src.getName());
+ dfs.mkdirs(dest);
+ //src.listFiles()
+ //src.listFiles((FilenameFilter)(new WildcardFileFilter("part*")))
+ for (File f : src.listFiles()) {
+ dfs.copyFromLocalFile(new Path(f.getAbsolutePath()), dest);
+ }
+ }
+
+ DataOutputStream confOutput = new DataOutputStream(new FileOutputStream(new File(HADOOP_CONF_PATH)));
+ conf.writeXml(confOutput);
+ confOutput.flush();
+ confOutput.close();
+ }
+
+ private void cleanupStores() throws IOException {
+ FileUtils.forceMkdir(new File("teststore"));
+ FileUtils.forceMkdir(new File("build"));
+ FileUtils.cleanDirectory(new File("teststore"));
+ FileUtils.cleanDirectory(new File("build"));
+ }
+
+ /**
+ * cleanup hdfs cluster
+ */
+ private void cleanupHDFS() throws Exception {
+ dfsCluster.shutdown();
+ }
+
+ public void tearDown() throws Exception {
+ PregelixHyracksIntegrationUtil.deinit();
+ LOGGER.info("Hyracks mini-cluster shut down");
+ cleanupHDFS();
+ }
+
+ public static Test suite() throws Exception {
+ List<String> onlys = getFileList(PATH_TO_ONLY);
+ File testData = new File(PATH_TO_JOBS);
+ File[] queries = testData.listFiles();
+ BubbleMergeSmallTestSuite testSuite = new BubbleMergeSmallTestSuite();
+ testSuite.setUp();
+ boolean onlyEnabled = false;
+ FileSystem dfs = FileSystem.get(testSuite.conf);
+
+ if (onlys.size() > 0) {
+ onlyEnabled = true;
+ }
+
+ for (File qFile : queries) {
+ if (qFile.isFile()) {
+ if (onlyEnabled && !isInList(onlys, qFile.getName())) {
+ continue;
+ } else {
+ for (String testPathStr : TestDir) {
+ File testDir = new File(testPathStr);
+ String resultFileName = ACTUAL_RESULT_DIR + File.separator + jobExtToResExt(qFile.getName())
+ + File.separator + "bin" + File.separator + testDir.getName();
+ String textFileName = ACTUAL_RESULT_DIR + File.separator + jobExtToResExt(qFile.getName())
+ + File.separator + "txt" + File.separator + testDir.getName();
+ testSuite.addTest(new BasicSmallTestCase(HADOOP_CONF_PATH, qFile.getName(), qFile
+ .getAbsolutePath().toString(), dfs,
+ HDFS_INPUTPATH + File.separator + testDir.getName(), resultFileName, textFileName));
+ }
+ }
+ }
+ }
+ return testSuite;
+ }
+
+ /**
+ * Runs the tests and collects their result in a TestResult.
+ */
+ @Override
+ public void run(TestResult result) {
+ try {
+ int testCount = countTestCases();
+ for (int i = 0; i < testCount; i++) {
+ // cleanupStores();
+ Test each = this.testAt(i);
+ if (result.shouldStop())
+ break;
+ runTest(each, result);
+ }
+ tearDown();
+ } catch (Exception e) {
+ throw new IllegalStateException(e);
+ }
+ }
+
+ protected static List<String> getFileList(String ignorePath) throws FileNotFoundException, IOException {
+ BufferedReader reader = new BufferedReader(new FileReader(ignorePath));
+ String s = null;
+ List<String> ignores = new ArrayList<String>();
+ while ((s = reader.readLine()) != null) {
+ ignores.add(s);
+ }
+ reader.close();
+ return ignores;
+ }
+
+ private static String jobExtToResExt(String fname) {
+ int dot = fname.lastIndexOf('.');
+ return fname.substring(0, dot);
+ }
+
+ private static boolean isInList(List<String> onlys, String name) {
+ for (String only : onlys)
+ if (name.indexOf(only) >= 0)
+ return true;
+ return false;
+ }
+
+}
diff --git a/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/PathMergeSmallTestSuite.java b/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/PathMergeSmallTestSuite.java
index cd81a97..857e4c3 100644
--- a/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/PathMergeSmallTestSuite.java
+++ b/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/PathMergeSmallTestSuite.java
@@ -43,9 +43,9 @@
public class PathMergeSmallTestSuite extends TestSuite {
private static final Logger LOGGER = Logger.getLogger(PathMergeSmallTestSuite.class.getName());
- public static final String PreFix = "data/input"; //"graphbuildresult";
+ public static final String PreFix = "data/actual/tipadd"; //"graphbuildresult";
public static final String[] TestDir = { PreFix + File.separator
- + "pathmerge"};/*, PreFix + File.separator
+ + "TipAddGraph/bin/read"};/*, PreFix + File.separator
/*+ "CyclePath"};, PreFix + File.separator
+ "SimplePath", PreFix + File.separator
+ "SinglePath", PreFix + File.separator
@@ -57,12 +57,12 @@
PreFix + File.separator + "Path", PreFix + File.separator + "BridgePath",
PreFix + File.separator + "CyclePath", PreFix + File.separator + "RingPath",
PreFix + File.separator + "LongPath", PreFix + File.separator + "TreePath" };*/
- private static final String ACTUAL_RESULT_DIR = "actual";
+ private static final String ACTUAL_RESULT_DIR = "data/actual/pathmerge";
private static final String PATH_TO_HADOOP_CONF = "src/test/resources/hadoop/conf";
private static final String PATH_TO_CLUSTER_STORE = "src/test/resources/cluster/stores.properties";
private static final String PATH_TO_CLUSTER_PROPERTIES = "src/test/resources/cluster/cluster.properties";
private static final String PATH_TO_JOBS = "src/test/resources/jobs/";
- private static final String PATH_TO_ONLY = "src/test/resources/only.txt";
+ private static final String PATH_TO_ONLY = "src/test/resources/only_pathmerge.txt";
public static final String HDFS_INPUTPATH = "/PathTestSet";
@@ -154,7 +154,7 @@
+ File.separator + "bin" + File.separator + testDir.getName();
String textFileName = ACTUAL_RESULT_DIR + File.separator + jobExtToResExt(qFile.getName())
+ File.separator + "txt" + File.separator + testDir.getName();
- testSuite.addTest(new PathMergeSmallTestCase(HADOOP_CONF_PATH, qFile.getName(), qFile
+ testSuite.addTest(new BasicSmallTestCase(HADOOP_CONF_PATH, qFile.getName(), qFile
.getAbsolutePath().toString(), dfs,
HDFS_INPUTPATH + File.separator + testDir.getName(), resultFileName, textFileName));
}
diff --git a/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/TipAddSmallTestSuite.java b/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/TipAddSmallTestSuite.java
new file mode 100644
index 0000000..f4456ce
--- /dev/null
+++ b/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/TipAddSmallTestSuite.java
@@ -0,0 +1,210 @@
+/*
+ * Copyright 2009-2010 by The Regents of the University of California
+ * Licensed 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 from
+ *
+ * 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 edu.uci.ics.genomix.pregelix.JobRun;
+
+import java.io.BufferedReader;
+import java.io.DataOutputStream;
+import java.io.File;
+import java.io.FileNotFoundException;
+import java.io.FileOutputStream;
+import java.io.FileReader;
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.logging.Logger;
+
+import junit.framework.Test;
+import junit.framework.TestResult;
+import junit.framework.TestSuite;
+
+import org.apache.commons.io.FileUtils;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hdfs.MiniDFSCluster;
+import org.apache.hadoop.mapred.JobConf;
+
+import edu.uci.ics.pregelix.core.jobgen.clusterconfig.ClusterConfig;
+import edu.uci.ics.pregelix.core.util.PregelixHyracksIntegrationUtil;
+
+@SuppressWarnings("deprecation")
+public class TipAddSmallTestSuite extends TestSuite {
+ private static final Logger LOGGER = Logger.getLogger(TipAddSmallTestSuite.class.getName());
+
+ public static final String PreFix = "data/input"; //"graphbuildresult";
+ public static final String[] TestDir = { PreFix + File.separator
+ + "read"};/*, PreFix + File.separator
+ /*+ "CyclePath"};, PreFix + File.separator
+ + "SimplePath", PreFix + File.separator
+ + "SinglePath", PreFix + File.separator
+ + "TreePath"};*/
+ /* + "2", PreFix + File.separator + "3", PreFix + File.separator + "4", PreFix + File.separator + "5",
+ PreFix + File.separator + "6", PreFix + File.separator + "7", PreFix + File.separator + "8",
+ PreFix + File.separator + "9", PreFix + File.separator + "TwoKmer", PreFix + File.separator + "ThreeKmer",
+ PreFix + File.separator + "SinglePath", PreFix + File.separator + "SimplePath",
+ PreFix + File.separator + "Path", PreFix + File.separator + "BridgePath",
+ PreFix + File.separator + "CyclePath", PreFix + File.separator + "RingPath",
+ PreFix + File.separator + "LongPath", PreFix + File.separator + "TreePath" };*/
+ private static final String ACTUAL_RESULT_DIR = "data/actual/tipadd";
+ private static final String PATH_TO_HADOOP_CONF = "src/test/resources/hadoop/conf";
+ private static final String PATH_TO_CLUSTER_STORE = "src/test/resources/cluster/stores.properties";
+ private static final String PATH_TO_CLUSTER_PROPERTIES = "src/test/resources/cluster/cluster.properties";
+ private static final String PATH_TO_JOBS = "src/test/resources/jobs/";
+ private static final String PATH_TO_ONLY = "src/test/resources/only_tipadd.txt";
+
+ public static final String HDFS_INPUTPATH = "/PathTestSet";
+
+ private static final String HADOOP_CONF_PATH = ACTUAL_RESULT_DIR + File.separator + "conf.xml";
+ private MiniDFSCluster dfsCluster;
+
+ private JobConf conf = new JobConf();
+ private int numberOfNC = 2;
+
+ public void setUp() throws Exception {
+ ClusterConfig.setStorePath(PATH_TO_CLUSTER_STORE);
+ ClusterConfig.setClusterPropertiesPath(PATH_TO_CLUSTER_PROPERTIES);
+ cleanupStores();
+ PregelixHyracksIntegrationUtil.init("src/test/resources/topology.xml");
+ LOGGER.info("Hyracks mini-cluster started");
+ FileUtils.forceMkdir(new File(ACTUAL_RESULT_DIR));
+ FileUtils.cleanDirectory(new File(ACTUAL_RESULT_DIR));
+ startHDFS();
+ }
+
+ private void startHDFS() throws IOException {
+ conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/core-site.xml"));
+ conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/mapred-site.xml"));
+ conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/hdfs-site.xml"));
+ FileSystem lfs = FileSystem.getLocal(new Configuration());
+ lfs.delete(new Path("build"), true);
+ System.setProperty("hadoop.log.dir", "logs");
+ dfsCluster = new MiniDFSCluster(conf, numberOfNC, true, null);
+ FileSystem dfs = FileSystem.get(conf);
+
+ for (String testDir : TestDir) {
+ File src = new File(testDir);
+ Path dest = new Path(HDFS_INPUTPATH + File.separator + src.getName());
+ dfs.mkdirs(dest);
+ //src.listFiles()
+ //src.listFiles((FilenameFilter)(new WildcardFileFilter("part*")))
+ for (File f : src.listFiles()) {
+ dfs.copyFromLocalFile(new Path(f.getAbsolutePath()), dest);
+ }
+ }
+
+ DataOutputStream confOutput = new DataOutputStream(new FileOutputStream(new File(HADOOP_CONF_PATH)));
+ conf.writeXml(confOutput);
+ confOutput.flush();
+ confOutput.close();
+ }
+
+ private void cleanupStores() throws IOException {
+ FileUtils.forceMkdir(new File("teststore"));
+ FileUtils.forceMkdir(new File("build"));
+ FileUtils.cleanDirectory(new File("teststore"));
+ FileUtils.cleanDirectory(new File("build"));
+ }
+
+ /**
+ * cleanup hdfs cluster
+ */
+ private void cleanupHDFS() throws Exception {
+ dfsCluster.shutdown();
+ }
+
+ public void tearDown() throws Exception {
+ PregelixHyracksIntegrationUtil.deinit();
+ LOGGER.info("Hyracks mini-cluster shut down");
+ cleanupHDFS();
+ }
+
+ public static Test suite() throws Exception {
+ List<String> onlys = getFileList(PATH_TO_ONLY);
+ File testData = new File(PATH_TO_JOBS);
+ File[] queries = testData.listFiles();
+ TipAddSmallTestSuite testSuite = new TipAddSmallTestSuite();
+ testSuite.setUp();
+ boolean onlyEnabled = false;
+ FileSystem dfs = FileSystem.get(testSuite.conf);
+
+ if (onlys.size() > 0) {
+ onlyEnabled = true;
+ }
+
+ for (File qFile : queries) {
+ if (qFile.isFile()) {
+ if (onlyEnabled && !isInList(onlys, qFile.getName())) {
+ continue;
+ } else {
+ for (String testPathStr : TestDir) {
+ File testDir = new File(testPathStr);
+ String resultFileName = ACTUAL_RESULT_DIR + File.separator + jobExtToResExt(qFile.getName())
+ + File.separator + "bin" + File.separator + testDir.getName();
+ String textFileName = ACTUAL_RESULT_DIR + File.separator + jobExtToResExt(qFile.getName())
+ + File.separator + "txt" + File.separator + testDir.getName();
+ testSuite.addTest(new BasicSmallTestCase(HADOOP_CONF_PATH, qFile.getName(), qFile
+ .getAbsolutePath().toString(), dfs,
+ HDFS_INPUTPATH + File.separator + testDir.getName(), resultFileName, textFileName));
+ }
+ }
+ }
+ }
+ return testSuite;
+ }
+
+ /**
+ * Runs the tests and collects their result in a TestResult.
+ */
+ @Override
+ public void run(TestResult result) {
+ try {
+ int testCount = countTestCases();
+ for (int i = 0; i < testCount; i++) {
+ // cleanupStores();
+ Test each = this.testAt(i);
+ if (result.shouldStop())
+ break;
+ runTest(each, result);
+ }
+ tearDown();
+ } catch (Exception e) {
+ throw new IllegalStateException(e);
+ }
+ }
+
+ protected static List<String> getFileList(String ignorePath) throws FileNotFoundException, IOException {
+ BufferedReader reader = new BufferedReader(new FileReader(ignorePath));
+ String s = null;
+ List<String> ignores = new ArrayList<String>();
+ while ((s = reader.readLine()) != null) {
+ ignores.add(s);
+ }
+ reader.close();
+ return ignores;
+ }
+
+ private static String jobExtToResExt(String fname) {
+ int dot = fname.lastIndexOf('.');
+ return fname.substring(0, dot);
+ }
+
+ private static boolean isInList(List<String> onlys, String name) {
+ for (String only : onlys)
+ if (name.indexOf(only) >= 0)
+ return true;
+ return false;
+ }
+
+}
diff --git a/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/TipRemoveSmallTestSuite.java b/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/TipRemoveSmallTestSuite.java
new file mode 100644
index 0000000..5ccfca5
--- /dev/null
+++ b/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/TipRemoveSmallTestSuite.java
@@ -0,0 +1,210 @@
+/*
+ * Copyright 2009-2010 by The Regents of the University of California
+ * Licensed 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 from
+ *
+ * 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 edu.uci.ics.genomix.pregelix.JobRun;
+
+import java.io.BufferedReader;
+import java.io.DataOutputStream;
+import java.io.File;
+import java.io.FileNotFoundException;
+import java.io.FileOutputStream;
+import java.io.FileReader;
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.logging.Logger;
+
+import junit.framework.Test;
+import junit.framework.TestResult;
+import junit.framework.TestSuite;
+
+import org.apache.commons.io.FileUtils;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hdfs.MiniDFSCluster;
+import org.apache.hadoop.mapred.JobConf;
+
+import edu.uci.ics.pregelix.core.jobgen.clusterconfig.ClusterConfig;
+import edu.uci.ics.pregelix.core.util.PregelixHyracksIntegrationUtil;
+
+@SuppressWarnings("deprecation")
+public class TipRemoveSmallTestSuite extends TestSuite {
+ private static final Logger LOGGER = Logger.getLogger(TipRemoveSmallTestSuite.class.getName());
+
+ public static final String PreFix = "data/actual/tipadd"; //"graphbuildresult";
+ public static final String[] TestDir = { PreFix + File.separator
+ + "TipAddGraph/bin/read"};/*, PreFix + File.separator
+ /*+ "CyclePath"};, PreFix + File.separator
+ + "SimplePath", PreFix + File.separator
+ + "SinglePath", PreFix + File.separator
+ + "TreePath"};*/
+ /* + "2", PreFix + File.separator + "3", PreFix + File.separator + "4", PreFix + File.separator + "5",
+ PreFix + File.separator + "6", PreFix + File.separator + "7", PreFix + File.separator + "8",
+ PreFix + File.separator + "9", PreFix + File.separator + "TwoKmer", PreFix + File.separator + "ThreeKmer",
+ PreFix + File.separator + "SinglePath", PreFix + File.separator + "SimplePath",
+ PreFix + File.separator + "Path", PreFix + File.separator + "BridgePath",
+ PreFix + File.separator + "CyclePath", PreFix + File.separator + "RingPath",
+ PreFix + File.separator + "LongPath", PreFix + File.separator + "TreePath" };*/
+ private static final String ACTUAL_RESULT_DIR = "data/actual/tipremove";
+ private static final String PATH_TO_HADOOP_CONF = "src/test/resources/hadoop/conf";
+ private static final String PATH_TO_CLUSTER_STORE = "src/test/resources/cluster/stores.properties";
+ private static final String PATH_TO_CLUSTER_PROPERTIES = "src/test/resources/cluster/cluster.properties";
+ private static final String PATH_TO_JOBS = "src/test/resources/jobs/";
+ private static final String PATH_TO_ONLY = "src/test/resources/only_tipremove.txt";
+
+ public static final String HDFS_INPUTPATH = "/PathTestSet";
+
+ private static final String HADOOP_CONF_PATH = ACTUAL_RESULT_DIR + File.separator + "conf.xml";
+ private MiniDFSCluster dfsCluster;
+
+ private JobConf conf = new JobConf();
+ private int numberOfNC = 2;
+
+ public void setUp() throws Exception {
+ ClusterConfig.setStorePath(PATH_TO_CLUSTER_STORE);
+ ClusterConfig.setClusterPropertiesPath(PATH_TO_CLUSTER_PROPERTIES);
+ cleanupStores();
+ PregelixHyracksIntegrationUtil.init("src/test/resources/topology.xml");
+ LOGGER.info("Hyracks mini-cluster started");
+ FileUtils.forceMkdir(new File(ACTUAL_RESULT_DIR));
+ FileUtils.cleanDirectory(new File(ACTUAL_RESULT_DIR));
+ startHDFS();
+ }
+
+ private void startHDFS() throws IOException {
+ conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/core-site.xml"));
+ conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/mapred-site.xml"));
+ conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/hdfs-site.xml"));
+ FileSystem lfs = FileSystem.getLocal(new Configuration());
+ lfs.delete(new Path("build"), true);
+ System.setProperty("hadoop.log.dir", "logs");
+ dfsCluster = new MiniDFSCluster(conf, numberOfNC, true, null);
+ FileSystem dfs = FileSystem.get(conf);
+
+ for (String testDir : TestDir) {
+ File src = new File(testDir);
+ Path dest = new Path(HDFS_INPUTPATH + File.separator + src.getName());
+ dfs.mkdirs(dest);
+ //src.listFiles()
+ //src.listFiles((FilenameFilter)(new WildcardFileFilter("part*")))
+ for (File f : src.listFiles()) {
+ dfs.copyFromLocalFile(new Path(f.getAbsolutePath()), dest);
+ }
+ }
+
+ DataOutputStream confOutput = new DataOutputStream(new FileOutputStream(new File(HADOOP_CONF_PATH)));
+ conf.writeXml(confOutput);
+ confOutput.flush();
+ confOutput.close();
+ }
+
+ private void cleanupStores() throws IOException {
+ FileUtils.forceMkdir(new File("teststore"));
+ FileUtils.forceMkdir(new File("build"));
+ FileUtils.cleanDirectory(new File("teststore"));
+ FileUtils.cleanDirectory(new File("build"));
+ }
+
+ /**
+ * cleanup hdfs cluster
+ */
+ private void cleanupHDFS() throws Exception {
+ dfsCluster.shutdown();
+ }
+
+ public void tearDown() throws Exception {
+ PregelixHyracksIntegrationUtil.deinit();
+ LOGGER.info("Hyracks mini-cluster shut down");
+ cleanupHDFS();
+ }
+
+ public static Test suite() throws Exception {
+ List<String> onlys = getFileList(PATH_TO_ONLY);
+ File testData = new File(PATH_TO_JOBS);
+ File[] queries = testData.listFiles();
+ TipRemoveSmallTestSuite testSuite = new TipRemoveSmallTestSuite();
+ testSuite.setUp();
+ boolean onlyEnabled = false;
+ FileSystem dfs = FileSystem.get(testSuite.conf);
+
+ if (onlys.size() > 0) {
+ onlyEnabled = true;
+ }
+
+ for (File qFile : queries) {
+ if (qFile.isFile()) {
+ if (onlyEnabled && !isInList(onlys, qFile.getName())) {
+ continue;
+ } else {
+ for (String testPathStr : TestDir) {
+ File testDir = new File(testPathStr);
+ String resultFileName = ACTUAL_RESULT_DIR + File.separator + jobExtToResExt(qFile.getName())
+ + File.separator + "bin" + File.separator + testDir.getName();
+ String textFileName = ACTUAL_RESULT_DIR + File.separator + jobExtToResExt(qFile.getName())
+ + File.separator + "txt" + File.separator + testDir.getName();
+ testSuite.addTest(new BasicSmallTestCase(HADOOP_CONF_PATH, qFile.getName(), qFile
+ .getAbsolutePath().toString(), dfs,
+ HDFS_INPUTPATH + File.separator + testDir.getName(), resultFileName, textFileName));
+ }
+ }
+ }
+ }
+ return testSuite;
+ }
+
+ /**
+ * Runs the tests and collects their result in a TestResult.
+ */
+ @Override
+ public void run(TestResult result) {
+ try {
+ int testCount = countTestCases();
+ for (int i = 0; i < testCount; i++) {
+ // cleanupStores();
+ Test each = this.testAt(i);
+ if (result.shouldStop())
+ break;
+ runTest(each, result);
+ }
+ tearDown();
+ } catch (Exception e) {
+ throw new IllegalStateException(e);
+ }
+ }
+
+ protected static List<String> getFileList(String ignorePath) throws FileNotFoundException, IOException {
+ BufferedReader reader = new BufferedReader(new FileReader(ignorePath));
+ String s = null;
+ List<String> ignores = new ArrayList<String>();
+ while ((s = reader.readLine()) != null) {
+ ignores.add(s);
+ }
+ reader.close();
+ return ignores;
+ }
+
+ private static String jobExtToResExt(String fname) {
+ int dot = fname.lastIndexOf('.');
+ return fname.substring(0, dot);
+ }
+
+ private static boolean isInList(List<String> onlys, String name) {
+ for (String only : onlys)
+ if (name.indexOf(only) >= 0)
+ return true;
+ return false;
+ }
+
+}
diff --git a/genomix/genomix-pregelix/src/test/resources/jobs/BridgeAddGraph.xml b/genomix/genomix-pregelix/src/test/resources/jobs/BridgeAddGraph.xml
new file mode 100644
index 0000000..4739d59
--- /dev/null
+++ b/genomix/genomix-pregelix/src/test/resources/jobs/BridgeAddGraph.xml
@@ -0,0 +1,142 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
+<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
+<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
+<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
+<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
+<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
+<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
+<property><name>mapred.submit.replication</name><value>10</value></property>
+<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
+<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
+<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
+<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
+<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
+<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
+<property><name>keep.failed.task.files</name><value>false</value></property>
+<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
+<property><name>mapred.output.value.class</name><value>edu.uci.ics.genomix.pregelix.io.VertexValueWritable</value></property>
+<property><name>io.bytes.per.checksum</name><value>512</value></property>
+<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
+<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
+<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
+<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
+<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
+<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
+<property><name>BridgeRemoveVertex.kmerSize</name><value>3</value></property>
+<property><name>fs.checkpoint.period</name><value>3600</value></property>
+<property><name>mapred.child.tmp</name><value>./tmp</value></property>
+<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
+<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
+<property><name>hadoop.logfile.count</name><value>10</value></property>
+<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
+<property><name>io.map.index.skip</name><value>0</value></property>
+<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
+<property><name>mapred.output.compress</name><value>false</value></property>
+<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
+<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
+<property><name>fs.checkpoint.size</name><value>67108864</value></property>
+<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
+<property><name>mapred.job.name</name><value>BridgeAddGraph</value></property>
+<property><name>local.cache.size</name><value>10737418240</value></property>
+<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
+<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
+<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
+<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
+<property><name>mapred.task.timeout</name><value>600000</value></property>
+<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
+<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
+<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
+<property><name>ipc.client.kill.max</name><value>10</value></property>
+<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
+<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
+<property><name>io.sort.record.percent</name><value>0.05</value></property>
+<property><name>hadoop.security.authorization</name><value>false</value></property>
+<property><name>mapred.max.tracker.failures</name><value>4</value></property>
+<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
+<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
+<property><name>mapred.map.tasks</name><value>2</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
+<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
+<property><name>fs.default.name</name><value>file:///</value></property>
+<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.type.PositionWritable</value></property>
+<property><name>tasktracker.http.threads</name><value>40</value></property>
+<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
+<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
+<property><name>mapred.reduce.tasks</name><value>1</value></property>
+<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
+<property><name>pregelix.vertexClass</name><value>edu.uci.ics.genomix.pregelix.operator.bridgeremove.BridgeAddVertex</value></property>
+<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
+<property><name>io.file.buffer.size</name><value>4096</value></property>
+<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
+<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
+<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
+<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
+<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
+<property><name>hadoop.native.lib</name><value>true</value></property>
+<property><name>fs.s3.block.size</name><value>67108864</value></property>
+<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
+<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
+<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
+<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
+<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
+<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
+<property><name>mapred.queue.names</name><value>default</value></property>
+<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
+<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
+<property><name>mapred.job.tracker</name><value>local</value></property>
+<property><name>io.skip.checksum.errors</name><value>false</value></property>
+<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
+<property><name>fs.s3.maxRetries</name><value>4</value></property>
+<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
+<property><name>fs.trash.interval</name><value>0</value></property>
+<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
+<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
+<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
+<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
+<property><name>io.sort.mb</name><value>100</value></property>
+<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
+<property><name>io.sort.factor</name><value>10</value></property>
+<property><name>mapred.task.profile</name><value>false</value></property>
+<property><name>job.end.retry.interval</name><value>30000</value></property>
+<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
+<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
+<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
+<property><name>webinterface.private.actions</name><value>false</value></property>
+<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
+<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
+<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
+<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
+<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.compress.map.output</name><value>false</value></property>
+<property><name>io.sort.spill.percent</name><value>0.80</value></property>
+<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
+<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
+<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
+<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
+<property><name>job.end.retry.attempts</name><value>0</value></property>
+<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
+<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat</value></property>
+<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
+<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
+<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
+<property><name>hadoop.logfile.size</name><value>10000000</value></property>
+<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.NaiveAlgorithmForPathMergeInputFormat</value></property>
+<property><name>mapred.job.queue.name</name><value>default</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
+<property><name>pregelix.incStateLength</name><value>true</value></property>
+<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
+<property><name>topology.script.number.args</name><value>100</value></property>
+<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
+<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
+<property><name>mapred.task.cache.levels</name><value>2</value></property>
+<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
+<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
+<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
+<property><name>mapred.min.split.size</name><value>0</value></property>
+<property><name>mapred.map.max.attempts</name><value>4</value></property>
+<property><name>jobclient.output.filter</name><value>FAILED</value></property>
+<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
+<property><name>mapred.acls.enabled</name><value>false</value></property>
+</configuration>
\ No newline at end of file
diff --git a/genomix/genomix-pregelix/src/test/resources/jobs/BridgeRemoveGraph.xml b/genomix/genomix-pregelix/src/test/resources/jobs/BridgeRemoveGraph.xml
new file mode 100644
index 0000000..b36258a
--- /dev/null
+++ b/genomix/genomix-pregelix/src/test/resources/jobs/BridgeRemoveGraph.xml
@@ -0,0 +1,142 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
+<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
+<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
+<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
+<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
+<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
+<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
+<property><name>mapred.submit.replication</name><value>10</value></property>
+<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
+<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
+<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
+<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
+<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
+<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
+<property><name>keep.failed.task.files</name><value>false</value></property>
+<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
+<property><name>mapred.output.value.class</name><value>edu.uci.ics.genomix.pregelix.io.VertexValueWritable</value></property>
+<property><name>io.bytes.per.checksum</name><value>512</value></property>
+<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
+<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
+<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
+<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
+<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
+<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
+<property><name>fs.checkpoint.period</name><value>3600</value></property>
+<property><name>mapred.child.tmp</name><value>./tmp</value></property>
+<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
+<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
+<property><name>hadoop.logfile.count</name><value>10</value></property>
+<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
+<property><name>io.map.index.skip</name><value>0</value></property>
+<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
+<property><name>mapred.output.compress</name><value>false</value></property>
+<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
+<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
+<property><name>fs.checkpoint.size</name><value>67108864</value></property>
+<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
+<property><name>mapred.job.name</name><value>BridgeRemoveGraph</value></property>
+<property><name>local.cache.size</name><value>10737418240</value></property>
+<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
+<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
+<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
+<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
+<property><name>mapred.task.timeout</name><value>600000</value></property>
+<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
+<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
+<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
+<property><name>ipc.client.kill.max</name><value>10</value></property>
+<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
+<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
+<property><name>io.sort.record.percent</name><value>0.05</value></property>
+<property><name>hadoop.security.authorization</name><value>false</value></property>
+<property><name>mapred.max.tracker.failures</name><value>4</value></property>
+<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
+<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
+<property><name>mapred.map.tasks</name><value>2</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
+<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
+<property><name>fs.default.name</name><value>file:///</value></property>
+<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.type.PositionWritable</value></property>
+<property><name>tasktracker.http.threads</name><value>40</value></property>
+<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
+<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
+<property><name>mapred.reduce.tasks</name><value>1</value></property>
+<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
+<property><name>pregelix.vertexClass</name><value>edu.uci.ics.genomix.pregelix.operator.bridgeremove.BridgeRemoveVertex</value></property>
+<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
+<property><name>io.file.buffer.size</name><value>4096</value></property>
+<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
+<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
+<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
+<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
+<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
+<property><name>hadoop.native.lib</name><value>true</value></property>
+<property><name>fs.s3.block.size</name><value>67108864</value></property>
+<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
+<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
+<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
+<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
+<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
+<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
+<property><name>mapred.queue.names</name><value>default</value></property>
+<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
+<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
+<property><name>mapred.job.tracker</name><value>local</value></property>
+<property><name>io.skip.checksum.errors</name><value>false</value></property>
+<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
+<property><name>fs.s3.maxRetries</name><value>4</value></property>
+<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
+<property><name>fs.trash.interval</name><value>0</value></property>
+<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
+<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
+<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
+<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
+<property><name>io.sort.mb</name><value>100</value></property>
+<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
+<property><name>io.sort.factor</name><value>10</value></property>
+<property><name>BasicPathMergeVertex.kmerSize</name><value>3</value></property>
+<property><name>mapred.task.profile</name><value>false</value></property>
+<property><name>job.end.retry.interval</name><value>30000</value></property>
+<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
+<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
+<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
+<property><name>webinterface.private.actions</name><value>false</value></property>
+<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
+<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
+<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
+<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
+<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.compress.map.output</name><value>false</value></property>
+<property><name>io.sort.spill.percent</name><value>0.80</value></property>
+<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
+<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
+<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
+<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
+<property><name>job.end.retry.attempts</name><value>0</value></property>
+<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
+<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat</value></property>
+<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
+<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
+<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
+<property><name>hadoop.logfile.size</name><value>10000000</value></property>
+<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanInputFormat</value></property>
+<property><name>mapred.job.queue.name</name><value>default</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
+<property><name>pregelix.incStateLength</name><value>true</value></property>
+<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
+<property><name>topology.script.number.args</name><value>100</value></property>
+<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
+<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
+<property><name>mapred.task.cache.levels</name><value>2</value></property>
+<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
+<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
+<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
+<property><name>mapred.min.split.size</name><value>0</value></property>
+<property><name>mapred.map.max.attempts</name><value>4</value></property>
+<property><name>jobclient.output.filter</name><value>FAILED</value></property>
+<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
+<property><name>mapred.acls.enabled</name><value>false</value></property>
+</configuration>
\ No newline at end of file
diff --git a/genomix/genomix-pregelix/src/test/resources/jobs/BubbleAddGraph.xml b/genomix/genomix-pregelix/src/test/resources/jobs/BubbleAddGraph.xml
new file mode 100644
index 0000000..452834a
--- /dev/null
+++ b/genomix/genomix-pregelix/src/test/resources/jobs/BubbleAddGraph.xml
@@ -0,0 +1,142 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
+<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
+<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
+<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
+<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
+<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
+<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
+<property><name>mapred.submit.replication</name><value>10</value></property>
+<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
+<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
+<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
+<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
+<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
+<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
+<property><name>keep.failed.task.files</name><value>false</value></property>
+<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
+<property><name>mapred.output.value.class</name><value>edu.uci.ics.genomix.pregelix.io.VertexValueWritable</value></property>
+<property><name>io.bytes.per.checksum</name><value>512</value></property>
+<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
+<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
+<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
+<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
+<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
+<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
+<property><name>fs.checkpoint.period</name><value>3600</value></property>
+<property><name>mapred.child.tmp</name><value>./tmp</value></property>
+<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
+<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
+<property><name>hadoop.logfile.count</name><value>10</value></property>
+<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
+<property><name>io.map.index.skip</name><value>0</value></property>
+<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
+<property><name>mapred.output.compress</name><value>false</value></property>
+<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
+<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
+<property><name>fs.checkpoint.size</name><value>67108864</value></property>
+<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
+<property><name>mapred.job.name</name><value>BubbleAddGraph</value></property>
+<property><name>local.cache.size</name><value>10737418240</value></property>
+<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
+<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
+<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
+<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
+<property><name>mapred.task.timeout</name><value>600000</value></property>
+<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
+<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
+<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
+<property><name>ipc.client.kill.max</name><value>10</value></property>
+<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
+<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
+<property><name>io.sort.record.percent</name><value>0.05</value></property>
+<property><name>hadoop.security.authorization</name><value>false</value></property>
+<property><name>mapred.max.tracker.failures</name><value>4</value></property>
+<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
+<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
+<property><name>mapred.map.tasks</name><value>2</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
+<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
+<property><name>fs.default.name</name><value>file:///</value></property>
+<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.type.PositionWritable</value></property>
+<property><name>tasktracker.http.threads</name><value>40</value></property>
+<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
+<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
+<property><name>mapred.reduce.tasks</name><value>1</value></property>
+<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
+<property><name>pregelix.vertexClass</name><value>edu.uci.ics.genomix.pregelix.operator.bubblemerge.BubbleAddVertex</value></property>
+<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
+<property><name>io.file.buffer.size</name><value>4096</value></property>
+<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
+<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
+<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
+<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
+<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
+<property><name>hadoop.native.lib</name><value>true</value></property>
+<property><name>fs.s3.block.size</name><value>67108864</value></property>
+<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
+<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
+<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
+<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
+<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
+<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
+<property><name>mapred.queue.names</name><value>default</value></property>
+<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
+<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
+<property><name>mapred.job.tracker</name><value>local</value></property>
+<property><name>BubbleAddVertex.kmerSize</name><value>3</value></property>
+<property><name>io.skip.checksum.errors</name><value>false</value></property>
+<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
+<property><name>fs.s3.maxRetries</name><value>4</value></property>
+<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
+<property><name>fs.trash.interval</name><value>0</value></property>
+<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
+<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
+<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
+<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
+<property><name>io.sort.mb</name><value>100</value></property>
+<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
+<property><name>io.sort.factor</name><value>10</value></property>
+<property><name>mapred.task.profile</name><value>false</value></property>
+<property><name>job.end.retry.interval</name><value>30000</value></property>
+<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
+<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
+<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
+<property><name>webinterface.private.actions</name><value>false</value></property>
+<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
+<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
+<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
+<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
+<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.compress.map.output</name><value>false</value></property>
+<property><name>io.sort.spill.percent</name><value>0.80</value></property>
+<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
+<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
+<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
+<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
+<property><name>job.end.retry.attempts</name><value>0</value></property>
+<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
+<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat</value></property>
+<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
+<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
+<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
+<property><name>hadoop.logfile.size</name><value>10000000</value></property>
+<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.NaiveAlgorithmForPathMergeInputFormat</value></property>
+<property><name>mapred.job.queue.name</name><value>default</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
+<property><name>pregelix.incStateLength</name><value>true</value></property>
+<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
+<property><name>topology.script.number.args</name><value>100</value></property>
+<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
+<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
+<property><name>mapred.task.cache.levels</name><value>2</value></property>
+<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
+<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
+<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
+<property><name>mapred.min.split.size</name><value>0</value></property>
+<property><name>mapred.map.max.attempts</name><value>4</value></property>
+<property><name>jobclient.output.filter</name><value>FAILED</value></property>
+<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
+<property><name>mapred.acls.enabled</name><value>false</value></property>
+</configuration>
\ No newline at end of file
diff --git a/genomix/genomix-pregelix/src/test/resources/jobs/BubbleMergeGraph.xml b/genomix/genomix-pregelix/src/test/resources/jobs/BubbleMergeGraph.xml
new file mode 100644
index 0000000..1b5cf0c
--- /dev/null
+++ b/genomix/genomix-pregelix/src/test/resources/jobs/BubbleMergeGraph.xml
@@ -0,0 +1,142 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
+<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
+<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
+<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
+<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
+<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
+<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
+<property><name>mapred.submit.replication</name><value>10</value></property>
+<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
+<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
+<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
+<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
+<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
+<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
+<property><name>keep.failed.task.files</name><value>false</value></property>
+<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
+<property><name>mapred.output.value.class</name><value>edu.uci.ics.genomix.pregelix.io.VertexValueWritable</value></property>
+<property><name>io.bytes.per.checksum</name><value>512</value></property>
+<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
+<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
+<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
+<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
+<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
+<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
+<property><name>fs.checkpoint.period</name><value>3600</value></property>
+<property><name>mapred.child.tmp</name><value>./tmp</value></property>
+<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
+<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
+<property><name>hadoop.logfile.count</name><value>10</value></property>
+<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
+<property><name>io.map.index.skip</name><value>0</value></property>
+<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
+<property><name>mapred.output.compress</name><value>false</value></property>
+<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
+<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
+<property><name>fs.checkpoint.size</name><value>67108864</value></property>
+<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
+<property><name>mapred.job.name</name><value>BubbleMergeGraph</value></property>
+<property><name>local.cache.size</name><value>10737418240</value></property>
+<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
+<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
+<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
+<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
+<property><name>mapred.task.timeout</name><value>600000</value></property>
+<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
+<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
+<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
+<property><name>ipc.client.kill.max</name><value>10</value></property>
+<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
+<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
+<property><name>io.sort.record.percent</name><value>0.05</value></property>
+<property><name>hadoop.security.authorization</name><value>false</value></property>
+<property><name>mapred.max.tracker.failures</name><value>4</value></property>
+<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
+<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
+<property><name>mapred.map.tasks</name><value>2</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
+<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
+<property><name>fs.default.name</name><value>file:///</value></property>
+<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.type.PositionWritable</value></property>
+<property><name>tasktracker.http.threads</name><value>40</value></property>
+<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
+<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
+<property><name>mapred.reduce.tasks</name><value>1</value></property>
+<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
+<property><name>pregelix.vertexClass</name><value>edu.uci.ics.genomix.pregelix.operator.bubblemerge.BubbleMergeVertex</value></property>
+<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
+<property><name>io.file.buffer.size</name><value>4096</value></property>
+<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
+<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
+<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
+<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
+<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
+<property><name>hadoop.native.lib</name><value>true</value></property>
+<property><name>fs.s3.block.size</name><value>67108864</value></property>
+<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
+<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
+<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
+<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
+<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
+<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
+<property><name>mapred.queue.names</name><value>default</value></property>
+<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
+<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
+<property><name>mapred.job.tracker</name><value>local</value></property>
+<property><name>io.skip.checksum.errors</name><value>false</value></property>
+<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
+<property><name>fs.s3.maxRetries</name><value>4</value></property>
+<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
+<property><name>fs.trash.interval</name><value>0</value></property>
+<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
+<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
+<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
+<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
+<property><name>io.sort.mb</name><value>100</value></property>
+<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
+<property><name>io.sort.factor</name><value>10</value></property>
+<property><name>mapred.task.profile</name><value>false</value></property>
+<property><name>job.end.retry.interval</name><value>30000</value></property>
+<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
+<property><name>BubbleMergeVertex.kmerSize</name><value>3</value></property>
+<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
+<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
+<property><name>webinterface.private.actions</name><value>false</value></property>
+<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
+<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
+<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
+<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
+<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.compress.map.output</name><value>false</value></property>
+<property><name>io.sort.spill.percent</name><value>0.80</value></property>
+<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
+<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
+<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
+<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
+<property><name>job.end.retry.attempts</name><value>0</value></property>
+<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
+<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat</value></property>
+<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
+<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
+<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
+<property><name>hadoop.logfile.size</name><value>10000000</value></property>
+<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanInputFormat</value></property>
+<property><name>mapred.job.queue.name</name><value>default</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
+<property><name>pregelix.incStateLength</name><value>true</value></property>
+<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
+<property><name>topology.script.number.args</name><value>100</value></property>
+<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
+<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
+<property><name>mapred.task.cache.levels</name><value>2</value></property>
+<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
+<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
+<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
+<property><name>mapred.min.split.size</name><value>0</value></property>
+<property><name>mapred.map.max.attempts</name><value>4</value></property>
+<property><name>jobclient.output.filter</name><value>FAILED</value></property>
+<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
+<property><name>mapred.acls.enabled</name><value>false</value></property>
+</configuration>
\ No newline at end of file
diff --git a/genomix/genomix-pregelix/src/test/resources/jobs/P4ForMergeGraph.xml b/genomix/genomix-pregelix/src/test/resources/jobs/P4ForMergeGraph.xml
new file mode 100644
index 0000000..ed5773c
--- /dev/null
+++ b/genomix/genomix-pregelix/src/test/resources/jobs/P4ForMergeGraph.xml
@@ -0,0 +1,142 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
+<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
+<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
+<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
+<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
+<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
+<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
+<property><name>mapred.submit.replication</name><value>10</value></property>
+<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
+<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
+<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
+<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
+<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
+<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
+<property><name>keep.failed.task.files</name><value>false</value></property>
+<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
+<property><name>mapred.output.value.class</name><value>edu.uci.ics.genomix.pregelix.io.VertexValueWritable</value></property>
+<property><name>io.bytes.per.checksum</name><value>512</value></property>
+<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
+<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
+<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
+<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
+<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
+<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
+<property><name>fs.checkpoint.period</name><value>3600</value></property>
+<property><name>mapred.child.tmp</name><value>./tmp</value></property>
+<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
+<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
+<property><name>hadoop.logfile.count</name><value>10</value></property>
+<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
+<property><name>io.map.index.skip</name><value>0</value></property>
+<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
+<property><name>mapred.output.compress</name><value>false</value></property>
+<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
+<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
+<property><name>fs.checkpoint.size</name><value>67108864</value></property>
+<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
+<property><name>mapred.job.name</name><value>P4ForMergeGraph</value></property>
+<property><name>local.cache.size</name><value>10737418240</value></property>
+<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
+<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
+<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
+<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
+<property><name>mapred.task.timeout</name><value>600000</value></property>
+<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
+<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
+<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
+<property><name>ipc.client.kill.max</name><value>10</value></property>
+<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
+<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
+<property><name>io.sort.record.percent</name><value>0.05</value></property>
+<property><name>hadoop.security.authorization</name><value>false</value></property>
+<property><name>mapred.max.tracker.failures</name><value>4</value></property>
+<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
+<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
+<property><name>mapred.map.tasks</name><value>2</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
+<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
+<property><name>fs.default.name</name><value>file:///</value></property>
+<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.type.PositionWritable</value></property>
+<property><name>tasktracker.http.threads</name><value>40</value></property>
+<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
+<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
+<property><name>mapred.reduce.tasks</name><value>1</value></property>
+<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
+<property><name>pregelix.vertexClass</name><value>edu.uci.ics.genomix.pregelix.operator.pathmerge.P4ForPathMergeVertex</value></property>
+<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
+<property><name>io.file.buffer.size</name><value>4096</value></property>
+<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
+<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
+<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
+<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
+<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
+<property><name>hadoop.native.lib</name><value>true</value></property>
+<property><name>fs.s3.block.size</name><value>67108864</value></property>
+<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
+<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
+<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
+<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
+<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
+<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
+<property><name>mapred.queue.names</name><value>default</value></property>
+<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
+<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
+<property><name>mapred.job.tracker</name><value>local</value></property>
+<property><name>io.skip.checksum.errors</name><value>false</value></property>
+<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
+<property><name>fs.s3.maxRetries</name><value>4</value></property>
+<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
+<property><name>fs.trash.interval</name><value>0</value></property>
+<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
+<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
+<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
+<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
+<property><name>io.sort.mb</name><value>100</value></property>
+<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
+<property><name>io.sort.factor</name><value>10</value></property>
+<property><name>BasicPathMergeVertex.kmerSize</name><value>3</value></property>
+<property><name>mapred.task.profile</name><value>false</value></property>
+<property><name>job.end.retry.interval</name><value>30000</value></property>
+<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
+<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
+<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
+<property><name>webinterface.private.actions</name><value>false</value></property>
+<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
+<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
+<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
+<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
+<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.compress.map.output</name><value>false</value></property>
+<property><name>io.sort.spill.percent</name><value>0.80</value></property>
+<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
+<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
+<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
+<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
+<property><name>job.end.retry.attempts</name><value>0</value></property>
+<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
+<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat</value></property>
+<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
+<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
+<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
+<property><name>hadoop.logfile.size</name><value>10000000</value></property>
+<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanInputFormat</value></property>
+<property><name>mapred.job.queue.name</name><value>default</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
+<property><name>pregelix.incStateLength</name><value>true</value></property>
+<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
+<property><name>topology.script.number.args</name><value>100</value></property>
+<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
+<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
+<property><name>mapred.task.cache.levels</name><value>2</value></property>
+<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
+<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
+<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
+<property><name>mapred.min.split.size</name><value>0</value></property>
+<property><name>mapred.map.max.attempts</name><value>4</value></property>
+<property><name>jobclient.output.filter</name><value>FAILED</value></property>
+<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
+<property><name>mapred.acls.enabled</name><value>false</value></property>
+</configuration>
\ No newline at end of file
diff --git a/genomix/genomix-pregelix/src/test/resources/jobs/TipAddGraph.xml b/genomix/genomix-pregelix/src/test/resources/jobs/TipAddGraph.xml
new file mode 100644
index 0000000..00c857e
--- /dev/null
+++ b/genomix/genomix-pregelix/src/test/resources/jobs/TipAddGraph.xml
@@ -0,0 +1,142 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
+<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
+<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
+<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
+<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
+<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
+<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
+<property><name>mapred.submit.replication</name><value>10</value></property>
+<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
+<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
+<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
+<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
+<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
+<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
+<property><name>keep.failed.task.files</name><value>false</value></property>
+<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
+<property><name>mapred.output.value.class</name><value>edu.uci.ics.genomix.pregelix.io.VertexValueWritable</value></property>
+<property><name>io.bytes.per.checksum</name><value>512</value></property>
+<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
+<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
+<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
+<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
+<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
+<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
+<property><name>fs.checkpoint.period</name><value>3600</value></property>
+<property><name>TipAddVertex.kmerSize</name><value>3</value></property>
+<property><name>mapred.child.tmp</name><value>./tmp</value></property>
+<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
+<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
+<property><name>hadoop.logfile.count</name><value>10</value></property>
+<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
+<property><name>io.map.index.skip</name><value>0</value></property>
+<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
+<property><name>mapred.output.compress</name><value>false</value></property>
+<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
+<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
+<property><name>fs.checkpoint.size</name><value>67108864</value></property>
+<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
+<property><name>mapred.job.name</name><value>TipAddGraph</value></property>
+<property><name>local.cache.size</name><value>10737418240</value></property>
+<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
+<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
+<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
+<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
+<property><name>mapred.task.timeout</name><value>600000</value></property>
+<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
+<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
+<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
+<property><name>ipc.client.kill.max</name><value>10</value></property>
+<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
+<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
+<property><name>io.sort.record.percent</name><value>0.05</value></property>
+<property><name>hadoop.security.authorization</name><value>false</value></property>
+<property><name>mapred.max.tracker.failures</name><value>4</value></property>
+<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
+<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
+<property><name>mapred.map.tasks</name><value>2</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
+<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
+<property><name>fs.default.name</name><value>file:///</value></property>
+<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.type.PositionWritable</value></property>
+<property><name>tasktracker.http.threads</name><value>40</value></property>
+<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
+<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
+<property><name>mapred.reduce.tasks</name><value>1</value></property>
+<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
+<property><name>pregelix.vertexClass</name><value>edu.uci.ics.genomix.pregelix.operator.tipremove.TipAddVertex</value></property>
+<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
+<property><name>io.file.buffer.size</name><value>4096</value></property>
+<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
+<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
+<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
+<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
+<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
+<property><name>hadoop.native.lib</name><value>true</value></property>
+<property><name>fs.s3.block.size</name><value>67108864</value></property>
+<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
+<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
+<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
+<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
+<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
+<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
+<property><name>mapred.queue.names</name><value>default</value></property>
+<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
+<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
+<property><name>mapred.job.tracker</name><value>local</value></property>
+<property><name>io.skip.checksum.errors</name><value>false</value></property>
+<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
+<property><name>fs.s3.maxRetries</name><value>4</value></property>
+<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
+<property><name>fs.trash.interval</name><value>0</value></property>
+<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
+<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
+<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
+<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
+<property><name>io.sort.mb</name><value>100</value></property>
+<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
+<property><name>io.sort.factor</name><value>10</value></property>
+<property><name>mapred.task.profile</name><value>false</value></property>
+<property><name>job.end.retry.interval</name><value>30000</value></property>
+<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
+<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
+<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
+<property><name>webinterface.private.actions</name><value>false</value></property>
+<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
+<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
+<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
+<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
+<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.compress.map.output</name><value>false</value></property>
+<property><name>io.sort.spill.percent</name><value>0.80</value></property>
+<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
+<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
+<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
+<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
+<property><name>job.end.retry.attempts</name><value>0</value></property>
+<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
+<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat</value></property>
+<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
+<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
+<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
+<property><name>hadoop.logfile.size</name><value>10000000</value></property>
+<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.NaiveAlgorithmForPathMergeInputFormat</value></property>
+<property><name>mapred.job.queue.name</name><value>default</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
+<property><name>pregelix.incStateLength</name><value>true</value></property>
+<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
+<property><name>topology.script.number.args</name><value>100</value></property>
+<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
+<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
+<property><name>mapred.task.cache.levels</name><value>2</value></property>
+<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
+<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
+<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
+<property><name>mapred.min.split.size</name><value>0</value></property>
+<property><name>mapred.map.max.attempts</name><value>4</value></property>
+<property><name>jobclient.output.filter</name><value>FAILED</value></property>
+<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
+<property><name>mapred.acls.enabled</name><value>false</value></property>
+</configuration>
\ No newline at end of file
diff --git a/genomix/genomix-pregelix/src/test/resources/jobs/TipRemoveGraph.xml b/genomix/genomix-pregelix/src/test/resources/jobs/TipRemoveGraph.xml
new file mode 100644
index 0000000..1fcacc9
--- /dev/null
+++ b/genomix/genomix-pregelix/src/test/resources/jobs/TipRemoveGraph.xml
@@ -0,0 +1,142 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
+<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
+<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
+<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
+<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
+<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
+<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
+<property><name>mapred.submit.replication</name><value>10</value></property>
+<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
+<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
+<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
+<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
+<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
+<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
+<property><name>keep.failed.task.files</name><value>false</value></property>
+<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
+<property><name>mapred.output.value.class</name><value>edu.uci.ics.genomix.pregelix.io.VertexValueWritable</value></property>
+<property><name>io.bytes.per.checksum</name><value>512</value></property>
+<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
+<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
+<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
+<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
+<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
+<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
+<property><name>fs.checkpoint.period</name><value>3600</value></property>
+<property><name>mapred.child.tmp</name><value>./tmp</value></property>
+<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
+<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
+<property><name>hadoop.logfile.count</name><value>10</value></property>
+<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
+<property><name>io.map.index.skip</name><value>0</value></property>
+<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
+<property><name>mapred.output.compress</name><value>false</value></property>
+<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
+<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
+<property><name>fs.checkpoint.size</name><value>67108864</value></property>
+<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
+<property><name>mapred.job.name</name><value>TipRemoveGraph</value></property>
+<property><name>local.cache.size</name><value>10737418240</value></property>
+<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
+<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
+<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
+<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
+<property><name>mapred.task.timeout</name><value>600000</value></property>
+<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
+<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
+<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
+<property><name>ipc.client.kill.max</name><value>10</value></property>
+<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
+<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
+<property><name>io.sort.record.percent</name><value>0.05</value></property>
+<property><name>hadoop.security.authorization</name><value>false</value></property>
+<property><name>mapred.max.tracker.failures</name><value>4</value></property>
+<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
+<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
+<property><name>mapred.map.tasks</name><value>2</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
+<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
+<property><name>fs.default.name</name><value>file:///</value></property>
+<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.type.PositionWritable</value></property>
+<property><name>tasktracker.http.threads</name><value>40</value></property>
+<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
+<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
+<property><name>mapred.reduce.tasks</name><value>1</value></property>
+<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
+<property><name>pregelix.vertexClass</name><value>edu.uci.ics.genomix.pregelix.operator.tipremove.TipRemoveVertex</value></property>
+<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
+<property><name>io.file.buffer.size</name><value>4096</value></property>
+<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
+<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
+<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
+<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
+<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
+<property><name>hadoop.native.lib</name><value>true</value></property>
+<property><name>fs.s3.block.size</name><value>67108864</value></property>
+<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
+<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
+<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
+<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
+<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
+<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
+<property><name>mapred.queue.names</name><value>default</value></property>
+<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
+<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
+<property><name>mapred.job.tracker</name><value>local</value></property>
+<property><name>io.skip.checksum.errors</name><value>false</value></property>
+<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
+<property><name>fs.s3.maxRetries</name><value>4</value></property>
+<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
+<property><name>fs.trash.interval</name><value>0</value></property>
+<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
+<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
+<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
+<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
+<property><name>io.sort.mb</name><value>100</value></property>
+<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
+<property><name>io.sort.factor</name><value>10</value></property>
+<property><name>BasicPathMergeVertex.kmerSize</name><value>3</value></property>
+<property><name>mapred.task.profile</name><value>false</value></property>
+<property><name>job.end.retry.interval</name><value>30000</value></property>
+<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
+<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
+<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
+<property><name>webinterface.private.actions</name><value>false</value></property>
+<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
+<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
+<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
+<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
+<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.compress.map.output</name><value>false</value></property>
+<property><name>io.sort.spill.percent</name><value>0.80</value></property>
+<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
+<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
+<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
+<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
+<property><name>job.end.retry.attempts</name><value>0</value></property>
+<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
+<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat</value></property>
+<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
+<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
+<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
+<property><name>hadoop.logfile.size</name><value>10000000</value></property>
+<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanInputFormat</value></property>
+<property><name>mapred.job.queue.name</name><value>default</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
+<property><name>pregelix.incStateLength</name><value>true</value></property>
+<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
+<property><name>topology.script.number.args</name><value>100</value></property>
+<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
+<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
+<property><name>mapred.task.cache.levels</name><value>2</value></property>
+<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
+<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
+<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
+<property><name>mapred.min.split.size</name><value>0</value></property>
+<property><name>mapred.map.max.attempts</name><value>4</value></property>
+<property><name>jobclient.output.filter</name><value>FAILED</value></property>
+<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
+<property><name>mapred.acls.enabled</name><value>false</value></property>
+</configuration>
\ No newline at end of file
diff --git a/genomix/genomix-pregelix/src/test/resources/only_bridgeremove.txt b/genomix/genomix-pregelix/src/test/resources/only_bridgeremove.txt
new file mode 100644
index 0000000..53537cb
--- /dev/null
+++ b/genomix/genomix-pregelix/src/test/resources/only_bridgeremove.txt
@@ -0,0 +1 @@
+BridgeRemoveGraph.xml
diff --git a/genomix/genomix-pregelix/src/test/resources/only_bubblemerge.txt b/genomix/genomix-pregelix/src/test/resources/only_bubblemerge.txt
new file mode 100644
index 0000000..417161c
--- /dev/null
+++ b/genomix/genomix-pregelix/src/test/resources/only_bubblemerge.txt
@@ -0,0 +1 @@
+BubbleMergeGraph.xml
diff --git a/genomix/genomix-pregelix/src/test/resources/only_pathmerge.txt b/genomix/genomix-pregelix/src/test/resources/only_pathmerge.txt
new file mode 100644
index 0000000..3d007d2
--- /dev/null
+++ b/genomix/genomix-pregelix/src/test/resources/only_pathmerge.txt
@@ -0,0 +1 @@
+P4ForMergeGraph.xml
diff --git a/genomix/genomix-pregelix/src/test/resources/only_tipadd.txt b/genomix/genomix-pregelix/src/test/resources/only_tipadd.txt
new file mode 100644
index 0000000..53eecdd
--- /dev/null
+++ b/genomix/genomix-pregelix/src/test/resources/only_tipadd.txt
@@ -0,0 +1 @@
+TipAddGraph.xml
diff --git a/genomix/genomix-pregelix/src/test/resources/only_tipremove.txt b/genomix/genomix-pregelix/src/test/resources/only_tipremove.txt
new file mode 100644
index 0000000..7392b4e
--- /dev/null
+++ b/genomix/genomix-pregelix/src/test/resources/only_tipremove.txt
@@ -0,0 +1 @@
+TipRemoveGraph.xml