Merge branch 'fullstack_genomix' of https://code.google.com/p/hyracks into fullstack_genomix
diff --git a/genomix/genomix-hadoop/actual3/complete2/.complete2-r-00000.crc b/genomix/genomix-hadoop/actual3/complete2/.complete2-r-00000.crc
index b0b2753..bccc1b3 100644
--- a/genomix/genomix-hadoop/actual3/complete2/.complete2-r-00000.crc
+++ b/genomix/genomix-hadoop/actual3/complete2/.complete2-r-00000.crc
Binary files differ
diff --git a/genomix/genomix-hadoop/actual3/complete2/complete2-r-00000 b/genomix/genomix-hadoop/actual3/complete2/complete2-r-00000
index d3d3667..2704be9 100755
--- a/genomix/genomix-hadoop/actual3/complete2/complete2-r-00000
+++ b/genomix/genomix-hadoop/actual3/complete2/complete2-r-00000
Binary files differ
diff --git a/genomix/genomix-hadoop/actual3/conf.xml b/genomix/genomix-hadoop/actual3/conf.xml
index 16a0edc..f662215 100644
--- a/genomix/genomix-hadoop/actual3/conf.xml
+++ b/genomix/genomix-hadoop/actual3/conf.xml
@@ -12,7 +12,7 @@
<property><name>dfs.namenode.logging.level</name><value>info</value></property>
<property><name>dfs.datanode.address</name><value>127.0.0.1:0</value></property>
<property><name>io.skip.checksum.errors</name><value>false</value></property>
-<property><name>fs.default.name</name><value>hdfs://localhost:62106</value></property>
+<property><name>fs.default.name</name><value>hdfs://localhost:50310</value></property>
<property><name>mapred.child.tmp</name><value>./tmp</value></property>
<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
<property><name>dfs.safemode.threshold.pct</name><value>0.999f</value></property>
@@ -125,7 +125,7 @@
<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
<property><name>dfs.namenode.decommission.interval</name><value>3</value></property>
-<property><name>dfs.http.address</name><value>localhost:62107</value></property>
+<property><name>dfs.http.address</name><value>localhost:50311</value></property>
<property><name>dfs.heartbeat.interval</name><value>3</value></property>
<property><name>mapred.job.tracker</name><value>local</value></property>
<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
diff --git a/genomix/genomix-hadoop/data/webmap/text.txt b/genomix/genomix-hadoop/data/webmap/text.txt
deleted file mode 100755
index c6cd7fe..0000000
--- a/genomix/genomix-hadoop/data/webmap/text.txt
+++ /dev/null
@@ -1,4 +0,0 @@
-@625E1AAXX100810:1:100:10000:10271/1
-AATAGAAGATCGAT
-+
-EDBDB?BEEEDGGEGGGDGGGA>DG@GGD;GD@DG@F?<B<BFFD?
diff --git a/genomix/genomix-hadoop/pom.xml b/genomix/genomix-hadoop/pom.xml
index f791f5b..ff6a7ee 100755
--- a/genomix/genomix-hadoop/pom.xml
+++ b/genomix/genomix-hadoop/pom.xml
@@ -22,8 +22,9 @@
<artifactId>maven-compiler-plugin</artifactId>
<version>2.0.2</version>
<configuration>
- <source>1.6</source>
- <target>1.6</target>
+ <source>1.7</source>
+ <target>1.7</target>
+ <fork>true</fork>
</configuration>
</plugin>
<plugin>
diff --git a/genomix/genomix-hadoop/src/.DS_Store b/genomix/genomix-hadoop/src/.DS_Store
new file mode 100644
index 0000000..1cf57ac
--- /dev/null
+++ b/genomix/genomix-hadoop/src/.DS_Store
Binary files differ
diff --git a/genomix/genomix-hadoop/src/main/.DS_Store b/genomix/genomix-hadoop/src/main/.DS_Store
new file mode 100644
index 0000000..f2a5476
--- /dev/null
+++ b/genomix/genomix-hadoop/src/main/.DS_Store
Binary files differ
diff --git a/genomix/genomix-hadoop/src/main/java/.DS_Store b/genomix/genomix-hadoop/src/main/java/.DS_Store
new file mode 100644
index 0000000..7806fed
--- /dev/null
+++ b/genomix/genomix-hadoop/src/main/java/.DS_Store
Binary files differ
diff --git a/genomix/genomix-hadoop/src/main/java/edu/.DS_Store b/genomix/genomix-hadoop/src/main/java/edu/.DS_Store
new file mode 100644
index 0000000..bc05a64
--- /dev/null
+++ b/genomix/genomix-hadoop/src/main/java/edu/.DS_Store
Binary files differ
diff --git a/genomix/genomix-hadoop/src/main/java/edu/uci/.DS_Store b/genomix/genomix-hadoop/src/main/java/edu/uci/.DS_Store
new file mode 100644
index 0000000..ec6ffce
--- /dev/null
+++ b/genomix/genomix-hadoop/src/main/java/edu/uci/.DS_Store
Binary files differ
diff --git a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/.DS_Store b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/.DS_Store
new file mode 100644
index 0000000..22fef5d
--- /dev/null
+++ b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/.DS_Store
Binary files differ
diff --git a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/MergePathDriver.java b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/MergePathDriver.java
index cfdf8d5..99eec46 100644
--- a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/MergePathDriver.java
+++ b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/MergePathDriver.java
@@ -23,8 +23,10 @@
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.SequenceFileInputFormat;
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
+import org.apache.hadoop.mapred.TextOutputFormat;
import org.apache.hadoop.mapred.lib.MultipleOutputs;
import org.apache.hadoop.mapred.lib.MultipleSequenceFileOutputFormat;
+import org.apache.hadoop.mapred.lib.MultipleTextOutputFormat;
import org.kohsuke.args4j.CmdLineParser;
import org.kohsuke.args4j.Option;
@@ -83,8 +85,9 @@
FileSystem dfs = FileSystem.get(conf);
dfs.delete(new Path(inputPath + "-step1"), true);
JobClient.runJob(conf);
+ int iMerge = 0;
/*----------------------------------------------------------------------*/
- for(int iMerge = 0; iMerge < mergeRound; iMerge ++){
+ for(iMerge = 0; iMerge < mergeRound; iMerge ++){
conf = new JobConf(MergePathDriver.class);
conf.setInt("sizeKmer", sizeKmer);
@@ -102,7 +105,6 @@
conf.setMapOutputValueClass(MergePathValueWritable.class);
conf.setInputFormat(SequenceFileInputFormat.class);
- conf.setOutputFormat(MultipleSequenceFileOutputFormat.class);
String uncomplete = "uncomplete" + iMerge;
String complete = "complete" + iMerge;
diff --git a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/MergePathMapper.java b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/MergePathMapper.java
index c3255f2..ff4c2ce 100644
--- a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/MergePathMapper.java
+++ b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/MergePathMapper.java
@@ -28,24 +28,24 @@
@SuppressWarnings("deprecation")
public class MergePathMapper extends MapReduceBase implements
- Mapper<KmerBytesWritable, MergePathValueWritable, KmerBytesWritable, MergePathValueWritable> {
+ Mapper<VKmerBytesWritable, MergePathValueWritable, VKmerBytesWritable, MergePathValueWritable> {
private int KMER_SIZE;
private VKmerBytesWritableFactory outputKmerFactory;
- private MergePathValueWritable outputAdjList;
+ private MergePathValueWritable outputValue;
private VKmerBytesWritable tmpKmer;
private VKmerBytesWritable outputKmer;
public void configure(JobConf job) {
KMER_SIZE = job.getInt("sizeKmer", 0);
outputKmerFactory = new VKmerBytesWritableFactory(KMER_SIZE);
- outputAdjList = new MergePathValueWritable();
+ outputValue = new MergePathValueWritable();
tmpKmer = new VKmerBytesWritable(KMER_SIZE);
outputKmer = new VKmerBytesWritable(KMER_SIZE);
}
@Override
- public void map(KmerBytesWritable key, MergePathValueWritable value,
- OutputCollector<KmerBytesWritable, MergePathValueWritable> output, Reporter reporter) throws IOException {
+ public void map(VKmerBytesWritable key, MergePathValueWritable value,
+ OutputCollector<VKmerBytesWritable, MergePathValueWritable> output, Reporter reporter) throws IOException {
byte precursor = (byte) 0xF0;
byte succeed = (byte) 0x0F;
@@ -59,14 +59,14 @@
byte succeedCode = GeneCode.getGeneCodeFromBitMap(succeed);
tmpKmer.set(outputKmerFactory.getLastKmerFromChain(KMER_SIZE, key));
outputKmer.set(outputKmerFactory.shiftKmerWithNextCode(tmpKmer, succeedCode));
-
- KmerBytesWritable mergedKmer = outputKmerFactory.getFirstKmerFromChain(value.getKmerSize()
- - (KMER_SIZE - 1), value.getKmer());
- outputAdjList.set(mergedKmer, adjBitMap, bitFlag);
- output.collect(outputKmer, outputAdjList);
+
+ tmpKmer.set(outputKmerFactory.getFirstKmerFromChain(key.getKmerLength() - (KMER_SIZE - 1), key));
+ outputValue.set(tmpKmer, adjBitMap, bitFlag);
+ output.collect(outputKmer, outputValue);
} else {
- outputAdjList.set(value);
- output.collect(key, outputAdjList);
+ outputKmer.set(key);
+ outputValue.set(value);
+ output.collect(key, outputValue);
}
}
}
diff --git a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/MergePathReducer.java b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/MergePathReducer.java
index cead0e8..44f7e8e 100644
--- a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/MergePathReducer.java
+++ b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/MergePathReducer.java
@@ -29,12 +29,14 @@
@SuppressWarnings("deprecation")
public class MergePathReducer extends MapReduceBase implements
- Reducer<KmerBytesWritable, MergePathValueWritable, KmerBytesWritable, MergePathValueWritable> {
+ Reducer<VKmerBytesWritable, MergePathValueWritable, VKmerBytesWritable, MergePathValueWritable> {
private VKmerBytesWritableFactory kmerFactory;
private VKmerBytesWritable outputKmer;
private VKmerBytesWritable tmpKmer;
private int KMER_SIZE;
- private MergePathValueWritable outputAdjList;
+ private MergePathValueWritable outputValue;
+ private MergePathValueWritable tmpOutputValue;
+
MultipleOutputs mos = null;
private int I_MERGE;
@@ -42,7 +44,7 @@
mos = new MultipleOutputs(job);
I_MERGE = Integer.parseInt(job.get("iMerge"));
KMER_SIZE = job.getInt("sizeKmer", 0);
- outputAdjList = new MergePathValueWritable();
+ outputValue = new MergePathValueWritable();
kmerFactory = new VKmerBytesWritableFactory(KMER_SIZE);
outputKmer = new VKmerBytesWritable(KMER_SIZE);
tmpKmer = new VKmerBytesWritable(KMER_SIZE);
@@ -50,58 +52,72 @@
@SuppressWarnings("unchecked")
@Override
- public void reduce(KmerBytesWritable key, Iterator<MergePathValueWritable> values,
- OutputCollector<KmerBytesWritable, MergePathValueWritable> output, Reporter reporter) throws IOException {
- outputAdjList = values.next();
-
-
+ public void reduce(VKmerBytesWritable key, Iterator<MergePathValueWritable> values,
+ OutputCollector<VKmerBytesWritable, MergePathValueWritable> output, Reporter reporter) throws IOException {
+ outputValue = values.next();
if (values.hasNext() == true) {
-
- if (outputAdjList.getFlag() == 1) {
- byte adjBitMap = outputAdjList.getAdjBitMap();
- byte bitFlag = outputAdjList.getFlag();
- outputKmer.set(kmerFactory.mergeTwoKmer(outputAdjList.getKmer(), key));
-
- outputAdjList = values.next();
- byte nextAdj = outputAdjList.getAdjBitMap();
+ if(outputValue.getFlag() != 1){
+ byte nextAdj = outputValue.getAdjBitMap();
byte succeed = (byte) 0x0F;
succeed = (byte) (succeed & nextAdj);
- adjBitMap = (byte) (adjBitMap & 0xF0);
- adjBitMap = (byte) (adjBitMap | succeed);
- outputAdjList.set(null, 0, 0, adjBitMap, bitFlag, KMER_SIZE + outputAdjList.getKmerSize());
-
- mos.getCollector("uncomplete" + I_MERGE, reporter).collect(outputKmer, outputAdjList);
- } else {
- byte nextAdj = outputAdjList.getAdjBitMap();
- byte succeed = (byte) 0x0F;
- succeed = (byte) (succeed & nextAdj);
- outputAdjList = values.next();
- byte adjBitMap = outputAdjList.getAdjBitMap();
- byte flag = outputAdjList.getFlag();
- int kmerSize = outputAdjList.getKmerSize();
- outputKmer.set(kmerFactory.mergeTwoKmer(outputAdjList.getKmer(), key));
+ outputValue = values.next();
+ byte adjBitMap = outputValue.getAdjBitMap();
+ byte flag = outputValue.getFlag();
+ outputKmer.set(kmerFactory.mergeTwoKmer(outputValue.getKmer(), key));
+
adjBitMap = (byte) (adjBitMap & 0xF0);
adjBitMap = (byte) (adjBitMap | succeed);
- outputAdjList.set(null, 0, 0, adjBitMap, flag, KMER_SIZE + kmerSize);
-
- mos.getCollector("uncomplete" + I_MERGE, reporter).collect(outputKmer, outputAdjList);
+ outputValue.set(null, 0, 0, adjBitMap, flag, 0);
+ mos.getCollector("uncomplete" + I_MERGE, reporter).collect(outputKmer, outputValue);
+ }
+ else{
+ tmpOutputValue.set(outputValue);
+ byte tmpAdjMap = tmpOutputValue.getAdjBitMap();
+
+ outputValue = values.next();
+ if(outputValue.getFlag() != 1) {
+ outputKmer.set(kmerFactory.mergeTwoKmer(tmpOutputValue.getKmer(), key));
+
+ byte nextAdj = outputValue.getAdjBitMap();
+ byte succeed = (byte) 0x0F;
+ succeed = (byte) (succeed & nextAdj);
+ tmpAdjMap = (byte) (tmpAdjMap & 0xF0);
+ tmpAdjMap = (byte) (tmpAdjMap | succeed);
+ outputValue.set(null, 0, 0, tmpAdjMap, tmpOutputValue.getFlag(), 0);
+ mos.getCollector("uncomplete" + I_MERGE, reporter).collect(outputKmer, outputValue);
+ }
+ else{
+
+ tmpKmer.set(kmerFactory.getFirstKmerFromChain(KMER_SIZE-1, key));
+ outputKmer.set(kmerFactory.mergeTwoKmer(tmpOutputValue.getKmer(), tmpKmer));
+ tmpOutputValue.set(null, 0, 0, tmpAdjMap, tmpOutputValue.getFlag(), 0);
+ mos.getCollector("complete" + I_MERGE, reporter).collect(outputKmer, tmpOutputValue);
+
+ tmpKmer.set(kmerFactory.getFirstKmerFromChain(KMER_SIZE-1, key));
+ outputKmer.set(kmerFactory.mergeTwoKmer(outputValue.getKmer(), tmpKmer));
+ outputValue.set(null, 0, 0, outputValue.getAdjBitMap(), outputValue.getFlag(), 0);
+ mos.getCollector("complete" + I_MERGE, reporter).collect(outputKmer, outputValue);
+
+ while(values.hasNext()) {
+ outputValue = values.next();
+ tmpKmer.set(kmerFactory.getFirstKmerFromChain(KMER_SIZE-1, key));
+ outputKmer.set(kmerFactory.mergeTwoKmer(outputValue.getKmer(), tmpKmer));
+ outputValue.set(null, 0, 0, outputValue.getAdjBitMap(), outputValue.getFlag(), 0);
+ mos.getCollector("complete" + I_MERGE, reporter).collect(outputKmer, outputValue);
+ }
+ }
}
} else {
- if (outputAdjList.getFlag() != 0) {
- byte adjBitMap = outputAdjList.getAdjBitMap();
- byte flag = outputAdjList.getFlag();
- int kmerSize = outputAdjList.getKmerSize();
-
- tmpKmer.set(kmerFactory.getFirstKmerFromChain(KMER_SIZE - 1, key));
- outputKmer.set(kmerFactory.mergeTwoKmer(outputAdjList.getKmer(), tmpKmer));
- outputAdjList.set(null, 0, 0, adjBitMap, flag, KMER_SIZE + kmerSize);
- mos.getCollector("complete" + I_MERGE, reporter).collect(outputKmer, outputAdjList);
+ if (outputValue.getFlag() != 0) {
+ tmpKmer.set(kmerFactory.getFirstKmerFromChain(KMER_SIZE-1, key));
+ outputKmer.set(kmerFactory.mergeTwoKmer(outputValue.getKmer(), tmpKmer));
+ outputValue.set(null, 0, 0, outputValue.getAdjBitMap(), outputValue.getFlag(), 0);
+ mos.getCollector("complete" + I_MERGE, reporter).collect(outputKmer, outputValue);
} else
- mos.getCollector("uncomplete" + I_MERGE, reporter).collect(key, outputAdjList);
+ mos.getCollector("uncomplete" + I_MERGE, reporter).collect(key, outputValue);
}
}
-
public void close() throws IOException {
// TODO Auto-generated method stub
mos.close();
diff --git a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/SNodeInitialMapper.java b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/SNodeInitialMapper.java
index ae824e7..5c4bdbe 100644
--- a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/SNodeInitialMapper.java
+++ b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/SNodeInitialMapper.java
@@ -22,8 +22,8 @@
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reporter;
-
import edu.uci.ics.genomix.type.KmerBytesWritable;
+import edu.uci.ics.genomix.type.GeneCode;
@SuppressWarnings("deprecation")
public class SNodeInitialMapper extends MapReduceBase implements
@@ -101,39 +101,34 @@
byte precursor = (byte) 0xF0;
byte succeed = (byte) 0x0F;
byte adjBitMap = value.get();
- byte flag = (byte) 0;
+ byte bitFlag = (byte) 0;
precursor = (byte) (precursor & adjBitMap);
precursor = (byte) ((precursor & 0xff) >> 4);
succeed = (byte) (succeed & adjBitMap);
boolean inDegree = measureDegree(precursor);
boolean outDegree = measureDegree(succeed);
- byte initial = 0;
- if (inDegree == true && outDegree == false) {
- flag = (byte) 2;
- switch (succeed) {
- case 1:
- initial = (byte) 0x00;
- break;
- case 2:
- initial = (byte) 0x01;
- break;
- case 4:
- initial = (byte) 0x02;
- break;
- case 8:
- initial = (byte) 0x03;
- break;
- }
- outputKmer.set(key);
- outputKmer.shiftKmerWithNextCode(initial);
- adjBitMap = (byte) (adjBitMap & 0xF0);
- outputAdjList.set(null, 0, 0, adjBitMap, flag, KMER_SIZE);
- output.collect(outputKmer, outputAdjList);
- }
+
if (inDegree == false && outDegree == false) {
outputKmer.set(key);
- outputAdjList.set(null, 0, 0, adjBitMap, flag, KMER_SIZE);
+ bitFlag = (byte) 2;
+ outputAdjList.set(null, 0, 0, adjBitMap, bitFlag, KMER_SIZE);
output.collect(outputKmer, outputAdjList);
}
+ else{
+ for(int i = 0 ; i < 4; i ++){
+ byte temp = 0x01;
+ byte shiftedCode = 0;
+ temp = (byte)(temp << i);
+ temp = (byte) (succeed & temp);
+ if(temp != 0 ){
+ byte succeedCode = GeneCode.getGeneCodeFromBitMap(temp);
+ shiftedCode = key.shiftKmerWithNextCode(succeedCode);
+ outputKmer.set(key);
+ outputAdjList.set(null, 0, 0, (byte)0, bitFlag, KMER_SIZE);
+ output.collect(outputKmer, outputAdjList);
+ key.shiftKmerWithPreCode(shiftedCode);
+ }
+ }
+ }
}
}
diff --git a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/SNodeInitialReducer.java b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/SNodeInitialReducer.java
index 734abd6..42badf5 100644
--- a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/SNodeInitialReducer.java
+++ b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/SNodeInitialReducer.java
@@ -16,50 +16,50 @@
import java.io.IOException;
import java.util.Iterator;
-
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
-
import edu.uci.ics.genomix.type.KmerBytesWritable;
+import edu.uci.ics.genomix.type.VKmerBytesWritable;
@SuppressWarnings("deprecation")
public class SNodeInitialReducer extends MapReduceBase implements
- Reducer<KmerBytesWritable, MergePathValueWritable, KmerBytesWritable, MergePathValueWritable> {
- private MergePathValueWritable outputAdjList = new MergePathValueWritable();
+ Reducer<KmerBytesWritable, MergePathValueWritable, VKmerBytesWritable, MergePathValueWritable> {
+ private VKmerBytesWritable outputKmer = new VKmerBytesWritable();
+ private MergePathValueWritable outputValue = new MergePathValueWritable();
@Override
public void reduce(KmerBytesWritable key, Iterator<MergePathValueWritable> values,
- OutputCollector<KmerBytesWritable, MergePathValueWritable> output, Reporter reporter) throws IOException {
- outputAdjList = values.next();
+ OutputCollector<VKmerBytesWritable, MergePathValueWritable> output, Reporter reporter) throws IOException {
+ outputKmer.set(key);
+ outputValue = values.next();
if (values.hasNext() == true) {
- if (outputAdjList.getFlag() != 2) {
- byte adjBitMap = outputAdjList.getAdjBitMap();
- int kmerSize = outputAdjList.getKmerSize();
+ if (outputValue.getFlag() == 2) {
byte bitFlag = 1;
- outputAdjList.set(null, 0, 0, adjBitMap, bitFlag, kmerSize);
- output.collect(key, outputAdjList);
-
+ outputValue.set(null, 0, 0, outputValue.getAdjBitMap(), bitFlag, outputValue.getKmerLength());
+ output.collect(outputKmer, outputValue);
} else {
boolean flag = false;
while (values.hasNext()) {
- outputAdjList = values.next();
- if (outputAdjList.getFlag() != 2) {
+ outputValue = values.next();
+ if (outputValue.getFlag() == 2) {
flag = true;
break;
}
}
if (flag == true) {
- byte adjBitMap = outputAdjList.getAdjBitMap();
- int kmerSize = outputAdjList.getKmerSize();
byte bitFlag = 1;
- outputAdjList.set(null, 0, 0, adjBitMap, bitFlag, kmerSize);
- output.collect(key, outputAdjList);
+ outputValue.set(null, 0, 0, outputValue.getAdjBitMap(), bitFlag, outputValue.getKmerLength());
+ output.collect(outputKmer, outputValue);
}
}
} else {
- output.collect(key, outputAdjList);
+ if (outputValue.getFlag() == 2) {
+ byte bitFlag = 0;
+ outputValue.set(null, 0, 0, outputValue.getAdjBitMap(), bitFlag, outputValue.getKmerLength());
+ output.collect(outputKmer, outputValue);
+ }
}
}
}
diff --git a/genomix/genomix-hadoop/testactual/source.txt b/genomix/genomix-hadoop/testactual/source.txt
deleted file mode 100644
index aa7a107..0000000
--- a/genomix/genomix-hadoop/testactual/source.txt
+++ /dev/null
@@ -1,3 +0,0 @@
-ATAGAAGATCGA A|T 1
-AATAGAAGATCG |A 1
-TAGAAGATCGAT A| 1