Merge branch 'fullstack_genomix' of https://code.google.com/p/hyracks into fullstack_genomix
diff --git a/genomix/genomix-hadoop/actual1/conf.xml b/genomix/genomix-hadoop/actual1/conf.xml
index 506913d..ea51bd0 100644
--- a/genomix/genomix-hadoop/actual1/conf.xml
+++ b/genomix/genomix-hadoop/actual1/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:61115</value></property>
+<property><name>fs.default.name</name><value>hdfs://localhost:54837</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:61116</value></property>
+<property><name>dfs.http.address</name><value>localhost:54838</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/actual1/result1/.part-00000.crc b/genomix/genomix-hadoop/actual1/result1/.part-00000.crc
index 3422e04..93d0276 100644
--- a/genomix/genomix-hadoop/actual1/result1/.part-00000.crc
+++ b/genomix/genomix-hadoop/actual1/result1/.part-00000.crc
Binary files differ
diff --git a/genomix/genomix-hadoop/actual1/result1/part-00000 b/genomix/genomix-hadoop/actual1/result1/part-00000
index c21f5f6..57a1fd6 100755
--- a/genomix/genomix-hadoop/actual1/result1/part-00000
+++ b/genomix/genomix-hadoop/actual1/result1/part-00000
Binary files differ
diff --git a/genomix/genomix-hadoop/actual2/conf.xml b/genomix/genomix-hadoop/actual2/conf.xml
index ff11b9e..e8ae529 100644
--- a/genomix/genomix-hadoop/actual2/conf.xml
+++ b/genomix/genomix-hadoop/actual2/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:61195</value></property>
+<property><name>fs.default.name</name><value>hdfs://localhost:54877</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:61196</value></property>
+<property><name>dfs.http.address</name><value>localhost:54878</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/actual2/result2/.part-00000.crc b/genomix/genomix-hadoop/actual2/result2/.part-00000.crc
index 3f8c2c5..9019bf8 100644
--- a/genomix/genomix-hadoop/actual2/result2/.part-00000.crc
+++ b/genomix/genomix-hadoop/actual2/result2/.part-00000.crc
Binary files differ
diff --git a/genomix/genomix-hadoop/actual2/result2/part-00000 b/genomix/genomix-hadoop/actual2/result2/part-00000
index ea3e875..c72ced3 100755
--- a/genomix/genomix-hadoop/actual2/result2/part-00000
+++ b/genomix/genomix-hadoop/actual2/result2/part-00000
Binary files differ
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..3434825 100644
--- a/genomix/genomix-hadoop/actual3/conf.xml
+++ b/genomix/genomix-hadoop/actual3/conf.xml
@@ -12,7 +12,11 @@
<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>
+<<<<<<< Updated upstream
+<property><name>fs.default.name</name><value>hdfs://localhost:55383</value></property>
+=======
+<property><name>fs.default.name</name><value>hdfs://localhost:50310</value></property>
+>>>>>>> Stashed changes
<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 +129,11 @@
<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>
+<<<<<<< Updated upstream
+<property><name>dfs.http.address</name><value>localhost:55384</value></property>
+=======
+<property><name>dfs.http.address</name><value>localhost:50311</value></property>
+>>>>>>> Stashed changes
<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/compare/result3/comparesource.txt b/genomix/genomix-hadoop/compare/result3/comparesource.txt
index 5f9dd78..ea6c574 100644
--- a/genomix/genomix-hadoop/compare/result3/comparesource.txt
+++ b/genomix/genomix-hadoop/compare/result3/comparesource.txt
@@ -1 +1,2 @@
-02 71 66 1
+CATC 68 1
+TCG 18 0
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..e0bf627
--- /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..325c6de
--- /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..dd6c872
--- /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..5e0c641
--- /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..4f27e83
--- /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..8f46380
--- /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/gbresultschecking/.DS_Store b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/gbresultschecking/.DS_Store
new file mode 100644
index 0000000..f5eb144
--- /dev/null
+++ b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/gbresultschecking/.DS_Store
Binary files differ
diff --git a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/.DS_Store b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/.DS_Store
new file mode 100644
index 0000000..f9e3926
--- /dev/null
+++ b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/.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..31995b6 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
@@ -23,12 +23,15 @@
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;
import edu.uci.ics.genomix.type.KmerBytesWritable;
+import edu.uci.ics.genomix.type.VKmerBytesWritable;
@SuppressWarnings("deprecation")
public class MergePathDriver {
@@ -74,7 +77,7 @@
conf.setInputFormat(SequenceFileInputFormat.class);
conf.setOutputFormat(SequenceFileOutputFormat.class);
- conf.setOutputKeyClass(KmerBytesWritable.class);
+ conf.setOutputKeyClass(VKmerBytesWritable.class);
conf.setOutputValueClass(MergePathValueWritable.class);
FileInputFormat.setInputPaths(conf, new Path(inputPath));
@@ -83,8 +86,9 @@
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);
@@ -98,24 +102,23 @@
conf.setMapperClass(MergePathMapper.class);
conf.setReducerClass(MergePathReducer.class);
- conf.setMapOutputKeyClass(KmerBytesWritable.class);
+ conf.setMapOutputKeyClass(VKmerBytesWritable.class);
conf.setMapOutputValueClass(MergePathValueWritable.class);
conf.setInputFormat(SequenceFileInputFormat.class);
- conf.setOutputFormat(MultipleSequenceFileOutputFormat.class);
String uncomplete = "uncomplete" + iMerge;
String complete = "complete" + iMerge;
MultipleOutputs.addNamedOutput(conf, uncomplete,
- MergePathMultiSeqOutputFormat.class, KmerBytesWritable.class,
+ MergePathMultiSeqOutputFormat.class, VKmerBytesWritable.class,
MergePathValueWritable.class);
MultipleOutputs.addNamedOutput(conf, complete,
- MergePathMultiSeqOutputFormat.class, KmerBytesWritable.class,
+ MergePathMultiTextOutputFormat.class, VKmerBytesWritable.class,
MergePathValueWritable.class);
- conf.setOutputKeyClass(KmerBytesWritable.class);
+ conf.setOutputKeyClass(VKmerBytesWritable.class);
conf.setOutputValueClass(MergePathValueWritable.class);
FileInputFormat.setInputPaths(conf, new Path(inputPath + "-step1"));
@@ -127,6 +130,46 @@
dfs.rename(new Path(outputPath + "/" + uncomplete), new Path(inputPath + "-step1"));
dfs.rename(new Path(outputPath + "/" + complete), new Path(mergeResultPath + "/" + complete));
}
+ /*----------------------------------------*/
+ conf = new JobConf(MergePathDriver.class);
+ conf.setInt("sizeKmer", sizeKmer);
+ conf.setInt("iMerge", iMerge);
+
+ if (defaultConfPath != null) {
+ conf.addResource(new Path(defaultConfPath));
+ }
+ conf.setJobName("Path Merge");
+
+ conf.setMapperClass(MergePathMapper.class);
+ conf.setReducerClass(MergePathReducer.class);
+
+ conf.setMapOutputKeyClass(VKmerBytesWritable.class);
+ conf.setMapOutputValueClass(MergePathValueWritable.class);
+
+ conf.setInputFormat(SequenceFileInputFormat.class);
+
+ String uncomplete = "uncomplete" + iMerge;
+ String complete = "complete" + iMerge;
+
+ MultipleOutputs.addNamedOutput(conf, uncomplete,
+ MergePathMultiTextOutputFormat.class, VKmerBytesWritable.class,
+ MergePathValueWritable.class);
+
+ MultipleOutputs.addNamedOutput(conf, complete,
+ MergePathMultiTextOutputFormat.class, VKmerBytesWritable.class,
+ MergePathValueWritable.class);
+
+ conf.setOutputKeyClass(VKmerBytesWritable.class);
+ conf.setOutputValueClass(MergePathValueWritable.class);
+
+ FileInputFormat.setInputPaths(conf, new Path(inputPath + "-step1"));
+ FileOutputFormat.setOutputPath(conf, new Path(outputPath));
+ conf.setNumReduceTasks(numReducers);
+ dfs.delete(new Path(outputPath), true);
+ JobClient.runJob(conf);
+ dfs.delete(new Path(inputPath + "-step1"), true);
+ dfs.rename(new Path(outputPath + "/" + uncomplete), new Path(inputPath + "-step1"));
+ dfs.rename(new Path(outputPath + "/" + complete), new Path(mergeResultPath + "/" + complete));
}
public static void main(String[] args) throws Exception {
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..fb55e18 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
@@ -20,32 +20,31 @@
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reporter;
-
import edu.uci.ics.genomix.type.GeneCode;
-import edu.uci.ics.genomix.type.KmerBytesWritable;
import edu.uci.ics.genomix.type.VKmerBytesWritable;
import edu.uci.ics.genomix.type.VKmerBytesWritableFactory;
@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;
@@ -54,19 +53,18 @@
precursor = (byte) (precursor & adjBitMap);
precursor = (byte) ((precursor & 0xff) >> 4);
succeed = (byte) (succeed & adjBitMap);
-
- if (bitFlag == 1) {
+ if (bitFlag == 1) {
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..921b233 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
@@ -22,19 +22,18 @@
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.lib.MultipleOutputs;
-
-import edu.uci.ics.genomix.type.KmerBytesWritable;
import edu.uci.ics.genomix.type.VKmerBytesWritable;
import edu.uci.ics.genomix.type.VKmerBytesWritableFactory;
@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 +41,8 @@
mos = new MultipleOutputs(job);
I_MERGE = Integer.parseInt(job.get("iMerge"));
KMER_SIZE = job.getInt("sizeKmer", 0);
- outputAdjList = new MergePathValueWritable();
+ outputValue = new MergePathValueWritable();
+ tmpOutputValue = new MergePathValueWritable();
kmerFactory = new VKmerBytesWritableFactory(KMER_SIZE);
outputKmer = new VKmerBytesWritable(KMER_SIZE);
tmpKmer = new VKmerBytesWritable(KMER_SIZE);
@@ -50,58 +50,73 @@
@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 {
- if (outputAdjList.getFlag() != 0) {
- byte adjBitMap = outputAdjList.getAdjBitMap();
- byte flag = outputAdjList.getFlag();
- int kmerSize = outputAdjList.getKmerSize();
+ else{
+ tmpOutputValue.set(outputValue);
+ byte tmpAdjMap = tmpOutputValue.getAdjBitMap();
- 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);
+ 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 (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/MergePathValueWritable.java b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/MergePathValueWritable.java
index c5ff116..5f04565 100644
--- a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/MergePathValueWritable.java
+++ b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmerging/MergePathValueWritable.java
@@ -28,115 +28,61 @@
public class MergePathValueWritable extends BinaryComparable implements WritableComparable<BinaryComparable> {
private static final byte[] EMPTY_BYTES = {};
- private int size;
- private byte[] bytes;
-
private byte adjBitMap;
private byte flag;
- private int kmerSize;
-
private VKmerBytesWritable kmer;
public MergePathValueWritable() {
- this((byte) 0, (byte) 0, (byte) 0, EMPTY_BYTES);
+ this((byte) 0, (byte) 0, 0, EMPTY_BYTES);
}
- public MergePathValueWritable(byte adjBitMap, byte flag, byte kmerSize, byte[] bytes) {
+ public MergePathValueWritable(byte adjBitMap, byte flag, int kmerSize, byte[] bytes) {
this.adjBitMap = adjBitMap;
this.flag = flag;
- this.kmerSize = kmerSize;
-
- this.bytes = bytes;
- this.size = bytes.length;
- this.kmer = new VKmerBytesWritable(kmerSize);
+ this.kmer = new VKmerBytesWritable(kmerSize, bytes);
kmer.set(bytes, 0, bytes.length);
}
- public void setSize(int size) {
- if (size > getCapacity()) {
- setCapacity(size * 3 / 2);
- }
- this.size = size;
+ public void set (MergePathValueWritable right) {
+ set(right.getBytes(), 0, right.getLength(), right.getAdjBitMap(), right.getFlag(), right.getKmerLength());
}
-
- public int getCapacity() {
- return bytes.length;
- }
-
- public void setCapacity(int new_cap) {
- if (new_cap != getCapacity()) {
- byte[] new_data = new byte[new_cap];
- if (new_cap < size) {
- size = new_cap;
- }
- if (size != 0) {
- System.arraycopy(bytes, 0, new_data, 0, size);
- }
- bytes = new_data;
- }
- }
-
- public void set(MergePathValueWritable newData) {
- set(newData.bytes, 0, newData.size, newData.adjBitMap, newData.flag, newData.kmerSize);
- }
-
public void set(KmerBytesWritable mergedKmer, byte adjBitMap, byte bitFlag) {
- set(mergedKmer.getBytes(),0,mergedKmer.getLength(), adjBitMap, bitFlag, mergedKmer.getKmerLength());
+ set(mergedKmer.getBytes(), 0, mergedKmer.getLength(), adjBitMap, bitFlag, mergedKmer.getKmerLength());
}
public void set(byte[] newData, int offset, int length, byte adjBitMap, byte flag, int kmerSize) {
- setSize(0);
if (length != 0) {
- setSize(length);
- System.arraycopy(newData, offset, bytes, 0, size);
kmer.set(kmerSize, newData, offset, length);
}
- this.adjBitMap = adjBitMap;
- this.flag = flag;
- this.kmerSize = kmerSize;
- }
-
- public KmerBytesWritable getKmer(){
- if (size != 0){
- return kmer;
- }
- return null;
+ this.adjBitMap = adjBitMap;
+ this.flag = flag;
}
@Override
public void readFields(DataInput arg0) throws IOException {
// TODO Auto-generated method stub
- setSize(0); // clear the old data
- setSize(arg0.readInt());
- if(size != 0){
- arg0.readFully(bytes, 0, size);
- kmer.set(bytes,0,size);
- }
+ kmer.readFields(arg0);
adjBitMap = arg0.readByte();
flag = arg0.readByte();
- kmerSize = arg0.readInt();
}
@Override
public void write(DataOutput arg0) throws IOException {
// TODO Auto-generated method stub
- arg0.writeInt(size);
- arg0.write(bytes, 0, size);
+ kmer.write(arg0);
arg0.writeByte(adjBitMap);
arg0.writeByte(flag);
- arg0.writeInt(kmerSize);
}
- @Override
- public byte[] getBytes() {
- // TODO Auto-generated method stub
- return bytes;
+ public KmerBytesWritable getKmer() {
+ if (kmer.getLength() != 0) {
+ return kmer;
+ }
+ return null;
}
-
- @Override
- public int getLength() {
- // TODO Auto-generated method stub
- return size;
+
+ public int getKmerLength() {
+ return kmer.getKmerLength();
}
public byte getAdjBitMap() {
@@ -147,26 +93,22 @@
return this.flag;
}
- public int getKmerSize() {
- return this.kmerSize;
- }
-
public String toString() {
- StringBuffer sb = new StringBuffer(3 * size);
- for (int idx = 0; idx < size; idx++) {
- // if not the first, put a blank separator in
- if (idx != 0) {
- sb.append(' ');
- }
- String num = Integer.toHexString(0xff & bytes[idx]);
- // if it is only one digit, add a leading 0.
- if (num.length() < 2) {
- sb.append('0');
- }
- sb.append(num);
- }
- return GeneCode.getSymbolFromBitMap(adjBitMap) + '\t' + String.valueOf(flag) + '\t' + sb.toString();
+ return GeneCode.getSymbolFromBitMap(adjBitMap) + '\t' + String.valueOf(flag);
}
-
+ @Override
+ public byte[] getBytes() {
+ // TODO Auto-generated method stub
+ if (kmer.getLength() != 0) {
+ return kmer.getBytes();
+ } else
+ return null;
+ }
+
+
+ @Override
+ public int getLength() {
+ return kmer.getLength();
+ }
}
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..617ecf0 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
@@ -97,43 +97,36 @@
@Override
public void map(KmerBytesWritable key, ByteWritable value,
OutputCollector<KmerBytesWritable, MergePathValueWritable> output, Reporter reporter) throws IOException {
-
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);///~~~~~kmersize----->0
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..2723b47 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 +16,51 @@
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());///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/src/main/java/edu/uci/ics/pathmergingh2/.DS_Store b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/.DS_Store
new file mode 100644
index 0000000..7c4ae29
--- /dev/null
+++ b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/.DS_Store
Binary files differ
diff --git a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/ENodeInitialReducer.java b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/ENodeInitialReducer.java
new file mode 100644
index 0000000..b955fcd
--- /dev/null
+++ b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/ENodeInitialReducer.java
@@ -0,0 +1,59 @@
+package edu.uci.ics.pathmergingh2;
+
+import java.io.IOException;
+import java.util.Iterator;
+import org.apache.hadoop.io.BytesWritable;
+import org.apache.hadoop.mapred.JobConf;
+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.KmerUtil;
+
+@SuppressWarnings("deprecation")
+public class ENodeInitialReducer extends MapReduceBase implements
+ Reducer<BytesWritable, MergePathValueWritable, BytesWritable, MergePathValueWritable> {
+ public BytesWritable outputKmer = new BytesWritable();
+ public MergePathValueWritable outputAdjList = new MergePathValueWritable();
+
+
+ @Override
+ public void reduce(BytesWritable key, Iterator<MergePathValueWritable> values,
+ OutputCollector<BytesWritable, MergePathValueWritable> output, Reporter reporter) throws IOException {
+ outputAdjList = values.next();
+ outputKmer.set(key);
+ if (values.hasNext() == true) {
+ byte bitFlag = outputAdjList.getFlag();
+ bitFlag = (byte) (bitFlag & 0xFE);
+ if (bitFlag == 2) {
+ bitFlag = (byte) (0x80 | outputAdjList.getFlag());
+ outputAdjList.set(null, 0, 0, outputAdjList.getAdjBitMap(), bitFlag, outputAdjList.getKmerLength());
+ output.collect(outputKmer, outputAdjList);
+
+ } else {
+ boolean flag = false;
+ while (values.hasNext()) {
+ outputAdjList = values.next();
+ if (outputAdjList.getFlag() == 2) {
+ flag = true;
+ break;
+ }
+ }
+ if (flag == true) {
+ bitFlag = (byte) (0x80 | outputAdjList.getFlag());
+ outputAdjList.set(null, 0, 0, outputAdjList.getAdjBitMap(), bitFlag, outputAdjList.getKmerLength());
+ output.collect(outputKmer, outputAdjList);
+ }
+ }
+ } else {
+ byte bitFlag = outputAdjList.getFlag();
+ bitFlag = (byte) (bitFlag & 0xFE);
+ if (bitFlag == 2) {
+ bitFlag = 0;
+ outputAdjList.set(null, 0, 0, outputAdjList.getAdjBitMap(), bitFlag, outputAdjList.getKmerLength());
+ output.collect(outputKmer, outputAdjList);
+ }
+ }
+ }
+}
+
diff --git a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/MergePathH2Driver.java b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/MergePathH2Driver.java
new file mode 100644
index 0000000..ca7f259
--- /dev/null
+++ b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/MergePathH2Driver.java
@@ -0,0 +1,163 @@
+package edu.uci.ics.pathmergingh2;
+
+import java.io.IOException;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.mapred.FileInputFormat;
+import org.apache.hadoop.mapred.FileOutputFormat;
+import org.apache.hadoop.mapred.JobClient;
+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;
+import edu.uci.ics.genomix.type.KmerBytesWritable;
+import edu.uci.ics.genomix.type.VKmerBytesWritable;
+
+@SuppressWarnings("deprecation")
+public class MergePathH2Driver {
+
+ private static class Options {
+ @Option(name = "-inputpath", usage = "the input path", required = true)
+ public String inputPath;
+
+ @Option(name = "-outputpath", usage = "the output path", required = true)
+ public String outputPath;
+
+ @Option(name = "-mergeresultpath", usage = "the merging results path", required = true)
+ public String mergeResultPath;
+
+ @Option(name = "-num-reducers", usage = "the number of reducers", required = true)
+ public int numReducers;
+
+ @Option(name = "-kmer-size", usage = "the size of kmer", required = true)
+ public int sizeKmer;
+
+ @Option(name = "-merge-rounds", usage = "the while rounds of merging", required = true)
+ public int mergeRound;
+
+ }
+
+
+ public void run(String inputPath, String outputPath, String mergeResultPath, int numReducers, int sizeKmer, int mergeRound, String defaultConfPath)
+ throws IOException{
+
+ JobConf conf = new JobConf(MergePathH2Driver.class);
+ conf.setInt("sizeKmer", sizeKmer);
+
+ if (defaultConfPath != null) {
+ conf.addResource(new Path(defaultConfPath));
+ }
+ conf.setJobName("Initial Path-Starting-Points Table");
+ conf.setMapperClass(SNodeInitialMapper.class);
+ conf.setReducerClass(SNodeInitialReducer.class);
+
+ conf.setMapOutputKeyClass(KmerBytesWritable.class);
+ conf.setMapOutputValueClass(MergePathValueWritable.class);
+
+ conf.setInputFormat(SequenceFileInputFormat.class);
+ conf.setOutputFormat(TextOutputFormat.class);
+
+ conf.setOutputKeyClass(VKmerBytesWritable.class);
+ conf.setOutputValueClass(MergePathValueWritable.class);
+
+ FileInputFormat.setInputPaths(conf, new Path(inputPath));
+ FileOutputFormat.setOutputPath(conf, new Path(outputPath));
+ conf.setNumReduceTasks(numReducers);
+ FileSystem dfs = FileSystem.get(conf);
+ dfs.delete(new Path(outputPath), true);
+ JobClient.runJob(conf);
+ int iMerge = 0;
+/*----------------------------------------------------------------------*/
+/* for(iMerge = 0; iMerge < mergeRound; iMerge ++){
+
+ conf = new JobConf(MergePathDriver.class);
+ conf.setInt("sizeKmer", sizeKmer);
+ conf.setInt("iMerge", iMerge);
+
+ if (defaultConfPath != null) {
+ conf.addResource(new Path(defaultConfPath));
+ }
+ conf.setJobName("Path Merge");
+
+ conf.setMapperClass(MergePathMapper.class);
+ conf.setReducerClass(MergePathReducer.class);
+
+ conf.setMapOutputKeyClass(VKmerBytesWritable.class);
+ conf.setMapOutputKeyClass(BytesWritable.class);
+
+<<<<<<< Updated upstream
+ MergePathMultiSeqOutputFormat.class, VKmerBytesWritable.class,
+ MergePathValueWritable.class);
+
+ MultipleOutputs.addNamedOutput(conf, complete,
+ MergePathMultiTextOutputFormat.class, VKmerBytesWritable.class,
+ MergePathValueWritable.class);
+
+ conf.setOutputKeyClass(VKmerBytesWritable.class);
+ conf.setOutputValueClass(MergePathValueWritable.class);
+
+ FileInputFormat.setInputPaths(conf, new Path(inputPath + "-step1"));
+ FileOutputFormat.setOutputPath(conf, new Path(outputPath));
+ conf.setNumReduceTasks(numReducers);
+ dfs.delete(new Path(outputPath), true);
+ JobClient.runJob(conf);
+ dfs.delete(new Path(inputPath + "-step1"), true);
+ dfs.rename(new Path(outputPath + "/" + uncomplete), new Path(inputPath + "-step1"));
+ dfs.rename(new Path(outputPath + "/" + complete), new Path(mergeResultPath + "/" + complete));
+<<<<<<< Updated upstream
+ }
+
+ conf = new JobConf(MergePathDriver.class);
+ conf.setInt("sizeKmer", sizeKmer);
+ conf.setInt("iMerge", iMerge);
+
+ if (defaultConfPath != null) {
+ conf.addResource(new Path(defaultConfPath));
+ }
+ conf.setJobName("Path Merge");
+
+ conf.setMapperClass(MergePathMapper.class);
+ conf.setReducerClass(MergePathReducer.class);
+
+ conf.setMapOutputKeyClass(VKmerBytesWritable.class);
+ conf.setMapOutputValueClass(MergePathValueWritable.class);
+
+ conf.setInputFormat(SequenceFileInputFormat.class);
+
+ String uncomplete = "uncomplete" + iMerge;
+ String complete = "complete" + iMerge;
+
+ MultipleOutputs.addNamedOutput(conf, uncomplete,
+ MergePathMultiTextOutputFormat.class, VKmerBytesWritable.class,
+ MergePathValueWritable.class);
+
+ MultipleOutputs.addNamedOutput(conf, complete,
+ MergePathMultiTextOutputFormat.class, VKmerBytesWritable.class,
+ MergePathValueWritable.class);
+
+ conf.setOutputKeyClass(VKmerBytesWritable.class);
+ conf.setOutputValueClass(MergePathValueWritable.class);
+
+ FileInputFormat.setInputPaths(conf, new Path(inputPath + "-step1"));
+ FileOutputFormat.setOutputPath(conf, new Path(outputPath));
+ conf.setNumReduceTasks(numReducers);
+ dfs.delete(new Path(outputPath), true);
+ JobClient.runJob(conf);
+ dfs.delete(new Path(inputPath + "-step1"), true);
+ dfs.rename(new Path(outputPath + "/" + uncomplete), new Path(inputPath + "-step1"));
+ dfs.rename(new Path(outputPath + "/" + complete), new Path(mergeResultPath + "/" + complete));*/
+ }
+
+ public static void main(String[] args) throws Exception {
+ Options options = new Options();
+ CmdLineParser parser = new CmdLineParser(options);
+ parser.parseArgument(args);
+ MergePathH2Driver driver = new MergePathH2Driver();
+ driver.run(options.inputPath, options.outputPath, options.mergeResultPath, options.numReducers, options.sizeKmer, options.mergeRound, null);
+ }
+}
diff --git a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/MergePathH2Mapper.java b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/MergePathH2Mapper.java
new file mode 100644
index 0000000..de7ecfc
--- /dev/null
+++ b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/MergePathH2Mapper.java
@@ -0,0 +1,86 @@
+package edu.uci.ics.pathmergingh2;
+
+import java.io.IOException;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.MapReduceBase;
+import org.apache.hadoop.mapred.Mapper;
+import org.apache.hadoop.mapred.OutputCollector;
+import org.apache.hadoop.mapred.Reporter;
+import edu.uci.ics.genomix.type.GeneCode;
+import edu.uci.ics.genomix.type.VKmerBytesWritable;
+import edu.uci.ics.genomix.type.VKmerBytesWritableFactory;
+
+@SuppressWarnings("deprecation")
+public class MergePathH2Mapper extends MapReduceBase implements
+ Mapper<VKmerBytesWritable, MergePathValueWritable, VKmerBytesWritable, MergePathValueWritable> {
+
+ private int KMER_SIZE;
+ private VKmerBytesWritableFactory outputKmerFactory;
+ 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);
+ outputValue = new MergePathValueWritable();
+ tmpKmer = new VKmerBytesWritable(KMER_SIZE);
+ outputKmer = new VKmerBytesWritable(KMER_SIZE);
+ }
+
+ @Override
+ public void map(VKmerBytesWritable key, MergePathValueWritable value,
+ OutputCollector<VKmerBytesWritable, MergePathValueWritable> output, Reporter reporter) throws IOException {
+ byte precursor = (byte) 0xF0;
+ byte succeed = (byte) 0x0F;
+ byte adjBitMap = value.getAdjBitMap();
+ byte bitFlag = value.getFlag();
+ precursor = (byte) (precursor & adjBitMap);
+ precursor = (byte) ((precursor & 0xff) >> 4);
+ succeed = (byte) (succeed & adjBitMap);
+ byte bitStartEnd = (byte) (0x81 & bitFlag);
+
+ switch (bitStartEnd) {
+ case (byte) 0x01:
+ byte succeedCode = GeneCode.getGeneCodeFromBitMap(succeed);
+ tmpKmer.set(outputKmerFactory.getLastKmerFromChain(KMER_SIZE, key));
+ outputKmer.set(outputKmerFactory.shiftKmerWithNextCode(tmpKmer, succeedCode));
+
+ tmpKmer.set(outputKmerFactory.getFirstKmerFromChain(key.getKmerLength() - (KMER_SIZE - 1), key));
+ bitFlag = (byte) (bitFlag | 0x08);
+ outputValue.set(tmpKmer, adjBitMap, bitFlag);
+ output.collect(outputKmer, outputValue);
+ break;
+ case (byte) 0x80:
+ tmpKmer.set(outputKmerFactory.getFirstKmerFromChain(KMER_SIZE, key));
+ outputKmer.set(tmpKmer);//?????
+ tmpKmer.set(outputKmerFactory.getLastKmerFromChain(key.getKmerLength() - KMER_SIZE, key));
+ bitFlag = (byte) (bitFlag | 0x10);
+ outputValue.set(tmpKmer, adjBitMap, bitFlag);
+ output.collect(outputKmer, outputValue);
+ break;
+ case (byte) 0x00:
+ succeedCode = GeneCode.getGeneCodeFromBitMap(succeed);
+ tmpKmer.set(outputKmerFactory.getLastKmerFromChain(KMER_SIZE, key));
+ outputKmer.set(outputKmerFactory.shiftKmerWithNextCode(tmpKmer, succeedCode));
+
+ tmpKmer.set(outputKmerFactory.getFirstKmerFromChain(key.getKmerLength() - (KMER_SIZE - 1), key));
+ bitFlag = (byte) (bitFlag | 0x08);
+ outputValue.set(tmpKmer, adjBitMap, bitFlag);
+ output.collect(outputKmer, outputValue);
+
+ bitFlag = (byte) (bitFlag & 0xF7);
+ tmpKmer.set(outputKmerFactory.getFirstKmerFromChain(KMER_SIZE, key));
+ outputKmer.set(tmpKmer);//?????
+ tmpKmer.set(outputKmerFactory.getLastKmerFromChain(key.getKmerLength() - KMER_SIZE, key));
+ bitFlag = (byte) (bitFlag | 0x10);
+ outputValue.set(tmpKmer, adjBitMap, bitFlag);
+ output.collect(outputKmer, outputValue);
+ break;
+ case (byte) 0x81:
+ outputKmer.set(key);
+ outputValue.set(null, 0, 0, adjBitMap, bitFlag, 0);//????????
+ break;
+ }
+ }
+}
diff --git a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/MergePathH2Reducer.java b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/MergePathH2Reducer.java
new file mode 100644
index 0000000..5d5b872
--- /dev/null
+++ b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/MergePathH2Reducer.java
@@ -0,0 +1,100 @@
+package edu.uci.ics.pathmergingh2;
+
+import java.io.IOException;
+import java.util.Iterator;
+
+import org.apache.hadoop.mapred.JobConf;
+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 org.apache.hadoop.mapred.lib.MultipleOutputs;
+import edu.uci.ics.genomix.type.VKmerBytesWritable;
+import edu.uci.ics.genomix.type.VKmerBytesWritableFactory;
+
+@SuppressWarnings("deprecation")
+public class MergePathH2Reducer extends MapReduceBase implements
+ Reducer<VKmerBytesWritable, MergePathValueWritable, VKmerBytesWritable, MergePathValueWritable> {
+ private VKmerBytesWritableFactory kmerFactory;
+ private VKmerBytesWritable outputKmer;
+ private VKmerBytesWritable tmpKmer1;
+ private VKmerBytesWritable tmpKmer2;
+ private int KMER_SIZE;
+ private MergePathValueWritable outputValue;
+ private MergePathValueWritable tmpOutputValue;
+
+ MultipleOutputs mos = null;
+ private int I_MERGE;
+
+
+ public void configure(JobConf job) {
+ mos = new MultipleOutputs(job);
+ I_MERGE = Integer.parseInt(job.get("iMerge"));
+ KMER_SIZE = job.getInt("sizeKmer", 0);
+ outputValue = new MergePathValueWritable();
+ tmpOutputValue = new MergePathValueWritable();
+ kmerFactory = new VKmerBytesWritableFactory(KMER_SIZE);
+ outputKmer = new VKmerBytesWritable(KMER_SIZE);
+ tmpKmer1 = new VKmerBytesWritable(KMER_SIZE);
+ tmpKmer2 = new VKmerBytesWritable(KMER_SIZE);
+ }
+
+ @SuppressWarnings("unchecked")
+ public void reduce(VKmerBytesWritable key, Iterator<MergePathValueWritable> values,
+ OutputCollector<VKmerBytesWritable, MergePathValueWritable> output, Reporter reporter) throws IOException {
+ outputValue = values.next();
+ if (values.hasNext() == true) {
+ byte bitFlag = outputValue.getFlag();
+ byte bitStartEnd = (byte) (0x81 & bitFlag);
+ byte bitPosiNegative = (byte) (0x18 & bitFlag);
+ byte succeed = (byte) 0x0F;
+
+ switch (bitPosiNegative) {
+ case (byte) 0x08:
+ tmpKmer1.set(kmerFactory.mergeTwoKmer(outputValue.getKmer(), key));
+ byte adjBitMap = outputValue.getAdjBitMap();
+ outputValue = values.next();
+ if (bitStartEnd == 0x80) {
+ tmpKmer2.set(kmerFactory.mergeTwoKmer(key, outputValue.getKmer()));
+ tmpOutputValue.set(null, 0, 0, outputValue.getAdjBitMap(), outputValue.getFlag(), 0);
+ mos.getCollector("uncomplete" + I_MERGE, reporter).collect(tmpKmer2, tmpOutputValue);
+ }
+
+ outputKmer.set(kmerFactory.mergeTwoKmer(tmpKmer1, outputValue.getKmer()));
+ succeed = (byte) (succeed & outputValue.getFlag());
+ adjBitMap = (byte) (adjBitMap & 0xF0);
+ adjBitMap = (byte) (adjBitMap | succeed);
+ byte outputFlag = (byte) (0x81 & bitFlag);
+ outputFlag = (byte) (outputFlag & outputValue.getFlag());
+ outputValue.set(null, 0, 0, adjBitMap, outputFlag, 0);
+ mos.getCollector("uncomplete" + I_MERGE, reporter).collect(outputKmer, outputValue);
+ break;
+ case (byte) 0x10:
+ tmpKmer1.set(kmerFactory.mergeTwoKmer(key, outputValue.getKmer()));
+ if (bitStartEnd == 0x80) {
+ tmpOutputValue.set(null, 0, 0, outputValue.getAdjBitMap(), outputValue.getFlag(), 0);
+ mos.getCollector("uncomplete" + I_MERGE, reporter).collect(tmpKmer1, tmpOutputValue);
+ }
+ succeed = (byte) (succeed & outputValue.getFlag());
+ outputValue = values.next();
+ outputKmer.set(kmerFactory.mergeTwoKmer(outputValue.getKmer(), tmpKmer1));
+ adjBitMap = outputValue.getAdjBitMap();
+ adjBitMap = (byte) (adjBitMap & 0xF0);
+ adjBitMap = (byte) (adjBitMap | succeed);
+ outputFlag = (byte) (0x81 & bitFlag);
+ outputFlag = (byte) (outputFlag & outputValue.getFlag());
+ outputValue.set(null, 0, 0, adjBitMap, outputFlag, 0);
+ mos.getCollector("uncomplete" + I_MERGE, reporter).collect(outputKmer, outputValue);
+ break;
+ }
+ } else {
+ byte bitFlag = outputValue.getFlag();
+ byte bitStartEnd = (byte) (0x81 & bitFlag);
+ if(bitStartEnd == 0x81) {
+ outputKmer.set(key);
+ mos.getCollector("complete" + I_MERGE, reporter).collect(outputKmer, outputValue);
+ }
+
+ }
+ }
+}
diff --git a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/MergePathMultiSeqOutputFormat.java b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/MergePathMultiSeqOutputFormat.java
new file mode 100644
index 0000000..cbde512
--- /dev/null
+++ b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/MergePathMultiSeqOutputFormat.java
@@ -0,0 +1,29 @@
+/*
+ * Copyright 2009-2012 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.pathmergingh2;
+
+import java.io.File;
+import org.apache.hadoop.io.BytesWritable;
+import org.apache.hadoop.mapred.lib.MultipleSequenceFileOutputFormat;
+
+
+public class MergePathMultiSeqOutputFormat extends MultipleSequenceFileOutputFormat<BytesWritable, MergePathValueWritable>{
+ @Override
+ protected String generateLeafFileName(String name) {
+ // TODO Auto-generated method stub System.out.println(name);
+ String[] names = name.split("-");
+ return names[0] + File.separator + name;
+ }
+}
diff --git a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/MergePathMultiTextOutputFormat.java b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/MergePathMultiTextOutputFormat.java
new file mode 100644
index 0000000..d6176e2
--- /dev/null
+++ b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/MergePathMultiTextOutputFormat.java
@@ -0,0 +1,28 @@
+/*
+ * Copyright 2009-2012 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.pathmergingh2;
+
+import java.io.File;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapred.lib.MultipleTextOutputFormat;
+
+public class MergePathMultiTextOutputFormat extends MultipleTextOutputFormat<Text, Text>{
+ @Override
+ protected String generateLeafFileName(String name) {
+ // TODO Auto-generated method stub System.out.println(name);
+ String[] names = name.split("-");
+ return names[0] + File.separator + name;
+ }
+}
diff --git a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/MergePathValueWritable.java b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/MergePathValueWritable.java
new file mode 100644
index 0000000..3faba46
--- /dev/null
+++ b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/MergePathValueWritable.java
@@ -0,0 +1,110 @@
+/*
+ * Copyright 2009-2012 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.pathmergingh2;
+
+import java.io.DataInput;
+import java.io.DataOutput;
+import java.io.IOException;
+
+import org.apache.hadoop.io.BinaryComparable;
+import org.apache.hadoop.io.WritableComparable;
+
+import edu.uci.ics.genomix.type.GeneCode;
+import edu.uci.ics.genomix.type.KmerBytesWritable;
+import edu.uci.ics.genomix.type.VKmerBytesWritable;
+
+public class MergePathValueWritable extends BinaryComparable implements WritableComparable<BinaryComparable> {
+
+ private static final byte[] EMPTY_BYTES = {};
+ private byte adjBitMap;
+ private byte flag;
+ private VKmerBytesWritable kmer;
+
+ public MergePathValueWritable() {
+ this((byte) 0, (byte) 0, 0, EMPTY_BYTES);
+ }
+
+ public MergePathValueWritable(byte adjBitMap, byte flag, int kmerSize, byte[] bytes) {
+ this.adjBitMap = adjBitMap;
+ this.flag = flag;
+ this.kmer = new VKmerBytesWritable(kmerSize, bytes);
+ kmer.set(bytes, 0, bytes.length);
+ }
+
+ public void set(MergePathValueWritable right) {
+ set(right.getAdjBitMap(), right.getFlag(), right.getKmer());
+ }
+
+ public void set(byte adjBitMap, byte flag, VKmerBytesWritable kmer) {
+ this.kmer.set(kmer);
+ this.adjBitMap = adjBitMap;
+ this.flag = flag;
+ }
+
+ @Override
+ public void readFields(DataInput arg0) throws IOException {
+ // TODO Auto-generated method stub
+ kmer.readFields(arg0);
+ adjBitMap = arg0.readByte();
+ flag = arg0.readByte();
+ }
+
+ @Override
+ public void write(DataOutput arg0) throws IOException {
+ // TODO Auto-generated method stub
+
+ kmer.write(arg0);
+ arg0.writeByte(adjBitMap);
+ arg0.writeByte(flag);
+ }
+
+ public VKmerBytesWritable getKmer() {
+ if (kmer.getLength() != 0) {
+ return kmer;
+ }
+ return null;
+ }
+
+ public byte getAdjBitMap() {
+ return this.adjBitMap;
+ }
+
+ public byte getFlag() {
+ return this.flag;
+ }
+
+ public String toString() {
+ return GeneCode.getSymbolFromBitMap(adjBitMap) + '\t' + String.valueOf(flag);
+ }
+
+ @Override
+ public byte[] getBytes() {
+ // TODO Auto-generated method stub
+ if (kmer.getLength() != 0) {
+ return kmer.getBytes();
+ } else
+ return null;
+
+ }
+
+ public int getKmerLength() {
+ return kmer.getKmerLength();
+ }
+
+ @Override
+ public int getLength() {
+ return kmer.getLength();
+ }
+}
diff --git a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/SNodeInitialMapper.java b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/SNodeInitialMapper.java
new file mode 100644
index 0000000..076b3d9
--- /dev/null
+++ b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/SNodeInitialMapper.java
@@ -0,0 +1,142 @@
+package edu.uci.ics.pathmergingh2;
+
+import java.io.IOException;
+import org.apache.hadoop.io.ByteWritable;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.MapReduceBase;
+import org.apache.hadoop.mapred.Mapper;
+import org.apache.hadoop.mapred.OutputCollector;
+import org.apache.hadoop.mapred.Reporter;
+import edu.uci.ics.genomix.type.GeneCode;
+import edu.uci.ics.genomix.type.KmerBytesWritable;
+
+@SuppressWarnings("deprecation")
+public class SNodeInitialMapper extends MapReduceBase implements
+ Mapper<KmerBytesWritable, ByteWritable, KmerBytesWritable, MergePathValueWritable> {
+
+ public int KMER_SIZE;
+ public KmerBytesWritable outputKmer;
+ public MergePathValueWritable outputAdjList;
+
+ public void configure(JobConf job) {
+ KMER_SIZE = Integer.parseInt(job.get("sizeKmer"));
+ outputKmer = new KmerBytesWritable(KMER_SIZE);
+ outputAdjList = new MergePathValueWritable();
+ }
+
+ boolean measureDegree(byte adjacent) {
+ boolean result = true;
+ switch (adjacent) {
+ case 0:
+ result = true;
+ break;
+ case 1:
+ result = false;
+ break;
+ case 2:
+ result = false;
+ break;
+ case 3:
+ result = true;
+ break;
+ case 4:
+ result = false;
+ break;
+ case 5:
+ result = true;
+ break;
+ case 6:
+ result = true;
+ break;
+ case 7:
+ result = true;
+ break;
+ case 8:
+ result = false;
+ break;
+ case 9:
+ result = true;
+ break;
+ case 10:
+ result = true;
+ break;
+ case 11:
+ result = true;
+ break;
+ case 12:
+ result = true;
+ break;
+ case 13:
+ result = true;
+ break;
+ case 14:
+ result = true;
+ break;
+ case 15:
+ result = true;
+ break;
+ }
+ return result;
+ }
+
+ @Override
+ public void map(KmerBytesWritable key, ByteWritable value,
+ OutputCollector<KmerBytesWritable, MergePathValueWritable> output, Reporter reporter) throws IOException {
+ byte precursor = (byte) 0xF0;
+ byte succeed = (byte) 0x0F;
+ byte adjBitMap = value.get();
+ 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);
+ if (key.toString().equals("CGC")) {
+ int a = 2;
+ int b = a;
+ }
+ if (key.toString().equals("TCG")) {
+ int a = 2;
+ int b = a;
+ }
+ if (inDegree == false && outDegree == false) {
+
+ outputKmer.set(key);
+ System.out.println(outputKmer.hashCode());
+ bitFlag = (byte) 2;
+ outputAdjList.set(null, 0, 0, adjBitMap, bitFlag, 0);
+ output.collect(outputKmer, outputAdjList);
+ } else {
+ for (int i = 0; i < 4; i++) {
+ byte temp = (byte) 0x01;
+ byte shiftedCode = 0;
+ temp = (byte) (temp << i);
+ temp = (byte) (precursor & temp);
+ if (temp != 0) {
+ byte precurCode = GeneCode.getGeneCodeFromBitMap(temp);
+ shiftedCode = key.shiftKmerWithPreCode(precurCode);
+ outputKmer.set(key);
+ bitFlag = (byte) 0x80;
+ outputAdjList.set(null, 0, 0, (byte) 0, bitFlag, 0);
+ output.collect(outputKmer, outputAdjList);
+ key.shiftKmerWithNextCode(shiftedCode);
+ }
+ }
+ for (int i = 0; i < 4; i++) {
+ byte temp = (byte) 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);
+ bitFlag = (byte) 0x01;
+ outputAdjList.set(null, 0, 0, (byte) 0, bitFlag, 0);
+ output.collect(outputKmer, outputAdjList);
+ key.shiftKmerWithPreCode(shiftedCode);
+ }
+ }
+ }
+ }
+}
diff --git a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/SNodeInitialReducer.java b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/SNodeInitialReducer.java
new file mode 100644
index 0000000..a858524
--- /dev/null
+++ b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/pathmergingh2/SNodeInitialReducer.java
@@ -0,0 +1,80 @@
+package edu.uci.ics.pathmergingh2;
+
+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, VKmerBytesWritable, MergePathValueWritable> {
+ private VKmerBytesWritable outputKmer = new VKmerBytesWritable();
+ private MergePathValueWritable outputValue = new MergePathValueWritable();
+
+ @Override
+ public void reduce(KmerBytesWritable key, Iterator<MergePathValueWritable> values,
+ OutputCollector<VKmerBytesWritable, MergePathValueWritable> output, Reporter reporter) throws IOException {
+ outputKmer.set(key);
+ outputValue = values.next();
+ byte startFlag = 0x00;
+ byte endFlag = 0x00;
+ byte targetPointFlag = 0x00;
+ byte targetAdjList = 0x00;
+ byte outputFlag = 0x00;
+ if(key.toString().equals("TCG")){
+ int a = 2;
+ int b = a;
+ }
+ if (values.hasNext() == true) {
+ switch (outputValue.getFlag()) {
+ case (byte) 0x01:
+ startFlag = (byte) 0x01;
+ break;
+ case (byte) 0x80:
+ endFlag = (byte) 0x80;
+ break;
+ case (byte) 0x02:
+ targetPointFlag = (byte) 0x02;
+ targetAdjList = outputValue.getAdjBitMap();
+ break;
+ }
+ while (values.hasNext()) {
+ outputValue = values.next();
+ switch (outputValue.getFlag()) {
+ case (byte) 0x01:
+ startFlag = (byte) 0x01;
+ break;
+ case (byte) 0x80:
+ endFlag = (byte) 0x80;
+ break;
+ case (byte) 0x02:
+ targetPointFlag = (byte) 0x02;
+ targetAdjList = outputValue.getAdjBitMap();
+ break;
+ }
+ if(startFlag != (byte) 0x00 && endFlag!= (byte) 0x00 && targetPointFlag != (byte) 0x00)
+ break;
+ }
+ if(targetPointFlag == (byte) 0x02) {
+ if(startFlag == (byte) 0x01) {
+ outputFlag = (byte) (outputFlag | startFlag);
+ }
+ if(endFlag == (byte) 0x80) {
+ outputFlag = (byte) (outputFlag | endFlag);
+ }
+ outputValue.set(null, 0, 0, targetAdjList, outputFlag, 0);
+ output.collect(outputKmer, outputValue);
+ }
+ } else {
+ if (outputValue.getFlag() == 2) {
+ byte bitFlag = 0;
+ outputValue.set(null, 0, 0, outputValue.getAdjBitMap(), bitFlag, 0);
+ output.collect(outputKmer, outputValue);
+ }
+ }
+ }
+}
diff --git a/genomix/genomix-hadoop/src/test/.DS_Store b/genomix/genomix-hadoop/src/test/.DS_Store
new file mode 100644
index 0000000..bfe14e8
--- /dev/null
+++ b/genomix/genomix-hadoop/src/test/.DS_Store
Binary files differ
diff --git a/genomix/genomix-hadoop/src/test/java/.DS_Store b/genomix/genomix-hadoop/src/test/java/.DS_Store
new file mode 100644
index 0000000..fb3684c
--- /dev/null
+++ b/genomix/genomix-hadoop/src/test/java/.DS_Store
Binary files differ
diff --git a/genomix/genomix-hadoop/src/test/java/edu/.DS_Store b/genomix/genomix-hadoop/src/test/java/edu/.DS_Store
new file mode 100644
index 0000000..f50e64b
--- /dev/null
+++ b/genomix/genomix-hadoop/src/test/java/edu/.DS_Store
Binary files differ
diff --git a/genomix/genomix-hadoop/src/test/java/edu/uci/.DS_Store b/genomix/genomix-hadoop/src/test/java/edu/uci/.DS_Store
new file mode 100644
index 0000000..9aea623
--- /dev/null
+++ b/genomix/genomix-hadoop/src/test/java/edu/uci/.DS_Store
Binary files differ
diff --git a/genomix/genomix-hadoop/src/test/java/edu/uci/ics/.DS_Store b/genomix/genomix-hadoop/src/test/java/edu/uci/ics/.DS_Store
new file mode 100644
index 0000000..64f18c4
--- /dev/null
+++ b/genomix/genomix-hadoop/src/test/java/edu/uci/ics/.DS_Store
Binary files differ
diff --git a/genomix/genomix-hadoop/src/test/java/edu/uci/ics/pathmerging/MergePathTest.java b/genomix/genomix-hadoop/src/test/java/edu/uci/ics/pathmerging/MergePathTest.java
index 95a9785..5e6e51e 100644
--- a/genomix/genomix-hadoop/src/test/java/edu/uci/ics/pathmerging/MergePathTest.java
+++ b/genomix/genomix-hadoop/src/test/java/edu/uci/ics/pathmerging/MergePathTest.java
@@ -18,6 +18,7 @@
import org.junit.Test;
import edu.uci.ics.genomix.type.KmerBytesWritable;
+import edu.uci.ics.genomix.type.VKmerBytesWritable;
import edu.uci.ics.utils.TestUtils;
@SuppressWarnings("deprecation")
@@ -33,7 +34,7 @@
private static final String RESULT_PATH = "/result3";
private static final String EXPECTED_PATH = "expected/result3";
private static final String TEST_SOURCE_DIR = COMPARE_DIR + RESULT_PATH + "/comparesource.txt";
- private static final int COUNT_REDUCER = 4;
+ private static final int COUNT_REDUCER = 1;
private static final int SIZE_KMER = 3;
private MiniDFSCluster dfsCluster;
@@ -48,12 +49,13 @@
startHadoop();
MergePathDriver tldriver = new MergePathDriver();
- tldriver.run(HDFS_PATH, RESULT_PATH, HDFA_PATH_DATA, COUNT_REDUCER, SIZE_KMER, 3, HADOOP_CONF_PATH);
-
- SequenceFile.Reader reader = null;
- Path path = new Path(HDFA_PATH_DATA + "/complete2" + "/complete2-r-00000");
+ tldriver.run(HDFS_PATH, RESULT_PATH, HDFA_PATH_DATA, COUNT_REDUCER, SIZE_KMER, 1, HADOOP_CONF_PATH);
+
+/* SequenceFile.Reader reader = null;
+ Path path = new Path(RESULT_PATH + "/part-00000");
+// Path path = new Path(RESULT_PATH + "/uncomplete0" + "/uncomplete0-r-00000");
reader = new SequenceFile.Reader(dfs, path, conf);
- KmerBytesWritable key = (KmerBytesWritable) ReflectionUtils.newInstance(reader.getKeyClass(), conf);
+ VKmerBytesWritable key = (VKmerBytesWritable) ReflectionUtils.newInstance(reader.getKeyClass(), conf);
MergePathValueWritable value = (MergePathValueWritable) ReflectionUtils.newInstance(reader.getValueClass(), conf);
File filePathTo = new File(TEST_SOURCE_DIR);
BufferedWriter bw = new BufferedWriter(new FileWriter(filePathTo));
@@ -61,10 +63,10 @@
bw.write(key.toString() + "\t" + value.getAdjBitMap() + "\t" + value.getFlag());
bw.newLine();
}
- bw.close();
-
+ bw.close();*/
dumpResult();
- TestUtils.compareWithResult(new File(TEST_SOURCE_DIR), new File(EXPECTED_PATH));
+
+// TestUtils.compareWithResult(new File(TEST_SOURCE_DIR), new File(EXPECTED_PATH));
cleanupHadoop();
@@ -96,7 +98,8 @@
}
private void dumpResult() throws IOException {
- Path src = new Path(HDFA_PATH_DATA + "/" + "complete2");
+// Path src = new Path(HDFA_PATH_DATA + "/" + "complete2");
+ Path src = new Path(RESULT_PATH);
Path dest = new Path(ACTUAL_RESULT_DIR + "/");
dfs.copyToLocalFile(src, dest);
}
diff --git a/genomix/genomix-hadoop/src/test/java/edu/uci/ics/pathmergingh2/MergePathH2Test.java b/genomix/genomix-hadoop/src/test/java/edu/uci/ics/pathmergingh2/MergePathH2Test.java
new file mode 100644
index 0000000..01b3884
--- /dev/null
+++ b/genomix/genomix-hadoop/src/test/java/edu/uci/ics/pathmergingh2/MergePathH2Test.java
@@ -0,0 +1,105 @@
+package edu.uci.ics.pathmergingh2;
+
+import java.io.BufferedWriter;
+import java.io.DataOutputStream;
+import java.io.File;
+import java.io.FileOutputStream;
+import java.io.FileWriter;
+import java.io.IOException;
+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.io.SequenceFile;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.MiniMRCluster;
+import org.apache.hadoop.util.ReflectionUtils;
+import org.junit.Test;
+import edu.uci.ics.genomix.type.KmerBytesWritable;
+import edu.uci.ics.genomix.type.VKmerBytesWritable;
+import edu.uci.ics.utils.TestUtils;
+
+@SuppressWarnings("deprecation")
+public class MergePathH2Test {
+ private static final String ACTUAL_RESULT_DIR = "actual4";
+ private static final String COMPARE_DIR = "compare";
+ private JobConf conf = new JobConf();
+ private static final String HADOOP_CONF_PATH = ACTUAL_RESULT_DIR + File.separator + "conf.xml";
+ private static final String DATA_PATH = "actual2" + "/result2" + "/part-00000";
+ private static final String HDFS_PATH = "/webmap";
+ private static final String HDFA_PATH_DATA = "/webmapdata";
+
+ private static final String RESULT_PATH = "/result4";
+ private static final String EXPECTED_PATH = "expected/result4";
+ private static final String TEST_SOURCE_DIR = COMPARE_DIR + RESULT_PATH + "/comparesource.txt";
+ private static final int COUNT_REDUCER = 1;
+ private static final int SIZE_KMER = 3;
+
+ private MiniDFSCluster dfsCluster;
+ private MiniMRCluster mrCluster;
+ private FileSystem dfs;
+
+ @SuppressWarnings("resource")
+ @Test
+ public void test() throws Exception {
+ FileUtils.forceMkdir(new File(ACTUAL_RESULT_DIR));
+ FileUtils.cleanDirectory(new File(ACTUAL_RESULT_DIR));
+ startHadoop();
+
+ MergePathH2Driver tldriver = new MergePathH2Driver();
+ tldriver.run(HDFS_PATH, RESULT_PATH, HDFA_PATH_DATA, COUNT_REDUCER, SIZE_KMER, 0, HADOOP_CONF_PATH);
+
+/* SequenceFile.Reader reader = null;
+ Path path = new Path(RESULT_PATH + "/part-00000");
+// Path path = new Path(RESULT_PATH + "/uncomplete0" + "/uncomplete0-r-00000");
+ reader = new SequenceFile.Reader(dfs, path, conf);
+ VKmerBytesWritable key = (VKmerBytesWritable) ReflectionUtils.newInstance(reader.getKeyClass(), conf);
+ MergePathValueWritable value = (MergePathValueWritable) ReflectionUtils.newInstance(reader.getValueClass(), conf);
+ File filePathTo = new File(TEST_SOURCE_DIR);
+ BufferedWriter bw = new BufferedWriter(new FileWriter(filePathTo));
+ while (reader.next(key, value)) {
+ bw.write(key.toString() + "\t" + value.getAdjBitMap() + "\t" + value.getFlag());
+ bw.newLine();
+ }
+ bw.close();*/
+ dumpResult();
+
+// TestUtils.compareWithResult(new File(TEST_SOURCE_DIR), new File(EXPECTED_PATH));
+
+ cleanupHadoop();
+
+ }
+ private void startHadoop() throws IOException {
+ FileSystem lfs = FileSystem.getLocal(new Configuration());
+ lfs.delete(new Path("build"), true);
+ System.setProperty("hadoop.log.dir", "logs");
+ dfsCluster = new MiniDFSCluster(conf, 2, true, null);
+ dfs = dfsCluster.getFileSystem();
+ mrCluster = new MiniMRCluster(4, dfs.getUri().toString(), 2);
+
+ Path src = new Path(DATA_PATH);
+ Path dest = new Path(HDFS_PATH + "/");
+ dfs.mkdirs(dest);
+ dfs.copyFromLocalFile(src, dest);
+ Path data = new Path(HDFA_PATH_DATA + "/");
+ dfs.mkdirs(data);
+
+ DataOutputStream confOutput = new DataOutputStream(new FileOutputStream(new File(HADOOP_CONF_PATH)));
+ conf.writeXml(confOutput);
+ confOutput.flush();
+ confOutput.close();
+ }
+
+ private void cleanupHadoop() throws IOException {
+ mrCluster.shutdown();
+ dfsCluster.shutdown();
+ }
+
+ private void dumpResult() throws IOException {
+// Path src = new Path(HDFA_PATH_DATA + "/" + "complete2");
+ Path src = new Path(RESULT_PATH);
+ Path dest = new Path(ACTUAL_RESULT_DIR + "/");
+ dfs.copyToLocalFile(src, dest);
+ }
+}
\ No newline at end of file
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