added vcluster --out-unvarying-clusters

build.xml

@@ -14,7 +14,7 @@
 
     <target name="-pre-init">
 <!--       <property name="project.name" value="NAME" />-->
-       <property name="version.num" value="0.9.3" />
+       <property name="version.num" value="0.9.4" />
         <tstamp>
             <format property="NOW" pattern="yyyy-MM-dd HH:mm:ss z" />
         </tstamp>

nbproject/genfiles.properties

@@ -3,6 +3,6 @@ build.xml.script.CRC32=17cdf327
 build.xml.stylesheet.CRC32=8064a381@1.75.2.48
 # This file is used by a NetBeans-based IDE to track changes in generated files such as build-impl.xml.
 # Do not edit this file. You may delete it but then the IDE will never regenerate such files for you.
-nbproject/build-impl.xml.data.CRC32=4397f2f8
-nbproject/build-impl.xml.script.CRC32=2022ac8e
-nbproject/build-impl.xml.stylesheet.CRC32=830a3534@1.80.1.48
+nbproject/build-impl.xml.data.CRC32=37bf6ae2
+nbproject/build-impl.xml.script.CRC32=6318acc5
+nbproject/build-impl.xml.stylesheet.CRC32=d549e5cc@1.98.0.48

nbproject/project.properties

@@ -19,8 +19,12 @@ build.test.results.dir=${build.dir}/test/results
 #debug.transport=dt_socket
 debug.classpath=\
     ${run.classpath}
+debug.modulepath=\
+    ${run.modulepath}
 debug.test.classpath=\
     ${run.test.classpath}
+debug.test.modulepath=\
+    ${run.test.modulepath}
 # Files in build.classes.dir which should be excluded from distribution jar
 dist.archive.excludes=
 # This directory is removed when the project is cleaned:
@@ -38,18 +42,23 @@ javac.classpath=
 javac.compilerargs=
 javac.deprecation=false
 javac.external.vm=false
+javac.modulepath=
+javac.processormodulepath=
 javac.processorpath=\
     ${javac.classpath}
 javac.source=1.8
 javac.target=1.8
 javac.test.classpath=\
     ${javac.classpath}:\
     ${build.classes.dir}
+javac.test.modulepath=\
+    ${javac.modulepath}
 javac.test.processorpath=\
     ${javac.test.classpath}
 javadoc.additionalparam=
 javadoc.author=false
 javadoc.encoding=${source.encoding}
+javadoc.html5=false
 javadoc.noindex=false
 javadoc.nonavbar=false
 javadoc.notree=false
@@ -58,6 +67,8 @@ javadoc.splitindex=true
 javadoc.use=true
 javadoc.version=false
 javadoc.windowtitle=
+jlink.launcher=false
+jlink.launcher.name=yakat
 jnlp.codebase.type=no.codebase
 jnlp.descriptor=application
 jnlp.enabled=false
@@ -79,7 +90,7 @@ manifest.custom.permissions=
 manifest.file=manifest.mf
 meta.inf.dir=${src.dir}/META-INF
 mkdist.disabled=false
-platform.active=default_platform
+platform.active=JDK_8
 project.license=apache20
 run.classpath=\
     ${javac.classpath}:\
@@ -88,9 +99,13 @@ run.classpath=\
 # You may also define separate properties like run-sys-prop.name=value instead of -Dname=value.
 # To set system properties for unit tests define test-sys-prop.name=value:
 run.jvmargs=
+run.modulepath=\
+    ${javac.modulepath}
 run.test.classpath=\
     ${javac.test.classpath}:\
     ${build.test.classes.dir}
+run.test.modulepath=\
+    ${javac.test.modulepath}
 source.encoding=UTF-8
 src.dir=src
 test.src.dir=test

nbproject/project.xml

@@ -4,6 +4,7 @@
     <configuration>
         <data xmlns="http://www.netbeans.org/ns/j2se-project/3">
             <name>yakat</name>
+            <explicit-platform explicit-source-supported="true"/>
             <source-roots>
                 <root id="src.dir"/>
             </source-roots>

src/vsearchprocess/VsearchClustersCaller.java

@@ -65,7 +65,7 @@ public VsearchClustersCaller(String[] args, String callerName, String toolName)
 
     private OptSet populateOptSet() {
         OptSet optSet = new OptSet("Parse MSA output of VSEARCH clustering, call variants within each cluster. "
-            + "Variants printed to stdout.");
+                + "Variants printed to stdout.");
 
         //CONSIDER SETTINGS
         //  INPUT LABELS TO DISTINGUISH SAMPLES, PREVENT CALLING SNPS WITHIN SAMPLES
@@ -79,7 +79,7 @@ private OptSet populateOptSet() {
         //INPUT
         optSet.setListingGroupLabel("[Input settings]");
         optSet.addOpt(new Opt(null, "sample-ids", "Space separated sample identifiers which form the prefices of the input FASTA identifiers")
-            .setMinValueArgs(1).setMaxValueArgs(Integer.MAX_VALUE).setRequired(true));
+                .setMinValueArgs(1).setMaxValueArgs(Integer.MAX_VALUE).setRequired(true));
         optSet.addOpt(new Opt(null, "clusters-msa", "The vsearch cluster msaout file, alternatively use stdin", 1));
 //        optSet.addOpt(new Opt(null, "original-fasta", "The original FASTA file gven to vsearch, if specified it will be used to extract the input sequences' lengths", 1));
 //        optSet.incrementLisitngGroup();
@@ -120,6 +120,7 @@ private OptSet populateOptSet() {
         optSet.addOpt(new Opt(null, "out-clusters-fasta", "Output clustered sequences (for which SNPs were called) to <arg> FASTA file", 1));
         optSet.addOpt(new Opt(null, "out-unclustered-fasta", "Output unclustered sequences to <arg> FASTA file", 1));
         optSet.addOpt(new Opt(null, "out-unclustered-min-len", "Minimum length required to output an unclustered sequence", 1).setMinValue(1).setDefaultValue(100));
+        optSet.addOpt(new Opt(null, "out-unvarying-clusters", "Output clusters (FASTA and/or MSA) for which no SNPs/indels called. Not reported by default"));
         optSet.addOpt(new Opt('o', "stdout-redirect", "Redirect stdout to this file", 1));
         optSet.addOpt(new Opt('e', "stderr-redirect", "Redirect stderr to this file", 1));
 ////        String headerNote = "Can be useful for external parallization (print header once)";
@@ -280,25 +281,26 @@ public void readAndProcessMSASequencesFromFasta(String fileName, OptSet optSet)
 
     }
 
-    private int processCluster(ClusteredSequencesMSA clusteredSeqs, OptSet optSet, int clusterNumber, BufferedWriter clustersFastaOut, 
+    private int processCluster(ClusteredSequencesMSA clusteredSeqs, OptSet optSet, int clusterNumber, BufferedWriter clustersFastaOut,
             BufferedWriter clustersMsaOut) throws IOException {
 
         int minSamplesClustered = (int) optSet.getOpt("min-samples-clustered").getValueOrDefault();
         int minSeqsClusteredIn = (int) optSet.getOpt("min-seqs-clustered-in").getValueOrDefault();
         int maxSeqsClusteredIn = (int) optSet.getOpt("max-seqs-clustered-in").getValueOrDefault();
-        
+
         int maxSeqsClusteredOut = (int) optSet.getOpt("max-seqs-clustered-out").getValueOrDefault();
         int maxIntraSnps = (int) optSet.getOpt("max-intra-snps").getValueOrDefault();
         int maxInterSnps = (int) optSet.getOpt("max-inter-snps").getValueOrDefault(Integer.MAX_VALUE);
 
         int maxIndelLength = (int) optSet.getOpt("max-indel-length").getValueOrDefault();
         int minIndelDistFromEnds = (int) optSet.getOpt("min-indel-distance").getValueOrDefault();
-        
+
         double minInterIdentity = (double) optSet.getOpt("min-inter-identity").getValueOrDefault();
 
         boolean reverseLex = optSet.getOpt("reverse-lex-order").getOptFlag();
         boolean supressIntra = optSet.getOpt("supress-intra-snps").getOptFlag();
         boolean supressInter = optSet.getOpt("supress-inter-snps").getOptFlag();
+        boolean outputUnvaryingClusters = optSet.getOpt("out-unvarying-clusters").getOptFlag();
 
         boolean appendSequencesToSnpList = true;
         int size = clusteredSeqs.size();
@@ -315,9 +317,9 @@ private int processCluster(ClusteredSequencesMSA clusteredSeqs, OptSet optSet, i
             //MERGE NON-CONFLICTING SEQUENCES WITHIN EACH SAMPLE
             if (clusteredSeqs.mergeSequencesWithinSamples()) {
 //                clusterString = "MERGED";
-                suffix= "MERGED";
+                suffix = "MERGED";
             }
-            
+
             //CALL BETWEEN SAMPLES
             clusteredSeqs.callSNPsBetweenAllSamples(maxIndelLength, minIndelDistFromEnds);
 //            boolean hasInter = false;
@@ -332,22 +334,22 @@ private int processCluster(ClusteredSequencesMSA clusteredSeqs, OptSet optSet, i
 //            } catch (NoSuchElementException e) {
 //                int x =0;
 //            }
-            
+
             int intra = clusteredSeqs.getIntraSnps().size();
             int inter = clusteredSeqs.getInterSnps().size();
 //             clusteredSeqs.printInterSnps(clusterNumber, reverseLex, DELIMITER, suffix, 0, appendSequencesToSnpList);
-            
+
             //PRINT            
-            if (intra <= maxIntraSnps &&  inter <= maxInterSnps && clusteredSeqs.size() <= maxSeqsClusteredOut) {
+            if (intra <= maxIntraSnps && inter <= maxInterSnps && clusteredSeqs.size() <= maxSeqsClusteredOut) {
                 ++clusterNumber;
 //                clusteredSeqs.printCluster((clusterNumber) + " " + clusterString, maxIndelLength);
-                if (clustersFastaOut != null && ((hasIntra && !supressIntra) || (hasInter && !supressInter))) {
-                    clustersFastaOut.write(clusteredSeqs.getClusterForPrint(clusterNumber, true).toString());
-//                    clustersFastaOut.newLine();
-                }
-                if (clustersMsaOut != null && ((hasIntra && !supressIntra) || (hasInter && !supressInter))) {
-                    clustersMsaOut.write(clusteredSeqs.getClusterForPrint(clusterNumber, false).toString());
-//                    clustersFastaOut.newLine();
+                if ((hasIntra && !supressIntra) || (hasInter && !supressInter) || outputUnvaryingClusters) {
+                    if (clustersFastaOut != null) {
+                        clustersFastaOut.write(clusteredSeqs.getClusterForPrint(clusterNumber, true).toString());
+                    }
+                    if (clustersMsaOut != null) {
+                        clustersMsaOut.write(clusteredSeqs.getClusterForPrint(clusterNumber, false).toString());
+                    }
                 }
                 if (!supressIntra) {
                     clusteredSeqs.printIntraSnps(clusterNumber, reverseLex, DELIMITER, "INTRA", appendSequencesToSnpList);