Changed syntax a bit to handle blank input/output

Author: mikessh

src/main/groovy/com/milaboratory/migec/Assemble.groovy

@@ -21,12 +21,14 @@ import groovyx.gpars.GParsPool
 import java.util.concurrent.LinkedBlockingQueue
 import java.util.concurrent.atomic.AtomicInteger
 
+import static com.milaboratory.migec.Util.BLANK_PATH
+
 //========================
 //          CLI
 //========================
 def DEFAULT_ASSEMBLE_MASK = "1:1", DEFAULT_MIN_COUNT = "10", DEFAULT_PARENT_CHILD_RATIO = "0.1"
 def cli = new CliBuilder(usage:
-        'Assemble [options] R1.fastq[.gz] [R2.fastq[.gz] or -] output_dir/')
+        "Assemble [options] R1.fastq[.gz] [R2.fastq[.gz] or ${BLANK_PATH}] output_dir/")
 cli.q(args: 1, argName: 'read quality (phred)',
         "barcode region quality threshold. Default: $Util.DEFAULT_UMI_QUAL_THRESHOLD")
 cli._(longOpt: 'assembly-mask', args: 1, argName: 'X:Y, X=0/1, Y=0/1',
@@ -91,7 +93,7 @@ if (!(inputFileName1.endsWith(".fastq") || inputFileName1.endsWith(".fastq.gz"))
     outputFilePrefix1 = Util.getFastqPrefix(inputFileName1) + ".t" + minMigSize + (filterCollisions ? ".cf" : "")
 }
 
-if (inputFileName2 != "-") {
+if (inputFileName2 != BLANK_PATH) {
     if (!(inputFileName2.endsWith(".fastq") || inputFileName2.endsWith(".fastq.gz"))) {
         println "[ERROR] Bad file extension $inputFileName2. Either .fastq, .fastq.gz or \'-\' should be provided as R2 file."
         System.exit(-1)
@@ -106,7 +108,7 @@ def offsetRange = Integer.parseInt(opt.'assembly-offset' ?: '5'),
     anchorRegion = Integer.parseInt(opt.'assembly-anchor' ?: '10')
 
 // I/O parameters
-boolean paired = inputFileName2 != "-"
+boolean paired = inputFileName2 != BLANK_PATH
 def assemblyIndices = [true, false]
 boolean bothReads = false
 if (paired) {

src/main/groovy/com/milaboratory/migec/CdrBlast.groovy

@@ -147,8 +147,9 @@ TMP_FOLDER_FILE.mkdirs()
 //if (!DEBUG)
 //    TMP_FOLDER_FILE.deleteOnExit()
 
-if (new File(outputFileName).parentFile)
-    new File(outputFileName).parentFile.mkdirs()
+def outputFile = null
+if (outputFileName != "-" && (outputFile = new File(outputFileName)).parentFile)
+    outputFile.parentFile.mkdirs()
 
 // BLAST SETTINGS
 int ALLELE_TAIL_INNER = 10, ALLELE_TAIL_OUTER = 6,
@@ -758,22 +759,23 @@ uniqueClonotypes.keySet().each {
     }
 }
 
-println "${timestamp()} Writing output"
-def outputFile = new File(outputFileName)
-outputFile.withPrintWriter { pw ->
-    pw.println("Count\tPercentage\t" +
-            "CDR3 nucleotide sequence\tCDR3 amino acid sequence\t" +
-            "V segments\tJ segments\tD segments\t" +
-            "Last V nucleotide position\t" +
-            "First D nucleotide position\tLast D nucleotide position\t" +
-            "First J nucleotide position\t" +
-            "Good events\tTotal events\tGood reads\tTotal reads")
-
-    (doSort ? cloneMap.sort { -it.value[0] } : cloneMap).each {
-        if (it.value[0] > 0)
-            pw.println(it.value[0] + "\t" + (it.value[0] / goodEvents) + // percentage from good events only
-                    "\t" + it.key +
-                    "\t" + it.value.collect().join("\t"))
+if (outputFile) {
+    println "${timestamp()} Writing output"
+    outputFile.withPrintWriter { pw ->
+        pw.println("Count\tPercentage\t" +
+                "CDR3 nucleotide sequence\tCDR3 amino acid sequence\t" +
+                "V segments\tJ segments\tD segments\t" +
+                "Last V nucleotide position\t" +
+                "First D nucleotide position\tLast D nucleotide position\t" +
+                "First J nucleotide position\t" +
+                "Good events\tTotal events\tGood reads\tTotal reads")
+
+        (doSort ? cloneMap.sort { -it.value[0] } : cloneMap).each {
+            if (it.value[0] > 0)
+                pw.println(it.value[0] + "\t" + (it.value[0] / goodEvents) + // percentage from good events only
+                        "\t" + it.key +
+                        "\t" + it.value.collect().join("\t"))
+        }
     }
 }
 
@@ -783,8 +785,10 @@ if (!DEBUG)
 //TMP_FOLDER_FILE.listFiles().each { it.deleteOnExit() }
 
 // Append to log and report to batch runner
-def logLine = [(assembledInput ? "asm" : "raw"), outputFile.absolutePath, inputFileNames.join(","),
-               goodEvents, mappedEvents, totalEvents, goodReads, mappedReads, totalReads].join("\t")
+def logLine = [(assembledInput ? "asm" : "raw"), outputFile ? outputFile.absolutePath : "-",
+               inputFileNames.join(","),
+               goodEvents, mappedEvents, totalEvents,
+               goodReads, mappedReads, totalReads].join("\t")
 
 if (logFileName) {
     def logFile = new File(logFileName)

src/main/groovy/com/milaboratory/migec/CdrBlastBatch.groovy

@@ -1,5 +1,7 @@
 package com.milaboratory.migec
 
+import static com.milaboratory.migec.Util.BLANK_PATH
+
 /**
  Copyright 2014 Mikhail Shugay (mikhail.shugay@gmail.com)
 
@@ -18,7 +20,8 @@ package com.milaboratory.migec
 
 def scriptName = getClass().canonicalName
 
-def cli = new CliBuilder(usage: "$scriptName [options] [checkout_dir/ or -] [assemble_dir/ or -] output_dir/\n" +
+def cli = new CliBuilder(usage: "$scriptName [options] " +
+        "[checkout_dir/ or ${BLANK_PATH}] [assemble_dir/ or ${BLANK_PATH}] output_dir/\n" +
         "Either --sample-metadata or -R argument is required.")
 cli.p(args: 1, "Number of threads to use")
 cli._(longOpt: "sample-metadata", args: 1, argName: "file",
@@ -85,7 +88,7 @@ if (!sampleInfoFileName && !opt.R) {
     System.exit(-1)
 }
 
-boolean processRaw = checkoutDir != "-", processAssembled = assembleDir != "-"
+boolean processRaw = checkoutDir != BLANK_PATH, processAssembled = assembleDir != BLANK_PATH
 if (!processRaw && !processAssembled) {
     println "[ERROR] At least one of assembled or raw (checkout) data directories should be specified"
     System.exit(-1)

src/main/groovy/com/milaboratory/migec/Checkout.groovy

@@ -22,9 +22,11 @@ import java.util.concurrent.LinkedBlockingQueue
 import java.util.concurrent.atomic.AtomicLong
 import java.util.regex.Pattern
 
+import static com.milaboratory.migec.Util.BLANK_PATH
+
 def mm = "15:0.2:0.05", rcm = "0:1", mtrim = "10", omf = "5", oss = "5", oms = "10"
 def cli = new CliBuilder(usage:
-        'Checkout [options] barcode_file R1.fastq[.gz] [R2.fastq[.gz] or -] output_dir/')
+        "Checkout [options] barcode_file R1.fastq[.gz] [R2.fastq[.gz] or ${BLANK_PATH}] output_dir/'")
 cli.o('Oriented reads, so master barcode has to be in R1. ' +
         'Default: scans both reads (if pair-end) for master barcode')
 cli.u('Save UMI region specified by capital N\'s in barcode sequence to the header')
@@ -158,7 +160,7 @@ def addBarcode = { String barcode, int slave ->
 new File(barcodesFileName).splitEachLine("[\t ]") { sl ->
     // filter by input file name
     if (
-    (inputFileName2 == "-" && (sl.size() < 4 || sl[3] == "." || (inputFileName1.contains(sl[3])))) ||
+    (inputFileName2 == BLANK_PATH && (sl.size() < 4 || sl[3] == "." || (inputFileName1.contains(sl[3])))) ||
             (sl.size() < 5 ||
                     ((sl[3] == "." || inputFileName1.contains(sl[3])) && (sl[4] == "." || inputFileName2.contains(sl[4]))))
     ) {
@@ -646,7 +648,7 @@ new HashSet(sampleIds).each { String sampleId -> // only unique
                 (paired ? new File("$outputDir/${sampleId}_R1.$fastqPrefix").absolutePath :
                         new File("$outputDir/${sampleId}_R0.$fastqPrefix").absolutePath)
                 + "\t" +
-                (paired ? new File("$outputDir/${sampleId}_R2.$fastqPrefix").absolutePath : "-"))
+                (paired ? new File("$outputDir/${sampleId}_R2.$fastqPrefix").absolutePath : BLANK_PATH))
         if (overlap)
             filelistWriter.println(sampleId + "\toverlapped\t" +
                     new File("$outputDir/${sampleId}_R12.$fastqPrefix").absolutePath + "\t-")

src/main/groovy/com/milaboratory/migec/Util.groovy

@@ -33,6 +33,8 @@ class Util {
         script.binding.setVariable("args", argArray)
         script.run()
     }
+    
+    static final String BLANK_PATH = "_"
 
     static final List<String> FILE_TYPES = ["paired", "unpaired", "overlapped"],
                               MASKS = ["0:1", "1:0", "1:1", "0:0"]