added unit test for bad sample names

sample names in the sample sheet can contain characters that are
illegal in filenames, causing Picard to fail when trying to write
files. a sanitization function (util.file.string_to_file_name()) is now
applied to sample names in illumina.py, and a unit test has been added
to test_illumina.py

test/input/TestDifficultSampleNames/RunInfo.xml

@@ -0,0 +1,15 @@
+<?xml version="1.0"?>
+<RunInfo xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" Version="2">
+  <Run Id="150821_M04004_0006_000000000-AEF96" Number="6">
+    <Flowcell>000000000-AEF96</Flowcell>
+    <Instrument>M04004</Instrument>
+    <Date>150821</Date>
+    <Reads>
+      <Read Number="1" NumCycles="101" IsIndexedRead="N" />
+      <Read Number="2" NumCycles="8" IsIndexedRead="Y" />
+      <Read Number="3" NumCycles="8" IsIndexedRead="Y" />
+      <Read Number="4" NumCycles="101" IsIndexedRead="N" />
+    </Reads>
+    <FlowcellLayout LaneCount="1" SurfaceCount="2" SwathCount="1" TileCount="14" />
+  </Run>
+</RunInfo>

test/input/TestDifficultSampleNames/SampleSheet.csv

@@ -0,0 +1,40 @@
+[Header],,,,,,,,,
+IEMFileVersion,4,,,,,,,,
+Investigator Name,James,,,,,,,,
+Experiment Name,EBoV HS ,,,,,,,,
+Date,8/18/2015,,,,,,,,
+Workflow,GenerateFASTQ,,,,,,,,
+Application,FASTQ Only,,,,,,,,
+Assay,Nextera XT,,,,,,,,
+Description,,,,,,,,,
+Chemistry,Amplicon,,,,,,,,
+,,,,,,,,,
+[Reads],,,,,,,,,
+101,,,,,,,,,
+101,,,,,,,,,
+,,,,,,,,,
+[Settings],,,,,,,,,
+ReverseComplement,0,,,,,,,,
+,,,,,,,,,
+[Data],,,,,,,,,
+Sample_ID,Sample_Name,Sample_Plate,Sample_Well,I7_Index_ID,index,I5_Index_ID,index2,Sample_Project,Description
+difficult/\//value+for'` -sample_name0.6,,,,N702,CGTACTAG,S502,CTCTCTAT,,
+difficult/\//value+for'` -sample_name0.5,,,,N702,CGTACTAG,S503,TATCCTCT,,
+difficult/\//value+for'` -sample_name0.4,,,,N702,CGTACTAG,S504,AGAGTAGA,,
+difficult/\//value+for'` -sample_name0.3,,,,N702,CGTACTAG,S505,GTAAGGAG,,
+difficult/\//value+for'` -sample_name0.1,,,,N702,CGTACTAG,S508,CTAAGCCT,,
+difficult/\//value+for'` -sample_name4.6,,,,N703,AGGCAGAA,S502,CTCTCTAT,,
+difficult/\//value+for'` -sample_name4.5,,,,N703,AGGCAGAA,S503,TATCCTCT,,
+difficult/\//value+for'` -sample_name4.4,,,,N703,AGGCAGAA,S504,AGAGTAGA,,
+difficult/\//value+for'` -sample_name4.3,,,,N703,AGGCAGAA,S505,GTAAGGAG,,
+difficult/\//value+for'` -sample_name4.1,,,,N703,AGGCAGAA,S508,CTAAGCCT,,
+difficult/\//value+for'` -sample_name20.6,,,,N704,TCCTGAGC,S502,CTCTCTAT,,
+difficult/\//value+for'` -sample_name20.5,,,,N704,TCCTGAGC,S503,TATCCTCT,,
+difficult/\//value+for'` -sample_name20.4,,,,N704,TCCTGAGC,S504,AGAGTAGA,,
+difficult/\//value+for'` -sample_name20.3,,,,N704,TCCTGAGC,S505,GTAAGGAG,,
+difficult/\//value+for'` -sample_name20.1,,,,N704,TCCTGAGC,S508,CTAAGCCT,,
+difficult/\//value+for'` -sample_name48.6,,,,N705,GGACTCCT,S502,CTCTCTAT,,
+difficult/\//value+for'` -sample_name48.5,,,,N705,GGACTCCT,S503,TATCCTCT,,
+difficult/\//value+for'` -sample_name48.4,,,,N705,GGACTCCT,S504,AGAGTAGA,,
+difficult/\//value+for'` -sample_name48.3,,,,N705,GGACTCCT,S505,GTAAGGAG,,
+difficult/\//value+for'` -sample_name48.1,,,,N705,GGACTCCT,S508,CTAAGCCT,,

test/unit/test_illumina.py

@@ -150,6 +150,29 @@ def test_tarball_fail_missing_data(self):
             self.assertRaises(Exception, idir.get_RunInfo())
 
 
+class TestDifficultSampleNames(TestCaseWithTmp):
+
+    def test_paired_1(self):
+        inDir = util.file.get_test_input_path(self)
+        outBam = util.file.mkstempfname('.bam')
+        outHeader = util.file.mkstempfname('.txt')
+        sampleSheet = os.path.join(inDir, 'SampleSheet.csv')
+        runInfo = os.path.join(inDir, 'RunInfo.xml')
+        fastq = (os.path.join(inDir, 'mebv-0-1_S5_L001_R1_001.fastq.gz'),
+                 os.path.join(inDir, 'mebv-0-1_S5_L001_R2_001.fastq.gz'))
+        illumina.miseq_fastq_to_bam(outBam, sampleSheet, fastq[0], inFastq2=fastq[1], runInfo=runInfo)
+        rgs = list(tools.samtools.SamtoolsTool().getReadGroups(outBam).values())
+        self.assertEqual(len(rgs), 1)
+        rgs = rgs[0]
+        self.assertEqual(rgs.get('ID'), 'AEF96')
+        self.assertEqual(rgs.get('PL'), 'illumina')
+        self.assertEqual(rgs.get('PU'), 'AEF96.1.CGTACTAG-CTAAGCCT')
+        # we care more about Picard not failing, but if we care about how filenames are processed:
+        #self.assertEqual(rgs.get('LB'), 'difficult-value+for_-sample_name0.1')
+        #self.assertEqual(rgs.get('SM'), 'difficult-value+for_-sample_name0.1')
+        self.assertEqual(rgs.get('CN'), 'M04004')
+        self.assertTrue(rgs.get('DT','').startswith('2015-08-2'))
+
 class TestMiseqToBam(TestCaseWithTmp):
 
     def test_paired_1(self):

util/file.py

@@ -342,7 +342,7 @@ def temp_catted_files(input_files, prefix=None, suffix=None):
 
 def string_to_file_name(string_value):
     replacements_dict = {
-        "\\": "_", # win directory separator 
+        "\\": "-", # win directory separator 
         "/": "-", # posix directory separator 
         "^": "_", # caret
         "&": "_and_", # background