Add logged warning for spaces in sample names.

This can lead to downstream failures in some contexts. In that case, the error message only mentions not being able to match read groups, with no extra information provided. With this change, we will at least have that reason availlable in the error logs. See https://smrtlink-sms.nanofluidics.com:8243/sl/analysis/results/32588?show=status
PacificBiosciences · Dec 15, 2020 · d4d0722 · d4d0722
1 parent e1718d2
commit d4d0722
Show file tree

Hide file tree

Showing 6 changed files with 33 additions and 4 deletions.
diff --git a/src/SampleNames.cpp b/src/SampleNames.cpp
@@ -28,9 +28,15 @@ std::string SampleNames::SanitizeSampleName(const std::string& in)
     if (trimmed.empty()) return fallbackSampleName;
     std::string sanitizedName;
     for (const char& c : trimmed) {
-        if (c < '!' || c > '~')
+        if (c < '!' || c > '~') {
             sanitizedName += '_';
-        else
+            if (c == ' ') {
+                std::ostringstream msg;
+                msg << "Sample name '" << in << "' contains a space character. "
+                    << "This may interfere with matching read groups and samples later.";
+                PBLOG_WARN << msg.str();
+            }
+        } else
             sanitizedName += c;
     }
     return sanitizedName;

diff --git a/tests/cram/biosampleConsensus.t b/tests/cram/biosampleConsensus.t
@@ -17,6 +17,7 @@
   *\tSM:testSample\t* (glob)
 
   $ $__PBTEST_PBMM2_EXE align $IN $REF $CRAMTMP/ccs3.bam --sample "   TEST bla   "
+  *Sample name '   TEST bla   ' contains a space character* (glob)
   $ samtools view -H $CRAMTMP/ccs3.bam | grep "@RG"
   *\tSM:TEST_bla\t* (glob)
 
@@ -37,12 +38,18 @@
   *\tSM:UnnamedSample\t* (glob)
 
   $ $__PBTEST_PBMM2_EXE align $MERGED $REF $CRAMTMP/ccs6.bam
+  *Sample name 'test test' contains a space character* (glob)
+  *Sample name 'test test' contains a space character* (glob)
+  *Sample name 'test test' contains a space character* (glob)
   $ samtools view -H $CRAMTMP/ccs6.bam | grep "@RG"
   *\tSM:bamSample\t* (glob)
   *\tSM:test_test\t* (glob)
   *\tSM:test_test\t* (glob)
 
   $ $__PBTEST_PBMM2_EXE align $MERGED $REF $CRAMTMP/ccs7.bam --sample testSample
+  *Sample name 'test test' contains a space character* (glob)
+  *Sample name 'test test' contains a space character* (glob)
+  *Sample name 'test test' contains a space character* (glob)
   $ samtools view -H $CRAMTMP/ccs7.bam | grep "@RG"
   *\tSM:testSample\t* (glob)
   *\tSM:testSample\t* (glob)

diff --git a/tests/cram/biosampleSubreads.t b/tests/cram/biosampleSubreads.t
@@ -11,6 +11,7 @@
   *\tSM:testSample\t* (glob)
 
   $ $__PBTEST_PBMM2_EXE align $IN $REF $CRAMTMP/out3.bam --sample "   TEST bla   "
+  *Sample name '   TEST bla   ' contains a space character* (glob)
   $ samtools view -H $CRAMTMP/out3.bam | grep "@RG"
   *\tSM:TEST_bla\t* (glob)
 
@@ -23,12 +24,17 @@
   *\tSM:UnnamedSample\t* (glob)
 
   $ $__PBTEST_PBMM2_EXE align $MERGED $REF $CRAMTMP/out6.bam
+  *Sample name '  UCLA 1023 ' contains a space character* (glob)
+  *Sample name 'test test ' contains a space character* (glob)
   $ samtools view -H $CRAMTMP/out6.bam | grep "@RG"
   *\tSM:3260208_188nM-GTAC_2xGCratio_LP7_100fps_15min_5kEColi_SP2p1_3uMSSB_BA243494\t* (glob)
   *\tSM:test_test\t* (glob)
   *\tSM:UCLA_1023\t* (glob)
 
+
   $ $__PBTEST_PBMM2_EXE align $MERGED $REF $CRAMTMP/out7.bam --sample testSample
+  *Sample name '  UCLA 1023 ' contains a space character* (glob)
+  *Sample name 'test test ' contains a space character* (glob)
   $ samtools view -H $CRAMTMP/out7.bam | grep "@RG"
   *\tSM:testSample\t* (glob)
   *\tSM:testSample\t* (glob)

diff --git a/tests/cram/splitsample.t b/tests/cram/splitsample.t
@@ -3,7 +3,8 @@
   $ NO_SM_BIOSAMPLES=$TESTDIR/data/no_sm_biosamples.subreadset.xml
 
   $ $__PBTEST_PBMM2_EXE align $MERGED $REF $CRAMTMP/split.bam --split-by-sample
-
+  *Sample name '  UCLA 1023 ' contains a space character* (glob)
+  *Sample name 'test test ' contains a space character* (glob)
   $ ls -l $CRAMTMP/split.*.bam | wc -l | tr -d ' '
   3
 
@@ -26,6 +27,8 @@
   10
 
   $ $__PBTEST_PBMM2_EXE align $MERGED $REF $CRAMTMP/split_dataset.alignmentset.xml --split-by-sample
+  *Sample name '  UCLA 1023 ' contains a space character* (glob)
+  *Sample name 'test test ' contains a space character* (glob)
 
   $ [[ -f $CRAMTMP/split_dataset.3260208_188nM-GTAC_2xGCratio_LP7_100fps_15min_5kEColi_SP2p1_3uMSSB_BA243494.alignmentset.xml ]] || echo "File does not exist!"
   $ [[ -f $CRAMTMP/split_dataset.test_test.alignmentset.xml ]] || echo "File does not exist!"
@@ -53,8 +56,11 @@
 
 When both --split-by-sample and --sample were set, expect to see only one bam file with SM overridden.
   $ IN=$TESTDIR/data/merged.consensusreadset.xml
-  $ $__PBTEST_PBMM2_EXE align $REF $IN $CRAMTMP/splitsampleoverride.consensusalignmentset.xml --sort -j 8 --split-by-sample --sample "MySample" 2>&1 | fgrep -v 'Requested more threads'
+  $ $__PBTEST_PBMM2_EXE align $REF $IN $CRAMTMP/splitsampleoverride.consensusalignmentset.xml --sort -j 8 --split-by-sample --sample "MySample"  2>&1 | fgrep -v 'Requested more threads'
   *Options --split-by-sample and --sample are mutually exclusive. Option --sample will be applied and --split-by-sample is ignored! (glob)
+  *Sample name 'test test' contains a space character* (glob)
+  *Sample name 'test test' contains a space character* (glob)
+  *Sample name 'test test' contains a space character* (glob)
   $ [[ -f $CRAMTMP/splitsampleoverride.bam ]] || echo "File does not exist!"
   $ samtools view -H $CRAMTMP/splitsampleoverride.bam | grep "@RG" | grep -v "@PG	ID:samtools" | cut -f 6 | sort | uniq
   SM:MySample

diff --git a/tests/cram/splitsamplejson.t b/tests/cram/splitsamplejson.t
@@ -3,6 +3,8 @@
   $ REF=ecoliK12_pbi_March2013.fasta
 
   $ $__PBTEST_PBMM2_EXE align $MERGED $REF $CRAMTMP/split_dataset_sorted_json.alignmentset.xml --split-by-sample
+  *Sample name '  UCLA 1023 ' contains a space character* (glob)
+  *Sample name 'test test ' contains a space character* (glob)
 
   $ [[ -f $CRAMTMP/split_dataset_sorted_json.3260208_188nM-GTAC_2xGCratio_LP7_100fps_15min_5kEColi_SP2p1_3uMSSB_BA243494.alignmentset.xml ]] || echo "File does not exist!"
   $ [[ -f $CRAMTMP/split_dataset_sorted_json.test_test.alignmentset.xml ]] || echo "File does not exist!"

diff --git a/tests/cram/splitsamplesorted.t b/tests/cram/splitsamplesorted.t
@@ -2,6 +2,8 @@
   $ REF=$TESTDIR/data/ecoliK12_pbi_March2013.fasta
 
   $ $__PBTEST_PBMM2_EXE align $MERGED $REF $CRAMTMP/split_dataset_sorted.alignmentset.xml --split-by-sample --sort
+  *Sample name '  UCLA 1023 ' contains a space character* (glob)
+  *Sample name 'test test ' contains a space character* (glob)
 
   $ [[ -f $CRAMTMP/split_dataset_sorted.3260208_188nM-GTAC_2xGCratio_LP7_100fps_15min_5kEColi_SP2p1_3uMSSB_BA243494.alignmentset.xml ]] || echo "File does not exist!"
   $ [[ -f $CRAMTMP/split_dataset_sorted.test_test.alignmentset.xml ]] || echo "File does not exist!"