Add similar check for different sequencing technologies

Unsure if stricly necessary, but seems like an error to map the same read group ID to different PL. Previously the map entry was blindly over-written. Add tests for this.
freebayes · Sep 15, 2016 · 53f594b · 53f594b
1 parent ee1ba6a
commit 53f594b
Show file tree

Hide file tree

Showing 2 changed files with 30 additions and 1 deletion.
diff --git a/src/AlleleParser.cpp b/src/AlleleParser.cpp
@@ -149,6 +149,26 @@ void AlleleParser::getSequencingTechnologies(void) {
                     cerr << "no sequencing technology specified in @RG tag (no PL: in @RG tag) " << endl << headerLine << endl;
                 }
             } else {
+                map<string, string>::iterator s = readGroupToTechnology.find(readGroupID);
+                if (s != readGroupToTechnology.end()) {
+                    if (s->second != tech) {
+                        ERROR("multiple technologies (PL) map to the same read group (RG)" << endl
+                              << endl
+                              << "technologies " << tech << " and " << s->second << " map to " << readGroupID << endl
+                              << endl
+                              << "As freebayes operates on a virtually merged stream of its input files," << endl
+                              << "it will not be possible to determine what technology an alignment belongs to" << endl
+                              << "at runtime." << endl
+                              << endl
+                              << "To resolve the issue, ensure that RG ids are unique to one technology" << endl
+                              << "across all the input files to freebayes." << endl
+                              << endl
+                              << "See bamaddrg (https://github.com/ekg/bamaddrg) for a method which can" << endl
+                              << "add RG tags to alignments." << endl);
+                        exit(1);
+                    }
+                    // if it's the same technology and RG combo, no worries
+                }
                 readGroupToTechnology[readGroupID] = tech;
                 technologies[tech] = true;
             }

diff --git a/test/t/02_multi_bam.t b/test/t/02_multi_bam.t
@@ -5,7 +5,7 @@ source ./bash-tap/bash-tap-bootstrap
 
 PATH=../bin:$PATH # for freebayes
 
-plan tests 5
+plan tests 7
 
 ref=$(basename $0).ref
 
@@ -60,11 +60,20 @@ bam1=$(make_bam "id1" "sample1" "platform1")
 bam2=$(make_bam "id2" "sample2" "platform2")
 is "$(run_freebayes -f ${ref} ${bam1} ${bam2})" "${expected}" "freebayes calls from two BAMs with different samples for different read groups"
 
+bam1=$(make_bam "id1" "sample1" "platform1")
+bam2=$(make_bam "id2" "sample1" "platform2")
+is "$(run_freebayes -f ${ref} ${bam1} ${bam2})" "${expected}" "freebayes calls from two BAMs with different technologies for different read groups"
+
 bam1=$(make_bam "id1" "sample1" "platform1")
 bam2=$(make_bam "id1" "sample2" "platform1")
 expected='ERROR\(freebayes\): multiple samples \(SM\) map to the same read group \(RG\)'
 like "$(run_freebayes -f ${ref} ${bam1} ${bam2})" "${expected}" "freebayes rejects two BAMs with different samples for same read groups"
 
+bam1=$(make_bam "id1" "sample1" "platform1")
+bam2=$(make_bam "id1" "sample1" "platform2")
+expected='ERROR\(freebayes\): multiple technologies \(PL\) map to the same read group \(RG\)'
+like "$(run_freebayes -f ${ref} ${bam1} ${bam2})" "${expected}" "freebayes rejects two BAMs with different technologies for same read groups"
+
 bam1=$(make_bam "id1" "sample1" "platform1")
 bam2=$(make_bam "id2" "sample2" "platform2" "" "C")
 expected=$(cat <<END