From 9e757e5346c495da05f66fb3ffe7c607d29e256c Mon Sep 17 00:00:00 2001
From: tgaspe <theodorogtc@gmail.com>
Date: Wed, 28 Aug 2024 10:57:59 +0200
Subject: [PATCH] bug fixing and adding tests

---
 .../bcftools_annotate/config.vsh.yaml         |  8 +----
 src/bcftools/bcftools_annotate/test.sh        | 28 ++++++++++++----
 .../bcftools_annotate/test_data/example.vcf   | 32 ++++++++++++++++++
 .../bcftools_annotate/test_data/output.vcf    | 33 +++++++++++++++++++
 4 files changed, 87 insertions(+), 14 deletions(-)
 create mode 100644 src/bcftools/bcftools_annotate/test_data/example.vcf
 create mode 100644 src/bcftools/bcftools_annotate/test_data/output.vcf

diff --git a/src/bcftools/bcftools_annotate/config.vsh.yaml b/src/bcftools/bcftools_annotate/config.vsh.yaml
index ec8f4ee4..0e915c77 100644
--- a/src/bcftools/bcftools_annotate/config.vsh.yaml
+++ b/src/bcftools/bcftools_annotate/config.vsh.yaml
@@ -37,7 +37,7 @@ argument_groups:
         required: true
          
   - name: Options
-    dexcription: | 
+    description: | 
       For examples on how to use use bcftools annotate see http://samtools.github.io/bcftools/howtos/annotate.html.
       For more details on the options see https://samtools.github.io/bcftools/bcftools.html#annotate.
     arguments:
@@ -135,12 +135,6 @@ argument_groups:
         description: | 
           Do not append version and command line information to the output VCF header..
 
-      - name: --samples_file
-        alternatives: --S
-        type: file
-        description: | 
-          File of samples to include.
-
       - name: --output_type
         alternatives: --O
         type: string
diff --git a/src/bcftools/bcftools_annotate/test.sh b/src/bcftools/bcftools_annotate/test.sh
index b13303f8..7e9ffb91 100644
--- a/src/bcftools/bcftools_annotate/test.sh
+++ b/src/bcftools/bcftools_annotate/test.sh
@@ -69,24 +69,38 @@ cat <<EOF > "$TMPDIR/example.vcf"
 20	1235237	.	T	.	.	.	.	GT	0/0	0|0	./.
 EOF
 
-
-
 # Test 1: Default Use
 mkdir "$TMPDIR/test1" && pushd "$TMPDIR/test1" > /dev/null
 
-echo "> Run bcftools_stats on VCF file"
+echo "> Run bcftools_annotate remove annotations"
 "$meta_executable" \
   --input "../example.vcf" \
-  --output "stats.txt" \
+  --output "annotated.vcf" \
+  --remove "ID,INFO/DP,FORMAT/DP"
 
 # checks
-assert_file_exists "stats.txt"
-assert_file_not_empty "stats.txt"
-assert_file_contains "stats.txt" "bcftools stats  ../example.vcf"
+assert_file_exists "annotated.vcf"
+assert_file_not_empty "annotated.vcf"
+#assert_file_contains "annotated.vcf" ""
 echo "- test1 succeeded -"
 
 popd > /dev/null
 
+# # Test 2: Rename annotations
+# mkdir "$TMPDIR/test2" && pushd "$TMPDIR/test2" > /dev/null
+
+# echo "> Run bcftools_annotate rename annotations"
+# "$meta_executable" \
+#   --input "../example.vcf" \
+#   --output "stats.txt" \
+#   --rename_annotations "ID=ID2,INFO/DP=INFO/Depth,FORMAT/DP=FORMAT/Depth"
+
+# # checks
+# assert_file_exists "stats.txt"
+# assert_file_not_empty "stats.txt"
+# #assert_file_contains "stats.txt" "bcftools stats  ../example.vcf"
+# echo "- test2 succeeded -"
+
 
 
 echo "---- All tests succeeded! ----"
diff --git a/src/bcftools/bcftools_annotate/test_data/example.vcf b/src/bcftools/bcftools_annotate/test_data/example.vcf
new file mode 100644
index 00000000..72ae410e
--- /dev/null
+++ b/src/bcftools/bcftools_annotate/test_data/example.vcf
@@ -0,0 +1,32 @@
+##fileformat=VCFv4.0
+##fileDate=20090805
+##source=myImputationProgramV3.1
+##reference=1000GenomesPilot-NCBI36
+##contig=<ID=19,length=58617616>
+##contig=<ID=20,length=58617616>
+##phasing=partial
+##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of Samples With Data">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=AC,Number=.,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Total Depth">
+##INFO=<ID=AF,Number=.,Type=Float,Description="Allele Frequency">
+##INFO=<ID=AA,Number=1,Type=String,Description="Ancestral Allele">
+##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP membership, build 129">
+##INFO=<ID=H2,Number=0,Type=Flag,Description="HapMap2 membership">
+##FILTER=<ID=q10,Description="Quality below 10">
+##FILTER=<ID=s50,Description="Less than 50% of samples have data">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth">
+##FORMAT=<ID=HQ,Number=2,Type=Integer,Description="Haplotype Quality">
+##ALT=<ID=DEL:ME:ALU,Description="Deletion of ALU element">
+##ALT=<ID=CNV,Description="Copy number variable region">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	NA00001	NA00002	NA00003
+19	111	.	A	C	9.6	.	.	GT:HQ	0|0:10,10	0|0:10,10	0/1:3,3
+19	112	.	A	G	10	.	.	GT:HQ	0|0:10,10	0|0:10,10	0/1:3,3
+20	14370	rs6054257	G	A	29	PASS	NS=3;DP=14;AF=0.5;DB;H2	GT:GQ:DP:HQ	0|0:48:1:51,51	1|0:48:8:51,51	1/1:43:5:.,.
+20	17330	.	T	A	3	q10	NS=3;DP=11;AF=0.017	GT:GQ:DP:HQ	0|0:49:3:58,50	0|1:3:5:65,3	0/0:41:3:.,.
+20	1110696	rs6040355	A	G,T	67	PASS	NS=2;DP=10;AF=0.333,0.667;AA=T;DB	GT:GQ:DP:HQ	1|2:21:6:23,27	2|1:2:0:18,2	2/2:35:4:.,.
+20	1230237	.	T	.	47	PASS	NS=3;DP=13;AA=T	GT:GQ:DP:HQ	0|0:54:.:56,60	0|0:48:4:51,51	0/0:61:2:.,.
+20	1234567	microsat1	G	GA,GAC	50	PASS	NS=3;DP=9;AA=G;AN=6;AC=3,1	GT:GQ:DP	0/1:.:4	0/2:17:2	1/1:40:3
+20	1235237	.	T	.	.	.	.	GT	0/0	0|0	./.
diff --git a/src/bcftools/bcftools_annotate/test_data/output.vcf b/src/bcftools/bcftools_annotate/test_data/output.vcf
new file mode 100644
index 00000000..f72e1adb
--- /dev/null
+++ b/src/bcftools/bcftools_annotate/test_data/output.vcf
@@ -0,0 +1,33 @@
+##fileformat=VCFv4.0
+##FILTER=<ID=PASS,Description="All filters passed">
+##fileDate=20090805
+##source=myImputationProgramV3.1
+##reference=1000GenomesPilot-NCBI36
+##contig=<ID=19,length=58617616>
+##contig=<ID=20,length=58617616>
+##phasing=partial
+##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of Samples With Data">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=AC,Number=.,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=AF,Number=.,Type=Float,Description="Allele Frequency">
+##INFO=<ID=AA,Number=1,Type=String,Description="Ancestral Allele">
+##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP membership, build 129">
+##INFO=<ID=H2,Number=0,Type=Flag,Description="HapMap2 membership">
+##FILTER=<ID=q10,Description="Quality below 10">
+##FILTER=<ID=s50,Description="Less than 50% of samples have data">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=HQ,Number=2,Type=Integer,Description="Haplotype Quality">
+##ALT=<ID=DEL:ME:ALU,Description="Deletion of ALU element">
+##ALT=<ID=CNV,Description="Copy number variable region">
+##bcftools_annotateVersion=1.16+htslib-1.16
+##bcftools_annotateCommand=annotate -x ID,INFO/DP,FORMAT/DP -o output.vcf example.vcf; Date=Wed Aug 28 08:53:36 2024
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	NA00001	NA00002	NA00003
+19	111	.	A	C	9.6	.	.	GT:HQ	0|0:10,10	0|0:10,10	0/1:3,3
+19	112	.	A	G	10	.	.	GT:HQ	0|0:10,10	0|0:10,10	0/1:3,3
+20	14370	.	G	A	29	PASS	NS=3;AF=0.5;DB;H2	GT:GQ:HQ	0|0:48:51,51	1|0:48:51,51	1/1:43:.,.
+20	17330	.	T	A	3	q10	NS=3;AF=0.017	GT:GQ:HQ	0|0:49:58,50	0|1:3:65,3	0/0:41:.,.
+20	1110696	.	A	G,T	67	PASS	NS=2;AF=0.333,0.667;AA=T;DB	GT:GQ:HQ	1|2:21:23,27	2|1:2:18,2	2/2:35:.,.
+20	1230237	.	T	.	47	PASS	NS=3;AA=T	GT:GQ:HQ	0|0:54:56,60	0|0:48:51,51	0/0:61:.,.
+20	1234567	.	G	GA,GAC	50	PASS	NS=3;AA=G;AN=6;AC=3,1	GT:GQ	0/1:.	0/2:17	1/1:40
+20	1235237	.	T	.	.	.	.	GT	0/0	0|0	./.