From 9264d9470c26d34b8d5ce0428e94e00ae0db7388 Mon Sep 17 00:00:00 2001
From: tgaspe <theodorogtc@gmail.com>
Date: Mon, 26 Aug 2024 15:08:53 +0200
Subject: [PATCH] Adding test for bcf file

---
 src/bcftools/bcftools_sort/config.vsh.yaml    |   2 +
 src/bcftools/bcftools_sort/test.sh            |  61 +++++++++++++++++-
 .../bcftools_sort/test_data/example.bcf       | Bin 0 -> 1183 bytes
 3 files changed, 60 insertions(+), 3 deletions(-)
 create mode 100644 src/bcftools/bcftools_sort/test_data/example.bcf

diff --git a/src/bcftools/bcftools_sort/config.vsh.yaml b/src/bcftools/bcftools_sort/config.vsh.yaml
index 9f52ead8..dce78704 100644
--- a/src/bcftools/bcftools_sort/config.vsh.yaml
+++ b/src/bcftools/bcftools_sort/config.vsh.yaml
@@ -38,6 +38,7 @@ argument_groups:
   - name: Options
     arguments:
       - name: --output_type
+        alternatives: -O
         type: string
         choices: [b, u, z, v]
         description: | 
@@ -55,6 +56,7 @@ resources:
 test_resources:
   - type: bash_script
     path: test.sh
+  - path: test_data
 
 engines:
   - type: docker
diff --git a/src/bcftools/bcftools_sort/test.sh b/src/bcftools/bcftools_sort/test.sh
index f74402c6..f406b8e2 100644
--- a/src/bcftools/bcftools_sort/test.sh
+++ b/src/bcftools/bcftools_sort/test.sh
@@ -6,6 +6,8 @@
 # Exit on error
 set -eo pipefail
 
+test_data="$meta_resources_dir/test_data"
+
 #############################################
 # helper functions
 assert_file_exists() {
@@ -104,6 +106,45 @@ cat <<EOF > "$TMPDIR/expected_output.vcf"
 20	1235237	.	T	.	.	.	.	GT	0/0	0|0	./.
 EOF
 
+cat <<EOF > "$TMPDIR/expected_bcf.vcf"
+##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=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">
+##bcftools_viewVersion=1.16+htslib-1.16
+##bcftools_viewCommand=view -O b -o example.bcf example.vcf.gz; Date=Mon Aug 26 13:00:22 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	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	./.
+EOF
+
+
 # Test 1: Default Use
 mkdir "$TMPDIR/test1" && pushd "$TMPDIR/test1" > /dev/null
 
@@ -111,7 +152,8 @@ echo "> Run bcftools_sort on VCF file"
 "$meta_executable" \
   --input "../example.vcf" \
   --output "output.vcf" \
-  --output_type "v"
+  --output_type "v" \
+  &> /dev/null
 
 # checks
 assert_file_exists "output.vcf"
@@ -121,10 +163,23 @@ echo "- test1 succeeded -"
 
 popd > /dev/null
 
-# Test 2: Output type   
+# Test 2: BCF file input
+mkdir "$TMPDIR/test2" && pushd "$TMPDIR/test2" > /dev/null
 
+echo "> Run bcftools_sort on BCF file"
+"$meta_executable" \
+  --input "${test_data}/example.bcf" \
+  --output "output.vcf" \
+  --output_type "v" \
+  &> /dev/null
 
-# Test 3: Output type
+# checks
+assert_file_exists "output.vcf"
+assert_file_not_empty "output.vcf"
+assert_identical_content "output.vcf" "../expected_bcf.vcf"
+echo "- test2 succeeded -"
+
+popd > /dev/null
 
 echo "---- All tests succeeded! ----"
 exit 0
diff --git a/src/bcftools/bcftools_sort/test_data/example.bcf b/src/bcftools/bcftools_sort/test_data/example.bcf
new file mode 100644
index 0000000000000000000000000000000000000000..d78ae010b4f1b6924f72b296a50e1cab5ca5f0ca
GIT binary patch
literal 1183
zcmV;Q1Yr9giwFb&00000{{{d;LjnMT1dWu>Z{tK1$6Y%~*IgFjN>zkFt7*dumQACv
z)1*JByX!bj8YxZFCR@0nNis<+`PbT$F697`koLlz6^H{jByRi%T=*A|_zyU9<izuj
zq;aU0P856WdGGVS@68)m^cv6ql;OBsZfKZv=y(=k>ZM-0+9}|*T&~t=c8@RA!$wtY
zYn@KMO8vfPxXf^DbxSi%1YV4KK5~ig)4^80QT<HCM{5zTN*GlYjQ8;#F2OtBnRtDw
zTGtKBoiGwm+MYA=h;>;k$Y9{nA@!&YHZsPzPHo4ce%mk|w%yVzjba&W`i{+vQ7B2?
z&zsa9v9Vg(E6clOxqK6U!A!xon#qBgJ0`wik5rd<%pfMbX|!r*p<AnyZ%wQo^;9|E
zy>_YEuo)duFIj}h1UW<0A(m@WAAM@DF@n^|)=ii>RBPP@+I1K)kv&Hf)1(2~uu(sl
z56}o|!@%E<f+)!#`YcG{4MDUJiu%sPW&wGQ%p>RnL`i>)v}QLBo)1jem?EE86gl1i
zlo219hR<gEUQCFnw(p*4mAY&kL3Wav)Rr=-nGRvM=27$LiwX43b;KzpIogt#4)b8!
zmq5^XKJ!3Ngp5GtWLA|K2+stOCCs4LX|<6>11o=QxOvo@80G-U%6>%LO%P9%|0SLf
z_msHG0y6^b9VL(G3mGRJ&nLt**fr`=(|L(x9J%c;x%s6fw<h&{*lS{=5`Gl)pC7mO
zm|RgbxM^)1lFlwpwQfkNckfW<dfaC*LtbW_-=%M65EQ2v!;~f1-J0-%lEHs^aDj3%
zm!!Ob0=s11rYSrYaF8NF$IXM&;{&bvJn3A8ehX$nwP6v#qeX4Dwdkw2E|X5W<6h6c
z5?91CNDt0|M@O(2I`;ZQ<~XMR`ISLmUP9*tUUES$KN&OMG<w^?eA!NSEQ{C!HJGFA
zGt@)d4x(R#9Z&$v`TVLsER4SV1chJuQ;@DrMo1|mxp;u_fubM<D?4jB{p8~8RBWGh
z#70%TIIfA1j(GlDYl=||ior<`qiTyS4a1P*yAt1vYurPQ<JP%oIPhNyXGr5Xo)h4*
zn$@y(PP)Iz3-C)x4>s3e2*RSD9sB+8{ksW2{T9FX!A^|rKlpP!ysvQ6uY;=qm(^@H
z^x}DVQep97Y`nQQ6Ze;vj)J6Kdwv<0c9ha?ww~1_PFj%!DJ8uvr8mItskF*T_aY4`
zA(fKek}!S(>nr!tpr;69IxQ@O_*I{Uc=k+)Lx3J2i!u2=kiXNvJ&f{7^E@zR;W4ZT
zX#toAiY82_)dl9yf4>tmUscjToXg(9#ZoCKZnhf==K-=Nr62wC)h|ci{PyuvDFX|u
zf%?>HCY{MZqzyg?Mj0-sX7;^xemZ@;5b4L?*W*Zs6(Oo-pnhJJ2O%-ukU)4DtMGc7
z;sLjJ7!;!d&KoiA)gLq5$xOKL+A{i{;}a%l>mSy&-MXgF@gm^skVQrkHieZSPKwWj
xMW0F^!Fq}p{sk88Nlg_A001A02m}BC000301^_}s0stET0{{R300000005SPILiP4

literal 0
HcmV?d00001