From 9889be55e353479eefa58cc3ae5b12349c9e6d1b Mon Sep 17 00:00:00 2001
From: Hendrik Cannoodt <hendrik.cannoodt@gmail.com>
Date: Fri, 19 Jan 2024 15:52:03 +0100
Subject: [PATCH 1/4] Quick conversion from snakemake wrapper

---
 src/bgzip/config.vsh.yaml | 43 +++++++++++++++++++++++++++++++++++++++
 src/bgzip/help.txt        | 19 +++++++++++++++++
 src/bgzip/test/test.vcf   | 23 +++++++++++++++++++++
 3 files changed, 85 insertions(+)
 create mode 100644 src/bgzip/config.vsh.yaml
 create mode 100644 src/bgzip/help.txt
 create mode 100644 src/bgzip/test/test.vcf

diff --git a/src/bgzip/config.vsh.yaml b/src/bgzip/config.vsh.yaml
new file mode 100644
index 00000000..7e98592f
--- /dev/null
+++ b/src/bgzip/config.vsh.yaml
@@ -0,0 +1,43 @@
+functionality:
+  name: bgzip
+  description: Block compression/decompression utility
+  arguments:
+    - name: --input
+      type: file
+      direction: input
+      description: file to be compressed or decompressed
+      required: true
+    - name: --output
+      type: file
+      direction: output
+      description: compressed or decompressed output
+      required: true
+    - name: --extra
+      type: string
+      description: extra arguments to pass to bgzip
+      required: false
+    - name: --threads
+      type: integer
+      description: number of threads to use
+      required: false
+      default: 1
+    # - name: log
+    #   type: file
+    #   direction: output
+    #   description: log file
+    #   required: false
+  resources:
+    - type: bash_script
+      text: |
+        bgzip -c "$par_extra" --threads "$par_threads" "$par_input" > "$par_output"
+  test_resources:
+    - type: bash_script
+      text: |
+        "$meta_executable" --input "$meta_resources_dir/test/test.vcf" --output "$meta_resources_dir/test.vcf.gz"
+    - type: file
+      path: test
+  info:
+    repository: https://github.com/samtools/htslib
+platforms:
+  - type: docker
+    image: quay.io/biocontainers/htslib:1.19--h81da01d_0
\ No newline at end of file
diff --git a/src/bgzip/help.txt b/src/bgzip/help.txt
new file mode 100644
index 00000000..ad75f6d1
--- /dev/null
+++ b/src/bgzip/help.txt
@@ -0,0 +1,19 @@
+
+Version: 1.19
+Usage:   bgzip [OPTIONS] [FILE] ...
+Options:
+   -b, --offset INT           decompress at virtual file pointer (0-based uncompressed offset)
+   -c, --stdout               write on standard output, keep original files unchanged
+   -d, --decompress           decompress
+   -f, --force                overwrite files without asking
+   -g, --rebgzip              use an index file to bgzip a file
+   -h, --help                 give this help
+   -i, --index                compress and create BGZF index
+   -I, --index-name FILE      name of BGZF index file [file.gz.gzi]
+   -k, --keep                 don't delete input files during operation
+   -l, --compress-level INT   Compression level to use when compressing; 0 to 9, or -1 for default [-1]
+   -r, --reindex              (re)index compressed file
+   -s, --size INT             decompress INT bytes (uncompressed size)
+   -t, --test                 test integrity of compressed file
+       --binary               Don't align blocks with text lines
+   -@, --threads INT          number of compression threads to use [1]
diff --git a/src/bgzip/test/test.vcf b/src/bgzip/test/test.vcf
new file mode 100644
index 00000000..11b5400e
--- /dev/null
+++ b/src/bgzip/test/test.vcf
@@ -0,0 +1,23 @@
+##fileformat=VCFv4.0
+##fileDate=20090805
+##source=https://www.internationalgenome.org/wiki/Analysis/vcf4.0/
+##reference=1000GenomesPilot-NCBI36
+##phasing=partial
+##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of Samples With Data">
+##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">
+#CHROM POS     ID        REF ALT    QUAL FILTER INFO                              FORMAT      NA00001        NA00002        NA00003
+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|0:54:7:56,60 0|0:48:4:51,51 0/0:61:2
+20     1234567 microsat1 GTCT   G,GTACT 50   PASS   NS=3;DP=9;AA=G                    GT:GQ:DP    0/1:35:4       0/2:17:2       1/1:40:3

From 3f13bea26ea49314b5a60662513fdb0936fea7a7 Mon Sep 17 00:00:00 2001
From: Hendrik Cannoodt <hendrik.cannoodt@gmail.com>
Date: Tue, 23 Jan 2024 15:42:13 +0100
Subject: [PATCH 2/4] reorder the fields a bit and expand the info field

---
 src/bgzip/config.vsh.yaml | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/src/bgzip/config.vsh.yaml b/src/bgzip/config.vsh.yaml
index 7e98592f..a4fe18e3 100644
--- a/src/bgzip/config.vsh.yaml
+++ b/src/bgzip/config.vsh.yaml
@@ -1,6 +1,14 @@
 functionality:
   name: bgzip
   description: Block compression/decompression utility
+  info:
+    homepage: https://www.htslib.org/
+    documentation: https://www.htslib.org/doc/bgzip.html
+    repository: https://github.com/samtools/htslib
+    licence: MIT
+  requirements:
+    cpus: 1
+    commands: [ bgzip ]
   arguments:
     - name: --input
       type: file
@@ -21,11 +29,6 @@ functionality:
       description: number of threads to use
       required: false
       default: 1
-    # - name: log
-    #   type: file
-    #   direction: output
-    #   description: log file
-    #   required: false
   resources:
     - type: bash_script
       text: |
@@ -36,8 +39,7 @@ functionality:
         "$meta_executable" --input "$meta_resources_dir/test/test.vcf" --output "$meta_resources_dir/test.vcf.gz"
     - type: file
       path: test
-  info:
-    repository: https://github.com/samtools/htslib
+
 platforms:
   - type: docker
     image: quay.io/biocontainers/htslib:1.19--h81da01d_0
\ No newline at end of file

From c1043613a0d58195c78044cc8fa05cbbfe0a8a81 Mon Sep 17 00:00:00 2001
From: Hendrik Cannoodt <hendrik.cannoodt@gmail.com>
Date: Fri, 26 Jan 2024 10:48:50 +0100
Subject: [PATCH 3/4] improve implementation of regular script and test script

---
 src/bgzip/config.vsh.yaml              | 48 +++++++++++++++++++-------
 src/bgzip/test_data/README.md          | 13 +++++++
 src/bgzip/{test => test_data}/test.vcf |  0
 3 files changed, 48 insertions(+), 13 deletions(-)
 create mode 100644 src/bgzip/test_data/README.md
 rename src/bgzip/{test => test_data}/test.vcf (100%)

diff --git a/src/bgzip/config.vsh.yaml b/src/bgzip/config.vsh.yaml
index a4fe18e3..bae1eb20 100644
--- a/src/bgzip/config.vsh.yaml
+++ b/src/bgzip/config.vsh.yaml
@@ -20,26 +20,48 @@ functionality:
       direction: output
       description: compressed or decompressed output
       required: true
-    - name: --extra
-      type: string
-      description: extra arguments to pass to bgzip
-      required: false
-    - name: --threads
-      type: integer
-      description: number of threads to use
-      required: false
-      default: 1
+    - name: --decompress
+      alternatives: -d
+      type: boolean_true
+      description: decompress the input file
   resources:
     - type: bash_script
       text: |
-        bgzip -c "$par_extra" --threads "$par_threads" "$par_input" > "$par_output"
+        [[ "$par_decompress" == "false" ]] && unset par_decompress
+        bgzip -c \
+          ${meta_cpus:+--threads "${meta_cpus}"} \
+          ${par_decompress:+-d} \
+          "$par_input" > "$par_output"
   test_resources:
     - type: bash_script
       text: |
-        "$meta_executable" --input "$meta_resources_dir/test/test.vcf" --output "$meta_resources_dir/test.vcf.gz"
+        set -e
+
+        "$meta_executable" --input "$meta_resources_dir/test_data/test.vcf" --output "test.vcf.gz"
+
+        echo ">> Checking output of compressing"
+        [ ! -f "test.vcf.gz" ] && echo "Output file test.vcf.gz does not exist" && exit 1
+
+        "$meta_executable" --input "test.vcf.gz" --output "test.vcf" --decompress
+
+        echo ">> Checking output of decompressing"
+        [ ! -f "test.vcf" ] && echo "Output file test.vcf does not exist" && exit 1
+
+        echo ">> Checking original and decompressed files are the same"
+        set +e
+        cmp --silent -- "$meta_resources_dir/test_data/test.vcf" "test.vcf"
+        [ $? -ne 0 ] && echo "files are different" && exit 1
+        set -e
+        
+        echo "> Test successful"
     - type: file
-      path: test
+      path: test_data
 
 platforms:
   - type: docker
-    image: quay.io/biocontainers/htslib:1.19--h81da01d_0
\ No newline at end of file
+    image: quay.io/biocontainers/htslib:1.19--h81da01d_0
+    setup:
+      - type: docker
+        run: |
+          bgzip -h | grep 'Version:' 2>&1 |  sed 's/Version:\s\(.*\)/arriba: "\1"/' > /var/software_versions.txt
+  - type: nextflow
\ No newline at end of file
diff --git a/src/bgzip/test_data/README.md b/src/bgzip/test_data/README.md
new file mode 100644
index 00000000..ce46295a
--- /dev/null
+++ b/src/bgzip/test_data/README.md
@@ -0,0 +1,13 @@
+# arriba test data
+
+Test data was obtained from https://github.com/snakemake/snakemake-wrappers/tree/master/bio/bgzip/test.
+
+__author__ = "William Rowell"
+__copyright__ = "Copyright 2020, William Rowell"
+__email__ = "wrowell@pacb.com"
+__license__ = "MIT"
+
+```bash
+git clone --depth 1 --single-branch --branch master https://github.com/snakemake/snakemake-wrappers /tmp/snakemake-wrappers
+cp -r /tmp/snakemake-wrappers/bio/bgzip/test/* src/bgzip/test_data
+```
\ No newline at end of file
diff --git a/src/bgzip/test/test.vcf b/src/bgzip/test_data/test.vcf
similarity index 100%
rename from src/bgzip/test/test.vcf
rename to src/bgzip/test_data/test.vcf

From 4a4ed79cfead717b5678e34ec0b5e9e70ec6ffa8 Mon Sep 17 00:00:00 2001
From: Hendrik Cannoodt <hendrik.cannoodt@gmail.com>
Date: Tue, 30 Jan 2024 15:53:06 +0100
Subject: [PATCH 4/4] Add extra arguments

---
 src/bgzip/config.vsh.yaml | 87 ++++++++++++++++++++++++++++++++-------
 src/bgzip/help.txt        |  3 ++
 2 files changed, 75 insertions(+), 15 deletions(-)

diff --git a/src/bgzip/config.vsh.yaml b/src/bgzip/config.vsh.yaml
index bae1eb20..38c7baab 100644
--- a/src/bgzip/config.vsh.yaml
+++ b/src/bgzip/config.vsh.yaml
@@ -9,28 +9,85 @@ functionality:
   requirements:
     cpus: 1
     commands: [ bgzip ]
-  arguments:
-    - name: --input
-      type: file
-      direction: input
-      description: file to be compressed or decompressed
-      required: true
-    - name: --output
-      type: file
-      direction: output
-      description: compressed or decompressed output
-      required: true
-    - name: --decompress
-      alternatives: -d
-      type: boolean_true
-      description: decompress the input file
+  argument_groups:
+    - name: Inputs
+      arguments:
+      - name: --input
+        type: file
+        direction: input
+        description: file to be compressed or decompressed
+        required: true
+    - name: Outputs
+      arguments:
+      - name: --output
+        type: file
+        direction: output
+        description: compressed or decompressed output
+        required: true
+      - name: --index_name
+        alternatives: -I
+        type: file
+        direction: output
+        description: name of BGZF index file [file.gz.gzi]
+    - name: Arguments
+      arguments:
+      - name: offset
+        alternatives: -b
+        type: integer
+        description: decompress at virtual file pointer (0-based uncompressed offset)
+      - name: --decompress
+        alternatives: -d
+        type: boolean_true
+        description: decompress the input file
+      - name: --rebgzip
+        alternatives: -g
+        type: boolean_true
+        description: use an index file to bgzip a file
+      - name: --index
+        alternatives: -i
+        type: boolean_true
+        description: compress and create BGZF index
+      - name: --compress_level
+        alternatives: -l
+        type: integer
+        description: compression level to use when compressing; 0 to 9, or -1 for default [-1]
+        min: -1
+        max: 9
+      - name: --reindex
+        alternatives: -r
+        type: boolean_true
+        description: (re)index the output file
+      - name: --size
+        alternatives: -s
+        type: integer
+        description: decompress INT bytes (uncompressed size)
+        min: 0
+      - name: --test
+        alternatives: -t
+        type: boolean_true
+        description: test integrity of compressed file
+      - name: --binary
+        type: boolean_true
+        description: Don't align blocks with text lines
   resources:
     - type: bash_script
       text: |
         [[ "$par_decompress" == "false" ]] && unset par_decompress
+        [[ "$par_rebgzip" == "false" ]] && unset par_rebgzip
+        [[ "$par_index" == "false" ]] && unset par_index
+        [[ "$par_reindex" == "false" ]] && unset par_reindex
+        [[ "$par_test" == "false" ]] && unset par_test
+        [[ "$par_binary" == "false" ]] && unset par_binary
         bgzip -c \
           ${meta_cpus:+--threads "${meta_cpus}"} \
           ${par_decompress:+-d} \
+          ${par_rebgzip:+-g} \
+          ${par_index:+-i} \
+          ${par_index_name:+-I "${par_index_name}"} \
+          ${par_compress_level:+-l "${par_compress_level}"} \
+          ${par_reindex:+-r} \
+          ${par_size:+-s "${par_size}"} \
+          ${par_test:+-t} \
           "$par_input" > "$par_output"
   test_resources:
     - type: bash_script
diff --git a/src/bgzip/help.txt b/src/bgzip/help.txt
index ad75f6d1..d4012efd 100644
--- a/src/bgzip/help.txt
+++ b/src/bgzip/help.txt
@@ -1,3 +1,6 @@
+```bash
+bgzip -h
+```
 
 Version: 1.19
 Usage:   bgzip [OPTIONS] [FILE] ...