Initial draft of flagstat component

src/samtools/flagstat/config.vsh.yaml

@@ -0,0 +1,50 @@
+name: samtools_flagstat
+namespace: samtools
+description: Counts the number of alignments in SAM/BAM/CRAM files for each FLAG type..
+keywords: [ stats, mapping, counts, bam, sam, cram]
+links:
+  homepage: https://www.htslib.org/
+  documentation: https://www.htslib.org/doc/samtools-flagstat.html
+  repository: https://github.com/samtools/samtools.git
+references: 
+  doi: 10.1093/bioinformatics/btp352, 10.1093/gigascience/giab008
+license: MIT/Expat
+
+argument_groups:
+  - name: Inputs
+    arguments:
+    - name: --bam
+      type: file
+      description: |
+        BAM input files.
+    - name: --bai
+      type: file
+      description: |
+        BAM index file.
+  - name: Outputs 
+    arguments:
+    - name: --output
+      type: file 
+      description: |
+        File containing samtools stats output.
+      direction: output
+      example: output.flagstat
+
+resources:
+  - type: bash_script
+    path: script.sh
+test_resources:
+  - type: bash_script
+    path: test.sh
+  - type: file
+    path: test_data
+engines:
+  - type: docker
+    image: quay.io/biocontainers/samtools:1.19.2--h50ea8bc_1
+    setup:
+      - type: docker
+        run: |
+          echo "$(samtools --version 2>&1)" > /var/software_versions.txt
+runners:
+- type: executable
+- type: nextflow

src/samtools/flagstat/help.txt

@@ -0,0 +1,13 @@
+```sh
+samtools flagstat --help
+```
+Usage: samtools flagstat [options] <in.bam>
+      --input-fmt-option OPT[=VAL]
+               Specify a single input file format option in the form
+               of OPTION or OPTION=VALUE
+  -@, --threads INT
+               Number of additional threads to use [0]
+      --verbosity INT
+               Set level of verbosity
+  -O, --output-fmt FORMAT[,OPT[=VAL]]...
+               Specify output format (json, tsv)

src/samtools/flagstat/script.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+
+## VIASH START
+## VIASH END
+
+set -e
+
+samtools flagstat \
+    "$par_input_bam" \
+    > "$par_output_stats"
+

src/samtools/flagstat/test.sh

@@ -0,0 +1,23 @@
+#!/bin/bash
+
+echo ">>> Testing $meta_functionality_name"
+
+"$meta_executable" \
+  --bam "$meta_resources_dir/test_data/chr19.bam" \
+  --bai "$meta_resources_dir/test_data/chr19.bam.bai" \
+  --output "$meta_resources_dir/test_data/chr19.flagstat"
+
+echo ">>> Checking whether output exists"
+[ ! -f "test_data/chr19.flagstat" ] && echo "File 'chr19.flagstat' does not exist!" && exit 1
+
+echo ">>> Checking whether output is non-empty"
+[ ! -s "test_data/chr19.flagstat" ] && echo "File 'chr19.flagstat' is empty!" && exit 1
+
+echo ">>> Checking whether output is correct"
+diff "$meta_resources_dir/test_data/chr19.flagstat" "$meta_resources_dir/test_data/chr19_ref.flagstat" || \
+    (echo "Output does not match expected output." && exit 1)
+
+rm "$meta_resources_dir/test_data/chr19.flagstat"
+
+echo "All tests succeeded!"
+exit 0

src/samtools/flagstat/test_data/chr19_ref.flagstat

@@ -0,0 +1,13 @@
+55197 + 0 in total (QC-passed reads + QC-failed reads)
+0 + 0 secondary
+0 + 0 supplementary
+0 + 0 duplicates
+55197 + 0 mapped (100.00% : N/A)
+0 + 0 paired in sequencing
+0 + 0 read1
+0 + 0 read2
+0 + 0 properly paired (N/A : N/A)
+0 + 0 with itself and mate mapped
+0 + 0 singletons (N/A : N/A)
+0 + 0 with mate mapped to a different chr
+0 + 0 with mate mapped to a different chr (mapQ>=5)

src/samtools/flagstat/test_data/script.sh

@@ -0,0 +1,6 @@
+#!/bin/bash
+
+# Download test data
+wget https://github.com/CGATOxford/UMI-tools/raw/master/tests/chr19.bam
+wget https://github.com/CGATOxford/UMI-tools/raw/master/tests/chr19.bam.bai
+