Merge remote-tracking branch 'origin/main' into extend_contributing

.github/workflows/test.yaml

@@ -0,0 +1,105 @@
+name: Component Testing
+
+on:
+  pull_request:
+  push:
+    branches: [ '**' ]
+
+jobs:
+  run_ci_check_job:
+    runs-on: ubuntu-latest
+    outputs:
+      run_ci: ${{ steps.github_cli.outputs.check }}
+    steps:
+      - name: 'Check if branch has an existing pull request and the trigger was a push'
+        id: github_cli
+        run: |
+          pull_request=$(gh pr list -R ${{ github.repository }} -H ${{ github.ref_name }} --json url --state open --limit 1 | jq '.[0].url')
+          # If the branch has a PR and this run was triggered by a push event, do not run
+          if [[ "$pull_request" != "null" && "$GITHUB_REF_NAME" != "main" && "${{ github.event_name == 'push' }}" == "true" && "${{ !contains(github.event.head_commit.message, 'ci force') }}" == "true" ]]; then
+            echo "check=false" >> $GITHUB_OUTPUT
+          else
+            echo "check=true" >> $GITHUB_OUTPUT
+          fi
+        env:
+           GH_TOKEN: ${{ github.token }}
+
+  # phase 1
+  list:
+    needs: run_ci_check_job
+    runs-on: ubuntu-latest
+    if: ${{ needs.run_ci_check_job.outputs.run_ci == 'true' }}
+
+    outputs:
+      matrix: ${{ steps.set_matrix.outputs.matrix }}
+
+    steps:
+    - uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+
+    - name: Get head git commit message
+      id: get_head_commit_message
+      run: echo "HEAD_COMMIT_MESSAGE=$(git show -s --format=%s ${{ github.event.pull_request.head.sha || github.sha }})" >> "$GITHUB_OUTPUT"
+
+    - uses: viash-io/viash-actions/setup@v5
+
+    - name: Check if all config can be parsed if there is no unicode support
+      run: |
+        LANG=C viash ns list > /dev/null
+
+    - name: Get changed files
+      id: changed-files
+      uses: tj-actions/changed-files@v42
+      with:
+        separator: ";"
+        diff_relative: true
+
+    - id: ns_list
+      uses: viash-io/viash-actions/ns-list@v5
+      with:
+        platform: docker
+        format: json
+        query: ^(?!workflows)
+
+    - id: ns_list_filtered
+      uses: viash-io/viash-actions/project/detect-changed-components@v5
+      with:
+        input_file: "${{ steps.ns_list.outputs.output_file }}"
+
+    - id: set_matrix
+      run: |
+        echo "matrix=$(jq -c '[ .[] | 
+          { 
+            "name": (.functionality.namespace + "/" + .functionality.name),
+            "config": .info.config,
+            "dir": .info.config | capture("^(?<dir>.*\/)").dir
+          }
+        ]' ${{ contains(steps.get_head_commit_message.outputs.HEAD_COMMIT_MESSAGE, 'ci force') && steps.ns_list.outputs.output_file || steps.ns_list_filtered.outputs.output_file }} )" >> $GITHUB_OUTPUT
+
+  # phase 2
+  viash_test:
+    needs: list
+    if: ${{ needs.list.outputs.matrix != '[]' && needs.list.outputs.matrix != '' }}
+    runs-on: ubuntu-latest
+
+    strategy:
+      fail-fast: false
+      matrix:
+        component: ${{ fromJson(needs.list.outputs.matrix) }}
+
+    steps:
+    # Remove unnecessary files to free up space. Otherwise, we get 'no space left on device.'
+    - uses: data-intuitive/reclaim-the-bytes@v2
+
+    - uses: actions/checkout@v4
+
+    - uses: viash-io/viash-actions/setup@v5
+
+    - name: Run test
+      timeout-minutes: 30
+      run: |
+        viash test \
+          "${{ matrix.component.config }}" \
+          --cpus 2 \
+          --memory "6gb"

CHANGELOG.md

@@ -8,6 +8,14 @@
 
 * `fastp`: An ultra-fast all-in-one FASTQ preprocessor (PR #3).
 
+* `busco`: Assess genome assembly and annotation completeness with single copy orthologs (PR #6).
+
+* `featurecounts`: Assign sequence reads to genomic features (PR #11).
+
+* `bgzip`: Add bgzip functionality to compress and decompress files (PR #13).
+
+* `pear`: Paired-end read merger (PR #10).
+
 ## MAJOR CHANGES
 
 ## MINOR CHANGES

src/bgzip/config.vsh.yaml

@@ -0,0 +1,127 @@
+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
+    reference:
+      doi: 10.1093/gigascience/giab007
+  requirements:
+    commands: [ bgzip ]
+  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}"} \
+          ${par_offset:+-b "${par_offset}"} \
+          ${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} \
+          ${par_binary:+--binary} \
+          "$par_input" > "$par_output"
+  test_resources:
+    - type: bash_script
+      text: |
+        set -e
+
+        "$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_data
+
+platforms:
+  - type: docker
+    image: quay.io/biocontainers/htslib:1.19--h81da01d_0
+    setup:
+      - type: docker
+        run: |
+          bgzip -h | grep 'Version:' 2>&1 |  sed 's/Version:\s\(.*\)/bgzip: "\1"/' > /var/software_versions.txt
+  - type: nextflow

src/bgzip/help.txt

@@ -0,0 +1,22 @@
+```bash
+bgzip -h
+```
+
+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]

src/bgzip/test_data/script.sh

@@ -0,0 +1,10 @@
+# bgzip test data
+
+# Test data was obtained from https://github.com/snakemake/snakemake-wrappers/tree/master/bio/bgzip/test.
+
+if [ ! -d /tmp/snakemake-wrappers ]; then
+  git clone --depth 1 --single-branch --branch master https://github.com/snakemake/snakemake-wrappers /tmp/snakemake-wrappers
+fi
+
+cp -r /tmp/snakemake-wrappers/bio/bgzip/test/* src/bgzip/test_data
+

src/bgzip/test_data/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