Merge pull request #3 from mirpedrol/fix-linting

fix nf-core linting

.github/workflows/test.yml

@@ -125,7 +125,7 @@ jobs:
         uses: nf-core/setup-nextflow@v2
 
       - name: Install nf-core tools development version
-        run: python -m pip install --upgrade --force-reinstall git+https://github.com/nf-core/tools.git@dev
+        run: python -m pip install --upgrade --force-reinstall git+https://github.com/mirpedrol/tools.git@modules-yml-ontology
 
       - name: Lint module ${{ matrix.tags }}
         run: nf-core modules --git-remote https://github.com/mirpedrol/class-modules lint ${{ matrix.tags }}

.gitignore

@@ -0,0 +1,2 @@
+.nf-test.log
+.nf-test/

modules/class-modules/pigz/compress/environment.yml

@@ -0,0 +1,9 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+name: "pigz_compress"
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - "pigz=2.8"

modules/class-modules/pigz/compress/main.nf

@@ -0,0 +1,45 @@
+process PIGZ_COMPRESS {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/pigz:2.8':
+        'biocontainers/pigz:2.8' }"
+
+    input:
+    tuple val(meta), path(raw_file)
+
+    output:
+    tuple val(meta), path("$archive"), emit: archive
+    path "versions.yml"              , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    archive = raw_file.toString() + ".gz"
+    """
+    # Note: needs --stdout for pigz to avoid the following issue:
+    #   pigz: skipping: ${raw_file} is a symbolic link
+    pigz --processes $task.cpus --stdout --force ${args} ${raw_file} > ${archive}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        pigz:\$(echo \$(pigz --version 2>&1) | sed 's/^.*pigz\\w*//' )
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    archive = raw_file.toString() + ".gz"
+    """
+    touch ${archive}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        pigz:\$(echo \$(pigz --version 2>&1) | sed 's/^.*pigz\\w*//' )
+    END_VERSIONS
+    """
+}

modules/class-modules/pigz/compress/meta.yml

@@ -0,0 +1,43 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/mirpedrol/class-modules/main/modules/yaml-schema.json
+name: "pigz_compress"
+description: Compresses files with pigz.
+keywords:
+  - compress
+  - gzip
+  - parallelized
+tools:
+  - "pigz":
+      description: "Parallel implementation of the gzip algorithm."
+      homepage: "https://zlib.net/pigz/"
+      documentation: "https://zlib.net/pigz/pigz.pdf"
+      identifier: ""
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1', single_end:false ]`
+    - raw_file:
+        type: file
+        description: File to be compressed
+        pattern: "*.*"
+output:
+  - archive:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - $archive:
+          type: file
+          description: The compressed file
+          pattern: "*.gz"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@leoisl"
+maintainers:
+  - "@leoisl"

modules/class-modules/pigz/compress/tests/main.nf.test

@@ -0,0 +1,49 @@
+nextflow_process {
+    name "Test Process PIGZ_COMPRESS"
+    script "../main.nf"
+    process "PIGZ_COMPRESS"
+
+    tag "modules"
+    tag "modules_classmodules"
+    tag "pigz"
+    tag "pigz/compress"
+
+    test("sarscov2 - genome - fasta") {
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test'], // meta map
+                    file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+                    ]
+                """
+            }
+        }
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    test("sarscov2 - genome - fasta - stub") {
+        options "-stub-run"
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test'], // meta map
+                    file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+                    ]
+                """
+            }
+        }
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(file(process.out.archive[0][1]).name).match() }
+            )
+        }
+    }
+}

modules/class-modules/pigz/compress/tests/main.nf.test.snap

@@ -0,0 +1,37 @@
+{
+    "sarscov2 - genome - fasta": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "genome.fasta.gz:md5,6e9fe4042a72f2345f644f239272b7e6"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,ca30e9e1ffa1394ba7eefdac8cf3a3ad"
+                ],
+                "archive": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "genome.fasta.gz:md5,6e9fe4042a72f2345f644f239272b7e6"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,ca30e9e1ffa1394ba7eefdac8cf3a3ad"
+                ]
+            }
+        ],
+        "timestamp": "2023-12-11T22:39:53.350546"
+    },
+    "sarscov2 - genome - fasta - stub": {
+        "content": [
+            "genome.fasta.gz"
+        ],
+        "timestamp": "2023-12-11T22:52:24.309192"
+    }
+}

modules/class-modules/pigz/compress/tests/tags.yml

@@ -0,0 +1,2 @@
+pigz/compress:
+  - "modules/nf-core/pigz/compress/**"

modules/class-modules/tcoffee/irmsd/main.nf

@@ -7,13 +7,13 @@ process TCOFFEE_IRMSD {
         'https://depot.galaxyproject.org/singularity/mulled-v2-a76a981c07359a31ff55b9dc13bd3da5ce1909c1:84c8f17f1259b49e2f7783b95b7a89c6f2cb199e-0':
         'biocontainers/mulled-v2-a76a981c07359a31ff55b9dc13bd3da5ce1909c1:84c8f17f1259b49e2f7783b95b7a89c6f2cb199e-0' }"
 
-    input:
-    tuple  val(meta),  file (msa)
-    tuple  val(meta2), file(template), file(structures)
+    input: 
+    tuple val(meta), path(msa)
+    tuple val(meta2), path(template), path(structures)
 
     output:
-    tuple val(meta), path ("${prefix}.irmsd"), emit: irmsd
-    path "versions.yml"                      , emit: versions
+    tuple val(meta), path("${prefix}.irmsd"), emit: irmsd
+    path "versions.yml"                     , emit: versions
 
     when:
     task.ext.when == null || task.ext.when

modules/class-modules/tcoffee/irmsd/meta.yml

@@ -6,8 +6,8 @@ keywords:
   - evaluation
 tools:
   - "tcoffee":
-      description: "A collection of tools for Multiple Alignments of DNA, RNA, Protein
-        Sequence"
+      description: "A collection of tools for Multiple Alignments of DNA, RNA, Protein\
+        \ Sequence"
       homepage: "http://www.tcoffee.org/Projects/tcoffee/"
       documentation: "https://tcoffee.readthedocs.io/en/latest/tcoffee_main_documentation.html"
       tool_dev_url: "https://github.com/cbcrg/tcoffee"
@@ -25,7 +25,27 @@ input:
         description: |
           Groovy Map containing sample information
           e.g. [ id:'test', ... ]
+    - msa:
+        type: file
+        description: fasta file containing the alignment to be evaluated. May be gzipped
+          or uncompressed.
+        pattern: "*.{aln,fa,fasta,fas}{.gz,}"
+        ontologies:
+          - edam: http://edamontology.org/format_1984
   - - meta2:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test', ... ]
+    - template:
+        type: file
+        description: T_coffee template file that maps sequences to the accessory information
+          files to be used.
+    - structures:
+        type: file
+        description: Structure file to be used in the alignment. For example, it could
+          be protein structures or secondary structures.
+
 output:
   - irmsd:
       - meta:

modules/class-modules/tcoffee/tcs/meta.yml

@@ -1,4 +1,4 @@
-# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+# yaml-language-server: $schema=https://raw.githubusercontent.com/mirpedrol/class-modules/main/modules/yaml-schema.json
 name: "tcoffee_tcs"
 description: Compute the TCS score for a MSA or for a MSA plus a library file. Outputs
   the tcs as it is and a csv with just the total TCS score.
@@ -29,12 +29,15 @@ input:
           e.g. [ id:'test', ... ]
     - msa:
         type: file
-        description: fasta file containing the alignment to be evaluated. May be gzipped
-          or uncompressed.
+        description: fasta file containing the alignment to be evaluated. May be gzipped or uncompressed.
         pattern: "*.{aln,fa,fasta,fas}{.gz,}"
         ontologies:
           - edam: http://edamontology.org/format_1984
   - - meta2:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test', ... ]
     - lib:
         type: file
         description: lib file containing the alignment library of the given msa.

modules/class-modules/untar/environment.yml

@@ -0,0 +1,11 @@
+name: untar
+
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+
+dependencies:
+  - conda-forge::grep=3.11
+  - conda-forge::sed=4.7
+  - conda-forge::tar=1.34

modules/class-modules/untar/main.nf

@@ -0,0 +1,63 @@
+process UNTAR {
+    tag "$archive"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/ubuntu:20.04' :
+        'nf-core/ubuntu:20.04' }"
+
+    input:
+    tuple val(meta), path(archive)
+
+    output:
+    tuple val(meta), path("$prefix"), emit: untar
+    path "versions.yml"             , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args  = task.ext.args ?: ''
+    def args2 = task.ext.args2 ?: ''
+    prefix    = task.ext.prefix ?: ( meta.id ? "${meta.id}" : archive.baseName.toString().replaceFirst(/\.tar$/, ""))
+
+    """
+    mkdir $prefix
+
+    ## Ensures --strip-components only applied when top level of tar contents is a directory
+    ## If just files or multiple directories, place all in prefix
+    if [[ \$(tar -taf ${archive} | grep -o -P "^.*?\\/" | uniq | wc -l) -eq 1 ]]; then
+        tar \\
+            -C $prefix --strip-components 1 \\
+            -xavf \\
+            $args \\
+            $archive \\
+            $args2
+    else
+        tar \\
+            -C $prefix \\
+            -xavf \\
+            $args \\
+            $archive \\
+            $args2
+    fi
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        untar: \$(echo \$(tar --version 2>&1) | sed 's/^.*(GNU tar) //; s/ Copyright.*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    prefix    = task.ext.prefix ?: ( meta.id ? "${meta.id}" : archive.toString().replaceFirst(/\.[^\.]+(.gz)?$/, ""))
+    """
+    mkdir $prefix
+    touch ${prefix}/file.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        untar: \$(echo \$(tar --version 2>&1) | sed 's/^.*(GNU tar) //; s/ Copyright.*\$//')
+    END_VERSIONS
+    """
+}