Merge pull request #30 from nf-core/database-untar

Adds ability to conditionally untar databases TAR files that contain DB directories

conf/modules.config

@@ -91,7 +91,7 @@ process {
         publishDir = [
             path: { "${params.outdir}/kraken2/${meta.db_name}" },
             mode: 'copy',
-            pattern: '.{fastq.gz,txt}'
+            pattern: '*.{fastq.gz,txt}'
         ]
         ext.args = { "${meta.db_params}" }
         ext.prefix = { "${meta.id}-${meta.db_name}" }

modules.json

@@ -24,6 +24,8 @@
             "multiqc": {
                 "git_sha": "20d8250d9f39ddb05dfb437603aaf99b5c0b2b41"
             },
+            "untar": {
+                "git_sha": "e080f4c8acf5760039ed12ec1f206170f3f9a918"
             "porechop": {
                 "git_sha": "e20e57f90b6787ac9a010a980cf6ea98bd990046"
             }

modules/nf-core/modules/untar/main.nf

@@ -0,0 +1,36 @@
+process UNTAR {
+    tag "$archive"
+    label 'process_low'
+
+    conda (params.enable_conda ? "conda-forge::tar=1.32" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://containers.biocontainers.pro/s3/SingImgsRepo/biocontainers/v1.2.0_cv1/biocontainers_v1.2.0_cv1.img' :
+        'biocontainers/biocontainers:v1.2.0_cv1' }"
+
+    input:
+    tuple val(meta), path(archive)
+
+    output:
+    tuple val(meta), path("$untar"), 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 ?: ''
+    untar     = archive.toString() - '.tar.gz'
+    """
+    tar \\
+        -xzvf \\
+        $args \\
+        $archive \\
+        $args2 \\
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        untar: \$(echo \$(tar --version 2>&1) | sed 's/^.*(GNU tar) //; s/ Copyright.*\$//')
+    END_VERSIONS
+    """
+}

modules/nf-core/modules/untar/meta.yml

@@ -0,0 +1,38 @@
+name: untar
+description: Extract files.
+keywords:
+  - untar
+  - uncompress
+tools:
+  - untar:
+      description: |
+        Extract tar.gz files.
+      documentation: https://www.gnu.org/software/tar/manual/
+      licence: ["GPL-3.0-or-later"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - archive:
+      type: file
+      description: File to be untar
+      pattern: "*.{tar}.{gz}"
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - untar:
+      type: file
+      description:
+      pattern: "*.*"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@joseespinosa"
+  - "@drpatelh"

subworkflows/local/db_check.nf

@@ -3,6 +3,7 @@
 //
 
 include { DATABASE_CHECK } from '../../modules/local/database_check'
+include { UNTAR          } from '../../modules/nf-core/modules/untar/main'
 
 workflow DB_CHECK {
     take:
@@ -17,10 +18,21 @@ workflow DB_CHECK {
         .dump(tag: "db_split_csv_out")
         .map { create_db_channels(it) }
         .dump(tag: "db_channel_prepped")
-        .set{ dbs }
+
+    ch_dbs_for_untar = parsed_samplesheet
+        .branch {
+            untar: it[1].toString().endsWith(".tar.gz")
+            skip: true
+        }
+
+    // TODO Filter to only run UNTAR on DBs of tools actually using?
+    // TODO make optional whether to save
+    UNTAR ( ch_dbs_for_untar.untar )
+
+    ch_final_dbs = ch_dbs_for_untar.skip.mix( UNTAR.out.untar )
 
     emit:
-    dbs                                       // channel: [ val(meta), [ db ] ]
+    dbs = ch_final_dbs                        // channel: [ val(meta), [ db ] ]
     versions = DATABASE_CHECK.out.versions // channel: [ versions.yml ]
 }
 

subworkflows/local/input_check.nf

@@ -42,7 +42,7 @@ workflow INPUT_CHECK {
 }
 
 // Function to get list of [ meta, [ fastq_1, fastq_2 ] ]
-def create_fastq_channel(LinkedHashMap row) {
+def create_fastq_channels(LinkedHashMap row) {
     // create meta map
     def meta = [:]
     meta.id                     = row.sample