Merge pull request #455 from maxulysse/dev_tools_update_2

Second attempt at updating all modules

.gitattributes

@@ -1 +1,3 @@
 *.config linguist-language=nextflow
+modules/nf-core/** linguist-generated
+subworkflows/nf-core/** linguist-generated

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,52 @@
+
+name: Bug report
+description: Report something that is broken or incorrect
+labels: bug
+body:
+
+  - type: markdown
+    attributes:
+      value: |
+        Before you post this issue, please check the documentation:
+
+        - [nf-core website: troubleshooting](https://nf-co.re/usage/troubleshooting)
+        - [nf-core/sarek pipeline documentation](https://nf-co.re/sarek/usage)
+
+  - type: textarea
+    id: description
+    attributes:
+      label: Description of the bug
+      description: A clear and concise description of what the bug is.
+    validations:
+      required: true
+
+  - type: textarea
+    id: command_used
+    attributes:
+      label: Command used and terminal output
+      description: Steps to reproduce the behaviour. Please paste the command you used to launch the pipeline and the output from your terminal.
+      render: console
+      placeholder: |
+        $ nextflow run ...
+
+        Some output where something broke
+
+  - type: textarea
+    id: files
+    attributes:
+      label: Relevant files
+      description: |
+        Please upload (drag and drop) and relevant files. Make into a `.zip` file if the extension is not allowed.
+        Your verbose log file `.nextflow.log` is often useful _(this is a hidden file in the directory where you launched the pipeline)_ as well as custom Nextflow configuration files.
+
+  - type: textarea
+    id: system
+    attributes:
+      label: System information
+      description: |
+        * Nextflow version _(eg. 21.04.01)_
+        * Hardware _(eg. HPC, Desktop, Cloud)_
+        * Executor _(eg. slurm, local, awsbatch)_
+        * Container engine: _(e.g. Docker, Singularity, Conda, Podman, Shifter or Charliecloud)_
+        * OS _(eg. CentOS Linux, macOS, Linux Mint)_
+        * Version of nf-core/sarek _(eg. 1.1, 1.5, 1.8.2)_

.github/ISSUE_TEMPLATE/config.yml

@@ -1,4 +1,3 @@
-blank_issues_enabled: false
 contact_links:
   - name: Join nf-core
     url: https://nf-co.re/join

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -0,0 +1,11 @@
+name: Feature request
+description: Suggest an idea for the nf-core/sarek pipeline
+labels: enhancement
+body:
+  - type: textarea
+    id: description
+    attributes:
+      label: Description of feature
+      description: Please describe your suggestion for a new feature. It might help to describe a problem or use case, plus any alternatives that you have considered.
+    validations:
+      required: true

.github/workflows/ci.yml

@@ -32,9 +32,9 @@ jobs:
           - 'gatk4_spark'
           - 'save_bam_mapped'
           - 'skip_markduplicates'
-          - 'targeted'
+          # - 'targeted'
           - 'tumor_normal_pair'
-          - 'variant_calling'
+          # - 'variant_calling'
     steps:
       - name: Check out pipeline code
         uses: actions/checkout@v2

.github/workflows/linting.yml

@@ -120,7 +120,7 @@ jobs:
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          pip install nf-core
+          pip install nf-core git+https://github.com/nf-core/tools.git@dev
 
       - name: Run nf-core lint
         env:

.nf-core.yml

@@ -1,5 +1,7 @@
 lint:
   files_unchanged:
+    - .github/workflows/linting.yml
+    - assets/multiqc_config.yaml
     - assets/nf-core-sarek_logo.png
     - docs/images/nf-core-sarek_logo.png
     - lib/NfcoreTemplate.groovy

conf/genomes.config

@@ -86,8 +86,8 @@ params {
         'small_hg38' {
             dbsnp                 = "${params.genomes_base}/data/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz"
             fasta                 = "${params.genomes_base}/data/genomics/homo_sapiens/genome/genome.fasta"
-            fasta_fai             = "${params.genomes_base}/data/genomics/homo_sapiens/genome/genome.fasta.fai"
             germline_resource     = "${params.genomes_base}/data/genomics/homo_sapiens/genome/vcf/gnomAD.r2.1.1.vcf.gz"
+            intervals             = "${params.genomes_base}/data/genomics/homo_sapiens/genome/genome.interval_list"
             known_indels          = "${params.genomes_base}/data/genomics/homo_sapiens/genome/vcf/mills_and_1000G.indels.vcf.gz"
             snpeff_db             = 'GRCh38.99'
             vep_genome            = 'GRCh38'

conf/modules.config

@@ -94,13 +94,11 @@ params {
         }
         'samtools_index_mapping' {
             publish_by_meta  = true
-            publish_files    = ['bai':'mapped']
+            publish_files    = ['bam': 'mapped', 'bai': 'mapped']
             publish_dir      = 'preprocessing'
         }
         'merge_bam_mapping' {
-            publish_by_meta  = true
-            publish_files    = ['bam':'mapped']
-            publish_dir      = 'preprocessing'
+            publish_files    = false
         }
         'seqkit_split2' {
             args             = "--by-size ${params.split_fastq}"
@@ -115,7 +113,7 @@ params {
             publish_files    = ['metrics': 'markduplicates']
         }
         'markduplicates' {
-            args             = 'REMOVE_DUPLICATES=false VALIDATION_STRINGENCY=LENIENT'
+            args             = '-REMOVE_DUPLICATES false -VALIDATION_STRINGENCY LENIENT'
             suffix           = '.md'
             publish_by_meta  = true
             publish_dir      = 'preprocessing'

conf/test.config

@@ -20,12 +20,12 @@ params {
     max_time   = 6.h
 
     // Input data
-    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/sarek/testdata/csv/tiny-manta-normal-https.csv'
+    input = "${baseDir}/tests/csv/3.0/fastq_single.csv"
 
     // Small reference genome
     igenomes_ignore   = true
-    genome            = 'smallGRCh37'
-    genomes_base      = "https://raw.githubusercontent.com/nf-core/test-datasets/sarek/reference"
+    genome            = 'small_hg38'
+    genomes_base      = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules'
     snpeff_db         = 'WBcel235.99'
     vep_species       = 'caenorhabditis_elegans'
     vep_cache_version = '104'
@@ -42,7 +42,7 @@ profiles {
         params.step                = 'annotate'
     }
     pair {
-        params.input               = 'https://raw.githubusercontent.com/nf-core/test-datasets/sarek/testdata/csv/tiny-manta-https.csv'
+        params.input               = "${baseDir}/tests/csv/3.0/fastq_pair.csv"
     }
     prepare_recalibration {
         params.input               = 'https://raw.githubusercontent.com/nf-core/test-datasets/sarek/testdata/csv/tiny-mapped-normal-https.csv'
@@ -77,22 +77,22 @@ profiles {
         params.trim_fastq          = true
     }
     use_gatk_spark {
-        params.use_gatk_spark      = 'markduplicates,bqsr'
+        params.use_gatk_spark      = 'bqsr,markduplicates'
     }
     umi_quiaseq {
         params.genome              = 'smallGRCh38'
         params.genomes_base        = 'https://raw.githubusercontent.com/nf-core/test-datasets/sarek/reference/chr20_hg38'
         params.input               = 'https://raw.githubusercontent.com/nf-core/test-datasets/sarek/testdata/csv/tiny-umi-qiaseq-https.csv'
-        params.read_structure1     = "12M11S+T"
-        params.read_structure2     = "12M11S+T"
+        params.read_structure1     = '12M11S+T'
+        params.read_structure2     = '12M11S+T'
         params.umi                 = true
     }
     umi_tso {
         genome                     = 'smallGRCh38'
         genomes_base               = 'https://raw.githubusercontent.com/nf-core/test-datasets/sarek/reference/chr20_hg38'
         input                      = 'https://raw.githubusercontent.com/nf-core/test-datasets/sarek/testdata/csv/tiny-umi-tso-https.csv'
-        read_structure1            = "7M1S+T"
-        read_structure2            = "7M1S+T"
+        read_structure1            = '7M1S+T'
+        read_structure2            = '7M1S+T'
         umi                        = true
     }
 }

lib/NfcoreSchema.groovy

@@ -105,9 +105,13 @@ class NfcoreSchema {
 
         // Collect expected parameters from the schema
         def expectedParams = []
+        def enums = [:]
         for (group in schemaParams) {
             for (p in group.value['properties']) {
                 expectedParams.push(p.key)
+                if (group.value['properties'][p.key].containsKey('enum')) {
+                    enums[p.key] = group.value['properties'][p.key]['enum']
+                }
             }
         }
 
@@ -155,7 +159,7 @@ class NfcoreSchema {
             println ''
             log.error 'ERROR: Validation of pipeline parameters failed!'
             JSONObject exceptionJSON = e.toJSON()
-            printExceptions(exceptionJSON, params_json, log)
+            printExceptions(exceptionJSON, params_json, log, enums)
             println ''
             has_error = true
         }
@@ -260,13 +264,12 @@ class NfcoreSchema {
 
         // Get pipeline parameters defined in JSON Schema
         def Map params_summary = [:]
-        def blacklist  = ['hostnames']
         def params_map = paramsLoad(getSchemaPath(workflow, schema_filename=schema_filename))
         for (group in params_map.keySet()) {
             def sub_params = new LinkedHashMap()
             def group_params = params_map.get(group)  // This gets the parameters of that particular group
             for (param in group_params.keySet()) {
-                if (params.containsKey(param) && !blacklist.contains(param)) {
+                if (params.containsKey(param)) {
                     def params_value = params.get(param)
                     def schema_value = group_params.get(param).default
                     def param_type   = group_params.get(param).type
@@ -330,7 +333,7 @@ class NfcoreSchema {
     //
     // Loop over nested exceptions and print the causingException
     //
-    private static void printExceptions(ex_json, params_json, log) {
+    private static void printExceptions(ex_json, params_json, log, enums, limit=5) {
         def causingExceptions = ex_json['causingExceptions']
         if (causingExceptions.length() == 0) {
             def m = ex_json['message'] =~ /required key \[([^\]]+)\] not found/
@@ -346,7 +349,16 @@ class NfcoreSchema {
             else {
                 def param = ex_json['pointerToViolation'] - ~/^#\//
                 def param_val = params_json[param].toString()
-                log.error "* --${param}: ${ex_json['message']} (${param_val})"
+                if (enums.containsKey(param)) {
+                    def error_msg = "* --${param}: '${param_val}' is not a valid choice (Available choices"
+                    if (enums[param].size() > limit) {
+                        log.error "${error_msg} (${limit} of ${enums[param].size()}): ${enums[param][0..limit-1].join(', ')}, ... )"
+                    } else {
+                        log.error "${error_msg}: ${enums[param].join(', ')})"
+                    }
+                } else {
+                    log.error "* --${param}: ${ex_json['message']} (${param_val})"
+                }
             }
         }
         for (ex in causingExceptions) {