Add nf-test

.github/workflows/ci.yml

@@ -1,10 +1,13 @@
-name: nf-core CI
 # This workflow runs the pipeline with the minimal test dataset to check that it completes without any syntax errors
+name: nf-core CI
 on:
   push:
     branches:
-      - dev
+      - "dev"
   pull_request:
+    branches:
+      - "dev"
+      - "master"
   release:
     types: [published]
   workflow_dispatch:
@@ -15,16 +18,31 @@ env:
   NXF_SINGULARITY_LIBRARYDIR: ${{ github.workspace }}/.singularity
 
 concurrency:
-  group: "${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}"
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
 
 jobs:
+  define_nxf_versions:
+    name: Choose nextflow versions to test against depending on target branch
+    runs-on: ubuntu-latest
+    outputs:
+      matrix: ${{ steps.nxf_versions.outputs.matrix }}
+    steps:
+      - id: nxf_versions
+        run: |
+          if [[ "${{ github.event_name }}" == "pull_request" && "${{ github.base_ref }}" == "dev" && "${{ matrix.NXF_VER }}" != "latest-everything" ]]; then
+            echo matrix='["latest-everything"]' | tee -a $GITHUB_OUTPUT
+          else
+            echo matrix='["latest-everything", "23.10.0"]' | tee -a $GITHUB_OUTPUT
+          fi
+
   test:
     name: "Run pipeline with test data (${{ matrix.NXF_VER }} | ${{ matrix.test_name }} | ${{ matrix.profile }})"
     # Only run on push if this is the nf-core dev branch (merged PRs)
     if: "${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'nf-core/eager') }}"
     runs-on: ubuntu-latest
     strategy:
+      fail-fast: false
       matrix:
         NXF_VER:
           - "24.04.2"

.gitignore

@@ -8,3 +8,4 @@ testing*
 *.pyc
 null/
 .nf-test*
+

conf/test.config

@@ -38,6 +38,7 @@ params {
     run_bamfiltering                      = true
     bamfiltering_minreadlength            = 30
     bamfiltering_mappingquality           = 37
+    bamfiltering_savefilteredbams         = true
 
     // Map Stats
     run_bedtools_coverage                 = true

nf-test.config

@@ -0,0 +1,14 @@
+config {
+
+    testsDir "tests"
+    workDir ".nf-test"
+    configFile "tests/nextflow.config"
+    profile ""
+
+    // load the necessary plugins
+    plugins {
+        load "[email protected]"
+        load "[email protected]"
+    }
+
+}

tests/nextflow.config

@@ -0,0 +1,5 @@
+/*
+========================================================================================
+    Nextflow config file for running tests
+========================================================================================
+*/

tests/test.nf.test

@@ -0,0 +1,95 @@
+nextflow_pipeline {
+
+    name "Test pipeline: NFCORE_EAGER"
+    script "main.nf"
+    tag "pipeline"
+    tag "nfcore_eager"
+    tag "test"
+
+    test("test_profile") {
+
+        when {
+            params {
+                outdir = "$outputDir"
+            }
+        }
+
+        then {
+
+            // Each top level results directory should be tested with individual snapshots/variables
+            // stable_name_<dir> is for files with variable md5sums (i.e. content) so only names will be compared
+            // stable_content_<dir> is for files with stable md5sums (i.e. content) so md5sums will be compared
+            // For both cases, use the third argument to specify globs to exclude certain files
+            // If a directory is fully stable, you can drop `stable_name_*`
+            // Generate with: nf-test test --tag test --profile docker,test --update-snapshot
+            // Test with:     nf-test test --tag test --profile docker,test
+            // NOTE: BAMs are always only stable in name, because:
+            //   a) sharding breaks header since the shard that was first is named in the header
+            //   b) the order of the reads in the BAMs is not stable (sorted, but reads that share a start position can be in any order)
+            //   point b) also causes BAIs to be unstable.
+
+            // Check that no files are missing/added
+            // Command legend:                                       Result directory to index      , include dirs?, exclude patterns                    , exclude pattern list, include patterns
+            def stable_name_all                 = getAllFilesFromDir("$outputDir/"                  , true         , ['pipeline_info/*']                 , null                , ['*', '**/*'] )
+
+            // Bam filtering
+            def stable_content_bamfiltering     = getAllFilesFromDir("$outputDir/bam_filtering"     , true         , ['*.{bam,bai}']                     , null                , ['*.flagstat'] )
+            def stable_name_bamfiltering        = getAllFilesFromDir("$outputDir/bam_filtering"     , true         , ['*.flagstat']                      , null                , ['*.{bam,bai}'] )
+
+            // Bam input stats
+            def stable_content_baminputstats    = getAllFilesFromDir("$outputDir/bam_input_stats"   , true         , null                                , null                , ['*.flagstat'] )
+
+            // Damage estimation
+            def stable_content_damageestimation = getAllFilesFromDir("$outputDir/damage_estimation" , true         , ['**/*.{svg,pdf,log}']              , null                , ['**/*.{txt,json}'] )
+            def stable_name_damageestimation    = getAllFilesFromDir("$outputDir/damage_estimation" , true         , ['**/*.{txt,json}']                 , null                , ['**/*.{svg,pdf,log}'] )
+
+            // Deduplication
+            def stable_content_deduplication    = getAllFilesFromDir("$outputDir/deduplication"     , true         , ['*.{bam,bai}']                     , null                , ['*.flagstat'] )
+            def stable_name_deduplication       = getAllFilesFromDir("$outputDir/deduplication"     , true         , ['*.flagstat']                      , null                , ['*.{bam,bai}'] )
+
+            // Final_bams
+            def stable_content_final_bams       = getAllFilesFromDir("$outputDir/final_bams"        , true         , null                                , null                , ['**/*.flagstat']  )
+            def stable_name_final_bams          = getAllFilesFromDir("$outputDir/final_bams"        , true         , null                                , null                , ['**/*.{bam,bai}']  )
+
+            // Mapping
+            def stable_content_mapping          = getAllFilesFromDir("$outputDir/mapping"           , true         , null                                , null                , ['**/*.flagstat'] )
+            def stable_name_mapping             = getAllFilesFromDir("$outputDir/mapping"           , true         , null                                , null                , ['**/*.{bam,bai}'] )
+
+            // Mapstats
+            // NOTE: GC content data and plot has minor changes between runs. I suspect this is because of the order of reads that start at the same position being unstable, but I am not sure.
+            def stable_content_mapstats         = getAllFilesFromDir("$outputDir/mapstats"          , true         , ['**/*.html', '**/mapped_reads_gc-content_distribution.txt', '**/genome_gc_content_per_window.png'], null , ['**/*.{bed,json,txt,log,css,png,js}'] )
+            def stable_name_mapstats            = getAllFilesFromDir("$outputDir/mapstats"          , true         , null                                                                                               , null , ['**/*.html', '**/mapped_reads_gc-content_distribution.txt', '**/genome_gc_content_per_window.png'] )
+
+            // MultiQC
+            def stable_name_multiqc             = getAllFilesFromDir("$outputDir/multiqc"           , true         , null                                , null                , ['*', '**/*'] )
+
+            // Preprocessing
+            def stable_content_preprocessing    = getAllFilesFromDir("$outputDir/preprocessing"     , true         , ['**/*.{zip,log}', '**/*fastp.html'], null                , ['**/*'] )
+            def stable_name_preprocessing       = getAllFilesFromDir("$outputDir/preprocessing"     , true         , null                                , null                , ['**/*.{zip,log}', '**/*fastp.html'] )
+
+            assertAll(
+                { assert workflow.success },
+                // This checks that there are no missing or additional output files.
+                // Also a good starting point to look at all the files in the output folder than need to be checked in subsequent sections.
+                { assert snapshot( stable_name_all*.name            ).match("all_files") },
+
+                // Checking changes to contents of each section
+                { assert snapshot( stable_content_bamfiltering    , stable_name_bamfiltering*.name     ).match("bam_filtering") },
+                { assert snapshot( stable_content_baminputstats   ).match("bam_input_stats") },
+                { assert snapshot( stable_content_damageestimation, stable_name_damageestimation*.name ).match("damage_estimation") },
+                { assert snapshot( stable_content_deduplication   , stable_name_deduplication*.name    ).match("deduplication") },
+                { assert snapshot( stable_content_final_bams      , stable_name_final_bams*.name       ).match("final_bams") },
+                // NOTE: The snapshot section for mapping cannot be named 'mapping'. See https://github.com/askimed/nf-test/issues/279
+                { assert snapshot( stable_content_mapping         , stable_name_mapping*.name          ).match("mapping_output") },
+                { assert snapshot( stable_content_mapstats        , stable_name_mapstats*.name         ).match("mapstats") },
+                { assert snapshot( stable_name_multiqc*.name      ).match("multiqc") },
+                { assert snapshot( stable_content_preprocessing   , stable_name_preprocessing*.name    ).match("preprocessing") },
+
+                // Versions
+                { assert new File("$outputDir/pipeline_info/nf_core_pipeline_software_mqc_versions.yml").exists() },
+
+
+            )
+        }
+    }
+}