Merge pull request #599 from maxulysse/dev_csv_check

Add checks for correct data type for params.step

CHANGELOG.md

@@ -99,6 +99,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#590](https://github.com/nf-core/sarek/pull/590) - Fix empty folders during scatter/gather
 - [#592](https://github.com/nf-core/sarek/pull/592) - Fix optional resources for Mutect2, GetPileupSummaries, and HaplotypeCaller: issue [#299](https://github.com/nf-core/sarek/issues/299), [#359](https://github.com/nf-core/sarek/issues/359), [#367](https://github.com/nf-core/sarek/issues/367)
 - [#598](https://github.com/nf-core/sarek/pull/598) - Remove WARNING message for config selector not matching
+- [#599](https://github.com/nf-core/sarek/pull/599) - Add checks for correct data type for `params.step`
+- [#599](https://github.com/nf-core/sarek/pull/599) - Add checks for no empty `--tools` with `--step variant_calling` or `--step annotation`
 - [#600](https://github.com/nf-core/sarek/pull/600) - Remove `nf-core lint` warnings
 
 ### Deprecated

workflows/sarek.nf

@@ -80,6 +80,16 @@ if(!params.dbsnp && !params.known_indels){
     }
 }
 
+if (params.step == "variant_calling" && !params.tools) {
+    log.error "Please specify at least one tool when using `--step variant_calling`.\nhttps://nf-co.re/sarek/parameters#tools"
+    exit 1
+}
+
+if (params.step == "annotation" && !params.tools) {
+    log.error "Please specify at least one tool when using `--step annotation`.\nhttps://nf-co.re/sarek/parameters#tools"
+    exit 1
+}
+
 // Save AWS IGenomes file containing annotation version
 def anno_readme = params.genomes[params.genome]?.readme
 if (anno_readme && file(anno_readme).exists()) {
@@ -943,18 +953,14 @@ def extract_csv(csv_file) {
 
     // check that the sample sheet is not 1 line or less, because it'll skip all subsequent checks if so.
     new File(csv_file.toString()).withReader('UTF-8') { reader ->
-      def line, numberOfLinesInSampleSheet = 0;
-      while ((line = reader.readLine()) != null) {
-        numberOfLinesInSampleSheet++
-      }
-      if( numberOfLinesInSampleSheet < 2){
-        log.error "Sample sheet had less than two lines. The sample sheet must be a csv file with a header, so at least two lines."
-        System.exit(1)
-      }
+        def line, numberOfLinesInSampleSheet = 0;
+        while ((line = reader.readLine()) != null) {numberOfLinesInSampleSheet++}
+        if (numberOfLinesInSampleSheet < 2) {
+            log.error "Sample sheet had less than two lines. The sample sheet must be a csv file with a header, so at least two lines."
+            System.exit(1)
+        }
     }
 
-
-
     Channel.from(csv_file).splitCsv(header: true)
         //Retrieves number of lanes by grouping together by patient and sample and counting how many entries there are for this combination
         .map{ row ->
@@ -1003,57 +1009,106 @@ def extract_csv(csv_file) {
             meta.data_type  = "fastq"
 
             meta.size       = 1 // default number of splitted fastq
-            return [meta, [fastq_1, fastq_2]]
+
+            if (params.step == 'mapping') return [meta, [fastq_1, fastq_2]]
+            else {
+                log.error "Samplesheet contains fastq files but step is `$params.step`. Please check your samplesheet or adjust the step parameter.\nhttps://nf-co.re/sarek/usage#input-samplesheet-configurations"
+                System.exit(1)
+            }
+
         // start from BAM
         } else if (row.lane && row.bam) {
             meta.id         = "${row.sample}-${row.lane}".toString()
             def bam         = file(row.bam,   checkIfExists: true)
             def CN          = params.seq_center ? "CN:${params.seq_center}\\t" : ''
             def read_group  = "\"@RG\\tID:${row_sample}_${row.lane}\\t${CN}PU:${row.lane}\\tSM:${row.sample}\\tLB:${row.sample}\\tPL:${params.seq_platform}\""
+
             meta.numLanes   = numLanes.toInteger()
             meta.read_group = read_group.toString()
             meta.data_type  = "bam"
+
             meta.size       = 1 // default number of splitted fastq
-            return [meta, bam]
+
+            if (params.step == 'mapping') return [meta, bam]
+            else {
+                log.error "Samplesheet contains ubam files but step is `$params.step`. Please check your samplesheet or adjust the step parameter.\nhttps://nf-co.re/sarek/usage#input-samplesheet-configurations"
+                System.exit(1)
+            }
+
         // recalibration
         } else if (row.table && row.cram) {
             meta.id   = meta.sample
             def cram  = file(row.cram,  checkIfExists: true)
             def crai  = file(row.crai,  checkIfExists: true)
             def table = file(row.table, checkIfExists: true)
+
             meta.data_type  = "cram"
-            return [meta, cram, crai, table]
+
+            if (!(params.step == 'mapping' || params.step == 'annotate')) return [meta, cram, crai, table]
+            else {
+                log.error "Samplesheet contains cram files but step is `$params.step`. Please check your samplesheet or adjust the step parameter.\nhttps://nf-co.re/sarek/usage#input-samplesheet-configurations"
+                System.exit(1)
+            }
+
         // recalibration when skipping MarkDuplicates
         } else if (row.table && row.bam) {
             meta.id   = meta.sample
             def bam   = file(row.bam,   checkIfExists: true)
             def bai   = file(row.bai,   checkIfExists: true)
             def table = file(row.table, checkIfExists: true)
+
             meta.data_type  = "bam"
-            return [meta, bam, bai, table]
+
+            if (!(params.step == 'mapping' || params.step == 'annotate')) return [meta, bam, bai, table]
+            else {
+                log.error "Samplesheet contains bam files but step is `$params.step`. Please check your samplesheet or adjust the step parameter.\nhttps://nf-co.re/sarek/usage#input-samplesheet-configurations"
+                System.exit(1)
+            }
+
         // prepare_recalibration or variant_calling
         } else if (row.cram) {
             meta.id = meta.sample
             def cram = file(row.cram, checkIfExists: true)
             def crai = file(row.crai, checkIfExists: true)
+
             meta.data_type  = "cram"
-            return [meta, cram, crai]
+
+            if (!(params.step == 'mapping' || params.step == 'annotate')) return [meta, cram, crai]
+            else {
+                log.error "Samplesheet contains bam files but step is `$params.step`. Please check your samplesheet or adjust the step parameter.\nhttps://nf-co.re/sarek/usage#input-samplesheet-configurations"
+                System.exit(1)
+            }
+
         // prepare_recalibration when skipping MarkDuplicates or `--step markduplicates`
         } else if (row.bam) {
             meta.id = meta.sample
             def bam = file(row.bam, checkIfExists: true)
             def bai = file(row.bai, checkIfExists: true)
+
             meta.data_type  = "bam"
-            return [meta, bam, bai]
+
+            if (!(params.step == 'mapping' || params.step == 'annotate')) return [meta, bam, bai]
+            else {
+                log.error "Samplesheet contains bam files but step is `$params.step`. Please check your samplesheet or adjust the step parameter.\nhttps://nf-co.re/sarek/usage#input-samplesheet-configurations"
+                System.exit(1)
+            }
+
         // annotation
         } else if (row.vcf) {
             meta.id = meta.sample
             def vcf = file(row.vcf, checkIfExists: true)
+
             meta.data_type     = "vcf"
             meta.variantcaller = row.variantcaller ?: ""
-            return [meta, vcf]
+
+            if (params.step == 'annotate') return [meta, vcf]
+            else {
+                log.error "Samplesheet contains vcf files but step is `$params.step`. Please check your samplesheet or adjust the step parameter.\nhttps://nf-co.re/sarek/usage#input-samplesheet-configurations"
+                System.exit(1)
+            }
         } else {
-            log.warn "Missing or unknown field in csv file header"
+            log.warn "Missing or unknown field in csv file header. Please check your samplesheet"
+            System.exit(1)
         }
     }
 }