Restore validation of SRA ids and ENA metadata fields

Signed-off-by: Ben Sherman <[email protected]>

Author: bentsherman

main.nf

@@ -32,11 +32,9 @@ include { Sample                  } from './workflows/sra'
 
 params {
 
-    // TODO: declare as Set<SraId> and construct SraId with isSraId()
     // Set of SRA/ENA/GEO/DDBJ identifiers to download their associated metadata and FastQ files
-    input: Set<String>
+    input: Path
 
-    // TODO: declare as EnaMetadataFields and construct with sraCheckENAMetadataFields()
     // Comma-separated list of ENA metadata fields to fetch before downloading data.
     ena_metadata_fields: String = ''
 
@@ -47,7 +45,7 @@ params {
     skip_fastq_download: Boolean = false
 
     // dbGaP repository key.
-    dbgap_key: Path? = null
+    dbgap_key: Path?
 
 }
 
@@ -63,20 +61,22 @@ workflow {
     //
     // SUBWORKFLOW: Run initialisation tasks
     //
-    PIPELINE_INITIALISATION (
+    ids = PIPELINE_INITIALISATION (
         params.version,
         params.help,
         params.validate_params,
         params.monochrome_logs,
         args,
-        workflow.outputDir
+        workflow.outputDir,
+        params.input,
+        params.ena_metadata_fields
     )
 
     //
     // WORKFLOW: Run primary workflows for the pipeline
     //
     sra = SRA (
-        Channel.fromList(params.input),
+        Channel.fromList(ids),
         [
             ena_metadata_fields: params.ena_metadata_fields,
             download_method: params.download_method,

subworkflows/local/utils_nfcore_fetchngs_pipeline/main.nf

@@ -29,12 +29,14 @@ include { workflowCitation          } from '../../nf-core/utils_nfcore_pipeline'
 workflow PIPELINE_INITIALISATION {
 
     take:
-    version             : boolean   // Display version and exit
-    help                : boolean   // Display help text
-    validate_params     : boolean   // Validate parameters against the schema at runtime
-    monochrome_logs     : boolean   // Do not use coloured log outputs
-    nextflow_cli_args   : List      // List of positional nextflow CLI args
-    outdir              : String    // The output directory where the results will be saved
+    version             : boolean       // Display version and exit
+    help                : boolean       // Display help text
+    validate_params     : boolean       // Validate parameters against the schema at runtime
+    monochrome_logs     : boolean       // Do not use coloured log outputs
+    nextflow_cli_args   : List<String>  // List of positional nextflow CLI args
+    outdir              : String        // The output directory where the results will be saved
+    input               : Path          // File containing SRA/ENA/GEO/DDBJ identifiers one per line to download their associated metadata and FastQ files
+    ena_metadata_fields : String        // Comma-separated list of ENA metadata fields to fetch before downloading data
 
     main:
 
@@ -69,6 +71,23 @@ workflow PIPELINE_INITIALISATION {
     UTILS_NFCORE_PIPELINE (
         nextflow_cli_args
     )
+
+    //
+    // Auto-detect input id type
+    //
+    ids = file(input)
+        .splitCsv(header:false, sep:'', strip:true)
+        .collect { row -> row[0] }
+        .toUnique()
+    if (!isSraId(ids)) {
+        error('Ids provided via --input not recognised please make sure they are either SRA / ENA / GEO / DDBJ ids!')
+    }
+    if (!sraCheckENAMetadataFields(ena_metadata_fields)) {
+        error("Invalid option: '${ena_metadata_fields}'. Minimally required fields for '--ena_metadata_fields': '${valid_ena_metadata_fields.join(',')}'")
+    }
+
+    emit:
+    ids
 }
 
 /*
@@ -118,39 +137,29 @@ workflow PIPELINE_COMPLETION {
 //
 // Check if input ids are from the SRA
 //
-def isSraId(input: Path) -> boolean {
-    def is_sra = false
+def isSraId(ids: List<String>) -> boolean {
     def total_ids = 0
     def no_match_ids = []
     def pattern = /^(((SR|ER|DR)[APRSX])|(SAM(N|EA|D))|(PRJ(NA|EB|DB))|(GS[EM]))(\d+)$/
-    input.eachLine { line ->
+    ids.each { id ->
         total_ids += 1
-        if (!(line =~ pattern)) {
-            no_match_ids << line
+        if (!(id =~ pattern)) {
+            no_match_ids << id
         }
     }
 
     def num_match = total_ids - no_match_ids.size()
-    if (num_match > 0) {
-        if (num_match == total_ids) {
-            is_sra = true
-        } else {
-            error("Mixture of ids provided via --input: ${no_match_ids.join(', ')}\nPlease provide either SRA / ENA / GEO / DDBJ ids!")
-        }
-    }
-    return is_sra
+    return num_match > 0 && num_match == total_ids
 }
 
 //
 // Check and validate parameters
 //
-def sraCheckENAMetadataFields(ena_metadata_fields) {
+def sraCheckENAMetadataFields(ena_metadata_fields: List<String>) -> boolean {
     // Check minimal ENA fields are provided to download FastQ files
     def valid_ena_metadata_fields = ['run_accession', 'experiment_accession', 'library_layout', 'fastq_ftp', 'fastq_md5']
     def actual_ena_metadata_fields = ena_metadata_fields ? ena_metadata_fields.split(',').collect{ it.trim().toLowerCase() } : valid_ena_metadata_fields
-    if (!actual_ena_metadata_fields.containsAll(valid_ena_metadata_fields)) {
-        error("Invalid option: '${ena_metadata_fields}'. Minimally required fields for '--ena_metadata_fields': '${valid_ena_metadata_fields.join(',')}'")
-    }
+    return actual_ena_metadata_fields.containsAll(valid_ena_metadata_fields)
 }
 
 //