Merge pull request #632 from drpatelh/attributes

Strip out samplesheet validation for now

CHANGELOG.md

@@ -16,6 +16,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Enhancements & fixes
 
 * Updated pipeline template to nf-core/tools `1.14`
+* Initial implementation of a standardised samplesheet JSON schema to use with user interfaces and for validation
 * Only FastQ files that require to be concatenated will be passed to `CAT_FASTQ` process
 * [[#449](https://github.com/nf-core/modules/pull/449)] - `--genomeSAindexNbases` will now be auto-calculated before building STAR indices
 * [[#460](https://github.com/nf-core/rnaseq/issues/460)] - Auto-detect and bypass featureCounts execution if biotype doesn't exist in GTF
@@ -34,7 +35,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 * [[#604](https://github.com/nf-core/rnaseq/issues/604)] - Additional fasta with GENCODE annotation results in biotype error
 * [[#610](https://github.com/nf-core/rnaseq/issues/610)] - save R objects as RDS
 * [[#619](https://github.com/nf-core/rnaseq/issues/619)] - implicit declaration of the workflow in main
-* [[#629](https://github.com/nf-core/modules/pull/629)] - Add and fix EditorConfig linting in entire pipeline
+* [[#629](https://github.com/nf-core/rnaseq/pull/629)] - Add and fix EditorConfig linting in entire pipeline
 * [[nf-core/modules#423](https://github.com/nf-core/modules/pull/423)] - Replace `publish_by_id` module option to `publish_by_meta`
 * [[nextflow#2060](https://github.com/nextflow-io/nextflow/issues/2060)] - Pipeline execution hang when native task fail to be submitted
 

assets/schema_input.json

@@ -9,17 +9,20 @@
         "properties": {
             "sample": {
                 "type": "string",
-                "pattern": "^\\S+$"
+                "pattern": "^\\S+$",
+                "errorMessage": "Sample name must be provided and cannot contain spaces"
             },
             "fastq_1": {
                 "type": "string",
-                "pattern": "^\\S+\\.fa?s?t?q\\.gz$"
+                "pattern": "^\\S+\\.f(ast)?q\\.gz$",
+                "errorMessage": "FastQ file for reads 1 must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
             },
             "fastq_2": {
+                "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'",
                 "anyOf": [
                     {
                         "type": "string",
-                        "pattern": "^\\S+\\.fa?s?t?q\\.gz$"
+                        "pattern": "^\\S+\\.f(ast)?q\\.gz$"
                     },
                     {
                         "type": "string",
@@ -29,6 +32,7 @@
             },
             "strandedness": {
                 "type": "string",
+                "errorMessage": "Strandedness must be provided and be one of 'forward', 'reverse' or 'unstranded'",
                 "enum": [
                     "forward",
                     "reverse",

assets/schema_public_data_ids.json

@@ -8,7 +8,8 @@
         "type": "array",
         "items": {
             "type": "string",
-            "pattern": "^[SEPG][RAS][RXSMPAJXE][EN]?[AB]?\\d{5,9}$"
+            "pattern": "^[SEPG][RAS][RXSMPAJXE][EN]?[AB]?\\d{4,9}$",
+            "errorMessage": "Please provide a valid SRA, GEO or ENA identifier"
         }
     }
 }

lib/NfcoreSchema.groovy

@@ -177,37 +177,6 @@ class NfcoreSchema {
         }
     }
 
-    //
-    // Function to validate a file by its schema, eg. sample sheets
-    //
-    /* groovylint-disable-next-line UnusedPrivateMethodParameter */
-    public static void validateFile(workflow, log, params, param_name, obj, schema_filename) {
-        // Load the schema
-        InputStream inputStream = new File(getSchemaPath(workflow, schema_filename)).newInputStream()
-        JSONObject rawSchema = new JSONObject(new JSONTokener(inputStream))
-        Schema schema = SchemaLoader.load(rawSchema)
-
-        // Convert the groovy object to a JSONArray
-        def jsonObj = new JsonBuilder(obj)
-        JSONArray objJSON = new JSONArray(jsonObj.toString())
-
-        // Validate
-        try {
-            schema.validate(objJSON)
-        } catch (ValidationException e) {
-            Map colors = NfcoreTemplate.logColours(params.monochrome_logs)
-            println ""
-            println "=${colors.red}====   ERROR: Validation of '$param_name' file failed!   ============================="
-            JSONObject exceptionJSON = e.toJSON()
-            println e.getMessage()
-            e.getCausingExceptions().stream().map(ValidationException::getMessage).forEach(System.out::println)
-            println "===================================================================================${colors.reset}"
-            println ""
-            System.exit(1)
-        }
-        log.debug "Validation passed: '$param_name' with '$schema_filename'"
-    }
-
     //
     // Beautify parameters for --help
     //

workflows/rnaseq.nf

@@ -27,7 +27,6 @@ for (param in checkPathParamList) { if (param) { file(param, checkIfExists: true
 
 // Check mandatory parameters
 if (params.input) { ch_input = file(params.input) } else { exit 1, 'Input samplesheet not specified!' }
-NfcoreSchema.validateFile(workflow, log, params, '--input', file(params.input).splitCsv( header:true, sep:','), 'assets/schema_input.json')
 
 // Check rRNA databases for sortmerna
 ch_ribo_db = file(params.ribo_database_manifest)

workflows/sra_download.nf

@@ -14,7 +14,6 @@ if (params.public_data_ids) {
 } else {
     exit 1, 'Input file with public database ids not specified!'
 }
-NfcoreSchema.validateFile(workflow, log, params, '--public_data_ids', file(params.public_data_ids).splitCsv(header:false, sep:'', strip:true), 'assets/schema_public_data_ids.json')
 
 /*
 ========================================================================================