diff --git a/lib/Schema.groovy b/lib/Schema.groovy
index e241f0c5..33a4175b 100644
--- a/lib/Schema.groovy
+++ b/lib/Schema.groovy
@@ -2,9 +2,17 @@
* This file holds several functions used to perform JSON parameter validation, help and summary rendering for the nf-core pipeline template.
*/
+import org.everit.json.schema.Schema as JsonSchema
+import org.everit.json.schema.loader.SchemaLoader
+import org.everit.json.schema.ValidationException
+import org.json.JSONObject
+import org.json.JSONTokener
+import org.json.JSONArray
import groovy.json.JsonSlurper
+import groovy.json.JsonBuilder
class Schema {
+
/*
* This method tries to read a JSON params file
*/
@@ -84,24 +92,24 @@ class Schema {
* Beautify parameters for --help
*/
private static String params_help(workflow, params, json_schema, command) {
- String output = Headers.nf_core(workflow, params.monochrome_logs) + "\n"
- output += "Typical pipeline command:\n\n"
+ String output = Headers.nf_core(workflow, params.monochrome_logs) + '\n'
+ output += 'Typical pipeline command:\n\n'
output += " ${command}\n\n"
def params_map = params_load(json_schema)
def max_chars = params_max_chars(params_map) + 1
for (group in params_map.keySet()) {
- output += group + "\n"
+ output += group + '\n'
def group_params = params_map.get(group) // This gets the parameters of that particular group
for (param in group_params.keySet()) {
- def type = "[" + group_params.get(param).type + "]"
+ def type = '[' + group_params.get(param).type + ']'
def description = group_params.get(param).description
- output += " \u001B[1m--" + param.padRight(max_chars) + "\u001B[1m" + type.padRight(10) + description + "\n"
+ output += " \u001B[1m--" + param.padRight(max_chars) + "\u001B[1m" + type.padRight(10) + description + '\n'
}
- output += "\n"
+ output += '\n'
}
output += Headers.dashed_line(params.monochrome_logs)
- output += "\n\n" + Checks.citation(workflow)
- output += "\n\n" + Headers.dashed_line(params.monochrome_logs)
+ output += '\n\n' + Checks.citation(workflow)
+ output += '\n\n' + Headers.dashed_line(params.monochrome_logs)
return output
}
@@ -110,7 +118,7 @@ class Schema {
*/
private static LinkedHashMap params_summary_map(workflow, params, json_schema) {
// Get a selection of core Nextflow workflow options
- def Map workflow_summary = [:]
+ def Map workflow_summary = [:]
if (workflow.revision) {
workflow_summary['revision'] = workflow.revision
}
@@ -127,7 +135,7 @@ class Schema {
workflow_summary['userName'] = workflow.userName
workflow_summary['profile'] = workflow.profile
workflow_summary['configFiles'] = workflow.configFiles.join(', ')
-
+
// Get pipeline parameters defined in JSON Schema
def Map params_summary = [:]
def blacklist = ['hostnames']
@@ -153,15 +161,15 @@ class Schema {
} else {
if (param_type == 'string') {
if (schema_value.contains('$baseDir') || schema_value.contains('${baseDir}')) {
- def sub_string = schema_value.replace('\$baseDir','')
- sub_string = sub_string.replace('\${baseDir}','')
+ def sub_string = schema_value.replace('\$baseDir', '')
+ sub_string = sub_string.replace('\${baseDir}', '')
if (params_value.contains(sub_string)) {
schema_value = params_value
}
}
if (schema_value.contains('$params.outdir') || schema_value.contains('${params.outdir}')) {
- def sub_string = schema_value.replace('\$params.outdir','')
- sub_string = sub_string.replace('\${params.outdir}','')
+ def sub_string = schema_value.replace('\$params.outdir', '')
+ sub_string = sub_string.replace('\${params.outdir}', '')
if ("${params.outdir}${sub_string}" == params_value) {
schema_value = params_value
}
@@ -183,22 +191,22 @@ class Schema {
* Beautify parameters for summary and return as string
*/
private static String params_summary_log(workflow, params, json_schema) {
- String output = Headers.nf_core(workflow, params.monochrome_logs) + "\n"
+ String output = Headers.nf_core(workflow, params.monochrome_logs) + '\n'
def params_map = params_summary_map(workflow, params, json_schema)
def max_chars = params_max_chars(params_map)
for (group in params_map.keySet()) {
def group_params = params_map.get(group) // This gets the parameters of that particular group
if (group_params) {
- output += group + "\n"
+ output += group + '\n'
for (param in group_params.keySet()) {
- output += " \u001B[1m" + param.padRight(max_chars) + ": \u001B[1m" + group_params.get(param) + "\n"
+ output += " \u001B[1m" + param.padRight(max_chars) + ": \u001B[1m" + group_params.get(param) + '\n'
}
- output += "\n"
+ output += '\n'
}
}
output += Headers.dashed_line(params.monochrome_logs)
- output += "\n\n" + Checks.citation(workflow)
- output += "\n\n" + Headers.dashed_line(params.monochrome_logs)
+ output += '\n\n' + Checks.citation(workflow)
+ output += '\n\n' + Headers.dashed_line(params.monochrome_logs)
return output
}
@@ -212,17 +220,115 @@ class Schema {
for (param in group_params.keySet()) {
summary_section += " $param${group_params.get(param) ?: 'N/A'}\n"
}
- summary_section += " \n"
+ summary_section += ' \n'
}
}
- String yaml_file_text = "id: '${workflow.manifest.name.replace('/','-')}-summary'\n"
+ String yaml_file_text = "id: '${workflow.manifest.name.replace('/', '-')}-summary'\n"
yaml_file_text += "description: ' - this information is collected when the pipeline is started.'\n"
yaml_file_text += "section_name: '${workflow.manifest.name} Workflow Summary'\n"
yaml_file_text += "section_href: 'https://github.com/${workflow.manifest.name}'\n"
yaml_file_text += "plot_type: 'html'\n"
- yaml_file_text += "data: |\n"
+ yaml_file_text += 'data: |\n'
yaml_file_text += "${summary_section}"
return yaml_file_text
}
-}
\ No newline at end of file
+
+ /*
+ * Function to loop over all parameters defined in schema and check
+ * whether the given paremeters adhere to the specificiations
+ */
+ /* groovylint-disable-next-line UnusedPrivateMethodParameter */
+ private static ArrayList validateParameters(params, jsonSchema, log) {
+ //=====================================================================//
+ // Validate parameters against the schema
+ InputStream inputStream = new File(jsonSchema).newInputStream()
+ JSONObject rawSchema = new JSONObject(new JSONTokener(inputStream))
+ JsonSchema schema = SchemaLoader.load(rawSchema)
+
+ // Clean the parameters
+ def cleanedParams = cleanParameters(params)
+
+ // Convert to JSONObject
+ def jsonParams = new JsonBuilder(cleanedParams)
+ JSONObject paramsJSON = new JSONObject(jsonParams.toString())
+
+ // Validate
+ try {
+ schema.validate(paramsJSON)
+ } catch (ValidationException e) {
+ log.error 'Found parameter violations!'
+ JSONObject exceptionJSON = e.toJSON()
+ printExceptions(exceptionJSON, log)
+ System.exit(1)
+ }
+
+ // Check for nextflow core params and unexpected params
+ def json = new File(jsonSchema).text
+ def Map schemaParams = (Map) new JsonSlurper().parseText(json).get('definitions')
+ def specifiedParamKeys = params.keySet()
+ def nf_params = ['profile', 'config', 'c', 'C', 'syslog', 'd', 'dockerize',
+ 'bg', 'h', 'log', 'quiet', 'q', 'v', 'version']
+ def unexpectedParams = []
+
+ // Collect expected parameters from the schema
+ def expectedParams = []
+ for (group in schemaParams) {
+ for (p in group.value['properties']) {
+ expectedParams.push(p.key)
+ }
+ }
+
+ for (specifiedParam in specifiedParamKeys) {
+ // nextflow params
+ if (nf_params.contains(specifiedParam)) {
+ log.error "ERROR: You used a core Nextflow option with two hyphens: --${specifiedParam}! Please resubmit with one."
+ System.exit(1)
+ }
+ // unexpected params
+ if (!expectedParams.contains(specifiedParam)) {
+ unexpectedParams.push(specifiedParam)
+ }
+ }
+
+ return unexpectedParams
+ }
+
+ // Loop over nested exceptions and print the causingException
+ private static void printExceptions(exJSON, log) {
+ def causingExceptions = exJSON['causingExceptions']
+ if (causingExceptions.length() == 0) {
+ log.error "${exJSON['message']} ${exJSON['pointerToViolation']}"
+ }
+ else {
+ log.error exJSON['message']
+ for (ex in causingExceptions) {
+ printExceptions(ex, log)
+ }
+ }
+ }
+
+ private static Map cleanParameters(params) {
+ def new_params = params.getClass().newInstance(params)
+ for (p in params) {
+ // remove anything evaluating to false
+ if (!p['value']) {
+ new_params.remove(p.key)
+ }
+ // Cast MemoryUnit to String
+ if (p['value'].getClass() == nextflow.util.MemoryUnit) {
+ new_params.replace(p.key, p['value'].toString())
+ }
+ // Cast Duration to String
+ if (p['value'].getClass() == nextflow.util.Duration) {
+ new_params.replace(p.key, p['value'].toString())
+ }
+ // Cast LinkedHashMap to String
+ if (p['value'].getClass() == LinkedHashMap) {
+ new_params.replace(p.key, p['value'].toString())
+ }
+ }
+ return new_params
+ }
+
+}
diff --git a/lib/external_java_deps.jar b/lib/external_java_deps.jar
new file mode 100644
index 00000000..805c8bb5
Binary files /dev/null and b/lib/external_java_deps.jar differ
diff --git a/main.nf b/main.nf
index 951d528f..8b321a88 100644
--- a/main.nf
+++ b/main.nf
@@ -17,11 +17,18 @@ nextflow.enable.dsl = 2
def json_schema = "$baseDir/nextflow_schema.json"
if (params.help) {
- def command = "nextflow run nf-core/cageseq --input samplesheet.csv --genome GRCh38 -profile docker"
+ def command = 'nextflow run nf-core/cageseq --input samplesheet.csv --genome GRCh38 -profile docker'
log.info Schema.params_help(workflow, params, json_schema, command)
exit 0
}
+////////////////////////////////////////////////////
+/* -- VALIDATE PARAMETERS -- */
+////////////////////////////////////////////////////+
+def unexpectedParams = []
+if (params.validate_params) {
+ unexpectedParams = Schema.validateParameters(params, json_schema, log)
+}
////////////////////////////////////////////////////
/* -- PRINT PARAMETER SUMMARY -- */
////////////////////////////////////////////////////
@@ -39,7 +46,6 @@ Checks.aws_batch(workflow, params)
// Check the hostnames against configured profiles
Checks.hostname(workflow, params, log)
-
/////////////////////////////
/* -- RUN MAIN WORKFLOW -- */
/////////////////////////////
@@ -49,6 +55,13 @@ workflow {
CAGESEQ ()
}
+workflow.onError {
+ // Print unexpected parameters
+ for (p in unexpectedParams) {
+ log.warn "Unexpected parameter: ${p}"
+ }
+}
+
/////////////////////////////
/* -- THE END -- */
-/////////////////////////////
\ No newline at end of file
+/////////////////////////////
diff --git a/nextflow.config b/nextflow.config
index 03fea8b4..19301e97 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -10,10 +10,11 @@ params {
// Workflow flags
genome = false
- input = 'data/*R1.fastq.gz'
+ input = false
outdir = './results'
publish_dir_mode = 'copy'
-
+ validate_params = true
+
// CAGE-seq specific options
// Alignment options
aligner = 'star'
@@ -48,7 +49,7 @@ params {
ribo_database_manifest = "$baseDir/assets/rrna-db-defaults.txt"
//Output options
- bigwig=false
+ bigwig = false
//Clustering options
min_cluster = 30
diff --git a/nextflow_schema.json b/nextflow_schema.json
index f107552e..b7a3e6f8 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -1,5 +1,5 @@
{
- "$schema": "https://json-schema.org/draft-07/schema",
+ "$schema": "http://json-schema.org/draft-07/schema",
"$id": "https://raw.githubusercontent.com/nf-core/cageseq/master/nextflow_schema.json",
"title": "nf-core/cageseq pipeline parameters",
"description": "CAGE-seq pipeline",
@@ -307,6 +307,11 @@
"move"
]
},
+ "validate_params": {
+ "type": "boolean",
+ "description": "Boolean whether to validate parameters against the schema at runtime",
+ "default": true
+ },
"name": {
"type": "string",
"description": "Workflow name.",
@@ -334,6 +339,7 @@
"description": "File size limit when attaching MultiQC reports to summary emails.",
"default": "25.MB",
"fa_icon": "fas fa-file-upload",
+ "pattern": "\\d+\\.?\\s*[KMGT]?B?",
"hidden": true,
"help_text": "If file generated by pipeline exceeds the threshold, it will not be attached."
},
@@ -392,6 +398,7 @@
"description": "Maximum amount of memory that can be requested for any single job.",
"default": "128.GB",
"fa_icon": "fas fa-memory",
+ "pattern": "\\d+\\.?\\s*[GT]?B?",
"hidden": true,
"help_text": "Use to set an upper-limit for the memory requirement for each process. Should be a string in the format integer-unit e.g. `--max_memory '8.GB'`"
},
@@ -401,6 +408,7 @@
"default": "240.h",
"fa_icon": "far fa-clock",
"hidden": true,
+ "pattern": "\\d+\\.?\\s*[mhd]",
"help_text": "Use to set an upper-limit for the time requirement for each process. Should be a string in the format integer-unit e.g. `--max_time '2.h'`"
}
}