Update input_assure.py to include additional check for multiple keys

bin/input_assure.py

@@ -2,7 +2,6 @@
 
 import json
 import argparse
-import sys
 import csv
 import gzip
 
@@ -14,31 +13,48 @@ def open_file(file_path, mode):
         return open(file_path, mode)
 
 def check_inputs(json_file, sample_id, address, output_error_file):
-    # Define a variable to store the match_status (True or False)
-    with open(json_file, "rt") as f:
+    with open_file(json_file, "rt") as f:
         json_data = json.load(f)
-    match_status = sample_id in json_data
 
-    # Define the original key in the JSON data
-    original_key = list(json_data.keys())[0]
+    # Define a variable to store the match_status (True or False)
+    match_status = sample_id in json_data
+
+    keys = list (json_data.keys())
+    original_key = keys[0]
 
+    # Initialize the error message
+    error_message = None 
+
+    # Check for multiple keys in the JSON file and define error message
+    if len(keys) > 1:
+        # Check if sample_id matches any key
+        if not match_status:
+            error_message = f"No key in the MLST JSON file ({json_file}) matches the specified sample ID '{sample_id}'. The first key '{original_key}' has been forcefully changed to '{sample_id}' and all other keys have been removed."
+            # Retain only the specified sample ID 
+            json_data = {sample_id: json_data.pop(original_key)}
+        else:
+            error_message = f"MLST JSON file ({json_file}) contains multiple keys: {keys}. The MLST JSON file has been modified to retain only the '{sample_id}' entry"
+            # Remove all keys expect the one matching sample_id
+            json_data = {sample_id: json_data[sample_id]} 
+    elif not match_status:
     # Define error message based on meta.address (query or reference)
-    if address == "null":
-        error_message = f"Query {sample_id} ID and JSON key in {json_file} DO NOT MATCH. The '{original_key}' key in {json_file} has been forcefully changed to '{sample_id}': User should manually check input files to ensure correctness."
-    else:
-        error_message = f"Reference {sample_id} ID and JSON key in {json_file} DO NOT MATCH. The '{original_key}' key in {json_file} has been forcefully changed to '{sample_id}': User should manually check input files to ensure correctness."
-
-    # Write sample ID and JSON key to error report CSV if not matched; include error message
-    if not match_status:
+        if address == "null":
+            error_message = f"Query {sample_id} ID and JSON key in {json_file} DO NOT MATCH. The '{original_key}' key in {json_file} has been forcefully changed to '{sample_id}': User should manually check input files to ensure correctness."
+        else:
+            error_message = f"Reference {sample_id} ID and JSON key in {json_file} DO NOT MATCH. The '{original_key}' key in {json_file} has been forcefully changed to '{sample_id}': User should manually check input files to ensure correctness."
+        # Update the JSON file with the new sample ID
+        json_data[sample_id] = json_data.pop(original_key)
+
+    # Write file containing relevant error messages
+    if error_message:
         with open(output_error_file, "w", newline="") as f:
             writer = csv.writer(f)
             writer.writerow(["sample", "JSON_key", "error_message"])
-            writer.writerow([sample_id, original_key, error_message])
+            writer.writerow([sample_id, keys, error_message])
 
-    # Update the JSON file with the new sample ID
-        json_data[sample_id] = json_data.pop(original_key)
-        with open(json_file, "wt") as f:
-            json.dump(json_data, f, indent=4)
+    # Write the updated JSON data back to the original file 
+    with open_file(json_file, "wt") as f:
+        json.dump(json_data, f, indent=4)
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(

modules/local/input_assure/main.nf

@@ -1,5 +1,5 @@
 process INPUT_ASSURE {
-    tag "Check Sample Inputs and Generate Error Report"
+    tag "Assures Inputs are Consistent"
     label 'process_single'
 
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
@@ -10,14 +10,14 @@ process INPUT_ASSURE {
     tuple val(meta), path(mlst)
 
     output:
-    tuple val(meta), path(mlst),      emit: match
+    tuple val(meta), path(mlst),                                    emit: result
     tuple val(meta), path("*_error_report.csv"), optional: true,    emit: error_report
     path("versions.yml"),                                           emit: versions
 
     script:
 
     """
-    input_check.py \\
+    input_assure.py \\
         --input ${mlst} \\
         --sample_id ${meta.id} \\
         --address ${meta.address} \\

workflows/gas_nomenclature.nf

@@ -72,15 +72,15 @@ workflow GAS_NOMENCLATURE {
     input = Channel.fromSamplesheet("input")
 
     // Ensure meta.id and mlst_file keys match; generate error report for samples where id ≠ key
-    id_key = INPUT_ASSURE(input)
-    ch_versions = ch_versions.mix(id_key.versions)
+    input_assure = INPUT_ASSURE(input)
+    ch_versions = ch_versions.mix(input_assure.versions)
 
     // Prepare reference and query TSV files for LOCIDEX_MERGE
-    profiles = id_key.match.branch {
+    profiles = input_assure.result.branch {
         query: !it[0].address
     }
-    reference_values = input.collect{ meta, profile -> profile}
-    query_values = profiles.query.collect{ meta, profile -> profile }
+    reference_values = input_assure.result.collect{ meta, mlst -> mlst}
+    query_values = profiles.query.collect{ meta, mlst -> mlst }
 
     // LOCIDEX modules
     ref_tag = Channel.value("ref")