Cleaning up, process_output.py outputs the input for now.

bin/process_output.py

@@ -43,14 +43,11 @@ def main(argv=None):
     input = Path(args.input)
     output = Path(args.output)
 
-    headers = ["query", "reference", "distance"]
-    results = [["A", "B", "1"], ["C", "D", "2"], ["E", "F", "3"]]
+    with open(output, "w") as output_file, \
+        open(input, "r") as input_file:
 
-    with open(output, "w") as output_file:
-        output_file.write((",").join(headers) + "\n")
-
-        for line in results:
-            output_file.write((",").join(line) + "\n")
+        for line in input_file:
+            output_file.write(line)
 
     print(f"Output written to [{output}]")
 

modules/local/append_metadata/main.nf

@@ -1,9 +1,9 @@
 process APPEND_METADATA {
-    tag "append_metadata"
+    tag "Appends metadata to distances"
     label 'process_single'
 
     input:
-    val distances_path       // cluster data as a TSV path
+    val distances_path      // distance data as a TSV path
                             // this needs to be "val", because "path"
                             // won't stage the file correctly for exec
     val metadata_rows       // metadata rows (no headers) to be appened, list of lists

modules/local/process_output/main.nf

@@ -9,7 +9,7 @@ process PROCESS_OUTPUT {
     path(distances)
 
     output:
-    path("results.csv"), emit: results
+    path("results.tsv"), emit: results
     path "versions.yml", emit: versions
 
     when:
@@ -21,7 +21,7 @@ process PROCESS_OUTPUT {
     process_output.py \\
         $args \\
         --input $distances \\
-        --output results.csv
+        --output results.tsv
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":