Add cleanlines process.

workflow/configs/biohpc.config

@@ -22,6 +22,9 @@ process {
     withName:tolines {
         container = 'docker://git.biohpc.swmed.edu:5050/astrocyte/workflows/biohpc/astrocyte_example_wordcount/centos:centos8'
     }
+    withName:cleanlines {
+        container = 'docker://git.biohpc.swmed.edu:5050/astrocyte/workflows/biohpc/astrocyte_example_wordcount/centos:centos8'
+    }
     withName:wordcounts {
         container = 'docker://git.biohpc.swmed.edu:5050/astrocyte/workflows/biohpc/astrocyte_example_wordcount/centos:centos8'
     }

workflow/main.nf

@@ -83,13 +83,30 @@ process tolines {
 
 }
 
+process cleanlines {
+
+    cpus 1
+
+    input:
+    file rawlines from tolines
+
+    output:
+    file "${rawlines.name}.cleanlines" into cleanlines
+
+    // "awk NF": Print all non-empty lines.
+    """
+    cat "$rawlines" | awk NF > ${rawlines.name}.cleanlines
+    """
+
+}
+
 process wordcounts {
 
     // Publish the outputs we create here into the workflow output directory
     publishDir "$baseDir/output", mode: 'copy'
 
     input:
-    file wordlines from tolines
+    file wordlines from cleanlines
 
     output:
     file "${wordlines.name}.wordcount"