process_all_reads_tb_profiler.cwl

gistfile1.txt

#!/usr/bin/env cwl-runner
cwlVersion: v1.0
class: Workflow

requirements:
  InlineJavascriptRequirement: {}
  ScatterFeatureRequirement: {}
  StepInputExpressionRequirement: {}

inputs:
  reads_dir:
    type: Directory

outputs:
  json_results:
    type: File[]
    outputSource: 
      process_read_pairs/json_output_file
  text_results:
    type: File[]?
    outputSource:
      process_read_pairs/text_output_file
steps:
  make_read_pairs:
    in:
      reads_dir: reads_dir
    out:
      - read_pairs
    run:
      class: ExpressionTool
      inputs:
        reads_dir:
          type: Directory
      outputs:
        read_pairs:
          type: 
            type: array
            items:
              type: array
              items: File
      expression: |
        ${ 
          var read_pairs = Array();
          inputs.reads_dir.listing.forEach( function (entry) {
            if (entry.class == "File" && (entry.location.endsWith("_2.fastq.gz") || entry.location.endsWith("_2.fastq."))) {
              var read1 = Object.assign({}, entry); // shallow copy
              read1.location = entry.location.replace('_2.fastq', '_1.fastq');
              read1.basename = entry.basename.replace('_2.fastq', '_1.fastq');
              read_pairs.push(Array(read1, entry));
            }
          });
          console.log("pairs: " + read_pairs);
          return {"read_pairs": read_pairs};
        }
  process_read_pairs:
    in:
      sequences:
        source: make_read_pairs/read_pairs
        valueFrom: |
          ${
            var res =  {
              "read1": self[0], 
              "read2": self[1]
            };
            console.log(res);
            return res;
          }
      output_prefix:
        source: make_read_pairs/read_pairs
        valueFrom: |
          ${
            // get just the prefix of the sequence name
            return self[0].basename.replace(/_1.fastq.*$/, '');
          }
      text_output:
        default: true
    out:
      - json_output_file
      - text_output_file
    scatter: 
      - sequences
      - output_prefix
    scatterMethod: dotproduct
    run:
      tb-profiler-profile.cwl