From c51d8564f577875e083830801b6459eb958849b7 Mon Sep 17 00:00:00 2001
From: HNHalstead <47102761+HNHalstead@users.noreply.github.com>
Date: Tue, 13 Feb 2024 16:26:52 -0800
Subject: [PATCH] editing to include cluster name in output when provided

---
 tasks/utilities/task_utilities.wdl          | 10 +++++++++-
 workflows/phylogenetics/wf_RECAPP_waphl.wdl |  4 ++--
 2 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/tasks/utilities/task_utilities.wdl b/tasks/utilities/task_utilities.wdl
index 41390cb2e..2b95255cc 100644
--- a/tasks/utilities/task_utilities.wdl
+++ b/tasks/utilities/task_utilities.wdl
@@ -230,8 +230,9 @@ task split_by_declared_cluster {
     cluster_list = "~{sep=' ' declared_cluster}".split(" ")
     seqs = "~{sep=' ' samplename}".split(" ")
     out = "~{cluster_name}_output.txt"
+    clust_out = "~{cluster_name}_clusters.txt"
 
-
+    
     clust_dict = {}
     for i in range(len(seqs)):
         if not cluster_list[i]:
@@ -252,12 +253,19 @@ task split_by_declared_cluster {
             fp.write("\n")
         print('Done')
 
+    with open(clust_out, 'w') as fp:
+        for li in clust_dict.keys():
+            fp.write("%s\n" % item)
+            #fp.write("\n")
+        print('Done')
+
     CODE
   >>>
   output {
     String date = read_string("DATE")
     File clade_list_file = "~{cluster_name}_output.txt"
     Array[Array[String]] clade_list = read_tsv("~{cluster_name}_output.txt")
+    Array[Array[String]] unique_clusters = read_tsv("~{cluster_name}_clusters.txt")
     String split_cluster_docker_image = docker
   }
   runtime {
diff --git a/workflows/phylogenetics/wf_RECAPP_waphl.wdl b/workflows/phylogenetics/wf_RECAPP_waphl.wdl
index 579d305b0..2c6f8dd3f 100644
--- a/workflows/phylogenetics/wf_RECAPP_waphl.wdl
+++ b/workflows/phylogenetics/wf_RECAPP_waphl.wdl
@@ -94,13 +94,13 @@ if (defined(declared_cluster)) {
 }
 }
 
-scatter (pair in zip(select_first([split_by_declared_cluster.clade_list, split_by_clade.clade_list]), range(length(select_first([split_by_declared_cluster.clade_list, split_by_clade.clade_list]))))) {
+scatter (pair in zip(select_first([split_by_declared_cluster.clade_list, split_by_clade.clade_list]), select_first([split_by_declared_cluster.unique_clusters, range(length(split_by_clade.clade_list))]))) {
 if (length(select_all(pair.left)) >= 3){
 call utilities.scatter_by_clade as scatter_by_clade  {
   input:
     clade_list = pair.left,
     cluster_name = cluster_name,
-    assembly_files = assembly_gff
+    assembly_files = assembly_gff,
 }
 
 call clade_analysis.clade_analysis as clade_analysis  {