From b6f18f873324729a138e9a231a8101c560ef7a76 Mon Sep 17 00:00:00 2001
From: Daniel Lundin <erik.rikard.daniel@gmail.com>
Date: Mon, 19 Sep 2022 09:49:00 +0200
Subject: [PATCH] eslreformat: descriptive suffix (#2081)

---
 modules/hmmer/eslreformat/main.nf               |  7 ++++---
 modules/hmmer/eslreformat/meta.yml              |  2 +-
 tests/modules/hmmer/eslreformat/main.nf         | 15 +++++++++++++++
 tests/modules/hmmer/eslreformat/nextflow.config |  4 ++++
 tests/modules/hmmer/eslreformat/test.yml        | 16 ++++++++++++++--
 5 files changed, 38 insertions(+), 6 deletions(-)

diff --git a/modules/hmmer/eslreformat/main.nf b/modules/hmmer/eslreformat/main.nf
index e813e816..c7c20ffb 100644
--- a/modules/hmmer/eslreformat/main.nf
+++ b/modules/hmmer/eslreformat/main.nf
@@ -11,8 +11,8 @@ process HMMER_ESLREFORMAT {
     tuple val(meta), path(seqfile)
 
     output:
-    tuple val(meta), path("*.sequences.gz"), emit: seqreformated
-    path "versions.yml"                    , emit: versions
+    tuple val(meta), path("*.*.gz"), emit: seqreformated
+    path "versions.yml"            , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -20,6 +20,7 @@ process HMMER_ESLREFORMAT {
     script:
     def args     = task.ext.args ?: ''
     def prefix   = task.ext.prefix ?: "${meta.id}"
+    def suffix   = args ? args.trim().tokenize(" ")[-1] : "sequences"
     // Use for any postprocessing of the sequence file, e.g. removal of gap characters
     def postproc = task.ext.postprocessing ?: ""
     """
@@ -27,7 +28,7 @@ process HMMER_ESLREFORMAT {
         $args \\
         $seqfile \\
         $postproc \\
-        | gzip -c > ${prefix}.sequences.gz
+        | gzip -c > ${prefix}.${suffix}.gz
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
diff --git a/modules/hmmer/eslreformat/meta.yml b/modules/hmmer/eslreformat/meta.yml
index eb85a4d7..39cb7ab2 100644
--- a/modules/hmmer/eslreformat/meta.yml
+++ b/modules/hmmer/eslreformat/meta.yml
@@ -35,7 +35,7 @@ output:
   - seqreformated:
       type: file
       description: Reformated sequence file
-      pattern: "*.sequences.gz"
+      pattern: "*.*.gz"
 
 authors:
   - "@erikrikarddaniel"
diff --git a/tests/modules/hmmer/eslreformat/main.nf b/tests/modules/hmmer/eslreformat/main.nf
index 82cc0666..aa1d3d69 100644
--- a/tests/modules/hmmer/eslreformat/main.nf
+++ b/tests/modules/hmmer/eslreformat/main.nf
@@ -4,6 +4,7 @@ nextflow.enable.dsl = 2
 
 include { HMMER_HMMALIGN                                 } from '../../../../modules/hmmer/hmmalign/main.nf'
 include { HMMER_ESLREFORMAT as HMMER_ESLREFORMAT_AFA     } from '../../../../modules/hmmer/eslreformat/main.nf'
+include { HMMER_ESLREFORMAT as HMMER_ESLREFORMAT_PHYLIP  } from '../../../../modules/hmmer/eslreformat/main.nf'
 include { HMMER_ESLREFORMAT as HMMER_ESLREFORMAT_UNALIGN } from '../../../../modules/hmmer/eslreformat/main.nf'
 
 workflow test_hmmer_eslreformat_afa {
@@ -20,6 +21,20 @@ workflow test_hmmer_eslreformat_afa {
     HMMER_ESLREFORMAT_AFA ( HMMER_HMMALIGN.out.sthlm )
 }
 
+workflow test_hmmer_eslreformat_phylip {
+    
+    input = [
+        [ id:'test' ], // meta map
+        file('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/hmmer/e_coli_k12_16s.fna.gz')      // Change to params.test_data syntax after the data is included in tests/config/test_data.config
+    ]
+
+    hmm   = file('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/hmmer/bac.16S_rRNA.hmm.gz')
+
+    HMMER_HMMALIGN ( input, hmm )
+
+    HMMER_ESLREFORMAT_PHYLIP ( HMMER_HMMALIGN.out.sthlm )
+}
+
 workflow test_hmmer_eslreformat_unalign {
     
     input = [
diff --git a/tests/modules/hmmer/eslreformat/nextflow.config b/tests/modules/hmmer/eslreformat/nextflow.config
index be48a765..40a83917 100644
--- a/tests/modules/hmmer/eslreformat/nextflow.config
+++ b/tests/modules/hmmer/eslreformat/nextflow.config
@@ -6,6 +6,10 @@ process {
         ext.args   = 'afa'
     }
     
+    withName: HMMER_ESLREFORMAT_PHYLIP {
+        ext.args   = ' -u phylip '
+    }
+    
     withName: HMMER_ESLREFORMAT_UNALIGN {
         ext.args   = '--gapsym=- afa'
         ext.postprocessing = '| sed "/^>/!s/-//g"'
diff --git a/tests/modules/hmmer/eslreformat/test.yml b/tests/modules/hmmer/eslreformat/test.yml
index 0f98bae0..b625c5f2 100644
--- a/tests/modules/hmmer/eslreformat/test.yml
+++ b/tests/modules/hmmer/eslreformat/test.yml
@@ -4,20 +4,32 @@
     - hmmer/eslreformat
     - hmmer
   files:
-    - path: output/hmmer/test.sequences.gz
+    - path: output/hmmer/test.afa.gz
       contains:
         - ">CP025268.1"
         - "aaa---UUGAAGAGUUUGAUCAUGGCUCAGAUUGAACGCUGGCGGCAGGCCUAACACAUG"
     - path: output/hmmer/versions.yml
       contains:
         - "easel:"
+- name: hmmer eslreformat test_hmmer_eslreformat_phylip
+  command: nextflow run ./tests/modules/hmmer/eslreformat -entry test_hmmer_eslreformat_phylip -c ./tests/config/nextflow.config  -c ./tests/modules/hmmer/eslreformat/nextflow.config
+  tags:
+    - hmmer/eslreformat
+    - hmmer
+  files:
+    - path: output/hmmer/test.phylip.gz
+      contains:
+        - "CP025268.1 AAA---UUGAAGAGUUUGAUCAUGGCUCAGAUUGAACGCUGGCGGCAGGCCUAACACAUG"
+    - path: output/hmmer/versions.yml
+      contains:
+        - "easel:"
 - name: hmmer eslreformat test_hmmer_eslreformat_unalign
   command: nextflow run ./tests/modules/hmmer/eslreformat -entry test_hmmer_eslreformat_unalign -c ./tests/config/nextflow.config  -c ./tests/modules/hmmer/eslreformat/nextflow.config
   tags:
     - hmmer/eslreformat
     - hmmer
   files:
-    - path: output/hmmer/test.sequences.gz
+    - path: output/hmmer/test.afa.gz
       contains:
         - ">CP025268.1"
         - "aaaUUGAAGAGUUUGAUCAUGGCUCAGAUUGAACGCUGGCGGCAGGCCUAACACAUG"