From d130a72d74899c3fd85db3c1c751b7b6848fd031 Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Fri, 8 Apr 2022 13:09:23 +0200
Subject: [PATCH] Get this working

---
 .github/workflows/ci.yml              |  1 +
 conf/modules.config                   |  6 +++---
 subworkflows/local/shortread_fastp.nf |  4 ++--
 workflows/taxprofiler.nf              | 18 ++++++++++++++++--
 4 files changed, 22 insertions(+), 7 deletions(-)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 7678645..53423cb 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -40,6 +40,7 @@ jobs:
           - "--shortread_complexityfilter_tool bbduk"
           - "--shortread_complexityfilter_tool prinseq"
           - "--run_merging"
+          - "--run_merging --shortread_clipmerge_mergepairs"
 
     steps:
       - name: Check out pipeline code
diff --git a/conf/modules.config b/conf/modules.config
index b59850f..7602e3f 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -163,7 +163,7 @@ process {
 
     withName: MALT_RUN {
         ext.args = { "${meta.db_params}" }
-        ext.prefix = { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
+        ext.prefix = if params.run_merging : { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
         publishDir = [
             path: { "${params.outdir}/malt/${meta.db_name}" },
             mode: params.publish_dir_mode,
@@ -173,7 +173,7 @@ process {
 
     withName: KRAKEN2_KRAKEN2 {
         ext.args = { "${meta.db_params}" }
-        ext.prefix = { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
+        ext.prefix = if params.run_merging : { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
         publishDir = [
             path: { "${params.outdir}/kraken2/${meta.db_name}" },
             mode: params.publish_dir_mode,
@@ -183,7 +183,7 @@ process {
 
     withName: METAPHLAN3 {
         publishDir = [
-            path: { "${params.outdir}/metaphlan3/${meta.db_name}" },
+        ext.prefix = if params.run_merging : { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
             mode: params.publish_dir_mode,
             pattern: '*.{biom,txt}'
         ]
diff --git a/subworkflows/local/shortread_fastp.nf b/subworkflows/local/shortread_fastp.nf
index 18baf17..04057b1 100644
--- a/subworkflows/local/shortread_fastp.nf
+++ b/subworkflows/local/shortread_fastp.nf
@@ -28,8 +28,8 @@ workflow SHORTREAD_FASTP {
                                         .map {
                                             meta, reads ->
                                                 def meta_new = meta.clone()
-                                                meta_new['single_end'] = 1
-                                                [ meta_new, reads ]
+                                                meta_new['single_end'] = true
+                                                [ meta_new, reads.flatten() ]
                                         }
 
         ch_fastp_reads_prepped = ch_fastp_reads_prepped_pe.mix( FASTP_SINGLE.out.reads )
diff --git a/workflows/taxprofiler.nf b/workflows/taxprofiler.nf
index 33d9725..e04d4d6 100644
--- a/workflows/taxprofiler.nf
+++ b/workflows/taxprofiler.nf
@@ -130,7 +130,8 @@ workflow TAXPROFILER {
     */
 
     if ( params.run_merging ) {
-        ch_reads_for_cat = ch_shortreads_filtered
+
+        ch_reads_for_cat_branch = ch_shortreads_filtered
             .mix( ch_longreads_preprocessed )
             .map {
                 meta, reads ->
@@ -139,8 +140,21 @@ workflow TAXPROFILER {
                     [ meta_new, reads ]
             }
             .groupTuple()
+            .map {
+                meta, reads ->
+                    [ meta, reads.flatten() ]
+            }
+            .branch {
+                // we can't concate files if there is not a second run, we branch
+                // here to separate them out, and mix after
+                cat: ( it[0]['single_end'] && it[1].size() > 1 ) || ( !it[0]['single_end'] && it[1].size() > 2 )
+                skip: true
+            }
+
+        ch_reads_for_cat_branch.cat.dump(tag: "for_catting")
+
+        ch_reads_runmerged = CAT_FASTQ ( ch_reads_for_cat_branch.cat ).reads.mix( ch_reads_for_cat_branch.skip )
 
-        ch_reads_runmerged = CAT_FASTQ ( ch_reads_for_cat ).reads
     } else {
         ch_reads_runmerged = ch_shortreads_filtered
             .mix( ch_longreads_preprocessed )