From 1419462906487a5d6e895586d8897898b67c31dc Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Mon, 23 Sep 2024 17:34:24 -0400
Subject: [PATCH] Revert "Remove necessity of meta.id_alt key"

This reverts commit 66a2b48afb3e3c82916be037e9d17c2d51321c9d.
---
 assets/schema_input.json           |  2 +-
 tests/workflows/snvphylnfc.nf.test |  4 ++--
 workflows/snvphylnfc.nf            | 30 +++++++++++++-----------------
 3 files changed, 16 insertions(+), 20 deletions(-)

diff --git a/assets/schema_input.json b/assets/schema_input.json
index 9e3f9e8..714cda3 100644
--- a/assets/schema_input.json
+++ b/assets/schema_input.json
@@ -16,7 +16,7 @@
             },
             "sample_name": {
                 "type": "string",
-                "meta": ["id"],
+                "meta": ["id", "id_alt"],
                 "errorMessage": "Sample name is optional, if provided will replace sample for filenames and outputs"
             },
             "fastq_1": {
diff --git a/tests/workflows/snvphylnfc.nf.test b/tests/workflows/snvphylnfc.nf.test
index fbb60f1..37e6006 100644
--- a/tests/workflows/snvphylnfc.nf.test
+++ b/tests/workflows/snvphylnfc.nf.test
@@ -75,11 +75,11 @@ nextflow_workflow {
     }
 
     test("selecting reference by sample id") {
-        tag "ref_sample_id"
+
         when {
             params {
                 input = "$baseDir/assets/samplesheet.csv"
-                reference_sample_id = "A 1#"
+                reference_sample_id = "A_1_"
                 outdir = "results"
             }
             workflow {}
diff --git a/workflows/snvphylnfc.nf b/workflows/snvphylnfc.nf
index 13e78bf..e704b64 100644
--- a/workflows/snvphylnfc.nf
+++ b/workflows/snvphylnfc.nf
@@ -95,20 +95,7 @@ workflow SNVPHYL {
         // or [meta, [fastq_1, fastq_2], reference_assembly] if fastq_2 exists
         // and remove non-alphanumeric characters in sample_names (meta.id), whilst also correcting for duplicate sample_names (meta.id)
         .map { meta, fastq_1, fastq_2, reference_assembly ->
-                fastq_2 ? tuple(meta, [ file(fastq_1), file(fastq_2) ], reference_assembly) :
-            tuple(meta, [ file(fastq_1) ], file(reference_assembly))}
-
-    // Channel of read tuples (meta, [fastq_1, fastq_2*]):
-    reads = input.map { meta, reads, reference_assembly -> tuple(meta, reads) }
-
-    // Channel of sample tuples (meta, assembly):
-    sample_assemblies = input.map { meta, reads, reference_assembly -> tuple(meta, reference_assembly ? reference_assembly : null) }
-
-    reference_genome = select_reference(params.refgenome, params.reference_sample_id, sample_assemblies)
-
-    // Ensure that, if 'meta.id' is supplied that follows it is appropriate for the pipeline
-    input = input.map { meta, reads, reference_assembly ->
-        if (!meta.id) {
+            if (!meta.id) {
                 meta.id = meta.irida_id
             } else {
                 // Non-alphanumeric characters (excluding _,-,.) will be replaced with "_"
@@ -121,8 +108,17 @@ workflow SNVPHYL {
             // Add the ID to the set of processed IDs
             processedIDs << meta.id
 
-            return [meta, reads, reference_assembly]
-    }
+            fastq_2 ? tuple(meta, [ file(fastq_1), file(fastq_2) ], reference_assembly) :
+            tuple(meta, [ file(fastq_1) ], file(reference_assembly))}
+
+
+    // Channel of read tuples (meta, [fastq_1, fastq_2*]):
+    reads = input.map { meta, reads, reference_assembly -> tuple(meta, reads) }
+
+    // Channel of sample tuples (meta, assembly):
+    sample_assemblies = input.map { meta, reads, reference_assembly -> tuple(meta, reference_assembly ? reference_assembly : null) }
+
+    reference_genome = select_reference(params.refgenome, params.reference_sample_id, sample_assemblies)
 
     INDEXING(
         reference_genome
@@ -266,7 +262,7 @@ def select_reference(refgenome, reference_sample_id, sample_assemblies) {
     }
     else if (reference_sample_id) {
         // Check each meta category (meta.id, meta.id_alt, meta.irida_id) for a match to params.reference_sample_id
-        reference_genome = sample_assemblies.filter { (it[0].id == reference_sample_id || it[0].irida_id == reference_sample_id) && it[1] != null}
+        reference_genome = sample_assemblies.filter { (it[0].id == reference_sample_id || it[0].irida_id == reference_sample_id || it[0].id_alt == reference_sample_id) && it[1] != null}
                                             .ifEmpty { error("The provided reference sample ID (${reference_sample_id}) is either missing or has no associated reference assembly.") }
                                             .map { it[1] }
                                             .first()