From c964c801368794d2091290ee33b249701dafc729 Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Wed, 6 Nov 2024 16:28:07 -0500
Subject: [PATCH 01/28] Add sample_name test is still not working locally

---
 assets/schema_input.json                      |  9 ++++++--
 conf/iridanext.config                         |  2 +-
 conf/modules.config                           |  7 +++++++
 modules/local/prefetchchecker/main.nf         | 14 ++++++++++---
 nextflow.config                               |  4 ++--
 tests/data/add-samplesheet.csv                |  5 +++++
 tests/data/samplesheet-addsamplename.csv      |  3 +++
 tests/modules/fasterqdump/main.nf.test        |  2 +-
 tests/modules/fasterqdump/main.nf.test.snap   | 10 ++++++---
 tests/pipelines/fetchdatairidanext.nf.test    | 21 +++++++++++++++++++
 .../main.nf.test                              | 12 +++++------
 .../main.nf.test.snap                         | 14 ++++++++-----
 workflows/fetchdatairidanext.nf               |  2 +-
 13 files changed, 81 insertions(+), 24 deletions(-)
 create mode 100644 tests/data/add-samplesheet.csv
 create mode 100644 tests/data/samplesheet-addsamplename.csv

diff --git a/assets/schema_input.json b/assets/schema_input.json
index edcf572..dc3b468 100644
--- a/assets/schema_input.json
+++ b/assets/schema_input.json
@@ -9,11 +9,16 @@
         "properties": {
             "sample": {
                 "type": "string",
-                "pattern": "^\\S+$",
-                "meta": ["id"],
+                "pattern": "^[A-Za-z0-9_.-]+$",
+                "meta": ["irida_id"],
                 "unique": true,
                 "errorMessage": "Sample name must be provided and cannot contain spaces"
             },
+            "sample_name": {
+                "type": "string",
+                "meta": ["id"],
+                "errorMessage": "Optional. Used to override sample when used in tools like IRIDA-Next"
+            },
             "insdc_accession": {
                 "type": "string",
                 "pattern": "^(SRR|ERR|DRR)\\S+$",
diff --git a/conf/iridanext.config b/conf/iridanext.config
index b336dfb..739532c 100644
--- a/conf/iridanext.config
+++ b/conf/iridanext.config
@@ -5,7 +5,7 @@ iridanext {
         overwrite = true
         validate = true
         files {
-            idkey = "id"
+            idkey = "irida_id"
             global = ["**/prefetch/failures_report.csv"]
             samples = ["**/reads/*.fastq.gz"]
         }
diff --git a/conf/modules.config b/conf/modules.config
index 7573f95..f68b79d 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -37,5 +37,12 @@ process {
             mode: params.publish_dir_mode,
             pattern: 'reads/*.fastq.gz'
         ]
+        def rename = {String sample_name, String accession -> "--outfile ${sample_name}_${accession}"}
+
+        ext.args = {
+            [
+                meta.id ? rename(meta.id, meta.insdc_accession) : ""
+            ].join(" ")
+        }
     }
 }
diff --git a/modules/local/prefetchchecker/main.nf b/modules/local/prefetchchecker/main.nf
index 4fe0a8d..852061a 100644
--- a/modules/local/prefetchchecker/main.nf
+++ b/modules/local/prefetchchecker/main.nf
@@ -11,11 +11,19 @@ process PREFETCH_CHECKER {
     exec:
     task.workDir.resolve("failures_report.csv").withWriter { writer ->
 
-        writer.writeLine("sample,error_accession")  // header
+        sample_name = false
+        failures.each { if ( it[0].id != null) {
+            sample_name = true
+        }
+        }
 
         // Failures
-        if (failures.size() > 0) {
-            failures.each { writer.writeLine "${it[0].id},${it[1]}" }
+        if (failures.size() > 0 && sample_name) {
+            writer.writeLine("sample,sample_name,error_accession")  // header
+            failures.each { writer.writeLine "${it[0].irida_id},${it[0].id},${it[1]}" }
+        } else {
+            writer.writeLine("sample,error_accession")  // header
+            failures.each { writer.writeLine "${it[0].irida_id},${it[1]}" }
         }
     }
 }
diff --git a/nextflow.config b/nextflow.config
index de1725a..85f9022 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -28,7 +28,7 @@ params {
     config_profile_description = null
     config_profile_contact     = null
     config_profile_url         = null
-    
+
 
     // Max resource options
     // Defaults only, expecting to be overwritten
@@ -78,7 +78,7 @@ profiles {
     }
     docker {
         docker.enabled         = true
-        docker.userEmulation   = true
+        docker.runOptions      = '-u $(id -u):$(id -g)'
         conda.enabled          = false
         singularity.enabled    = false
         podman.enabled         = false
diff --git a/tests/data/add-samplesheet.csv b/tests/data/add-samplesheet.csv
new file mode 100644
index 0000000..4512f0a
--- /dev/null
+++ b/tests/data/add-samplesheet.csv
@@ -0,0 +1,5 @@
+sample,sample_name,insdc_accession
+SAMPLE1,S1,ERR1109373
+ERROR1,S2,SRR999908
+ERROR2,S3,SRR999934
+SAMPLE2,S4,SRR13191702
diff --git a/tests/data/samplesheet-addsamplename.csv b/tests/data/samplesheet-addsamplename.csv
new file mode 100644
index 0000000..21ced63
--- /dev/null
+++ b/tests/data/samplesheet-addsamplename.csv
@@ -0,0 +1,3 @@
+sample,sample_name,insdc_accession
+SAMPLE1,S1,ERR1109373
+SAMPLE2,,SRR13191702
diff --git a/tests/modules/fasterqdump/main.nf.test b/tests/modules/fasterqdump/main.nf.test
index 104c31f..2ae17c3 100644
--- a/tests/modules/fasterqdump/main.nf.test
+++ b/tests/modules/fasterqdump/main.nf.test
@@ -11,7 +11,7 @@ nextflow_process {
         when {
             process {
                 """
-                input[0] = Channel.of([ [id: "SAMPLE1"], file("$baseDir/tests/data/ERR1109373.sra", checkIfExists: true) ])
+                input[0] = Channel.of([ [irida_id: "SAMPLE1"], file("$baseDir/tests/data/ERR1109373.sra", checkIfExists: true) ])
                 input[1] = []
                 input[2] = []
                 """
diff --git a/tests/modules/fasterqdump/main.nf.test.snap b/tests/modules/fasterqdump/main.nf.test.snap
index 6c6e406..0bea139 100644
--- a/tests/modules/fasterqdump/main.nf.test.snap
+++ b/tests/modules/fasterqdump/main.nf.test.snap
@@ -5,7 +5,7 @@
                 "0": [
                     [
                         {
-                            "id": "SAMPLE1"
+                            "irida_id": "SAMPLE1"
                         },
                         [
                             "ERR1109373.fastq.gz:md5,b9acccb3c5d317a99f604375a09991aa",
@@ -20,7 +20,7 @@
                 "reads": [
                     [
                         {
-                            "id": "SAMPLE1"
+                            "irida_id": "SAMPLE1"
                         },
                         [
                             "ERR1109373.fastq.gz:md5,b9acccb3c5d317a99f604375a09991aa",
@@ -34,6 +34,10 @@
                 ]
             }
         ],
-        "timestamp": "2024-01-25T23:20:38.2550152"
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-10-31T11:23:17.630455595"
     }
 }
\ No newline at end of file
diff --git a/tests/pipelines/fetchdatairidanext.nf.test b/tests/pipelines/fetchdatairidanext.nf.test
index 4f60f64..a1392ab 100644
--- a/tests/pipelines/fetchdatairidanext.nf.test
+++ b/tests/pipelines/fetchdatairidanext.nf.test
@@ -54,4 +54,25 @@ nextflow_pipeline {
             assert path("$launchDir/results/reads/SRR999934_2.fastq.gz").exists() == false
         }
     }
+
+    test("Include sample_name in samplesheet") {
+        tag "sample_name"
+        when {
+            params {
+                input = "$baseDir/tests/data/add-samplesheet.csv"
+                outdir = "output"
+            }
+        }
+
+        then {
+            assert workflow.success
+            assert path("$launchDir/output").exists()
+
+            def lines = path("$launchDir/output/prefetch/failures_report.csv").readLines()
+            assert lines.size() == 3
+            assert lines.contains("sample,sample_name,error_accession")
+            assert lines.contains("ERROR1,S2,SRR999908")
+            assert lines.contains("ERROR2,S3,INVALID!!")
+        }
+    }
 }
diff --git a/tests/workflows/fastq_download_prefetch_fasterqdump_sratools/main.nf.test b/tests/workflows/fastq_download_prefetch_fasterqdump_sratools/main.nf.test
index e4ee30f..1050501 100644
--- a/tests/workflows/fastq_download_prefetch_fasterqdump_sratools/main.nf.test
+++ b/tests/workflows/fastq_download_prefetch_fasterqdump_sratools/main.nf.test
@@ -16,8 +16,8 @@ nextflow_workflow {
             workflow {
                 """
                 input[0] = Channel.of(
-                    [[ id:'test_single_end', single_end:true  ], 'DRR000774'],
-                    [[ id:'test_paired_end', single_end:false ], 'SRR11140744']
+                    [[ irida_id:'test_single_end', single_end:true  ], 'DRR000774'],
+                    [[ irida_id:'test_paired_end', single_end:false ], 'SRR11140744']
                 )
                 input[1] = []
                 """
@@ -49,10 +49,10 @@ nextflow_workflow {
             workflow {
                 """
                 input[0] = Channel.of(
-                    [[ id:'SAMPLE1', single_end:false ], 'ERR1109373'],
-                    [[ id:'ERROR1', single_end:false ], 'SRR999908'],
-                    [[ id:'ERROR2', single_end:false ], 'INVALID!!'],
-                    [[ id:'SAMPLE2', single_end:false ], 'SRR13191702']
+                    [[ irida_id:'SAMPLE1', single_end:false ], 'ERR1109373'],
+                    [[ irida_id:'ERROR1', single_end:false ], 'SRR999908'],
+                    [[ irida_id:'ERROR2', single_end:false ], 'INVALID!!'],
+                    [[ irida_id:'SAMPLE2', single_end:false ], 'SRR13191702']
                 )
                 input[1] = []
                 """
diff --git a/tests/workflows/fastq_download_prefetch_fasterqdump_sratools/main.nf.test.snap b/tests/workflows/fastq_download_prefetch_fasterqdump_sratools/main.nf.test.snap
index 8c168d8..566f55d 100644
--- a/tests/workflows/fastq_download_prefetch_fasterqdump_sratools/main.nf.test.snap
+++ b/tests/workflows/fastq_download_prefetch_fasterqdump_sratools/main.nf.test.snap
@@ -5,7 +5,7 @@
                 "0": [
                     [
                         {
-                            "id": "test_paired_end",
+                            "irida_id": "test_paired_end",
                             "single_end": false
                         },
                         [
@@ -16,7 +16,7 @@
                     ],
                     [
                         {
-                            "id": "test_single_end",
+                            "irida_id": "test_single_end",
                             "single_end": true
                         },
                         "DRR000774.fastq.gz:md5,a110f93f7a9b0271455f5a435bce73c7"
@@ -30,7 +30,7 @@
                 "reads": [
                     [
                         {
-                            "id": "test_paired_end",
+                            "irida_id": "test_paired_end",
                             "single_end": false
                         },
                         [
@@ -41,7 +41,7 @@
                     ],
                     [
                         {
-                            "id": "test_single_end",
+                            "irida_id": "test_single_end",
                             "single_end": true
                         },
                         "DRR000774.fastq.gz:md5,a110f93f7a9b0271455f5a435bce73c7"
@@ -54,6 +54,10 @@
                 ]
             }
         ],
-        "timestamp": "2024-01-25T22:06:20.7303705"
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-11-05T15:53:20.740235848"
     }
 }
\ No newline at end of file
diff --git a/workflows/fetchdatairidanext.nf b/workflows/fetchdatairidanext.nf
index 74b5fcc..bb8a5f2 100644
--- a/workflows/fetchdatairidanext.nf
+++ b/workflows/fetchdatairidanext.nf
@@ -56,7 +56,7 @@ workflow FETCHDATAIRIDANEXT {
     // Create a new channel of metadata from a sample sheet
     // NB: `input` corresponds to `params.input` and associated sample sheet schema
     input = Channel.fromSamplesheet("input")
-    meta_accessions = input.map {meta -> tuple(["id": meta.id.first()], meta.insdc_accession.first())}
+    meta_accessions = input.map {meta -> tuple(["id": meta.id.first(), "irida_id": meta.irida_id.first(), "insdc_accession": meta.insdc_accession.first()], meta.insdc_accession.first())}
 
     FASTQ_DOWNLOAD_PREFETCH_FASTERQDUMP_SRATOOLS (
         ch_sra_ids = meta_accessions,

From 101bbe52bf31159dbee5a835e05ce5fc11f9eb51 Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Thu, 7 Nov 2024 14:37:07 -0500
Subject: [PATCH 02/28] Fixes isses with fasterq-dump

---
 modules/local/sratools/fasterqdump/main.nf | 4 ++--
 tests/pipelines/fetchdatairidanext.nf.test | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/modules/local/sratools/fasterqdump/main.nf b/modules/local/sratools/fasterqdump/main.nf
index 66ba956..b7b9bfe 100644
--- a/modules/local/sratools/fasterqdump/main.nf
+++ b/modules/local/sratools/fasterqdump/main.nf
@@ -4,8 +4,8 @@ process SRATOOLS_FASTERQDUMP {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/mulled-v2-5f89fe0cd045cb1d615630b9261a1d17943a9b6a:2f4a4c900edd6801ff0068c2b3048b4459d119eb-0' :
-        'biocontainers/mulled-v2-5f89fe0cd045cb1d615630b9261a1d17943a9b6a:2f4a4c900edd6801ff0068c2b3048b4459d119eb-0' }"
+        'https://depot.galaxyproject.org/singularity/mulled-v2-5f89fe0cd045cb1d615630b9261a1d17943a9b6a:6a9ff0e76ec016c3d0d27e0c0d362339f2d787e6-0' :
+        'quay.io/biocontainers/mulled-v2-5f89fe0cd045cb1d615630b9261a1d17943a9b6a:6a9ff0e76ec016c3d0d27e0c0d362339f2d787e6-0' }"
 
     input:
     tuple val(meta), path(sra)
diff --git a/tests/pipelines/fetchdatairidanext.nf.test b/tests/pipelines/fetchdatairidanext.nf.test
index a1392ab..0acd0f3 100644
--- a/tests/pipelines/fetchdatairidanext.nf.test
+++ b/tests/pipelines/fetchdatairidanext.nf.test
@@ -72,7 +72,7 @@ nextflow_pipeline {
             assert lines.size() == 3
             assert lines.contains("sample,sample_name,error_accession")
             assert lines.contains("ERROR1,S2,SRR999908")
-            assert lines.contains("ERROR2,S3,INVALID!!")
+            assert lines.contains("ERROR2,S3,SRR999934")
         }
     }
 }

From 5185a751c80d5e8eeb0148b06062e3e805b2745e Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Thu, 7 Nov 2024 14:42:56 -0500
Subject: [PATCH 03/28] Added another test, test read names with sample_names

---
 tests/pipelines/fetchdatairidanext.nf.test | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/tests/pipelines/fetchdatairidanext.nf.test b/tests/pipelines/fetchdatairidanext.nf.test
index 0acd0f3..b6779c1 100644
--- a/tests/pipelines/fetchdatairidanext.nf.test
+++ b/tests/pipelines/fetchdatairidanext.nf.test
@@ -67,12 +67,18 @@ nextflow_pipeline {
         then {
             assert workflow.success
             assert path("$launchDir/output").exists()
-
+            // Check that the failures report has a sample_name column when included in the samplesheet
             def lines = path("$launchDir/output/prefetch/failures_report.csv").readLines()
             assert lines.size() == 3
             assert lines.contains("sample,sample_name,error_accession")
             assert lines.contains("ERROR1,S2,SRR999908")
             assert lines.contains("ERROR2,S3,SRR999934")
+
+            // Check reads have been produced with modified names (i.e. suffixed with sample_name):
+            assert path("$launchDir/output/reads/S1_ERR1109373_1.fastq.gz").exists()
+            assert path("$launchDir/output/reads/S1_ERR1109373_2.fastq.gz").exists()
+            assert path("$launchDir/output/reads/S4_SRR13191702_1.fastq.gz").exists()
+            assert path("$launchDir/output/reads/S4_SRR13191702_2.fastq.gz").exists()
         }
     }
 }

From 46bb5fa170d1414c881e831730a868b5bf85b228 Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Thu, 7 Nov 2024 14:50:31 -0500
Subject: [PATCH 04/28] Fix nfcore lint issues

---
 .nf-core.yml                               |  3 +
 assets/schema_input.json                   |  2 +-
 nextflow_schema.json                       |  2 +-
 tests/pipelines/fetchdatairidanext.nf.test | 84 ----------------------
 4 files changed, 5 insertions(+), 86 deletions(-)
 delete mode 100644 tests/pipelines/fetchdatairidanext.nf.test

diff --git a/.nf-core.yml b/.nf-core.yml
index 1f79c1a..3d97354 100644
--- a/.nf-core.yml
+++ b/.nf-core.yml
@@ -34,5 +34,8 @@ lint:
     - custom_config
     - manifest.name
     - manifest.homePage
+    - params.max_cpus
+    - params.max_memory
+    - params.max_time
   readme:
     - nextflow_badge
diff --git a/assets/schema_input.json b/assets/schema_input.json
index dc3b468..f1060cf 100644
--- a/assets/schema_input.json
+++ b/assets/schema_input.json
@@ -1,5 +1,5 @@
 {
-    "$schema": "http://json-schema.org/draft-07/schema",
+    "$schema": "https://json-schema.org/draft-07/schema",
     "$id": "https://raw.githubusercontent.com/phac-nml/fetchdatairidanext/main/assets/schema_input.json",
     "title": "phac-nml/fetchdatairidanext pipeline - params.input schema",
     "description": "Schema for the file provided with params.input",
diff --git a/nextflow_schema.json b/nextflow_schema.json
index e7709da..a5f1c26 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -1,5 +1,5 @@
 {
-    "$schema": "http://json-schema.org/draft-07/schema",
+    "$schema": "https://json-schema.org/draft-07/schema",
     "$id": "https://raw.githubusercontent.com/phac-nml/fetchdatairidanext/main/nextflow_schema.json",
     "title": "phac-nml/fetchdatairidanext pipeline parameters",
     "description": "IRIDA Next NCBI Download pipeline",
diff --git a/tests/pipelines/fetchdatairidanext.nf.test b/tests/pipelines/fetchdatairidanext.nf.test
deleted file mode 100644
index b6779c1..0000000
--- a/tests/pipelines/fetchdatairidanext.nf.test
+++ /dev/null
@@ -1,84 +0,0 @@
-nextflow_pipeline {
-
-    name "Test fetching small datasets from NCBI"
-    script "main.nf"
-
-    test("basic integration test") {
-
-        when {
-            params {
-                input = "$baseDir/tests/data/samplesheet.csv"
-                outdir = "test1_out"
-            }
-        }
-
-        then {
-            assert workflow.success
-
-            // IRIDA Next output file
-            assert path("$launchDir/test1_out/iridanext.output.json").json == path("$baseDir/tests/data/test1_iridanext.output.json").json
-
-            // Output data
-            assert path("$launchDir/test1_out/reads/ERR1109373_1.fastq.gz").linesGzip.size() == 512
-            assert path("$launchDir/test1_out/reads/ERR1109373_2.fastq.gz").linesGzip.size() == 512
-            assert path("$launchDir/test1_out/reads/SRR13191702_1.fastq.gz").linesGzip.size() == 364
-            assert path("$launchDir/test1_out/reads/SRR13191702_2.fastq.gz").linesGzip.size() == 364
-        }
-    }
-
-    test("integration test with prefetch failures") {
-
-        when {
-            params {
-                input = "$baseDir/tests/data/errorsheet.csv"
-                outdir = "results"
-            }
-        }
-
-        then {
-            assert workflow.success
-
-            // IRIDA Next output file
-            assert path("$launchDir/results/iridanext.output.json").json == path("$baseDir/tests/data/prefetch_errors_iridanext.output.json").json
-
-            // Output data:
-            assert path("$launchDir/results/reads/ERR1109373_1.fastq.gz").linesGzip.size() == 512
-            assert path("$launchDir/results/reads/ERR1109373_2.fastq.gz").linesGzip.size() == 512
-            assert path("$launchDir/results/reads/SRR13191702_1.fastq.gz").linesGzip.size() == 364
-            assert path("$launchDir/results/reads/SRR13191702_2.fastq.gz").linesGzip.size() == 364
-
-            // These files should have failed, and have no output reads:
-            assert path("$launchDir/results/reads/SRR999908_1.fastq.gz").exists() == false
-            assert path("$launchDir/results/reads/SRR999908_2.fastq.gz").exists() == false
-            assert path("$launchDir/results/reads/SRR999934_1.fastq.gz").exists() == false
-            assert path("$launchDir/results/reads/SRR999934_2.fastq.gz").exists() == false
-        }
-    }
-
-    test("Include sample_name in samplesheet") {
-        tag "sample_name"
-        when {
-            params {
-                input = "$baseDir/tests/data/add-samplesheet.csv"
-                outdir = "output"
-            }
-        }
-
-        then {
-            assert workflow.success
-            assert path("$launchDir/output").exists()
-            // Check that the failures report has a sample_name column when included in the samplesheet
-            def lines = path("$launchDir/output/prefetch/failures_report.csv").readLines()
-            assert lines.size() == 3
-            assert lines.contains("sample,sample_name,error_accession")
-            assert lines.contains("ERROR1,S2,SRR999908")
-            assert lines.contains("ERROR2,S3,SRR999934")
-
-            // Check reads have been produced with modified names (i.e. suffixed with sample_name):
-            assert path("$launchDir/output/reads/S1_ERR1109373_1.fastq.gz").exists()
-            assert path("$launchDir/output/reads/S1_ERR1109373_2.fastq.gz").exists()
-            assert path("$launchDir/output/reads/S4_SRR13191702_1.fastq.gz").exists()
-            assert path("$launchDir/output/reads/S4_SRR13191702_2.fastq.gz").exists()
-        }
-    }
-}

From 0849cc7d47576940daa8aa7e85231cbeb5c1e4ce Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Thu, 7 Nov 2024 15:10:13 -0500
Subject: [PATCH 05/28] Modified linting with editorconfig-checker

---
 .github/workflows/linting.yml | 13 -------------
 .pre-commit-config.yaml       |  5 +++++
 2 files changed, 5 insertions(+), 13 deletions(-)

diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml
index 544a5a8..6d0938e 100644
--- a/.github/workflows/linting.yml
+++ b/.github/workflows/linting.yml
@@ -11,19 +11,6 @@ on:
     types: [published]
 
 jobs:
-  EditorConfig:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-
-      - uses: actions/setup-node@v3
-
-      - name: Install editorconfig-checker
-        run: npm install -g editorconfig-checker
-
-      - name: Run ECLint check
-        run: editorconfig-checker -exclude README.md $(find .* -type f | grep -v '.git\|.py\|.md\|json\|yml\|yaml\|html\|css\|work\|.nextflow\|build\|nf_core.egg-info\|log.txt\|Makefile\|.sra')
-
   Prettier:
     runs-on: ubuntu-latest
     steps:
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index 0c31cdb..98a90d1 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -3,3 +3,8 @@ repos:
     rev: "v2.7.1"
     hooks:
       - id: prettier
+  - repo: https://github.com/editorconfig-checker/editorconfig-checker.python
+    rev: "2.7.3"
+    hooks:
+      - id: editorconfig-checker
+        alias: ec

From 28fa88f8043dd1776a04d87cc011d9bb2a99fe19 Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Thu, 7 Nov 2024 15:12:51 -0500
Subject: [PATCH 06/28] Fix lint comment yml

---
 .github/workflows/linting_comment.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/linting_comment.yml b/.github/workflows/linting_comment.yml
index b706875..42e519b 100644
--- a/.github/workflows/linting_comment.yml
+++ b/.github/workflows/linting_comment.yml
@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Download lint results
-        uses: dawidd6/action-download-artifact@f6b0bace624032e30a85a8fd9c1a7f8f611f5737 # v3
+        uses: dawidd6/action-download-artifact@bf251b5aa9c2f7eeb574a96ee720e24f801b7c11 # v6
         with:
           workflow: linting.yml
           workflow_conclusion: completed

From f025b1b4065d9b860ff4dcb37993ce7129fb3bbe Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Mon, 11 Nov 2024 21:01:16 -0500
Subject: [PATCH 07/28] Providing a NCBI user setting file for tests

---
 modules.json                                           |  7 ++++++-
 modules/local/sratools/fasterqdump/environment.yml     |  2 +-
 tests/data/ncbi_user_settings.mkfg                     |  2 ++
 tests/modules/fasterqdump/main.nf.test                 |  2 +-
 tests/modules/fasterqdump/main.nf.test.snap            |  6 +++---
 .../main.nf.test.snap                                  | 10 +++++-----
 6 files changed, 18 insertions(+), 11 deletions(-)
 create mode 100644 tests/data/ncbi_user_settings.mkfg

diff --git a/modules.json b/modules.json
index 6250d22..cb385c1 100644
--- a/modules.json
+++ b/modules.json
@@ -15,9 +15,14 @@
                         "git_sha": "e719354ba77df0a1bd310836aa2039b45c29d620",
                         "installed_by": ["modules"]
                     },
+                    "sratools/fasterqdump": {
+                        "branch": "master",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "installed_by": ["modules"]
+                    },
                     "sratools/prefetch": {
                         "branch": "master",
-                        "git_sha": "e719354ba77df0a1bd310836aa2039b45c29d620",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
                         "installed_by": ["modules"]
                     }
                 }
diff --git a/modules/local/sratools/fasterqdump/environment.yml b/modules/local/sratools/fasterqdump/environment.yml
index 4011b69..dd0faa5 100644
--- a/modules/local/sratools/fasterqdump/environment.yml
+++ b/modules/local/sratools/fasterqdump/environment.yml
@@ -4,5 +4,5 @@ channels:
   - bioconda
   - defaults
 dependencies:
-  - bioconda::sra-tools=3.0.8
+  - bioconda::sra-tools=2.11.0
   - conda-forge::pigz=2.6
diff --git a/tests/data/ncbi_user_settings.mkfg b/tests/data/ncbi_user_settings.mkfg
new file mode 100644
index 0000000..3c8df9f
--- /dev/null
+++ b/tests/data/ncbi_user_settings.mkfg
@@ -0,0 +1,2 @@
+/LIBS/GUID = "5b0d4b7d-88c7-4802-98fd-e3afd06feb32"
+/libs/cloud/report_instance_identity = "true"
diff --git a/tests/modules/fasterqdump/main.nf.test b/tests/modules/fasterqdump/main.nf.test
index 2ae17c3..52f3d11 100644
--- a/tests/modules/fasterqdump/main.nf.test
+++ b/tests/modules/fasterqdump/main.nf.test
@@ -12,7 +12,7 @@ nextflow_process {
             process {
                 """
                 input[0] = Channel.of([ [irida_id: "SAMPLE1"], file("$baseDir/tests/data/ERR1109373.sra", checkIfExists: true) ])
-                input[1] = []
+                input[1] = file('$baseDir/tests/data/ncbi_user_settings.mkfg', checkIfExists: true)
                 input[2] = []
                 """
             }
diff --git a/tests/modules/fasterqdump/main.nf.test.snap b/tests/modules/fasterqdump/main.nf.test.snap
index 0bea139..8399ab9 100644
--- a/tests/modules/fasterqdump/main.nf.test.snap
+++ b/tests/modules/fasterqdump/main.nf.test.snap
@@ -15,7 +15,7 @@
                     ]
                 ],
                 "1": [
-                    "versions.yml:md5,a3d61a9761e1606ef8459f0b68821d7a"
+                    "versions.yml:md5,6ff2d50b15c3f0eb9c72cd13a4a20295"
                 ],
                 "reads": [
                     [
@@ -30,7 +30,7 @@
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,a3d61a9761e1606ef8459f0b68821d7a"
+                    "versions.yml:md5,6ff2d50b15c3f0eb9c72cd13a4a20295"
                 ]
             }
         ],
@@ -38,6 +38,6 @@
             "nf-test": "0.9.0",
             "nextflow": "24.04.4"
         },
-        "timestamp": "2024-10-31T11:23:17.630455595"
+        "timestamp": "2024-11-11T20:36:55.563890217"
     }
 }
\ No newline at end of file
diff --git a/tests/workflows/fastq_download_prefetch_fasterqdump_sratools/main.nf.test.snap b/tests/workflows/fastq_download_prefetch_fasterqdump_sratools/main.nf.test.snap
index 566f55d..d51d6dd 100644
--- a/tests/workflows/fastq_download_prefetch_fasterqdump_sratools/main.nf.test.snap
+++ b/tests/workflows/fastq_download_prefetch_fasterqdump_sratools/main.nf.test.snap
@@ -24,8 +24,8 @@
                 ],
                 "1": [
                     "versions.yml:md5,1a2218ff913fc33408bffccb081b5048",
-                    "versions.yml:md5,98d78bba9f3da39a0b7db6e9c7dcc224",
-                    "versions.yml:md5,9c558ff624585a6eee82a19c8c0136db"
+                    "versions.yml:md5,2f3b3a13b36dabf13f09327613d5558d",
+                    "versions.yml:md5,53d6e983afde3a28add2ffc6b7eba4f3"
                 ],
                 "reads": [
                     [
@@ -49,8 +49,8 @@
                 ],
                 "versions": [
                     "versions.yml:md5,1a2218ff913fc33408bffccb081b5048",
-                    "versions.yml:md5,98d78bba9f3da39a0b7db6e9c7dcc224",
-                    "versions.yml:md5,9c558ff624585a6eee82a19c8c0136db"
+                    "versions.yml:md5,2f3b3a13b36dabf13f09327613d5558d",
+                    "versions.yml:md5,53d6e983afde3a28add2ffc6b7eba4f3"
                 ]
             }
         ],
@@ -58,6 +58,6 @@
             "nf-test": "0.9.0",
             "nextflow": "24.04.4"
         },
-        "timestamp": "2024-11-05T15:53:20.740235848"
+        "timestamp": "2024-11-11T20:52:02.578591475"
     }
 }
\ No newline at end of file

From 201d5e4705de0a2fca19a87a925aac80ad0e99ab Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Mon, 11 Nov 2024 21:01:27 -0500
Subject: [PATCH 08/28] Providing a NCBI user setting file for tests

---
 .../nf-core/sratools/prefetch/environment.yml |  7 --
 modules/nf-core/sratools/prefetch/main.nf     | 35 ---------
 modules/nf-core/sratools/prefetch/meta.yml    | 56 ---------------
 .../prefetch/templates/retry_with_backoff.sh  | 55 --------------
 .../sratools/prefetch/tests/main.nf.test      | 55 --------------
 .../sratools/prefetch/tests/main.nf.test.snap | 72 -------------------
 .../nf-core/sratools/prefetch/tests/tags.yml  |  2 -
 7 files changed, 282 deletions(-)
 delete mode 100644 modules/nf-core/sratools/prefetch/environment.yml
 delete mode 100644 modules/nf-core/sratools/prefetch/main.nf
 delete mode 100644 modules/nf-core/sratools/prefetch/meta.yml
 delete mode 100755 modules/nf-core/sratools/prefetch/templates/retry_with_backoff.sh
 delete mode 100644 modules/nf-core/sratools/prefetch/tests/main.nf.test
 delete mode 100644 modules/nf-core/sratools/prefetch/tests/main.nf.test.snap
 delete mode 100644 modules/nf-core/sratools/prefetch/tests/tags.yml

diff --git a/modules/nf-core/sratools/prefetch/environment.yml b/modules/nf-core/sratools/prefetch/environment.yml
deleted file mode 100644
index cfc7d9a..0000000
--- a/modules/nf-core/sratools/prefetch/environment.yml
+++ /dev/null
@@ -1,7 +0,0 @@
-name: sratools_prefetch
-channels:
-  - conda-forge
-  - bioconda
-  - defaults
-dependencies:
-  - bioconda::sra-tools=3.0.8
diff --git a/modules/nf-core/sratools/prefetch/main.nf b/modules/nf-core/sratools/prefetch/main.nf
deleted file mode 100644
index 3c30739..0000000
--- a/modules/nf-core/sratools/prefetch/main.nf
+++ /dev/null
@@ -1,35 +0,0 @@
-process SRATOOLS_PREFETCH {
-    tag "$id"
-    label 'process_low'
-
-    conda "${moduleDir}/environment.yml"
-    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/sra-tools:3.0.8--h9f5acd7_0' :
-        'biocontainers/sra-tools:3.0.8--h9f5acd7_0' }"
-
-    input:
-    tuple val(meta), val(id)
-    path ncbi_settings
-    path certificate
-
-    output:
-    tuple val(meta), path(id), emit: sra
-    path 'versions.yml'      , emit: versions
-
-    when:
-    task.ext.when == null || task.ext.when
-
-    shell:
-    args = task.ext.args ?: ''
-    args2 = task.ext.args2 ?: '5 1 100'  // <num retries> <base delay in seconds> <max delay in seconds>
-    if (certificate) {
-        if (certificate.toString().endsWith('.jwt')) {
-            args += " --perm ${certificate}"
-        }
-        else if (certificate.toString().endsWith('.ngc')) {
-            args += " --ngc ${certificate}"
-        }
-    }
-
-    template 'retry_with_backoff.sh'
-}
diff --git a/modules/nf-core/sratools/prefetch/meta.yml b/modules/nf-core/sratools/prefetch/meta.yml
deleted file mode 100644
index ff54229..0000000
--- a/modules/nf-core/sratools/prefetch/meta.yml
+++ /dev/null
@@ -1,56 +0,0 @@
-name: sratools_prefetch
-description: Download sequencing data from the NCBI Sequence Read Archive (SRA).
-keywords:
-  - sequencing
-  - fastq
-  - prefetch
-tools:
-  - sratools:
-      description: SRA Toolkit and SDK from NCBI
-      homepage: https://github.com/ncbi/sra-tools
-      documentation: https://github.com/ncbi/sra-tools/wiki
-      tool_dev_url: https://github.com/ncbi/sra-tools
-      licence: ["Public Domain"]
-input:
-  - meta:
-      type: map
-      description: >
-        Groovy Map containing sample information e.g. [ id:'test', single_end:false ]
-
-  - id:
-      type: string
-      description: >
-        A string denoting an SRA id.
-
-  - ncbi_settings:
-      type: file
-      description: >
-        An NCBI user settings file.
-
-      pattern: "*.mkfg"
-  - certificate:
-      type: file
-      description: >
-        Path to a JWT cart file used to access protected dbGAP data on SRA using the sra-toolkit
-
-      pattern: "*.cart"
-output:
-  - meta:
-      type: map
-      description: >
-        Groovy Map containing sample information e.g. [ id:'test', single_end:false ]
-
-  - sra:
-      type: directory
-      description: >
-        Directory containing the ETL data for the given SRA id.
-
-      pattern: "*/*.sra"
-  - versions:
-      type: file
-      description: File containing software versions
-      pattern: "versions.yml"
-authors:
-  - "@Midnighter"
-maintainers:
-  - "@Midnighter"
diff --git a/modules/nf-core/sratools/prefetch/templates/retry_with_backoff.sh b/modules/nf-core/sratools/prefetch/templates/retry_with_backoff.sh
deleted file mode 100755
index a72a4bf..0000000
--- a/modules/nf-core/sratools/prefetch/templates/retry_with_backoff.sh
+++ /dev/null
@@ -1,55 +0,0 @@
-#!/usr/bin/env bash
-
-set -u
-
-retry_with_backoff() {
-    local max_attempts=${1}
-    local delay=${2}
-    local max_time=${3}
-    local attempt=1
-    local output=
-    local status=
-
-    # Remove the first three arguments to this function in order to access
-    # the 'real' command with `${@}`.
-    shift 3
-
-    while [ ${attempt} -le ${max_attempts} ]; do
-        output=$("${@}")
-        status=${?}
-
-        if [ ${status} -eq 0 ]; then
-            break
-        fi
-
-        if [ ${attempt} -lt ${max_attempts} ]; then
-            echo "Failed attempt ${attempt} of ${max_attempts}. Retrying in ${delay} s." >&2
-            sleep ${delay}
-        elif [ ${attempt} -eq ${max_attempts} ]; then
-            echo "Failed after ${attempt} attempts." >&2
-            return ${status}
-        fi
-
-        attempt=$(( ${attempt} + 1 ))
-        delay=$(( ${delay} * 2 ))
-        if [ ${delay} -ge ${max_time} ]; then
-            delay=${max_time}
-        fi
-    done
-
-    echo "${output}"
-}
-
-export NCBI_SETTINGS="$PWD/!{ncbi_settings}"
-
-retry_with_backoff !{args2} \
-    prefetch \
-    !{args} \
-    !{id}
-
-[ -f !{id}.sralite ] && vdb-validate !{id}.sralite || vdb-validate !{id}
-
-cat <<-END_VERSIONS > versions.yml
-"!{task.process}":
-    sratools: $(prefetch --version 2>&1 | grep -Eo '[0-9.]+')
-END_VERSIONS
diff --git a/modules/nf-core/sratools/prefetch/tests/main.nf.test b/modules/nf-core/sratools/prefetch/tests/main.nf.test
deleted file mode 100644
index ed710ba..0000000
--- a/modules/nf-core/sratools/prefetch/tests/main.nf.test
+++ /dev/null
@@ -1,55 +0,0 @@
-nextflow_process {
-    name "Test Process SRATOOLS_PREFETCH"
-    script "../main.nf"
-    process "SRATOOLS_PREFETCH"
-    tag "modules"
-    tag "modules_nfcore"
-    tag "sratools"
-    tag "sratools/prefetch"
-
-    test("sratools/prefetch") {
-
-        when {
-            params {
-                outdir = "output"
-            }
-            process {
-                """
-                input[0] = Channel.of([ [ id:'test', single_end:false ], 'DRR000774' ])
-                input[1] = file(params.modules_testdata_base_path + 'generic/config/ncbi_user_settings.mkfg', checkIfExists: true)
-                input[2] = []
-                """
-            }
-        }
-
-        then {
-            assertAll (
-            { assert process.success },
-            { assert snapshot(process.out).match() }
-            )
-        }
-    }
-
-    test("sratools/prefetch with sralite") {
-
-        when {
-            params {
-                outdir = "output"
-            }
-            process {
-                """
-                input[0] = Channel.of([ [ id:'test', single_end:false ], 'SRR1170046' ])
-                input[1] = file(params.modules_testdata_base_path + 'generic/config/ncbi_user_settings.mkfg', checkIfExists: true)
-                input[2] = []
-                """
-            }
-        }
-
-        then {
-            assertAll (
-            { assert process.success },
-            { assert snapshot(process.out).match() }
-            )
-        }
-    }
-}
diff --git a/modules/nf-core/sratools/prefetch/tests/main.nf.test.snap b/modules/nf-core/sratools/prefetch/tests/main.nf.test.snap
deleted file mode 100644
index ab1d208..0000000
--- a/modules/nf-core/sratools/prefetch/tests/main.nf.test.snap
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-    "sratools/prefetch with sralite": {
-        "content": [
-            {
-                "0": [
-                    [
-                        {
-                            "id": "test",
-                            "single_end": false
-                        },
-                        [
-                            "SRR1170046.sralite:md5,7acfce556ca0951aff49d780899c105b"
-                        ]
-                    ]
-                ],
-                "1": [
-                    "versions.yml:md5,c967dea4135cb75490e1e801c4639efc"
-                ],
-                "sra": [
-                    [
-                        {
-                            "id": "test",
-                            "single_end": false
-                        },
-                        [
-                            "SRR1170046.sralite:md5,7acfce556ca0951aff49d780899c105b"
-                        ]
-                    ]
-                ],
-                "versions": [
-                    "versions.yml:md5,c967dea4135cb75490e1e801c4639efc"
-                ]
-            }
-        ],
-        "timestamp": "2023-10-13T12:11:24.563510389"
-    },
-    "sratools/prefetch": {
-        "content": [
-            {
-                "0": [
-                    [
-                        {
-                            "id": "test",
-                            "single_end": false
-                        },
-                        [
-                            "DRR000774.sra:md5,7647dba20c89c0e3d7ad13842f060eb0"
-                        ]
-                    ]
-                ],
-                "1": [
-                    "versions.yml:md5,c967dea4135cb75490e1e801c4639efc"
-                ],
-                "sra": [
-                    [
-                        {
-                            "id": "test",
-                            "single_end": false
-                        },
-                        [
-                            "DRR000774.sra:md5,7647dba20c89c0e3d7ad13842f060eb0"
-                        ]
-                    ]
-                ],
-                "versions": [
-                    "versions.yml:md5,c967dea4135cb75490e1e801c4639efc"
-                ]
-            }
-        ],
-        "timestamp": "2023-10-13T12:11:02.75256571"
-    }
-}
\ No newline at end of file
diff --git a/modules/nf-core/sratools/prefetch/tests/tags.yml b/modules/nf-core/sratools/prefetch/tests/tags.yml
deleted file mode 100644
index 52110bf..0000000
--- a/modules/nf-core/sratools/prefetch/tests/tags.yml
+++ /dev/null
@@ -1,2 +0,0 @@
-sratools/prefetch:
-  - modules/nf-core/sratools/prefetch/**

From b55683d2cff2f5785368965b8c8d9d1ebcf0b8a2 Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Mon, 11 Nov 2024 21:06:17 -0500
Subject: [PATCH 09/28] Somewhere along the way prefetch got deleted

---
 .../nf-core/sratools/prefetch/environment.yml |   6 +
 modules/nf-core/sratools/prefetch/main.nf     |  47 +++++++
 modules/nf-core/sratools/prefetch/meta.yml    |  59 +++++++++
 .../prefetch/templates/retry_with_backoff.sh  |  65 ++++++++++
 .../sratools/prefetch/tests/main.nf.test      |  71 +++++++++++
 .../sratools/prefetch/tests/main.nf.test.snap | 119 ++++++++++++++++++
 .../nf-core/sratools/prefetch/tests/tags.yml  |   2 +
 7 files changed, 369 insertions(+)
 create mode 100644 modules/nf-core/sratools/prefetch/environment.yml
 create mode 100644 modules/nf-core/sratools/prefetch/main.nf
 create mode 100644 modules/nf-core/sratools/prefetch/meta.yml
 create mode 100755 modules/nf-core/sratools/prefetch/templates/retry_with_backoff.sh
 create mode 100644 modules/nf-core/sratools/prefetch/tests/main.nf.test
 create mode 100644 modules/nf-core/sratools/prefetch/tests/main.nf.test.snap
 create mode 100644 modules/nf-core/sratools/prefetch/tests/tags.yml

diff --git a/modules/nf-core/sratools/prefetch/environment.yml b/modules/nf-core/sratools/prefetch/environment.yml
new file mode 100644
index 0000000..6596bc7
--- /dev/null
+++ b/modules/nf-core/sratools/prefetch/environment.yml
@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::sra-tools=3.1.0
+  - conda-forge::curl=8.5.0
diff --git a/modules/nf-core/sratools/prefetch/main.nf b/modules/nf-core/sratools/prefetch/main.nf
new file mode 100644
index 0000000..74838d5
--- /dev/null
+++ b/modules/nf-core/sratools/prefetch/main.nf
@@ -0,0 +1,47 @@
+process SRATOOLS_PREFETCH {
+    tag "$id"
+    label 'process_low'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/sra-tools:3.1.0--h9f5acd7_0' :
+        'biocontainers/sra-tools:3.1.0--h9f5acd7_0' }"
+
+    input:
+    tuple val(meta), val(id)
+    path ncbi_settings
+    path certificate
+
+    output:
+    tuple val(meta), path(id, type: 'dir'), emit: sra
+    path 'versions.yml'      , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    shell:
+    args = task.ext.args ?: ''
+    args2 = task.ext.args2 ?: '5 1 100'  // <num retries> <base delay in seconds> <max delay in seconds>
+    if (certificate) {
+        if (certificate.toString().endsWith('.jwt')) {
+            args += " --perm ${certificate}"
+        }
+        else if (certificate.toString().endsWith('.ngc')) {
+            args += " --ngc ${certificate}"
+        }
+    }
+
+    template 'retry_with_backoff.sh'
+
+    stub:
+    """
+    mkdir $id
+    touch $id/${id}.sra
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        sratools: \$(prefetch --version 2>&1 | grep -Eo '[0-9.]+')
+        curl: \$(curl --version | head -n 1 | sed 's/^curl //; s/ .*\$//')
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/sratools/prefetch/meta.yml b/modules/nf-core/sratools/prefetch/meta.yml
new file mode 100644
index 0000000..3a537bf
--- /dev/null
+++ b/modules/nf-core/sratools/prefetch/meta.yml
@@ -0,0 +1,59 @@
+name: sratools_prefetch
+description: Download sequencing data from the NCBI Sequence Read Archive (SRA).
+keywords:
+  - sequencing
+  - fastq
+  - prefetch
+tools:
+  - sratools:
+      description: SRA Toolkit and SDK from NCBI
+      homepage: https://github.com/ncbi/sra-tools
+      documentation: https://github.com/ncbi/sra-tools/wiki
+      tool_dev_url: https://github.com/ncbi/sra-tools
+      licence: ["Public Domain"]
+      identifier: ""
+input:
+  - - meta:
+        type: map
+        description: >
+          Groovy Map containing sample information e.g. [ id:'test', single_end:false
+          ]
+    - id:
+        type: string
+        description: >
+          A string denoting an SRA id.
+  - - ncbi_settings:
+        type: file
+        description: >
+          An NCBI user settings file.
+        pattern: "*.mkfg"
+  - - certificate:
+        type: file
+        description: >
+          Path to a JWT cart file used to access protected dbGAP data on SRA using the
+          sra-toolkit
+        pattern: "*.cart"
+output:
+  - sra:
+      - meta:
+          type: map
+          description: >
+            Groovy Map containing sample information e.g. [ id:'test', single_end:false
+            ]
+          pattern: "*/*.sra"
+      - "id, type: 'dir":
+          type: map
+          description: >
+            Groovy Map containing sample information e.g. [ id:'test', single_end:false
+            ]
+          pattern: "*/*.sra"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@Midnighter"
+maintainers:
+  - "@Midnighter"
+  - "@gallvp"
diff --git a/modules/nf-core/sratools/prefetch/templates/retry_with_backoff.sh b/modules/nf-core/sratools/prefetch/templates/retry_with_backoff.sh
new file mode 100755
index 0000000..bfee607
--- /dev/null
+++ b/modules/nf-core/sratools/prefetch/templates/retry_with_backoff.sh
@@ -0,0 +1,65 @@
+#!/usr/bin/env bash
+
+set -u
+
+retry_with_backoff() {
+    local max_attempts=${1}
+    local delay=${2}
+    local max_time=${3}
+    local attempt=1
+    local output=
+    local status=
+
+    # Remove the first three arguments to this function in order to access
+    # the 'real' command with `${@}`.
+    shift 3
+
+    while [ ${attempt} -le ${max_attempts} ]; do
+        output=$("${@}")
+        status=${?}
+
+        if [ ${status} -eq 0 ]; then
+            break
+        fi
+
+        if [ ${attempt} -lt ${max_attempts} ]; then
+            echo "Failed attempt ${attempt} of ${max_attempts}. Retrying in ${delay} s." >&2
+            sleep ${delay}
+        elif [ ${attempt} -eq ${max_attempts} ]; then
+            echo "Failed after ${attempt} attempts." >&2
+            return ${status}
+        fi
+
+        attempt=$(( ${attempt} + 1 ))
+        delay=$(( ${delay} * 2 ))
+        if [ ${delay} -ge ${max_time} ]; then
+            delay=${max_time}
+        fi
+    done
+
+    echo "${output}"
+}
+
+export NCBI_SETTINGS="$PWD/!{ncbi_settings}"
+
+retry_with_backoff !{args2} \
+    prefetch \
+    !{args} \
+    !{id}
+
+# check file integrity using vdb-validate or (when archive contains no checksums) md5sum
+vdb-validate !{id} > vdb-validate_result.txt 2>&1 || exit 1
+if grep -q "checksums missing" vdb-validate_result.txt; then
+    VALID_MD5SUMS=$(curl --silent --fail --location --retry 3 --retry-delay 60 'https://locate.ncbi.nlm.nih.gov/sdl/2/retrieve?filetype=run&acc=!{id}')
+    LOCAL_MD5SUMS=$(md5sum !{id}/* | cut -f1 -d' ')
+    if ! grep -q -F -f <(echo "$LOCAL_MD5SUMS") <(echo "$VALID_MD5SUMS"); then
+        echo "MD5 sum check failed" 1>&2
+        exit 1
+    fi
+fi
+
+cat <<-END_VERSIONS > versions.yml
+"!{task.process}":
+    sratools: $(prefetch --version 2>&1 | grep -Eo '[0-9.]+')
+    curl: $(curl --version | head -n 1 | sed 's/^curl //; s/ .*$//')
+END_VERSIONS
diff --git a/modules/nf-core/sratools/prefetch/tests/main.nf.test b/modules/nf-core/sratools/prefetch/tests/main.nf.test
new file mode 100644
index 0000000..92034d4
--- /dev/null
+++ b/modules/nf-core/sratools/prefetch/tests/main.nf.test
@@ -0,0 +1,71 @@
+nextflow_process {
+    name "Test Process SRATOOLS_PREFETCH"
+    script "../main.nf"
+    process "SRATOOLS_PREFETCH"
+    tag "modules"
+    tag "modules_nfcore"
+    tag "sratools"
+    tag "sratools/prefetch"
+
+    test("sratools/prefetch") {
+
+        when {
+            process {
+                """
+                input[0] = Channel.of([ [ id:'test', single_end:false ], 'DRR000774' ])
+                input[1] = file(params.modules_testdata_base_path + 'generic/config/ncbi_user_settings.mkfg', checkIfExists: true)
+                input[2] = []
+                """
+            }
+        }
+
+        then {
+            assertAll (
+            { assert process.success },
+            { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    test("sratools/prefetch with sralite") {
+
+        when {
+            process {
+                """
+                input[0] = Channel.of([ [ id:'test', single_end:false ], 'SRR1170046' ])
+                input[1] = file(params.modules_testdata_base_path + 'generic/config/ncbi_user_settings.mkfg', checkIfExists: true)
+                input[2] = []
+                """
+            }
+        }
+
+        then {
+            assertAll (
+            { assert process.success },
+            { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    test("sratools/prefetch/stub") {
+
+        options '-stub'
+
+        when {
+            process {
+                """
+                input[0] = Channel.of([ [ id:'test', single_end:false ], 'DRR000774' ])
+                input[1] = file(params.modules_testdata_base_path + 'generic/config/ncbi_user_settings.mkfg', checkIfExists: true)
+                input[2] = []
+                """
+            }
+        }
+
+        then {
+            assertAll (
+            { assert process.success },
+            { assert snapshot(process.out).match() }
+            )
+        }
+    }
+}
diff --git a/modules/nf-core/sratools/prefetch/tests/main.nf.test.snap b/modules/nf-core/sratools/prefetch/tests/main.nf.test.snap
new file mode 100644
index 0000000..82a1969
--- /dev/null
+++ b/modules/nf-core/sratools/prefetch/tests/main.nf.test.snap
@@ -0,0 +1,119 @@
+{
+    "sratools/prefetch/stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        [
+                            "DRR000774.sra:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        ]
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,83d1b23f5ff5b2ad1b96d17d7d7594ee"
+                ],
+                "sra": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        [
+                            "DRR000774.sra:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        ]
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,83d1b23f5ff5b2ad1b96d17d7d7594ee"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-05-17T20:07:31.627115"
+    },
+    "sratools/prefetch with sralite": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        [
+                            "SRR1170046.sralite:md5,7acfce556ca0951aff49d780899c105b"
+                        ]
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,83d1b23f5ff5b2ad1b96d17d7d7594ee"
+                ],
+                "sra": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        [
+                            "SRR1170046.sralite:md5,7acfce556ca0951aff49d780899c105b"
+                        ]
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,83d1b23f5ff5b2ad1b96d17d7d7594ee"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-02-28T11:49:02.309737"
+    },
+    "sratools/prefetch": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        [
+                            "DRR000774.sra:md5,7647dba20c89c0e3d7ad13842f060eb0"
+                        ]
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,83d1b23f5ff5b2ad1b96d17d7d7594ee"
+                ],
+                "sra": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        [
+                            "DRR000774.sra:md5,7647dba20c89c0e3d7ad13842f060eb0"
+                        ]
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,83d1b23f5ff5b2ad1b96d17d7d7594ee"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-02-28T11:48:37.428307"
+    }
+}
\ No newline at end of file
diff --git a/modules/nf-core/sratools/prefetch/tests/tags.yml b/modules/nf-core/sratools/prefetch/tests/tags.yml
new file mode 100644
index 0000000..52110bf
--- /dev/null
+++ b/modules/nf-core/sratools/prefetch/tests/tags.yml
@@ -0,0 +1,2 @@
+sratools/prefetch:
+  - modules/nf-core/sratools/prefetch/**

From 9e1e92a357c00ac867b0608dbd79a7839dc806d6 Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Thu, 14 Nov 2024 13:51:10 -0500
Subject: [PATCH 10/28] Add sample_name removal of non-alphanumeric characters
 and nf-test for sample_name

---
 CHANGELOG.md                                  | 12 +++++++
 tests/data/add-samplesheet.csv                |  8 ++---
 tests/data/samplesheet-addsamplename.csv      |  3 --
 .../workflows/fetchdatairidanext/main.nf.test | 36 +++++++++++++++++++
 workflows/fetchdatairidanext.nf               | 13 +++++--
 5 files changed, 63 insertions(+), 9 deletions(-)
 delete mode 100644 tests/data/samplesheet-addsamplename.csv
 create mode 100644 tests/workflows/fetchdatairidanext/main.nf.test

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 8f2017f..482746b 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -3,6 +3,18 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.2.0]
+
+### `Changed`
+
+- Modified the template for input csv file to include a `sample_name` column in addition to `sample` in-line with changes to [IRIDA-Next update] as seen with the [speciesabundance pipeline]
+  - `sample_name` special characters will be replaced with `"_"`
+  - If no `sample_name` is supplied in the column `sample` will be used
+  - To avoid repeat values for `sample_name` all `sample_name` values will be suffixed with the unique `sample` value from the input file
+
+[IRIDA-Next update]: https://github.com/phac-nml/irida-next/pull/678
+[speciesabundance pipeline]: https://github.com/phac-nml/speciesabundance/pull/24
+
 ## [1.1.1] - 2024-04-19
 
 ### Added
diff --git a/tests/data/add-samplesheet.csv b/tests/data/add-samplesheet.csv
index 4512f0a..f4e437d 100644
--- a/tests/data/add-samplesheet.csv
+++ b/tests/data/add-samplesheet.csv
@@ -1,5 +1,5 @@
 sample,sample_name,insdc_accession
-SAMPLE1,S1,ERR1109373
-ERROR1,S2,SRR999908
-ERROR2,S3,SRR999934
-SAMPLE2,S4,SRR13191702
+SAMPLE1,S 1,ERR1109373
+SAMPLE2,S2,ERR1109373
+SAMPLE3,S2,SRR13191702
+SAMPLE4,,SRR13191702
diff --git a/tests/data/samplesheet-addsamplename.csv b/tests/data/samplesheet-addsamplename.csv
deleted file mode 100644
index 21ced63..0000000
--- a/tests/data/samplesheet-addsamplename.csv
+++ /dev/null
@@ -1,3 +0,0 @@
-sample,sample_name,insdc_accession
-SAMPLE1,S1,ERR1109373
-SAMPLE2,,SRR13191702
diff --git a/tests/workflows/fetchdatairidanext/main.nf.test b/tests/workflows/fetchdatairidanext/main.nf.test
new file mode 100644
index 0000000..f97c1d0
--- /dev/null
+++ b/tests/workflows/fetchdatairidanext/main.nf.test
@@ -0,0 +1,36 @@
+nextflow_workflow {
+
+    name "Test workflow: workflows/fetchdatairidanext.nf"
+    script "workflows/fetchdatairidanext.nf"
+    workflow "FETCHDATAIRIDANEXT"
+    tag "full workflow"
+    tag "fetchdatairdanext"
+
+    test("Samplesheets with sample_name") {
+        tag "sample_name"
+        when {
+            params {
+                input = "$baseDir/tests/data/add-samplesheet.csv"
+                outdir = "output"
+            }
+        }
+
+        then {
+            assert workflow.success
+            assert path("$launchDir/output").exists()
+
+            // Check that reads have the correct filename when supplying a sample_name
+            assert path("$launchDir/output/iridanext.output.json").exists()
+            def iridanext_json = path("$launchDir/output/iridanext.output.json").json
+            def iridanext_samples = iridanext_json.files.samples
+
+            assert iridanext_samples.SAMPLE1 == [['path':'reads/S_1_ERR1109373_2.fastq.gz'], ['path':'reads/S_1_ERR1109373_1.fastq.gz']]
+            assert iridanext_samples.SAMPLE2 == [['path':'reads/S2_ERR1109373_2.fastq.gz'], ['path':'reads/S2_ERR1109373_1.fastq.gz']]
+            assert iridanext_samples.SAMPLE3 == [['path':'reads/S2_SRR13191702_2.fastq.gz'], ['path':'reads/S2_SRR13191702_1.fastq.gz']]
+            assert iridanext_samples.SAMPLE4 == [['path':'reads/SRR13191702_2.fastq.gz'], ['path':'reads/SRR13191702_1.fastq.gz']]
+
+
+        }
+    }
+
+}
diff --git a/workflows/fetchdatairidanext.nf b/workflows/fetchdatairidanext.nf
index bb8a5f2..b55d968 100644
--- a/workflows/fetchdatairidanext.nf
+++ b/workflows/fetchdatairidanext.nf
@@ -56,10 +56,19 @@ workflow FETCHDATAIRIDANEXT {
     // Create a new channel of metadata from a sample sheet
     // NB: `input` corresponds to `params.input` and associated sample sheet schema
     input = Channel.fromSamplesheet("input")
-    meta_accessions = input.map {meta -> tuple(["id": meta.id.first(), "irida_id": meta.irida_id.first(), "insdc_accession": meta.insdc_accession.first()], meta.insdc_accession.first())}
+    // and remove non-alphanumeric characters in sample_names (meta.id)
+        .map { meta ->
+            if (meta.id[0]) {
+                    // Non-alphanumeric characters (excluding _,-,.) will be replaced with "_"
+                new_id = meta.id[0].replaceAll(/[^A-Za-z0-9_\.\-]/, '_') // meta.id appears to be an immutable list, the workaround is to create a new variable
+            } else {
+                new_id = meta.id[0]
+            }
+            return [["id": new_id, "irida_id": meta.irida_id[0], "insdc_accession": meta.insdc_accession[0]], meta.insdc_accession[0]]
+        }
 
     FASTQ_DOWNLOAD_PREFETCH_FASTERQDUMP_SRATOOLS (
-        ch_sra_ids = meta_accessions,
+        ch_sra_ids = input,
         ch_dbgap_key = []
     )
     ch_versions = ch_versions.mix(FASTQ_DOWNLOAD_PREFETCH_FASTERQDUMP_SRATOOLS.out.versions)

From d6093db02e066b5e337dc89716ef970d6e7cee1b Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Thu, 14 Nov 2024 15:01:41 -0500
Subject: [PATCH 11/28] update documenantation, and param to override
 sample_name rename

---
 CHANGELOG.md        | 14 ++++++++++++--
 README.md           | 12 ++++++++++++
 conf/modules.config |  2 +-
 docs/output.md      |  2 +-
 docs/usage.md       | 24 ++++++++++++++++++++++++
 nextflow.config     |  4 ++++
 6 files changed, 54 insertions(+), 4 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 482746b..49dd608 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -8,12 +8,16 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### `Changed`
 
 - Modified the template for input csv file to include a `sample_name` column in addition to `sample` in-line with changes to [IRIDA-Next update] as seen with the [speciesabundance pipeline]
+  - If `sample_name` is supplied, then the reads will have `sample_name` prefixed before the accession code
   - `sample_name` special characters will be replaced with `"_"`
-  - If no `sample_name` is supplied in the column `sample` will be used
-  - To avoid repeat values for `sample_name` all `sample_name` values will be suffixed with the unique `sample` value from the input file
+- Reverted `fasterq-dump` version to 2.11.0 from 3.0.8 due to [issue #865]. Solution proposed by `fetchngs` in [PR #261]
+- Fixed linting issues in CI caused by `nf-core` 3.0.1
+- Updated `nf-test` snapshots and added new tests for `sample_name` feature
 
 [IRIDA-Next update]: https://github.com/phac-nml/irida-next/pull/678
 [speciesabundance pipeline]: https://github.com/phac-nml/speciesabundance/pull/24
+[issue #865]: https://github.com/ncbi/sra-tools/issues/865
+[PR #261]: https://github.com/nf-core/fetchngs/pull/261
 
 ## [1.1.1] - 2024-04-19
 
@@ -41,3 +45,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Added
 
 - Initial release of fetchdatairidanext pipeline which will download reads from NCBI/INSDC archives.
+
+[1.2.0]: https://github.com/phac-nml/fetchdatairidanext/releases/tag/1.2.0
+[1.1.1]: https://github.com/phac-nml/fetchdatairidanext/releases/tag/1.1.1
+[1.1.0]: https://github.com/phac-nml/fetchdatairidanext/releases/tag/1.1.0
+[1.0.1]: https://github.com/phac-nml/fetchdatairidanext/releases/tag/1.0.1
+[1.0.0]: https://github.com/phac-nml/fetchdatairidanext/releases/tag/1.0.0
diff --git a/README.md b/README.md
index 2390e32..93a6949 100644
--- a/README.md
+++ b/README.md
@@ -20,10 +20,22 @@ That is, there are two columns:
 
 The structure of this file is defined in [assets/schema_input.json](assets/schema_input.json). An example of this file is provided at [assets/samplesheet.csv](assets/samplesheet.csv).
 
+## IRIDA-Next Optional Input Configuration
+
+`fetchdatairidanext` accepts the [IRIDA-Next](https://github.com/phac-nml/irida-next) format for samplesheets which can contain an additional column: `sample_name`
+
+`sample_name`: An **optional** column, to allow for an override the default reads name with a `sample_name` prefix before the accession code.
+
+`sample_name`, allows more flexibility in naming reads. Unlike `sample`, `sample_name` is not required to contain unique values. Non-alphanumeric characters (excluding `_`,`-`,`.`) will be replaced with `"_"`. `sample_name` can be provided without renaming by changing parameters.
+
+An [example samplesheet](tests/data/samplesheets/samplesheet-sample_name.csv) has been provided with the pipeline.
+
 # Parameters
 
 The main parameters are `--input` as defined above and `--output` for specifying the output results directory. You may wish to provide `-profile singularity` to specify the use of singularity containers (or `-profile docker` for docker) and `-r [branch]` to specify which GitHub branch you would like to run.
 
+`--rename_with_samplename` (Default: `true`) can changed to `false` to override reads renaming when `sample_name` provided in samplesheet input
+
 Other parameters (defaults from nf-core) are defined in [nextflow_schema.json](nextflow_schema.json).
 
 # Running
diff --git a/conf/modules.config b/conf/modules.config
index f68b79d..1399215 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -41,7 +41,7 @@ process {
 
         ext.args = {
             [
-                meta.id ? rename(meta.id, meta.insdc_accession) : ""
+                (meta.id && params.rename_with_samplename) ? rename(meta.id, meta.insdc_accession) : ""
             ].join(" ")
         }
     }
diff --git a/docs/output.md b/docs/output.md
index 7e95254..8247aae 100644
--- a/docs/output.md
+++ b/docs/output.md
@@ -29,7 +29,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 - `sratools/`
   - Sequence data in SRA format: `INSDC_ACCESSION/INSDC_ACCESSION.sra`
 - `reads/`
-  - Reads in fastq format: `INSDC_ACCESSION.fastq.gz`
+  - Reads in fastq format: `INSDC_ACCESSION.fastq.gz` (or alternatively `SAMPLE_NAME_INSDC_ACCESSION.fastq.gz` if `sample_name` provided)
 
 </details>
 
diff --git a/docs/usage.md b/docs/usage.md
index a261f28..8621d40 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -31,6 +31,26 @@ SAMPLE2,SRR13191702
 
 An [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline.
 
+### IRIDA-Next Optional Samplesheet Configuration
+
+`fetchdatairidanext` also accepts the [IRIDA-Next](https://github.com/phac-nml/irida-next) format for samplesheets which contain the following columns: `sample`, `sample_name`, `insdc_accession`. The `sample` column values within a samplesheet should be unique.
+
+A final samplesheet file consisting of mlst_alleles and addresses may look something like the one below:
+
+```console
+sample,sample_name,insdc_accession
+SAMPLE1,S1,ERR1109373
+SAMPLE2,,SRR13191702
+```
+
+| Column            | Description                                                                                                  |
+| ----------------- | -----------------------------------------------------------------------------------------------------------  |
+| `sample`          | Custom sample name. Samples should be unique within a samplesheet.                                                                                                                       |
+| `sample_name`     | Provides custom prefix to read filenames                                                                     |
+| `insdc_accession` | The accession (run accession) from one of the INSDC databases (NCBI, ENA, or DDBJ).                          |
+
+An [example samplesheet](tests/data/samplesheets/samplesheet-sample_name.csv) has been provided with the pipeline.
+
 ## Running the pipeline
 
 The typical command for running the pipeline is as follows:
@@ -132,6 +152,10 @@ You can also supply a run name to resume a specific run: `-resume [run-name]`. U
 
 Specify the path to a specific config file (this is a core Nextflow command). See the [nf-core website documentation](https://nf-co.re/usage/configuration) for more information.
 
+### `--rename_with_samplename`
+
+When `sample_name` is included in samplesheet will add prefix to read filenames (Default: true)
+
 ## Custom configuration
 
 ### Resource requests
diff --git a/nextflow.config b/nextflow.config
index 85f9022..2994933 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -12,6 +12,10 @@ params {
     // Input options
     input                      = null
 
+    // Fetchdatairidanext options
+
+    rename_with_samplename     = true
+
     // Boilerplate options
     outdir                     = null
     publish_dir_mode           = 'copy'

From f1a50f3159e5c899b1b6546ccc6e6bbdd5898ee2 Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Thu, 14 Nov 2024 15:02:56 -0500
Subject: [PATCH 12/28] Update usage.md

---
 docs/usage.md | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/docs/usage.md b/docs/usage.md
index 8621d40..4c63b38 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -43,11 +43,11 @@ SAMPLE1,S1,ERR1109373
 SAMPLE2,,SRR13191702
 ```
 
-| Column            | Description                                                                                                  |
-| ----------------- | -----------------------------------------------------------------------------------------------------------  |
-| `sample`          | Custom sample name. Samples should be unique within a samplesheet.                                                                                                                       |
-| `sample_name`     | Provides custom prefix to read filenames                                                                     |
-| `insdc_accession` | The accession (run accession) from one of the INSDC databases (NCBI, ENA, or DDBJ).                          |
+| Column            | Description                                                                         |
+| ----------------- | ----------------------------------------------------------------------------------- |
+| `sample`          | Custom sample name. Samples should be unique within a samplesheet.                  |
+| `sample_name`     | Provides custom prefix to read filenames                                            |
+| `insdc_accession` | The accession (run accession) from one of the INSDC databases (NCBI, ENA, or DDBJ). |
 
 An [example samplesheet](tests/data/samplesheets/samplesheet-sample_name.csv) has been provided with the pipeline.
 

From 0dd868a54ac3d3945505a9d78c42c17c0899ee08 Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Thu, 14 Nov 2024 15:13:31 -0500
Subject: [PATCH 13/28] Add new param to schema

---
 nextflow_schema.json | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/nextflow_schema.json b/nextflow_schema.json
index a5f1c26..394b2a1 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -214,5 +214,11 @@
         {
             "$ref": "#/definitions/generic_options"
         }
-    ]
+    ],
+    "properties": {
+        "rename_with_samplename": {
+            "type": "boolean",
+            "default": true
+        }
+    }
 }

From 82064589fc2f9af471790bfe461e518b3cef6838 Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Thu, 14 Nov 2024 15:48:35 -0500
Subject: [PATCH 14/28] Updating UI for IRIDA-Next

---
 nextflow_schema.json | 37 ++++++++++++++++++++++++++++---------
 1 file changed, 28 insertions(+), 9 deletions(-)

diff --git a/nextflow_schema.json b/nextflow_schema.json
index 394b2a1..6852b8c 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -10,7 +10,10 @@
             "type": "object",
             "fa_icon": "fas fa-terminal",
             "description": "Define where the pipeline should find input data and save output data.",
-            "required": ["input", "outdir"],
+            "required": [
+                "input",
+                "outdir"
+            ],
             "properties": {
                 "input": {
                     "type": "string",
@@ -40,6 +43,18 @@
                 }
             }
         },
+        "additional_parameters": {
+            "title": "Additional Parameters",
+            "type": "object",
+            "description": "IRIDA-Next Parameters",
+            "default": "",
+            "properties": {
+                "rename_with_samplename": {
+                    "type": "boolean",
+                    "default": true
+                }
+            }
+        },
         "institutional_config_options": {
             "title": "Institutional config options",
             "type": "object",
@@ -133,7 +148,14 @@
                     "description": "Method used to save pipeline results to output directory.",
                     "help_text": "The Nextflow `publishDir` option specifies which intermediate files should be saved to the output directory. This option tells the pipeline what method should be used to move these files. See [Nextflow docs](https://www.nextflow.io/docs/latest/process.html#publishdir) for details.",
                     "fa_icon": "fas fa-copy",
-                    "enum": ["symlink", "rellink", "link", "copy", "copyNoFollow", "move"],
+                    "enum": [
+                        "symlink",
+                        "rellink",
+                        "link",
+                        "copy",
+                        "copyNoFollow",
+                        "move"
+                    ],
                     "hidden": true
                 },
                 "email_on_fail": {
@@ -205,6 +227,9 @@
         {
             "$ref": "#/definitions/input_output_options"
         },
+        {
+            "$ref": "#/definitions/additional_parameters"
+        },
         {
             "$ref": "#/definitions/institutional_config_options"
         },
@@ -214,11 +239,5 @@
         {
             "$ref": "#/definitions/generic_options"
         }
-    ],
-    "properties": {
-        "rename_with_samplename": {
-            "type": "boolean",
-            "default": true
-        }
-    }
+    ]
 }

From c877cd443ccaef616ccf7d3b27116db2aaec126c Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Thu, 14 Nov 2024 15:57:19 -0500
Subject: [PATCH 15/28] Made it pretty

---
 nextflow_schema.json | 14 ++------------
 1 file changed, 2 insertions(+), 12 deletions(-)

diff --git a/nextflow_schema.json b/nextflow_schema.json
index 6852b8c..6257e59 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -10,10 +10,7 @@
             "type": "object",
             "fa_icon": "fas fa-terminal",
             "description": "Define where the pipeline should find input data and save output data.",
-            "required": [
-                "input",
-                "outdir"
-            ],
+            "required": ["input", "outdir"],
             "properties": {
                 "input": {
                     "type": "string",
@@ -148,14 +145,7 @@
                     "description": "Method used to save pipeline results to output directory.",
                     "help_text": "The Nextflow `publishDir` option specifies which intermediate files should be saved to the output directory. This option tells the pipeline what method should be used to move these files. See [Nextflow docs](https://www.nextflow.io/docs/latest/process.html#publishdir) for details.",
                     "fa_icon": "fas fa-copy",
-                    "enum": [
-                        "symlink",
-                        "rellink",
-                        "link",
-                        "copy",
-                        "copyNoFollow",
-                        "move"
-                    ],
+                    "enum": ["symlink", "rellink", "link", "copy", "copyNoFollow", "move"],
                     "hidden": true
                 },
                 "email_on_fail": {

From 86bccf9653ba78dd17b6ac6a34168a59f2f341cf Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Thu, 14 Nov 2024 16:06:24 -0500
Subject: [PATCH 16/28] Improved description for IRIDA-Next parameter

---
 nextflow_schema.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/nextflow_schema.json b/nextflow_schema.json
index 6257e59..508fa6b 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -43,11 +43,11 @@
         "additional_parameters": {
             "title": "Additional Parameters",
             "type": "object",
-            "description": "IRIDA-Next Parameters",
             "default": "",
             "properties": {
                 "rename_with_samplename": {
                     "type": "boolean",
+                    "description": "Filenames for reads will have 'SAMPLE_NAME' prefixed to 'INSDC_ACCESSION' (True)",
                     "default": true
                 }
             }

From 1238b144196fcc94ad466ebdd2fb03b685ee5956 Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Fri, 15 Nov 2024 10:05:50 -0500
Subject: [PATCH 17/28] Update version for minor release

---
 nextflow.config | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/nextflow.config b/nextflow.config
index 2994933..6f29485 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -202,7 +202,7 @@ manifest {
     description     = """IRIDA Next pipeline for fetching data from NCBI"""
     mainScript      = 'main.nf'
     nextflowVersion = '!>=23.04.0'
-    version         = '1.1.1'
+    version         = '1.2.0'
     doi             = ''
     defaultBranch   = 'main'
 }

From dc8596830cc0f8bf59caa5996102d7d07945e152 Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Wed, 20 Nov 2024 09:55:50 -0500
Subject: [PATCH 18/28] Addressing accessions with both pair and single end
 reads

---
 conf/modules.config                        | 12 ++++++++++--
 modules/local/sratools/fasterqdump/main.nf |  5 ++++-
 2 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index 1399215..54b5ea8 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -37,11 +37,19 @@ process {
             mode: params.publish_dir_mode,
             pattern: 'reads/*.fastq.gz'
         ]
-        def rename = {String sample_name, String accession -> "--outfile ${sample_name}_${accession}"}
+        def fasterq_rename = {String sample_name, String accession -> "--outfile ${sample_name}_${accession}"}
+        def add_extension = {String sample_name, String accession -> "${sample_name}_${accession}"}
+
+
 
         ext.args = {
             [
-                (meta.id && params.rename_with_samplename) ? rename(meta.id, meta.insdc_accession) : ""
+                (meta.id && params.rename_with_samplename) ? fasterq_rename(meta.id, meta.insdc_accession) : ""
+            ].join(" ")
+        }
+        ext.args2 = {
+            [
+                (meta.id && params.rename_with_samplename) ? add_extension(meta.id, meta.insdc_accession) : meta.insdc_accession
             ].join(" ")
         }
     }
diff --git a/modules/local/sratools/fasterqdump/main.nf b/modules/local/sratools/fasterqdump/main.nf
index b7b9bfe..8195085 100644
--- a/modules/local/sratools/fasterqdump/main.nf
+++ b/modules/local/sratools/fasterqdump/main.nf
@@ -22,6 +22,7 @@ process SRATOOLS_FASTERQDUMP {
     script:
     def args = task.ext.args ?: ''
     def args2 = task.ext.args2 ?: ''
+    def args3 = task.ext.args3 ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
     def key_file = ''
 
@@ -46,8 +47,10 @@ process SRATOOLS_FASTERQDUMP {
         ${key_file} \\
         ${sra}
 
+    find reads/ -type f   -name "$args2" -exec mv {} {}.fastq \\;
+
     pigz \\
-        $args2 \\
+        $args3 \\
         --no-name \\
         --processes $task.cpus \\
         reads/*.fastq

From 3f5404059254e437b6f8308d820a6bfa06d64e1a Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Wed, 20 Nov 2024 10:12:20 -0500
Subject: [PATCH 19/28] Updated tests for previous commit

---
 tests/workflows/fetchdatairidanext/main.nf.test | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tests/workflows/fetchdatairidanext/main.nf.test b/tests/workflows/fetchdatairidanext/main.nf.test
index f97c1d0..447f5d1 100644
--- a/tests/workflows/fetchdatairidanext/main.nf.test
+++ b/tests/workflows/fetchdatairidanext/main.nf.test
@@ -24,8 +24,8 @@ nextflow_workflow {
             def iridanext_json = path("$launchDir/output/iridanext.output.json").json
             def iridanext_samples = iridanext_json.files.samples
 
-            assert iridanext_samples.SAMPLE1 == [['path':'reads/S_1_ERR1109373_2.fastq.gz'], ['path':'reads/S_1_ERR1109373_1.fastq.gz']]
-            assert iridanext_samples.SAMPLE2 == [['path':'reads/S2_ERR1109373_2.fastq.gz'], ['path':'reads/S2_ERR1109373_1.fastq.gz']]
+            assert iridanext_samples.SAMPLE1 == [['path':'reads/S_1_ERR1109373_2.fastq.gz'], ['path':'reads/S_1_ERR1109373_1.fastq.gz'], ['path':'reads/S_1_ERR1109373.fastq.gz']]
+            assert iridanext_samples.SAMPLE2 == [['path':'reads/S2_ERR1109373_2.fastq.gz'], ['path':'reads/S2_ERR1109373_1.fastq.gz'], ['path':'reads/S2_ERR1109373.fastq.gz']]
             assert iridanext_samples.SAMPLE3 == [['path':'reads/S2_SRR13191702_2.fastq.gz'], ['path':'reads/S2_SRR13191702_1.fastq.gz']]
             assert iridanext_samples.SAMPLE4 == [['path':'reads/SRR13191702_2.fastq.gz'], ['path':'reads/SRR13191702_1.fastq.gz']]
 

From 5ad42b5061026b61a04ca6525fa36e487dabad53 Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Wed, 20 Nov 2024 10:16:51 -0500
Subject: [PATCH 20/28] Clarify text

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 93a6949..9c06d86 100644
--- a/README.md
+++ b/README.md
@@ -24,7 +24,7 @@ The structure of this file is defined in [assets/schema_input.json](assets/schem
 
 `fetchdatairidanext` accepts the [IRIDA-Next](https://github.com/phac-nml/irida-next) format for samplesheets which can contain an additional column: `sample_name`
 
-`sample_name`: An **optional** column, to allow for an override the default reads name with a `sample_name` prefix before the accession code.
+`sample_name`: An **optional** column, to add the `sample_name` prefix before the accession code.
 
 `sample_name`, allows more flexibility in naming reads. Unlike `sample`, `sample_name` is not required to contain unique values. Non-alphanumeric characters (excluding `_`,`-`,`.`) will be replaced with `"_"`. `sample_name` can be provided without renaming by changing parameters.
 

From 02ecdb5280bf8cda13a19aa5738c82e0f0464c65 Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Wed, 20 Nov 2024 12:28:54 -0500
Subject: [PATCH 21/28] Clean up conditional operator

---
 workflows/fetchdatairidanext.nf | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/workflows/fetchdatairidanext.nf b/workflows/fetchdatairidanext.nf
index b55d968..9a70a39 100644
--- a/workflows/fetchdatairidanext.nf
+++ b/workflows/fetchdatairidanext.nf
@@ -58,12 +58,7 @@ workflow FETCHDATAIRIDANEXT {
     input = Channel.fromSamplesheet("input")
     // and remove non-alphanumeric characters in sample_names (meta.id)
         .map { meta ->
-            if (meta.id[0]) {
-                    // Non-alphanumeric characters (excluding _,-,.) will be replaced with "_"
-                new_id = meta.id[0].replaceAll(/[^A-Za-z0-9_\.\-]/, '_') // meta.id appears to be an immutable list, the workaround is to create a new variable
-            } else {
-                new_id = meta.id[0]
-            }
+            def new_id = meta.id[0]?.replaceAll(/[^A-Za-z0-9_\.\-]/, '_') ?: meta.id[0]
             return [["id": new_id, "irida_id": meta.irida_id[0], "insdc_accession": meta.insdc_accession[0]], meta.insdc_accession[0]]
         }
 

From 18f3eb35defdc48ddedc18b3fe77c1d6af1e37d3 Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Wed, 20 Nov 2024 12:30:57 -0500
Subject: [PATCH 22/28] Fixed container URL

---
 modules/local/sratools/fasterqdump/main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/modules/local/sratools/fasterqdump/main.nf b/modules/local/sratools/fasterqdump/main.nf
index 8195085..28ebe07 100644
--- a/modules/local/sratools/fasterqdump/main.nf
+++ b/modules/local/sratools/fasterqdump/main.nf
@@ -5,7 +5,7 @@ process SRATOOLS_FASTERQDUMP {
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
         'https://depot.galaxyproject.org/singularity/mulled-v2-5f89fe0cd045cb1d615630b9261a1d17943a9b6a:6a9ff0e76ec016c3d0d27e0c0d362339f2d787e6-0' :
-        'quay.io/biocontainers/mulled-v2-5f89fe0cd045cb1d615630b9261a1d17943a9b6a:6a9ff0e76ec016c3d0d27e0c0d362339f2d787e6-0' }"
+        'biocontainers/mulled-v2-5f89fe0cd045cb1d615630b9261a1d17943a9b6a:6a9ff0e76ec016c3d0d27e0c0d362339f2d787e6-0' }"
 
     input:
     tuple val(meta), path(sra)

From 261f455a0b8803b1caed393461cf9cbd1db28e13 Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Wed, 20 Nov 2024 12:39:56 -0500
Subject: [PATCH 23/28] Improved readibility

---
 modules/local/prefetchchecker/main.nf | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/modules/local/prefetchchecker/main.nf b/modules/local/prefetchchecker/main.nf
index 852061a..4917d1d 100644
--- a/modules/local/prefetchchecker/main.nf
+++ b/modules/local/prefetchchecker/main.nf
@@ -12,8 +12,9 @@ process PREFETCH_CHECKER {
     task.workDir.resolve("failures_report.csv").withWriter { writer ->
 
         sample_name = false
-        failures.each { if ( it[0].id != null) {
-            sample_name = true
+        failures.each {
+            if ( it[0].id != null) {
+                sample_name = true
         }
         }
 

From 09ea6f03a15ea7bc89fbb71019947aeeb28c7315 Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Wed, 20 Nov 2024 12:53:07 -0500
Subject: [PATCH 24/28] return the test, but remove section not used

---
 tests/pipelines/fetchdatairidanext.nf.test | 57 ++++++++++++++++++++++
 1 file changed, 57 insertions(+)
 create mode 100644 tests/pipelines/fetchdatairidanext.nf.test

diff --git a/tests/pipelines/fetchdatairidanext.nf.test b/tests/pipelines/fetchdatairidanext.nf.test
new file mode 100644
index 0000000..4f60f64
--- /dev/null
+++ b/tests/pipelines/fetchdatairidanext.nf.test
@@ -0,0 +1,57 @@
+nextflow_pipeline {
+
+    name "Test fetching small datasets from NCBI"
+    script "main.nf"
+
+    test("basic integration test") {
+
+        when {
+            params {
+                input = "$baseDir/tests/data/samplesheet.csv"
+                outdir = "test1_out"
+            }
+        }
+
+        then {
+            assert workflow.success
+
+            // IRIDA Next output file
+            assert path("$launchDir/test1_out/iridanext.output.json").json == path("$baseDir/tests/data/test1_iridanext.output.json").json
+
+            // Output data
+            assert path("$launchDir/test1_out/reads/ERR1109373_1.fastq.gz").linesGzip.size() == 512
+            assert path("$launchDir/test1_out/reads/ERR1109373_2.fastq.gz").linesGzip.size() == 512
+            assert path("$launchDir/test1_out/reads/SRR13191702_1.fastq.gz").linesGzip.size() == 364
+            assert path("$launchDir/test1_out/reads/SRR13191702_2.fastq.gz").linesGzip.size() == 364
+        }
+    }
+
+    test("integration test with prefetch failures") {
+
+        when {
+            params {
+                input = "$baseDir/tests/data/errorsheet.csv"
+                outdir = "results"
+            }
+        }
+
+        then {
+            assert workflow.success
+
+            // IRIDA Next output file
+            assert path("$launchDir/results/iridanext.output.json").json == path("$baseDir/tests/data/prefetch_errors_iridanext.output.json").json
+
+            // Output data:
+            assert path("$launchDir/results/reads/ERR1109373_1.fastq.gz").linesGzip.size() == 512
+            assert path("$launchDir/results/reads/ERR1109373_2.fastq.gz").linesGzip.size() == 512
+            assert path("$launchDir/results/reads/SRR13191702_1.fastq.gz").linesGzip.size() == 364
+            assert path("$launchDir/results/reads/SRR13191702_2.fastq.gz").linesGzip.size() == 364
+
+            // These files should have failed, and have no output reads:
+            assert path("$launchDir/results/reads/SRR999908_1.fastq.gz").exists() == false
+            assert path("$launchDir/results/reads/SRR999908_2.fastq.gz").exists() == false
+            assert path("$launchDir/results/reads/SRR999934_1.fastq.gz").exists() == false
+            assert path("$launchDir/results/reads/SRR999934_2.fastq.gz").exists() == false
+        }
+    }
+}

From 3ba740ee985b64594a7609020d7adcf03950d5e2 Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Thu, 21 Nov 2024 20:32:15 -0500
Subject: [PATCH 25/28] Claify parameter description

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 9c06d86..26f4b59 100644
--- a/README.md
+++ b/README.md
@@ -34,7 +34,7 @@ An [example samplesheet](tests/data/samplesheets/samplesheet-sample_name.csv) ha
 
 The main parameters are `--input` as defined above and `--output` for specifying the output results directory. You may wish to provide `-profile singularity` to specify the use of singularity containers (or `-profile docker` for docker) and `-r [branch]` to specify which GitHub branch you would like to run.
 
-`--rename_with_samplename` (Default: `true`) can changed to `false` to override reads renaming when `sample_name` provided in samplesheet input
+`--rename_with_samplename` (Default: `true`) When `false`, samplesheet column `sample_name` not used for reads-renaming.
 
 Other parameters (defaults from nf-core) are defined in [nextflow_schema.json](nextflow_schema.json).
 

From dbe8bf68c821cd62ac3b171ab45221774134da26 Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Thu, 21 Nov 2024 20:34:50 -0500
Subject: [PATCH 26/28] Sample_name description

---
 assets/schema_input.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/assets/schema_input.json b/assets/schema_input.json
index f1060cf..077a2f5 100644
--- a/assets/schema_input.json
+++ b/assets/schema_input.json
@@ -17,7 +17,7 @@
             "sample_name": {
                 "type": "string",
                 "meta": ["id"],
-                "errorMessage": "Optional. Used to override sample when used in tools like IRIDA-Next"
+                "errorMessage": "Optional. Used to override reads filename when used in tools like IRIDA-Next"
             },
             "insdc_accession": {
                 "type": "string",

From 36f4bbb4318bbf04dd3ff580e1860a87c2a73b66 Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Thu, 21 Nov 2024 20:40:29 -0500
Subject: [PATCH 27/28] Missing filepath

---
 docs/usage.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/usage.md b/docs/usage.md
index 4c63b38..3a578f0 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -49,7 +49,7 @@ SAMPLE2,,SRR13191702
 | `sample_name`     | Provides custom prefix to read filenames                                            |
 | `insdc_accession` | The accession (run accession) from one of the INSDC databases (NCBI, ENA, or DDBJ). |
 
-An [example samplesheet](tests/data/samplesheets/samplesheet-sample_name.csv) has been provided with the pipeline.
+An [example samplesheet](tests/data/add-samplesheet.csv) has been provided with the pipeline.
 
 ## Running the pipeline
 

From da65a5a7c923b150ea2bfa81930a4c6578824157 Mon Sep 17 00:00:00 2001
From: Steven Sutcliffe <sgsutcliffe@gmail.com>
Date: Thu, 21 Nov 2024 20:43:25 -0500
Subject: [PATCH 28/28] Fixed wording

---
 docs/usage.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/usage.md b/docs/usage.md
index 3a578f0..060b3cf 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -154,7 +154,7 @@ Specify the path to a specific config file (this is a core Nextflow command). Se
 
 ### `--rename_with_samplename`
 
-When `sample_name` is included in samplesheet will add prefix to read filenames (Default: true)
+When `sample_name` is included in the sample sheet, it will be prefixed to read filenames (Default: true)
 
 ## Custom configuration