From be3ec58f3bcc5bc044e18c4290949ae7a5ec2deb Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Mon, 24 Mar 2025 16:55:45 +0000
Subject: [PATCH 01/18] wip, need container with pyyaml

---
 modules/local/rundirparser/environment.yml    |  7 ++
 modules/local/rundirparser/main.nf            | 69 ++++++++++++++++++
 modules/local/rundirparser/meta.yml           | 68 +++++++++++++++++
 modules/local/rundirparser/rundirparser.py    | 27 +++++++
 modules/local/rundirparser/tests/main.nf.test | 73 +++++++++++++++++++
 workflows/seqinspector.nf                     | 14 ++++
 6 files changed, 258 insertions(+)
 create mode 100644 modules/local/rundirparser/environment.yml
 create mode 100644 modules/local/rundirparser/main.nf
 create mode 100644 modules/local/rundirparser/meta.yml
 create mode 100644 modules/local/rundirparser/rundirparser.py
 create mode 100644 modules/local/rundirparser/tests/main.nf.test

diff --git a/modules/local/rundirparser/environment.yml b/modules/local/rundirparser/environment.yml
new file mode 100644
index 0000000..4b3c9d3
--- /dev/null
+++ b/modules/local/rundirparser/environment.yml
@@ -0,0 +1,7 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - "YOUR-TOOL-HERE"
diff --git a/modules/local/rundirparser/main.nf b/modules/local/rundirparser/main.nf
new file mode 100644
index 0000000..751640c
--- /dev/null
+++ b/modules/local/rundirparser/main.nf
@@ -0,0 +1,69 @@
+// TODO nf-core: If in doubt look at other nf-core/modules to see how we are doing things! :)
+//               https://github.com/nf-core/modules/tree/master/modules/nf-core/
+//               You can also ask for help via your pull request or on the #modules channel on the nf-core Slack workspace:
+//               https://nf-co.re/join
+// TODO nf-core: A module file SHOULD only define input and output files as command-line parameters.
+//               All other parameters MUST be provided using the "task.ext" directive, see here:
+//               https://www.nextflow.io/docs/latest/process.html#ext
+//               where "task.ext" is a string.
+//               Any parameters that need to be evaluated in the context of a particular sample
+//               e.g. single-end/paired-end data MUST also be defined and evaluated appropriately.
+// TODO nf-core: Software that can be piped together SHOULD be added to separate module files
+//               unless there is a run-time, storage advantage in implementing in this way
+//               e.g. it's ok to have a single module for bwa to output BAM instead of SAM:
+//                 bwa mem | samtools view -B -T ref.fasta
+// TODO nf-core: Optional inputs are not currently supported by Nextflow. However, using an empty
+//               list (`[]`) instead of a file can be used to work around this issue.
+
+process RUNDIRPARSER {
+    tag "$rundir.baseName"
+    label 'process_single'
+
+    // TODO nf-core: List required Conda package(s).
+    //               Software MUST be pinned to channel (i.e. "bioconda"), version (i.e. "1.10").
+    //               For Conda, the build (i.e. "h9402c20_2") must be EXCLUDED to support installation on different operating systems.
+    // TODO nf-core: See section in main README for further information regarding finding and adding container addresses to the section below.
+    conda "python=3.12"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/python:3.12' :
+        'python:3.12' }"
+
+    input:
+    path(rundir)
+    path(parser_script)
+
+    output:
+    path("*_mqc.yaml"), emit: yaml
+    path "versions.yml", emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${rundir.baseName}"
+    """
+    python ${parser_script} ${rundir}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        rundirparser: \$(python --version |& sed '1!d ; s/Python //')
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${rundir.baseName}"
+    // TODO nf-core: A stub section should mimic the execution of the original module as best as possible
+    //               Have a look at the following examples:
+    //               Simple example: https://github.com/nf-core/modules/blob/818474a292b4860ae8ff88e149fbcda68814114d/modules/nf-core/bcftools/annotate/main.nf#L47-L63
+    //               Complex example: https://github.com/nf-core/modules/blob/818474a292b4860ae8ff88e149fbcda68814114d/modules/nf-core/bedtools/split/main.nf#L38-L54
+    """
+    touch rundir_metadata.yml
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        rundirparser: "stub_version"
+    END_VERSIONS
+    """
+}
diff --git a/modules/local/rundirparser/meta.yml b/modules/local/rundirparser/meta.yml
new file mode 100644
index 0000000..7027a80
--- /dev/null
+++ b/modules/local/rundirparser/meta.yml
@@ -0,0 +1,68 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "rundirparser"
+## TODO nf-core: Add a description of the module and list keywords
+description: write your description here
+keywords:
+  - sort
+  - example
+  - genomics
+tools:
+  - "rundirparser":
+      ## TODO nf-core: Add a description and other details for the software below
+      description: ""
+      homepage: ""
+      documentation: ""
+      tool_dev_url: ""
+      doi: ""
+      licence:
+      identifier:
+
+## TODO nf-core: Add a description of all of the variables used as input
+input:
+  # Only when we have meta
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1', single_end:false ]`
+
+    ## TODO nf-core: Delete / customise this example input
+    - bam:
+        type: file
+        description: Sorted BAM/CRAM/SAM file
+        pattern: "*.{bam,cram,sam}"
+        ontologies:
+          - edam: "http://edamontology.org/format_25722"
+          - edam: "http://edamontology.org/format_2573"
+          - edam: "http://edamontology.org/format_3462"
+
+## TODO nf-core: Add a description of all of the variables used as output
+output:
+  - bam:
+      #Only when we have meta
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      ## TODO nf-core: Delete / customise this example output
+      - "*.bam":
+          type: file
+          description: Sorted BAM/CRAM/SAM file
+          pattern: "*.{bam,cram,sam}"
+          ontologies:
+            - edam: "http://edamontology.org/format_25722"
+            - edam: "http://edamontology.org/format_2573"
+            - edam: "http://edamontology.org/format_3462"
+
+  - versions:
+      - "versions.yml":
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+
+authors:
+  - "@kedhammar"
+maintainers:
+  - "@kedhammar"
diff --git a/modules/local/rundirparser/rundirparser.py b/modules/local/rundirparser/rundirparser.py
new file mode 100644
index 0000000..f5056cd
--- /dev/null
+++ b/modules/local/rundirparser/rundirparser.py
@@ -0,0 +1,27 @@
+# rundirparser.py
+import sys
+import yaml
+
+
+def parse_rundir(rundir):
+    # Dummy implementation, replace with actual logic
+    return_dict = {
+        "rundir": rundir,
+        "samples": [
+            {"sample_id": "SAMPLE_1", "metric_1": 10, "metric_2": 20},
+            {"sample_id": "SAMPLE_2", "metric_1": 15, "metric_2": 25},
+            {"sample_id": "SAMPLE_3", "metric_1": 20, "metric_2": 30},
+        ],
+    }
+    return return_dict
+
+
+def main():
+    rundir = sys.argv[1]
+    metadata = parse_rundir(rundir)
+    with open(f"{rundir}_mqc.yml", "w") as outfile:
+        yaml.dump(metadata, outfile, default_flow_style=False)
+
+
+if __name__ == "__main__":
+    main()
diff --git a/modules/local/rundirparser/tests/main.nf.test b/modules/local/rundirparser/tests/main.nf.test
new file mode 100644
index 0000000..c1e8440
--- /dev/null
+++ b/modules/local/rundirparser/tests/main.nf.test
@@ -0,0 +1,73 @@
+// TODO nf-core: Once you have added the required tests, please run the following command to build this file:
+// nf-core modules test rundirparser
+nextflow_process {
+
+    name "Test Process RUNDIRPARSER"
+    script "../main.nf"
+    process "RUNDIRPARSER"
+
+    tag "modules"
+    tag "modules_"
+    tag "rundirparser"
+
+    // TODO nf-core: Change the test name preferably indicating the test-data and file-format used
+    test("sarscov2 - bam") {
+
+        // TODO nf-core: If you are created a test for a chained module
+        // (the module requires running more than one process to generate the required output)
+        // add the 'setup' method here.
+        // You can find more information about how to use a 'setup' method in the docs (https://nf-co.re/docs/contributing/modules#steps-for-creating-nf-test-for-chained-modules).
+
+        when {
+            process {
+                """
+                // TODO nf-core: define inputs of the process here. Example:
+                
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.sorted.bam', checkIfExists: true),
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+                //TODO nf-core: Add all required assertions to verify the test output.
+                // See https://nf-co.re/docs/contributing/tutorials/nf-test_assertions for more information and examples.
+            )
+        }
+
+    }
+
+    // TODO nf-core: Change the test name preferably indicating the test-data and file-format used but keep the " - stub" suffix.
+    test("sarscov2 - bam - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                // TODO nf-core: define inputs of the process here. Example:
+                
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.sorted.bam', checkIfExists: true),
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+                //TODO nf-core: Add all required assertions to verify the test output.
+            )
+        }
+
+    }
+
+}
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 9488cea..dade251 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -10,6 +10,7 @@ include { SEQTK_SAMPLE                  } from '../modules/nf-core/seqtk/sample/
 include { FASTQC                        } from '../modules/nf-core/fastqc/main'
 include { SEQFU_STATS                   } from '../modules/nf-core/seqfu/stats'
 include { FASTQSCREEN_FASTQSCREEN       } from '../modules/nf-core/fastqscreen/fastqscreen/main'
+include { RUNDIRPARSER                  } from '../modules/local/rundirparser/main'
 
 include { MULTIQC as MULTIQC_GLOBAL     } from '../modules/nf-core/multiqc/main'
 include { MULTIQC as MULTIQC_PER_TAG    } from '../modules/nf-core/multiqc/main'
@@ -38,6 +39,19 @@ workflow SEQINSPECTOR {
     ch_multiqc_extra_files = Channel.empty()
     ch_multiqc_reports     = Channel.empty()
 
+    //
+    // MODULE: Parse rundir info
+    //
+    if (!("rundirparser" in skip_tools)) {
+
+        ch_rundir = ch_samplesheet
+            .map { meta, _reads -> meta.rundir }
+            .distinct()
+            .view()
+
+        RUNDIRPARSER(ch_rundir, "${projectDir}/modules/local/rundirparser/rundirparser.py")
+    }
+
     //
     // MODULE: Run Seqtk sample to perform subsampling
     //

From 80caa982eca7b37117424bff3a44d0514e70e565 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 25 Mar 2025 08:40:27 +0000
Subject: [PATCH 02/18] fix conda env and functional containers

---
 modules/local/rundirparser/environment.yml | 6 +++---
 modules/local/rundirparser/main.nf         | 8 ++++----
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/modules/local/rundirparser/environment.yml b/modules/local/rundirparser/environment.yml
index 4b3c9d3..046f88d 100644
--- a/modules/local/rundirparser/environment.yml
+++ b/modules/local/rundirparser/environment.yml
@@ -1,7 +1,7 @@
----
-# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
 channels:
   - conda-forge
   - bioconda
 dependencies:
-  - "YOUR-TOOL-HERE"
+  - pip
+  - pip:
+      - PyYAML==6.0.2
diff --git a/modules/local/rundirparser/main.nf b/modules/local/rundirparser/main.nf
index 751640c..81a1fe4 100644
--- a/modules/local/rundirparser/main.nf
+++ b/modules/local/rundirparser/main.nf
@@ -23,17 +23,17 @@ process RUNDIRPARSER {
     //               Software MUST be pinned to channel (i.e. "bioconda"), version (i.e. "1.10").
     //               For Conda, the build (i.e. "h9402c20_2") must be EXCLUDED to support installation on different operating systems.
     // TODO nf-core: See section in main README for further information regarding finding and adding container addresses to the section below.
-    conda "python=3.12"
+    conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/python:3.12' :
-        'python:3.12' }"
+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/ad/ad2bcce70756f81c07c7e2ffd9b66213bf48ace786466395ac3a402840df2ffb/data' :
+        'community.wave.seqera.io/library/pip_pyyaml:c2ecf27a7f63796e' }"
 
     input:
     path(rundir)
     path(parser_script)
 
     output:
-    path("*_mqc.yaml"), emit: yaml
+    path("*_mqc.yml"), emit: yaml
     path "versions.yml", emit: versions
 
     when:

From 7144a475aa0587bc62d090462b1e4e964a2aa457 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 25 Mar 2025 09:47:30 +0000
Subject: [PATCH 03/18] spacing

---
 modules/nf-core/seqfu/stats/main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/modules/nf-core/seqfu/stats/main.nf b/modules/nf-core/seqfu/stats/main.nf
index 0f8bb3e..2ea8e43 100644
--- a/modules/nf-core/seqfu/stats/main.nf
+++ b/modules/nf-core/seqfu/stats/main.nf
@@ -14,7 +14,7 @@ process SEQFU_STATS {
 
     output:
     tuple val(meta), path("*.tsv")    ,  emit: stats
-    tuple val(meta), path("*_mqc.txt"), emit: multiqc
+    tuple val(meta), path("*_mqc.txt"),  emit: multiqc
     path "versions.yml"               ,  emit: versions
 
     when:

From aec2ad351b1cf86a812851b7e1b9b39068a839ce Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 25 Mar 2025 09:47:54 +0000
Subject: [PATCH 04/18] channel magic to refactor meta on rundir-level

---
 modules/local/rundirparser/main.nf |  6 +++---
 workflows/seqinspector.nf          | 17 ++++++++++++++---
 2 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/modules/local/rundirparser/main.nf b/modules/local/rundirparser/main.nf
index 81a1fe4..de31d5e 100644
--- a/modules/local/rundirparser/main.nf
+++ b/modules/local/rundirparser/main.nf
@@ -29,12 +29,12 @@ process RUNDIRPARSER {
         'community.wave.seqera.io/library/pip_pyyaml:c2ecf27a7f63796e' }"
 
     input:
-    path(rundir)
+    tuple val(joint_meta), path(rundir)
     path(parser_script)
 
     output:
-    path("*_mqc.yml"), emit: yaml
-    path "versions.yml", emit: versions
+    tuple val(joint_meta), path("*_mqc.yml"), emit: multiqc
+    path "versions.yml",                      emit: versions
 
     when:
     task.ext.when == null || task.ext.when
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index dade251..5f3e4e6 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -45,11 +45,22 @@ workflow SEQINSPECTOR {
     if (!("rundirparser" in skip_tools)) {
 
         ch_rundir = ch_samplesheet
-            .map { meta, _reads -> meta.rundir }
-            .distinct()
-            .view()
+            // Group by rundir to merge tags from samples with the same rundir
+            .map { meta, _reads -> [meta.rundir, meta] }
+            .groupTuple()
+            // Create a new meta object with merged tags for each unique rundir
+            .map { rundir, metas ->
+                // Collect all tags across all samples with this rundir
+                def all_tags = metas.collect { it.tags }.flatten().unique()
+                // Create a new meta object with the merged tags
+                def new_meta = [tags: all_tags]
+                // Return the new structure
+                [new_meta, rundir]
+            }
 
         RUNDIRPARSER(ch_rundir, "${projectDir}/modules/local/rundirparser/rundirparser.py")
+        ch_multiqc_files = ch_multiqc_files.mix(RUNDIRPARSER.out.multiqc.first())
+        ch_versions = ch_versions.mix(RUNDIRPARSER.out.versions.first())
     }
 
     //

From 9b0f0e7bd4304fa0844a9723c57e8fd17abc9567 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 25 Mar 2025 10:02:12 +0000
Subject: [PATCH 05/18] update process versioning and stubs

---
 modules/local/rundirparser/main.nf | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/modules/local/rundirparser/main.nf b/modules/local/rundirparser/main.nf
index de31d5e..3d6ea9e 100644
--- a/modules/local/rundirparser/main.nf
+++ b/modules/local/rundirparser/main.nf
@@ -47,7 +47,8 @@ process RUNDIRPARSER {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        rundirparser: \$(python --version |& sed '1!d ; s/Python //')
+        Python: \$(python --version |& sed '1!d ; s/Python //')
+        PyYAML: \$(python -c "import yaml; print(yaml.__version__)")
     END_VERSIONS
     """
 
@@ -59,11 +60,12 @@ process RUNDIRPARSER {
     //               Simple example: https://github.com/nf-core/modules/blob/818474a292b4860ae8ff88e149fbcda68814114d/modules/nf-core/bcftools/annotate/main.nf#L47-L63
     //               Complex example: https://github.com/nf-core/modules/blob/818474a292b4860ae8ff88e149fbcda68814114d/modules/nf-core/bedtools/split/main.nf#L38-L54
     """
-    touch rundir_metadata.yml
+    touch rundir_mqc.yml
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        rundirparser: "stub_version"
+        Python: stub_version
+        PyYAML: stub_version
     END_VERSIONS
     """
 }

From 915965becbb34247dbec76954990bed17d7b5db2 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 25 Mar 2025 11:11:32 +0000
Subject: [PATCH 06/18] remove todo:s, make process agnostic to mqc file
 extensions

---
 modules/local/rundirparser/main.nf | 27 +++------------------------
 1 file changed, 3 insertions(+), 24 deletions(-)

diff --git a/modules/local/rundirparser/main.nf b/modules/local/rundirparser/main.nf
index 3d6ea9e..3c9206a 100644
--- a/modules/local/rundirparser/main.nf
+++ b/modules/local/rundirparser/main.nf
@@ -1,28 +1,7 @@
-// TODO nf-core: If in doubt look at other nf-core/modules to see how we are doing things! :)
-//               https://github.com/nf-core/modules/tree/master/modules/nf-core/
-//               You can also ask for help via your pull request or on the #modules channel on the nf-core Slack workspace:
-//               https://nf-co.re/join
-// TODO nf-core: A module file SHOULD only define input and output files as command-line parameters.
-//               All other parameters MUST be provided using the "task.ext" directive, see here:
-//               https://www.nextflow.io/docs/latest/process.html#ext
-//               where "task.ext" is a string.
-//               Any parameters that need to be evaluated in the context of a particular sample
-//               e.g. single-end/paired-end data MUST also be defined and evaluated appropriately.
-// TODO nf-core: Software that can be piped together SHOULD be added to separate module files
-//               unless there is a run-time, storage advantage in implementing in this way
-//               e.g. it's ok to have a single module for bwa to output BAM instead of SAM:
-//                 bwa mem | samtools view -B -T ref.fasta
-// TODO nf-core: Optional inputs are not currently supported by Nextflow. However, using an empty
-//               list (`[]`) instead of a file can be used to work around this issue.
-
 process RUNDIRPARSER {
     tag "$rundir.baseName"
     label 'process_single'
 
-    // TODO nf-core: List required Conda package(s).
-    //               Software MUST be pinned to channel (i.e. "bioconda"), version (i.e. "1.10").
-    //               For Conda, the build (i.e. "h9402c20_2") must be EXCLUDED to support installation on different operating systems.
-    // TODO nf-core: See section in main README for further information regarding finding and adding container addresses to the section below.
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
         'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/ad/ad2bcce70756f81c07c7e2ffd9b66213bf48ace786466395ac3a402840df2ffb/data' :
@@ -33,8 +12,8 @@ process RUNDIRPARSER {
     path(parser_script)
 
     output:
-    tuple val(joint_meta), path("*_mqc.yml"), emit: multiqc
-    path "versions.yml",                      emit: versions
+    tuple val(joint_meta), path("*_mqc.*"), emit: multiqc
+    path "versions.yml",                    emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -60,7 +39,7 @@ process RUNDIRPARSER {
     //               Simple example: https://github.com/nf-core/modules/blob/818474a292b4860ae8ff88e149fbcda68814114d/modules/nf-core/bcftools/annotate/main.nf#L47-L63
     //               Complex example: https://github.com/nf-core/modules/blob/818474a292b4860ae8ff88e149fbcda68814114d/modules/nf-core/bedtools/split/main.nf#L38-L54
     """
-    touch rundir_mqc.yml
+    touch rundir_mqc.txt
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

From 5546c1069db9cf295166b34201a1cceb84e92647 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 25 Mar 2025 11:11:56 +0000
Subject: [PATCH 07/18] generate _mqc.txt dummy file with table from rundir
 keys

---
 modules/local/rundirparser/rundirparser.py | 60 +++++++++++++++++-----
 1 file changed, 48 insertions(+), 12 deletions(-)

diff --git a/modules/local/rundirparser/rundirparser.py b/modules/local/rundirparser/rundirparser.py
index f5056cd..0820d4e 100644
--- a/modules/local/rundirparser/rundirparser.py
+++ b/modules/local/rundirparser/rundirparser.py
@@ -5,22 +5,58 @@
 
 def parse_rundir(rundir):
     # Dummy implementation, replace with actual logic
-    return_dict = {
-        "rundir": rundir,
-        "samples": [
-            {"sample_id": "SAMPLE_1", "metric_1": 10, "metric_2": 20},
-            {"sample_id": "SAMPLE_2", "metric_1": 15, "metric_2": 25},
-            {"sample_id": "SAMPLE_3", "metric_1": 20, "metric_2": 30},
-        ],
-    }
-    return return_dict
+
+    yml_contents = """# plot_type: 'table'
+# section_name: 'rundir stats'
+# description: 'dummy rundir stats'
+# pconfig:
+#     namespace: 'Cust Data'
+# headers:
+#     col1:
+#         title: '#Seqs'
+#         description: 'Number of sequences'
+#         format: '{:,.0f}'
+#     col2:
+#         title: 'Total bp'
+#         description: 'Total size of the dataset'
+#     col3:
+#         title: 'Avg'
+#         description: 'Average sequence length'
+#     col4:
+#         title: 'N50'
+#         description: '50% of the sequences are longer than this size'
+#     col5:
+#         title: 'N75'
+#         description: '75% of the sequences are longer than this size'
+#     col6:
+#         title: 'N90'
+#         description: '90% of the sequences are longer than this size'
+#     col7:
+#         title: 'Min'
+#         description: 'Length of the shortest sequence'
+#     col8:
+#         title: 'Max'
+#         description: 'Length of the longest sequence'
+#     col9:
+#         title: 'auN'
+#         description: 'Area under the Nx curve'
+#     col10:
+#         title: 'GC'
+#         description: 'Relative GC content (excluding Ns)'
+"""
+    tsv_contents = f"""Sample	col1	col2	col3	col4	col5	col6	col7	col8	col9	col10
+{rundir}	10	147806	14780.6000000	22507	16573	15322	22801.9181765	344	33340	NaN
+"""
+
+    contents = yml_contents + tsv_contents
+
+    with open(f"{rundir}_mqc.txt", "w") as f:
+        f.write(contents)
 
 
 def main():
     rundir = sys.argv[1]
-    metadata = parse_rundir(rundir)
-    with open(f"{rundir}_mqc.yml", "w") as outfile:
-        yaml.dump(metadata, outfile, default_flow_style=False)
+    parse_rundir(rundir)
 
 
 if __name__ == "__main__":

From c87f4766c93586fe0d9cdb415de30e23b384a9e4 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 25 Mar 2025 11:12:19 +0000
Subject: [PATCH 08/18] clean up formatting and underscore unused variables

---
 workflows/seqinspector.nf | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 5f3e4e6..c26f9a9 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -150,14 +150,14 @@ workflow SEQINSPECTOR {
         Channel.fromPath(params.multiqc_logo, checkIfExists: true) :
         Channel.empty()
 
-    summary_params                        = paramsSummaryMap(
+    summary_params = paramsSummaryMap(
         workflow, parameters_schema: "nextflow_schema.json")
-    ch_workflow_summary                   = Channel.value(
+    ch_workflow_summary = Channel.value(
         paramsSummaryMultiqc(summary_params))
     ch_multiqc_custom_methods_description = params.multiqc_methods_description ?
         file(params.multiqc_methods_description, checkIfExists: true) :
         file("$projectDir/assets/methods_description_template.yml", checkIfExists: true)
-    ch_methods_description                = Channel.value(
+    ch_methods_description = Channel.value(
         methodsDescriptionText(ch_multiqc_custom_methods_description))
 
     ch_multiqc_extra_files = ch_multiqc_extra_files.mix(
@@ -172,7 +172,7 @@ workflow SEQINSPECTOR {
 
     MULTIQC_GLOBAL (
         ch_multiqc_files
-            .map { meta, file -> file }
+            .map { _meta, file -> file }
             .mix(ch_multiqc_extra_files)
             .collect(),
         ch_multiqc_config.toList(),
@@ -183,7 +183,7 @@ workflow SEQINSPECTOR {
     )
 
     ch_tags = ch_multiqc_files
-        .map { meta, sample -> meta.tags }
+        .map { meta, _sample -> meta.tags }
         .flatten()
         .unique()
 
@@ -193,13 +193,13 @@ workflow SEQINSPECTOR {
     // Group samples by tag
     tagged_mqc_files = ch_tags
         .combine(ch_multiqc_files)
-        .filter { sample_tag, meta, sample -> sample_tag in meta.tags }
-        .map { sample_tag, meta, sample -> [sample_tag, sample] }
+        .filter { sample_tag, meta, _sample -> sample_tag in meta.tags }
+        .map { sample_tag, _meta, sample -> [sample_tag, sample] }
         .mix(multiqc_extra_files_per_tag)
         .groupTuple()
         .tap { mqc_by_tag }
         .collectFile {
-            sample_tag, samples ->
+            sample_tag, _samples ->
             def prefix_tag = "[TAG:${sample_tag}]"
             [
                 "${prefix_tag}_multiqc_extra_config.yml",
@@ -212,7 +212,7 @@ workflow SEQINSPECTOR {
         }
         .map { file -> [ (file =~ /\[TAG:(.+)\]/)[0][1], file ] }
         .join(mqc_by_tag)
-        .multiMap { sample_tag, config, samples ->
+        .multiMap { _sample_tag, config, samples ->
             samples_per_tag: samples
             config: config
         }

From 4d3a70ff709cc1d76b917c980dbc7f87f9b9d3ac Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 25 Mar 2025 11:52:45 +0000
Subject: [PATCH 09/18] use module binary instead of supplying script as
 process input

---
 modules/local/rundirparser/main.nf                             | 3 +--
 .../local/rundirparser/{ => resources/usr/bin}/rundirparser.py | 2 +-
 nextflow.config                                                | 3 +++
 workflows/seqinspector.nf                                      | 2 +-
 4 files changed, 6 insertions(+), 4 deletions(-)
 rename modules/local/rundirparser/{ => resources/usr/bin}/rundirparser.py (98%)
 mode change 100644 => 100755

diff --git a/modules/local/rundirparser/main.nf b/modules/local/rundirparser/main.nf
index 3c9206a..86591fb 100644
--- a/modules/local/rundirparser/main.nf
+++ b/modules/local/rundirparser/main.nf
@@ -9,7 +9,6 @@ process RUNDIRPARSER {
 
     input:
     tuple val(joint_meta), path(rundir)
-    path(parser_script)
 
     output:
     tuple val(joint_meta), path("*_mqc.*"), emit: multiqc
@@ -22,7 +21,7 @@ process RUNDIRPARSER {
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${rundir.baseName}"
     """
-    python ${parser_script} ${rundir}
+    rundirparser.py ${rundir}
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
diff --git a/modules/local/rundirparser/rundirparser.py b/modules/local/rundirparser/resources/usr/bin/rundirparser.py
old mode 100644
new mode 100755
similarity index 98%
rename from modules/local/rundirparser/rundirparser.py
rename to modules/local/rundirparser/resources/usr/bin/rundirparser.py
index 0820d4e..6a965f9
--- a/modules/local/rundirparser/rundirparser.py
+++ b/modules/local/rundirparser/resources/usr/bin/rundirparser.py
@@ -1,4 +1,4 @@
-# rundirparser.py
+#!/usr/bin/env python
 import sys
 import yaml
 
diff --git a/nextflow.config b/nextflow.config
index bb1cb27..caefca9 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -6,6 +6,9 @@
 ----------------------------------------------------------------------------------------
 */
 
+// Enable use of module binaries for e.g. module specific Python scripts
+nextflow.enable.moduleBinaries = true
+
 // Global default params, used in configs
 params {
 
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index c26f9a9..ea26529 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -58,7 +58,7 @@ workflow SEQINSPECTOR {
                 [new_meta, rundir]
             }
 
-        RUNDIRPARSER(ch_rundir, "${projectDir}/modules/local/rundirparser/rundirparser.py")
+        RUNDIRPARSER( ch_rundir )
         ch_multiqc_files = ch_multiqc_files.mix(RUNDIRPARSER.out.multiqc.first())
         ch_versions = ch_versions.mix(RUNDIRPARSER.out.versions.first())
     }

From 137629a798fc2fcf728e6527f287d4ac1cd32a30 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 25 Mar 2025 14:23:10 +0000
Subject: [PATCH 10/18] add all multiqc files to channel, not just first

---
 workflows/seqinspector.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index ea26529..d0af814 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -59,7 +59,7 @@ workflow SEQINSPECTOR {
             }
 
         RUNDIRPARSER( ch_rundir )
-        ch_multiqc_files = ch_multiqc_files.mix(RUNDIRPARSER.out.multiqc.first())
+        ch_multiqc_files = ch_multiqc_files.mix(RUNDIRPARSER.out.multiqc)
         ch_versions = ch_versions.mix(RUNDIRPARSER.out.versions.first())
     }
 

From 82d285a495bba34e99cbec9774c0b61ec6a454f7 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Tue, 25 Mar 2025 15:02:34 +0000
Subject: [PATCH 11/18] extend suffix to differentiate from other _mqc files

---
 modules/local/rundirparser/main.nf                           | 2 +-
 modules/local/rundirparser/resources/usr/bin/rundirparser.py | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/modules/local/rundirparser/main.nf b/modules/local/rundirparser/main.nf
index 86591fb..8c18b8a 100644
--- a/modules/local/rundirparser/main.nf
+++ b/modules/local/rundirparser/main.nf
@@ -11,7 +11,7 @@ process RUNDIRPARSER {
     tuple val(joint_meta), path(rundir)
 
     output:
-    tuple val(joint_meta), path("*_mqc.*"), emit: multiqc
+    tuple val(joint_meta), path("*_rundir_mqc.*"), emit: multiqc
     path "versions.yml",                    emit: versions
 
     when:
diff --git a/modules/local/rundirparser/resources/usr/bin/rundirparser.py b/modules/local/rundirparser/resources/usr/bin/rundirparser.py
index 6a965f9..9e08887 100755
--- a/modules/local/rundirparser/resources/usr/bin/rundirparser.py
+++ b/modules/local/rundirparser/resources/usr/bin/rundirparser.py
@@ -50,7 +50,7 @@ def parse_rundir(rundir):
 
     contents = yml_contents + tsv_contents
 
-    with open(f"{rundir}_mqc.txt", "w") as f:
+    with open(f"{rundir}_rundir_mqc.txt", "w") as f:
         f.write(contents)
 
 

From 70cacab7eb29a361f01387c7ce40c376e7463dbe Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Wed, 26 Mar 2025 08:49:46 +0000
Subject: [PATCH 12/18] give mqc outputs the same name so they will be merged
 automatically in the multiqc report generation, make function take output
 name as cmd parameter

---
 modules/local/rundirparser/main.nf               | 16 ++++++----------
 .../resources/usr/bin/rundirparser.py            |  7 ++++---
 2 files changed, 10 insertions(+), 13 deletions(-)

diff --git a/modules/local/rundirparser/main.nf b/modules/local/rundirparser/main.nf
index 8c18b8a..fe12323 100644
--- a/modules/local/rundirparser/main.nf
+++ b/modules/local/rundirparser/main.nf
@@ -11,17 +11,17 @@ process RUNDIRPARSER {
     tuple val(joint_meta), path(rundir)
 
     output:
-    tuple val(joint_meta), path("*_rundir_mqc.*"), emit: multiqc
+    tuple val(joint_meta), path("*_mqc.*"), emit: multiqc
     path "versions.yml",                    emit: versions
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
-    def args = task.ext.args ?: ''
-    def prefix = task.ext.prefix ?: "${rundir.baseName}"
+    // def args = task.ext.args ?: ''
+    // def prefix = task.ext.prefix ?: "${rundir.baseName}"
     """
-    rundirparser.py ${rundir}
+    rundirparser.py ${rundir} ${moduleDir.baseName}_mqc.txt
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
@@ -31,12 +31,8 @@ process RUNDIRPARSER {
     """
 
     stub:
-    def args = task.ext.args ?: ''
-    def prefix = task.ext.prefix ?: "${rundir.baseName}"
-    // TODO nf-core: A stub section should mimic the execution of the original module as best as possible
-    //               Have a look at the following examples:
-    //               Simple example: https://github.com/nf-core/modules/blob/818474a292b4860ae8ff88e149fbcda68814114d/modules/nf-core/bcftools/annotate/main.nf#L47-L63
-    //               Complex example: https://github.com/nf-core/modules/blob/818474a292b4860ae8ff88e149fbcda68814114d/modules/nf-core/bedtools/split/main.nf#L38-L54
+    // def args = task.ext.args ?: ''
+    // def prefix = task.ext.prefix ?: "${rundir.baseName}"
     """
     touch rundir_mqc.txt
 
diff --git a/modules/local/rundirparser/resources/usr/bin/rundirparser.py b/modules/local/rundirparser/resources/usr/bin/rundirparser.py
index 9e08887..68e91df 100755
--- a/modules/local/rundirparser/resources/usr/bin/rundirparser.py
+++ b/modules/local/rundirparser/resources/usr/bin/rundirparser.py
@@ -3,7 +3,7 @@
 import yaml
 
 
-def parse_rundir(rundir):
+def parse_rundir(rundir, outname):
     # Dummy implementation, replace with actual logic
 
     yml_contents = """# plot_type: 'table'
@@ -50,13 +50,14 @@ def parse_rundir(rundir):
 
     contents = yml_contents + tsv_contents
 
-    with open(f"{rundir}_rundir_mqc.txt", "w") as f:
+    with open(outname, "w") as f:
         f.write(contents)
 
 
 def main():
     rundir = sys.argv[1]
-    parse_rundir(rundir)
+    outname = sys.argv[2]
+    parse_rundir(rundir, outname)
 
 
 if __name__ == "__main__":

From f0999e8b778f5ac51169489bff9ae6860a68b08a Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Wed, 26 Mar 2025 09:07:48 +0000
Subject: [PATCH 13/18] actually, let the script differentiate between seq
 platforms and name the outfile accordingly, for proper downstream grouping

---
 modules/local/rundirparser/main.nf                 |  2 +-
 .../rundirparser/resources/usr/bin/rundirparser.py | 14 +++++++++++---
 2 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/modules/local/rundirparser/main.nf b/modules/local/rundirparser/main.nf
index fe12323..bc96977 100644
--- a/modules/local/rundirparser/main.nf
+++ b/modules/local/rundirparser/main.nf
@@ -21,7 +21,7 @@ process RUNDIRPARSER {
     // def args = task.ext.args ?: ''
     // def prefix = task.ext.prefix ?: "${rundir.baseName}"
     """
-    rundirparser.py ${rundir} ${moduleDir.baseName}_mqc.txt
+    rundirparser.py ${rundir}
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
diff --git a/modules/local/rundirparser/resources/usr/bin/rundirparser.py b/modules/local/rundirparser/resources/usr/bin/rundirparser.py
index 68e91df..b8db68d 100755
--- a/modules/local/rundirparser/resources/usr/bin/rundirparser.py
+++ b/modules/local/rundirparser/resources/usr/bin/rundirparser.py
@@ -3,9 +3,11 @@
 import yaml
 
 
-def parse_rundir(rundir, outname):
+def parse_rundir(rundir):
     # Dummy implementation, replace with actual logic
 
+    sequencing_platform = None
+
     yml_contents = """# plot_type: 'table'
 # section_name: 'rundir stats'
 # description: 'dummy rundir stats'
@@ -50,14 +52,20 @@ def parse_rundir(rundir, outname):
 
     contents = yml_contents + tsv_contents
 
+    """
+    File names should be unique between sequencing platforms, but otherwise identical
+    so multiple rundirs of the same platform will be written to the same table
+    in the MultiQC report.
+    """
+    outname = f"{sequencing_platform or 'rundirparser'}_mqc.txt"
+
     with open(outname, "w") as f:
         f.write(contents)
 
 
 def main():
     rundir = sys.argv[1]
-    outname = sys.argv[2]
-    parse_rundir(rundir, outname)
+    parse_rundir(rundir)
 
 
 if __name__ == "__main__":

From e38676ded0ec046888c9957415f5cd74531cc625 Mon Sep 17 00:00:00 2001
From: kedhammar <alfred.kedhammar@scilifelab.se>
Date: Wed, 26 Mar 2025 10:36:55 +0100
Subject: [PATCH 14/18] editorconfig

---
 modules/local/rundirparser/tests/main.nf.test | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/modules/local/rundirparser/tests/main.nf.test b/modules/local/rundirparser/tests/main.nf.test
index c1e8440..0dc321d 100644
--- a/modules/local/rundirparser/tests/main.nf.test
+++ b/modules/local/rundirparser/tests/main.nf.test
@@ -22,7 +22,7 @@ nextflow_process {
             process {
                 """
                 // TODO nf-core: define inputs of the process here. Example:
-                
+
                 input[0] = [
                     [ id:'test', single_end:false ], // meta map
                     file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.sorted.bam', checkIfExists: true),
@@ -51,7 +51,7 @@ nextflow_process {
             process {
                 """
                 // TODO nf-core: define inputs of the process here. Example:
-                
+
                 input[0] = [
                     [ id:'test', single_end:false ], // meta map
                     file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.sorted.bam', checkIfExists: true),

From 7873d53d7b1db287f38ea6fbd4e2a221724175ba Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Wed, 26 Mar 2025 13:16:28 +0000
Subject: [PATCH 15/18] fix quotes and make rundirparser publish results with
 individual names for test consistency

---
 conf/modules.config | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index 4a653ed..60e7895 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -18,11 +18,11 @@ process {
         saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
     ]
 
-    withName: SEQTK_SAMPLE {
+    withName: 'SEQTK_SAMPLE' {
         ext.args = '-s100'
     }
 
-    withName: FASTQC {
+    withName: 'FASTQC' {
         ext.args = '--quiet'
     }
 
@@ -35,6 +35,14 @@ process {
         ]
     }
 
+    withName: 'RUNDIRPARSER' {
+        publishDir = [
+            path: { "${params.outdir}/rundirparser" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : "${dir_meta.dirname}_$filename" }
+        ]
+    }
+
     withName: 'MULTIQC_GLOBAL' {
         ext.args   = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
         publishDir = [

From d45ee52aa7f4d3c56541039e1c7eecf1b88f62f4 Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Wed, 26 Mar 2025 13:17:09 +0000
Subject: [PATCH 16/18] clean up meta object names

---
 modules/local/rundirparser/main.nf | 10 +++-------
 workflows/seqinspector.nf          |  4 ++--
 2 files changed, 5 insertions(+), 9 deletions(-)

diff --git a/modules/local/rundirparser/main.nf b/modules/local/rundirparser/main.nf
index bc96977..95d9719 100644
--- a/modules/local/rundirparser/main.nf
+++ b/modules/local/rundirparser/main.nf
@@ -1,5 +1,5 @@
 process RUNDIRPARSER {
-    tag "$rundir.baseName"
+    tag "$rundir.simpleName"
     label 'process_single'
 
     conda "${moduleDir}/environment.yml"
@@ -8,18 +8,16 @@ process RUNDIRPARSER {
         'community.wave.seqera.io/library/pip_pyyaml:c2ecf27a7f63796e' }"
 
     input:
-    tuple val(joint_meta), path(rundir)
+    tuple val(dir_meta), path(rundir)
 
     output:
-    tuple val(joint_meta), path("*_mqc.*"), emit: multiqc
+    tuple val(dir_meta), path("*_mqc.*"), emit: multiqc
     path "versions.yml",                    emit: versions
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
-    // def args = task.ext.args ?: ''
-    // def prefix = task.ext.prefix ?: "${rundir.baseName}"
     """
     rundirparser.py ${rundir}
 
@@ -31,8 +29,6 @@ process RUNDIRPARSER {
     """
 
     stub:
-    // def args = task.ext.args ?: ''
-    // def prefix = task.ext.prefix ?: "${rundir.baseName}"
     """
     touch rundir_mqc.txt
 
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index 9f94c11..ff92239 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -53,9 +53,9 @@ workflow SEQINSPECTOR {
                 // Collect all tags across all samples with this rundir
                 def all_tags = metas.collect { it.tags }.flatten().unique()
                 // Create a new meta object with the merged tags
-                def new_meta = [tags: all_tags]
+                def dir_meta = [tags: all_tags, dirname: rundir.simpleName]
                 // Return the new structure
-                [new_meta, rundir]
+                [dir_meta, rundir]
             }
 
         RUNDIRPARSER( ch_rundir )

From 9c66ff89b1aa83603bc082073215ff020ef506bb Mon Sep 17 00:00:00 2001
From: Alfred Kedhammar <alfred.kedhammar@scilifelab.se>
Date: Wed, 26 Mar 2025 13:37:21 +0000
Subject: [PATCH 17/18] docs and formatting

---
 conf/modules.config                |  3 +++
 modules/local/rundirparser/main.nf |  2 +-
 workflows/seqinspector.nf          | 17 ++++++++++++-----
 3 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index 60e7895..9327925 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -39,6 +39,9 @@ process {
         publishDir = [
             path: { "${params.outdir}/rundirparser" },
             mode: params.publish_dir_mode,
+            // The process _mqc.txt outputs should have identical names for the same sequencing platforms
+            // in order to be grouped together in the MultiQC report, but here we need to enforce uniqueness
+            // to avoid overwriting results in the publishDir.
             saveAs: { filename -> filename.equals('versions.yml') ? null : "${dir_meta.dirname}_$filename" }
         ]
     }
diff --git a/modules/local/rundirparser/main.nf b/modules/local/rundirparser/main.nf
index 95d9719..335acef 100644
--- a/modules/local/rundirparser/main.nf
+++ b/modules/local/rundirparser/main.nf
@@ -12,7 +12,7 @@ process RUNDIRPARSER {
 
     output:
     tuple val(dir_meta), path("*_mqc.*"), emit: multiqc
-    path "versions.yml",                    emit: versions
+    path "versions.yml",                  emit: versions
 
     when:
     task.ext.when == null || task.ext.when
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
index ff92239..0472ab3 100644
--- a/workflows/seqinspector.nf
+++ b/workflows/seqinspector.nf
@@ -44,21 +44,28 @@ workflow SEQINSPECTOR {
     //
     if (!("rundirparser" in skip_tools)) {
 
+        // From samplesheet channel serving (sampleMetaObj, sampleReadsPath) tuples:
+        // --> Create new rundir channel serving (rundirMetaObj, rundirPath) tuples
         ch_rundir = ch_samplesheet
-            // Group by rundir to merge tags from samples with the same rundir
+            // Group by rundir
             .map { meta, _reads -> [meta.rundir, meta] }
             .groupTuple()
-            // Create a new meta object with merged tags for each unique rundir
+            // From all meta objects associated with a given rundir...
             .map { rundir, metas ->
-                // Collect all tags across all samples with this rundir
+                // Collect all unique tags into a list
                 def all_tags = metas.collect { it.tags }.flatten().unique()
-                // Create a new meta object with the merged tags
+                // Create a new meta object whose attributes are...
+                //  1. tags: The list of merged tags, used for grouping MultiQC reports
+                //  2. dirname: The simple name of the rundir, used for setting unique output names in publishDir
                 def dir_meta = [tags: all_tags, dirname: rundir.simpleName]
-                // Return the new structure
+                // Return the new structure, to...
+                //  1. Feed into rundir specific processes
+                //  2. Mix with the ch_multiqc_files channel downstream
                 [dir_meta, rundir]
             }
 
         RUNDIRPARSER( ch_rundir )
+
         ch_multiqc_files = ch_multiqc_files.mix(RUNDIRPARSER.out.multiqc)
         ch_versions = ch_versions.mix(RUNDIRPARSER.out.versions.first())
     }

From fabdac5825980f03fb30b9f695b758d8ffcb93fd Mon Sep 17 00:00:00 2001
From: matrulda <matilda.aslin@medsci.uu.se>
Date: Wed, 26 Mar 2025 16:53:08 +0100
Subject: [PATCH 18/18] Add parse_illumina.py

---
 modules/local/rundirparser/main.nf            |  6 +-
 .../resources/usr/bin/parse_illumina.py       | 95 +++++++++++++++++++
 2 files changed, 99 insertions(+), 2 deletions(-)
 create mode 100755 modules/local/rundirparser/resources/usr/bin/parse_illumina.py

diff --git a/modules/local/rundirparser/main.nf b/modules/local/rundirparser/main.nf
index 335acef..c702e57 100644
--- a/modules/local/rundirparser/main.nf
+++ b/modules/local/rundirparser/main.nf
@@ -4,8 +4,8 @@ process RUNDIRPARSER {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/ad/ad2bcce70756f81c07c7e2ffd9b66213bf48ace786466395ac3a402840df2ffb/data' :
-        'community.wave.seqera.io/library/pip_pyyaml:c2ecf27a7f63796e' }"
+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/41/412df2cdcf04e0a12971ba61b12cacaa5a49705442afe99ad96668bebbb8f880/data' :
+        'community.wave.seqera.io/library/pip_pyyaml_xmltodict:a4e48bd1ab4b6a53' }"
 
     input:
     tuple val(dir_meta), path(rundir)
@@ -19,7 +19,9 @@ process RUNDIRPARSER {
 
     script:
     """
+    # TODO: check what kind of seq platfrom to decide which script to use
     rundirparser.py ${rundir}
+    parse_illumina.py ${rundir}
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
diff --git a/modules/local/rundirparser/resources/usr/bin/parse_illumina.py b/modules/local/rundirparser/resources/usr/bin/parse_illumina.py
new file mode 100755
index 0000000..5d210ab
--- /dev/null
+++ b/modules/local/rundirparser/resources/usr/bin/parse_illumina.py
@@ -0,0 +1,95 @@
+#!/usr/bin/env python3
+
+import os
+import yaml
+import sys
+from datetime import datetime
+from pathlib import Path
+import xmltodict
+
+
+def read_run_parameters(directory):
+    alt_1 = directory / "runParameters.xml"
+    alt_2 = directory / "RunParameters.xml"
+    if alt_1.exists():
+        with open(alt_1) as f:
+            return xmltodict.parse(f.read())
+    elif alt_2.exists():
+        with open(alt_2) as f:
+            return xmltodict.parse(f.read())
+    else:
+        raise Exception("[Rr]unParameters.xml not found!")
+
+
+def find(d, tag):
+    if isinstance(d, dict):
+        if tag in d:
+            yield d[tag]
+        for k, v in d.items():
+            if isinstance(v, dict):
+                yield from find(v, tag)
+            if isinstance(v, list):
+                for i in v:
+                    yield from find(i, tag)
+
+
+def construct_data(run_parameters):
+    run_parameters_tags = {
+        "RunId": "Run ID",
+        "RunID": "Run ID",
+        "InstrumentType": "Instrument type",
+        "ApplicationName": "Control software",
+        "Application": "Control software",
+        "ApplicationVersion": "Control software version",
+        "SystemSuiteVersion": "Control software version",
+        "Flowcell": "Flowcell type",
+        "FlowCellMode": "Flowcell type",
+        "ReagentKitVersion": "Reagent kit version",
+        "RTAVersion": "RTA Version",
+        "RtaVersion": "RTA Version",
+    }
+    data = {}
+    for k, v in run_parameters_tags.items():
+        for key, value in run_parameters_tags.items():
+            info = list(find(run_parameters, key))
+            if info:
+                data[value] = info[0]
+        return data
+
+
+def construct_multiqc_yaml(directory):
+
+    directory_name = directory.name
+    run_parameters = read_run_parameters(directory)
+
+    data = construct_data(run_parameters)
+
+    #TODO: MultiQC currently ignores the data in this yaml RUDE
+    metadata = {
+        "custom_data": {
+            "my_data_type": {
+                "id": "mqc_seq_metadata",
+                "section_name": "Sequencing instrument metadata",
+                "description": directory_name,
+                "plot_type": "table",
+                "pconfig": {
+                    "id": 'custom_table',
+                    "title": 'Custom Table',
+                    "no_headers": "true",
+                    },
+                "data": data,
+            }
+        }
+    }
+
+    return metadata
+
+
+if __name__ == "__main__":
+    rundir_path = Path(sys.argv[1])
+    output_file = "illumina_mqc.yml"
+
+    multiqc_yaml = construct_multiqc_yaml(rundir_path)
+
+    with open(output_file, "w") as f:
+        yaml.dump(multiqc_yaml, f)