FIX: tag collision warning

CHANGELOG.md

@@ -10,6 +10,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### `Fixed`
 
 - [#182](https://github.com/nf-core/seqinspector/pull/182) Keep modules diff to a minimum
+- [#183](https://github.com/nf-core/seqinspector/pull/183) Fix tag collision warning message that was actually printed for every tag
 
 ### `Changed`
 

docs/usage.md

@@ -61,6 +61,21 @@ sample4 path/to/run_dir/sample4_lane2_group3_r1.fq.gz         path/to/run_dir co
 
 Another [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline.
 
+### tags
+
+Tags can be used to group samples in special reports, for example in the MultiQC per tag report.
+They are optional and can be used for any purpose you like.
+For example, you could use them to group samples by experimental condition, or by sequencing run.
+Tags are meant to be case-sensitive and should be separated by a colon (`:`) if you want to use multiple tags for a sample.
+Some file systems are not case sensitive, e.g. on MacOS. We recommend precaution when using similar tags with different cases on such file systems.
+A warning will be displayed if you have multiple tags that only differ in case, but the pipeline will not stop and will run as normal.
+
+```bash
+WARN: Tag name collision: [lane1, Lane1, LANE1]
+WARN: Tag name collision: [group1, Group1]
+WARN: Tag name collision: [test, Test, TEST]
+```
+
 ## Running the pipeline
 
 A typical command for running the pipeline is as follows:

subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf

@@ -104,46 +104,34 @@ workflow PIPELINE_INITIALISATION {
         .toList()
         .size()
 
-    channel.fromList(samplesheetToList(input, "${projectDir}/assets/schema_input.json"))
+    ch_samplesheet = channel.fromList(samplesheetToList(input, "${projectDir}/assets/schema_input.json"))
         .toList()
         .flatMap { item -> item.withIndex().collect { entry, idx -> entry + "${idx + 1}" } }
         .map { meta, fastq_1, fastq_2, idx ->
             def tags = meta.tags ? meta.tags.tokenize(":") : []
             def pad_positions = [nr_samples.length(), 2].max()
             def zero_padded_idx = idx.padLeft(pad_positions, "0")
-            def updated_meta = meta + [id: "${meta.sample}_${zero_padded_idx}", tags: tags]
-            if (!fastq_2) {
-                return [
-                    updated_meta.id,
-                    updated_meta + [single_end: true],
-                    [fastq_1],
-                ]
-            }
-            else {
-                return [
-                    updated_meta.id,
-                    updated_meta + [single_end: false],
-                    [fastq_1, fastq_2],
-                ]
-            }
+            def new_meta = [id: "${meta.sample}_${zero_padded_idx}"]
+            return [
+                new_meta.id,
+                meta + [id: new_meta.id, tags: tags, single_end: fastq_2 ? false : true],
+                fastq_2 ? [fastq_1, fastq_2] : [fastq_1],
+            ]
         }
         .groupTuple()
-        .map { meta ->
-            validateInputSamplesheet(meta)
-        }
+        .map { meta -> validateInputSamplesheet(meta) }
         .transpose()
-        .set { ch_samplesheet }
 
     ch_samplesheet
         .map { meta, _fastqs ->
-            meta.tags
+            [meta.tags]
         }
         .flatten()
         .unique()
-        .map { tag_name -> [tag_name.toLowerCase(), tag_name] }
+        .map { tag -> [tag.toLowerCase(), tag] }
         .groupTuple()
         .map { _tag_lowercase, tags ->
-            if (tags.size() == 1) {
+            if (tags.size() != 1) {
                 log.warn("Tag name collision: " + tags)
             }
         }

tests/MiSeq.nf.test.snap

@@ -699,11 +699,9 @@
                 "SAMPLE_PAIRED_END_1_01.bam:md5,ac811b20d56132f5e039b3e8fd217405",
                 "SAMPLE_PAIRED_END_2_02.bam:md5,57892fc4314e66e8e20de4f5d82f9b5d"
             ],
-            [
-                "WARN: Tag name collision: [Bpacificus]"
-            ]
+            "No warnings"
         ],
-        "timestamp": "2026-02-19T16:07:01.63849991",
+        "timestamp": "2026-02-26T16:06:35.381277259",
         "meta": {
             "nf-test": "0.9.4",
             "nextflow": "25.10.4"

tests/NovaSeq6000.nf.test

@@ -35,6 +35,12 @@ nextflow_pipeline {
             params: [
                 input : pipelines_testdata_base_path + 'seqinspector/testdata/NovaSeq6000/samplesheet_no_rundirs.csv'
             ]
+        ],
+        [
+            name: "NovaSeq6000 data test - tag collision",
+            params: [
+                input : pipelines_testdata_base_path + 'seqinspector/testdata/NovaSeq6000/samplesheet_tag_collision.csv'
+            ]
         ]
     ]