Merge pull request #25 from phac-nml/dev

Update to version 0.2.2

CHANGELOG.md

@@ -3,6 +3,12 @@
 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).
 
+## [0.2.2] - 2024/09/13
+
+### `Changed`
+
+- Updated FILTER_QUERY to process query IDs from a file rather than passing them as a string, preventing errors caused by long argument strings [PR24](https://github.com/phac-nml/gasnomenclature/pull/24)
+
 ## [0.2.1] - 2024/09/10
 
 ### `Changed`
@@ -29,3 +35,5 @@ Initial release of the Genomic Address Nomenclature pipeline to be used to assig
 
 [0.1.0]: https://github.com/phac-nml/gasnomenclature/releases/tag/0.1.0
 [0.2.0]: https://github.com/phac-nml/gasnomenclature/releases/tag/0.2.0
+[0.2.1]: https://github.com/phac-nml/gasnomenclature/releases/tag/0.2.1
+[0.2.2]: https://github.com/phac-nml/gasnomenclature/releases/tag/0.2.2

modules/local/filter_query/main.nf

@@ -22,14 +22,12 @@ process FILTER_QUERY {
     def out_delimiter = out_format == "tsv" ? "\t" : (out_format == "csv" ? "," : out_format)
     def out_extension = out_format == "tsv" ? 'tsv' : 'csv'
 
-    // Join the query IDs in the correct csvtk filter2 required format
-    def queryID = query_ids.collect { id -> "\$id == \"${id}\"" }.join(" || ")
-
     """
     # Filter the query samples only; keep only the 'id' and 'address' columns
-    csvtk filter2 \\
+    csvtk grep \\
         ${addresses} \\
-        --filter '$queryID' \\
+        -f 1 \\
+        -P ${query_ids} \\
         --delimiter "${delimiter}" \\
         --out-delimiter "${out_delimiter}" | \\
     csvtk cut -f id,address > ${outputFile}.${out_extension}
@@ -39,7 +37,4 @@ process FILTER_QUERY {
         csvtk: \$(echo \$( csvtk version | sed -e "s/csvtk v//g" ))
     END_VERSIONS
     """
-
-
 }
-

nextflow.config

@@ -222,7 +222,7 @@ manifest {
     description     = """Gas Nomenclature assignment pipeline"""
     mainScript      = 'main.nf'
     nextflowVersion = '!>=23.04.0'
-    version         = '0.2.1'
+    version         = '0.2.2'
     doi             = ''
     defaultBranch   = 'main'
 }

workflows/gas_nomenclature.nf

@@ -144,7 +144,7 @@ workflow GAS_NOMENCLATURE {
     ch_versions = ch_versions.mix(called_data.versions)
 
     // Filter the new queried samples and addresses into a CSV/JSON file for the IRIDANext plug in
-    query_ids = profiles.query.collect { it[0].id }
+    query_ids = profiles.query.collectFile { it[0].id + '\n' }
 
     new_addresses = FILTER_QUERY(query_ids, called_data.distances, "tsv", "csv")
     ch_versions = ch_versions.mix(new_addresses.versions)