Use research software taxonomy terms

kb/kb_test.go

@@ -203,6 +203,43 @@ func TestRailsHasTaxonomy(t *testing.T) {
 	}
 }
 
+func TestResearchToolTaxonomy(t *testing.T) {
+	base := loadKB(t)
+	want := map[string][]string{
+		"Jupyter":           {"role:application", "function:interactive-computing", "function:literate-programming", "technology:jupyter"},
+		"Quarto":            {"function:documentation", "function:literate-programming", "function:report-generation", "function:site-generation", "technology:quarto"},
+		"Nextflow":          {"role:orchestrator", "function:workflow-orchestration", "domain:research", "domain:scientific-computing", "technology:nextflow"},
+		"Snakemake":         {"role:orchestrator", "function:workflow-orchestration", "domain:research", "domain:scientific-computing", "technology:snakemake"},
+		"nf-core":           {"role:build-tool", "function:automation", "domain:bioinformatics", "domain:scientific-computing", "audience:researcher", "technology:nextflow"},
+		"nf-test":           {"role:testing-framework", "function:testing", "domain:scientific-computing", "audience:researcher", "technology:nextflow"},
+		"MultiQC":           {"role:cli-tool", "function:report-generation", "function:visualization", "domain:bioinformatics", "domain:scientific-computing", "audience:researcher"},
+		"Dockstore":         {"role:registry", "layer:infrastructure", "domain:scientific-computing", "audience:researcher"},
+		"DVC":               {"role:cli-tool", "function:data-provenance", "function:data-version-control", "domain:data-science", "audience:data-scientist", "audience:researcher"},
+		"BenchmarkTools.jl": {"role:testing-framework", "function:benchmarking", "domain:scientific-computing", "audience:researcher", "technology:julia"},
+		"Documenter.jl":     {"function:documentation", "function:site-generation", "technology:julia"},
+		"JuliaFormatter":    {"role:formatter", "technology:julia"},
+		"Runic":             {"role:formatter", "technology:julia"},
+		"Fortitude":         {"role:linter", "technology:fortran"},
+		"targets":           {"role:build-tool", "role:orchestrator", "function:workflow-orchestration", "domain:data-science", "domain:research", "domain:scientific-computing", "audience:data-scientist", "audience:researcher"},
+		"R Markdown":        {"function:documentation", "function:literate-programming", "function:report-generation"},
+		"knitr":             {"function:documentation", "function:literate-programming", "function:report-generation"},
+	}
+	for name, tags := range want {
+		tool := base.ByName[name]
+		if tool == nil {
+			t.Errorf("%s not found in KB", name)
+			continue
+		}
+		got := slices.Clone(tool.Taxonomy.Tags())
+		wantTags := slices.Clone(tags)
+		sort.Strings(got)
+		sort.Strings(wantTags)
+		if !slices.Equal(got, wantTags) {
+			t.Errorf("%s taxonomy = %v, want %v", name, got, wantTags)
+		}
+	}
+}
+
 func TestPriorityNicheLanguagesHaveSinks(t *testing.T) {
 	base := loadKB(t)
 	for _, name := range []string{

kb/testdata/oss-taxonomy-terms.txt

@@ -12,6 +12,7 @@ audience:security-professional
 audience:student
 audience:sysadmin
 audience:writer
+domain:bioinformatics
 domain:blockchain
 domain:cloud-computing
 domain:content-management
@@ -25,11 +26,13 @@ domain:finance
 domain:game-development
 domain:geospatial
 domain:healthcare
+domain:high-performance-computing
 domain:machine-learning
 domain:mobile-development
 domain:multimedia
 domain:natural-language-processing
 domain:networking
+domain:research
 domain:robotics
 domain:scientific-computing
 domain:security
@@ -49,7 +52,10 @@ function:configuration
 function:connection-pooling
 function:containerization
 function:coverage
+function:data-analysis
 function:data-mapping
+function:data-provenance
+function:data-version-control
 function:database-management
 function:database-migrations
 function:dependency-injection
@@ -65,8 +71,10 @@ function:graph-database
 function:gui-toolkit
 function:http-client
 function:image-processing
+function:interactive-computing
 function:internationalization
 function:language-server
+function:literate-programming
 function:logging
 function:messaging
 function:mocking
@@ -78,6 +86,7 @@ function:parsing
 function:payments
 function:process-execution
 function:release-management
+function:report-generation
 function:routing
 function:rpc
 function:runtime-management
@@ -99,9 +108,11 @@ function:text-processing
 function:tui
 function:type-checking
 function:validation
+function:version-control
 function:visualization
 function:webhooks
 function:websocket
+function:workflow-orchestration
 layer:application-layer
 layer:backend
 layer:data-layer
@@ -131,6 +142,7 @@ role:native-extension
 role:orchestrator
 role:package-manager
 role:plugin
+role:registry
 role:runtime
 role:sdk
 role:server
@@ -156,6 +168,7 @@ technology:express
 technology:fastapi
 technology:flask
 technology:flutter
+technology:fortran
 technology:git
 technology:github-actions
 technology:go
@@ -166,12 +179,15 @@ technology:java
 technology:javascript
 technology:jenkins
 technology:jquery
+technology:julia
+technology:jupyter
 technology:kotlin
 technology:kubernetes
 technology:laravel
 technology:linux
 technology:mongodb
 technology:mysql
+technology:nextflow
 technology:nextjs
 technology:nginx
 technology:nix
@@ -180,6 +196,7 @@ technology:objective-c
 technology:php
 technology:postgresql
 technology:python
+technology:quarto
 technology:r
 technology:rails
 technology:react
@@ -188,6 +205,7 @@ technology:ruby
 technology:rust
 technology:sass
 technology:scala
+technology:snakemake
 technology:spring-boot
 technology:sqlite
 technology:svelte

knowledge/_shared/dockstore.toml

@@ -13,8 +13,7 @@ files = [".dockstore.yml", ".dockstore.yaml", ".github/.dockstore.yml", ".github
 files = [".dockstore.yml", ".dockstore.yaml", ".github/.dockstore.yml", ".github/.dockstore.yaml"]
 
 [taxonomy]
-role = ["cli-tool"]
+role = ["registry"]
 layer = ["infrastructure"]
-function = ["deployment"]
 domain = ["scientific-computing"]
 audience = ["researcher"]

knowledge/_shared/dvc.toml

@@ -20,6 +20,6 @@ lockfile = "dvc.lock"
 
 [taxonomy]
 role = ["cli-tool"]
-function = ["file-management"]
+function = ["data-provenance", "data-version-control"]
 domain = ["data-science"]
 audience = ["data-scientist", "researcher"]

knowledge/_shared/jupyter.toml

@@ -20,3 +20,5 @@ files = ["jupyter_server_config.py", "jupyter_notebook_config.py", "jupyter_lab_
 
 [taxonomy]
 role = ["application"]
+function = ["interactive-computing", "literate-programming"]
+technology = ["jupyter"]

knowledge/_shared/multiqc.toml

@@ -18,6 +18,6 @@ files = ["multiqc_config.yml", "multiqc_config.yaml", ".multiqc_config.yml", ".m
 
 [taxonomy]
 role = ["cli-tool"]
-function = ["visualization"]
-domain = ["scientific-computing"]
+function = ["report-generation", "visualization"]
+domain = ["bioinformatics", "scientific-computing"]
 audience = ["researcher"]

knowledge/_shared/nextflow.toml

@@ -17,5 +17,6 @@ files = ["nextflow.config"]
 
 [taxonomy]
 role = ["orchestrator"]
-function = ["automation"]
-domain = ["scientific-computing"]
+function = ["workflow-orchestration"]
+domain = ["research", "scientific-computing"]
+technology = ["nextflow"]

knowledge/_shared/nf-core.toml

@@ -20,5 +20,6 @@ files = [".nf-core.yml", ".nf-core.yaml"]
 [taxonomy]
 role = ["build-tool"]
 function = ["automation"]
-domain = ["scientific-computing"]
+domain = ["bioinformatics", "scientific-computing"]
 audience = ["researcher"]
+technology = ["nextflow"]

knowledge/_shared/nf-test.toml

@@ -21,3 +21,4 @@ role = ["testing-framework"]
 function = ["testing"]
 domain = ["scientific-computing"]
 audience = ["researcher"]
+technology = ["nextflow"]

knowledge/_shared/quarto.toml

@@ -19,4 +19,5 @@ alternatives = ["quarto preview"]
 files = ["_quarto.yml", "_quarto.yaml"]
 
 [taxonomy]
-function = ["documentation", "site-generation"]
+function = ["documentation", "literate-programming", "report-generation", "site-generation"]
+technology = ["quarto"]

knowledge/_shared/snakemake.toml

@@ -19,5 +19,6 @@ files = ["Snakefile", "**/Snakefile", "*.smk", "**/*.smk"]
 
 [taxonomy]
 role = ["orchestrator"]
-function = ["automation"]
-domain = ["scientific-computing"]
+function = ["workflow-orchestration"]
+domain = ["research", "scientific-computing"]
+technology = ["snakemake"]

knowledge/fortran/fortitude.toml

@@ -24,3 +24,4 @@ files = ["fortitude.toml", ".fortitude.toml", "fpm.toml", "pyproject.toml"]
 
 [taxonomy]
 role = ["linter"]
+technology = ["fortran"]

knowledge/julia/benchmarktools.toml

@@ -19,3 +19,4 @@ role = ["testing-framework"]
 function = ["benchmarking"]
 domain = ["scientific-computing"]
 audience = ["researcher"]
+technology = ["julia"]

knowledge/julia/documenter.toml

@@ -22,3 +22,4 @@ files = ["docs/Project.toml", "docs/make.jl"]
 
 [taxonomy]
 function = ["documentation", "site-generation"]
+technology = ["julia"]

knowledge/julia/juliaformatter.toml

@@ -20,3 +20,4 @@ files = [".JuliaFormatter.toml"]
 
 [taxonomy]
 role = ["formatter"]
+technology = ["julia"]

knowledge/julia/runic.toml

@@ -13,3 +13,4 @@ ecosystems = ["julia"]
 
 [taxonomy]
 role = ["formatter"]
+technology = ["julia"]

knowledge/r/knitr.toml

@@ -14,4 +14,4 @@ ecosystems = ["r"]
 "DESCRIPTION" = ["VignetteBuilder: knitr"]
 
 [taxonomy]
-function = ["documentation"]
+function = ["documentation", "literate-programming", "report-generation"]

knowledge/r/rmarkdown.toml

@@ -13,4 +13,4 @@ dev_dependencies = ["rmarkdown"]
 ecosystems = ["r"]
 
 [taxonomy]
-function = ["documentation"]
+function = ["documentation", "literate-programming", "report-generation"]

knowledge/r/targets.toml

@@ -21,6 +21,6 @@ files = ["_targets.R"]
 
 [taxonomy]
 role = ["build-tool", "orchestrator"]
-function = ["automation"]
-domain = ["data-science", "scientific-computing"]
+function = ["workflow-orchestration"]
+domain = ["data-science", "research", "scientific-computing"]
 audience = ["data-scientist", "researcher"]