Benjamin Admin
c13aa9183a
Extends Method C: for each unknown narrative token that pattern text names, suggest
the keyword_dictionary tag = the RequiredComponentTags shared by the naming
patterns (ranked by frequency, kept only when shared by >=40% of them, top 3).
Surfaces real dictionary gaps like "zwischenkreis" -> stored_energy and
"updates" -> has_software, which close coverage without hand-editing the dict.
Two precision fixes to Method C while here:
- patternsMentioning now matches WHOLE WORDS, not substrings — substring matching
flagged fragments like "stehen" inside "entstehen" and produced nonsensical
tag suggestions.
- a token is only proposed with a tag if one is shared by >=40% of its naming
patterns, so diffuse common verbs (spread across categories) drop out.
Wired into iace-audit propose -> audit-reports/vocab.{md,json}. Residual
common-verb noise is left to the human/LLM filter rather than a hand-grown
stopword list. Type 4 (coverage blind spots) + P3 (pin accepted proposals into a
GT case) remain for slice 6.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
37 lines
1.2 KiB
Go
37 lines
1.2 KiB
Go
package audit
|
|
|
|
import (
|
|
"testing"
|
|
|
|
"github.com/breakpilot/ai-compliance-sdk/internal/iace"
|
|
)
|
|
|
|
func TestSuggestTagsFor_RanksSharedRequiredTags(t *testing.T) {
|
|
byID := map[string]iace.HazardPattern{
|
|
"P1": {ID: "P1", RequiredComponentTags: []string{"backflow_risk", "dom_warewashing"}},
|
|
"P2": {ID: "P2", RequiredComponentTags: []string{"backflow_risk"}},
|
|
"P3": {ID: "P3", RequiredComponentTags: []string{"sharp_edge"}},
|
|
}
|
|
got := suggestTagsFor([]string{"P1", "P2", "P3"}, byID)
|
|
if len(got) == 0 || got[0] != "backflow_risk" {
|
|
t.Fatalf("want backflow_risk ranked first (2 patterns), got %v", got)
|
|
}
|
|
}
|
|
|
|
func TestSuggestTagsFor_TopThreeStableAlpha(t *testing.T) {
|
|
byID := map[string]iace.HazardPattern{
|
|
"P1": {ID: "P1", RequiredComponentTags: []string{"d", "b", "a", "c"}},
|
|
}
|
|
got := suggestTagsFor([]string{"P1"}, byID)
|
|
if len(got) != 3 || got[0] != "a" || got[1] != "b" || got[2] != "c" {
|
|
t.Fatalf("want stable alpha top-3 [a b c], got %v", got)
|
|
}
|
|
}
|
|
|
|
func TestSuggestTagsFor_UnknownPatternIgnored(t *testing.T) {
|
|
byID := map[string]iace.HazardPattern{}
|
|
if got := suggestTagsFor([]string{"missing"}, byID); len(got) != 0 {
|
|
t.Fatalf("want empty for unknown patterns, got %v", got)
|
|
}
|
|
}
|