feat(ai-sdk): authority-aware re-ranking for legal RAG (Phase 1) (#31)

ai-compliance-sdk/internal/ucca/authority_test.go

@@ -0,0 +1,125 @@
+package ucca
+
+import "testing"
+
+func TestClassifyAuthority(t *testing.T) {
+	tests := []struct {
+		name    string
+		result  LegalSearchResult
+		wantW   int
+		wantSC  string
+		wantJur string
+	}{
+		{"tagged binding EU", LegalSearchResult{AuthorityWeight: 100, SourceClass: "binding_law", Jurisdiction: "EU"}, 100, "binding_law", "EU"},
+		{"tagged guidance DE", LegalSearchResult{AuthorityWeight: 70, SourceClass: "supervisory_guidance", Jurisdiction: "DE"}, 70, "supervisory_guidance", "DE"},
+		{"tagged foreign CH", LegalSearchResult{AuthorityWeight: 0, SourceClass: "foreign_law", Jurisdiction: "CH"}, 0, "foreign_law", "CH"},
+		{"untagged ENISA guidance", LegalSearchResult{RegulationShort: "ENISA", ArticleLabel: "ENISA CRA Standards Mapping"}, 70, "supervisory_guidance", "EU"},
+		{"untagged CRA binding", LegalSearchResult{RegulationShort: "CRA", ArticleLabel: "Art. 13 CRA", Category: "regulation"}, 100, "binding_law", "EU"},
+		{"untagged BDSG binding DE", LegalSearchResult{RegulationShort: "BDSG", ArticleLabel: "§ 38 BDSG"}, 100, "binding_law", "DE"},
+		{"untagged RevDSG foreign", LegalSearchResult{RegulationShort: "RevDSG", ArticleLabel: "RevDSG (CH)"}, 0, "foreign_law", "CH"},
+		{"untagged unknown", LegalSearchResult{RegulationShort: "", ArticleLabel: ""}, 50, "unknown", "EU"},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := classifyAuthority(tt.result)
+			if got.weight != tt.wantW || got.sourceClass != tt.wantSC || got.jurisdiction != tt.wantJur {
+				t.Errorf("classifyAuthority() = {%d %s %s}, want {%d %s %s}",
+					got.weight, got.sourceClass, got.jurisdiction, tt.wantW, tt.wantSC, tt.wantJur)
+			}
+		})
+	}
+}
+
+func TestQueryDomain(t *testing.T) {
+	tests := []struct{ q, want string }{
+		{"Welche Anforderungen an Security Updates?", "cyber"},
+		{"Wer braucht einen Datenschutzbeauftragten?", "data_protection"},
+		{"Was sind besondere Kategorien personenbezogener Daten?", "data_protection"},
+		{"Welche Pflichten beim Hochrisiko-KI-System?", "ai"},
+		{"Wie spaet ist es?", ""},
+	}
+	for _, tt := range tests {
+		if got := queryDomain(tt.q); got != tt.want {
+			t.Errorf("queryDomain(%q) = %q, want %q", tt.q, got, tt.want)
+		}
+	}
+}
+
+func TestChunkDomain(t *testing.T) {
+	tests := []struct {
+		name string
+		r    LegalSearchResult
+		want string
+	}{
+		{"CRA cyber", LegalSearchResult{RegulationShort: "CRA", ArticleLabel: "Art. 13 CRA"}, "cyber"},
+		{"DSGVO dp", LegalSearchResult{RegulationShort: "DSGVO", ArticleLabel: "Art. 9 DSGVO"}, "data_protection"},
+		{"AI Act ai", LegalSearchResult{RegulationShort: "AI Act", ArticleLabel: "Art. 10 AI Act"}, "ai"},
+		{"MDR product", LegalSearchResult{RegulationShort: "MDR", ArticleLabel: "Art. 13 EU MDR"}, "product_safety"},
+		{"unknown", LegalSearchResult{RegulationShort: "XYZ"}, ""},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := chunkDomain(tt.r); got != tt.want {
+				t.Errorf("chunkDomain() = %q, want %q", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestScopeClass(t *testing.T) {
+	tests := []struct {
+		name string
+		r    LegalSearchResult
+		want string
+	}{
+		{"BDSG Teil 3 law enforcement", LegalSearchResult{RegulationShort: "BDSG", ArticleLabel: "§ 48 BDSG"}, "law_enforcement"},
+		{"BDSG general part", LegalSearchResult{RegulationShort: "BDSG", ArticleLabel: "§ 38 BDSG"}, "general"},
+		{"DSGVO general", LegalSearchResult{RegulationShort: "DSGVO", ArticleLabel: "Art. 9 DSGVO"}, "general"},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := scopeClass(tt.r); got != tt.want {
+				t.Errorf("scopeClass() = %q, want %q", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestResultMatchesTopic(t *testing.T) {
+	tests := []struct {
+		name  string
+		query string
+		r     LegalSearchResult
+		want  bool
+	}{
+		{"besondere Kategorien -> Art 9 match", "Was sind besondere Kategorien?", LegalSearchResult{ArticleLabel: "Art. 9 DSGVO"}, true},
+		{"besondere Kategorien -> Art 90 no match", "Was sind besondere Kategorien?", LegalSearchResult{ArticleLabel: "Art. 90 DSGVO"}, false},
+		{"security updates -> CRA Anhang I", "Anforderungen an Security Updates?", LegalSearchResult{ArticleLabel: "CRA Anhang I"}, true},
+		{"no topic keyword", "Wie spaet ist es?", LegalSearchResult{ArticleLabel: "Art. 9 DSGVO"}, false},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := resultMatchesTopic(tt.query, tt.r); got != tt.want {
+				t.Errorf("resultMatchesTopic() = %v, want %v", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestNormMatches(t *testing.T) {
+	tests := []struct {
+		hay, norm string
+		want      bool
+	}{
+		{"Art. 9 DSGVO", "Art. 9", true},
+		{"Art. 90 DSGVO", "Art. 9", false},
+		{"§ 38 BDSG", "§ 38 BDSG", true},
+		{"§ 380 BDSG", "§ 38", false},
+		{"Art. 14 CRA", "Art. 14 CRA", true},
+	}
+	for _, tt := range tests {
+		if got := normMatches(tt.hay, tt.norm); got != tt.want {
+			t.Errorf("normMatches(%q,%q) = %v, want %v", tt.hay, tt.norm, got, tt.want)
+		}
+	}
+}