breakpilot-compliance/ai-compliance-sdk/internal/ucca/authority_rerank_test.go

package ucca

import "testing"

func bindingRes(label, reg, jur string, score float64) LegalSearchResult {
	return LegalSearchResult{ArticleLabel: label, RegulationShort: reg, SourceClass: "binding_law", AuthorityWeight: 100, Jurisdiction: jur, Score: score}
}

func guidanceRes(label, reg string, score float64) LegalSearchResult {
	return LegalSearchResult{ArticleLabel: label, RegulationShort: reg, SourceClass: "supervisory_guidance", AuthorityWeight: 70, Jurisdiction: "EU", Score: score}
}

func foreignRes(label string, score float64) LegalSearchResult {
	return LegalSearchResult{ArticleLabel: label, RegulationShort: "RevDSG", SourceClass: "foreign_law", AuthorityWeight: 0, Jurisdiction: "CH", Score: score}
}

// Acceptance criteria (Phase 1) expressed as ordering tests.
func TestRerankByAuthority_Acceptance(t *testing.T) {
	t.Run("guidance does not overtake semantically competitive binding", func(t *testing.T) {
		out := rerankByAuthority("Was gilt hier?", []LegalSearchResult{
			guidanceRes("ENISA Mapping", "ENISA", 0.72),
			bindingRes("CRA Anhang I", "CRA", "EU", 0.66),
		})
		if out[0].RegulationShort != "CRA" {
			t.Fatalf("binding must rank first over competitive guidance, got %q", out[0].RegulationShort)
		}
	})

	t.Run("foreign law demoted on DE/EU question but kept", func(t *testing.T) {
		in := []LegalSearchResult{foreignRes("RevDSG Art 1", 0.85), bindingRes("Art. 9 DSGVO", "DSGVO", "EU", 0.62)}
		out := rerankByAuthority("Welche Daten sind besonders geschuetzt?", in)
		if out[0].RegulationShort != "DSGVO" {
			t.Fatalf("binding EU must beat foreign on a DE/EU query, got %q", out[0].RegulationShort)
		}
		if len(out) != 2 {
			t.Fatalf("foreign law must be kept, got len=%d", len(out))
		}
	})

	t.Run("off-domain binding demoted but not removed", func(t *testing.T) {
		in := []LegalSearchResult{
			bindingRes("Art. 13 EU MDR", "MDR", "EU", 0.70),
			bindingRes("Art. 13 CRA", "CRA", "EU", 0.60),
		}
		out := rerankByAuthority("Welche Pflichten hat der Hersteller von Produkten mit digitalen Elementen?", in)
		if out[0].RegulationShort != "CRA" {
			t.Fatalf("on-domain CRA must beat off-domain MDR, got %q", out[0].RegulationShort)
		}
		if len(out) != 2 {
			t.Fatalf("off-domain MDR must be kept, got len=%d", len(out))
		}
	})

	t.Run("same-regime binding wins over guidance", func(t *testing.T) {
		out := rerankByAuthority("Was gilt hier?", []LegalSearchResult{
			bindingRes("Art. 13 CRA", "CRA", "EU", 0.70),
			guidanceRes("ENISA Mapping", "ENISA", 0.60),
		})
		if out[0].RegulationShort != "CRA" {
			t.Fatalf("binding must win, got %q", out[0].RegulationShort)
		}
	})

	t.Run("BDSG Teil 3 demoted below DSGVO on general DP question", func(t *testing.T) {
		in := []LegalSearchResult{
			bindingRes("§ 48 BDSG", "BDSG", "DE", 0.70), // Teil 3 (law enforcement)
			bindingRes("Art. 9 DSGVO", "DSGVO", "EU", 0.62),
		}
		out := rerankByAuthority("Was sind besondere Kategorien personenbezogener Daten?", in)
		if out[0].RegulationShort != "DSGVO" {
			t.Fatalf("DSGVO must beat BDSG Teil 3 on a general DP question, got %q", out[0].RegulationShort)
		}
	})

	// Subsidiarity (KB-2026.1 BDSG-pilot regression): a national implementing § that is NOT a
	// co-primary topic norm must not outrank the primary DSGVO article on a general question.
	t.Run("subsidiarity dp_05: BDSG §23 below DSGVO Art.6 (Rechtsgrundlage)", func(t *testing.T) {
		in := []LegalSearchResult{
			bindingRes("§ 23 BDSG", "BDSG", "DE", 0.70),
			bindingRes("Art. 6 DSGVO", "DSGVO", "EU", 0.66),
		}
		out := rerankByAuthority("Welche Rechtsgrundlagen erlauben eine Verarbeitung personenbezogener Daten?", in)
		if out[0].RegulationShort != "DSGVO" {
			t.Fatalf("DSGVO Art.6 must beat general BDSG §, got %q", out[0].ArticleLabel)
		}
		if len(out) != 2 {
			t.Fatalf("BDSG must stay visible (soft demote), got len=%d", len(out))
		}
	})

	t.Run("subsidiarity dp_08: BDSG §70 below DSGVO Art.28 (Auftragsverarbeitung)", func(t *testing.T) {
		in := []LegalSearchResult{
			bindingRes("§ 70 BDSG", "BDSG", "DE", 0.70), // Teil 3 → scope + subsidiarity
			bindingRes("Art. 28 DSGVO", "DSGVO", "EU", 0.66),
		}
		out := rerankByAuthority("Was muss ein Auftragsverarbeitungsvertrag enthalten?", in)
		if out[0].RegulationShort != "DSGVO" {
			t.Fatalf("DSGVO Art.28 must beat BDSG §70, got %q", out[0].ArticleLabel)
		}
	})

	t.Run("subsidiarity dp_11: BDSG §22 below DSGVO Art.32 on a TOM question", func(t *testing.T) {
		in := []LegalSearchResult{
			bindingRes("§ 22 BDSG", "BDSG", "DE", 0.70),
			bindingRes("Art. 32 DSGVO", "DSGVO", "EU", 0.66),
		}
		out := rerankByAuthority("Welche technischen und organisatorischen Massnahmen verlangt das Datenschutzrecht?", in)
		if out[0].RegulationShort != "DSGVO" {
			t.Fatalf("DSGVO Art.32 must beat BDSG §22 on a non-topic TOM question, got %q", out[0].ArticleLabel)
		}
	})

	t.Run("cr_07: a 'DSGVO' mention scopes the domain so BDSG Teil-3 §64 is demoted", func(t *testing.T) {
		in := []LegalSearchResult{
			bindingRes("§ 64 BDSG", "BDSG", "DE", 0.70), // Teil 3 (law enforcement)
			bindingRes("Art. 32 DSGVO", "DSGVO", "EU", 0.66),
		}
		// Query has no DP keyword but names the DSGVO → domain fallback scopes it data_protection,
		// so scope+subsidiarity demote the law-enforcement § below the primary norm.
		out := rerankByAuthority("Welche rechtliche Grundlage gilt fuer technische und organisatorische Massnahmen - DSGVO oder ein Standard?", in)
		if out[0].RegulationShort != "DSGVO" {
			t.Fatalf("DSGVO must win on a DSGVO-mention question, got %q", out[0].ArticleLabel)
		}
	})

	t.Run("co-primary dp_01: BDSG §38 stays top on a DSB question (national special rule)", func(t *testing.T) {
		in := []LegalSearchResult{
			bindingRes("§ 38 BDSG", "BDSG", "DE", 0.66),
			bindingRes("Art. 37 DSGVO", "DSGVO", "EU", 0.64),
		}
		out := rerankByAuthority("Ab wann muss ein Datenschutzbeauftragter benannt werden?", in)
		// DSB topic → §38 is co-primary (topic-matched, NOT subsidiarity-demoted) and keeps its
		// semantic lead; Art. 37 stays a close second. Both remain top-2.
		if out[0].RegulationShort != "BDSG" {
			t.Fatalf("BDSG §38 (DSB co-primary) must stay top, got %q", out[0].ArticleLabel)
		}
		if out[1].RegulationShort != "DSGVO" {
			t.Fatalf("Art. 37 DSGVO must stay co-primary second, got %q", out[1].ArticleLabel)
		}
	})

	t.Run("nothing is dropped and topic amplifies", func(t *testing.T) {
		in := []LegalSearchResult{
			guidanceRes("ENISA", "ENISA", 0.72),
			bindingRes("CRA Anhang I", "CRA", "EU", 0.66),
			foreignRes("RevDSG", 0.5),
		}
		out := rerankByAuthority("Anforderungen an Security Updates?", in)
		if len(out) != len(in) {
			t.Fatalf("rerank must preserve all results, got %d want %d", len(out), len(in))
		}
		if out[0].ArticleLabel != "CRA Anhang I" {
			t.Fatalf("topic+authority must lift CRA Anhang I to top, got %q", out[0].ArticleLabel)
		}
	})

	t.Run("single result returned unchanged", func(t *testing.T) {
		in := []LegalSearchResult{bindingRes("Art. 1 CRA", "CRA", "EU", 0.5)}
		if out := rerankByAuthority("x", in); len(out) != 1 {
			t.Fatalf("len=%d", len(out))
		}
	})
}