package ucca

import (
	"context"
	"encoding/json"
	"fmt"
	"os"
	"strings"
	"testing"
)

// TestGuidanceFixE2E runs the 10 hard cases through the REAL LegalRAGClient against the
// homogeneous build collection. Guarded by RUN_E2E=1. Reports the rank of the expected
// document within the returned top-K — proving whether the guidanceIntentSignals fix lifts
// guidance (WP248/WP260) back into the prompt. Toggle RAG_HYBRID_SEARCH to compare modes.
func TestGuidanceFixE2E(t *testing.T) {
	if os.Getenv("RUN_E2E") != "1" {
		t.Skip("set RUN_E2E=1 + QDRANT_URL/OLLAMA_URL to run")
	}
	c := NewLegalRAGClient()
	coll := os.Getenv("E2E_COLLECTION")
	if coll == "" {
		coll = "bp_compliance_kb_2026_1_build"
	}
	cases := []struct{ id, q, expect string }{
		{"GQ-0012", "Welche neun Kriterien nennt WP248 fuer ein voraussichtlich hohes Risiko?", "WP248"},
		{"GQ-0013", "Ab wie vielen der WP248-Kriterien ist in der Regel eine Datenschutz-Folgenabschaetzung erforderlich?", "WP248"},
		{"GQ-0023", "Welche Anforderungen stellt WP260 an eine klare und einfache Sprache?", "WP260"},
		{"GQ-0024", "Was versteht WP260 unter Layered Privacy Notices?", "WP260"},
		{"GQ-0054", "Welche grundlegenden Cybersecurity-Anforderungen enthaelt Annex I Part I?", "CRA"},
		{"GQ-0060", "Wann muss eine aktiv ausgenutzte Schwachstelle gemeldet werden?", "CRA"},
		{"GQ-0074", "Benoetigt eine SPS ohne Netzwerkanschluss eine CRA-Bewertung?", "CRA"},
		{"GQ-0079", "Welche grundlegenden Sicherheits- und Gesundheitsschutzanforderungen enthaelt Anhang III?", "MASCHVO"},
		{"GQ-0091", "Welche Anforderungen gelten fuer wesentliche Veraenderungen einer Maschine?", "MASCHVO"},
		{"GQ-0070", "Wie greifen CRA und Maschinenverordnung bei einer vernetzten Maschine ineinander?", "CRA"},
	}
	fmt.Printf("\n### hybrid=%v collection=%s\n", os.Getenv("RAG_HYBRID_SEARCH") != "false", coll)
	for _, tc := range cases {
		res, err := c.SearchCollection(context.Background(), coll, tc.q, nil, 8)
		if err != nil {
			t.Fatalf("%s: %v", tc.id, err)
		}
		rank := -1
		for i, r := range res {
			lab := strings.ToUpper(r.RegulationCode + " " + r.ArticleLabel)
			if strings.Contains(lab, tc.expect) {
				rank = i + 1
				break
			}
		}
		top1 := ""
		if len(res) > 0 {
			top1 = res[0].RegulationCode + " (" + res[0].SourceClass + ")"
		}
		status := "FAIL"
		if rank > 0 {
			status = "OK"
		}
		fmt.Printf("%-9s expect=%-8s rank_in_top8=%-2d  %-5s  top1=%s\n", tc.id, tc.expect, rank, status, top1)
	}
}

// TestBenchE2E runs the FULL ComplianceBench (E2E_BENCH_FILE) through the real client and
// prints, per question, the ordered top-8 regulation codes. Diffing BEFORE vs AFTER proves
// the fix only perturbs guidance-intent queries (gated on queryWantsGuidance) and never the
// norm questions — the Knowledge-Freeze regression guard.
func TestBenchE2E(t *testing.T) {
	if os.Getenv("RUN_E2E") != "1" {
		t.Skip("set RUN_E2E=1 + E2E_BENCH_FILE")
	}
	path := os.Getenv("E2E_BENCH_FILE")
	if path == "" {
		t.Skip("E2E_BENCH_FILE not set")
	}
	raw, err := os.ReadFile(path)
	if err != nil {
		t.Fatal(err)
	}
	var bench struct {
		Questions []struct {
			ID       string `json:"id"`
			Question string `json:"question"`
		} `json:"questions"`
	}
	if err := json.Unmarshal(raw, &bench); err != nil {
		t.Fatal(err)
	}
	c := NewLegalRAGClient()
	coll := os.Getenv("E2E_COLLECTION")
	if coll == "" {
		coll = "bp_compliance_kb_2026_1_build"
	}
	fmt.Printf("### BENCH n=%d hybrid=%v\n", len(bench.Questions), os.Getenv("RAG_HYBRID_SEARCH") != "false")
	for _, q := range bench.Questions {
		res, err := c.SearchCollection(context.Background(), coll, q.Question, nil, 8)
		if err != nil {
			t.Fatalf("%s: %v", q.ID, err)
		}
		codes := make([]string, 0, len(res))
		for _, r := range res {
			codes = append(codes, strings.ReplaceAll(r.RegulationCode, ";", ","))
		}
		fmt.Printf("BENCH|%s|%s\n", q.ID, strings.Join(codes, ";"))
	}
}