keyhunter/pkg/recon/sources/bing_test.go

package sources

import (
	"context"
	"encoding/json"
	"errors"
	"net/http"
	"net/http/httptest"
	"strings"
	"sync/atomic"
	"testing"
	"time"

	"github.com/salvacybersec/keyhunter/pkg/recon"
)

func bingStubHandler(t *testing.T, calls *int32) http.HandlerFunc {
	t.Helper()
	return func(w http.ResponseWriter, r *http.Request) {
		atomic.AddInt32(calls, 1)
		if !strings.HasPrefix(r.URL.Path, "/v7.0/search") {
			t.Errorf("unexpected path: %s", r.URL.Path)
		}
		if got := r.Header.Get("Ocp-Apim-Subscription-Key"); got != "testkey" {
			t.Errorf("missing subscription key header: %q", got)
		}
		body := map[string]any{
			"webPages": map[string]any{
				"value": []map[string]any{
					{"name": "result1", "url": "https://pastebin.com/xyz789", "snippet": "found"},
					{"name": "result2", "url": "https://github.com/user/repo/blob/main/.env", "snippet": "key"},
					{"name": "result3", "url": "https://example.com/leak", "snippet": "data"},
				},
			},
		}
		w.Header().Set("Content-Type", "application/json")
		_ = json.NewEncoder(w).Encode(body)
	}
}

func TestBingDorkSource_EnabledRequiresAPIKey(t *testing.T) {
	reg := syntheticRegistry()
	lim := recon.NewLimiterRegistry()

	if s := NewBingDorkSource("", reg, lim); s.Enabled(recon.Config{}) {
		t.Error("expected Enabled=false with empty key")
	}
	if s := NewBingDorkSource("key", reg, lim); !s.Enabled(recon.Config{}) {
		t.Error("expected Enabled=true with key")
	}
}

func TestBingDorkSource_SweepEmptyKeyReturnsNil(t *testing.T) {
	reg := syntheticRegistry()
	lim := recon.NewLimiterRegistry()
	s := NewBingDorkSource("", reg, lim)

	out := make(chan recon.Finding, 10)
	if err := s.Sweep(context.Background(), "", out); err != nil {
		t.Fatalf("expected nil, got %v", err)
	}
	close(out)
	if n := countFindings(out); n != 0 {
		t.Fatalf("expected 0 findings, got %d", n)
	}
}

func TestBingDorkSource_SweepEmitsFindings(t *testing.T) {
	reg := syntheticRegistry()
	lim := recon.NewLimiterRegistry()
	_ = lim.For("bing", 1000, 100)

	var calls int32
	srv := httptest.NewServer(bingStubHandler(t, &calls))
	defer srv.Close()

	s := NewBingDorkSource("testkey", reg, lim)
	s.BaseURL = srv.URL

	out := make(chan recon.Finding, 32)
	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
	defer cancel()

	done := make(chan error, 1)
	go func() { done <- s.Sweep(ctx, "", out); close(out) }()

	var findings []recon.Finding
	for f := range out {
		findings = append(findings, f)
	}
	if err := <-done; err != nil {
		t.Fatalf("Sweep error: %v", err)
	}

	// 2 keywords * 3 items = 6 findings
	if len(findings) != 6 {
		t.Fatalf("expected 6 findings, got %d", len(findings))
	}
	for _, f := range findings {
		if f.SourceType != "recon:bing" {
			t.Errorf("SourceType=%q want recon:bing", f.SourceType)
		}
	}
	if got := atomic.LoadInt32(&calls); got != 2 {
		t.Errorf("expected 2 calls, got %d", got)
	}
}

func TestBingDorkSource_CtxCancelled(t *testing.T) {
	reg := syntheticRegistry()
	lim := recon.NewLimiterRegistry()
	_ = lim.For("bing", 1000, 100)

	s := NewBingDorkSource("key", reg, lim)
	s.BaseURL = "http://127.0.0.1:1"

	ctx, cancel := context.WithCancel(context.Background())
	cancel()

	out := make(chan recon.Finding, 1)
	err := s.Sweep(ctx, "", out)
	if !errors.Is(err, context.Canceled) {
		t.Fatalf("expected context.Canceled, got %v", err)
	}
}

func TestBingDorkSource_Unauthorized(t *testing.T) {
	reg := syntheticRegistry()
	lim := recon.NewLimiterRegistry()
	_ = lim.For("bing", 1000, 100)

	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
		w.WriteHeader(http.StatusUnauthorized)
		_, _ = w.Write([]byte("invalid key"))
	}))
	defer srv.Close()

	s := NewBingDorkSource("key", reg, lim)
	s.BaseURL = srv.URL

	out := make(chan recon.Finding, 1)
	err := s.Sweep(context.Background(), "", out)
	if !errors.Is(err, ErrUnauthorized) {
		t.Fatalf("expected ErrUnauthorized, got %v", err)
	}
}