Files
keyhunter/pkg/recon/sources/google_test.go
salvacybersec 7272e65207 feat(11-01): add GoogleDorkSource and BingDorkSource with formatQuery updates
- GoogleDorkSource uses Google Custom Search JSON API (APIKey+CX required)
- BingDorkSource uses Bing Web Search API v7 (Ocp-Apim-Subscription-Key header)
- formatQuery now handles google/bing/duckduckgo/yandex/brave dork syntax
- Both sources follow established pattern: retry via Client, rate limit via LimiterRegistry
2026-04-06 11:54:36 +03:00

159 lines
4.1 KiB
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 googleStubHandler(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, "/customsearch/v1") {
t.Errorf("unexpected path: %s", r.URL.Path)
}
if r.URL.Query().Get("key") != "testkey" {
t.Errorf("missing api key in query")
}
if r.URL.Query().Get("cx") != "testcx" {
t.Errorf("missing cx in query")
}
body := map[string]any{
"items": []map[string]any{
{"title": "result1", "link": "https://pastebin.com/abc123", "snippet": "found key"},
{"title": "result2", "link": "https://github.com/org/repo/blob/main/env", "snippet": "another"},
},
}
w.Header().Set("Content-Type", "application/json")
_ = json.NewEncoder(w).Encode(body)
}
}
func TestGoogleDorkSource_EnabledRequiresBothKeys(t *testing.T) {
reg := syntheticRegistry()
lim := recon.NewLimiterRegistry()
tests := []struct {
apiKey, cx string
want bool
}{
{"", "", false},
{"key", "", false},
{"", "cx", false},
{"key", "cx", true},
}
for _, tt := range tests {
s := NewGoogleDorkSource(tt.apiKey, tt.cx, reg, lim)
if got := s.Enabled(recon.Config{}); got != tt.want {
t.Errorf("Enabled(apiKey=%q, cx=%q) = %v, want %v", tt.apiKey, tt.cx, got, tt.want)
}
}
}
func TestGoogleDorkSource_SweepEmptyCredsReturnsNil(t *testing.T) {
reg := syntheticRegistry()
lim := recon.NewLimiterRegistry()
s := NewGoogleDorkSource("", "", reg, lim)
out := make(chan recon.Finding, 10)
if err := s.Sweep(context.Background(), "", out); err != nil {
t.Fatalf("expected nil err, got %v", err)
}
close(out)
if n := countFindings(out); n != 0 {
t.Fatalf("expected 0 findings, got %d", n)
}
}
func TestGoogleDorkSource_SweepEmitsFindings(t *testing.T) {
reg := syntheticRegistry()
lim := recon.NewLimiterRegistry()
_ = lim.For("google", 1000, 100)
var calls int32
srv := httptest.NewServer(googleStubHandler(t, &calls))
defer srv.Close()
s := NewGoogleDorkSource("testkey", "testcx", 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 * 2 items = 4 findings
if len(findings) != 4 {
t.Fatalf("expected 4 findings, got %d", len(findings))
}
for _, f := range findings {
if f.SourceType != "recon:google" {
t.Errorf("SourceType=%q want recon:google", f.SourceType)
}
if f.Confidence != "low" {
t.Errorf("Confidence=%q want low", f.Confidence)
}
}
if got := atomic.LoadInt32(&calls); got != 2 {
t.Errorf("expected 2 API calls, got %d", got)
}
}
func TestGoogleDorkSource_CtxCancelled(t *testing.T) {
reg := syntheticRegistry()
lim := recon.NewLimiterRegistry()
_ = lim.For("google", 1000, 100)
s := NewGoogleDorkSource("key", "cx", 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 TestGoogleDorkSource_Unauthorized(t *testing.T) {
reg := syntheticRegistry()
lim := recon.NewLimiterRegistry()
_ = lim.For("google", 1000, 100)
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(http.StatusUnauthorized)
_, _ = w.Write([]byte("bad key"))
}))
defer srv.Close()
s := NewGoogleDorkSource("key", "cx", 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)
}
}