Files
keyhunter/pkg/recon/sources/npm_test.go
salvacybersec 4b268d109f feat(13-01): implement NpmSource and PyPISource with httptest tests
- NpmSource searches npm registry JSON API for provider keywords
- PyPISource scrapes pypi.org search HTML for project links
- Both credentialless, rate-limited at 1 req/2s, burst 2
- httptest-based tests verify Sweep, ctx cancellation, Name/Rate/Burst
2026-04-06 12:52:31 +03:00

142 lines
3.3 KiB
Go

package sources
import (
"context"
"net/http"
"net/http/httptest"
"testing"
"time"
"github.com/salvacybersec/keyhunter/pkg/providers"
"github.com/salvacybersec/keyhunter/pkg/recon"
)
func npmTestRegistry() *providers.Registry {
return providers.NewRegistryFromProviders([]providers.Provider{
{Name: "openai", Keywords: []string{"sk-proj-"}},
})
}
const npmFixtureJSON = `{
"objects": [
{
"package": {
"name": "openai-key-checker",
"links": {"npm": "https://www.npmjs.com/package/openai-key-checker"}
}
},
{
"package": {
"name": "sk-proj-util",
"links": {"npm": ""}
}
}
]
}`
func newNpmTestSource(srvURL string) *NpmSource {
return &NpmSource{
BaseURL: srvURL,
Registry: npmTestRegistry(),
Limiters: recon.NewLimiterRegistry(),
Client: NewClient(),
}
}
func TestNpm_Sweep_ExtractsFindings(t *testing.T) {
var hits int
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if r.URL.Path != "/-/v1/search" {
t.Errorf("unexpected path: %s", r.URL.Path)
}
if r.URL.Query().Get("text") == "" {
t.Errorf("missing text param")
}
hits++
w.Header().Set("Content-Type", "application/json")
_, _ = w.Write([]byte(npmFixtureJSON))
}))
defer srv.Close()
src := newNpmTestSource(srv.URL)
out := make(chan recon.Finding, 16)
ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
defer cancel()
if err := src.Sweep(ctx, "", out); err != nil {
t.Fatalf("Sweep err: %v", err)
}
close(out)
var findings []recon.Finding
for f := range out {
findings = append(findings, f)
}
if len(findings) != 2 {
t.Fatalf("expected 2 findings, got %d", len(findings))
}
got := map[string]bool{}
for _, f := range findings {
got[f.Source] = true
if f.SourceType != "recon:npm" {
t.Errorf("unexpected SourceType: %s", f.SourceType)
}
if f.Confidence != "low" {
t.Errorf("unexpected Confidence: %s", f.Confidence)
}
}
if !got["https://www.npmjs.com/package/openai-key-checker"] {
t.Error("missing finding with npm link")
}
// Second package has empty links.npm — should get constructed URL.
if !got["https://www.npmjs.com/package/sk-proj-util"] {
t.Error("missing finding with constructed URL")
}
if hits == 0 {
t.Fatal("server was never hit")
}
}
func TestNpm_EnabledAlwaysTrue(t *testing.T) {
s := &NpmSource{}
if !s.Enabled(recon.Config{}) {
t.Fatal("expected Enabled=true")
}
}
func TestNpm_Sweep_CtxCancelled(t *testing.T) {
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
time.Sleep(500 * time.Millisecond)
_, _ = w.Write([]byte(npmFixtureJSON))
}))
defer srv.Close()
src := newNpmTestSource(srv.URL)
ctx, cancel := context.WithCancel(context.Background())
cancel()
out := make(chan recon.Finding, 4)
if err := src.Sweep(ctx, "", out); err == nil {
t.Fatal("expected ctx error")
}
}
func TestNpm_NameAndRate(t *testing.T) {
s := &NpmSource{}
if s.Name() != "npm" {
t.Errorf("unexpected name: %s", s.Name())
}
if s.Burst() != 2 {
t.Errorf("burst: %d", s.Burst())
}
if s.RespectsRobots() {
t.Error("expected RespectsRobots=false")
}
want := float64(1) / 2
got := float64(s.RateLimit())
if got < want-0.01 || got > want+0.01 {
t.Errorf("rate limit=%v want~%v", got, want)
}
}