Files
keyhunter/pkg/recon/sources/packagist_test.go
salvacybersec 018bb165fe feat(13-02): implement GoProxySource and PackagistSource with tests
- GoProxySource parses pkg.go.dev HTML search results for module paths
- PackagistSource queries Packagist JSON search API for PHP packages
- GoProxy regex requires domain dot to filter non-module paths
2026-04-06 12:53:37 +03:00

122 lines
3.0 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 packagistTestRegistry() *providers.Registry {
return providers.NewRegistryFromProviders([]providers.Provider{
{Name: "openai", Keywords: []string{"sk-proj-"}},
})
}
const packagistFixtureJSON = `{
"results": [
{"name": "vendor/openai-php", "url": "https://packagist.org/packages/vendor/openai-php"},
{"name": "other/llm-sdk", "url": "https://packagist.org/packages/other/llm-sdk"}
]
}`
func newPackagistTestSource(srvURL string) *PackagistSource {
return &PackagistSource{
BaseURL: srvURL,
Registry: packagistTestRegistry(),
Limiters: recon.NewLimiterRegistry(),
Client: NewClient(),
}
}
func TestPackagist_Sweep_ExtractsFindings(t *testing.T) {
var hits int
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if r.URL.Path != "/search.json" {
t.Errorf("unexpected path: %s", r.URL.Path)
}
if r.URL.Query().Get("q") == "" {
t.Errorf("missing q param")
}
hits++
w.Header().Set("Content-Type", "application/json")
_, _ = w.Write([]byte(packagistFixtureJSON))
}))
defer srv.Close()
src := newPackagistTestSource(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))
}
want1 := "https://packagist.org/packages/vendor/openai-php"
want2 := "https://packagist.org/packages/other/llm-sdk"
got := map[string]bool{}
for _, f := range findings {
got[f.Source] = true
if f.SourceType != "recon:packagist" {
t.Errorf("unexpected SourceType: %s", f.SourceType)
}
}
if !got[want1] || !got[want2] {
t.Fatalf("missing expected sources; got=%v", got)
}
if hits == 0 {
t.Fatal("server was never hit")
}
}
func TestPackagist_NameAndRate(t *testing.T) {
s := &PackagistSource{}
if s.Name() != "packagist" {
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")
}
}
func TestPackagist_EnabledAlwaysTrue(t *testing.T) {
s := &PackagistSource{}
if !s.Enabled(recon.Config{}) {
t.Fatal("expected Enabled=true")
}
}
func TestPackagist_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(packagistFixtureJSON))
}))
defer srv.Close()
src := newPackagistTestSource(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")
}
}