keyhunter/pkg/recon/sources/github_test.go

package sources

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

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

// syntheticRegistry builds a two-provider registry for tests.
func syntheticRegistry() *providers.Registry {
	return providers.NewRegistryFromProviders([]providers.Provider{
		{Name: "openai", Keywords: []string{"sk-proj-"}},
		{Name: "anthropic", Keywords: []string{"sk-ant-"}},
	})
}

// ghStubHandler returns a handler that echoes the query back in two items.
func ghStubHandler(t *testing.T, calls *int32) http.HandlerFunc {
	t.Helper()
	return func(w http.ResponseWriter, r *http.Request) {
		atomic.AddInt32(calls, 1)
		if r.URL.Path != "/search/code" {
			t.Errorf("unexpected path: %s", r.URL.Path)
		}
		if got := r.Header.Get("Authorization"); got != "Bearer testtoken" {
			t.Errorf("missing bearer token: %q", got)
		}
		if got := r.Header.Get("Accept"); !strings.Contains(got, "text-match") {
			t.Errorf("missing text-match accept header: %q", got)
		}
		q := r.URL.Query().Get("q")
		body := map[string]any{
			"items": []map[string]any{
				{
					"html_url":   "https://github.com/org/repo/blob/main/a.env#" + q,
					"repository": map[string]any{"full_name": "org/repo"},
					"text_matches": []map[string]any{
						{"fragment": "snippet for " + q},
					},
				},
				{
					"html_url":   "https://github.com/org/repo/blob/main/b.env#" + q,
					"repository": map[string]any{"full_name": "org/repo"},
				},
			},
		}
		w.Header().Set("Content-Type", "application/json")
		_ = json.NewEncoder(w).Encode(body)
	}
}

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

	if s := NewGitHubSource("", reg, lim); s.Enabled(recon.Config{}) {
		t.Errorf("expected Enabled=false with empty token")
	}
	if s := NewGitHubSource("tok", reg, lim); !s.Enabled(recon.Config{}) {
		t.Errorf("expected Enabled=true with token")
	}
}

func TestGitHubSource_SweepEmptyTokenReturnsNil(t *testing.T) {
	reg := syntheticRegistry()
	lim := recon.NewLimiterRegistry()
	s := NewGitHubSource("", 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 TestGitHubSource_SweepEmitsFindings(t *testing.T) {
	reg := syntheticRegistry()
	lim := recon.NewLimiterRegistry()

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

	s := NewGitHubSource("testtoken", reg, lim)
	s.BaseURL = srv.URL
	// Use a generous limiter so the test doesn't wait seconds for each query.
	// Overwrite via the limiter registry by pre-registering at high rate.
	_ = lim.For(s.Name(), 1000, 100)

	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)
	}

	// syntheticRegistry has 2 keywords -> 2 queries -> 2 items each = 4 findings.
	if len(findings) != 4 {
		t.Fatalf("expected 4 findings, got %d", len(findings))
	}
	for _, f := range findings {
		if f.SourceType != "recon:github" {
			t.Errorf("SourceType=%q want recon:github", f.SourceType)
		}
		if !strings.HasPrefix(f.Source, "https://github.com/org/repo/blob/main/") {
			t.Errorf("Source=%q unexpected", f.Source)
		}
		if f.ProviderName != "openai" && f.ProviderName != "anthropic" {
			t.Errorf("ProviderName=%q unexpected", f.ProviderName)
		}
	}

	// Two queries -> two calls.
	if got := atomic.LoadInt32(&calls); got != 2 {
		t.Errorf("expected 2 calls, got %d", got)
	}
}

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

	// Track which query came in so we can assert providerName mapping per-call.
	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
		q := r.URL.Query().Get("q")
		body := fmt.Sprintf(`{"items":[{"html_url":"https://example/%s","repository":{"full_name":"o/r"}}]}`, q)
		w.Header().Set("Content-Type", "application/json")
		_, _ = w.Write([]byte(body))
	}))
	defer srv.Close()

	s := NewGitHubSource("tok", reg, lim)
	s.BaseURL = srv.URL

	out := make(chan recon.Finding, 8)
	ctx, cancel := context.WithTimeout(context.Background(), 3*time.Second)
	defer cancel()
	if err := s.Sweep(ctx, "", out); err != nil {
		t.Fatalf("Sweep: %v", err)
	}
	close(out)

	// BuildQueries returns sorted keywords: sk-ant- then sk-proj-.
	// So findings should arrive in that order.
	var got []string
	for f := range out {
		got = append(got, f.ProviderName)
	}
	if len(got) != 2 {
		t.Fatalf("expected 2 findings, got %d", len(got))
	}
	if got[0] != "anthropic" || got[1] != "openai" {
		t.Errorf("expected sorted provider names [anthropic openai], got %v", got)
	}
}

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

	s := NewGitHubSource("tok", reg, lim)
	s.BaseURL = "http://127.0.0.1:1" // unused, should never be reached

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

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

	s := NewGitHubSource("tok", 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)
	}
}

// Compile-time assertion that GitHubSource satisfies recon.ReconSource.
var _ recon.ReconSource = (*GitHubSource)(nil)

func countFindings(ch <-chan recon.Finding) int {
	n := 0
	for range ch {
		n++
	}
	return n
}