keyhunter/pkg/recon/sources/commoncrawl_test.go

package sources

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

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

func commonCrawlStubHandler(t *testing.T, calls *int32) http.HandlerFunc {
	t.Helper()
	return func(w http.ResponseWriter, r *http.Request) {
		atomic.AddInt32(calls, 1)
		if r.URL.Query().Get("query") == "" {
			t.Errorf("missing query param")
		}
		w.Header().Set("Content-Type", "application/json")
		// NDJSON: one JSON object per line
		enc := json.NewEncoder(w)
		_ = enc.Encode(ccIndexRecord{URL: "https://example.com/api/config", Timestamp: "20240301120000", Status: "200"})
		_ = enc.Encode(ccIndexRecord{URL: "https://example.com/env.js", Timestamp: "20240301130000", Status: "200"})
	}
}

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

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

	src := &CommonCrawlSource{
		BaseURL:   srv.URL,
		IndexName: "CC-MAIN-2024-10",
		Registry:  reg,
		Limiters:  lim,
		Client:    NewClient(),
	}

	out := make(chan recon.Finding, 32)
	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
	defer cancel()

	done := make(chan error, 1)
	go func() { done <- src.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 results = 4 findings
	if len(findings) != 4 {
		t.Fatalf("expected 4 findings, got %d", len(findings))
	}
	for _, f := range findings {
		if f.SourceType != "recon:commoncrawl" {
			t.Errorf("SourceType=%q want recon:commoncrawl", f.SourceType)
		}
	}
	if got := atomic.LoadInt32(&calls); got != 2 {
		t.Errorf("expected 2 server calls, got %d", got)
	}
}

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

	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
		w.Header().Set("Content-Type", "application/json")
		enc := json.NewEncoder(w)
		_ = enc.Encode(ccIndexRecord{URL: "https://target.com/leak.js", Timestamp: "20240101000000", Status: "200"})
	}))
	defer srv.Close()

	src := &CommonCrawlSource{
		BaseURL:   srv.URL,
		IndexName: "CC-MAIN-2024-10",
		Registry:  reg,
		Limiters:  lim,
		Client:    NewClient(),
	}

	out := make(chan recon.Finding, 32)
	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
	defer cancel()

	done := make(chan error, 1)
	go func() { done <- src.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)
	}

	for _, f := range findings {
		if f.Source != "https://target.com/leak.js" {
			t.Errorf("Source=%q want https://target.com/leak.js", f.Source)
		}
	}
}

func TestCommonCrawl_EnabledAlwaysTrue(t *testing.T) {
	s := &CommonCrawlSource{}
	if !s.Enabled(recon.Config{}) {
		t.Fatal("expected Enabled=true")
	}
}

func TestCommonCrawl_NameAndRate(t *testing.T) {
	s := &CommonCrawlSource{}
	if s.Name() != "commoncrawl" {
		t.Errorf("unexpected name: %s", s.Name())
	}
	if s.Burst() != 1 {
		t.Errorf("burst: %d", s.Burst())
	}
	if !s.RespectsRobots() {
		t.Error("expected RespectsRobots=true")
	}
}

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

	src := &CommonCrawlSource{
		BaseURL:   "http://127.0.0.1:1",
		IndexName: "CC-MAIN-2024-10",
		Registry:  reg,
		Limiters:  lim,
		Client:    NewClient(),
	}

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

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

func TestCommonCrawl_NilRegistryNoError(t *testing.T) {
	src := &CommonCrawlSource{Client: NewClient()}
	out := make(chan recon.Finding, 1)
	if err := src.Sweep(context.Background(), "", out); err != nil {
		t.Fatalf("expected nil, got %v", err)
=======
	"net/http"
	"net/http/httptest"
	"testing"
	"time"

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

func TestCommonCrawl_Name(t *testing.T) {
	s := &CommonCrawlSource{}
	if s.Name() != "commoncrawl" {
		t.Fatalf("expected commoncrawl, got %s", s.Name())
	}
}

func TestCommonCrawl_Enabled(t *testing.T) {
	s := &CommonCrawlSource{}
	if !s.Enabled(recon.Config{}) {
		t.Fatal("CommonCrawlSource should always be enabled (credentialless)")
	}
}

func TestCommonCrawl_Sweep(t *testing.T) {
	mux := http.NewServeMux()
	mux.HandleFunc("/", func(w http.ResponseWriter, r *http.Request) {
		w.Header().Set("Content-Type", "application/json")
		// NDJSON format: one JSON object per line.
		_, _ = w.Write([]byte(`{"url":"https://example.com/.env","timestamp":"20240101000000","status":"200","filename":"CC-MAIN-2024.warc.gz","length":"1234","offset":"5678"}
`))
	})

	srv := httptest.NewServer(mux)
	defer srv.Close()

	reg := providers.NewRegistryFromProviders([]providers.Provider{
		{Name: "openai", Keywords: []string{"sk-proj-"}},
	})

	s := &CommonCrawlSource{
		BaseURL:  srv.URL,
		Registry: reg,
		Client:   NewClient(),
	}

	out := make(chan recon.Finding, 10)
	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
	defer cancel()

	err := s.Sweep(ctx, "", out)
	close(out)
	if err != nil {
		t.Fatalf("Sweep error: %v", err)
	}

	var findings []recon.Finding
	for f := range out {
		findings = append(findings, f)
	}
	if len(findings) == 0 {
		t.Fatal("expected at least one finding from Common Crawl index")
	}
	if findings[0].SourceType != "recon:commoncrawl" {
		t.Fatalf("expected recon:commoncrawl, got %s", findings[0].SourceType)
>>>>>>> worktree-agent-adad8c10
	}
}