feat(12-03): implement AzureBlobScanner, DOSpacesScanner, and all cloud scanner tests

- AzureBlobScanner enumerates public Azure Blob containers with XML listing
- DOSpacesScanner enumerates public DO Spaces across 5 regions (S3-compatible XML)
- httptest-based tests for all four scanners: sweep, empty registry, ctx cancel, metadata
- All sources credentialless, compile-time interface assertions

pkg/recon/sources/s3scanner_test.go

@@ -0,0 +1,139 @@
+package sources
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/salvacybersec/keyhunter/pkg/providers"
+	"github.com/salvacybersec/keyhunter/pkg/recon"
+)
+
+func cloudTestRegistry() *providers.Registry {
+	return providers.NewRegistryFromProviders([]providers.Provider{
+		{Name: "testprov", Keywords: []string{"testprov-key"}},
+	})
+}
+
+func s3TestServer() *httptest.Server {
+	mux := http.NewServeMux()
+
+	// Respond to HEAD for the testprov-keys bucket with 200 (public).
+	mux.HandleFunc("/testprov-keys/", func(w http.ResponseWriter, r *http.Request) {
+		if r.Method == http.MethodHead {
+			w.WriteHeader(http.StatusOK)
+			return
+		}
+		// GET — return S3 ListBucketResult XML.
+		w.Header().Set("Content-Type", "application/xml")
+		_, _ = w.Write([]byte(`<?xml version="1.0" encoding="UTF-8"?>
+<ListBucketResult>
+  <Contents><Key>.env</Key></Contents>
+  <Contents><Key>config.yaml</Key></Contents>
+  <Contents><Key>readme.md</Key></Contents>
+  <Contents><Key>data/settings.json</Key></Contents>
+</ListBucketResult>`))
+	})
+
+	// All other buckets return 404 (not found).
+	mux.HandleFunc("/", func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(http.StatusNotFound)
+	})
+
+	return httptest.NewServer(mux)
+}
+
+func TestS3Scanner_Sweep(t *testing.T) {
+	srv := s3TestServer()
+	defer srv.Close()
+
+	src := &S3Scanner{
+		Registry: cloudTestRegistry(),
+		BaseURL:  srv.URL + "/%s/",
+		client:   NewClient(),
+	}
+
+	out := make(chan recon.Finding, 32)
+	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+	defer cancel()
+
+	if err := src.Sweep(ctx, "", out); err != nil {
+		t.Fatalf("Sweep error: %v", err)
+	}
+	close(out)
+
+	var findings []recon.Finding
+	for f := range out {
+		findings = append(findings, f)
+	}
+
+	// .env, config.yaml, data/settings.json match; readme.md does not.
+	if len(findings) != 3 {
+		t.Fatalf("expected 3 findings, got %d: %+v", len(findings), findings)
+	}
+
+	for _, f := range findings {
+		if f.SourceType != "recon:s3" {
+			t.Errorf("unexpected SourceType: %s", f.SourceType)
+		}
+		if f.Confidence != "medium" {
+			t.Errorf("unexpected Confidence: %s", f.Confidence)
+		}
+	}
+}
+
+func TestS3Scanner_EmptyRegistry(t *testing.T) {
+	src := &S3Scanner{
+		Registry: providers.NewRegistryFromProviders(nil),
+		Limiters: recon.NewLimiterRegistry(),
+		client:   NewClient(),
+	}
+
+	out := make(chan recon.Finding, 4)
+	ctx := context.Background()
+	if err := src.Sweep(ctx, "", out); err != nil {
+		t.Fatalf("Sweep error: %v", err)
+	}
+	close(out)
+
+	if len(out) != 0 {
+		t.Fatal("expected 0 findings with empty registry")
+	}
+}
+
+func TestS3Scanner_CtxCancelled(t *testing.T) {
+	srv := s3TestServer()
+	defer srv.Close()
+
+	src := &S3Scanner{
+		Registry: cloudTestRegistry(),
+		BaseURL:  srv.URL + "/%s/",
+		client:   NewClient(),
+	}
+
+	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 TestS3Scanner_EnabledAndMeta(t *testing.T) {
+	s := &S3Scanner{}
+	if s.Name() != "s3" {
+		t.Fatalf("unexpected name: %s", s.Name())
+	}
+	if !s.Enabled(recon.Config{}) {
+		t.Fatal("expected Enabled=true")
+	}
+	if s.RespectsRobots() {
+		t.Fatal("expected RespectsRobots=false")
+	}
+	if s.Burst() != 3 {
+		t.Fatal("expected Burst=3")
+	}
+}