[fix] - Dropbox detector

pkg/detectors/dropbox/dropbox.go

@@ -3,73 +3,91 @@ package dropbox
 import (
 	"context"
 	"fmt"
-	regexp "github.com/wasilibs/go-re2"
+	"io"
 	"net/http"
 
+	regexp "github.com/wasilibs/go-re2"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
 )
 
-type Scanner struct{}
+type Scanner struct{ client *http.Client }
 
 // Ensure the Scanner satisfies the interface at compile time.
 var _ detectors.Detector = (*Scanner)(nil)
 
 var (
-	keyPat = regexp.MustCompile(`\b(sl\.[A-Za-z0-9\-\_]{130,140})\b`)
+	defaultClient = common.SaneHttpClient()
+	keyPat        = regexp.MustCompile(`sl\.u\.[0-9a-zA-Z_-]+`)
 )
 
 // Keywords are used for efficiently pre-filtering chunks.
 // Use identifiers in the secret preferably, or the provider name.
-func (s Scanner) Keywords() []string {
-	return []string{"sl."}
-}
+func (s Scanner) Keywords() []string { return []string{"sl.u."} }
 
 // FromData will find and optionally verify Dropbox secrets in a given set of bytes.
 func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
-
 	dataStr := string(data)
 
-	matches := keyPat.FindAllStringSubmatch(dataStr, -1)
-
-	for _, match := range matches {
+	uniqueMatches := make(map[string]struct{})
+	for _, match := range keyPat.FindAllStringSubmatch(dataStr, -1) {
+		uniqueMatches[match[0]] = struct{}{}
+	}
 
-		result := detectors.Result{
+	for match := range uniqueMatches {
+		s1 := detectors.Result{
 			DetectorType: detectorspb.DetectorType_Dropbox,
-			Raw:          []byte(match[1]),
+			Raw:          []byte(match),
 		}
 
 		if verify {
-
-			baseURL := "https://api.dropboxapi.com/2/users/get_current_account"
-
-			client := common.SaneHttpClient()
-
-			req, err := http.NewRequestWithContext(ctx, "POST", baseURL, nil)
-			if err != nil {
-				continue
-			}
-			req.Header.Add("Authorization", fmt.Sprintf("Bearer %s", match[1]))
-			res, err := client.Do(req)
-			if err == nil {
-				res.Body.Close() // The request body is unused.
-
-				// 200 means good key for get current user
-				// 400 is bad (malformed)
-				// 403 bad scope
-				if res.StatusCode == http.StatusOK {
-					result.Verified = true
-				}
+			client := s.client
+			if client == nil {
+				client = defaultClient
 			}
+
+			isVerified, verificationErr := verifyMatch(ctx, client, match)
+			s1.Verified = isVerified
+			s1.SetVerificationError(verificationErr, match)
 		}
 
-		results = append(results, result)
+		results = append(results, s1)
 	}
 
 	return
 }
 
+func verifyMatch(ctx context.Context, client *http.Client, token string) (bool, error) {
+	const baseURL = "https://api.dropboxapi.com/2/check/user"
+	req, err := http.NewRequestWithContext(ctx, http.MethodPost, baseURL, nil)
+	if err != nil {
+		return false, nil
+	}
+	req.Header.Add("Authorization", "Bearer "+token)
+
+	res, err := client.Do(req)
+	if err != nil {
+		return false, err
+	}
+	defer func() {
+		_, _ = io.Copy(io.Discard, res.Body)
+		_ = res.Body.Close()
+	}()
+
+	switch res.StatusCode {
+	case http.StatusOK:
+		return true, nil
+	case http.StatusUnauthorized:
+		// 401 access token not found
+		// The secret is determinately not verified (nothing to do)
+		return false, nil
+	default:
+		return false, fmt.Errorf("unexpected HTTP response status %d", res.StatusCode)
+	}
+}
+
 func (s Scanner) Type() detectorspb.DetectorType {
 	return detectorspb.DetectorType_Dropbox
 }

pkg/detectors/dropbox/dropbox_integration_test.go

@@ -0,0 +1,149 @@
+//go:build detectors
+// +build detectors
+
+package dropbox
+
+import (
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/context"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestDropbox_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors5")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+
+	secret := testSecrets.MustGetField("DROPBOX")
+	secretInactive := testSecrets.MustGetField("DROPBOX_INACTIVE")
+
+	type args struct {
+		ctx    context.Context
+		data   []byte
+		verify bool
+	}
+	tests := []struct {
+		name                string
+		s                   Scanner
+		args                args
+		want                []detectors.Result
+		wantErr             bool
+		wantVerificationErr bool
+	}{
+		{
+			name: "found, verified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a dropbox secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Dropbox,
+					Verified:     true,
+					Raw:          []byte(secret),
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a dropbox secret %s within", secretInactive)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Dropbox,
+					Verified:     false,
+					Raw:          []byte(secretInactive),
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "not found",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte("You cannot find the secret within"),
+				verify: true,
+			},
+			want:    nil,
+			wantErr: false,
+		},
+		{
+			name: "found, would be verified if not for timeout",
+			s:    Scanner{client: common.SaneHttpClientTimeOut(1 * time.Microsecond)},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a dropbox token %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Dropbox,
+					Verified:     false,
+					Raw:          []byte(secret),
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: true,
+		},
+		{
+			name: "found, verified but unexpected api surface",
+			s:    Scanner{client: common.ConstantResponseHttpClient(500, "")},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a dropbox secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Dropbox,
+					Verified:     false,
+					Raw:          []byte(secret),
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: true,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got, err := tt.s.FromData(tt.args.ctx, tt.args.verify, tt.args.data)
+			if (err != nil) != tt.wantErr {
+				t.Errorf("Dropbox.FromData() error = %v, wantErr %v", err, tt.wantErr)
+				return
+			}
+
+			for i := range got {
+				if len(got[i].Raw) == 0 {
+					t.Fatalf("no raw secret present: \n %+v", got[i])
+				}
+				if (got[i].VerificationError() != nil) != tt.wantVerificationErr {
+					t.Fatalf("wantVerificationError = %v, verification error = %v", tt.wantVerificationErr, got[i].VerificationError())
+				}
+			}
+			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "verificationError", "ExtraData")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("Box.FromData() %s diff: (-got +want)\n%s", tt.name, diff)
+			}
+		})
+	}
+}