Detector-Competition-Fix: Fix FakeJSON (deprecated) (#2073)

pkg/detectors/fakejson/fakejson.go

@@ -1,89 +0,0 @@
-package fakejson
-
-import (
-	"context"
-	"fmt"
-	"io"
-	"net/http"
-	"regexp"
-	"strings"
-
-	"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{}
-
-// Ensure the Scanner satisfies the interface at compile time.
-var _ detectors.Detector = (*Scanner)(nil)
-
-var (
-	client = common.SaneHttpClient()
-
-	// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
-	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"fakejson"}) + `\b([a-zA-Z0-9]{22})\b`)
-)
-
-// 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{"fakejson"}
-}
-
-// FromData will find and optionally verify FakeJSON 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 {
-		if len(match) != 2 {
-			continue
-		}
-		resMatch := strings.TrimSpace(match[1])
-
-		s1 := detectors.Result{
-			DetectorType: detectorspb.DetectorType_FakeJSON,
-			Raw:          []byte(resMatch),
-		}
-
-		if verify {
-			payload := strings.NewReader(fmt.Sprintf(`{"token":"%s","data":{"user_name":"nameFirst","user_email":"internetEmail","_repeat":3}}`, resMatch))
-			req, err := http.NewRequestWithContext(ctx, "POST", "https://app.fakejson.com/q", payload)
-			if err != nil {
-				continue
-			}
-			req.Header.Add("Content-Type", "application/json")
-			res, err := client.Do(req)
-			if err == nil {
-				bodyBytes, err := io.ReadAll(res.Body)
-				if err == nil {
-					bodyString := string(bodyBytes)
-					validResponse := strings.Contains(bodyString, `"user_email":`)
-					defer res.Body.Close()
-					if res.StatusCode >= 200 && res.StatusCode < 300 {
-						if validResponse {
-							s1.Verified = true
-						} else {
-							s1.Verified = false
-						}
-					} else {
-						// This function will check false positives for common test words, but also it will make sure the key appears 'random' enough to be a real key.
-						if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
-							continue
-						}
-					}
-				}
-			}
-		}
-
-		results = append(results, s1)
-	}
-
-	return results, nil
-}
-
-func (s Scanner) Type() detectorspb.DetectorType {
-	return detectorspb.DetectorType_FakeJSON
-}

pkg/detectors/fakejson/fakejson_test.go

@@ -1,120 +0,0 @@
-//go:build detectors
-// +build detectors
-
-package fakejson
-
-import (
-	"context"
-	"fmt"
-	"testing"
-	"time"
-
-	"github.com/kylelemons/godebug/pretty"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
-)
-
-func TestFakeJSON_FromChunk(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
-	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors1")
-	if err != nil {
-		t.Fatalf("could not get test secrets from GCP: %s", err)
-	}
-	secret := testSecrets.MustGetField("FAKEJSON")
-	inactiveSecret := testSecrets.MustGetField("FAKEJSON_INACTIVE")
-
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
-	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
-	}{
-		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a fakejson secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_FakeJSON,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
-		},
-		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a fakejson secret %s within but not valid", inactiveSecret)), // the secret would satisfy the regex but not pass validation
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_FakeJSON,
-					Verified:     false,
-				},
-			},
-			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,
-		},
-	}
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			s := Scanner{}
-			got, err := s.FromData(tt.args.ctx, tt.args.verify, tt.args.data)
-			if (err != nil) != tt.wantErr {
-				t.Errorf("FakeJSON.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])
-				}
-				got[i].Raw = nil
-			}
-			if diff := pretty.Compare(got, tt.want); diff != "" {
-				t.Errorf("FakeJSON.FromData() %s diff: (-got +want)\n%s", tt.name, diff)
-			}
-		})
-	}
-}
-
-func BenchmarkFromData(benchmark *testing.B) {
-	ctx := context.Background()
-	s := Scanner{}
-	for name, data := range detectors.MustGetBenchmarkData() {
-		benchmark.Run(name, func(b *testing.B) {
-			b.ResetTimer()
-			for n := 0; n < b.N; n++ {
-				_, err := s.FromData(ctx, false, data)
-				if err != nil {
-					b.Fatal(err)
-				}
-			}
-		})
-	}
-}

pkg/engine/defaults.go

@@ -238,7 +238,6 @@ import (
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/extractorapi"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/facebookoauth"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/faceplusplus"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/fakejson"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/fastforex"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/fastlypersonaltoken"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/feedier"
@@ -1116,7 +1115,6 @@ func DefaultDetectors() []detectors.Detector {
 		bitcoinaverage.Scanner{},
 		zipcodeapi.Scanner{},
 		gyazo.Scanner{},
-		fakejson.Scanner{},
 		// sparkpost.Scanner{},
 		locationiq.Scanner{},
 		saucelabs.Scanner{},

proto/detectors.proto

@@ -443,7 +443,7 @@ enum DetectorType {
   BitcoinAverage = 432;
   CommerceJS = 433;
   DetectLanguage = 434;
-  FakeJSON = 435;
+  FakeJSON = 435 [deprecated = true];
   Graphhopper = 436;
   Lexigram = 437;
   LinkPreview = 438;