Added pattern unit tests for detectors starting with the letters i through m (#3614)

* added pattern unit tests for detectors starting with the letters i through m

* removed unused variable from ldap pattern tests

* reset invoiceocean.go file to original

* reset jdbc.go file to original

* updated jdbc files file to original

* removed built tags from jdbc pattern test file

* updated mailgun detector to latest

* updated mixpanel detector to latest

* merged mongodb detector changes from main

---------

Co-authored-by: Kashif Khan <[email protected]>

pkg/detectors/ibmclouduserkey/ibmclouduserkey_integration_test.go

@@ -0,0 +1,117 @@
+//go:build detectors
+// +build detectors
+
+package ibmclouduserkey
+
+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 TestIbmCloudUserKey_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors3")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	secret := testSecrets.MustGetField("IBMCLOUDUSERKEY_TOKEN")
+	inactiveSecret := testSecrets.MustGetField("IBMCLOUDUSERKEY_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 ibmclouduserkey secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_IbmCloudUserKey,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a ibmclouduserkey 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_IbmCloudUserKey,
+					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("IbmCloudUserKey.FromData() error = %v, wantErr %v", err, tt.wantErr)
+				return
+			}
+			for i := range got {
+				got[i].Raw = nil
+			}
+			if diff := pretty.Compare(got, tt.want); diff != "" {
+				t.Errorf("IbmCloudUserKey.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/detectors/ibmclouduserkey/ibmclouduserkey_test.go

@@ -1,117 +1,91 @@
-//go:build detectors
-// +build detectors
-
 package ibmclouduserkey
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestIbmCloudUserKey_FromChunk(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
-	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors3")
-	if err != nil {
-		t.Fatalf("could not get test secrets from GCP: %s", err)
-	}
-	secret := testSecrets.MustGetField("IBMCLOUDUSERKEY_TOKEN")
-	inactiveSecret := testSecrets.MustGetField("IBMCLOUDUSERKEY_INACTIVE")
+var (
+	validPattern   = "0y0tceatuuwnIqFvzpfvb8Td6-07esplajvPznSvizma"
+	invalidPattern = "A0y0tceatuuwnIqFvzpfvb8Td6-07esplajvPznSvizmaF"
+	keyword        = "ibmclouduserkey"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestIbmCloudUserKey_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a ibmclouduserkey secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_IbmCloudUserKey,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword ibmclouduserkey",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a ibmclouduserkey 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_IbmCloudUserKey,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("IbmCloudUserKey.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				return
 			}
-			for i := range got {
-				got[i].Raw = nil
-			}
-			if diff := pretty.Compare(got, tt.want); diff != "" {
-				t.Errorf("IbmCloudUserKey.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
+				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
 				}
 			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
+			}
 		})
 	}
 }

pkg/detectors/iconfinder/iconfinder_integreation_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package iconfinder
+
+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 TestIconFinder_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("ICONFINDER")
+	inactiveSecret := testSecrets.MustGetField("ICONFINDER_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 iconfinder secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_IconFinder,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a iconfinder 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_IconFinder,
+					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("IconFinder.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("IconFinder.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/detectors/iconfinder/iconfinder_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package iconfinder
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestIconFinder_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("ICONFINDER")
-	inactiveSecret := testSecrets.MustGetField("ICONFINDER_INACTIVE")
+var (
+	validPattern   = "g48QWZXPpNeQjaUghu3aqKTxqcMtjVoY94Fv0lkYj4EGpbXTHd2GjbhWZ2uTmZLa"
+	invalidPattern = "g48QWZXPpNeQ-aUghu3aqKTxqcMtjVoY94Fv0lkY-4EGpbXTHd2GjbhWZ2uTmZLa"
+	keyword        = "iconfinder"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestIconFinder_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a iconfinder secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_IconFinder,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword iconfinder",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a iconfinder 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_IconFinder,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("IconFinder.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("IconFinder.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/iexapis/iexapis_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package iexapis
+
+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 TestIexapis_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors3")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	secret := testSecrets.MustGetField("IEXAPIS")
+	inactiveSecret := testSecrets.MustGetField("IEXAPIS_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 iexapis secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Iexapis,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a iexapis 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_Iexapis,
+					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("Iexapis.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("Iexapis.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/detectors/iexapis/iexapis_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package iexapis
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestIexapis_FromChunk(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
-	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors3")
-	if err != nil {
-		t.Fatalf("could not get test secrets from GCP: %s", err)
-	}
-	secret := testSecrets.MustGetField("IEXAPIS")
-	inactiveSecret := testSecrets.MustGetField("IEXAPIS_INACTIVE")
+var (
+	validPattern   = "sk_d21e2be3622049c7809f95cc02313821"
+	invalidPattern = "sg_h21e2be3622049c7809f95cc02313821"
+	keyword        = "iexapis"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestIexapis_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a iexapis secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Iexapis,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword iexapis",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a iexapis 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_Iexapis,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Iexapis.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Iexapis.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/iexcloud/iexcloud_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package iexcloud
+
+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 TestIexcloud_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("IEXCLOUD")
+	inactiveSecret := testSecrets.MustGetField("IEXCLOUD_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 iexcloud secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Iexcloud,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a iexcloud 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_Iexcloud,
+					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("Iexcloud.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("Iexcloud.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/detectors/iexcloud/iexcloud_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package iexcloud
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestIexcloud_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("IEXCLOUD")
-	inactiveSecret := testSecrets.MustGetField("IEXCLOUD_INACTIVE")
+var (
+	validPattern   = "sk_e51a4bf78d4c4c6ab906bac4c783cb91"
+	invalidPattern = "Ask_e51a4bf78d4c4c6ab906bac4c783cb91F"
+	keyword        = "iexcloud"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestIexcloud_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a iexcloud secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Iexcloud,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword iexcloud",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a iexcloud 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_Iexcloud,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Iexcloud.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Iexcloud.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/imagekit/imagekit_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package imagekit
+
+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 TestImagekit_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors3")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	secret := testSecrets.MustGetField("IMAGEKIT_TOKEN")
+	inactiveSecret := testSecrets.MustGetField("IMAGEKIT_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 imagekit secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Imagekit,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a imagekit 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_Imagekit,
+					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("Imagekit.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("Imagekit.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/detectors/imagekit/imagekit_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package imagekit
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestImagekit_FromChunk(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
-	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors3")
-	if err != nil {
-		t.Fatalf("could not get test secrets from GCP: %s", err)
-	}
-	secret := testSecrets.MustGetField("IMAGEKIT_TOKEN")
-	inactiveSecret := testSecrets.MustGetField("IMAGEKIT_INACTIVE")
+var (
+	validPattern   = "cHJpdmF0ZV9vNlM5MGxtbVE2Z0ZLbHFLS0xh"
+	invalidPattern = "-HJpdmF0ZV9vNlM5MGxtbVE2Z0ZLbHFLS0xh"
+	keyword        = "imagekit"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestImagekit_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a imagekit secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Imagekit,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword imagekit",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a imagekit 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_Imagekit,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Imagekit.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Imagekit.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/imagga/imagga_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package imagga
+
+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 TestImagga_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("IMAGGA")
+	inactiveSecret := testSecrets.MustGetField("IMAGGA_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 imagga secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Imagga,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a imagga 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_Imagga,
+					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("Imagga.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("Imagga.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/detectors/imagga/imagga_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package imagga
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestImagga_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("IMAGGA")
-	inactiveSecret := testSecrets.MustGetField("IMAGGA_INACTIVE")
+var (
+	validPattern   = "2Lnr2CqKYvAzUrQ7mv0twEviqSq03Zq=w0F7EOJvY30J8oj5KSQZVxQmW5UYUI7bEEdjhmDK"
+	invalidPattern = "2Lnr2CqKYvAzUrQ7mv0twEviqSq03Zq=w0F7EOJvY30J8oj5KSQZVxQmW5UYUI7bEEdjhmD"
+	keyword        = "imagga"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestImagga_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a imagga secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Imagga,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword imagga",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a imagga 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_Imagga,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Imagga.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Imagga.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/impala/impala_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package impala
+
+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 TestImpala_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("IMPALA")
+	inactiveSecret := testSecrets.MustGetField("IMPALA_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 impala secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Impala,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a impala 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_Impala,
+					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("Impala.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("Impala.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/detectors/impala/impala_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package impala
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestImpala_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("IMPALA")
-	inactiveSecret := testSecrets.MustGetField("IMPALA_INACTIVE")
+var (
+	validPattern   = "2MitCEv5ZAguR57EJkD7deNBssSC0lNr897akiBb9cEMoi"
+	invalidPattern = "2MitCEv5ZAguR57EJkD7deNBssSC0lNr897akiBb9cEMo"
+	keyword        = "impala"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestImpala_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a impala secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Impala,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword impala",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a impala 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_Impala,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Impala.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Impala.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/infura/infura_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package infura
+
+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 TestInfura_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors4")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	secret := testSecrets.MustGetField("INFURA")
+	inactiveSecret := testSecrets.MustGetField("INFURA_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 infura secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Infura,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a infura 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_Infura,
+					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("Infura.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("Infura.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/detectors/infura/infura_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package infura
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestInfura_FromChunk(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
-	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors4")
-	if err != nil {
-		t.Fatalf("could not get test secrets from GCP: %s", err)
-	}
-	secret := testSecrets.MustGetField("INFURA")
-	inactiveSecret := testSecrets.MustGetField("INFURA_INACTIVE")
+var (
+	validPattern   = "8vr0j5458z4xq57qkozagbt2l6nnjetq"
+	invalidPattern = "8vr0j5458z4xq57qkozagbt2l6nnjet"
+	keyword        = "infura"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestInfura_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a infura secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Infura,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword infura",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a infura 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_Infura,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Infura.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Infura.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/insightly/insightly_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package insightly
+
+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 TestInsightly_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("INSIGHTLY")
+	inactiveSecret := testSecrets.MustGetField("INSIGHTLY_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 insightly secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Insightly,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a insightly 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_Insightly,
+					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("Insightly.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("Insightly.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/detectors/insightly/insightly_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package insightly
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestInsightly_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("INSIGHTLY")
-	inactiveSecret := testSecrets.MustGetField("INSIGHTLY_INACTIVE")
+var (
+	validPattern   = "9ytdevl7jl75ylv06jx1m3qzktlr0x89m8fr"
+	invalidPattern = "9ytdevl7jl75ylv06jx1m3qzktlr0x89m8f"
+	keyword        = "insightly"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestInsightly_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a insightly secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Insightly,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword insightly",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a insightly 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_Insightly,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Insightly.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Insightly.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/instabot/instabot_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package instabot
+
+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 TestInstabot_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors4")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	secret := testSecrets.MustGetField("INSTABOT")
+	inactiveSecret := testSecrets.MustGetField("INSTABOT_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 instabot secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Instabot,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a instabot 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_Instabot,
+					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("Instabot.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("Instabot.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/detectors/instabot/instabot_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package instabot
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestInstabot_FromChunk(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
-	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors4")
-	if err != nil {
-		t.Fatalf("could not get test secrets from GCP: %s", err)
-	}
-	secret := testSecrets.MustGetField("INSTABOT")
-	inactiveSecret := testSecrets.MustGetField("INSTABOT_INACTIVE")
+var (
+	validPattern   = "7tB=6ZFzMLh7npsKURT3wqCRE0lAAn/4bLgkuR7Q=IFt"
+	invalidPattern = "7tB=6ZFzMLh7npsKURT3wqCRE0lAAn/4bLgkuR7Q=IF"
+	keyword        = "instabot"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestInstabot_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a instabot secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Instabot,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword instabot",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a instabot 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_Instabot,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Instabot.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Instabot.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/instamojo/instamojo_integration_test.go

@@ -0,0 +1,123 @@
+//go:build detectors
+// +build detectors
+
+package instamojo
+
+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 TestInstamojo_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)
+	}
+	id := testSecrets.MustGetField("INSTAMOJO_CLIENT_ID")
+	secret := testSecrets.MustGetField("INSTAMOJO_SECRET")
+	inactiveSecret := testSecrets.MustGetField("INSTAMOJO_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 instamojo secret %s within id %s", secret, id)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Instamojo,
+					Verified:     true,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a instamojo secret %s within but not valid, within id %s", inactiveSecret, id)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Instamojo,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: true,
+		},
+		{
+			name: "not found",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte("You cannot find the secret within"),
+				verify: true,
+			},
+			want:                nil,
+			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("Instamojo.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("Instamojo.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/detectors/instamojo/instamojo_test.go

@@ -1,122 +1,87 @@
-//go:build detectors
-// +build detectors
-
 package instamojo
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestInstamojo_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)
-	}
-	id := testSecrets.MustGetField("INSTAMOJO_CLIENT_ID")
-	secret := testSecrets.MustGetField("INSTAMOJO_SECRET")
-	inactiveSecret := testSecrets.MustGetField("INSTAMOJO_INACTIVE")
+var (
+	validKeyPattern      = "ZrGOAl9jlTlAKxw4hXZXeRmd6wvndEr2pX0fqDv2"
+	invalidKeyPattern    = "VdZVfhpWN0O0FL0KKZauMMtgJytUPAmkNRO9Vwq"
+	validSecretPattern   = "a1B2c3D4e5F6g7H8i9J0k1L2m3N4o5P6q7R8s9T0u1V2w3X4y5Z6a7B8c9D0e1F2g3H4i5J6k7L8m9N0o1P2q3R4s5T6u7V8w9X0y1Z2a3B4c5D6e7F8g9H0D2e3F4g5"
+	invalidSecretPattern = "V2w3X4y5Z6a7!8c9D0e1F2g3H4i5J6k7L8m9N0o@P2q3R4s5T6u7V8w9X0y1Z2a3_4c5D6e7F8g9H0i1J2k3L4m5-6o7P8q9R0s1T2u3V4w5X6y7Z8a9B0c1D2e3F4+="
+	keyword              = "instamojo"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestInstamojo_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name                string
-		s                   Scanner
-		args                args
-		want                []detectors.Result
-		wantErr             bool
-		wantVerificationErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a instamojo secret %s within id %s", secret, id)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Instamojo,
-					Verified:     true,
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: false,
+			name:  "valid pattern - with keyword instamojo",
+			input: fmt.Sprintf("%s '%s' %s '%s'", keyword, validKeyPattern, keyword, validSecretPattern),
+			want:  []string{"ZrGOAl9jlTlAKxw4hXZXeRmd6wvndEr2pX0fqDv2"},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a instamojo secret %s within but not valid, within id %s", inactiveSecret, id)), // the secret would satisfy the regex but not pass validation
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Instamojo,
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: true,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s' secret = '%s'", keyword, validKeyPattern, validSecretPattern),
+			want:  []string{},
 		},
 		{
-			name: "not found",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte("You cannot find the secret within"),
-				verify: true,
-			},
-			want:                nil,
-			wantErr:             false,
-			wantVerificationErr: true,
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s key = '%s' secret = '%s'", keyword, invalidKeyPattern, invalidSecretPattern),
+			want:  []string{},
 		},
 	}
-	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("Instamojo.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Instamojo.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/intercom/intercom_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package intercom
+
+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 TestInterCom_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors3")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	secret := testSecrets.MustGetField("INTERCOM_TOKEN")
+	inactiveSecret := testSecrets.MustGetField("INTERCOM_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 intercom secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Intercom,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a intercom 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_Intercom,
+					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("InterCom.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("InterCom.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/detectors/intercom/intercom_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package intercom
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestInterCom_FromChunk(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
-	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors3")
-	if err != nil {
-		t.Fatalf("could not get test secrets from GCP: %s", err)
-	}
-	secret := testSecrets.MustGetField("INTERCOM_TOKEN")
-	inactiveSecret := testSecrets.MustGetField("INTERCOM_INACTIVE")
+var (
+	validPattern   = "dG9rOmE2EzJhNmQwXzdsOpFfNDcxNV84GPU2XzMnMWRiYTIxOTc2ZDevLcB="
+	invalidPattern = "m2=L&7-I2',Ei.pC16@~s<w<r:7UeE2?jZ<l(<YdCLq,8<^o#v8woZ7wpv]="
+	keyword        = "intercom"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestInterCom_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a intercom secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Intercom,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword intercom",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a intercom 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_Intercom,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("InterCom.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("InterCom.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/interseller/interseller_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package interseller
+
+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 TestInterseller_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors4")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	secret := testSecrets.MustGetField("INTERSELLER")
+	inactiveSecret := testSecrets.MustGetField("INTERSELLER_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 interseller secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Interseller,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a interseller 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_Interseller,
+					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("Interseller.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("Interseller.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/detectors/interseller/interseller_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package interseller
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestInterseller_FromChunk(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
-	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors4")
-	if err != nil {
-		t.Fatalf("could not get test secrets from GCP: %s", err)
-	}
-	secret := testSecrets.MustGetField("INTERSELLER")
-	inactiveSecret := testSecrets.MustGetField("INTERSELLER_INACTIVE")
+var (
+	validPattern   = "7e1e818a-2bc5-5042-5b5d-8bf2465e1d81"
+	invalidPattern = "7e1e818a-2bc5-5042-5b5d-8bf2465e1d8"
+	keyword        = "interseller"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestInterseller_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a interseller secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Interseller,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword interseller",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a interseller 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_Interseller,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Interseller.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Interseller.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/intrinio/intrinio_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package intrinio
+
+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 TestIntrinio_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("INTRINIO")
+	inactiveSecret := testSecrets.MustGetField("INTRINIO_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 intrinio secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Intrinio,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a intrinio 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_Intrinio,
+					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("Intrinio.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("Intrinio.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/detectors/intrinio/intrinio_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package intrinio
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestIntrinio_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("INTRINIO")
-	inactiveSecret := testSecrets.MustGetField("INTRINIO_INACTIVE")
+var (
+	validPattern   = "RgqgmHdKJ4nQD7jk4whnZe6iox2sHSbcQf4UaLYE2UAw"
+	invalidPattern = "RgqgmHdKJ4nQD7jk4whnZe6iox2sHSbcQf4UaLYE2UA"
+	keyword        = "intrinio"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestIntrinio_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a intrinio secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Intrinio,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword intrinio",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a intrinio 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_Intrinio,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Intrinio.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Intrinio.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/invoiceocean/invoiceocean_integration_test.go

@@ -0,0 +1,121 @@
+//go:build detectors
+// +build detectors
+
+package invoiceocean
+
+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 TestInvoiceocean_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors2")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	secret := testSecrets.MustGetField("INVOICEOCEAN")
+	url := testSecrets.MustGetField("INVOICEOCEAN_URL")
+	inactiveSecret := testSecrets.MustGetField("INVOICEOCEAN_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 invoiceocean secret %s within %s", secret, url)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_InvoiceOcean,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a invoiceocean secret %s within %s but not valid", inactiveSecret, url)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_InvoiceOcean,
+					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("Invoiceocean.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("Invoiceocean.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/detectors/invoiceocean/invoiceocean_test.go

@@ -1,120 +1,87 @@
-//go:build detectors
-// +build detectors
-
 package invoiceocean
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestInvoiceocean_FromChunk(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
-	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors2")
-	if err != nil {
-		t.Fatalf("could not get test secrets from GCP: %s", err)
-	}
-	secret := testSecrets.MustGetField("INVOICEOCEAN")
-	url := testSecrets.MustGetField("INVOICEOCEAN_URL")
-	inactiveSecret := testSecrets.MustGetField("INVOICEOCEAN_INACTIVE")
+var (
+	validKeyPattern   = "ZWd1e2141Q2R1ds23sdX"
+	invalidKeyPattern = "ZWd.e214-Q2R1ds$3sd="
+	validUrlPattern   = "4f2a9c.invoiceocean.com"
+	invalidUrlPattern = "4f2a9c.invoiceocean.net"
+	keyword           = "invoiceocean"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestInvoiceocean_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a invoiceocean secret %s within %s", secret, url)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_InvoiceOcean,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword invoiceocean",
+			input: fmt.Sprintf("%s '%s' %s '%s'", keyword, validKeyPattern, keyword, validUrlPattern),
+			want:  []string{"ZWd1e2141Q2R1ds23sdX"},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a invoiceocean secret %s within %s but not valid", inactiveSecret, url)), // the secret would satisfy the regex but not pass validation
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_InvoiceOcean,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s' secret = '%s'", keyword, validKeyPattern, validUrlPattern),
+			want:  []string{},
 		},
 		{
-			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:  "invalid pattern",
+			input: fmt.Sprintf("%s key = '%s' secret = '%s'", keyword, invalidKeyPattern, invalidUrlPattern),
+			want:  []string{},
 		},
 	}
-	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("Invoiceocean.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Invoiceocean.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/ip2location/ip2location_integration_test.go

@@ -0,0 +1,128 @@
+//go:build detectors
+// +build detectors
+
+package ip2location
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestIp2location_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("IP2LOCATION")
+	inactiveSecret := testSecrets.MustGetField("IP2LOCATION_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 ip2location secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Ip2location,
+					Verified:     true,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a ip2location 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_Ip2location,
+					Verified:     false,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: 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,
+			wantVerificationErr: false,
+		},
+	}
+	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("Ip2location.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.want[i].VerificationError(), got[i].VerificationError())
+				}
+			}
+			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "verificationError")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("Ip2location.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/detectors/ip2location/ip2location_test.go

@@ -1,127 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package ip2location
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
 	"github.com/google/go-cmp/cmp"
-	"github.com/google/go-cmp/cmp/cmpopts"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestIp2location_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("IP2LOCATION")
-	inactiveSecret := testSecrets.MustGetField("IP2LOCATION_INACTIVE")
+var (
+	validPattern   = "UBENM81QDKGJ7GHB6Q68L2B4Z06DO3YD"
+	invalidPattern = "UBENM81QDKGJ7GHB6Q68L2B4Z06DO3Y"
+	keyword        = "ip2location"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestIp2location_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name                string
-		s                   Scanner
-		args                args
-		want                []detectors.Result
-		wantErr             bool
-		wantVerificationErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a ip2location secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Ip2location,
-					Verified:     true,
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: false,
+			name:  "valid pattern - with keyword ip2location",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a ip2location 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_Ip2location,
-					Verified:     false,
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "not found",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte("You cannot find the secret within"),
-				verify: true,
-			},
-			want:                nil,
-			wantErr:             false,
-			wantVerificationErr: false,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Ip2location.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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.want[i].VerificationError(), got[i].VerificationError())
-				}
-			}
-			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "verificationError")
-			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
-				t.Errorf("Ip2location.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/ipapi/ipapi_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package ipapi
+
+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 TestIpapi_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("IPAPI")
+	inactiveSecret := testSecrets.MustGetField("IPAPI_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 ipapi secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Ipapi,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a ipapi 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_Ipapi,
+					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("Ipapi.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("Ipapi.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/detectors/ipapi/ipapi_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package ipapi
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestIpapi_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("IPAPI")
-	inactiveSecret := testSecrets.MustGetField("IPAPI_INACTIVE")
+var (
+	validPattern   = "af6dmku2agtwytrdfxxyf3gcszoa6one"
+	invalidPattern = "af6dmku2agtwytrdfxxyf3gcszoa6on"
+	keyword        = "ipapi"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestIpapi_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a ipapi secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Ipapi,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword ipapi",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a ipapi 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_Ipapi,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Ipapi.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Ipapi.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/ipgeolocation/ipgeolocation_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package ipgeolocation
+
+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 TestIPGeolocation_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("IPGEOLOCATION")
+	inactiveSecret := testSecrets.MustGetField("IPGEOLOCATION_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 ipgeolocation secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_IPGeolocation,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a ipgeolocation 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_IPGeolocation,
+					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("IPGeolocation.FromData() error = %v, wantErr %v", err, tt.wantErr)
+				return
+			}
+			for i := range got {
+				if len(got[i].Raw) == 0 {
+					t.Fatal("no raw secret present")
+				}
+				got[i].Raw = nil
+			}
+			if diff := pretty.Compare(got, tt.want); diff != "" {
+				t.Errorf("IPGeolocation.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/detectors/ipgeolocation/ipgeolocation_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package ipgeolocation
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestIPGeolocation_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("IPGEOLOCATION")
-	inactiveSecret := testSecrets.MustGetField("IPGEOLOCATION_INACTIVE")
+var (
+	validPattern   = "08blecim3dji81ott4ipeh7kk3mcqs9f"
+	invalidPattern = "08blecim3dji81ott4ipeh7kk3mcqs9"
+	keyword        = "ipgeolocation"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestIPGeolocation_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a ipgeolocation secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_IPGeolocation,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword ipgeolocation",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a ipgeolocation 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_IPGeolocation,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("IPGeolocation.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				return
 			}
-			for i := range got {
-				if len(got[i].Raw) == 0 {
-					t.Fatal("no raw secret present")
-				}
-				got[i].Raw = nil
-			}
-			if diff := pretty.Compare(got, tt.want); diff != "" {
-				t.Errorf("IPGeolocation.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/ipinfo/ipinfo_integration_test.go

@@ -0,0 +1,162 @@
+//go:build detectors
+// +build detectors
+
+package ipinfo
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestIpinfo_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("IPINFO")
+	inactiveSecret := testSecrets.MustGetField("IPINFO_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 ipinfo secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_IPInfo,
+					Verified:     true,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a ipinfo 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_IPInfo,
+					Verified:     false,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: 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,
+			wantVerificationErr: 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 ipinfo secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_IPInfo,
+					Verified:     false,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: true,
+		},
+		{
+			name: "found, verified but unexpected api surface",
+			s:    Scanner{client: common.ConstantResponseHttpClient(404, "")},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a ipinfo secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_IPInfo,
+					Verified:     false,
+				},
+			},
+			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("Ipinfo.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{}, "Raw", "verificationError")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("Ipinfo.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/detectors/ipinfo/ipinfo_test.go

@@ -1,161 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package ipinfo
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
 	"github.com/google/go-cmp/cmp"
-	"github.com/google/go-cmp/cmp/cmpopts"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestIpinfo_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("IPINFO")
-	inactiveSecret := testSecrets.MustGetField("IPINFO_INACTIVE")
+var (
+	validPattern   = "3ff77bb6fe6885"
+	invalidPattern = "3ff77bb6fe688"
+	keyword        = "ipinfo"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestIpinfo_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name                string
-		s                   Scanner
-		args                args
-		want                []detectors.Result
-		wantErr             bool
-		wantVerificationErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a ipinfo secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_IPInfo,
-					Verified:     true,
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: false,
+			name:  "valid pattern - with keyword ipinfo",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a ipinfo 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_IPInfo,
-					Verified:     false,
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "not found",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte("You cannot find the secret within"),
-				verify: true,
-			},
-			want:                nil,
-			wantErr:             false,
-			wantVerificationErr: false,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
 		},
 		{
-			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 ipinfo secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_IPInfo,
-					Verified:     false,
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: true,
-		},
-		{
-			name: "found, verified but unexpected api surface",
-			s:    Scanner{client: common.ConstantResponseHttpClient(404, "")},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a ipinfo secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_IPInfo,
-					Verified:     false,
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: true,
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Ipinfo.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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{}, "Raw", "verificationError")
-			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
-				t.Errorf("Ipinfo.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/ipinfodb/ipinfodb_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package ipinfodb
+
+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 TestIPinfoDB_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("IPINFODB")
+	inactiveSecret := testSecrets.MustGetField("IPINFODB_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 ipinfodb secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_IPinfoDB,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a ipinfodb 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_IPinfoDB,
+					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("IPinfoDB.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("IPinfoDB.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/detectors/ipinfodb/ipinfodb_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package ipinfodb
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestIPinfoDB_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("IPINFODB")
-	inactiveSecret := testSecrets.MustGetField("IPINFODB_INACTIVE")
+var (
+	validPattern   = "5n2gzgwp07ttl1gsizaxcdkmb0osp0eiqi39nkzqq2mqqe94jrhwvhc2lvgqkta5"
+	invalidPattern = "5n2gzgwp07ttl1gsizaxcdkmb0osp0eiqi39nkzqq2mqqe94jrhwvhc2lvgqkta"
+	keyword        = "ipinfodb"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestIPinfoDB_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a ipinfodb secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_IPinfoDB,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword ipinfodb",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a ipinfodb 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_IPinfoDB,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("IPinfoDB.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("IPinfoDB.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/ipquality/ipquality_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package ipquality
+
+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 TestIpquality_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors2")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	secret := testSecrets.MustGetField("IPQUALITY")
+	inactiveSecret := testSecrets.MustGetField("IPQUALITY_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 ipquality secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_IPQuality,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a ipquality 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_IPQuality,
+					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("Ipquality.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("Ipquality.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/detectors/ipquality/ipquality_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package ipquality
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestIpquality_FromChunk(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
-	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors2")
-	if err != nil {
-		t.Fatalf("could not get test secrets from GCP: %s", err)
-	}
-	secret := testSecrets.MustGetField("IPQUALITY")
-	inactiveSecret := testSecrets.MustGetField("IPQUALITY_INACTIVE")
+var (
+	validPattern   = "p1b3ref1b3gzpn15gduecwvhaat0du5k"
+	invalidPattern = "p1b3ref1b3gzpn15gduecwvhaat0du5"
+	keyword        = "ipquality"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestIpquality_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a ipquality secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_IPQuality,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword ipquality",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a ipquality 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_IPQuality,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Ipquality.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Ipquality.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/ipstack/ipstack_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package ipstack
+
+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 TestIpStack_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors3")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	secret := testSecrets.MustGetField("IPSTACK_TOKEN")
+	inactiveSecret := testSecrets.MustGetField("IPSTACK_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 IPSTACK secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_IpStack,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a IPSTACK 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_IpStack,
+					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("IpStack.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("IPSTACK.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/detectors/ipstack/ipstack_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package ipstack
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestIpStack_FromChunk(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
-	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors3")
-	if err != nil {
-		t.Fatalf("could not get test secrets from GCP: %s", err)
-	}
-	secret := testSecrets.MustGetField("IPSTACK_TOKEN")
-	inactiveSecret := testSecrets.MustGetField("IPSTACK_INACTIVE")
+var (
+	validPattern   = "FA0E2B0be2fd6076b59c8696783eadeB"
+	invalidPattern = "FA0E2B0be2fd6076b59c8696783eade"
+	keyword        = "ipstack"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestIpStack_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a IPSTACK secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_IpStack,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword ipstack",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a IPSTACK 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_IpStack,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("IpStack.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("IPSTACK.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/jdbc/jdbc_integration_test.go

@@ -190,3 +190,192 @@ func TestJdbcVerified(t *testing.T) {
 		})
 	}
 }
+
+func TestJdbc_FromChunk(t *testing.T) {
+	type args struct {
+		ctx    context.Context
+		data   []byte
+		verify bool
+	}
+	tests := []struct {
+		name    string
+		args    args
+		want    []detectors.Result
+		wantErr bool
+	}{
+		{
+			name: "found, unverified",
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(`jdbc connection string: jdbc:mysql://hello.test.us-east-1.rds.amazonaws.com:3306/testdb?password=testpassword <-`),
+				verify: false,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_JDBC,
+					Verified:     false,
+					Redacted:     "jdbc:mysql://hello.test.us-east-1.rds.amazonaws.com:3306/testdb?password=************",
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified numeric password",
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(`jdbc connection string: jdbc:postgresql://host:5342/testdb?password=123456 <-`),
+				verify: false,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_JDBC,
+					Verified:     false,
+					Redacted:     "jdbc:postgresql://host:5342/testdb?password=******",
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "not found",
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte("You cannot find the secret within"),
+				verify: false,
+			},
+			want:    nil,
+			wantErr: false,
+		},
+		{
+			name: "found double quoted string, unverified",
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(`CONN="jdbc:postgres://hello.test.us-east-1.rds.amazonaws.com:3306/testdb?password=testpassword"`),
+				verify: false,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_JDBC,
+					Verified:     false,
+					Redacted:     "jdbc:postgres://hello.test.us-east-1.rds.amazonaws.com:3306/testdb?password=************",
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found single quoted string, unverified",
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(`CONN='jdbc:postgres://hello.test.us-east-1.rds.amazonaws.com:3306/testdb?password=testpassword'`),
+				verify: false,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_JDBC,
+					Verified:     false,
+					Redacted:     "jdbc:postgres://hello.test.us-east-1.rds.amazonaws.com:3306/testdb?password=************",
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "sqlserver, unverified",
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(`jdbc:sqlserver://a.b.c.net;database=database-name;spring.datasource.password=super-secret-password`),
+				verify: false,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_JDBC,
+					Verified:     false,
+					Redacted:     "jdbc:sqlserver://a.b.c.net;database=database-name;spring.datasource.password=*********************",
+				},
+			},
+			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("Jdbc.FromData() error = %v, wantErr %v", err, tt.wantErr)
+				return
+			}
+			if os.Getenv("FORCE_PASS_DIFF") == "true" {
+				return
+			}
+			for i := range got {
+				if len(got[i].Raw) == 0 {
+					t.Fatal("no raw secret present")
+				}
+				got[i].Raw = nil
+				got[i].AnalysisInfo = nil
+			}
+			if diff := pretty.Compare(got, tt.want); diff != "" {
+				t.Errorf("Jdbc.FromData() %s diff: (-got +want)\n%s", tt.name, diff)
+			}
+		})
+	}
+}
+
+func TestJdbc_Redact(t *testing.T) {
+	tests := []struct {
+		name string
+		conn string
+		want string
+	}{
+		{
+			name: "basic auth'",
+			conn: "//user:secret@tcp(127.0.0.1:3306)/",
+			want: "//user:******@tcp(127.0.0.1:3306)/",
+		},
+		{
+			name: "basic auth including raw string 'pass'",
+			conn: "//wrongUser:wrongPass@tcp(127.0.0.1:3306)/",
+			want: "//wrongUser:*********@tcp(127.0.0.1:3306)/",
+		},
+		{
+			name: "basic auth including raw string 'pass' with unfortunate db name",
+			conn: "//wrongUser:wrongPass@tcp(127.0.0.1:3306)/passwords",
+			want: "//wrongUser:*********@tcp(127.0.0.1:3306)/passwords",
+		},
+		{
+			name: "url param-style",
+			conn: "jdbc:postgresql://localhost:5432/foo?sslmode=disable&password=p@ssw04d",
+			want: "jdbc:postgresql://localhost:5432/foo?sslmode=disable&password=********",
+		},
+		{
+			name: "odbc-style without server",
+			conn: "//odbc:server=localhost;user id=sa;database=master;password=/p?s=sw&rd",
+			want: "//odbc:server=localhost;user id=sa;database=master;password=**********",
+		},
+		{
+			name: "odbc-style with server",
+			conn: "jdbc:sqlserver://a.b.c.net;database=database-name;spring.datasource.password=super-secret-password",
+			want: "jdbc:sqlserver://a.b.c.net;database=database-name;spring.datasource.password=*********************",
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := tryRedactAnonymousJDBC(tt.conn)
+			assert.Equal(t, tt.want, got)
+		})
+	}
+}
+
+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/detectors/jdbc/jdbc_test.go

@@ -1,143 +1,81 @@
-//go:build detectors
-// +build detectors
-
 package jdbc
 
 import (
 	"context"
+	"fmt"
 	"os"
 	"testing"
 
-	"github.com/stretchr/testify/assert"
-
+	"github.com/google/go-cmp/cmp"
 	"github.com/kylelemons/godebug/pretty"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestJdbc_FromChunk(t *testing.T) {
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+var (
+	validPattern   = "jdbc:mysql:localhost:3306/mydatabase"
+	invalidPattern = "jdbc:my?ql:localhost:3306/my database"
+	keyword        = "jdbc"
+)
+
+func TestJdbc_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, unverified",
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(`jdbc connection string: jdbc:mysql://hello.test.us-east-1.rds.amazonaws.com:3306/testdb?password=testpassword <-`),
-				verify: false,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_JDBC,
-					Verified:     false,
-					Redacted:     "jdbc:mysql://hello.test.us-east-1.rds.amazonaws.com:3306/testdb?password=************",
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified numeric password",
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(`jdbc connection string: jdbc:postgresql://host:5342/testdb?password=123456 <-`),
-				verify: false,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_JDBC,
-					Verified:     false,
-					Redacted:     "jdbc:postgresql://host:5342/testdb?password=******",
-				},
-			},
-			wantErr: false,
-		},
-		{
-			name: "not found",
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte("You cannot find the secret within"),
-				verify: false,
-			},
-			want:    nil,
-			wantErr: false,
-		},
-		{
-			name: "found double quoted string, unverified",
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(`CONN="jdbc:postgres://hello.test.us-east-1.rds.amazonaws.com:3306/testdb?password=testpassword"`),
-				verify: false,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_JDBC,
-					Verified:     false,
-					Redacted:     "jdbc:postgres://hello.test.us-east-1.rds.amazonaws.com:3306/testdb?password=************",
-				},
-			},
-			wantErr: false,
-		},
-		{
-			name: "found single quoted string, unverified",
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(`CONN='jdbc:postgres://hello.test.us-east-1.rds.amazonaws.com:3306/testdb?password=testpassword'`),
-				verify: false,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_JDBC,
-					Verified:     false,
-					Redacted:     "jdbc:postgres://hello.test.us-east-1.rds.amazonaws.com:3306/testdb?password=************",
-				},
-			},
-			wantErr: false,
-		},
-		{
-			name: "sqlserver, unverified",
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(`jdbc:sqlserver://a.b.c.net;database=database-name;spring.datasource.password=super-secret-password`),
-				verify: false,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_JDBC,
-					Verified:     false,
-					Redacted:     "jdbc:sqlserver://a.b.c.net;database=database-name;spring.datasource.password=*********************",
-				},
-			},
-			wantErr: false,
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Jdbc.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				return
 			}
-			if os.Getenv("FORCE_PASS_DIFF") == "true" {
+
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
 				return
 			}
-			for i := range got {
-				if len(got[i].Raw) == 0 {
-					t.Fatal("no raw secret present")
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
-				got[i].Raw = nil
-				got[i].AnalysisInfo = nil
+				return
 			}
-			if diff := pretty.Compare(got, tt.want); diff != "" {
-				t.Errorf("Jdbc.FromData() %s diff: (-got +want)\n%s", tt.name, diff)
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}
@@ -193,64 +131,3 @@ func TestJdbc_FromDataWithIgnorePattern(t *testing.T) {
 		})
 	}
 }
-
-func TestJdbc_Redact(t *testing.T) {
-	tests := []struct {
-		name string
-		conn string
-		want string
-	}{
-		{
-			name: "basic auth'",
-			conn: "//user:secret@tcp(127.0.0.1:3306)/",
-			want: "//user:******@tcp(127.0.0.1:3306)/",
-		},
-		{
-			name: "basic auth including raw string 'pass'",
-			conn: "//wrongUser:wrongPass@tcp(127.0.0.1:3306)/",
-			want: "//wrongUser:*********@tcp(127.0.0.1:3306)/",
-		},
-		{
-			name: "basic auth including raw string 'pass' with unfortunate db name",
-			conn: "//wrongUser:wrongPass@tcp(127.0.0.1:3306)/passwords",
-			want: "//wrongUser:*********@tcp(127.0.0.1:3306)/passwords",
-		},
-		{
-			name: "url param-style",
-			conn: "jdbc:postgresql://localhost:5432/foo?sslmode=disable&password=p@ssw04d",
-			want: "jdbc:postgresql://localhost:5432/foo?sslmode=disable&password=********",
-		},
-		{
-			name: "odbc-style without server",
-			conn: "//odbc:server=localhost;user id=sa;database=master;password=/p?s=sw&rd",
-			want: "//odbc:server=localhost;user id=sa;database=master;password=**********",
-		},
-		{
-			name: "odbc-style with server",
-			conn: "jdbc:sqlserver://a.b.c.net;database=database-name;spring.datasource.password=super-secret-password",
-			want: "jdbc:sqlserver://a.b.c.net;database=database-name;spring.datasource.password=*********************",
-		},
-	}
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			got := tryRedactAnonymousJDBC(tt.conn)
-			assert.Equal(t, tt.want, got)
-		})
-	}
-}
-
-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/detectors/jiratoken/v1/jiratoken_integration_test.go

@@ -0,0 +1,179 @@
+//go:build detectors
+// +build detectors
+
+package jiratoken
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestJiraToken_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("JIRA_TOKEN")
+	inactiveSecret := testSecrets.MustGetField("JIRA_INACTIVE")
+	email := testSecrets.MustGetField("JIRA_EMAIL")
+	domain := testSecrets.MustGetField("JIRA_DOMAIN")
+
+	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 jira secret %s within jira %s with jira %s", secret, email, domain)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_JiraToken,
+					Verified:     true,
+					ExtraData: map[string]string{
+						"rotation_guide": "https://howtorotate.com/docs/tutorials/atlassian/",
+						"version":        "1",
+					},
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a jira secret %s within jira %s but not jira %s valid", inactiveSecret, email, domain)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_JiraToken,
+					Verified:     false,
+					ExtraData: map[string]string{
+						"rotation_guide": "https://howtorotate.com/docs/tutorials/atlassian/",
+						"version":        "1",
+					},
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: 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,
+			wantVerificationErr: 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 jira secret %s within jira %s with jira %s", secret, email, domain)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_JiraToken,
+					Verified:     false,
+					ExtraData: map[string]string{
+						"rotation_guide": "https://howtorotate.com/docs/tutorials/atlassian/",
+						"version":        "1",
+					},
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: true,
+		},
+		{
+			name: "found, verified but unexpected api surface",
+			s:    Scanner{client: common.ConstantResponseHttpClient(404, "")},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a jira secret %s within jira %s with jira %s", secret, email, domain)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_JiraToken,
+					Verified:     false,
+					ExtraData: map[string]string{
+						"rotation_guide": "https://howtorotate.com/docs/tutorials/atlassian/",
+						"version":        "1",
+					},
+				},
+			},
+			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("JiraToken.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{}, "Raw", "RawV2", "verificationError")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("JiraToken.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/detectors/jiratoken/v1/jiratoken_test.go

@@ -1,178 +1,89 @@
-//go:build detectors
-// +build detectors
-
 package jiratoken
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
 	"github.com/google/go-cmp/cmp"
-	"github.com/google/go-cmp/cmp/cmpopts"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
 
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestJiraToken_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("JIRA_TOKEN")
-	inactiveSecret := testSecrets.MustGetField("JIRA_INACTIVE")
-	email := testSecrets.MustGetField("JIRA_EMAIL")
-	domain := testSecrets.MustGetField("JIRA_DOMAIN")
+var (
+	validTokenPattern    = "Z7VoIYJ0K4rFWLBfkhOsLAWX"
+	invalidTokenPattern  = "Z7VoI?J0K4rF#LBfkhO&LAWX"
+	validDomainPattern   = "hereisavalidsubdomain.heresalongdomain.com"
+	invalidDomainPattern = "?y4r3fs1ewqec12v1e3tl.5Hcsrcehic89saXd.ro@"
+	validEmailPattern    = "[email protected]"
+	invalidEmailPattern  = "xfKF_BZq7/grum.com"
+	keyword              = "jira"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestJiraToken_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name                string
-		s                   Scanner
-		args                args
-		want                []detectors.Result
-		wantErr             bool
-		wantVerificationErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a jira secret %s within jira %s with jira %s", secret, email, domain)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_JiraToken,
-					Verified:     true,
-					ExtraData: map[string]string{
-						"rotation_guide": "https://howtorotate.com/docs/tutorials/atlassian/",
-						"version":        "1",
-					},
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: false,
+			name:  "valid pattern - with keyword jira",
+			input: fmt.Sprintf("%s %s          \n%s %s\n%s %s", keyword, validTokenPattern, keyword, validDomainPattern, keyword, validEmailPattern),
+			want:  []string{validEmailPattern + ":" + validTokenPattern + ":" + validDomainPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a jira secret %s within jira %s but not jira %s valid", inactiveSecret, email, domain)), // the secret would satisfy the regex but not pass validation
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_JiraToken,
-					Verified:     false,
-					ExtraData: map[string]string{
-						"rotation_guide": "https://howtorotate.com/docs/tutorials/atlassian/",
-						"version":        "1",
-					},
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: false,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s' domain = '%s' email = '%s'", keyword, validTokenPattern, validDomainPattern, validEmailPattern),
+			want:  []string{},
 		},
 		{
-			name: "not found",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte("You cannot find the secret within"),
-				verify: true,
-			},
-			want:                nil,
-			wantErr:             false,
-			wantVerificationErr: 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 jira secret %s within jira %s with jira %s", secret, email, domain)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_JiraToken,
-					Verified:     false,
-					ExtraData: map[string]string{
-						"rotation_guide": "https://howtorotate.com/docs/tutorials/atlassian/",
-						"version":        "1",
-					},
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: true,
-		},
-		{
-			name: "found, verified but unexpected api surface",
-			s:    Scanner{client: common.ConstantResponseHttpClient(404, "")},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a jira secret %s within jira %s with jira %s", secret, email, domain)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_JiraToken,
-					Verified:     false,
-					ExtraData: map[string]string{
-						"rotation_guide": "https://howtorotate.com/docs/tutorials/atlassian/",
-						"version":        "1",
-					},
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: true,
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s key = '%s' domain = '%s' email = '%s'", keyword, invalidTokenPattern, invalidDomainPattern, invalidEmailPattern),
+			want:  []string{},
 		},
 	}
-	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("JiraToken.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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{}, "Raw", "RawV2", "verificationError")
-			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
-				t.Errorf("JiraToken.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/jiratoken/v2/jiratoken_v2_integration_test.go

@@ -0,0 +1,179 @@
+//go:build detectors
+// +build detectors
+
+package jiratoken
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestJiraToken_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("JIRA_V2_TOKEN")
+	inactiveSecret := testSecrets.MustGetField("JIRA_V2_INACTIVE")
+	email := testSecrets.MustGetField("JIRA_V2_EMAIL")
+	domain := testSecrets.MustGetField("JIRA_V2_DOMAIN")
+
+	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 jira secret %s within jira %s with jira %s", secret, email, domain)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_JiraToken,
+					Verified:     true,
+					ExtraData: map[string]string{
+						"rotation_guide": "https://howtorotate.com/docs/tutorials/atlassian/",
+						"version":        "2",
+					},
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a jira secret %s within jira %s but not jira %s valid", inactiveSecret, email, domain)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_JiraToken,
+					Verified:     false,
+					ExtraData: map[string]string{
+						"rotation_guide": "https://howtorotate.com/docs/tutorials/atlassian/",
+						"version":        "2",
+					},
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: 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,
+			wantVerificationErr: 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 jira secret %s within jira %s with jira %s", secret, email, domain)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_JiraToken,
+					Verified:     false,
+					ExtraData: map[string]string{
+						"rotation_guide": "https://howtorotate.com/docs/tutorials/atlassian/",
+						"version":        "2",
+					},
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: true,
+		},
+		{
+			name: "found, verified but unexpected api surface",
+			s:    Scanner{client: common.ConstantResponseHttpClient(404, "")},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a jira secret %s within jira %s with jira %s", secret, email, domain)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_JiraToken,
+					Verified:     false,
+					ExtraData: map[string]string{
+						"rotation_guide": "https://howtorotate.com/docs/tutorials/atlassian/",
+						"version":        "2",
+					},
+				},
+			},
+			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("JiraToken.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{}, "Raw", "RawV2", "verificationError")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("JiraToken.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/detectors/jiratoken/v2/jiratoken_v2_test.go

@@ -1,178 +1,89 @@
-//go:build detectors
-// +build detectors
-
 package jiratoken
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
 	"github.com/google/go-cmp/cmp"
-	"github.com/google/go-cmp/cmp/cmpopts"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
 
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestJiraToken_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("JIRA_V2_TOKEN")
-	inactiveSecret := testSecrets.MustGetField("JIRA_V2_INACTIVE")
-	email := testSecrets.MustGetField("JIRA_V2_EMAIL")
-	domain := testSecrets.MustGetField("JIRA_V2_DOMAIN")
+var (
+	validTokenPattern    = "9nsCADa7812Z7VoIsYJ0K4rFWLBfk=1rhOsLAW"
+	invalidTokenPattern  = "9nsCA?a7812Z7VoI%YJ0K4rFWLBfk91rhOsLAW"
+	validDomainPattern   = "hereisavalidsubdomain.heresalongdomain.com"
+	invalidDomainPattern = "?y4r3fs1ewqec12v1e3tl.5Hcsrcehic89saXd.ro@"
+	validEmailPattern    = "[email protected]"
+	invalidEmailPattern  = "xfKF_BZq7/grum.com"
+	keyword              = "jira"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestJiraToken_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name                string
-		s                   Scanner
-		args                args
-		want                []detectors.Result
-		wantErr             bool
-		wantVerificationErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a jira secret %s within jira %s with jira %s", secret, email, domain)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_JiraToken,
-					Verified:     true,
-					ExtraData: map[string]string{
-						"rotation_guide": "https://howtorotate.com/docs/tutorials/atlassian/",
-						"version":        "2",
-					},
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: false,
+			name:  "valid pattern - with keyword jira",
+			input: fmt.Sprintf("%s %s          \n%s %s\n%s %s", keyword, validTokenPattern, keyword, validDomainPattern, keyword, validEmailPattern),
+			want:  []string{validEmailPattern + ":" + validTokenPattern + ":" + validDomainPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a jira secret %s within jira %s but not jira %s valid", inactiveSecret, email, domain)), // the secret would satisfy the regex but not pass validation
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_JiraToken,
-					Verified:     false,
-					ExtraData: map[string]string{
-						"rotation_guide": "https://howtorotate.com/docs/tutorials/atlassian/",
-						"version":        "2",
-					},
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: false,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s' domain = '%s' email = '%s'", keyword, validTokenPattern, validDomainPattern, validEmailPattern),
+			want:  []string{},
 		},
 		{
-			name: "not found",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte("You cannot find the secret within"),
-				verify: true,
-			},
-			want:                nil,
-			wantErr:             false,
-			wantVerificationErr: 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 jira secret %s within jira %s with jira %s", secret, email, domain)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_JiraToken,
-					Verified:     false,
-					ExtraData: map[string]string{
-						"rotation_guide": "https://howtorotate.com/docs/tutorials/atlassian/",
-						"version":        "2",
-					},
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: true,
-		},
-		{
-			name: "found, verified but unexpected api surface",
-			s:    Scanner{client: common.ConstantResponseHttpClient(404, "")},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a jira secret %s within jira %s with jira %s", secret, email, domain)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_JiraToken,
-					Verified:     false,
-					ExtraData: map[string]string{
-						"rotation_guide": "https://howtorotate.com/docs/tutorials/atlassian/",
-						"version":        "2",
-					},
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: true,
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s key = '%s' domain = '%s' email = '%s'", keyword, invalidTokenPattern, invalidDomainPattern, invalidEmailPattern),
+			want:  []string{},
 		},
 	}
-	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("JiraToken.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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{}, "Raw", "RawV2", "verificationError")
-			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
-				t.Errorf("JiraToken.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/jotform/jotform_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package jotform
+
+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 TestJotform_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("JOTFORM")
+	inactiveSecret := testSecrets.MustGetField("JOTFORM_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 jotform secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Jotform,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a jotform 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_Jotform,
+					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("Jotform.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("Jotform.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/detectors/jotform/jotform_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package jotform
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestJotform_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("JOTFORM")
-	inactiveSecret := testSecrets.MustGetField("JOTFORM_INACTIVE")
+var (
+	validPattern   = "4q5fbhf90noexp56sxr86mhf3gAf31en"
+	invalidPattern = "4q5fbhf90noexp56sxr86mhf3gAf31e"
+	keyword        = "jotform"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestJotform_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a jotform secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Jotform,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword jotform",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a jotform 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_Jotform,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Jotform.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Jotform.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/jumpcloud/jumpcloud_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package jumpcloud
+
+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 TestJumpcloud_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors3")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	secret := testSecrets.MustGetField("JUMPCLOUD_TOKEN")
+	inactiveSecret := testSecrets.MustGetField("JUMPCLOUD_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 jumpcloud secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Jumpcloud,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a jumpcloud 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_Jumpcloud,
+					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("Jumpcloud.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("Jumpcloud.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/detectors/jumpcloud/jumpcloud_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package jumpcloud
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestJumpcloud_FromChunk(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
-	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors3")
-	if err != nil {
-		t.Fatalf("could not get test secrets from GCP: %s", err)
-	}
-	secret := testSecrets.MustGetField("JUMPCLOUD_TOKEN")
-	inactiveSecret := testSecrets.MustGetField("JUMPCLOUD_INACTIVE")
+var (
+	validPattern   = "ugys2uNNSDMylExbF0n4ttJrxL4ghI4YWK1nr0HM"
+	invalidPattern = "ugys2uNNSDMylExbF0n4ttJrxL4ghI4YWK1nr0H"
+	keyword        = "jumpcloud"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestJumpcloud_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a jumpcloud secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Jumpcloud,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword jumpcloud",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a jumpcloud 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_Jumpcloud,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Jumpcloud.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Jumpcloud.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/jupiterone/jupiterone_integration_test.go

@@ -0,0 +1,162 @@
+//go:build detectors
+// +build detectors
+
+package jupiterone
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestJupiterone_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("JUPITERONE")
+	inactiveSecret := testSecrets.MustGetField("JUPITERONE_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 jupiterone secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_JupiterOne,
+					Verified:     true,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a jupiterone 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_JupiterOne,
+					Verified:     false,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: 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,
+			wantVerificationErr: 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 jupiterone secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_JupiterOne,
+					Verified:     false,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: true,
+		},
+		{
+			name: "found, verified but unexpected api surface",
+			s:    Scanner{client: common.ConstantResponseHttpClient(404, "")},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a jupiterone secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_JupiterOne,
+					Verified:     false,
+				},
+			},
+			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("Jupiterone.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{}, "Raw", "verificationError")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("Jupiterone.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/detectors/jupiterone/jupiterone_test.go

@@ -1,161 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package jupiterone
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
 	"github.com/google/go-cmp/cmp"
-	"github.com/google/go-cmp/cmp/cmpopts"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestJupiterone_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("JUPITERONE")
-	inactiveSecret := testSecrets.MustGetField("JUPITERONE_INACTIVE")
+var (
+	validPattern   = "k62e5DggsqyrvjehnWM11M6h4kznOBmLYPcV1MfjNOncXis7cX90yAUyNXnlGNld1KT8iHYZoQxm"
+	invalidPattern = "k62e5DggsqyrvjehnWM11M6h4kznOBmLYPcV1MfjNOncXis7cX90yAUyNXnlGNld1KT8iHYZoQx"
+	keyword        = "jupiterone"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestJupiterone_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name                string
-		s                   Scanner
-		args                args
-		want                []detectors.Result
-		wantErr             bool
-		wantVerificationErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a jupiterone secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_JupiterOne,
-					Verified:     true,
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: false,
+			name:  "valid pattern - with keyword jupiterone",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a jupiterone 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_JupiterOne,
-					Verified:     false,
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "not found",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte("You cannot find the secret within"),
-				verify: true,
-			},
-			want:                nil,
-			wantErr:             false,
-			wantVerificationErr: false,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
 		},
 		{
-			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 jupiterone secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_JupiterOne,
-					Verified:     false,
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: true,
-		},
-		{
-			name: "found, verified but unexpected api surface",
-			s:    Scanner{client: common.ConstantResponseHttpClient(404, "")},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a jupiterone secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_JupiterOne,
-					Verified:     false,
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: true,
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Jupiterone.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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{}, "Raw", "verificationError")
-			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
-				t.Errorf("Jupiterone.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/juro/juro_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package juro
+
+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 TestJuro_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("JURO")
+	inactiveSecret := testSecrets.MustGetField("JURO_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 juro secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Juro,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a juro 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_Juro,
+					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("Juro.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("Juro.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/detectors/juro/juro_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package juro
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestJuro_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("JURO")
-	inactiveSecret := testSecrets.MustGetField("JURO_INACTIVE")
+var (
+	validPattern   = "b2hKUaFGc0nyBmk3xRr0cyPCzRJOGW97G9WIhBtQ"
+	invalidPattern = "b2hKUaFGc0nyBmk3xRr0cyPCzRJOGW97G9WIhBt"
+	keyword        = "juro"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestJuro_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a juro secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Juro,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword juro",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a juro 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_Juro,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Juro.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Juro.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/kanban/kanban_integration_test.go

@@ -0,0 +1,121 @@
+//go:build detectors
+// +build detectors
+
+package kanban
+
+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 TestKanban_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors2")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	secret := testSecrets.MustGetField("KANBAN")
+	url := testSecrets.MustGetField("KANBAN_URL")
+	inactiveSecret := testSecrets.MustGetField("KANBAN_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 kanban secret %s within %s", secret, url)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Kanban,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a kanban secret %s within %s but not valid", inactiveSecret, url)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Kanban,
+					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("Kanban.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("Kanban.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/detectors/kanban/kanban_test.go

@@ -1,120 +1,87 @@
-//go:build detectors
-// +build detectors
-
 package kanban
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestKanban_FromChunk(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
-	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors2")
-	if err != nil {
-		t.Fatalf("could not get test secrets from GCP: %s", err)
-	}
-	secret := testSecrets.MustGetField("KANBAN")
-	url := testSecrets.MustGetField("KANBAN_URL")
-	inactiveSecret := testSecrets.MustGetField("KANBAN_INACTIVE")
+var (
+	validKeyPattern   = "11XQ98FVS8WI"
+	invalidKeyPattern = "11?Q98FV=8WI"
+	validUrlPattern   = "tn1vjduk6fjhoqscmqx9hpa.kanbantool.com"
+	invalidUrlPattern = "Tn1vjduk6fjhoqscmqx9hpa.kanbantool.com"
+	keyword           = "kanban"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestKanban_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a kanban secret %s within %s", secret, url)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Kanban,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword kanban",
+			input: fmt.Sprintf("%s '%s' %s '%s'", keyword, validKeyPattern, keyword, validUrlPattern),
+			want:  []string{validKeyPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a kanban secret %s within %s but not valid", inactiveSecret, url)), // the secret would satisfy the regex but not pass validation
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Kanban,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s' url = '%s'", keyword, validKeyPattern, validUrlPattern),
+			want:  []string{},
 		},
 		{
-			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:  "invalid pattern",
+			input: fmt.Sprintf("%s key = '%s' url = '%s'", keyword, invalidKeyPattern, invalidUrlPattern),
+			want:  []string{},
 		},
 	}
-	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("Kanban.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Kanban.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/kanbantool/kanbantool_integration_test.go

@@ -0,0 +1,120 @@
+package kanbantool
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/kylelemons/godebug/pretty"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestKanbantool_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors4")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	secret := testSecrets.MustGetField("KANBANTOOL")
+	inactiveSecret := testSecrets.MustGetField("KANBANTOOL_INACTIVE")
+	domain := testSecrets.MustGetField("KANBANTOOL_DOMAIN")
+
+	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 kanbantool secret %s within kanbantool %s", secret, domain)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Kanbantool,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a kanbantool secret %s within but not valid kanbantool %s", inactiveSecret, domain)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Kanbantool,
+					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("Kanbantool.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[i], tt.want[0]); diff != "" {
+					t.Errorf("Kanbantool.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/detectors/kanbantool/kanbantool_test.go

@@ -4,116 +4,84 @@ import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
 
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestKanbantool_FromChunk(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
-	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors4")
-	if err != nil {
-		t.Fatalf("could not get test secrets from GCP: %s", err)
-	}
-	secret := testSecrets.MustGetField("KANBANTOOL")
-	inactiveSecret := testSecrets.MustGetField("KANBANTOOL_INACTIVE")
-	domain := testSecrets.MustGetField("KANBANTOOL_DOMAIN")
+var (
+	validKeyPattern      = "H1EC2BUPZ22S"
+	invalidKeyPattern    = "?1EC2BU=Z22S"
+	validDomainPattern   = "86DzV1nrzA53SPRijUoX2o"
+	invalidDomainPattern = "?6DzV1nrA53SPRijUoX2o="
+	keyword              = "kanbantool"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestKanbantool_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a kanbantool secret %s within kanbantool %s", secret, domain)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Kanbantool,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword kanbantool",
+			input: fmt.Sprintf("%s '%s' %s '%s'", keyword, validKeyPattern, keyword, validDomainPattern),
+			want:  []string{validKeyPattern, validKeyPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a kanbantool secret %s within but not valid kanbantool %s", inactiveSecret, domain)), // the secret would satisfy the regex but not pass validation
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Kanbantool,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n key = '%s' domain: '%s'", keyword, validKeyPattern, validDomainPattern),
+			want:  []string{},
 		},
 		{
-			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:  "invalid pattern",
+			input: fmt.Sprintf("%s key = '%s' secret = '%s'", keyword, invalidKeyPattern, invalidDomainPattern),
+			want:  []string{},
 		},
 	}
-	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("Kanbantool.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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[i], tt.want[0]); diff != "" {
-					t.Errorf("Kanbantool.FromData() %s diff: (-got +want)\n%s", tt.name, diff)
-				}
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
 			}
 
-		})
-	}
-}
-
-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)
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/karmacrm/karmacrm_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package karmacrm
+
+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 TestKarmaCRM_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("KARMACRM")
+	inactiveSecret := testSecrets.MustGetField("KARMACRM_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 karmacrm secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_KarmaCRM,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a karmacrm 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_KarmaCRM,
+					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("KarmaCRM.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("KarmaCRM.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/detectors/karmacrm/karmacrm_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package karmacrm
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestKarmaCRM_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("KARMACRM")
-	inactiveSecret := testSecrets.MustGetField("KARMACRM_INACTIVE")
+var (
+	validPattern   = "ThGCnHSUKBY9OBnpIZ59"
+	invalidPattern = "ThGCnHSUKBY9OBnpIZ5"
+	keyword        = "karmacrm"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestKarmaCRM_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a karmacrm secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_KarmaCRM,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword karmacrm",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a karmacrm 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_KarmaCRM,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("KarmaCRM.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("KarmaCRM.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/keenio/keenio_integration_test.go

@@ -0,0 +1,121 @@
+//go:build detectors
+// +build detectors
+
+package keenio
+
+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 TestKeenIO_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("KEENIO")
+	inactiveSecret := testSecrets.MustGetField("KEENIO_INACTIVE")
+	orgId := testSecrets.MustGetField("KEENIO_ID")
+
+	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 keenio secret %s within keenid %s", secret, orgId)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_KeenIO,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a keenio secret %s within keenid %s but not valid", inactiveSecret, orgId)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_KeenIO,
+					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("KeenIO.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("KeenIO.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/detectors/keenio/keenio_test.go

@@ -1,120 +1,87 @@
-//go:build detectors
-// +build detectors
-
 package keenio
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestKeenIO_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("KEENIO")
-	inactiveSecret := testSecrets.MustGetField("KEENIO_INACTIVE")
-	orgId := testSecrets.MustGetField("KEENIO_ID")
+var (
+	validKeyPattern   = "15AP0WODU2PTXS7AMCVEKXVHHNCOTJTJKMOXYQWFY649VTW5E8DNO5JAN3WIZDNY"
+	invalidKeyPattern = "?dsa0WODU2PTXS7AMCVEKXVHHNCOTJTJKMOXYQWFY649VTW5E8dsf3JAN3WIZDN="
+	validIdPattern    = "u95zu2ka660bfte1gj2u14s3"
+	invalidIdPattern  = "?95ZU2ka660BftE1Gj2u14s="
+	keyword           = "keenio"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestKeenIO_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a keenio secret %s within keenid %s", secret, orgId)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_KeenIO,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword keenio",
+			input: fmt.Sprintf("%s '%s' %s '%s'", keyword, validKeyPattern, keyword, validIdPattern),
+			want:  []string{validKeyPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a keenio secret %s within keenid %s but not valid", inactiveSecret, orgId)), // the secret would satisfy the regex but not pass validation
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_KeenIO,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n key = '%s' domain: '%s'", keyword, validKeyPattern, validIdPattern),
+			want:  []string{},
 		},
 		{
-			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:  "invalid pattern",
+			input: fmt.Sprintf("%s key = '%s' %s secret = '%s'", keyword, invalidKeyPattern, keyword, invalidIdPattern),
+			want:  []string{},
 		},
 	}
-	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("KeenIO.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("KeenIO.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/kickbox/kickbox_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package kickbox
+
+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 TestKickbox_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors2")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	secret := testSecrets.MustGetField("KICKBOX")
+	inactiveSecret := testSecrets.MustGetField("KICKBOX_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 kickbox secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Kickbox,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a kickbox 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_Kickbox,
+					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("Kickbox.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("Kickbox.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/detectors/kickbox/kickbox_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package kickbox
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestKickbox_FromChunk(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
-	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors2")
-	if err != nil {
-		t.Fatalf("could not get test secrets from GCP: %s", err)
-	}
-	secret := testSecrets.MustGetField("KICKBOX")
-	inactiveSecret := testSecrets.MustGetField("KICKBOX_INACTIVE")
+var (
+	validPattern   = "_DN4IVERUcAbdO2ibFCriJAyfyuaDys7u08ilesdQxON2oUsobOusDu1UFkclGq8P"
+	invalidPattern = "?DN4IVERUcAbdO2ibFCriJAyfyuaDys7u08ilesdQxON2oUsobOusDu1UFkclGq8="
+	keyword        = "kickbox"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestKickbox_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a kickbox secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Kickbox,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword kickbox",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a kickbox 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_Kickbox,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Kickbox.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Kickbox.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/klaviyo/klaviyo_integration_test.go

@@ -0,0 +1,162 @@
+//go:build detectors
+// +build detectors
+
+package klaviyo
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestKlaviyo_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("KLAVIYO")
+	inactiveSecret := testSecrets.MustGetField("KLAVIYO_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 klaviyo secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Klaviyo,
+					Verified:     true,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a klaviyo 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_Klaviyo,
+					Verified:     false,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: 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,
+			wantVerificationErr: 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 klaviyo secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Klaviyo,
+					Verified:     false,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: true,
+		},
+		{
+			name: "found, verified but unexpected api surface",
+			s:    Scanner{client: common.ConstantResponseHttpClient(404, "")},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a klaviyo secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Klaviyo,
+					Verified:     false,
+				},
+			},
+			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("Klaviyo.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{}, "Raw", "verificationError")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("Klaviyo.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/detectors/klaviyo/klaviyo_test.go

@@ -1,161 +1,80 @@
-//go:build detectors
-// +build detectors
-
 package klaviyo
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
 	"github.com/google/go-cmp/cmp"
-	"github.com/google/go-cmp/cmp/cmpopts"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestKlaviyo_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("KLAVIYO")
-	inactiveSecret := testSecrets.MustGetField("KLAVIYO_INACTIVE")
+var (
+	validPattern   = "pk_1234567890abcdefghijklmnopqrstuvwx"
+	invalidPattern = "pk_1234567890abcdefghijklmnopqrstu-_="
+	keyword        = "klaviyo"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestKlaviyo_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name                string
-		s                   Scanner
-		args                args
-		want                []detectors.Result
-		wantErr             bool
-		wantVerificationErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a klaviyo secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Klaviyo,
-					Verified:     true,
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: false,
+			name:  "valid pattern - with keyword klaviyo",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a klaviyo 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_Klaviyo,
-					Verified:     false,
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: 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,
-			wantVerificationErr: 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 klaviyo secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Klaviyo,
-					Verified:     false,
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: true,
-		},
-		{
-			name: "found, verified but unexpected api surface",
-			s:    Scanner{client: common.ConstantResponseHttpClient(404, "")},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a klaviyo secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Klaviyo,
-					Verified:     false,
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: true,
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Klaviyo.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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{}, "Raw", "verificationError")
-			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
-				t.Errorf("Klaviyo.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/klipfolio/klipfolio_integration_test.go

@@ -0,0 +1,117 @@
+//go:build detectors
+// +build detectors
+
+package klipfolio
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/kylelemons/godebug/pretty"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestKlipfolio_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors2")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	secret := testSecrets.MustGetField("KLIPFOLIO")
+	inactiveSecret := testSecrets.MustGetField("KLIPFOLIO_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 klipfolio secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Klipfolio,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a klipfolio 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_Klipfolio,
+					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("Klipfolio.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("Klipfolio.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++ {
+				s.FromData(ctx, false, data)
+			}
+		})
+	}
+}

pkg/detectors/klipfolio/klipfolio_test.go

@@ -1,116 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package klipfolio
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
 
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestKlipfolio_FromChunk(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
-	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors2")
-	if err != nil {
-		t.Fatalf("could not get test secrets from GCP: %s", err)
-	}
-	secret := testSecrets.MustGetField("KLIPFOLIO")
-	inactiveSecret := testSecrets.MustGetField("KLIPFOLIO_INACTIVE")
+var (
+	validPattern   = "8fd61e953ce814446c36975623c3d77aa97cc35c"
+	invalidPattern = "8fd61e953ce814446c36975623c3d77aa97cc35"
+	keyword        = "klipfolio"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestKlipfolio_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a klipfolio secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Klipfolio,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword klipfolio",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a klipfolio 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_Klipfolio,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Klipfolio.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Klipfolio.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++ {
-				s.FromData(ctx, false, data)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
+				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/knapsackpro/knapsackpro_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package knapsackpro
+
+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 TestKnapsackPro_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors3")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	secret := testSecrets.MustGetField("KNAPSACKPRO")
+	inactiveSecret := testSecrets.MustGetField("KNAPSACKPRO_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 knapsackpro secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_KnapsackPro,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a knapsackpro 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_KnapsackPro,
+					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("KnapsackPro.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("KnapsackPro.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/detectors/knapsackpro/knapsackpro_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package knapsackpro
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestKnapsackPro_FromChunk(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
-	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors3")
-	if err != nil {
-		t.Fatalf("could not get test secrets from GCP: %s", err)
-	}
-	secret := testSecrets.MustGetField("KNAPSACKPRO")
-	inactiveSecret := testSecrets.MustGetField("KNAPSACKPRO_INACTIVE")
+var (
+	validPattern   = "njei162j3zfnwzx97yezow5ck2fg2mr1"
+	invalidPattern = "njei162j3zfnwzx97yezow5ck2fg2mr"
+	keyword        = "knapsackpro"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestKnapsackPro_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a knapsackpro secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_KnapsackPro,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword knapsackpro",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a knapsackpro 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_KnapsackPro,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("KnapsackPro.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("KnapsackPro.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/kontent/kontent_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package kontent
+
+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 TestKontent_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("KONTENT")
+	inactiveSecret := testSecrets.MustGetField("KONTENT_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 kontent secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Kontent,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a kontent 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_Kontent,
+					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("Kontent.FromData() error = %v, wantErr %v", err, tt.wantErr)
+				return
+			}
+			for i := range got {
+				if len(got[i].Raw) == 0 {
+					t.Fatal("no raw secret present")
+				}
+				got[i].Raw = nil
+			}
+			if diff := pretty.Compare(got, tt.want); diff != "" {
+				t.Errorf("Kontent.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/detectors/kontent/kontent_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package kontent
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestKontent_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("KONTENT")
-	inactiveSecret := testSecrets.MustGetField("KONTENT_INACTIVE")
+var (
+	validPattern   = "jca9is4icbynssyi1y4spdwcbwe3vwv9jn4d"
+	invalidPattern = "jca9is4icbynssyi1y4spdwcbwe3vwv9jn4"
+	keyword        = "kontent"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestKontent_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a kontent secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Kontent,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword kontent",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a kontent 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_Kontent,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Kontent.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				return
 			}
-			for i := range got {
-				if len(got[i].Raw) == 0 {
-					t.Fatal("no raw secret present")
-				}
-				got[i].Raw = nil
-			}
-			if diff := pretty.Compare(got, tt.want); diff != "" {
-				t.Errorf("Kontent.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/kraken/kraken_integration_test.go

@@ -0,0 +1,122 @@
+//go:build detectors
+// +build detectors
+
+package kraken
+
+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 TestKraken_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("KRAKEN")
+	inactiveSecret := testSecrets.MustGetField("KRAKEN_INACTIVE")
+	private := testSecrets.MustGetField("KRAKEN_PRIVATE")
+	inactivePrivate := testSecrets.MustGetField("KRAKEN_PRIVATE_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 kraken secret %s with kraken private key %s within", secret, private)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Kraken,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a kraken secret %s with kraken private key %s within but not valid", inactiveSecret, inactivePrivate)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Kraken,
+					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("Kraken.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("Kraken.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/detectors/kraken/kraken_test.go

@@ -1,121 +1,88 @@
-//go:build detectors
-// +build detectors
-
 package kraken
 
 import (
 	"context"
 	"fmt"
+	"strings"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestKraken_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("KRAKEN")
-	inactiveSecret := testSecrets.MustGetField("KRAKEN_INACTIVE")
-	private := testSecrets.MustGetField("KRAKEN_PRIVATE")
-	inactivePrivate := testSecrets.MustGetField("KRAKEN_PRIVATE_INACTIVE")
+var (
+	validKeyPattern       = "m=MN/0yYJ/5xqpE15JYDJtCFdDF7RDLuiXtTiSF1FU1H9waiub1kgwI= "
+	invalidKeyPattern     = "m=MN/0yYJ/5xqpE15JYDJtCFdDF7RDLuiXtTiSF1FU1H9waiub1kgwI="
+	validPrivKeyPattern   = "Oe1xUe+sNT7F5SboHSpfCubMhJlAaghB3SZ=NMmkIHTSzWVoF3uTOnxv32cgI+WuEDXYS+z5MvX+q9IUJ1cYo=+ "
+	invalidPrivKeyPattern = "Oe1xUe+sNT7F5SboHSpfCubMhJlAaghB3SZ=NMmkIHTSzWVoF3uTOnxv32cgI+WuEDXYS+z5MvX+q9IUJ1cYo=+"
+	keyword               = "kraken"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestKraken_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a kraken secret %s with kraken private key %s within", secret, private)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Kraken,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword kraken",
+			input: fmt.Sprintf("%s '%s' %s '%s'", keyword, validKeyPattern, keyword, validPrivKeyPattern),
+			want:  []string{strings.TrimSpace(validKeyPattern) + strings.TrimSpace(validPrivKeyPattern)},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a kraken secret %s with kraken private key %s within but not valid", inactiveSecret, inactivePrivate)), // the secret would satisfy the regex but not pass validation
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Kraken,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n key = '%s' domain: '%s'", keyword, validKeyPattern, validPrivKeyPattern),
+			want:  []string{},
 		},
 		{
-			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:  "invalid pattern",
+			input: fmt.Sprintf("%s key = '%s' secret = '%s'", keyword, invalidKeyPattern, invalidPrivKeyPattern),
+			want:  []string{},
 		},
 	}
-	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("Kraken.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Kraken.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/kucoin/kucoin_integration_test.go

@@ -0,0 +1,121 @@
+//go:build detectors
+// +build detectors
+
+package kucoin
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/kylelemons/godebug/pretty"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestKuCoin_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors2")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	secret := testSecrets.MustGetField("KUCOIN")
+	inactiveSecret := testSecrets.MustGetField("KUCOIN_INACTIVE")
+	key := testSecrets.MustGetField("KUCOIN_KEY")
+	inactiveKey := testSecrets.MustGetField("KUCOIN_KEY_INACTIVE")
+	passphrase := testSecrets.MustGetField("KUCOIN_PASSPHRASE")
+	inactivePassphrase := testSecrets.MustGetField("KUCOIN_PASSPHRASE_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 kucoin key %s with kucoin secret %s and kucoin passphrase %s within", key, secret, passphrase)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_KuCoin,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a kucoin key %s with kucoin secret %s and kucoin passphrase %s within but not valid", inactiveKey, inactiveSecret, inactivePassphrase)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_KuCoin,
+					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("KuCoin.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("KuCoin.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++ {
+				s.FromData(ctx, false, data)
+			}
+		})
+	}
+}

pkg/detectors/kucoin/kucoin_test.go

@@ -1,120 +1,89 @@
-//go:build detectors
-// +build detectors
-
 package kucoin
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
 
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestKuCoin_FromChunk(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
-	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors2")
-	if err != nil {
-		t.Fatalf("could not get test secrets from GCP: %s", err)
-	}
-	secret := testSecrets.MustGetField("KUCOIN")
-	inactiveSecret := testSecrets.MustGetField("KUCOIN_INACTIVE")
-	key := testSecrets.MustGetField("KUCOIN_KEY")
-	inactiveKey := testSecrets.MustGetField("KUCOIN_KEY_INACTIVE")
-	passphrase := testSecrets.MustGetField("KUCOIN_PASSPHRASE")
-	inactivePassphrase := testSecrets.MustGetField("KUCOIN_PASSPHRASE_INACTIVE")
+var (
+	validKeyPattern          = "c19c2539c53367c726a5c04c"
+	invalidKeyPattern        = "X19c2539c53367c726a5c04c"
+	validSecretPattern       = "2313b299-7ba8-66b6-5b30-3e94050324ff"
+	invalidSecretPattern     = "X313b299-7ba8-66b6-5b30-3e94050324ff"
+	validPassphrasePattern   = "_4K~W4|RHH--o}:BiwRhY9J2pl/5x,"
+	invalidPassphrasePattern = "_4Kix,"
+	keyword                  = "kucoin"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestKuCoin_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a kucoin key %s with kucoin secret %s and kucoin passphrase %s within", key, secret, passphrase)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_KuCoin,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword kucoin",
+			input: fmt.Sprintf("%s %s %s %s %s %s", keyword, validPassphrasePattern, keyword, validSecretPattern, keyword, validKeyPattern),
+			want:  []string{validKeyPattern + validPassphrasePattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a kucoin key %s with kucoin secret %s and kucoin passphrase %s within but not valid", inactiveKey, inactiveSecret, inactivePassphrase)), // the secret would satisfy the regex but not pass validation
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_KuCoin,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s' domain = '%s' email = '%s'", keyword, validKeyPattern, validSecretPattern, validPassphrasePattern),
+			want:  []string{},
 		},
 		{
-			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:  "invalid pattern",
+			input: fmt.Sprintf("%s key = '%s' domain = '%s' email = '%s'", keyword, invalidKeyPattern, invalidSecretPattern, invalidPassphrasePattern),
+			want:  []string{},
 		},
 	}
-	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("KuCoin.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("KuCoin.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++ {
-				s.FromData(ctx, false, data)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
+				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/kylas/kylas_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package kylas
+
+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 TestKylas_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("KYLAS")
+	inactiveSecret := testSecrets.MustGetField("KYLAS_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 kylas secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Kylas,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a kylas 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_Kylas,
+					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("Kylas.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("Kylas.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/detectors/kylas/kylas_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package kylas
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestKylas_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("KYLAS")
-	inactiveSecret := testSecrets.MustGetField("KYLAS_INACTIVE")
+var (
+	validPattern   = "dozvko9mlnqqxg5ontcanklqzvw2-lo0jvge"
+	invalidPattern = "dozvko9mlnqqxg5ontcanklqzvw2-lo0jvg"
+	keyword        = "kylas"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestKylas_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a kylas secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Kylas,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword kylas",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a kylas 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_Kylas,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Kylas.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Kylas.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/languagelayer/languagelayer_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package languagelayer
+
+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 TestLanguageLayer_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("LANGUAGELAYER")
+	inactiveSecret := testSecrets.MustGetField("LANGUAGELAYER_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 languagelayer secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_LanguageLayer,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a languagelayer 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_LanguageLayer,
+					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("LanguageLayer.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("LanguageLayer.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/detectors/languagelayer/languagelayer_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package languagelayer
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestLanguageLayer_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("LANGUAGELAYER")
-	inactiveSecret := testSecrets.MustGetField("LANGUAGELAYER_INACTIVE")
+var (
+	validPattern   = "ze1z7svucm5z17kyizcve7gin44socz5"
+	invalidPattern = "ze1z7svucm5z17kyizcve7gin44socz"
+	keyword        = "languagelayer"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestLanguageLayer_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a languagelayer secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_LanguageLayer,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword languagelayer",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a languagelayer 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_LanguageLayer,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("LanguageLayer.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("LanguageLayer.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/launchdarkly/launchdarkly_integration_test.go

@@ -0,0 +1,162 @@
+//go:build detectors
+// +build detectors
+
+package launchdarkly
+
+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 TestLaunchDarkly_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors3")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	sdkSecret := testSecrets.MustGetField("LAUNCHDARKLY_SDK_TOKEN")
+	secret := testSecrets.MustGetField("LAUNCHDARKLY_TOKEN")
+	inactiveSecret := testSecrets.MustGetField("LAUNCHDARKLY_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 launchdarkly secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_LaunchDarkly,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a launchdarkly 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_LaunchDarkly,
+					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,
+		},
+		{
+			name: "found, valid but unexpected api response",
+			s:    Scanner{client: common.ConstantResponseHttpClient(500, "")},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a launchdarkly secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_LaunchDarkly,
+					Verified:     false,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: true,
+		},
+		{
+			name: "found, valid sdk token",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a launchdarkly sdk secret %s within", sdkSecret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_LaunchDarkly,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+	}
+	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("LaunchDarkly.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
+
+				// Do we expect to be comparing the ExtraData?
+				got[i].ExtraData = nil
+
+				// If we expect a verification error, copy over the one we got so the later comparison can work
+				if tt.wantVerificationErr && len(tt.want) > i {
+					tt.want[i].SetVerificationError(got[i].VerificationError())
+				}
+			}
+			if diff := pretty.Compare(got, tt.want); diff != "" {
+				t.Errorf("LaunchDarkly.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/detectors/launchdarkly/launchdarkly_test.go

@@ -1,161 +1,80 @@
-//go:build detectors
-// +build detectors
-
 package launchdarkly
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestLaunchDarkly_FromChunk(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
-	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors3")
-	if err != nil {
-		t.Fatalf("could not get test secrets from GCP: %s", err)
-	}
-	sdkSecret := testSecrets.MustGetField("LAUNCHDARKLY_SDK_TOKEN")
-	secret := testSecrets.MustGetField("LAUNCHDARKLY_TOKEN")
-	inactiveSecret := testSecrets.MustGetField("LAUNCHDARKLY_INACTIVE")
+var (
+	validPattern   = "sdk-5gykyl1b-wgrq-41lc-z6q1-h7zn5fdlcybw"
+	invalidPattern = "sdk-5gykyl1b-wgrq-41lc-z6q1-h7zn5fdlcyb"
+	keyword        = "launchdarkly"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestLaunchDarkly_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name                string
-		s                   Scanner
-		args                args
-		want                []detectors.Result
-		wantErr             bool
-		wantVerificationErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a launchdarkly secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_LaunchDarkly,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword launchdarkly",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a launchdarkly 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_LaunchDarkly,
-					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,
-		},
-		{
-			name: "found, valid but unexpected api response",
-			s:    Scanner{client: common.ConstantResponseHttpClient(500, "")},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a launchdarkly secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_LaunchDarkly,
-					Verified:     false,
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: true,
-		},
-		{
-			name: "found, valid sdk token",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a launchdarkly sdk secret %s within", sdkSecret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_LaunchDarkly,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("LaunchDarkly.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				return
 			}
-			for i := range got {
-				if len(got[i].Raw) == 0 {
-					t.Fatalf("no raw secret present: \n %+v", got[i])
+
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
-				got[i].Raw = nil
+				return
+			}
 
-				// Do we expect to be comparing the ExtraData?
-				got[i].ExtraData = nil
-
-				// If we expect a verification error, copy over the one we got so the later comparison can work
-				if tt.wantVerificationErr && len(tt.want) > i {
-					tt.want[i].SetVerificationError(got[i].VerificationError())
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
 				}
 			}
-			if diff := pretty.Compare(got, tt.want); diff != "" {
-				t.Errorf("LaunchDarkly.FromData() %s diff: (-got +want)\n%s", tt.name, diff)
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
 			}
-		})
-	}
-}
 
-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)
-				}
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/ldap/ldap_integration_test.go

@@ -15,6 +15,7 @@ import (
 
 	"github.com/google/go-cmp/cmp"
 	"github.com/google/go-cmp/cmp/cmpopts"
+	"github.com/kylelemons/godebug/pretty"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
 
@@ -238,3 +239,81 @@ func startOpenLDAP() error {
 func stopOpenLDAP() {
 	exec.Command("docker", "kill", containerID).Run()
 }
+
+func TestLdap_FromChunk(t *testing.T) {
+	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 with IAD lib usage, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(`Set ou = dso.OpenDSObject("LDAP://DC.business.com/OU=IT,DC=Business,DC=com", "Business\administrator", "Pa$$word01", 1)`),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_LDAP,
+					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("Ldap.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("Ldap.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/detectors/ldap/ldap_test.go

@@ -1,91 +1,85 @@
-//go:build detectors
-// +build detectors
-
 package ldap
 
 import (
 	"context"
+	"fmt"
 	"testing"
 
-	"github.com/kylelemons/godebug/pretty"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/google/go-cmp/cmp"
 
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestLdap_FromChunk(t *testing.T) {
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+var (
+	validUriPattern        = "ldaps://127.0.0.1:389"
+	invalidUriPattern      = "idaps://127.0.0.1:389"
+	validUsernamePattern   = "cCOfHuyrVdDdcWCAbKLCSAlospWAdCmfKwr="
+	invalidUsernamePattern = "0fHuy2VdDdcWCAbKLC412lospWAdCmfKwr9="
+	validPasswordPattern   = "A:J$NL9~6:u:L$_:VO4tf))h#v0i}O"
+	invalidPasswordPattern = "A:J$NL9~6:u:L$_:VO4tf))h#v0i}O"
+	validIadPattern        = "OpenDSObject(\"ldaps://www\", \"ABC\", \"XYZ\", 123)"
+	invalidIadPattern      = "OpenDSObject(\"ldaps://www\", \"ABC\", \"XYZ\", ?)"
+)
+
+func TestLdap_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found with IAD lib usage, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(`Set ou = dso.OpenDSObject("LDAP://DC.business.com/OU=IT,DC=Business,DC=com", "Business\administrator", "Pa$$word01", 1)`),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_LDAP,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern",
+			input: fmt.Sprintf("%s bind '%s' pass '%s' %s", validUriPattern, validIadPattern, validPasswordPattern, validUsernamePattern),
+			want:  []string{"ldaps://www\tABC\tXYZ"},
 		},
 		{
-			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:  "invalid pattern",
+			input: fmt.Sprintf("%s key = bind '%s' pass '%s %s", invalidUriPattern, invalidUsernamePattern, invalidPasswordPattern, invalidIadPattern),
+			want:  []string{},
 		},
 	}
-	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("Ldap.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Ldap.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/leadfeeder/leadfeeder_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package leadfeeder
+
+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 TestLeadfeeder_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("LEADFEEDER")
+	inactiveSecret := testSecrets.MustGetField("LEADFEEDER_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 leadfeeder secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Leadfeeder,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a leadfeeder 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_Leadfeeder,
+					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("Leadfeeder.FromData() error = %v, wantErr %v", err, tt.wantErr)
+				return
+			}
+			for i := range got {
+				if len(got[i].Raw) == 0 {
+					t.Fatal("no raw secret present")
+				}
+				got[i].Raw = nil
+			}
+			if diff := pretty.Compare(got, tt.want); diff != "" {
+				t.Errorf("Leadfeeder.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/detectors/leadfeeder/leadfeeder_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package leadfeeder
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestLeadfeeder_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("LEADFEEDER")
-	inactiveSecret := testSecrets.MustGetField("LEADFEEDER_INACTIVE")
+var (
+	validPattern   = "7zy0rgEn3QnW3oGW8PCuWWlDkLOBMpz307kKsm9OJa4"
+	invalidPattern = "7zy0rgEn3QnW3oGW8PCuWWlDkLOBMpz307kKsm9OJa="
+	keyword        = "leadfeeder"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestLeadfeeder_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a leadfeeder secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Leadfeeder,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword leadfeeder",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a leadfeeder 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_Leadfeeder,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Leadfeeder.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				return
 			}
-			for i := range got {
-				if len(got[i].Raw) == 0 {
-					t.Fatal("no raw secret present")
-				}
-				got[i].Raw = nil
-			}
-			if diff := pretty.Compare(got, tt.want); diff != "" {
-				t.Errorf("Leadfeeder.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/lemlist/lemlist_integration_test.go

@@ -0,0 +1,117 @@
+package lemlist
+
+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 TestLemlist_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors3")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	secret := testSecrets.MustGetField("LEMLIST")
+	inactiveSecret := testSecrets.MustGetField("LEMLIST_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 lemlist secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Lemlist,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a lemlist 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_Lemlist,
+					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("Lemlist.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("Lemlist.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/detectors/lemlist/lemlist_test.go

@@ -4,113 +4,87 @@ import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestLemlist_FromChunk(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
-	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors3")
-	if err != nil {
-		t.Fatalf("could not get test secrets from GCP: %s", err)
-	}
-	secret := testSecrets.MustGetField("LEMLIST")
-	inactiveSecret := testSecrets.MustGetField("LEMLIST_INACTIVE")
+var (
+	validPattern   = "24203d9f149dd02d1d944ee799cfb57e"
+	invalidPattern = "24203d9f149dd02d1d944ee799cfb57"
+	keyword        = "lemlist"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestLemlist_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a lemlist secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Lemlist,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword lemlist",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a lemlist 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_Lemlist,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Lemlist.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Lemlist.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/lemonsqueezy/lemonsqueezy_integration_test.go

@@ -0,0 +1,128 @@
+//go:build detectors
+// +build detectors
+
+package lemonsqueezy
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestLemonsqueezy_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("LEMONSQUEEZY")
+	inactiveSecret := testSecrets.MustGetField("LEMONSQUEEZY_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 lemonsqueezy secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_LemonSqueezy,
+					Verified:     true,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a lemonsqueezy 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_LemonSqueezy,
+					Verified:     false,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: 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,
+			wantVerificationErr: false,
+		},
+	}
+	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("Lemonsqueezy.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{}, "Raw", "verificationError")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("Lemonsqueezy.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/detectors/lemonsqueezy/lemonsqueezy_test.go

@@ -1,127 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package lemonsqueezy
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
 	"github.com/google/go-cmp/cmp"
-	"github.com/google/go-cmp/cmp/cmpopts"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestLemonsqueezy_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("LEMONSQUEEZY")
-	inactiveSecret := testSecrets.MustGetField("LEMONSQUEEZY_INACTIVE")
+var (
+	validPattern   = "eyJ0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiJ9.TkOQyjzXNs1ExektRLyW2wxKeFk7VWEE0NVQwaBSKjO5EKaXBwZciTfpIPOFKupmt0PkIChZLcI8fX5XOHQK6hy1e2f7gWW0A00ixqbQUAUyfOTBXSHdrZrK6QNd9xi7q7B2m7ei3rfSipMMod7oHyxvVKwKckwcdfDlZ5OwtDy1lhBFeYZWcGiTM2qvTOWQkBMezkwhz23YONwYK2MOP0PaasJhryNui98LbiiXju20dV2tlxslqJD6i856axkolvQRhJWM7y2Jp37iDgIABh6b13LadPbWJgKiOKkrow4UyzYCrcDOQ5Y6to.c8zXA41FY2GgWUWXjwqoem5A6q46CgLicuYZ4M2XuGZ747WQz1ZmtbnLZn4nclSWLpJUEgdxQpNt8GBVBB2_3B4on1m2HkOHBqjrfn5kHuYSeR_zHNPdLXZBER4tpUPx7Dijl1T8WO6cri32vj8oM2o4ihLeFD1Ewd_OYpP-CIzC4jOKn4DFbgtr7CWaE4vf4XEFSn4B4v-XEjgjmSRDcw_a-wRXRnSZCL8UoiN9k0cMyxqXFHxfiFrMcghwFIKHt37fhHEidYh8SwJy3XdJzusRpynUtoHcpfNhgts9Ik3W7jg_HAhMvbg5XxMUYhtQty32sonozf5cVuoXUD0HOe7gbLNMxaHNT8RVYRSHTqzV1FXLdtGBsZMke-6pKuhC1erbPpLB57os6bKetCkwswk9yZI_eNi4MtR8KnhO8aeWUrz2QJUMY6xXI0a1E0yES8yxGQsSe3CHlVhGgjQuLZf9p2_30YB-yu3NIjJTkamgsaWA41H0eX_SuDci35uO"
+	invalidPattern = "eyJ0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiJ9.TkOQyjzXNs1ExektRLyW2wxKeFk7VWEE0NVQwaBSKjO5EKaXBwZciTfpIPOFKupmt0PkIChZLcI8fX5XOHQK6hy1e2f7gWW0A00ixqbQUAUyfOTBXSHdrZrK6QNd9xi7q7B2m7ei3rfSipMMod7oHyxvVKwKc.c8zXA41FY2GgWUWXjwqoem5A6q46CgLicuYZ4M2XuGZ747WQz1ZmtbnLZn4nclSWLpJUEgdxQpNt8GBVBB2_3B4on1m2HkOHBqjrfn5kHuYSeR_zHNPdLXZBER4tpUPx7Dijl1T8WO6cri32vj8oM2o4ihLeFD1Ewd_OYpP-CIzC4jOKn4DFbgtr7CWaE4vf4XEFSn4B4v-XEjgjmSRDcw_a-wRXRnSZCL8UoiN9k0cMyxqXFHxfiFrMcghwFIKH"
+	keyword        = "lemonsqueezy"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestLemonsqueezy_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name                string
-		s                   Scanner
-		args                args
-		want                []detectors.Result
-		wantErr             bool
-		wantVerificationErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a lemonsqueezy secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_LemonSqueezy,
-					Verified:     true,
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: false,
+			name:  "valid pattern - with keyword lemonsqueezy",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a lemonsqueezy 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_LemonSqueezy,
-					Verified:     false,
-				},
-			},
-			wantErr:             false,
-			wantVerificationErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "not found",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte("You cannot find the secret within"),
-				verify: true,
-			},
-			want:                nil,
-			wantErr:             false,
-			wantVerificationErr: false,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Lemonsqueezy.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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{}, "Raw", "verificationError")
-			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
-				t.Errorf("Lemonsqueezy.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/lendflow/lendflow_integration_test.go

@@ -0,0 +1,117 @@
+//go:build detectors
+// +build detectors
+
+package lendflow
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/kylelemons/godebug/pretty"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestLendflow_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors2")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	secret := testSecrets.MustGetField("LENDFLOW")
+	inactiveSecret := testSecrets.MustGetField("LENDFLOW_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 lendflow secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Lendflow,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a lendflow 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_Lendflow,
+					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("Lendflow.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("Lendflow.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++ {
+				s.FromData(ctx, false, data)
+			}
+		})
+	}
+}

pkg/detectors/lendflow/lendflow_test.go

@@ -1,116 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package lendflow
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
 
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestLendflow_FromChunk(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
-	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors2")
-	if err != nil {
-		t.Fatalf("could not get test secrets from GCP: %s", err)
-	}
-	secret := testSecrets.MustGetField("LENDFLOW")
-	inactiveSecret := testSecrets.MustGetField("LENDFLOW_INACTIVE")
+var (
+	validPattern   = "RODlvb3v108LswHD7gCZcyHdCIK8T90Hgg12.VF24VyD6akOZS1NmAZ4tVRmtyhyLeNELvCqZnBuiAtJqyMUN2JQHC6vQgzrcAMwPglMjiAZ8gBPIVsQSRiHDvJA89BPQpjAOCxGQynOoSvECoSH5WCldSnl8lN0BNKyeK9J0DSKitEaS9G00qVY9emKcNEQWCWXZeZXLsDXReCcOUEr1Cmi1tpsueqxT34TG4zvaPa2npM10TCKLqKsJrdfZL4oWtZVnZob0QBBkU7k.nQcGbtHUBtYXGUIQYZ1Et1ROaE4Rg0gM-Kw3YtvcVgoV5ro02tydPtPGqSAzf5SBt3LYqQriHmcmW5cx-tASACVQwoT1dpJtxrUP1sa5mHuvstgxDFVe1DxDpMjXYVNL3immaAxqnD6NHs4FzKdNvXvz7p969aIe9q7YdpdyDbFL6x2FINKkqrJ2uMIUNvECITzDjHLGQP3hDcbfJUQ47bDAi3XpbqtFhZTlDd29VwxfEMoA3xi-6rKIS9xXsRxCsLdEt3mhwIxEW89oXKLFHxjXYMGNvl-91H2hw0TIvhzXJHrG3VE1NKXq9E1WoC6OfQPa7qV-lz26nq1jGSW7ENR9HWfc4ppiHj20PGczp6YZPRUIbaTcrOi64F09uOKLInZCIIKI94-bqjlEK5dAune7Fm8pmRqOUPIEnRydJi4ilWiG2cm1xDgU4nb3F507dsjHVi-V0TFyrI-69lrF0TEh7jb8sBjU6yusaRGdannDKBFSnz2d3LVVAn7udGuk2ZNIjYi6equNRYhQ3wJnKQCGIqLaGGQdgH9ILiDB0T9e5aED0taqYpvMFgby6UJGJeNatazX1KMj1NMwMWd3ZIBia7Dlc1lkbWlePlQEh2mZTBcOsvh7lOzLmIu1NKDzByZI3VUhKq5wY3JXJdGeiD3EBPphUt5eaz9Mt0nrK8J"
+	invalidPattern = "?ODlvb3v108LswHD7gCZcyHdCIK8T90Hgg12.VF24VyD6akOZS1NmAZ4tVRmtyhyLeNELvCqZnBuiAtJqyMUN2JQHC6vQgzrcAMwPglMjiAZ8gBPIVsQSRiHDvJA89BPQpjAOCxGQynOoSvECoSH5WCldSnl8lN0BNKyeK9J0DSKitEaS9G00qVY9emKcNEQWCWXZeZXLsDXReCcOUEr1Cmi1tpsueqxT34TG4zvaPa2npM10TCKLqKsJrdfZL4oWtZVnZob0QBBkU7k.nQcGbtHUBtYXGUIQYZ1Et1ROaE4Rg0gM-Kw3YtvcVgoV5ro02tydPtPGqSAzf5SBt3LYqQriHmcmW5cx-tASACVQwoT1dpJtxrUP1sa5mHuvstgxDFVe1DxDpMjXYVNL3immaAxqnD6NHs4FzKdNvXvz7p969aIe9q7YdpdyDbFL6x2FINKkqrJ2uMIUNvECITzDjHLGQP3hDcbfJUQ47bDAi3XpbqtFhZTlDd29VwxfEMoA3xi-6rKIS9xXsRxCsLdEt3mhwIxEW89oXKLFHxjXYMGNvl-91H2hw0TIvhzXJHrG3VE1NKXq9E1WoC6OfQPa7qV-lz26nq1jGSW7ENR9HWfc4ppiHj20PGczp6YZPRUIbaTcrOi64F09uOKLInZCIIKI94-bqjlEK5dAune7Fm8pmRqOUPIEnRydJi4ilWiG2cm1xDgU4nb3F507dsjHVi-V0TFyrI-69lrF0TEh7jb8sBjU6yusaRGdannDKBFSnz2d3LVVAn7udGuk2ZNIjYi6equNRYhQ3wJnKQCGIqLaGGQdgH9ILiDB0T9e5aED0taqYpvMFgby6UJGJeNatazX1KMj1NMwMWd3ZIBia7Dlc1lkbWlePlQEh2mZTBcOsvh7lOzLmIu1NKDzByZI3VUhKq5wY3JXJdGeiD3EBPphUt5eaz9Mt0nrK8J"
+	keyword        = "lendflow"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestLendflow_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a lendflow secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Lendflow,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword lendflow",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a lendflow 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_Lendflow,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Lendflow.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Lendflow.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++ {
-				s.FromData(ctx, false, data)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
+				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/lessannoyingcrm/lessannoyingcrm_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package lessannoyingcrm
+
+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 TestLessAnnoyingCRM_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors3")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	secret := testSecrets.MustGetField("LESSANNOYINGCRM_TOKEN")
+	inactiveSecret := testSecrets.MustGetField("LESSANNOYINGCRM_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 lessannoyingcrm secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_LessAnnoyingCRM,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a lessannoyingcrm 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_LessAnnoyingCRM,
+					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("LessAnnoyingCRM.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("LessAnnoyingCRM.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/detectors/lessannoyingcrm/lessannoyingcrm_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package lessannoyingcrm
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestLessAnnoyingCRM_FromChunk(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
-	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors3")
-	if err != nil {
-		t.Fatalf("could not get test secrets from GCP: %s", err)
-	}
-	secret := testSecrets.MustGetField("LESSANNOYINGCRM_TOKEN")
-	inactiveSecret := testSecrets.MustGetField("LESSANNOYINGCRM_INACTIVE")
+var (
+	validPattern   = "xiPi5OZDPlnS6WmR0JropSAMlcHCSCRWVN2D1sVttofuZQpdYuPKmWD81"
+	invalidPattern = "xiPi5OZDPlnS6WmR0JropSAMlcHCSCRWVN2D1sVttofuZQpdYuPKmWD8"
+	keyword        = "lessannoyingcrm"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestLessAnnoyingCRM_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a lessannoyingcrm secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_LessAnnoyingCRM,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword lessannoyingcrm",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a lessannoyingcrm 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_LessAnnoyingCRM,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("LessAnnoyingCRM.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("LessAnnoyingCRM.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}

pkg/detectors/lexigram/lexigram_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package lexigram
+
+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 TestLexigram_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("LEXIGRAM")
+	inactiveSecret := testSecrets.MustGetField("LEXIGRAM_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 lexigram secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Lexigram,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a lexigram 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_Lexigram,
+					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("Lexigram.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("Lexigram.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/detectors/lexigram/lexigram_test.go

@@ -1,119 +1,90 @@
-//go:build detectors
-// +build detectors
-
 package lexigram
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
-	"github.com/kylelemons/godebug/pretty"
+	"github.com/google/go-cmp/cmp"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestLexigram_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("LEXIGRAM")
-	inactiveSecret := testSecrets.MustGetField("LEXIGRAM_INACTIVE")
+var (
+	validPattern   = "FyIcB4LRVZ4iEJVky0JvzVS6yzreDuFgz8zSmfXNlWuEIE29ad6Wmc9sQtUzWBp8dV960IeSdWk5V182naPy0uAty27gdFtyl6TvCz0gJdprxKyZfNzxVeAy5Qlghzl4Ivk9jXe2p7gnafM3iUvK2vemq5FroXXgUJTZ0SHqR6QGv0wk9WGEa5aAxDUiQ91e2xI6leUbTIoxXQyF1P1rxYZswimIbGTHy6H7oMuTbXFrX3XDdphMqyHYjGlzYDfY3nREvC83XsgIlawdTV0FdPXzXxqB4ELorpo3z8kCsWm1H"
+	invalidPattern = "=yIcB4LRVZ4iEJVky0JvzVS6yzreDuFgz8zSmfXNlWuEIE29ad6Wmc9sQtUzWBp8dV960IeSdWk5V182naPy0uAty27gdFtyl6TvCz0gJdprxKyZfNzxVeAy5Qlghzl4Ivk9jXe2p7gnafM3iUvK2vemq5FroXXgUJTZ0SHqR6QGv0wk9WGEa5aAxDUiQ91e2xI6leUbTIoxXQyF1P1rxYZswimIbGTHy6H7oMuTbXFrX3XDdphMqyHYjGlzYDfY3nREvC83XsgIlawdTV0FdPXzXxqB4ELorpo3z8kCsWm1H"
+	keyword        = "lexigram"
+)
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
+func TestLexigram_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a lexigram secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Lexigram,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with keyword lexigram",
+			input: fmt.Sprintf("%s token = '%s'", keyword, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a lexigram 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_Lexigram,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - ignore duplicate",
+			input: fmt.Sprintf("%s token = '%s' | '%s'", keyword, validPattern, validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			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:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("%s keyword is not close to the real key in the data\n = '%s'", keyword, validPattern),
+			want:  []string{},
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("%s = '%s'", keyword, invalidPattern),
+			want:  []string{},
 		},
 	}
-	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("Lexigram.FromData() error = %v, wantErr %v", err, tt.wantErr)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				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("Lexigram.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)
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			if len(results) != len(test.want) {
+				if len(results) == 0 {
+					t.Errorf("did not receive result")
+				} else {
+					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
 				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
 			}
 		})
 	}