Added Pattern test cases for detectors (#3354)

* Added Pattern test cases for detectors

* restructured the unit tests

* Added pattern test cases for few more detectors

* Added pattern test case for 3 more detectors

* formatted testing patterns

pkg/detectors/abbysale/abbysale_integration_test.go

@@ -0,0 +1,168 @@
+//go:build detectors
+// +build detectors
+
+package abbysale
+
+import (
+	"context"
+	"fmt"
+	"github.com/google/go-cmp/cmp/cmpopts"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"testing"
+	"time"
+
+	"github.com/google/go-cmp/cmp"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+)
+
+func TestAbbysale_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("ABBYSALE_TOKEN")
+	inactiveSecret := testSecrets.MustGetField("ABBYSALE_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 abbysale secret %s within but verified", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Abbysale,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, real secrets, verification error due to timeout",
+			s:    Scanner{client: common.SaneHttpClientTimeOut(1 * time.Microsecond)},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a abbysale secret %s within but verified", secret)),
+				verify: true,
+			},
+			want: func() []detectors.Result {
+				r := detectors.Result{
+					DetectorType: detectorspb.DetectorType_Abbysale,
+					Verified:     false,
+				}
+				r.SetVerificationError(context.DeadlineExceeded)
+				return []detectors.Result{r}
+			}(),
+			wantErr: false,
+		},
+		{
+			name: "found, real secrets, verification error due to unexpected api surface",
+			s:    Scanner{client: common.ConstantResponseHttpClient(500, "{}")},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a abbysale secret %s within but verified", secret)),
+				verify: true,
+			},
+			want: func() []detectors.Result {
+				r := detectors.Result{
+					DetectorType: detectorspb.DetectorType_Abbysale,
+					Verified:     false,
+				}
+				r.SetVerificationError(fmt.Errorf("unexpected HTTP response status 500"))
+				return []detectors.Result{r}
+			}(),
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a abbysale secret %s within but verified", inactiveSecret)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Abbysale,
+					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) {
+			got, err := tt.s.FromData(tt.args.ctx, tt.args.verify, tt.args.data)
+			if (err != nil) != tt.wantErr {
+				t.Errorf("Abbysale.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])
+				}
+				gotErr := ""
+				if got[i].VerificationError() != nil {
+					gotErr = got[i].VerificationError().Error()
+				}
+				wantErr := ""
+				if tt.want[i].VerificationError() != nil {
+					wantErr = tt.want[i].VerificationError().Error()
+				}
+
+				if gotErr != wantErr {
+					t.Fatalf("wantVerificationError = %v, verification error = %v", tt.want[i].VerificationError(), got[i].VerificationError())
+				}
+			}
+			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("Abbysale.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/abbysale/abbysale_test.go

@@ -1,167 +1,85 @@
-//go:build detectors
-// +build detectors
-
 package abbysale
 
 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 TestAbbysale_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("ABBYSALE_TOKEN")
-	inactiveSecret := testSecrets.MustGetField("ABBYSALE_INACTIVE")
+var (
+	validPattern   = "123abcDEF456ghiJKL789mnoPQR012stuVWX3456"
+	invalidPattern = "123abcDEF456ghiJKL789mnoPQR012stuVWX"
+)
+
+func TestAbbySale_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
 	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 abbysale secret %s within but verified", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Abbysale,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern",
+			input: fmt.Sprintf("abbysale token = '%s'", validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, real secrets, verification error due to timeout",
-			s:    Scanner{client: common.SaneHttpClientTimeOut(1 * time.Microsecond)},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a abbysale secret %s within but verified", secret)),
-				verify: true,
-			},
-			want: func() []detectors.Result {
-				r := detectors.Result{
-					DetectorType: detectorspb.DetectorType_Abbysale,
-					Verified:     false,
-				}
-				r.SetVerificationError(context.DeadlineExceeded)
-				return []detectors.Result{r}
-			}(),
-			wantErr: false,
+			name:  "valid pattern - out of prefix range",
+			input: fmt.Sprintf("abbysale token keyword is not close to the real token = '%s'", validPattern),
+			want:  nil,
 		},
 		{
-			name: "found, real secrets, verification error due to unexpected api surface",
-			s:    Scanner{client: common.ConstantResponseHttpClient(500, "{}")},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a abbysale secret %s within but verified", secret)),
-				verify: true,
-			},
-			want: func() []detectors.Result {
-				r := detectors.Result{
-					DetectorType: detectorspb.DetectorType_Abbysale,
-					Verified:     false,
-				}
-				r.SetVerificationError(fmt.Errorf("unexpected HTTP response status 500"))
-				return []detectors.Result{r}
-			}(),
-			wantErr: false,
-		},
-		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a abbysale secret %s within but verified", inactiveSecret)), // the secret would satisfy the regex but not pass validation
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Abbysale,
-					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:  "invalid pattern",
+			input: fmt.Sprintf("abbysale = '%s'", invalidPattern),
+			want:  nil,
 		},
 	}
-	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("Abbysale.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])
-				}
-				gotErr := ""
-				if got[i].VerificationError() != nil {
-					gotErr = got[i].VerificationError().Error()
-				}
-				wantErr := ""
-				if tt.want[i].VerificationError() != nil {
-					wantErr = tt.want[i].VerificationError().Error()
-				}
 
-				if gotErr != wantErr {
-					t.Fatalf("wantVerificationError = %v, verification error = %v", tt.want[i].VerificationError(), got[i].VerificationError())
+			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{}{}
 				}
 			}
-			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError")
-			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
-				t.Errorf("Abbysale.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/abstract/abstract_integration_test.go

@@ -0,0 +1,168 @@
+//go:build detectors
+// +build detectors
+
+package abstract
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestAbstract_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("ABSTRACT")
+	inactiveSecret := testSecrets.MustGetField("ABSTRACT_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 abstract secret %s within but verified", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Abstract,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, real secrets, verification error due to timeout",
+			s:    Scanner{client: common.SaneHttpClientTimeOut(1 * time.Microsecond)},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a abstract secret %s within but verified", secret)),
+				verify: true,
+			},
+			want: func() []detectors.Result {
+				r := detectors.Result{
+					DetectorType: detectorspb.DetectorType_Abstract,
+					Verified:     false,
+				}
+				r.SetVerificationError(context.DeadlineExceeded)
+				return []detectors.Result{r}
+			}(),
+			wantErr: false,
+		},
+		{
+			name: "found, real secrets, verification error due to unexpected api surface",
+			s:    Scanner{client: common.ConstantResponseHttpClient(500, "{}")},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a abstract secret %s within", secret)),
+				verify: true,
+			},
+			want: func() []detectors.Result {
+				r := detectors.Result{
+					DetectorType: detectorspb.DetectorType_Abstract,
+					Verified:     false,
+				}
+				r.SetVerificationError(fmt.Errorf("unexpected HTTP response status 500"))
+				return []detectors.Result{r}
+			}(),
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a abstract secret %s within but not valid", inactiveSecret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Abstract,
+					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) {
+			time.Sleep(900 * time.Millisecond) // avoid rate limiting
+			got, err := tt.s.FromData(tt.args.ctx, tt.args.verify, tt.args.data)
+			if (err != nil) != tt.wantErr {
+				t.Errorf("Abstract.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])
+				}
+				gotErr := ""
+				if got[i].VerificationError() != nil {
+					gotErr = got[i].VerificationError().Error()
+				}
+				wantErr := ""
+				if tt.want[i].VerificationError() != nil {
+					wantErr = tt.want[i].VerificationError().Error()
+				}
+				if gotErr != wantErr {
+					t.Fatalf("wantVerificationError = %v, verification error = %v", tt.want[i].VerificationError(), got[i].VerificationError())
+				}
+			}
+			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("Abstract.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/abstract/abstract_test.go

@@ -1,167 +1,85 @@
-//go:build detectors
-// +build detectors
-
 package abstract
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
 	"github.com/google/go-cmp/cmp"
-	"github.com/google/go-cmp/cmp/cmpopts"
 
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestAbstract_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("ABSTRACT")
-	inactiveSecret := testSecrets.MustGetField("ABSTRACT_INACTIVE")
+var (
+	validPattern   = "qwerty12345iugt67s7a7sa0akhsxz82"
+	invalidPattern = "zxcvbr12345iugt67s7a7sa0akhsXz820"
+)
+
+func TestAbstract_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
 	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 abstract secret %s within but verified", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Abstract,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern",
+			input: fmt.Sprintf("abstract token = '%s'", validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, real secrets, verification error due to timeout",
-			s:    Scanner{client: common.SaneHttpClientTimeOut(1 * time.Microsecond)},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a abstract secret %s within but verified", secret)),
-				verify: true,
-			},
-			want: func() []detectors.Result {
-				r := detectors.Result{
-					DetectorType: detectorspb.DetectorType_Abstract,
-					Verified:     false,
-				}
-				r.SetVerificationError(context.DeadlineExceeded)
-				return []detectors.Result{r}
-			}(),
-			wantErr: false,
+			name:  "valid pattern - out of prefix range",
+			input: fmt.Sprintf("abstract token keyword is not close to the real token = '%s'", validPattern),
+			want:  nil,
 		},
 		{
-			name: "found, real secrets, verification error due to unexpected api surface",
-			s:    Scanner{client: common.ConstantResponseHttpClient(500, "{}")},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a abstract secret %s within", secret)),
-				verify: true,
-			},
-			want: func() []detectors.Result {
-				r := detectors.Result{
-					DetectorType: detectorspb.DetectorType_Abstract,
-					Verified:     false,
-				}
-				r.SetVerificationError(fmt.Errorf("unexpected HTTP response status 500"))
-				return []detectors.Result{r}
-			}(),
-			wantErr: false,
-		},
-		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a abstract secret %s within but not valid", inactiveSecret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Abstract,
-					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:  "invalid pattern",
+			input: fmt.Sprintf("abstract = '%s'", invalidPattern),
+			want:  nil,
 		},
 	}
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			time.Sleep(900 * time.Millisecond) // avoid rate limiting
-			got, err := tt.s.FromData(tt.args.ctx, tt.args.verify, tt.args.data)
-			if (err != nil) != tt.wantErr {
-				t.Errorf("Abstract.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])
-				}
-				gotErr := ""
-				if got[i].VerificationError() != nil {
-					gotErr = got[i].VerificationError().Error()
-				}
-				wantErr := ""
-				if tt.want[i].VerificationError() != nil {
-					wantErr = tt.want[i].VerificationError().Error()
-				}
-				if gotErr != wantErr {
-					t.Fatalf("wantVerificationError = %v, verification error = %v", tt.want[i].VerificationError(), got[i].VerificationError())
-				}
-			}
-			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError")
-			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
-				t.Errorf("Abstract.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/abuseipdb/abuseipdb_integration_test.go

@@ -0,0 +1,167 @@
+//go:build detectors
+// +build detectors
+
+package abuseipdb
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestAbuseIPDB_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("ABUSEIPDB")
+	inactiveSecret := testSecrets.MustGetField("ABUSEIPDB_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 abuseipdb secret %s within but verified", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_AbuseIPDB,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, real secrets, verification error due to timeout",
+			s:    Scanner{client: common.SaneHttpClientTimeOut(1 * time.Microsecond)},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a abuseipdb secret %s within", secret)),
+				verify: true,
+			},
+			want: func() []detectors.Result {
+				r := detectors.Result{
+					DetectorType: detectorspb.DetectorType_AbuseIPDB,
+					Verified:     false,
+				}
+				r.SetVerificationError(context.DeadlineExceeded)
+				return []detectors.Result{r}
+			}(),
+			wantErr: false,
+		},
+		{
+			name: "found, real secrets, verification error due to unexpected api surface",
+			s:    Scanner{client: common.ConstantResponseHttpClient(500, "{}")},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a abuseipdb secret %s within", secret)),
+				verify: true,
+			},
+			want: func() []detectors.Result {
+				r := detectors.Result{
+					DetectorType: detectorspb.DetectorType_AbuseIPDB,
+					Verified:     false,
+				}
+				r.SetVerificationError(fmt.Errorf("unexpected HTTP response status 500"))
+				return []detectors.Result{r}
+			}(),
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a abuseipdb secret %s within", inactiveSecret)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_AbuseIPDB,
+					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) {
+			got, err := tt.s.FromData(tt.args.ctx, tt.args.verify, tt.args.data)
+			if (err != nil) != tt.wantErr {
+				t.Errorf("AbuseIPDB.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])
+				}
+				gotErr := ""
+				if got[i].VerificationError() != nil {
+					gotErr = got[i].VerificationError().Error()
+				}
+				wantErr := ""
+				if tt.want[i].VerificationError() != nil {
+					wantErr = tt.want[i].VerificationError().Error()
+				}
+				if gotErr != wantErr {
+					t.Fatalf("wantVerificationError = %v, verification error = %v", tt.want[i].VerificationError(), got[i].VerificationError())
+				}
+			}
+			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("AbuseIPDB.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/abuseipdb/abuseipdb_test.go

@@ -1,166 +1,85 @@
-//go:build detectors
-// +build detectors
-
 package abuseipdb
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
 	"github.com/google/go-cmp/cmp"
-	"github.com/google/go-cmp/cmp/cmpopts"
 
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestAbuseIPDB_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("ABUSEIPDB")
-	inactiveSecret := testSecrets.MustGetField("ABUSEIPDB_INACTIVE")
+var (
+	validPattern   = "123abcdef456ghijkl789mnopqr012stuvwx3455123abcdef456ghijkl789mnopqr012stuvwx3455"
+	invalidPattern = "123abcdef456Ghijkl789mnopqr012stuvwx3455123abcdef456ghijkl789mnopqr012stuvwX"
+)
+
+func TestAbuseipdb_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
 	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 abuseipdb secret %s within but verified", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_AbuseIPDB,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern",
+			input: fmt.Sprintf("abuseipdb token = '%s'", validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, real secrets, verification error due to timeout",
-			s:    Scanner{client: common.SaneHttpClientTimeOut(1 * time.Microsecond)},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a abuseipdb secret %s within", secret)),
-				verify: true,
-			},
-			want: func() []detectors.Result {
-				r := detectors.Result{
-					DetectorType: detectorspb.DetectorType_AbuseIPDB,
-					Verified:     false,
-				}
-				r.SetVerificationError(context.DeadlineExceeded)
-				return []detectors.Result{r}
-			}(),
-			wantErr: false,
+			name:  "valid pattern - out of prefix range",
+			input: fmt.Sprintf("abuseipdb token keyword is not close to the real token = '%s'", validPattern),
+			want:  nil,
 		},
 		{
-			name: "found, real secrets, verification error due to unexpected api surface",
-			s:    Scanner{client: common.ConstantResponseHttpClient(500, "{}")},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a abuseipdb secret %s within", secret)),
-				verify: true,
-			},
-			want: func() []detectors.Result {
-				r := detectors.Result{
-					DetectorType: detectorspb.DetectorType_AbuseIPDB,
-					Verified:     false,
-				}
-				r.SetVerificationError(fmt.Errorf("unexpected HTTP response status 500"))
-				return []detectors.Result{r}
-			}(),
-			wantErr: false,
-		},
-		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a abuseipdb secret %s within", inactiveSecret)), // the secret would satisfy the regex but not pass validation
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_AbuseIPDB,
-					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:  "invalid pattern",
+			input: fmt.Sprintf("abuseipdb = '%s'", invalidPattern),
+			want:  nil,
 		},
 	}
-	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("AbuseIPDB.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])
-				}
-				gotErr := ""
-				if got[i].VerificationError() != nil {
-					gotErr = got[i].VerificationError().Error()
-				}
-				wantErr := ""
-				if tt.want[i].VerificationError() != nil {
-					wantErr = tt.want[i].VerificationError().Error()
-				}
-				if gotErr != wantErr {
-					t.Fatalf("wantVerificationError = %v, verification error = %v", tt.want[i].VerificationError(), got[i].VerificationError())
-				}
-			}
-			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError")
-			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
-				t.Errorf("AbuseIPDB.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/accuweather/accuweather_integration_test.go

@@ -0,0 +1,168 @@
+//go:build detectors
+// +build detectors
+
+package accuweather
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestAccuweather_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("ACCUWEATHER")
+	inactiveSecret := testSecrets.MustGetField("ACCUWEATHER_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 accuweather secret %s within but verified", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Accuweather,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, real secrets, verification error due to timeout",
+			s:    Scanner{client: common.SaneHttpClientTimeOut(1 * time.Microsecond)},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a accuweather secret %s within", secret)),
+				verify: true,
+			},
+			want: func() []detectors.Result {
+				r := detectors.Result{
+					DetectorType: detectorspb.DetectorType_Accuweather,
+					Verified:     false,
+				}
+				r.SetVerificationError(context.DeadlineExceeded)
+				return []detectors.Result{r}
+			}(),
+			wantErr: false,
+		},
+		{
+			name: "found, real secrets, verification error due to unexpected api surface",
+			s:    Scanner{client: common.ConstantResponseHttpClient(500, "{}")},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a accuweather secret %s within", secret)),
+				verify: true,
+			},
+			want: func() []detectors.Result {
+				r := detectors.Result{
+					DetectorType: detectorspb.DetectorType_Accuweather,
+					Verified:     false,
+				}
+				r.SetVerificationError(fmt.Errorf("unexpected HTTP response status 500"))
+				return []detectors.Result{r}
+			}(),
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a accuweather secret %s within but verified", inactiveSecret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Accuweather,
+					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) {
+			got, err := tt.s.FromData(tt.args.ctx, tt.args.verify, tt.args.data)
+			if (err != nil) != tt.wantErr {
+				t.Errorf("Accuweather.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])
+				}
+				gotErr := ""
+				if got[i].VerificationError() != nil {
+					gotErr = got[i].VerificationError().Error()
+				}
+				wantErr := ""
+				if tt.want[i].VerificationError() != nil {
+					wantErr = tt.want[i].VerificationError().Error()
+				}
+				if gotErr != wantErr {
+					t.Fatalf("wantVerificationError = %v, verification error = %v", tt.want[i].VerificationError(), got[i].VerificationError())
+				}
+				got[i].Raw = nil
+			}
+			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("Accuweather.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/accuweather/accuweather_test.go

@@ -1,167 +1,85 @@
-//go:build detectors
-// +build detectors
-
 package accuweather
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
 
 	"github.com/google/go-cmp/cmp"
-	"github.com/google/go-cmp/cmp/cmpopts"
 
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestAccuweather_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("ACCUWEATHER")
-	inactiveSecret := testSecrets.MustGetField("ACCUWEATHER_INACTIVE")
+var (
+	validPattern   = "dqftwc490oPc%xae67sBSF741M56%sd091a"
+	invalidPattern = "dqftwc490oPc%xae67sBSF741M56=sd091a"
+)
+
+func TestAccuWeather_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
 	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 accuweather secret %s within but verified", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Accuweather,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern",
+			input: fmt.Sprintf("accuweather token = '%s'", validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, real secrets, verification error due to timeout",
-			s:    Scanner{client: common.SaneHttpClientTimeOut(1 * time.Microsecond)},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a accuweather secret %s within", secret)),
-				verify: true,
-			},
-			want: func() []detectors.Result {
-				r := detectors.Result{
-					DetectorType: detectorspb.DetectorType_Accuweather,
-					Verified:     false,
-				}
-				r.SetVerificationError(context.DeadlineExceeded)
-				return []detectors.Result{r}
-			}(),
-			wantErr: false,
+			name:  "valid pattern - out of prefix range",
+			input: fmt.Sprintf("accuweather token keyword is not close to the real token = '%s'", validPattern),
+			want:  nil,
 		},
 		{
-			name: "found, real secrets, verification error due to unexpected api surface",
-			s:    Scanner{client: common.ConstantResponseHttpClient(500, "{}")},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a accuweather secret %s within", secret)),
-				verify: true,
-			},
-			want: func() []detectors.Result {
-				r := detectors.Result{
-					DetectorType: detectorspb.DetectorType_Accuweather,
-					Verified:     false,
-				}
-				r.SetVerificationError(fmt.Errorf("unexpected HTTP response status 500"))
-				return []detectors.Result{r}
-			}(),
-			wantErr: false,
-		},
-		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a accuweather secret %s within but verified", inactiveSecret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Accuweather,
-					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:  "invalid pattern",
+			input: fmt.Sprintf("accuweather = '%s'", invalidPattern),
+			want:  nil,
 		},
 	}
-	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("Accuweather.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])
-				}
-				gotErr := ""
-				if got[i].VerificationError() != nil {
-					gotErr = got[i].VerificationError().Error()
-				}
-				wantErr := ""
-				if tt.want[i].VerificationError() != nil {
-					wantErr = tt.want[i].VerificationError().Error()
-				}
-				if gotErr != wantErr {
-					t.Fatalf("wantVerificationError = %v, verification error = %v", tt.want[i].VerificationError(), got[i].VerificationError())
-				}
-				got[i].Raw = nil
-			}
-			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError")
-			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
-				t.Errorf("Accuweather.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/adobeio/adobeio_integration_test.go

@@ -0,0 +1,121 @@
+//go:build detectors
+// +build detectors
+
+package adobeio
+
+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 TestAdobeIO_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("ADOBEIO_TOKEN")
+	id := testSecrets.MustGetField("ADOBEIO_PRODUCT")
+	inactiveSecret := testSecrets.MustGetField("ADOBEIO_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 adobeio secret %s within adobeio %s", secret, id)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_AdobeIO,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a adobeio secret %s within adobeio %s but not valid", inactiveSecret, id)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_AdobeIO,
+					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("AdobeIO.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("AdobeIO.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/adobeio/adobeio_test.go

@@ -1,120 +1,85 @@
-//go:build detectors
-// +build detectors
-
 package adobeio
 
 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 TestAdobeIO_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("ADOBEIO_TOKEN")
-	id := testSecrets.MustGetField("ADOBEIO_PRODUCT")
-	inactiveSecret := testSecrets.MustGetField("ADOBEIO_INACTIVE")
+var (
+	validPattern   = "zxcv0987mnbv1234poiu6749gtnrfv54/WDcv0981Mn.B"
+	invalidPattern = "Rzxc#0987$%bv1234poiu6749gtnrfv54"
+)
+
+func TestAdobeIO_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
 	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 adobeio secret %s within adobeio %s", secret, id)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_AdobeIO,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern",
+			input: fmt.Sprintf("adobe = '%s'", validPattern),
+			want:  []string{"zxcv0987mnbv1234poiu6749gtnrfv54WDcv0981Mn.B"},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a adobeio secret %s within adobeio %s but not valid", inactiveSecret, id)), // the secret would satisfy the regex but not pass validation
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_AdobeIO,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - out of prefix range",
+			input: fmt.Sprintf("adobe keyword is not close to the real id and secret = '%s'", validPattern),
+			want:  nil,
 		},
 		{
-			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("adobe%s", invalidPattern),
+			want:  nil,
 		},
 	}
-	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("AdobeIO.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("AdobeIO.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/adzuna/adzuna_integration_test.go

@@ -0,0 +1,168 @@
+//go:build detectors
+// +build detectors
+
+package adzuna
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestAdzuna_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("ADZUNA")
+	id := testSecrets.MustGetField("ADZUNA_ID")
+	inactiveSecret := testSecrets.MustGetField("ADZUNA_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 adzuna secret %s within adzuna %s", secret, id)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Adzuna,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, real secrets, verification error due to timeout",
+			s:    Scanner{client: common.SaneHttpClientTimeOut(1 * time.Microsecond)},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a adzuna secret %s within adzuna %s", secret, id)),
+				verify: true,
+			},
+			want: func() []detectors.Result {
+				r := detectors.Result{
+					DetectorType: detectorspb.DetectorType_Adzuna,
+					Verified:     false,
+				}
+				r.SetVerificationError(context.DeadlineExceeded)
+				return []detectors.Result{r}
+			}(),
+			wantErr: false,
+		},
+		{
+			name: "found, real secrets, verification error due to unexpected api surface",
+			s:    Scanner{client: common.ConstantResponseHttpClient(500, "{}")},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a adzuna secret %s within adzuna %s", secret, id)),
+				verify: true,
+			},
+			want: func() []detectors.Result {
+				r := detectors.Result{
+					DetectorType: detectorspb.DetectorType_Adzuna,
+					Verified:     false,
+				}
+				r.SetVerificationError(fmt.Errorf("unexpected HTTP response status 500"))
+				return []detectors.Result{r}
+			}(),
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a adzuna secret %s within adzuna %s but not valid", inactiveSecret, id)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Adzuna,
+					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) {
+			got, err := tt.s.FromData(tt.args.ctx, tt.args.verify, tt.args.data)
+			if (err != nil) != tt.wantErr {
+				t.Errorf("Adzuna.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])
+				}
+				gotErr := ""
+				if got[i].VerificationError() != nil {
+					gotErr = got[i].VerificationError().Error()
+				}
+				wantErr := ""
+				if tt.want[i].VerificationError() != nil {
+					wantErr = tt.want[i].VerificationError().Error()
+				}
+				if gotErr != wantErr {
+					t.Fatalf("wantVerificationError = %v, verification error = %v", tt.want[i].VerificationError(), got[i].VerificationError())
+				}
+			}
+			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("Adzuna.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/adzuna/adzuna_test.go

@@ -1,167 +1,96 @@
-//go:build detectors
-// +build detectors
-
 package adzuna
 
 import (
 	"context"
 	"fmt"
+	"strings"
 	"testing"
-	"time"
 
 	"github.com/google/go-cmp/cmp"
-	"github.com/google/go-cmp/cmp/cmpopts"
 
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestAdzuna_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("ADZUNA")
-	id := testSecrets.MustGetField("ADZUNA_ID")
-	inactiveSecret := testSecrets.MustGetField("ADZUNA_INACTIVE")
+var (
+	validPattern   = "asdf0987mnbv1234qsxojb6ygb2wsx0o/qsc0f098"
+	invalidPattern = "as#f0987mnbv1234^sxojb6ygb2wsx0o/qsc0f098"
+)
+
+func TestAdzuna_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
 	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 adzuna secret %s within adzuna %s", secret, id)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Adzuna,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern",
+			input: fmt.Sprintf("adzuna = '%s'", validPattern),
+			want:  []string{"asdf0987mnbv1234qsxojb6ygb2wsx0oqsc0f098"},
 		},
 		{
-			name: "found, real secrets, verification error due to timeout",
-			s:    Scanner{client: common.SaneHttpClientTimeOut(1 * time.Microsecond)},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a adzuna secret %s within adzuna %s", secret, id)),
-				verify: true,
-			},
-			want: func() []detectors.Result {
-				r := detectors.Result{
-					DetectorType: detectorspb.DetectorType_Adzuna,
-					Verified:     false,
-				}
-				r.SetVerificationError(context.DeadlineExceeded)
-				return []detectors.Result{r}
-			}(),
-			wantErr: false,
+			name:  "valid pattern - out of prefix range",
+			input: fmt.Sprintf("adzuna keyword is not close to the real id and secret = '%s'", validPattern),
+			want:  nil,
 		},
 		{
-			name: "found, real secrets, verification error due to unexpected api surface",
-			s:    Scanner{client: common.ConstantResponseHttpClient(500, "{}")},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a adzuna secret %s within adzuna %s", secret, id)),
-				verify: true,
-			},
-			want: func() []detectors.Result {
-				r := detectors.Result{
-					DetectorType: detectorspb.DetectorType_Adzuna,
-					Verified:     false,
-				}
-				r.SetVerificationError(fmt.Errorf("unexpected HTTP response status 500"))
-				return []detectors.Result{r}
-			}(),
-			wantErr: false,
+			name:  "valid pattern - only key",
+			input: fmt.Sprintf("adzuna %s", strings.Split(validPattern, "/")[0]),
+			want:  nil,
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a adzuna secret %s within adzuna %s but not valid", inactiveSecret, id)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Adzuna,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - only id",
+			input: fmt.Sprintf("adzuna %s", strings.Split(validPattern, "/")[1]),
+			want:  nil,
 		},
 		{
-			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("adzuna %s", invalidPattern),
+			want:  nil,
 		},
 	}
-	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("Adzuna.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])
-				}
-				gotErr := ""
-				if got[i].VerificationError() != nil {
-					gotErr = got[i].VerificationError().Error()
-				}
-				wantErr := ""
-				if tt.want[i].VerificationError() != nil {
-					wantErr = tt.want[i].VerificationError().Error()
-				}
-				if gotErr != wantErr {
-					t.Fatalf("wantVerificationError = %v, verification error = %v", tt.want[i].VerificationError(), got[i].VerificationError())
-				}
-			}
-			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError")
-			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
-				t.Errorf("Adzuna.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/aeroworkflow/aeroworkflow_integration_test.go

@@ -0,0 +1,165 @@
+//go:build detectors
+// +build detectors
+
+package aeroworkflow
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestAeroworkflow_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("AEROWORKFLOW_SECRET")
+	id := testSecrets.MustGetField("AEROWORKFLOW_ID")
+	inactiveSecret := testSecrets.MustGetField("AEROWORKFLOW_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 aeroworkflow secret %s within aeroworkflow %s", secret, id)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Aeroworkflow,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, real secrets, verification error due to timeout",
+			s:    Scanner{client: common.SaneHttpClientTimeOut(1 * time.Microsecond)},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a aeroworkflow secret %s within aeroworkflow %s", secret, id)),
+				verify: true,
+			},
+			want: func() []detectors.Result {
+				r := detectors.Result{
+					DetectorType: detectorspb.DetectorType_Aeroworkflow,
+					Verified:     false,
+				}
+				r.SetVerificationError(context.DeadlineExceeded)
+				return []detectors.Result{r}
+			}(),
+			wantErr: false,
+		},
+		{
+			name: "found, real secrets, verification error due to unexpected api surface",
+			s:    Scanner{client: common.ConstantResponseHttpClient(500, "{}")},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a aeroworkflow secret %s within aeroworkflow %s", secret, id)),
+				verify: true,
+			},
+			want: func() []detectors.Result {
+				r := detectors.Result{
+					DetectorType: detectorspb.DetectorType_Aeroworkflow,
+					Verified:     false,
+				}
+				r.SetVerificationError(fmt.Errorf("unexpected HTTP response status 500"))
+				return []detectors.Result{r}
+			}(),
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a aeroworkflow secret %s within aeroworkflow %s but not valid", inactiveSecret, id)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Aeroworkflow,
+					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) {
+			got, err := tt.s.FromData(tt.args.ctx, tt.args.verify, tt.args.data)
+			if (err != nil) != tt.wantErr {
+				t.Errorf("Aeroworkflow.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])
+				}
+				gotErr := ""
+				if got[i].VerificationError() != nil {
+					gotErr = got[i].VerificationError().Error()
+				}
+				wantErr := ""
+				if tt.want[i].VerificationError() != nil {
+					wantErr = tt.want[i].VerificationError().Error()
+				}
+				if gotErr != wantErr {
+					t.Fatalf("wantVerificationError = %v, verification error = %v", tt.want[i].VerificationError(), got[i].VerificationError())
+				}
+			}
+			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("Aeroworkflow.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/aeroworkflow/aeroworkflow_test.go

@@ -1,163 +1,96 @@
-//go:build detectors
-// +build detectors
-
 package aeroworkflow
 
 import (
 	"context"
 	"fmt"
+	"strings"
 	"testing"
-	"time"
 
 	"github.com/google/go-cmp/cmp"
-	"github.com/google/go-cmp/cmp/cmpopts"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestAeroworkflow_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("AEROWORKFLOW_SECRET")
-	id := testSecrets.MustGetField("AEROWORKFLOW_ID")
-	inactiveSecret := testSecrets.MustGetField("AEROWORKFLOW_INACTIVE")
+var (
+	validPattern   = "qscVgy!WdvG;^#O:*?TG/806445634"
+	invalidPattern = "qscVg&!WdvG;^#O:*?TG/8064456A4"
+)
+
+func TestAeroWorkflow_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
 	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 aeroworkflow secret %s within aeroworkflow %s", secret, id)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Aeroworkflow,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern",
+			input: fmt.Sprintf("aeroworkflow = '%s'", validPattern),
+			want:  []string{"qscVgy!WdvG;^#O:*?TG806445634"},
 		},
 		{
-			name: "found, real secrets, verification error due to timeout",
-			s:    Scanner{client: common.SaneHttpClientTimeOut(1 * time.Microsecond)},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a aeroworkflow secret %s within aeroworkflow %s", secret, id)),
-				verify: true,
-			},
-			want: func() []detectors.Result {
-				r := detectors.Result{
-					DetectorType: detectorspb.DetectorType_Aeroworkflow,
-					Verified:     false,
-				}
-				r.SetVerificationError(context.DeadlineExceeded)
-				return []detectors.Result{r}
-			}(),
-			wantErr: false,
+			name:  "valid pattern - out of prefix range",
+			input: fmt.Sprintf("aeroworkflow keyword is not close to the real id and secret = '%s'", validPattern),
+			want:  nil,
 		},
 		{
-			name: "found, real secrets, verification error due to unexpected api surface",
-			s:    Scanner{client: common.ConstantResponseHttpClient(500, "{}")},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a aeroworkflow secret %s within aeroworkflow %s", secret, id)),
-				verify: true,
-			},
-			want: func() []detectors.Result {
-				r := detectors.Result{
-					DetectorType: detectorspb.DetectorType_Aeroworkflow,
-					Verified:     false,
-				}
-				r.SetVerificationError(fmt.Errorf("unexpected HTTP response status 500"))
-				return []detectors.Result{r}
-			}(),
-			wantErr: false,
+			name:  "valid pattern - only key",
+			input: fmt.Sprintf("aeroworkflow %s", strings.Split(validPattern, "/")[0]),
+			want:  nil,
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a aeroworkflow secret %s within aeroworkflow %s but not valid", inactiveSecret, id)), // the secret would satisfy the regex but not pass validation
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Aeroworkflow,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - only id",
+			input: fmt.Sprintf("aeroworkflow %s", strings.Split(validPattern, "/")[1]),
+			want:  nil,
 		},
 		{
-			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("aeroworkflow %s", invalidPattern),
+			want:  nil,
 		},
 	}
-	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("Aeroworkflow.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])
-				}
-				gotErr := ""
-				if got[i].VerificationError() != nil {
-					gotErr = got[i].VerificationError().Error()
-				}
-				wantErr := ""
-				if tt.want[i].VerificationError() != nil {
-					wantErr = tt.want[i].VerificationError().Error()
-				}
-				if gotErr != wantErr {
-					t.Fatalf("wantVerificationError = %v, verification error = %v", tt.want[i].VerificationError(), got[i].VerificationError())
-				}
-			}
-			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError")
-			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
-				t.Errorf("Aeroworkflow.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/agora/agora_integration_test.go

@@ -0,0 +1,192 @@
+//go:build detectors
+// +build detectors
+
+package agora
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestAgora_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)
+	}
+	id := testSecrets.MustGetField("AGORA")
+	secret := testSecrets.MustGetField("AGORA_SECRET")
+	inactiveSecret := testSecrets.MustGetField("AGORA_SECRET_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 agora secret %s within agora id %s but verified", secret, id)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Agora,
+					Verified:     false,
+				},
+				{
+					DetectorType: detectorspb.DetectorType_Agora,
+					Verified:     true,
+				},
+				{
+					DetectorType: detectorspb.DetectorType_Agora,
+					Verified:     false,
+				},
+				{
+					DetectorType: detectorspb.DetectorType_Agora,
+					Verified:     false,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, real secrets, verification error due to timeout",
+			s:    Scanner{client: common.SaneHttpClientTimeOut(1 * time.Microsecond)},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a agora secret %s within agora id %s but verified", secret, id)),
+				verify: true,
+			},
+			want: func() []detectors.Result {
+				r := detectors.Result{
+					DetectorType: detectorspb.DetectorType_Agora,
+					Verified:     false,
+				}
+				r.SetVerificationError(context.DeadlineExceeded)
+				return []detectors.Result{r, r, r, r}
+			}(),
+			wantErr: false,
+		},
+		{
+			name: "found, real secrets, verification error due to unexpected api surface",
+			s:    Scanner{client: common.ConstantResponseHttpClient(500, "{}")},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a agora secret %s within agora id %s but verified", secret, id)),
+				verify: true,
+			},
+			want: func() []detectors.Result {
+				r := detectors.Result{
+					DetectorType: detectorspb.DetectorType_Agora,
+					Verified:     false,
+				}
+				r.SetVerificationError(fmt.Errorf("unexpected HTTP response status 500"))
+				return []detectors.Result{r, r, r, r}
+			}(),
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a agora secret %s within agora id %s but not valid ", inactiveSecret, id)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Agora,
+					Verified:     false,
+				},
+				{
+					DetectorType: detectorspb.DetectorType_Agora,
+					Verified:     false,
+				},
+				{
+					DetectorType: detectorspb.DetectorType_Agora,
+					Verified:     false,
+				},
+				{
+					DetectorType: detectorspb.DetectorType_Agora,
+					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) {
+			got, err := tt.s.FromData(tt.args.ctx, tt.args.verify, tt.args.data)
+			if (err != nil) != tt.wantErr {
+				t.Errorf("Agora.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")
+				}
+				gotErr := ""
+				if got[i].VerificationError() != nil {
+					gotErr = got[i].VerificationError().Error()
+				}
+				wantErr := ""
+				if tt.want[i].VerificationError() != nil {
+					wantErr = tt.want[i].VerificationError().Error()
+				}
+				if gotErr != wantErr {
+					t.Fatalf("wantVerificationError = %v, verification error = %v", tt.want[i].VerificationError(), got[i].VerificationError())
+				}
+			}
+			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("Agora.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/agora/agora_test.go

@@ -1,191 +1,96 @@
-//go:build detectors
-// +build detectors
-
 package agora
 
 import (
 	"context"
 	"fmt"
+	"strings"
 	"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 TestAgora_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)
-	}
-	id := testSecrets.MustGetField("AGORA")
-	secret := testSecrets.MustGetField("AGORA_SECRET")
-	inactiveSecret := testSecrets.MustGetField("AGORA_SECRET_INACTIVE")
+var (
+	validPattern   = "asdf0987mnbv1234qsxojb6ygb2wsx0o/beqr7215fr4g6bfjkmnvxrtygb2wsxap"
+	invalidPattern = "asdf0987mNbv1234qsxojb6ygb2w$x0o/beqr7215fr4g6bfjkmnVxrtygb2wsxap"
+)
+
+func TestAgora_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
 	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 agora secret %s within agora id %s but verified", secret, id)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Agora,
-					Verified:     false,
-				},
-				{
-					DetectorType: detectorspb.DetectorType_Agora,
-					Verified:     true,
-				},
-				{
-					DetectorType: detectorspb.DetectorType_Agora,
-					Verified:     false,
-				},
-				{
-					DetectorType: detectorspb.DetectorType_Agora,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern",
+			input: fmt.Sprintf("agora = '%s'", validPattern),
+			want:  []string{"asdf0987mnbv1234qsxojb6ygb2wsx0oasdf0987mnbv1234qsxojb6ygb2wsx0o"},
 		},
 		{
-			name: "found, real secrets, verification error due to timeout",
-			s:    Scanner{client: common.SaneHttpClientTimeOut(1 * time.Microsecond)},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a agora secret %s within agora id %s but verified", secret, id)),
-				verify: true,
-			},
-			want: func() []detectors.Result {
-				r := detectors.Result{
-					DetectorType: detectorspb.DetectorType_Agora,
-					Verified:     false,
-				}
-				r.SetVerificationError(context.DeadlineExceeded)
-				return []detectors.Result{r, r, r, r}
-			}(),
-			wantErr: false,
+			name:  "valid pattern - out of prefix range",
+			input: fmt.Sprintf("agora keyword is not close to the real key and secret = '%s'", validPattern),
+			want:  nil,
 		},
 		{
-			name: "found, real secrets, verification error due to unexpected api surface",
-			s:    Scanner{client: common.ConstantResponseHttpClient(500, "{}")},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a agora secret %s within agora id %s but verified", secret, id)),
-				verify: true,
-			},
-			want: func() []detectors.Result {
-				r := detectors.Result{
-					DetectorType: detectorspb.DetectorType_Agora,
-					Verified:     false,
-				}
-				r.SetVerificationError(fmt.Errorf("unexpected HTTP response status 500"))
-				return []detectors.Result{r, r, r, r}
-			}(),
-			wantErr: false,
+			name:  "valid pattern - only key",
+			input: fmt.Sprintf("agora %s", strings.Split(validPattern, "/")[0]),
+			want:  []string{"asdf0987mnbv1234qsxojb6ygb2wsx0oasdf0987mnbv1234qsxojb6ygb2wsx0o"},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a agora secret %s within agora id %s but not valid ", inactiveSecret, id)), // the secret would satisfy the regex but not pass validation
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Agora,
-					Verified:     false,
-				},
-				{
-					DetectorType: detectorspb.DetectorType_Agora,
-					Verified:     false,
-				},
-				{
-					DetectorType: detectorspb.DetectorType_Agora,
-					Verified:     false,
-				},
-				{
-					DetectorType: detectorspb.DetectorType_Agora,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - only secret",
+			input: fmt.Sprintf("agora %s", strings.Split(validPattern, "/")[1]),
+			want:  []string{"beqr7215fr4g6bfjkmnvxrtygb2wsxapbeqr7215fr4g6bfjkmnvxrtygb2wsxap"},
 		},
 		{
-			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("agora %s", invalidPattern),
+			want:  nil,
 		},
 	}
-	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("Agora.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")
-				}
-				gotErr := ""
-				if got[i].VerificationError() != nil {
-					gotErr = got[i].VerificationError().Error()
-				}
-				wantErr := ""
-				if tt.want[i].VerificationError() != nil {
-					wantErr = tt.want[i].VerificationError().Error()
-				}
-				if gotErr != wantErr {
-					t.Fatalf("wantVerificationError = %v, verification error = %v", tt.want[i].VerificationError(), got[i].VerificationError())
-				}
-			}
-			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError")
-			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
-				t.Errorf("Agora.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/aha/aha_integration_test.go

@@ -0,0 +1,168 @@
+//go:build detectors
+// +build detectors
+
+package aha
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestAha_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)
+	}
+	domain := testSecrets.MustGetField("AHA_DOMAIN")
+	secret := testSecrets.MustGetField("AHA_SECRET")
+	inactiveSecret := testSecrets.MustGetField("AHA_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{client: common.ConstantResponseHttpClient(200, "{}")},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a aha secret %s within %s but verified", secret, domain)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Aha,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, real secrets, verification error due to timeout",
+			s:    Scanner{client: common.SaneHttpClientTimeOut(1 * time.Microsecond)},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a aha secret %s within %s but verified", secret, domain)),
+				verify: true,
+			},
+			want: func() []detectors.Result {
+				r := detectors.Result{
+					DetectorType: detectorspb.DetectorType_Aha,
+					Verified:     false,
+				}
+				r.SetVerificationError(context.DeadlineExceeded)
+				return []detectors.Result{r}
+			}(),
+			wantErr: false,
+		},
+		{
+			name: "found, real secrets, verification error due to unexpected api surface",
+			s:    Scanner{client: common.ConstantResponseHttpClient(500, "{}")},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a aha secret %s within %s but verified", secret, domain)),
+				verify: true,
+			},
+			want: func() []detectors.Result {
+				r := detectors.Result{
+					DetectorType: detectorspb.DetectorType_Aha,
+					Verified:     false,
+				}
+				r.SetVerificationError(fmt.Errorf("unexpected HTTP response status 500"))
+				return []detectors.Result{r}
+			}(),
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a aha secret %s within but not valid domain %s", inactiveSecret, domain)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Aha,
+					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) {
+			got, err := tt.s.FromData(tt.args.ctx, tt.args.verify, tt.args.data)
+			if (err != nil) != tt.wantErr {
+				t.Errorf("Aha.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])
+				}
+				gotErr := ""
+				if got[i].VerificationError() != nil {
+					gotErr = got[i].VerificationError().Error()
+				}
+				wantErr := ""
+				if tt.want[i].VerificationError() != nil {
+					wantErr = tt.want[i].VerificationError().Error()
+				}
+				if gotErr != wantErr {
+					t.Fatalf("wantVerificationError = %v, verification error = %v", tt.want[i].VerificationError(), got[i].VerificationError())
+				}
+			}
+			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("Aha.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/aha/aha_test.go

@@ -1,167 +1,104 @@
-//go:build detectors
-// +build detectors
-
 package aha
 
 import (
 	"context"
 	"fmt"
+	"strings"
 	"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 TestAha_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)
-	}
-	domain := testSecrets.MustGetField("AHA_DOMAIN")
-	secret := testSecrets.MustGetField("AHA_SECRET")
-	inactiveSecret := testSecrets.MustGetField("AHA_INACTIVE")
+var (
+	validPattern   = "00112233445566778899aabbccddeeff00112233445566778899aabbccddeeff/example.aha.io"
+	invalidPattern = "00112233445566778899aabbCC$%eeff00112233445566778899aabbccddeeff/example.fake.io"
+)
+
+func TestAha_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
+
+	key := strings.Split(validPattern, "/")[0]
+	url := strings.Split(validPattern, "/")[1]
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name  string
+		input string
+		want  []string
 	}{
 		{
-			name: "found, verified",
-			s:    Scanner{client: common.ConstantResponseHttpClient(200, "{}")},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a aha secret %s within %s but verified", secret, domain)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Aha,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern",
+			input: fmt.Sprintf("aha.io = '%s'", validPattern),
+			want:  []string{key},
 		},
 		{
-			name: "found, real secrets, verification error due to timeout",
-			s:    Scanner{client: common.SaneHttpClientTimeOut(1 * time.Microsecond)},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a aha secret %s within %s but verified", secret, domain)),
-				verify: true,
-			},
-			want: func() []detectors.Result {
-				r := detectors.Result{
-					DetectorType: detectorspb.DetectorType_Aha,
-					Verified:     false,
-				}
-				r.SetVerificationError(context.DeadlineExceeded)
-				return []detectors.Result{r}
-			}(),
-			wantErr: false,
+			name:  "valid pattern - detect URL far away from keyword",
+			input: fmt.Sprintf("aha.io = '%s\n URL is not close to the keyword but should be detected %s'", key, url),
+			want:  []string{key},
 		},
 		{
-			name: "found, real secrets, verification error due to unexpected api surface",
-			s:    Scanner{client: common.ConstantResponseHttpClient(500, "{}")},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a aha secret %s within %s but verified", secret, domain)),
-				verify: true,
-			},
-			want: func() []detectors.Result {
-				r := detectors.Result{
-					DetectorType: detectorspb.DetectorType_Aha,
-					Verified:     false,
-				}
-				r.SetVerificationError(fmt.Errorf("unexpected HTTP response status 500"))
-				return []detectors.Result{r}
-			}(),
-			wantErr: false,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("aha.io keyword is not close to the real key and secret = '%s'", validPattern),
+			want:  nil,
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a aha secret %s within but not valid domain %s", inactiveSecret, domain)), // the secret would satisfy the regex but not pass validation
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Aha,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - only key",
+			input: fmt.Sprintf("aha.io %s", key),
+			want:  []string{key},
 		},
 		{
-			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 - only URL",
+			input: fmt.Sprintf("aha.io %s", url),
+			want:  nil,
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("aha.io %s", invalidPattern),
+			want:  nil,
 		},
 	}
-	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("Aha.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])
-				}
-				gotErr := ""
-				if got[i].VerificationError() != nil {
-					gotErr = got[i].VerificationError().Error()
-				}
-				wantErr := ""
-				if tt.want[i].VerificationError() != nil {
-					wantErr = tt.want[i].VerificationError().Error()
-				}
-				if gotErr != wantErr {
-					t.Fatalf("wantVerificationError = %v, verification error = %v", tt.want[i].VerificationError(), got[i].VerificationError())
-				}
-			}
-			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError")
-			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
-				t.Errorf("Aha.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/airbrakeprojectkey/airbrakeprojectkey_integration_test.go

@@ -0,0 +1,121 @@
+//go:build detectors
+// +build detectors
+
+package airbrakeprojectkey
+
+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 TestAirbrakeProjectKey_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("AIRBRAKEPROJECTKEY_TOKEN")
+	id := testSecrets.MustGetField("AIRBRAKEPROJECTKEY_ID")
+	inactiveSecret := testSecrets.MustGetField("AIRBRAKEPROJECTKEY_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 airbrake secret %s within airbrake %s but verified", secret, id)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_AirbrakeProjectKey,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a airbrake secret %s within airbrake %s but not valid", inactiveSecret, id)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_AirbrakeProjectKey,
+					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("AirbrakeProjectKey.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("AirbrakeProjectKey.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/airbrakeprojectkey/airbrakeprojectkey_test.go

@@ -1,120 +1,96 @@
-//go:build detectors
-// +build detectors
-
 package airbrakeprojectkey
 
 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 TestAirbrakeProjectKey_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("AIRBRAKEPROJECTKEY_TOKEN")
-	id := testSecrets.MustGetField("AIRBRAKEPROJECTKEY_ID")
-	inactiveSecret := testSecrets.MustGetField("AIRBRAKEPROJECTKEY_INACTIVE")
+var (
+	validPattern   = "qwmnerBv56zxpocvkjqr78afvYUx90Op/451298"
+	invalidPattern = "qwmnerBv56zxpocvkjqr78afvYU$90Op/4512987"
+)
+
+func TestAirBrakeProjectKey_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
 	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 airbrake secret %s within airbrake %s but verified", secret, id)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_AirbrakeProjectKey,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern",
+			input: fmt.Sprintf("airbrake = '%s'", validPattern),
+			want:  []string{"qwmnerBv56zxpocvkjqr78afvYUx90Op451298"},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a airbrake secret %s within airbrake %s but not valid", inactiveSecret, id)), // the secret would satisfy the regex but not pass validation
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_AirbrakeProjectKey,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("airbrake keyword is not close to the real key and secret = '%s'", validPattern),
+			want:  nil,
 		},
 		{
-			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 - only key",
+			input: fmt.Sprintf("airbrake %s", strings.Split(validPattern, "/")[0]),
+			want:  nil,
+		},
+		{
+			name:  "valid pattern - only ID",
+			input: fmt.Sprintf("airbrake %s", strings.Split(validPattern, "/")[0]),
+			want:  nil,
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("airbrake = '%s'", invalidPattern),
+			want:  nil,
 		},
 	}
-	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("AirbrakeProjectKey.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("AirbrakeProjectKey.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/airbrakeuserkey/airbrakeuserkey_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package airbrakeuserkey
+
+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 TestAirbrakeUserKey_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("AIRBRAKEUSERKEY_TOKEN")
+	inactiveSecret := testSecrets.MustGetField("AIRBRAKEUSERKEY_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 airbrakeuserkey secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_AirbrakeUserKey,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a airbrakeuserkey 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_AirbrakeUserKey,
+					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("AirbrakeUserKey.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("AirbrakeUserKey.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/airbrakeuserkey/airbrakeuserkey_test.go

@@ -1,119 +1,85 @@
-//go:build detectors
-// +build detectors
-
 package airbrakeuserkey
 
 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 TestAirbrakeUserKey_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("AIRBRAKEUSERKEY_TOKEN")
-	inactiveSecret := testSecrets.MustGetField("AIRBRAKEUSERKEY_INACTIVE")
+var (
+	validPattern   = "qsCGuilpkk2ngrsz75wtYqsCGuilpkk2ngrsz75w"
+	invalidPattern = "Qs%CGuil#pkk2ngrsz75wtYqsCGuilpkk2ngrsz75w"
+)
+
+func TestAirBrakeUserKey_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
 	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 airbrakeuserkey secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_AirbrakeUserKey,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern",
+			input: fmt.Sprintf("airbrake = '%s'", validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a airbrakeuserkey 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_AirbrakeUserKey,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("airbrake keyword is not close to the real key and secret = '%s'", validPattern),
+			want:  nil,
 		},
 		{
-			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("airbrake = '%s'", invalidPattern),
+			want:  nil,
 		},
 	}
-	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("AirbrakeUserKey.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("AirbrakeUserKey.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/airship/airship.go

@@ -21,7 +21,7 @@ var (
 	client = common.SaneHttpClient()
 
 	// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
-	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"airship"}) + `\b([0-9Aa-zA-Z]{91})\b`)
+	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"airship"}) + `\b([0-9a-zA-Z]{91})\b`)
 )
 
 // Keywords are used for efficiently pre-filtering chunks.

pkg/detectors/airship/airship_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package airship
+
+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 TestAirship_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("AIRSHIP")
+	inactiveSecret := testSecrets.MustGetField("AIRSHIP_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 airship secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Airship,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a airship 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_Airship,
+					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("Airship.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("Airship.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/airship/airship_test.go

@@ -1,119 +1,85 @@
-//go:build detectors
-// +build detectors
-
 package airship
 
 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 TestAirship_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("AIRSHIP")
-	inactiveSecret := testSecrets.MustGetField("AIRSHIP_INACTIVE")
+var (
+	validPattern   = "123abcdef456ghijkl789mnopqr012stuvwx3455123abcdef456ghijkl789mnopqr012stuvwx3455trdfrq95acr"
+	invalidPattern = "123#abcdef456gh$ijkl789mnopqr012stuvwX3455123abcdef456ghijkl789mnopqr012stuvwx3455trdfrq"
+)
+
+func TestAirship_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
 	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 airship secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Airship,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern",
+			input: fmt.Sprintf("airship = '%s'", validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a airship 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_Airship,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("airship keyword is not close to the real key and secret = '%s'", validPattern),
+			want:  nil,
 		},
 		{
-			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("airship = '%s'", invalidPattern),
+			want:  nil,
 		},
 	}
-	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("Airship.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("Airship.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/airtableapikey/airtableapikey.go

@@ -13,7 +13,7 @@ import (
 	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
 )
 
-type Scanner struct{
+type Scanner struct {
 	detectors.DefaultMultiPartCredentialProvider
 }
 
@@ -51,7 +51,6 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 
 	if len(keyMatches) == 0 {
 		keyMatches = personalKeyMatches
-
 	}
 
 	for _, keyMatch := range keyMatches {

pkg/detectors/airtableapikey/airtableapikey_integration_test.go

@@ -0,0 +1,125 @@
+//go:build detectors
+// +build detectors
+
+package airtableapikey
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestAirtableApiKey_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("AIRTABLEAPIKEY_KEY")
+	inactiveSecret := testSecrets.MustGetField("AIRTABLEAPIKEY_KEY_INACTIVE")
+	app := testSecrets.MustGetField("AIRTABLEAPIKEY_APP")
+
+	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 airtableapikey secret %s within airtable https://api.airtable.com/v0/%s/Projects", secret, app)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_AirtableApiKey,
+					Redacted:     app,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a airtableapikey secret %s within airtable %s", inactiveSecret, app)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_AirtableApiKey,
+					Redacted:     app,
+					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("AirtableApiKey.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
+			}
+			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("Airtable.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/airtableapikey/airtableapikey_test.go

@@ -1,124 +1,86 @@
-//go:build detectors
-// +build detectors
-
 package airtableapikey
 
 import (
 	"context"
 	"fmt"
 	"testing"
-	"time"
-
-	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
 
 	"github.com/google/go-cmp/cmp"
-	"github.com/google/go-cmp/cmp/cmpopts"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 )
 
-func TestAirtableApiKey_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("AIRTABLEAPIKEY_KEY")
-	inactiveSecret := testSecrets.MustGetField("AIRTABLEAPIKEY_KEY_INACTIVE")
-	app := testSecrets.MustGetField("AIRTABLEAPIKEY_APP")
+var (
+	validPattern            = "app_pOcv67-Yuztyq / key_Yuztyq-pOcv67"
+	validPersonalKeyPattern = "app_pOcv67-Yuztyq / patWtrafrcg64DP0w.AA1AA2BB3CC4DD5EE6FF7GG8HH9II0JJ1KK2LL3MM4NN5OO6PP7QQ8aaaaaaaaaa"
+	invalidPattern          = "app_pOcv67%Yuztyq/key_Yuztyq*pOcv67"
+)
+
+func TestAirTableApiKey_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
 	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 airtableapikey secret %s within airtable https://api.airtable.com/v0/%s/Projects", secret, app)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_AirtableApiKey,
-					Redacted:     app,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with key",
+			input: fmt.Sprintf("airtable secrets: %s", validPattern),
+			want:  []string{"key_Yuztyq-pOcv67app_pOcv67-Yuztyq"},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a airtableapikey secret %s within airtable %s", inactiveSecret, app)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_AirtableApiKey,
-					Redacted:     app,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with personal key",
+			input: fmt.Sprintf("airtable secrets: %s", validPersonalKeyPattern),
+			want:  []string{"patWtrafrcg64DP0w.AA1AA2BB3CC4DD5EE6FF7GG8HH9II0JJ1KK2LL3MM4NN5OO6PP7QQ8aaaaaaaaaaapp_pOcv67-Yuztyq"},
 		},
 		{
-			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("airtable secrets: '%s'", invalidPattern),
+			want:  nil,
 		},
 	}
-	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("AirtableApiKey.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
-			}
-			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError")
-			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
-				t.Errorf("Airtable.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/airvisual/airvisual_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package airvisual
+
+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 TestAirVisual_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("AIRVISUAL")
+	inactiveSecret := testSecrets.MustGetField("AIRVISUAL_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 airvisual secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_AirVisual,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a airvisual 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_AirVisual,
+					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("AirVisual.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("AirVisual.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/airvisual/airvisual_test.go

@@ -1,119 +1,85 @@
-//go:build detectors
-// +build detectors
-
 package airvisual
 
 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 TestAirVisual_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("AIRVISUAL")
-	inactiveSecret := testSecrets.MustGetField("AIRVISUAL_INACTIVE")
+var (
+	validPattern   = "qscgyygcsq-wdvvok7slklklaasnd8afafxd"
+	invalidPattern = "wdvvok7slklklaasnd8afafxd"
+)
+
+func TestAirVisual_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
 	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 airvisual secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_AirVisual,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern",
+			input: fmt.Sprintf("airvisual = '%s'", validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a airvisual 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_AirVisual,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("airvisual keyword is not close to the real key and secret = '%s'", validPattern),
+			want:  nil,
 		},
 		{
-			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("airvisual key: '%s'", invalidPattern),
+			want:  nil,
 		},
 	}
-	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("AirVisual.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("AirVisual.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/aiven/aiven_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package aiven
+
+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 TestAiven_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("AIVEN")
+	inactiveSecret := testSecrets.MustGetField("AIVEN_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 aiven secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Aiven,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a aiven 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_Aiven,
+					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("Aiven.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("Aiven.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/aiven/aiven_test.go

@@ -1,119 +1,85 @@
-//go:build detectors
-// +build detectors
-
 package aiven
 
 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 TestAiven_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("AIVEN")
-	inactiveSecret := testSecrets.MustGetField("AIVEN_INACTIVE")
+var (
+	validPattern   = `ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef123/+==ABCdef12`
+	invalidPattern = `ABCdef123`
+)
+
+func TestAiven_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
 	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 aiven secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Aiven,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern",
+			input: fmt.Sprintf("aiven = '%s'", validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a aiven 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_Aiven,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("aiven keyword is not close to the real key and secret = '%s'", validPattern),
+			want:  nil,
 		},
 		{
-			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("aiven = '%s'", invalidPattern),
+			want:  nil,
 		},
 	}
-	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("Aiven.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("Aiven.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/alconost/alconost_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package alconost
+
+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 TestAlconost_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("ALCONOST")
+	inactiveSecret := testSecrets.MustGetField("ALCONOST_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 alconost secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Alconost,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a alconost 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_Alconost,
+					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("Alconost.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("Alconost.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/alconost/alconost_test.go

@@ -1,119 +1,85 @@
-//go:build detectors
-// +build detectors
-
 package alconost
 
 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 TestAlconost_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("ALCONOST")
-	inactiveSecret := testSecrets.MustGetField("ALCONOST_INACTIVE")
+var (
+	validPattern   = "wdvnousa87acfxp9ioasrea4tbeasrfa"
+	invalidPattern = "wdvnousa87acfxp9ioasr$a4tBeasrfa"
+)
+
+func TestAlconost_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
 	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 alconost secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Alconost,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern",
+			input: fmt.Sprintf("alconost: '%s'", validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a alconost 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_Alconost,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("alconost keyword is not close to the real key in the data = '%s'", validPattern),
+			want:  nil,
 		},
 		{
-			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("alconost: '%s'", invalidPattern),
+			want:  nil,
 		},
 	}
-	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("Alconost.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("Alconost.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/alegra/alegra.go

@@ -12,7 +12,7 @@ import (
 	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
 )
 
-type Scanner struct{
+type Scanner struct {
 	detectors.DefaultMultiPartCredentialProvider
 }
 
@@ -24,7 +24,7 @@ var (
 
 	// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
 	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"alegra"}) + `\b([a-z0-9-]{20})\b`)
-	idPat  = regexp.MustCompile(detectors.PrefixRegex([]string{"alegra"}) + `\b([a-zA-Z0-9.-@]{25,30})\b`)
+	idPat  = regexp.MustCompile(detectors.PrefixRegex([]string{"alegra"}) + `\b([a-zA-Z0-9\.\-\@]{25,30})\b`)
 )
 
 // Keywords are used for efficiently pre-filtering chunks.

pkg/detectors/alegra/alegra_integration_test.go

@@ -0,0 +1,121 @@
+//go:build detectors
+// +build detectors
+
+package alegra
+
+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 TestAlegra_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("ALEGRA")
+	id := testSecrets.MustGetField("ACCOUNT_USER")
+	inactiveSecret := testSecrets.MustGetField("ALEGRA_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 alegra secret %s within alegra %s", secret, id)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Alegra,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a alegra secret %s within alegra %s but not valid", inactiveSecret, id)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Alegra,
+					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("Alegra.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("Alegra.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/alegra/alegra_test.go

@@ -1,120 +1,91 @@
-//go:build detectors
-// +build detectors
-
 package alegra
 
 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 TestAlegra_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("ALEGRA")
-	id := testSecrets.MustGetField("ACCOUNT_USER")
-	inactiveSecret := testSecrets.MustGetField("ALEGRA_INACTIVE")
+var (
+	validPattern            = "wdvn-usa87a-fxp9ioas/[email protected]"
+	validSpecialCharPattern = "wdvn-usa87a-fxp9ioas / [email protected]"
+	invalidPattern          = "wdvn-usa87a-fxp9ioas/[email protected]"
+)
+
+func TestAlegra_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
 	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 alegra secret %s within alegra %s", secret, id)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Alegra,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern",
+			input: fmt.Sprintf("alegra: '%s'", validPattern),
+			want:  []string{"[email protected]"},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a alegra secret %s within alegra %s but not valid", inactiveSecret, id)), // the secret would satisfy the regex but not pass validation
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Alegra,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - with special characters",
+			input: fmt.Sprintf("alegra: '%s'", validSpecialCharPattern),
+			want:  []string{"[email protected]"},
 		},
 		{
-			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("alegra keyword is not close to the real key and id = '%s'", validPattern),
+			want:  nil,
+		},
+		{
+			name:  "invalid pattern",
+			input: fmt.Sprintf("alegra: '%s'", invalidPattern),
+			want:  nil,
 		},
 	}
-	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("Alegra.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("Alegra.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/aletheiaapi/aletheiaapi_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package aletheiaapi
+
+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 TestAletheiaApi_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("ALETHEIAAPI")
+	inactiveSecret := testSecrets.MustGetField("ALETHEIAAPI_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 aletheiaapi secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_AletheiaApi,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a aletheiaapi 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_AletheiaApi,
+					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("AletheiaApi.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("AletheiaApi.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/aletheiaapi/aletheiaapi_test.go

@@ -1,119 +1,85 @@
-//go:build detectors
-// +build detectors
-
 package aletheiaapi
 
 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 TestAletheiaApi_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("ALETHEIAAPI")
-	inactiveSecret := testSecrets.MustGetField("ALETHEIAAPI_INACTIVE")
+var (
+	validPattern   = "TEST01KEYPATTERN2024ALETHEIAAPIN"
+	invalidPattern = "TEST01kEYPATTERN2024ALETHEIAAPIN"
+)
+
+func TestAleTheIaAPI_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
 	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 aletheiaapi secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_AletheiaApi,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern",
+			input: fmt.Sprintf("aletheiaapi: '%s'", validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a aletheiaapi 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_AletheiaApi,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("aletheiaapi keyword is not close to the real key and secret = '%s'", validPattern),
+			want:  nil,
 		},
 		{
-			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("aletheiaapi: '%s'", invalidPattern),
+			want:  nil,
 		},
 	}
-	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("AletheiaApi.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("AletheiaApi.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/algoliaadminkey/algoliaadminkey_integration_test.go

@@ -0,0 +1,121 @@
+//go:build detectors
+// +build detectors
+
+package algoliaadminkey
+
+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 TestAlgoliaAdminKey_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("ALGOLIAADMINKEY_TOKEN")
+	inactiveSecret := testSecrets.MustGetField("ALGOLIAADMINKEY_INACTIVE")
+	id := testSecrets.MustGetField("ALGOLIAADMINKEY_APPID")
+
+	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 algolia secret %s within algolia %s", secret, id)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_AlgoliaAdminKey,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a algolia secret %s within algolia %s but not valid", inactiveSecret, id)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_AlgoliaAdminKey,
+					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("AlgoliaAdminKey.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("AlgoliaAdminKey.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/algoliaadminkey/algoliaadminkey_test.go

@@ -1,120 +1,85 @@
-//go:build detectors
-// +build detectors
-
 package algoliaadminkey
 
 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 TestAlgoliaAdminKey_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("ALGOLIAADMINKEY_TOKEN")
-	inactiveSecret := testSecrets.MustGetField("ALGOLIAADMINKEY_INACTIVE")
-	id := testSecrets.MustGetField("ALGOLIAADMINKEY_APPID")
+var (
+	validPattern   = "AlgoliaAdminKey010TESTINGPlmiOPC/ADMIN01KEY"
+	invalidPattern = "AlgoliaAdminN$TKey010TESTINGPlmiOPC/NonAdmin01ID"
+)
+
+func TestAlgoliaAdminKey_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
 	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 algolia secret %s within algolia %s", secret, id)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_AlgoliaAdminKey,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern",
+			input: fmt.Sprintf("algolia: '%s'", validPattern),
+			want:  []string{"AlgoliaAdminKey010TESTINGPlmiOPCADMIN01KEY"},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a algolia secret %s within algolia %s but not valid", inactiveSecret, id)), // the secret would satisfy the regex but not pass validation
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_AlgoliaAdminKey,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("algolia keyword is not close to the real key and secret = '%s'", validPattern),
+			want:  nil,
 		},
 		{
-			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("algolia: '%s'", invalidPattern),
+			want:  nil,
 		},
 	}
-	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("AlgoliaAdminKey.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("AlgoliaAdminKey.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/alibaba/alibaba_integration_test.go

@@ -0,0 +1,186 @@
+//go:build detectors
+// +build detectors
+
+package alibaba
+
+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 TestAlibaba_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("ALIBABA_SECRET")
+	inactiveSecret := testSecrets.MustGetField("ALIBABA_SECRET_INACTIVE")
+	id := testSecrets.MustGetField("ALIBABA_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 alibaba secret %s within alibaba %s", secret, id)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Alibaba,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, real secrets, verification error due to timeout",
+			s:    Scanner{client: common.SaneHttpClientTimeOut(1 * time.Microsecond)},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a alibaba secret %s within alibaba %s", secret, id)),
+				verify: true,
+			},
+			want: func() []detectors.Result {
+				r := detectors.Result{
+					DetectorType: detectorspb.DetectorType_Alibaba,
+					Verified:     false,
+				}
+				r.SetVerificationError(context.DeadlineExceeded)
+				return []detectors.Result{r}
+			}(),
+			wantErr: false,
+		},
+		{
+			name: "found, real secrets, verification error due to unexpected api surface",
+			s:    Scanner{client: common.ConstantResponseHttpClient(500, "{}")},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a alibaba secret %s within alibaba %s", secret, id)),
+				verify: true,
+			},
+			want: func() []detectors.Result {
+				r := detectors.Result{
+					DetectorType: detectorspb.DetectorType_Alibaba,
+					Verified:     false,
+				}
+				r.SetVerificationError(fmt.Errorf("unexpected HTTP response status 500"))
+				return []detectors.Result{r}
+			}(),
+			wantErr: false,
+		},
+		{
+			name: "found, real secrets, verification error due to broken json",
+			s:    Scanner{client: common.ConstantResponseHttpClient(418, "{")},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a alibaba secret %s within alibaba %s", secret, id)),
+				verify: true,
+			},
+			want: func() []detectors.Result {
+				r := detectors.Result{
+					DetectorType: detectorspb.DetectorType_Alibaba,
+					Verified:     false,
+				}
+				r.SetVerificationError(fmt.Errorf("unexpected EOF"))
+				return []detectors.Result{r}
+			}(),
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a alibaba secret %s within alibaba %s but not valid", inactiveSecret, id)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Alibaba,
+					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) {
+			got, err := tt.s.FromData(tt.args.ctx, tt.args.verify, tt.args.data)
+			if (err != nil) != tt.wantErr {
+				t.Errorf("Alibaba.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])
+				}
+				gotErr := ""
+				if got[i].VerificationError() != nil {
+					gotErr = got[i].VerificationError().Error()
+				}
+				wantErr := ""
+				if tt.want[i].VerificationError() != nil {
+					wantErr = tt.want[i].VerificationError().Error()
+				}
+				if gotErr != wantErr {
+					t.Fatalf("wantVerificationError = %v, verification error = %v", tt.want[i].VerificationError(), got[i].VerificationError())
+				}
+			}
+			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("Alibaba.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/alibaba/alibaba_test.go

@@ -1,185 +1,85 @@
-//go:build detectors
-// +build detectors
-
 package alibaba
 
 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 TestAlibaba_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("ALIBABA_SECRET")
-	inactiveSecret := testSecrets.MustGetField("ALIBABA_SECRET_INACTIVE")
-	id := testSecrets.MustGetField("ALIBABA_ID")
+var (
+	validPattern   = "abcDEF123ghiJKL456mnoPQR789std/LTAI123ABCdef456ghijkLMN"
+	invalidPattern = "abcDEF123ghiJKL456m$oPQR789/123ABCdef456ghijkLMN;"
+)
+
+func TestAliBaba_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
 	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 alibaba secret %s within alibaba %s", secret, id)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Alibaba,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern",
+			input: fmt.Sprintf("LTAI: '%s'", validPattern),
+			want:  []string{"abcDEF123ghiJKL456mnoPQR789stdLTAI123ABCdef456ghijkLMN"},
 		},
 		{
-			name: "found, real secrets, verification error due to timeout",
-			s:    Scanner{client: common.SaneHttpClientTimeOut(1 * time.Microsecond)},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a alibaba secret %s within alibaba %s", secret, id)),
-				verify: true,
-			},
-			want: func() []detectors.Result {
-				r := detectors.Result{
-					DetectorType: detectorspb.DetectorType_Alibaba,
-					Verified:     false,
-				}
-				r.SetVerificationError(context.DeadlineExceeded)
-				return []detectors.Result{r}
-			}(),
-			wantErr: false,
+			name:  "valid pattern - ignore special characters at end",
+			input: fmt.Sprintf("LTAI: '%s\"''", validPattern),
+			want:  []string{"abcDEF123ghiJKL456mnoPQR789stdLTAI123ABCdef456ghijkLMN"},
 		},
 		{
-			name: "found, real secrets, verification error due to unexpected api surface",
-			s:    Scanner{client: common.ConstantResponseHttpClient(500, "{}")},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a alibaba secret %s within alibaba %s", secret, id)),
-				verify: true,
-			},
-			want: func() []detectors.Result {
-				r := detectors.Result{
-					DetectorType: detectorspb.DetectorType_Alibaba,
-					Verified:     false,
-				}
-				r.SetVerificationError(fmt.Errorf("unexpected HTTP response status 500"))
-				return []detectors.Result{r}
-			}(),
-			wantErr: false,
-		},
-		{
-			name: "found, real secrets, verification error due to broken json",
-			s:    Scanner{client: common.ConstantResponseHttpClient(418, "{")},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a alibaba secret %s within alibaba %s", secret, id)),
-				verify: true,
-			},
-			want: func() []detectors.Result {
-				r := detectors.Result{
-					DetectorType: detectorspb.DetectorType_Alibaba,
-					Verified:     false,
-				}
-				r.SetVerificationError(fmt.Errorf("unexpected EOF"))
-				return []detectors.Result{r}
-			}(),
-			wantErr: false,
-		},
-		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a alibaba secret %s within alibaba %s but not valid", inactiveSecret, id)), // the secret would satisfy the regex but not pass validation
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_Alibaba,
-					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:  "invalid pattern",
+			input: fmt.Sprintf("LTAI: '%s'", invalidPattern),
+			want:  nil,
 		},
 	}
-	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("Alibaba.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])
-				}
-				gotErr := ""
-				if got[i].VerificationError() != nil {
-					gotErr = got[i].VerificationError().Error()
-				}
-				wantErr := ""
-				if tt.want[i].VerificationError() != nil {
-					wantErr = tt.want[i].VerificationError().Error()
-				}
-				if gotErr != wantErr {
-					t.Fatalf("wantVerificationError = %v, verification error = %v", tt.want[i].VerificationError(), got[i].VerificationError())
-				}
-			}
-			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError")
-			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
-				t.Errorf("Alibaba.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/alienvault/alienvault_integration_test.go

@@ -0,0 +1,120 @@
+//go:build detectors
+// +build detectors
+
+package alienvault
+
+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 TestAlienVault_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("ALIENVAULT")
+	inactiveSecret := testSecrets.MustGetField("ALIENVAULT_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 alienvault secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_AlienVault,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a alienvault 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_AlienVault,
+					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("AlienVault.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("AlienVault.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/alienvault/alienvault_test.go

@@ -1,119 +1,85 @@
-//go:build detectors
-// +build detectors
-
 package alienvault
 
 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 TestAlienVault_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("ALIENVAULT")
-	inactiveSecret := testSecrets.MustGetField("ALIENVAULT_INACTIVE")
+var (
+	validPattern   = "a3b9f8c1e2d4f5b6c7d8e9a0b1c2d3e4f5a6b7c8d9e0f1a2b3c4d5e6f7a8b9c0"
+	invalidPattern = "A$3b9f8c1e2d4f5b6c7d8e9a0b1c2d3e4f5a6b7c8d9e0f1a2b3c4d"
+)
+
+func TestAlienVault_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
 
-	type args struct {
-		ctx    context.Context
-		data   []byte
-		verify bool
-	}
 	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 alienvault secret %s within", secret)),
-				verify: true,
-			},
-			want: []detectors.Result{
-				{
-					DetectorType: detectorspb.DetectorType_AlienVault,
-					Verified:     true,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern",
+			input: fmt.Sprintf("alienvault: '%s'", validPattern),
+			want:  []string{validPattern},
 		},
 		{
-			name: "found, unverified",
-			s:    Scanner{},
-			args: args{
-				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("You can find a alienvault 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_AlienVault,
-					Verified:     false,
-				},
-			},
-			wantErr: false,
+			name:  "valid pattern - key out of prefix range",
+			input: fmt.Sprintf("alienvault keyword is not close to the real key in the data\n = '%s'", validPattern),
+			want:  nil,
 		},
 		{
-			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("alienvault: '%s'", invalidPattern),
+			want:  nil,
 		},
 	}
-	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("AlienVault.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("AlienVault.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)
 			}
 		})
 	}