trufflehog/pkg/detectors/flyio/flyio_test.go

package flyio

import (
	"context"
	"testing"

	"github.com/google/go-cmp/cmp"

	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
)

func TestFlyio_Pattern(t *testing.T) {
	d := Scanner{}
	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
	tests := []struct {
		name  string
		input string
		want  []string
	}{
		{
			name:  "typical pattern",
			input: "flyio_token = 'FlyV1 fm2_AD1shwGbLSpZSPEXM1vhcbPZowurCDkXySOOJj0w4G2abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890'",
			want:  []string{"FlyV1 fm2_AD1shwGbLSpZSPEXM1vhcbPZowurCDkXySOOJj0w4G2abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890"},
		},
		{
			name:  "invalid pattern - too short",
			input: "flyio_token = 'FlyV1 fm2_short'",
			want:  []string{},
		},
		{
			name:  "invalid pattern - wrong prefix",
			input: "flyio_token = 'FlyV2 fm2_AD1shwGbLSpZSPEXM1vhcbPZowurCDkXySOOJj0w4G2abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890'",
			want:  []string{},
		},
	}

	for _, test := range tests {
		t.Run(test.name, func(t *testing.T) {
			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
			if len(test.want) > 0 && len(matchedDetectors) == 0 {
				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
				return
			}

			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 && len(test.want) > 0 {
					t.Errorf("did not receive result")
				} else if len(results) > 0 && len(test.want) == 0 {
					t.Errorf("expected no results, but received %d", len(results))
				} 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)
			}
		})
	}
}

func TestFlyio_IsFalsePositive(t *testing.T) {
	s := Scanner{}

	tests := []struct {
		name     string
		token    string
		expected bool
		reason   string
	}{
		{
			name:     "token with AAAAAA - should not be flagged as false positive",
			token:    "FlyV1 fm2_abcdAAAAAA1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890",
			expected: false,
			reason:   "",
		},
		{
			name:     "token with example pattern - should be false positive",
			token:    "FlyV1 fm2_1234example567890zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321",
			expected: true,
			reason:   "contains term: example",
		},
		{
			name:     "token with sample pattern - should be false positive",
			token:    "FlyV1 fm2_1234sample567890zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321",
			expected: true,
			reason:   "contains term: sample",
		},
		{
			name:     "token with xxxxxx pattern - should be false positive",
			token:    "FlyV1 fm2_1234xxxxxx567890zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA0987654321",
			expected: true,
			reason:   "contains term: xxxxxx",
		},
		{
			name:     "valid token without AAAAAA - should not be false positive",
			token:    "FlyV1 fm2_1234567890zyxwvutsrqponmlkjihgfZYXWVUTSRQPONMLKJIHGF0987654321zyxwvutsrqponmlkjihgfZYXWVUTSRQPONMLKJIHGF0987654321zyxwvutsrqponmlkjihgfZYXWVUTSRQPONMLKJIHGF0987654321zyxwvutsrqponmlkjihgfZYXWVUTSRQPONMLKJIHGF0987654321zyxwvutsrqponmlkjihgfZYXWVUTSRQPONMLKJIHGF0987654321zyxwvutsrqponmlkjihgfZYXWVUTSRQPONMLKJIHGF0987654321zyxwvutsrqponmlkjihgfZYXWVUTSRQPONMLKJIHGF0987654321zyxwvutsrqponmlkjihgfZYXWVUTSRQPONMLKJIHGF0987654321zyxwvutsrqponmlkjihgfZYXWVUTSRQPONMLKJIHGF0987654321",
			expected: false,
			reason:   "",
		},
		{
			name:     "regular string without pattern - should not be false positive",
			token:    "XYZABC123789def456",
			expected: false,
			reason:   "",
		},
	}

	for _, tt := range tests {
		t.Run(tt.name, func(t *testing.T) {
			result := detectors.Result{
				DetectorType: detectorspb.DetectorType_FlyIO,
				Raw:          []byte(tt.token),
			}

			isFP, reason := s.IsFalsePositive(result)

			if isFP != tt.expected {
				t.Errorf("IsFalsePositive() got = %v, want %v (reason: %s)", isFP, tt.expected, reason)
			}

			if tt.expected && reason != tt.reason {
				t.Errorf("IsFalsePositive() reason got = %v, want %v", reason, tt.reason)
			}
		})
	}
}

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)
				}
			}
		})
	}
}