feat(detectors): update template (#2342)

hack/generate/generate.go

@@ -85,8 +85,10 @@ func mustWriteTemplates(jobs []templateJob) {
 		tmplRaw := string(tmplBytes)
 
 		for _, rplString := range job.ReplaceString {
+			rplTitle := cases.Title(language.AmericanEnglish).String(rplString)
+			tmplRaw = strings.ReplaceAll(tmplRaw, "DetectorType_"+rplTitle, "DetectorType_<<.Name>>")
 			tmplRaw = strings.ReplaceAll(tmplRaw, strings.ToLower(rplString), "<<.NameLower>>")
-			tmplRaw = strings.ReplaceAll(tmplRaw, cases.Title(language.AmericanEnglish).String(rplString), "<<.NameTitle>>")
+			tmplRaw = strings.ReplaceAll(tmplRaw, rplTitle, "<<.NameTitle>>")
 			tmplRaw = strings.ReplaceAll(tmplRaw, strings.ToUpper(rplString), "<<.NameUpper>>")
 		}
 
@@ -98,6 +100,7 @@ func mustWriteTemplates(jobs []templateJob) {
 			log.Fatal(err)
 		}
 		err = tmpl.Execute(f, templateData{
+			Name:      *name,
 			NameTitle: nameTitle,
 			NameLower: nameLower,
 			NameUpper: nameUpper,
@@ -109,6 +112,7 @@ func mustWriteTemplates(jobs []templateJob) {
 }
 
 type templateData struct {
+	Name      string
 	NameTitle string
 	NameLower string
 	NameUpper string

pkg/detectors/alchemy/alchemy.go

@@ -3,9 +3,10 @@ package alchemy
 import (
 	"context"
 	"fmt"
-	regexp "github.com/wasilibs/go-re2"
+	"io"
 	"net/http"
-	"strings"
+
+	regexp "github.com/wasilibs/go-re2"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -22,7 +23,7 @@ var _ detectors.Detector = (*Scanner)(nil)
 var (
 	defaultClient = 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{"alchemy"}) + `\b([0-9a-zA-Z]{23}_[0-9a-zA-Z]{8})\b`)
+	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"alchemy"}) + `\b([a-zA-Z0-9]{23}_[a-zA-Z0-9]{8})\b`)
 )
 
 // Keywords are used for efficiently pre-filtering chunks.
@@ -35,53 +36,65 @@ func (s Scanner) Keywords() []string {
 func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
 	dataStr := string(data)
 
-	matches := keyPat.FindAllStringSubmatch(dataStr, -1)
-
-	for _, match := range matches {
-		if len(match) != 2 {
-			continue
-		}
-		resMatch := strings.TrimSpace(match[1])
+	uniqueMatches := make(map[string]struct{})
+	for _, match := range keyPat.FindAllStringSubmatch(dataStr, -1) {
+		uniqueMatches[match[1]] = struct{}{}
+	}
 
+	for match := range uniqueMatches {
 		s1 := detectors.Result{
 			DetectorType: detectorspb.DetectorType_Alchemy,
-			Raw:          []byte(resMatch),
+			Raw:          []byte(match),
 		}
 
 		if verify {
 			client := s.client
 			if client == nil {
 				client = defaultClient
 			}
-			req, err := http.NewRequestWithContext(ctx, "GET", "https://eth-mainnet.g.alchemy.com/v2/"+resMatch+"/getNFTs/?owner=vitalik.eth", nil)
-			if err != nil {
-				continue
-			}
-			res, err := client.Do(req)
-			if err == nil {
-				defer res.Body.Close()
-				if res.StatusCode >= 200 && res.StatusCode < 300 {
-					s1.Verified = true
-				} else if res.StatusCode == 401 {
-					// The secret is determinately not verified (nothing to do)
-				} else {
-					err = fmt.Errorf("unexpected HTTP response status %d", res.StatusCode)
-					s1.SetVerificationError(err, resMatch)
-				}
-			} else {
-				s1.SetVerificationError(err, resMatch)
-			}
+
+			isVerified, extraData, verificationErr := verifyMatch(ctx, client, match)
+			s1.Verified = isVerified
+			s1.ExtraData = extraData
+			s1.SetVerificationError(verificationErr, match)
 		}
 
 		// This function will check false positives for common test words, but also it will make sure the key appears 'random' enough to be a real key.
-		if !s1.Verified && detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
+		if !s1.Verified && detectors.IsKnownFalsePositive(match, detectors.DefaultFalsePositives, true) {
 			continue
 		}
 
 		results = append(results, s1)
 	}
 
-	return results, nil
+	return
+}
+
+func verifyMatch(ctx context.Context, client *http.Client, token string) (bool, map[string]string, error) {
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, "https://eth-mainnet.g.alchemy.com/v2/"+token+"/getNFTs/?owner=vitalik.eth", nil)
+	if err != nil {
+		return false, nil, nil
+	}
+
+	res, err := client.Do(req)
+	if err != nil {
+		return false, nil, err
+	}
+	defer func() {
+		_, _ = io.Copy(io.Discard, res.Body)
+		_ = res.Body.Close()
+	}()
+
+	if res.StatusCode >= 200 && res.StatusCode < 300 {
+		// If the endpoint returns useful information, we can return it as a map.
+		return true, nil, nil
+	} else if res.StatusCode == 401 {
+		// The secret is determinately not verified (nothing to do)
+		return false, nil, nil
+	} else {
+		err = fmt.Errorf("unexpected HTTP response status %d", res.StatusCode)
+		return false, nil, err
+	}
 }
 
 func (s Scanner) Type() detectorspb.DetectorType {

pkg/detectors/alchemy/alchemy_test.go

@@ -12,12 +12,71 @@ import (
 	"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/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
 )
 
+func TestAlchemy_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
+	tests := []struct {
+		name  string
+		input string
+		want  []string
+	}{
+		{
+			name:  "typical pattern",
+			input: "alchemy_token = '3aBcDFE5678901234567890_1a2b3c4d'",
+			want:  []string{"3aBcDFE5678901234567890_1a2b3c4d"},
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			chunkSpecificDetectors := make(map[ahocorasick.DetectorKey]detectors.Detector, 2)
+			ahoCorasickCore.PopulateMatchingDetectors(test.input, chunkSpecificDetectors)
+			if len(chunkSpecificDetectors) == 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 {
+					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)
+			}
+		})
+	}
+}
+
 func TestAlchemy_FromChunk(t *testing.T) {
 	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
 	defer cancel()

pkg/engine/ahocorasickcore.go → pkg/engine/ahocorasick/ahocorasickcore.go

@@ -1,9 +1,10 @@
-package engine
+package ahocorasick
 
 import (
 	"strings"
 
 	ahocorasick "github.com/BobuSumisu/aho-corasick"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/custom_detectors"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"

pkg/engine/ahocorasickcore_test.go → pkg/engine/ahocorasick/ahocorasickcore_test.go

@@ -1,10 +1,11 @@
-package engine
+package ahocorasick
 
 import (
 	"context"
 	"testing"
 
 	"github.com/stretchr/testify/assert"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/custom_detectors"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/custom_detectorspb"

pkg/engine/engine.go

@@ -17,6 +17,7 @@ import (
 	"github.com/trufflesecurity/trufflehog/v3/pkg/context"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/decoders"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/giturl"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/output"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
@@ -65,7 +66,7 @@ type Engine struct {
 	printAvgDetectorTime bool
 
 	// ahoCorasickHandler manages the Aho-Corasick trie and related keyword lookups.
-	ahoCorasickCore *AhoCorasickCore
+	ahoCorasickCore *ahocorasick.AhoCorasickCore
 
 	// Engine synchronization primitives.
 	sourceManager        *sources.SourceManager
@@ -314,7 +315,7 @@ func (e *Engine) initialize(ctx context.Context, options ...Option) error {
 	ctx.Logger().V(4).Info("engine initialized")
 
 	ctx.Logger().V(4).Info("setting up aho-corasick core")
-	e.ahoCorasickCore = NewAhoCorasickCore(e.detectors)
+	e.ahoCorasickCore = ahocorasick.NewAhoCorasickCore(e.detectors)
 	ctx.Logger().V(4).Info("set up aho-corasick core")
 
 	return nil
@@ -463,7 +464,7 @@ func (e *Engine) detectorWorker(ctx context.Context) {
 
 	// Reuse the same map to avoid allocations.
 	const avgDetectorsPerChunk = 2
-	chunkSpecificDetectors := make(map[DetectorKey]detectors.Detector, avgDetectorsPerChunk)
+	chunkSpecificDetectors := make(map[ahocorasick.DetectorKey]detectors.Detector, avgDetectorsPerChunk)
 	for originalChunk := range e.ChunksChan() {
 		for chunk := range sources.Chunker(originalChunk) {
 			atomic.AddUint64(&e.metrics.BytesScanned, uint64(len(chunk.Data)))