feat(hubspot): unify v1 and v2 implementation

pkg/detectors/hubspotapikey/hubspotapikey.go → pkg/detectors/hubspot_apikey/v1/hubspot_apikey_v1.go

@@ -1,11 +1,11 @@
-package hubspotapikey
+package v1
 
 import (
 	"context"
 	"fmt"
 	"io"
 	"net/http"
-	// "log"
+
 	regexp "github.com/wasilibs/go-re2"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
@@ -17,11 +17,13 @@ type Scanner struct {
 	client *http.Client
 }
 
-func (s Scanner) Version() int { return 1 }
-
 // Ensure the Scanner satisfies the interface at compile time.
-var _ detectors.Detector = (*Scanner)(nil)
-var _ detectors.Versioner = (*Scanner)(nil)
+var _ interface {
+	detectors.Detector
+	detectors.Versioner
+} = (*Scanner)(nil)
+
+func (s Scanner) Version() int { return 1 }
 
 var (
 	defaultClient = common.SaneHttpClient()
@@ -32,7 +34,7 @@ var (
 // Keywords are used for efficiently pre-filtering chunks.
 // Use identifiers in the secret preferably, or the provider name.
 func (s Scanner) Keywords() []string {
-	return []string{"hubspot", "hubapi", "hapikey", "hapi_key"}
+	return []string{"hubapi", "hapikey", "hapi_key", "hubspot"}
 }
 
 // FromData will find and optionally verify HubSpotApiKey secrets in a given set of bytes.

pkg/detectors/hubspotapikey/hubspotapikey_test.go → pkg/detectors/hubspot_apikey/v1/hubspot_apikey_v1_integration_test.go

@@ -1,7 +1,7 @@
 //go:build detectors
 // +build detectors
 
-package hubspotapikey
+package v1
 
 import (
 	"context"
@@ -10,6 +10,7 @@ import (
 	"time"
 
 	"github.com/kylelemons/godebug/pretty"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"

pkg/detectors/hubspot_apikey/v1/hubspot_apikey_v1_test.go

@@ -0,0 +1,91 @@
+package v1
+
+import (
+	"context"
+	"testing"
+
+	"github.com/google/go-cmp/cmp"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
+)
+
+func TestHubspotV1_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
+	tests := []struct {
+		name  string
+		input string
+		want  []string
+	}{
+		{
+			name: "hapikey",
+			input: `// const hapikey = 'b714cac4-a45c-42af-9905-da4de8838d75';
+const { HAPI_KEY } = process.env;
+const hs = new HubSpotAPI({ hapikey: HAPI_KEY });`,
+			want: []string{"b714cac4-a45c-42af-9905-da4de8838d75"},
+		},
+		// TODO: Doesn't work because it's more than 40 characters.
+		//	{
+		//		name: "hubapi",
+		//		input: `curl https://api.hubapi.com/contacts/v1/lists/all/contacts/all \
+		//--header "Authorization: Bearer b71aa2ed-9c76-417d-bd8e-c5f4980d21ef"`,
+		//		want: []string{"b71aa2ed-9c76-417d-bd8e-c5f4980d21ef"},
+		//	},
+		{
+			name: "hubspot_1",
+			input: `const hs = new HubSpotAPI("76a836c8-469d-4426-8a3b-194ca930b7a1");
+
+const blogPosts = hs.blog.getPosts({ name: 'Inbound' });`,
+			want: []string{"76a836c8-469d-4426-8a3b-194ca930b7a1"},
+		},
+		{
+			name: "hubspot_2",
+			input: `	'hubspot' => [
+	       // 'api_key' => 'e9ff285d-6b7f-455a-a56d-9ec8c4abbd47',         // @ts dev`,
+			want: []string{"e9ff285d-6b7f-455a-a56d-9ec8c4abbd47"},
+		},
+	}
+
+	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
+			}
+
+			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/hubspot_apikey/v2/hubspot_apikey_v2.go

@@ -0,0 +1,106 @@
+package v2
+
+import (
+	"context"
+	"fmt"
+	"io"
+	"net/http"
+
+	regexp "github.com/wasilibs/go-re2"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+type Scanner struct {
+	client *http.Client
+}
+
+func (s Scanner) Version() int { return 2 }
+
+// Ensure the Scanner satisfies the interface at compile time.
+var _ interface {
+	detectors.Detector
+	detectors.Versioner
+} = (*Scanner)(nil)
+
+var (
+	defaultClient = common.SaneHttpClient()
+
+	keyPat = regexp.MustCompile(`\b(pat-(?:eu|na)1-[A-Za-z0-9]{8}\-[A-Za-z0-9]{4}\-[A-Za-z0-9]{4}\-[A-Za-z0-9]{4}\-[A-Za-z0-9]{12})\b`)
+)
+
+// Keywords are used for efficiently pre-filtering chunks.
+// Use identifiers in the secret preferably, or the provider name.
+func (s Scanner) Keywords() []string {
+	return []string{"pat-na1-", "pat-eu1-"}
+}
+
+// FromData will find and optionally verify HubSpotApiKey secrets in a given set of bytes.
+func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
+	dataStr := string(data)
+
+	uniqueMatches := make(map[string]struct{})
+	for _, match := range keyPat.FindAllStringSubmatch(dataStr, -1) {
+		uniqueMatches[match[1]] = struct{}{}
+	}
+
+	for token := range uniqueMatches {
+		s1 := detectors.Result{
+			DetectorType: detectorspb.DetectorType_HubSpotApiKey,
+			Raw:          []byte(token),
+			Redacted:     token[8:] + "...",
+		}
+
+		if verify {
+			client := s.client
+			if client == nil {
+				client = defaultClient
+			}
+
+			verified, verificationErr := verifyToken(ctx, client, token)
+			s1.Verified = verified
+			s1.SetVerificationError(verificationErr)
+		}
+
+		results = append(results, s1)
+	}
+
+	return results, nil
+}
+func verifyToken(ctx context.Context, client *http.Client, token string) (bool, error) {
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, "https://api.hubapi.com/account-info/v3/api-usage/daily/private-apps", nil)
+	if err != nil {
+		return false, err
+	}
+	req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", token))
+	res, err := client.Do(req)
+	if err != nil {
+		return false, err
+	}
+	defer func() {
+		_, _ = io.Copy(io.Discard, res.Body)
+		_ = res.Body.Close()
+	}()
+
+	switch res.StatusCode {
+	case http.StatusOK:
+		return true, nil
+	case http.StatusUnauthorized:
+		return false, nil
+	case http.StatusForbidden:
+		// The token is valid but lacks permission for the endpoint.
+		return true, nil
+	default:
+		return false, fmt.Errorf("unexpected HTTP response status %d", res.StatusCode)
+	}
+}
+
+func (s Scanner) Type() detectorspb.DetectorType {
+	return detectorspb.DetectorType_HubSpotApiKey
+}
+
+func (s Scanner) Description() string {
+	return "HubSpot is a CRM platform that provides tools for marketing, sales, and customer service. HubSpot API keys can be used to access and modify data within the HubSpot platform."
+}

pkg/detectors/hubspotapikeyv2/hubspotapikeyv2_test.go → pkg/detectors/hubspot_apikey/v2/hubspot_apikey_v2_integration_test.go

@@ -1,7 +1,7 @@
 //go:build detectors
 // +build detectors
 
-package hubspotapikeyv2
+package v2
 
 import (
 	"context"
@@ -10,6 +10,7 @@ import (
 	"time"
 
 	"github.com/kylelemons/godebug/pretty"
+
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"

pkg/detectors/hubspot_apikey/v2/hubspot_apikey_v2_test.go

@@ -0,0 +1,82 @@
+package v2
+
+import (
+	"context"
+	"testing"
+
+	"github.com/google/go-cmp/cmp"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
+)
+
+func TestHubspotV2_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
+	tests := []struct {
+		name  string
+		input string
+		want  []string
+	}{
+		{
+			name: "eu key",
+			input: `
+const private_app_token = 'pat-eu1-1457aed5-04c6-40e2-83ad-a862d3cf19f2';
+
+app.get('/homepage', async (req, res) => {
+    const contactsEndpoint = 'https://api.hubspot.com/crm/v3/objects/contacts';`,
+			want: []string{"pat-eu1-1457aed5-04c6-40e2-83ad-a862d3cf19f2"},
+		},
+		{
+			name: "na key",
+			input: `hubspot:
+   api:
+      url: https://api.hubapi.com
+      auth-token: pat-na1-ffbb9f50-d96b-4abc-84f1-b986617be1b5
+   subscriptions:`,
+			want: []string{"pat-na1-ffbb9f50-d96b-4abc-84f1-b986617be1b5"},
+		},
+	}
+
+	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
+			}
+
+			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)
+			}
+		})
+	}
+}