Support azure git links (#1662)

* Support azure git links.

* update comment.

* update test names.

pkg/giturl/giturl.go

@@ -2,6 +2,7 @@ package giturl
 
 import (
 	"net/url"
+	"strconv"
 	"strings"
 
 	"github.com/pkg/errors"
@@ -13,8 +14,29 @@ const (
 	providerGithub    provider = "Github"
 	providerGitlab    provider = "Gitlab"
 	providerBitbucket provider = "Bitbucket"
+	providerAzure     provider = "Azure"
+
+	urlGithub    = "github.com/"
+	urlGitlab    = "gitlab.com/"
+	urlBitbucket = "bitbucket.org/"
+	urlAzure     = "dev.azure.com/"
 )
 
+func determineProvider(repo string) provider {
+	switch {
+	case strings.Contains(repo, urlGithub):
+		return providerGithub
+	case strings.Contains(repo, urlGitlab):
+		return providerGitlab
+	case strings.Contains(repo, urlBitbucket):
+		return providerBitbucket
+	case strings.Contains(repo, urlAzure):
+		return providerAzure
+	default:
+		return ""
+	}
+}
+
 func NormalizeBitbucketRepo(repoURL string) (string, error) {
 	if !strings.HasPrefix(repoURL, "https") {
 		return "", errors.New("Bitbucket requires https repo urls: e.g. https://bitbucket.org/org/repo.git")
@@ -88,3 +110,35 @@ func NormalizeOrgRepoURL(provider provider, repoURL string) (string, error) {
 	parsed.Path += ".git"
 	return parsed.String(), nil
 }
+
+// GenerateLink crafts a link to the specific file from a commit.
+// Supports GitHub, GitLab, Bitbucket, and Azure Repos.
+// If the provider supports hyperlinks to specific lines, the line number will be included.
+func GenerateLink(repo, commit, file string, line int64) string {
+	switch determineProvider(repo) {
+	case providerBitbucket:
+		return repo[:len(repo)-4] + "/commits/" + commit
+
+	case providerGithub, providerGitlab:
+		var baseLink string
+		if file == "" {
+			baseLink = repo[:len(repo)-4] + "/commit/" + commit
+		} else {
+			baseLink = repo[:len(repo)-4] + "/blob/" + commit + "/" + file
+			if line > 0 {
+				baseLink += "#L" + strconv.FormatInt(line, 10)
+			}
+		}
+		return baseLink
+
+	case providerAzure:
+		baseLink := repo + "?path=" + file + "&version=GB" + commit
+		if line > 0 {
+			baseLink += "&line=" + strconv.FormatInt(line, 10)
+		}
+		return baseLink
+
+	default:
+		return ""
+	}
+}

pkg/giturl/giturl_test.go

@@ -7,6 +7,8 @@ import (
 )
 
 func Test_NormalizeOrgRepoURL(t *testing.T) {
+	t.Parallel()
+
 	tests := map[string]struct {
 		Provider provider
 		Repo     string
@@ -43,6 +45,8 @@ func Test_NormalizeOrgRepoURL(t *testing.T) {
 }
 
 func Test_NormalizeBitbucketRepo(t *testing.T) {
+	t.Parallel()
+
 	tests := map[string]struct {
 		Repo string
 		Out  string
@@ -69,6 +73,8 @@ func Test_NormalizeBitbucketRepo(t *testing.T) {
 }
 
 func Test_NormalizeGitlabRepo(t *testing.T) {
+	t.Parallel()
+
 	tests := map[string]struct {
 		Repo string
 		Out  string
@@ -93,3 +99,73 @@ func Test_NormalizeGitlabRepo(t *testing.T) {
 		}
 	}
 }
+
+func TestGenerateLink(t *testing.T) {
+	t.Parallel()
+
+	type args struct {
+		repo   string
+		commit string
+		file   string
+		line   int64
+	}
+	tests := []struct {
+		name string
+		args args
+		want string
+	}{
+		{
+			name: "github link gen",
+			args: args{
+				repo:   "https://github.com/trufflesec-julian/confluence-go-api.git",
+				commit: "047b4a2ba42fc5b6c0bd535c5307434a666db5ec",
+				file:   ".gitignore",
+			},
+			want: "https://github.com/trufflesec-julian/confluence-go-api/blob/047b4a2ba42fc5b6c0bd535c5307434a666db5ec/.gitignore",
+		},
+		{
+			name: "github link gen with line",
+			args: args{
+				repo:   "https://github.com/trufflesec-julian/confluence-go-api.git",
+				commit: "047b4a2ba42fc5b6c0bd535c5307434a666db5ec",
+				file:   ".gitignore",
+				line:   int64(4),
+			},
+			want: "https://github.com/trufflesec-julian/confluence-go-api/blob/047b4a2ba42fc5b6c0bd535c5307434a666db5ec/.gitignore#L4",
+		},
+		{
+			name: "github link gen - no file",
+			args: args{
+				repo:   "https://github.com/trufflesec-julian/confluence-go-api.git",
+				commit: "047b4a2ba42fc5b6c0bd535c5307434a666db5ec",
+			},
+			want: "https://github.com/trufflesec-julian/confluence-go-api/commit/047b4a2ba42fc5b6c0bd535c5307434a666db5ec",
+		},
+		{
+			name: "Azure link gen",
+			args: args{
+				repo:   "https://dev.azure.com/org/project/_git/repo",
+				commit: "abcdef",
+				file:   "main.go",
+			},
+			want: "https://dev.azure.com/org/project/_git/repo?path=main.go&version=GBabcdef",
+		},
+		{
+			name: "Azure link gen with line",
+			args: args{
+				repo:   "https://dev.azure.com/org/project/_git/repo",
+				commit: "abcdef",
+				file:   "main.go",
+				line:   int64(20),
+			},
+			want: "https://dev.azure.com/org/project/_git/repo?path=main.go&version=GBabcdef&line=20",
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := GenerateLink(tt.args.repo, tt.args.commit, tt.args.file, tt.args.line); got != tt.want {
+				t.Errorf("generateLink() = %v, want %v", got, tt.want)
+			}
+		})
+	}
+}

pkg/sources/git/git.go

@@ -9,7 +9,6 @@ import (
 	"os/exec"
 	"path/filepath"
 	"runtime"
-	"strconv"
 	"strings"
 	"sync/atomic"
 	"time"
@@ -693,28 +692,6 @@ func normalizeConfig(scanOptions *ScanOptions, repo *git.Repository) (err error)
 	return nil
 }
 
-// GenerateLink crafts a link to the specific file from a commit. This works in most major git providers (Github/Gitlab)
-func GenerateLink(repo, commit, file string, line int64) string {
-	// bitbucket links are commits not commit...
-	if strings.Contains(repo, "bitbucket.org/") {
-		return repo[:len(repo)-4] + "/commits/" + commit
-	}
-	var link string
-	if file == "" {
-		link = repo[:len(repo)-4] + "/commit/" + commit
-	} else {
-		link = repo[:len(repo)-4] + "/blob/" + commit + "/" + file
-
-		// Both GitHub and Gitlab support hyperlinking to a specific line with #L<number>, e.g.:
-		// https://github.com/trufflesecurity/trufflehog/blob/e856a6890d0da5a218f4f9283500b80043884641/go.mod#L169
-		// https://gitlab.com/pdftk-java/pdftk/-/blob/88559a08f34175b6fae76c40a88f0377f64a12d7/java/com/gitlab/pdftk_java/report.java#L893
-		if line > 0 && (strings.Contains(repo, "github") || strings.Contains(repo, "gitlab")) {
-			link += "#L" + strconv.FormatInt(line, 10)
-		}
-	}
-	return link
-}
-
 func stripPassword(u string) (string, error) {
 	if strings.HasPrefix(u, "git@") {
 		return u, nil

pkg/sources/git/git_test.go

@@ -151,55 +151,6 @@ func TestSource_Scan(t *testing.T) {
 	}
 }
 
-func Test_generateLink(t *testing.T) {
-	type args struct {
-		repo   string
-		commit string
-		file   string
-		line   int64
-	}
-	tests := []struct {
-		name string
-		args args
-		want string
-	}{
-		{
-			name: "test link gen",
-			args: args{
-				repo:   "https://github.com/trufflesec-julian/confluence-go-api.git",
-				commit: "047b4a2ba42fc5b6c0bd535c5307434a666db5ec",
-				file:   ".gitignore",
-			},
-			want: "https://github.com/trufflesec-julian/confluence-go-api/blob/047b4a2ba42fc5b6c0bd535c5307434a666db5ec/.gitignore",
-		},
-		{
-			name: "test link gen",
-			args: args{
-				repo:   "https://github.com/trufflesec-julian/confluence-go-api.git",
-				commit: "047b4a2ba42fc5b6c0bd535c5307434a666db5ec",
-				file:   ".gitignore",
-				line:   int64(4),
-			},
-			want: "https://github.com/trufflesec-julian/confluence-go-api/blob/047b4a2ba42fc5b6c0bd535c5307434a666db5ec/.gitignore#L4",
-		},
-		{
-			name: "test link gen - no file",
-			args: args{
-				repo:   "https://github.com/trufflesec-julian/confluence-go-api.git",
-				commit: "047b4a2ba42fc5b6c0bd535c5307434a666db5ec",
-			},
-			want: "https://github.com/trufflesec-julian/confluence-go-api/commit/047b4a2ba42fc5b6c0bd535c5307434a666db5ec",
-		},
-	}
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			if got := GenerateLink(tt.args.repo, tt.args.commit, tt.args.file, tt.args.line); got != tt.want {
-				t.Errorf("generateLink() = %v, want %v", got, tt.want)
-			}
-		})
-	}
-}
-
 // We ran into an issue where upgrading a dependency caused the git patch chunking to break
 // So this test exists to make sure that when something changes, we know about it.
 func TestSource_Chunks_Integration(t *testing.T) {

pkg/sources/github/github.go

@@ -29,6 +29,7 @@ import (
 	"github.com/trufflesecurity/trufflehog/v3/pkg/cache/memory"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/context"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/giturl"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/credentialspb"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/source_metadatapb"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/sourcespb"
@@ -261,7 +262,7 @@ func (s *Source) Init(aCtx context.Context, name string, jobID, sourceID int64,
 						File:       sanitizer.UTF8(file),
 						Email:      sanitizer.UTF8(email),
 						Repository: sanitizer.UTF8(repository),
-						Link:       git.GenerateLink(repository, commit, file, line),
+						Link:       giturl.GenerateLink(repository, commit, file, line),
 						Timestamp:  sanitizer.UTF8(timestamp),
 						Line:       line,
 						Visibility: s.visibilityOf(aCtx, repository),

pkg/sources/gitlab/gitlab.go

@@ -127,7 +127,7 @@ func (s *Source) Init(_ context.Context, name string, jobId, sourceId int64, ver
 						File:       sanitizer.UTF8(file),
 						Email:      sanitizer.UTF8(email),
 						Repository: sanitizer.UTF8(repository),
-						Link:       git.GenerateLink(repository, commit, file, line),
+						Link:       giturl.GenerateLink(repository, commit, file, line),
 						Timestamp:  sanitizer.UTF8(timestamp),
 						Line:       line,
 					},