Support repo license (#24872)

Close #278
Close #24076

## Solutions:
- Use
[google/licenseclassifier](https://github.com/google/licenseclassifier/)
Test result between
[google/licensecheck](https://github.com/google/licensecheck) and
[go-license-detector](https://github.com/go-enry/go-license-detector):
https://github.com/go-gitea/gitea/pull/24872#issuecomment-1560361167
Test result between
[google/licensecheck](https://github.com/google/licensecheck) and
[google/licenseclassifier](https://github.com/google/licenseclassifier/):
https://github.com/go-gitea/gitea/pull/24872#issuecomment-1576092178
- Generate License Convert Name List to avoid import license templates
with same contents
Gitea automatically get latest license data from[
spdx/license-list-data](https://github.com/spdx/license-list-data).
But unfortunately, some license templates have same contents. #20915
[click here to see the
list](https://github.com/go-gitea/gitea/pull/24872#issuecomment-1584141684)
So we will generate a list of these license templates with same contents
and create a new file to save the result when using `make
generate-license`. (Need to decide the save path)
- Save License info into a new table `repo_license`
Can easily support searching repo by license in the future.

## Screen shot
Single License:

![image](https://github.com/go-gitea/gitea/assets/18380374/41260bd7-0b4c-4038-8592-508706cffa9f)

Multiple Licenses:

![image](https://github.com/go-gitea/gitea/assets/18380374/34ce2f73-7e18-446b-9b96-ecc4fb61bd70)

Triggers:
- [x] Push commit to default branch
- [x] Create repo
- [x] Mirror repo
- [x] When Default Branch is changed, licenses should be updated

Todo:
- [x] Save Licenses info in to DB when there's a change to license file
in the commit
- [x] DB Migration
- [x] A nominal test?
- [x] Select which library to
use(https://github.com/go-gitea/gitea/pull/24872#issuecomment-1560361167)
- [x] API Support
- [x] Add repo license table
- ~Select license in settings if there are several licenses(Not
recommended)~
- License board(later, not in this PR)

![image](https://github.com/go-gitea/gitea/assets/18380374/2c3c3bf8-bcc2-4c6d-8ce0-81d1a9733878)

---------

Co-authored-by: silverwind <me@silverwind.io>
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
Co-authored-by: Denys Konovalov <kontakt@denyskon.de>
Co-authored-by: delvh <dev.lh@web.de>
Co-authored-by: KN4CK3R <admin@oldschoolhack.me>
Co-authored-by: 6543 <6543@obermui.de>
Co-authored-by: 6543 <m.huber@kithara.com>
Co-authored-by: a1012112796 <1012112796@qq.com>
Co-authored-by: techknowlogick <techknowlogick@gitea.com>

build/generate-licenses.go

@@ -1,3 +1,6 @@
+// Copyright 2017 The Gitea Authors. All rights reserved.
+// SPDX-License-Identifier: MIT
+
 //go:build ignore
 
 package main
@@ -5,6 +8,8 @@ package main
 import (
 	"archive/tar"
 	"compress/gzip"
+	"crypto/md5"
+	"encoding/hex"
 	"flag"
 	"fmt"
 	"io"
@@ -15,6 +20,8 @@ import (
 	"path/filepath"
 	"strings"
 
+	"code.gitea.io/gitea/build/license"
+	"code.gitea.io/gitea/modules/json"
 	"code.gitea.io/gitea/modules/util"
 )
 
@@ -77,7 +84,7 @@ func main() {
 	}
 
 	tr := tar.NewReader(gz)
-
+	aliasesFiles := make(map[string][]string)
 	for {
 		hdr, err := tr.Next()
 
@@ -97,26 +104,73 @@ func main() {
 			continue
 		}
 
-		if strings.HasPrefix(filepath.Base(hdr.Name), "README") {
+		fileBaseName := filepath.Base(hdr.Name)
+		licenseName := strings.TrimSuffix(fileBaseName, ".txt")
+
+		if strings.HasPrefix(fileBaseName, "README") {
 			continue
 		}
 
-		if strings.HasPrefix(filepath.Base(hdr.Name), "deprecated_") {
+		if strings.HasPrefix(fileBaseName, "deprecated_") {
 			continue
 		}
-		out, err := os.Create(path.Join(destination, strings.TrimSuffix(filepath.Base(hdr.Name), ".txt")))
+		out, err := os.Create(path.Join(destination, licenseName))
 		if err != nil {
 			log.Fatalf("Failed to create new file. %s", err)
 		}
 
 		defer out.Close()
 
-		if _, err := io.Copy(out, tr); err != nil {
+		// some license files have same content, so we need to detect these files and create a convert map into a json file
+		// Later we use this convert map to avoid adding same license content with different license name
+		h := md5.New()
+		// calculate md5 and write file in the same time
+		r := io.TeeReader(tr, h)
+		if _, err := io.Copy(out, r); err != nil {
 			log.Fatalf("Failed to write new file. %s", err)
 		} else {
 			fmt.Printf("Written %s\n", out.Name())
+
+			md5 := hex.EncodeToString(h.Sum(nil))
+			aliasesFiles[md5] = append(aliasesFiles[md5], licenseName)
 		}
 	}
 
+	// generate convert license name map
+	licenseAliases := make(map[string]string)
+	for _, fileNames := range aliasesFiles {
+		if len(fileNames) > 1 {
+			licenseName := license.GetLicenseNameFromAliases(fileNames)
+			if licenseName == "" {
+				// license name should not be empty as expected
+				// if it is empty, we need to rewrite the logic of GetLicenseNameFromAliases
+				log.Fatalf("GetLicenseNameFromAliases: license name is empty")
+			}
+			for _, fileName := range fileNames {
+				licenseAliases[fileName] = licenseName
+			}
+		}
+	}
+	// save convert license name map to file
+	b, err := json.Marshal(licenseAliases)
+	if err != nil {
+		log.Fatalf("Failed to create json bytes. %s", err)
+	}
+
+	licenseAliasesDestination := filepath.Join(destination, "etc", "license-aliases.json")
+	if err := os.MkdirAll(filepath.Dir(licenseAliasesDestination), 0o755); err != nil {
+		log.Fatalf("Failed to create directory for license aliases json file. %s", err)
+	}
+
+	f, err := os.Create(licenseAliasesDestination)
+	if err != nil {
+		log.Fatalf("Failed to create license aliases json file. %s", err)
+	}
+	defer f.Close()
+
+	if _, err = f.Write(b); err != nil {
+		log.Fatalf("Failed to write license aliases json file. %s", err)
+	}
+
 	fmt.Println("Done")
 }

build/license/aliasgenerator.go

@@ -0,0 +1,41 @@
+// Copyright 2024 The Gitea Authors. All rights reserved.
+// SPDX-License-Identifier: MIT
+
+package license
+
+import "strings"
+
+func GetLicenseNameFromAliases(fnl []string) string {
+	if len(fnl) == 0 {
+		return ""
+	}
+
+	shortestItem := func(list []string) string {
+		s := list[0]
+		for _, l := range list[1:] {
+			if len(l) < len(s) {
+				s = l
+			}
+		}
+		return s
+	}
+	allHasPrefix := func(list []string, s string) bool {
+		for _, l := range list {
+			if !strings.HasPrefix(l, s) {
+				return false
+			}
+		}
+		return true
+	}
+
+	sl := shortestItem(fnl)
+	slv := strings.Split(sl, "-")
+	var result string
+	for i := len(slv); i >= 0; i-- {
+		result = strings.Join(slv[:i], "-")
+		if allHasPrefix(fnl, result) {
+			return result
+		}
+	}
+	return ""
+}

build/license/aliasgenerator_test.go

@@ -0,0 +1,39 @@
+// Copyright 2024 The Gitea Authors. All rights reserved.
+// SPDX-License-Identifier: MIT
+
+package license
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestGetLicenseNameFromAliases(t *testing.T) {
+	tests := []struct {
+		target string
+		inputs []string
+	}{
+		{
+			// real case which you can find in license-aliases.json
+			target: "AGPL-1.0",
+			inputs: []string{
+				"AGPL-1.0-only",
+				"AGPL-1.0-or-late",
+			},
+		},
+		{
+			target: "",
+			inputs: []string{
+				"APSL-1.0",
+				"AGPL-1.0-only",
+				"AGPL-1.0-or-late",
+			},
+		},
+	}
+
+	for _, tt := range tests {
+		result := GetLicenseNameFromAliases(tt.inputs)
+		assert.Equal(t, result, tt.target)
+	}
+}

go.mod

@@ -68,6 +68,7 @@ require (
 	github.com/gogs/go-gogs-client v0.0.0-20210131175652-1d7215cd8d85
 	github.com/golang-jwt/jwt/v5 v5.2.1
 	github.com/google/go-github/v61 v61.0.0
+	github.com/google/licenseclassifier/v2 v2.0.0
 	github.com/google/pprof v0.0.0-20240618054019-d3b898a103f8
 	github.com/google/uuid v1.6.0
 	github.com/gorilla/feeds v1.2.0

go.sum

@@ -441,6 +441,8 @@ github.com/google/go-tpm v0.9.0/go.mod h1:FkNVkc6C+IsvDI9Jw1OveJmxGZUUaKxtrpOS47
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
 github.com/google/gofuzz v1.2.0 h1:xRy4A+RhZaiKjJ1bPfwQ8sedCA+YS2YcCHW6ec7JMi0=
 github.com/google/gofuzz v1.2.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
+github.com/google/licenseclassifier/v2 v2.0.0 h1:1Y57HHILNf4m0ABuMVb6xk4vAJYEUO0gDxNpog0pyeA=
+github.com/google/licenseclassifier/v2 v2.0.0/go.mod h1:cOjbdH0kyC9R22sdQbYsFkto4NGCAc+ZSwbeThazEtM=
 github.com/google/pprof v0.0.0-20240227163752-401108e1b7e7/go.mod h1:czg5+yv1E0ZGTi6S6vVK1mke0fV+FaUhNGcd6VRS9Ik=
 github.com/google/pprof v0.0.0-20240618054019-d3b898a103f8 h1:ASJ/LAqdCHOyMYI+dwNxn7Rd8FscNkMyTr1KZU1JI/M=
 github.com/google/pprof v0.0.0-20240618054019-d3b898a103f8/go.mod h1:K1liHPHnj73Fdn/EKuT8nrFqBihUSKXoLYU0BuatOYo=
@@ -735,6 +737,7 @@ github.com/sassoftware/go-rpmutils v0.4.0/go.mod h1:3goNWi7PGAT3/dlql2lv3+MSN5jN
 github.com/segmentio/asm v1.2.0 h1:9BQrFxC+YOHJlTlHGkTrFWf59nbL3XnCoFLTwDCI7ys=
 github.com/segmentio/asm v1.2.0/go.mod h1:BqMnlJP91P8d+4ibuonYZw9mfnzI9HfxselHZr5aAcs=
 github.com/serenize/snaker v0.0.0-20171204205717-a683aaf2d516/go.mod h1:Yow6lPLSAXx2ifx470yD/nUe22Dv5vBvxK/UK9UUTVs=
+github.com/sergi/go-diff v1.1.0/go.mod h1:STckp+ISIX8hZLjrqAeVduY0gWCT9IjLuqbuNXdaHfM=
 github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3 h1:n661drycOFuPLCN3Uc8sB6B/s6Z4t2xvBgU1htSHuq8=
 github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3/go.mod h1:A0bzQcvG0E7Rwjx0REVgAGH58e96+X0MeOfepqsbeW4=
 github.com/shopspring/decimal v1.2.0/go.mod h1:DKyhrW/HYNuLGql+MJL6WCR6knT2jwCFRcu2hWCYk4o=

models/fixtures/repo_license.yml

@@ -0,0 +1 @@
+[] # empty

models/fixtures/repository.yml

@@ -26,7 +26,7 @@
   fork_id: 0
   is_template: false
   template_id: 0
-  size: 7597
+  size: 8478
   is_fsck_enabled: true
   close_issues_via_commit_in_any_branch: false
 

models/migrations/migrations.go

@@ -500,7 +500,7 @@ var migrations = []Migration{
 	// v259 -> v260
 	NewMigration("Convert scoped access tokens", v1_20.ConvertScopedAccessTokens),
 
-	// Gitea 1.20.0 ends at 260
+	// Gitea 1.20.0 ends at v260
 
 	// v260 -> v261
 	NewMigration("Drop custom_labels column of action_runner table", v1_21.DropCustomLabelsColumnOfActionRunner),
@@ -601,6 +601,8 @@ var migrations = []Migration{
 	NewMigration("Add metadata column for comment table", v1_23.AddCommentMetaDataColumn),
 	// v304 -> v305
 	NewMigration("Add index for release sha1", v1_23.AddIndexForReleaseSha1),
+	// v305 -> v306
+	NewMigration("Add Repository Licenses", v1_23.AddRepositoryLicenses),
 }
 
 // GetCurrentDBVersion returns the current db version

models/migrations/v1_23/v305.go

@@ -0,0 +1,23 @@
+// Copyright 2024 The Gitea Authors. All rights reserved.
+// SPDX-License-Identifier: MIT
+
+package v1_23 //nolint
+
+import (
+	"code.gitea.io/gitea/modules/timeutil"
+
+	"xorm.io/xorm"
+)
+
+func AddRepositoryLicenses(x *xorm.Engine) error {
+	type RepoLicense struct {
+		ID          int64 `xorm:"pk autoincr"`
+		RepoID      int64 `xorm:"UNIQUE(s) NOT NULL"`
+		CommitID    string
+		License     string             `xorm:"VARCHAR(255) UNIQUE(s) NOT NULL"`
+		CreatedUnix timeutil.TimeStamp `xorm:"INDEX CREATED"`
+		UpdatedUnix timeutil.TimeStamp `xorm:"INDEX UPDATED"`
+	}
+
+	return x.Sync(new(RepoLicense))
+}

models/repo/license.go

@@ -0,0 +1,120 @@
+// Copyright 2024 The Gitea Authors. All rights reserved.
+// SPDX-License-Identifier: MIT
+
+package repo
+
+import (
+	"context"
+
+	"code.gitea.io/gitea/models/db"
+	"code.gitea.io/gitea/modules/timeutil"
+)
+
+func init() {
+	db.RegisterModel(new(RepoLicense))
+}
+
+type RepoLicense struct { //revive:disable-line:exported
+	ID          int64 `xorm:"pk autoincr"`
+	RepoID      int64 `xorm:"UNIQUE(s) NOT NULL"`
+	CommitID    string
+	License     string             `xorm:"VARCHAR(255) UNIQUE(s) NOT NULL"`
+	CreatedUnix timeutil.TimeStamp `xorm:"INDEX CREATED"`
+	UpdatedUnix timeutil.TimeStamp `xorm:"INDEX UPDATED"`
+}
+
+// RepoLicenseList defines a list of repo licenses
+type RepoLicenseList []*RepoLicense //revive:disable-line:exported
+
+func (rll RepoLicenseList) StringList() []string {
+	var licenses []string
+	for _, rl := range rll {
+		licenses = append(licenses, rl.License)
+	}
+	return licenses
+}
+
+// GetRepoLicenses returns the license statistics for a repository
+func GetRepoLicenses(ctx context.Context, repo *Repository) (RepoLicenseList, error) {
+	licenses := make(RepoLicenseList, 0)
+	if err := db.GetEngine(ctx).Where("`repo_id` = ?", repo.ID).Asc("`license`").Find(&licenses); err != nil {
+		return nil, err
+	}
+	return licenses, nil
+}
+
+// UpdateRepoLicenses updates the license statistics for repository
+func UpdateRepoLicenses(ctx context.Context, repo *Repository, commitID string, licenses []string) error {
+	oldLicenses, err := GetRepoLicenses(ctx, repo)
+	if err != nil {
+		return err
+	}
+	for _, license := range licenses {
+		upd := false
+		for _, o := range oldLicenses {
+			// Update already existing license
+			if o.License == license {
+				if _, err := db.GetEngine(ctx).ID(o.ID).Cols("`commit_id`").Update(o); err != nil {
+					return err
+				}
+				upd = true
+				break
+			}
+		}
+		// Insert new license
+		if !upd {
+			if err := db.Insert(ctx, &RepoLicense{
+				RepoID:   repo.ID,
+				CommitID: commitID,
+				License:  license,
+			}); err != nil {
+				return err
+			}
+		}
+	}
+	// Delete old licenses
+	licenseToDelete := make([]int64, 0, len(oldLicenses))
+	for _, o := range oldLicenses {
+		if o.CommitID != commitID {
+			licenseToDelete = append(licenseToDelete, o.ID)
+		}
+	}
+	if len(licenseToDelete) > 0 {
+		if _, err := db.GetEngine(ctx).In("`id`", licenseToDelete).Delete(&RepoLicense{}); err != nil {
+			return err
+		}
+	}
+
+	return nil
+}
+
+// CopyLicense Copy originalRepo license information to destRepo (use for forked repo)
+func CopyLicense(ctx context.Context, originalRepo, destRepo *Repository) error {
+	repoLicenses, err := GetRepoLicenses(ctx, originalRepo)
+	if err != nil {
+		return err
+	}
+	if len(repoLicenses) > 0 {
+		newRepoLicenses := make(RepoLicenseList, 0, len(repoLicenses))
+
+		for _, rl := range repoLicenses {
+			newRepoLicense := &RepoLicense{
+				RepoID:   destRepo.ID,
+				CommitID: rl.CommitID,
+				License:  rl.License,
+			}
+			newRepoLicenses = append(newRepoLicenses, newRepoLicense)
+		}
+		if err := db.Insert(ctx, &newRepoLicenses); err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+// CleanRepoLicenses will remove all license record of the repo
+func CleanRepoLicenses(ctx context.Context, repo *Repository) error {
+	return db.DeleteBeans(ctx, &RepoLicense{
+		RepoID: repo.ID,
+	})
+}

modules/repository/license.go

@@ -23,7 +23,7 @@ type LicenseValues struct {
 func GetLicense(name string, values *LicenseValues) ([]byte, error) {
 	data, err := options.License(name)
 	if err != nil {
-		return nil, fmt.Errorf("GetRepoInitFile[%s]: %w", name, err)
+		return nil, fmt.Errorf("GetLicense[%s]: %w", name, err)
 	}
 	return fillLicensePlaceholder(name, values, data), nil
 }

modules/structs/repo.go

@@ -114,6 +114,7 @@ type Repository struct {
 	MirrorUpdated time.Time     `json:"mirror_updated,omitempty"`
 	RepoTransfer  *RepoTransfer `json:"repo_transfer"`
 	Topics        []string      `json:"topics"`
+	Licenses      []string      `json:"licenses"`
 }
 
 // CreateRepoOption options when creating repository

options/license/etc/license-aliases.json

@@ -0,0 +1 @@
+{"AGPL-1.0-only":"AGPL-1.0","AGPL-1.0-or-later":"AGPL-1.0","AGPL-3.0-only":"AGPL-3.0","AGPL-3.0-or-later":"AGPL-3.0","CAL-1.0":"CAL-1.0","CAL-1.0-Combined-Work-Exception":"CAL-1.0","GFDL-1.1-invariants-only":"GFDL-1.1","GFDL-1.1-invariants-or-later":"GFDL-1.1","GFDL-1.1-no-invariants-only":"GFDL-1.1","GFDL-1.1-no-invariants-or-later":"GFDL-1.1","GFDL-1.1-only":"GFDL-1.1","GFDL-1.1-or-later":"GFDL-1.1","GFDL-1.2-invariants-only":"GFDL-1.2","GFDL-1.2-invariants-or-later":"GFDL-1.2","GFDL-1.2-no-invariants-only":"GFDL-1.2","GFDL-1.2-no-invariants-or-later":"GFDL-1.2","GFDL-1.2-only":"GFDL-1.2","GFDL-1.2-or-later":"GFDL-1.2","GFDL-1.3-invariants-only":"GFDL-1.3","GFDL-1.3-invariants-or-later":"GFDL-1.3","GFDL-1.3-no-invariants-only":"GFDL-1.3","GFDL-1.3-no-invariants-or-later":"GFDL-1.3","GFDL-1.3-only":"GFDL-1.3","GFDL-1.3-or-later":"GFDL-1.3","GPL-1.0-only":"GPL-1.0","GPL-1.0-or-later":"GPL-1.0","GPL-2.0-only":"GPL-2.0","GPL-2.0-or-later":"GPL-2.0","GPL-3.0-only":"GPL-3.0","GPL-3.0-or-later":"GPL-3.0","LGPL-2.0-only":"LGPL-2.0","LGPL-2.0-or-later":"LGPL-2.0","LGPL-2.1-only":"LGPL-2.1","LGPL-2.1-or-later":"LGPL-2.1","LGPL-3.0-only":"LGPL-3.0","LGPL-3.0-or-later":"LGPL-3.0","MPL-2.0":"MPL-2.0","MPL-2.0-no-copyleft-exception":"MPL-2.0","OFL-1.0":"OFL-1.0","OFL-1.0-RFN":"OFL-1.0","OFL-1.0-no-RFN":"OFL-1.0","OFL-1.1":"OFL-1.1","OFL-1.1-RFN":"OFL-1.1","OFL-1.1-no-RFN":"OFL-1.1"}

options/locale/locale_en-US.ini

@@ -1040,6 +1040,7 @@ issue_labels_helper = Select an issue label set.
 license = License
 license_helper = Select a license file.
 license_helper_desc = A license governs what others can and can't do with your code. Not sure which one is right for your project? See <a target="_blank" rel="noopener noreferrer" href="%s">Choose a license.</a>
+multiple_licenses = Multiple Licenses
 object_format = Object Format
 object_format_helper = Object format of the repository. Cannot be changed later. SHA1 is most compatible.
 readme = README
@@ -2942,6 +2943,7 @@ dashboard.start_schedule_tasks = Start actions schedule tasks
 dashboard.sync_branch.started = Branches Sync started
 dashboard.sync_tag.started = Tags Sync started
 dashboard.rebuild_issue_indexer = Rebuild issue indexer
+dashboard.sync_repo_licenses = Sync repo licenses
 
 users.user_manage_panel = User Account Management
 users.new_account = Create User Account

routers/api/v1/api.go

@@ -1327,6 +1327,7 @@ func Routes() *web.Router {
 				m.Get("/issue_config", context.ReferencesGitRepo(), repo.GetIssueConfig)
 				m.Get("/issue_config/validate", context.ReferencesGitRepo(), repo.ValidateIssueConfig)
 				m.Get("/languages", reqRepoReader(unit.TypeCode), repo.GetLanguages)
+				m.Get("/licenses", reqRepoReader(unit.TypeCode), repo.GetLicenses)
 				m.Get("/activities/feeds", repo.ListRepoActivityFeeds)
 				m.Get("/new_pin_allowed", repo.AreNewIssuePinsAllowed)
 				m.Group("/avatar", func() {

routers/api/v1/repo/license.go

@@ -0,0 +1,51 @@
+// Copyright 2024 The Gitea Authors. All rights reserved.
+// SPDX-License-Identifier: MIT
+
+package repo
+
+import (
+	"net/http"
+
+	repo_model "code.gitea.io/gitea/models/repo"
+	"code.gitea.io/gitea/modules/log"
+	"code.gitea.io/gitea/services/context"
+)
+
+// GetLicenses returns licenses
+func GetLicenses(ctx *context.APIContext) {
+	// swagger:operation GET /repos/{owner}/{repo}/licenses repository repoGetLicenses
+	// ---
+	// summary: Get repo licenses
+	// produces:
+	//   - application/json
+	// parameters:
+	// - name: owner
+	//   in: path
+	//   description: owner of the repo
+	//   type: string
+	//   required: true
+	// - name: repo
+	//   in: path
+	//   description: name of the repo
+	//   type: string
+	//   required: true
+	// responses:
+	//   "404":
+	//     "$ref": "#/responses/notFound"
+	//   "200":
+	//     "$ref": "#/responses/LicensesList"
+
+	licenses, err := repo_model.GetRepoLicenses(ctx, ctx.Repo.Repository)
+	if err != nil {
+		log.Error("GetRepoLicenses failed: %v", err)
+		ctx.InternalServerError(err)
+		return
+	}
+
+	resp := make([]string, len(licenses))
+	for i := range licenses {
+		resp[i] = licenses[i].License
+	}
+
+	ctx.JSON(http.StatusOK, resp)
+}

routers/api/v1/repo/repo.go

@@ -731,6 +731,7 @@ func updateBasicProperties(ctx *context.APIContext, opts api.EditRepoOption) err
 	}
 
 	// Default branch only updated if changed and exist or the repository is empty
+	updateRepoLicense := false
 	if opts.DefaultBranch != nil && repo.DefaultBranch != *opts.DefaultBranch && (repo.IsEmpty || ctx.Repo.GitRepo.IsBranchExist(*opts.DefaultBranch)) {
 		if !repo.IsEmpty {
 			if err := gitrepo.SetDefaultBranch(ctx, ctx.Repo.Repository, *opts.DefaultBranch); err != nil {
@@ -739,6 +740,7 @@ func updateBasicProperties(ctx *context.APIContext, opts api.EditRepoOption) err
 					return err
 				}
 			}
+			updateRepoLicense = true
 		}
 		repo.DefaultBranch = *opts.DefaultBranch
 	}
@@ -748,6 +750,15 @@ func updateBasicProperties(ctx *context.APIContext, opts api.EditRepoOption) err
 		return err
 	}
 
+	if updateRepoLicense {
+		if err := repo_service.AddRepoToLicenseUpdaterQueue(&repo_service.LicenseUpdaterOptions{
+			RepoID: ctx.Repo.Repository.ID,
+		}); err != nil {
+			ctx.Error(http.StatusInternalServerError, "AddRepoToLicenseUpdaterQueue", err)
+			return err
+		}
+	}
+
 	log.Trace("Repository basic settings updated: %s/%s", owner.Name, repo.Name)
 	return nil
 }

routers/api/v1/swagger/repo.go

@@ -359,6 +359,13 @@ type swaggerLanguageStatistics struct {
 	Body map[string]int64 `json:"body"`
 }
 
+// LicensesList
+// swagger:response LicensesList
+type swaggerLicensesList struct {
+	// in: body
+	Body []string `json:"body"`
+}
+
 // CombinedStatus
 // swagger:response CombinedStatus
 type swaggerCombinedStatus struct {

routers/init.go

@@ -172,6 +172,8 @@ func InitWebInstalled(ctx context.Context) {
 
 	actions_service.Init()
 
+	mustInit(repo_service.InitLicenseClassifier)
+
 	// Finally start up the cron
 	cron.NewContext(ctx)
 }

routers/private/default_branch.go

@@ -12,6 +12,7 @@ import (
 	"code.gitea.io/gitea/modules/gitrepo"
 	"code.gitea.io/gitea/modules/private"
 	gitea_context "code.gitea.io/gitea/services/context"
+	repo_service "code.gitea.io/gitea/services/repository"
 )
 
 // SetDefaultBranch updates the default branch
@@ -36,5 +37,15 @@ func SetDefaultBranch(ctx *gitea_context.PrivateContext) {
 		})
 		return
 	}
+
+	if err := repo_service.AddRepoToLicenseUpdaterQueue(&repo_service.LicenseUpdaterOptions{
+		RepoID: ctx.Repo.Repository.ID,
+	}); err != nil {
+		ctx.JSON(http.StatusInternalServerError, private.Response{
+			Err: fmt.Sprintf("Unable to set default branch on repository: %s/%s Error: %v", ownerName, repoName, err),
+		})
+		return
+	}
+
 	ctx.PlainText(http.StatusOK, "success")
 }

routers/private/hook_post_receive.go

@@ -278,10 +278,19 @@ func HookPostReceive(ctx *gitea_context.PrivateContext) {
 
 			branch := refFullName.BranchName()
 
-			// If our branch is the default branch of an unforked repo - there's no PR to create or refer to
-			if !repo.IsFork && branch == baseRepo.DefaultBranch {
-				results = append(results, private.HookPostReceiveBranchResult{})
-				continue
+			if branch == baseRepo.DefaultBranch {
+				if err := repo_service.AddRepoToLicenseUpdaterQueue(&repo_service.LicenseUpdaterOptions{
+					RepoID: repo.ID,
+				}); err != nil {
+					ctx.JSON(http.StatusInternalServerError, private.Response{Err: err.Error()})
+					return
+				}
+
+				// If our branch is the default branch of an unforked repo - there's no PR to create or refer to
+				if !repo.IsFork {
+					results = append(results, private.HookPostReceiveBranchResult{})
+					continue
+				}
 			}
 
 			pr, err := issues_model.GetUnmergedPullRequest(ctx, repo.ID, baseRepo.ID, branch, baseRepo.DefaultBranch, issues_model.PullRequestFlowGithub)

routers/web/repo/branch.go

@@ -89,7 +89,7 @@ func Branches(ctx *context.Context) {
 	pager := context.NewPagination(int(branchesCount), pageSize, page, 5)
 	pager.SetDefaultParams(ctx)
 	ctx.Data["Page"] = pager
-
+	ctx.Data["LicenseFileName"] = repo_service.LicenseFileName
 	ctx.HTML(http.StatusOK, tplBranch)
 }
 

routers/web/repo/commit.go

@@ -29,7 +29,7 @@ import (
 	"code.gitea.io/gitea/modules/util"
 	"code.gitea.io/gitea/services/context"
 	"code.gitea.io/gitea/services/gitdiff"
-	git_service "code.gitea.io/gitea/services/repository"
+	repo_service "code.gitea.io/gitea/services/repository"
 )
 
 const (
@@ -101,7 +101,7 @@ func Commits(ctx *context.Context) {
 	pager := context.NewPagination(int(commitsCount), pageSize, page, 5)
 	pager.SetDefaultParams(ctx)
 	ctx.Data["Page"] = pager
-
+	ctx.Data["LicenseFileName"] = repo_service.LicenseFileName
 	ctx.HTML(http.StatusOK, tplCommits)
 }
 
@@ -218,6 +218,8 @@ func SearchCommits(ctx *context.Context) {
 	}
 	ctx.Data["Username"] = ctx.Repo.Owner.Name
 	ctx.Data["Reponame"] = ctx.Repo.Repository.Name
+	ctx.Data["RefName"] = ctx.Repo.RefName
+	ctx.Data["LicenseFileName"] = repo_service.LicenseFileName
 	ctx.HTML(http.StatusOK, tplCommits)
 }
 
@@ -263,12 +265,12 @@ func FileHistory(ctx *context.Context) {
 	pager := context.NewPagination(int(commitsCount), setting.Git.CommitsRangeSize, page, 5)
 	pager.SetDefaultParams(ctx)
 	ctx.Data["Page"] = pager
-
+	ctx.Data["LicenseFileName"] = repo_service.LicenseFileName
 	ctx.HTML(http.StatusOK, tplCommits)
 }
 
 func LoadBranchesAndTags(ctx *context.Context) {
-	response, err := git_service.LoadBranchesAndTags(ctx, ctx.Repo, ctx.PathParam("sha"))
+	response, err := repo_service.LoadBranchesAndTags(ctx, ctx.Repo, ctx.PathParam("sha"))
 	if err == nil {
 		ctx.JSON(http.StatusOK, response)
 		return

routers/web/repo/release.go

@@ -289,7 +289,6 @@ func releasesOrTagsFeed(ctx *context.Context, isReleasesOnly bool, formatType st
 // SingleRelease renders a single release's page
 func SingleRelease(ctx *context.Context) {
 	ctx.Data["PageIsReleaseList"] = true
-	ctx.Data["DefaultBranch"] = ctx.Repo.Repository.DefaultBranch
 
 	writeAccess := ctx.Repo.CanWrite(unit.TypeReleases)
 	ctx.Data["CanCreateRelease"] = writeAccess && !ctx.Repo.Repository.IsArchived

routers/web/repo/view.go

@@ -51,6 +51,7 @@ import (
 	"code.gitea.io/gitea/routers/web/feed"
 	"code.gitea.io/gitea/services/context"
 	issue_service "code.gitea.io/gitea/services/issue"
+	repo_service "code.gitea.io/gitea/services/repository"
 	files_service "code.gitea.io/gitea/services/repository/files"
 
 	"github.com/nektos/act/pkg/model"
@@ -1077,6 +1078,7 @@ func renderHomeCode(ctx *context.Context) {
 	ctx.Data["TreeLink"] = treeLink
 	ctx.Data["TreeNames"] = treeNames
 	ctx.Data["BranchLink"] = branchLink
+	ctx.Data["LicenseFileName"] = repo_service.LicenseFileName
 	ctx.HTML(http.StatusOK, tplRepoHome)
 }
 

services/context/repo.go

@@ -404,6 +404,13 @@ func repoAssignment(ctx *Context, repo *repo_model.Repository) {
 	ctx.Data["PushMirrors"] = pushMirrors
 	ctx.Data["RepoName"] = ctx.Repo.Repository.Name
 	ctx.Data["IsEmptyRepo"] = ctx.Repo.Repository.IsEmpty
+
+	repoLicenses, err := repo_model.GetRepoLicenses(ctx, ctx.Repo.Repository)
+	if err != nil {
+		ctx.ServerError("GetRepoLicenses", err)
+		return
+	}
+	ctx.Data["DetectedRepoLicenses"] = repoLicenses.StringList()
 }
 
 // RepoAssignment returns a middleware to handle repository assignment

services/convert/repository.go

@@ -175,6 +175,11 @@ func innerToRepo(ctx context.Context, repo *repo_model.Repository, permissionInR
 		language = repo.PrimaryLanguage.Language
 	}
 
+	repoLicenses, err := repo_model.GetRepoLicenses(ctx, repo)
+	if err != nil {
+		return nil
+	}
+
 	repoAPIURL := repo.APIURL()
 
 	return &api.Repository{
@@ -238,6 +243,7 @@ func innerToRepo(ctx context.Context, repo *repo_model.Repository, permissionInR
 		RepoTransfer:                  transfer,
 		Topics:                        repo.Topics,
 		ObjectFormatName:              repo.ObjectFormatName,
+		Licenses:                      repoLicenses.StringList(),
 	}
 }
 

services/cron/tasks_basic.go

@@ -156,6 +156,16 @@ func registerCleanupPackages() {
 	})
 }
 
+func registerSyncRepoLicenses() {
+	RegisterTaskFatal("sync_repo_licenses", &BaseConfig{
+		Enabled:    false,
+		RunAtStart: false,
+		Schedule:   "@annually",
+	}, func(ctx context.Context, _ *user_model.User, config Config) error {
+		return repo_service.SyncRepoLicenses(ctx)
+	})
+}
+
 func initBasicTasks() {
 	if setting.Mirror.Enabled {
 		registerUpdateMirrorTask()
@@ -172,4 +182,5 @@ func initBasicTasks() {
 	if setting.Packages.Enabled {
 		registerCleanupPackages()
 	}
+	registerSyncRepoLicenses()
 }

services/migrations/gitea_uploader_test.go

@@ -26,6 +26,7 @@ import (
 	"code.gitea.io/gitea/modules/optional"
 	"code.gitea.io/gitea/modules/structs"
 	"code.gitea.io/gitea/modules/test"
+	repo_service "code.gitea.io/gitea/services/repository"
 
 	"github.com/stretchr/testify/assert"
 )
@@ -302,6 +303,8 @@ func TestGiteaUploadUpdateGitForPullRequest(t *testing.T) {
 	toRepoName := "migrated"
 	uploader := NewGiteaLocalUploader(context.Background(), fromRepoOwner, fromRepoOwner.Name, toRepoName)
 	uploader.gitServiceType = structs.GiteaService
+
+	assert.NoError(t, repo_service.Init(context.Background()))
 	assert.NoError(t, uploader.CreateRepo(&base.Repository{
 		Description: "description",
 		OriginalURL: fromRepo.RepoPath(),