gitea/modules/repository/license.go
yp05327 70b7df0e5e
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>
2024-10-01 15:25:08 -04:00

114 lines
2.8 KiB
Go

// Copyright 2023 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package repository
import (
"bufio"
"bytes"
"fmt"
"regexp"
"strings"
"code.gitea.io/gitea/modules/options"
)
type LicenseValues struct {
Owner string
Email string
Repo string
Year string
}
func GetLicense(name string, values *LicenseValues) ([]byte, error) {
data, err := options.License(name)
if err != nil {
return nil, fmt.Errorf("GetLicense[%s]: %w", name, err)
}
return fillLicensePlaceholder(name, values, data), nil
}
func fillLicensePlaceholder(name string, values *LicenseValues, origin []byte) []byte {
placeholder := getLicensePlaceholder(name)
scanner := bufio.NewScanner(bytes.NewReader(origin))
output := bytes.NewBuffer(nil)
for scanner.Scan() {
line := scanner.Text()
if placeholder.MatchLine == nil || placeholder.MatchLine.MatchString(line) {
for _, v := range placeholder.Owner {
line = strings.ReplaceAll(line, v, values.Owner)
}
for _, v := range placeholder.Email {
line = strings.ReplaceAll(line, v, values.Email)
}
for _, v := range placeholder.Repo {
line = strings.ReplaceAll(line, v, values.Repo)
}
for _, v := range placeholder.Year {
line = strings.ReplaceAll(line, v, values.Year)
}
}
output.WriteString(line + "\n")
}
return output.Bytes()
}
type licensePlaceholder struct {
Owner []string
Email []string
Repo []string
Year []string
MatchLine *regexp.Regexp
}
func getLicensePlaceholder(name string) *licensePlaceholder {
// Some universal placeholders.
// If you want to add a new one, make sure you have check it by `grep -r 'NEW_WORD' options/license` and all of them are placeholders.
ret := &licensePlaceholder{
Owner: []string{
"<name of author>",
"<owner>",
"[NAME]",
"[name of copyright owner]",
"[name of copyright holder]",
"<COPYRIGHT HOLDERS>",
"<copyright holders>",
"<AUTHOR>",
"<author's name or designee>",
"[one or more legally recognised persons or entities offering the Work under the terms and conditions of this Licence]",
},
Email: []string{
"[EMAIL]",
},
Repo: []string{
"<program>",
"<one line to give the program's name and a brief idea of what it does.>",
},
Year: []string{
"<year>",
"[YEAR]",
"{YEAR}",
"[yyyy]",
"[Year]",
"[year]",
},
}
// Some special placeholders for specific licenses.
// It's unsafe to apply them to all licenses.
switch name {
case "0BSD":
return &licensePlaceholder{
Owner: []string{"AUTHOR"},
Email: []string{"EMAIL"},
Year: []string{"YEAR"},
MatchLine: regexp.MustCompile(`Copyright \(C\) YEAR by AUTHOR EMAIL`), // there is another AUTHOR in the file, but it's not a placeholder
}
// Other special placeholders can be added here.
}
return ret
}