mirror of
https://github.com/go-gitea/gitea.git
synced 2024-11-16 02:18:22 -07:00
ff460ca74d
`enry.IsVendor` is kinda slow as it simply iterates across all regexps. This PR ajdusts the regexps to combine them to make this process a little quicker. Related #15143 Signed-off-by: Andrew Thornton <art27@cantab.net>
114 lines
2.4 KiB
Go
114 lines
2.4 KiB
Go
// Copyright 2020 The Gitea Authors. All rights reserved.
|
|
// Use of this source code is governed by a MIT-style
|
|
// license that can be found in the LICENSE file.
|
|
|
|
// +build gogit
|
|
|
|
package git
|
|
|
|
import (
|
|
"bytes"
|
|
"io"
|
|
"io/ioutil"
|
|
|
|
"code.gitea.io/gitea/modules/analyze"
|
|
|
|
"github.com/go-enry/go-enry/v2"
|
|
"github.com/go-git/go-git/v5"
|
|
"github.com/go-git/go-git/v5/plumbing"
|
|
"github.com/go-git/go-git/v5/plumbing/object"
|
|
)
|
|
|
|
// GetLanguageStats calculates language stats for git repository at specified commit
|
|
func (repo *Repository) GetLanguageStats(commitID string) (map[string]int64, error) {
|
|
r, err := git.PlainOpen(repo.Path)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
rev, err := r.ResolveRevision(plumbing.Revision(commitID))
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
commit, err := r.CommitObject(*rev)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
tree, err := commit.Tree()
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
sizes := make(map[string]int64)
|
|
err = tree.Files().ForEach(func(f *object.File) error {
|
|
if f.Size == 0 || analyze.IsVendor(f.Name) || enry.IsDotFile(f.Name) ||
|
|
enry.IsDocumentation(f.Name) || enry.IsConfiguration(f.Name) {
|
|
return nil
|
|
}
|
|
|
|
// If content can not be read or file is too big just do detection by filename
|
|
var content []byte
|
|
if f.Size <= bigFileSize {
|
|
content, _ = readFile(f, fileSizeLimit)
|
|
}
|
|
if enry.IsGenerated(f.Name, content) {
|
|
return nil
|
|
}
|
|
|
|
// TODO: Use .gitattributes file for linguist overrides
|
|
|
|
language := analyze.GetCodeLanguage(f.Name, content)
|
|
if language == enry.OtherLanguage || language == "" {
|
|
return nil
|
|
}
|
|
|
|
// group languages, such as Pug -> HTML; SCSS -> CSS
|
|
group := enry.GetLanguageGroup(language)
|
|
if group != "" {
|
|
language = group
|
|
}
|
|
|
|
sizes[language] += f.Size
|
|
|
|
return nil
|
|
})
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
// filter special languages unless they are the only language
|
|
if len(sizes) > 1 {
|
|
for language := range sizes {
|
|
langtype := enry.GetLanguageType(language)
|
|
if langtype != enry.Programming && langtype != enry.Markup {
|
|
delete(sizes, language)
|
|
}
|
|
}
|
|
}
|
|
|
|
return sizes, nil
|
|
}
|
|
|
|
func readFile(f *object.File, limit int64) ([]byte, error) {
|
|
r, err := f.Reader()
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
defer r.Close()
|
|
|
|
if limit <= 0 {
|
|
return ioutil.ReadAll(r)
|
|
}
|
|
|
|
size := f.Size
|
|
if limit > 0 && size > limit {
|
|
size = limit
|
|
}
|
|
buf := bytes.NewBuffer(nil)
|
|
buf.Grow(int(size))
|
|
_, err = io.Copy(buf, io.LimitReader(r, limit))
|
|
return buf.Bytes(), err
|
|
}
|