This repository has been archived on 2024-01-04. You can view files and clone it, but cannot push or open issues or pull requests.
forgejo/modules/git/repo_language_stats_gogit.go

196 lines
4.6 KiB
Go
Raw Normal View History

Use native git variants by default with go-git variants as build tag (#13673) * Move last commit cache back into modules/git Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove go-git from the interface for last commit cache Signed-off-by: Andrew Thornton <art27@cantab.net> * move cacheref to last_commit_cache Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove go-git from routers/private/hook Signed-off-by: Andrew Thornton <art27@cantab.net> * Move FindLFSFiles to pipeline Signed-off-by: Andrew Thornton <art27@cantab.net> * Make no-go-git variants Signed-off-by: Andrew Thornton <art27@cantab.net> * Submodule RefID Signed-off-by: Andrew Thornton <art27@cantab.net> * fix issue with GetCommitsInfo Signed-off-by: Andrew Thornton <art27@cantab.net> * fix GetLastCommitForPaths Signed-off-by: Andrew Thornton <art27@cantab.net> * Improve efficiency Signed-off-by: Andrew Thornton <art27@cantab.net> * More efficiency Signed-off-by: Andrew Thornton <art27@cantab.net> * even faster Signed-off-by: Andrew Thornton <art27@cantab.net> * Reduce duplication * As per @lunny Signed-off-by: Andrew Thornton <art27@cantab.net> * attempt to fix drone Signed-off-by: Andrew Thornton <art27@cantab.net> * fix test-tags Signed-off-by: Andrew Thornton <art27@cantab.net> * default to use no-go-git variants and add gogit build tag Signed-off-by: Andrew Thornton <art27@cantab.net> * placate lint Signed-off-by: Andrew Thornton <art27@cantab.net> * as per @6543 Signed-off-by: Andrew Thornton <art27@cantab.net> Co-authored-by: 6543 <6543@obermui.de> Co-authored-by: techknowlogick <techknowlogick@gitea.io>
2020-12-17 14:00:47 +00:00
// 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.
//go:build gogit
Use native git variants by default with go-git variants as build tag (#13673) * Move last commit cache back into modules/git Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove go-git from the interface for last commit cache Signed-off-by: Andrew Thornton <art27@cantab.net> * move cacheref to last_commit_cache Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove go-git from routers/private/hook Signed-off-by: Andrew Thornton <art27@cantab.net> * Move FindLFSFiles to pipeline Signed-off-by: Andrew Thornton <art27@cantab.net> * Make no-go-git variants Signed-off-by: Andrew Thornton <art27@cantab.net> * Submodule RefID Signed-off-by: Andrew Thornton <art27@cantab.net> * fix issue with GetCommitsInfo Signed-off-by: Andrew Thornton <art27@cantab.net> * fix GetLastCommitForPaths Signed-off-by: Andrew Thornton <art27@cantab.net> * Improve efficiency Signed-off-by: Andrew Thornton <art27@cantab.net> * More efficiency Signed-off-by: Andrew Thornton <art27@cantab.net> * even faster Signed-off-by: Andrew Thornton <art27@cantab.net> * Reduce duplication * As per @lunny Signed-off-by: Andrew Thornton <art27@cantab.net> * attempt to fix drone Signed-off-by: Andrew Thornton <art27@cantab.net> * fix test-tags Signed-off-by: Andrew Thornton <art27@cantab.net> * default to use no-go-git variants and add gogit build tag Signed-off-by: Andrew Thornton <art27@cantab.net> * placate lint Signed-off-by: Andrew Thornton <art27@cantab.net> * as per @6543 Signed-off-by: Andrew Thornton <art27@cantab.net> Co-authored-by: 6543 <6543@obermui.de> Co-authored-by: techknowlogick <techknowlogick@gitea.io>
2020-12-17 14:00:47 +00:00
// +build gogit
package git
import (
"bytes"
"context"
Use native git variants by default with go-git variants as build tag (#13673) * Move last commit cache back into modules/git Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove go-git from the interface for last commit cache Signed-off-by: Andrew Thornton <art27@cantab.net> * move cacheref to last_commit_cache Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove go-git from routers/private/hook Signed-off-by: Andrew Thornton <art27@cantab.net> * Move FindLFSFiles to pipeline Signed-off-by: Andrew Thornton <art27@cantab.net> * Make no-go-git variants Signed-off-by: Andrew Thornton <art27@cantab.net> * Submodule RefID Signed-off-by: Andrew Thornton <art27@cantab.net> * fix issue with GetCommitsInfo Signed-off-by: Andrew Thornton <art27@cantab.net> * fix GetLastCommitForPaths Signed-off-by: Andrew Thornton <art27@cantab.net> * Improve efficiency Signed-off-by: Andrew Thornton <art27@cantab.net> * More efficiency Signed-off-by: Andrew Thornton <art27@cantab.net> * even faster Signed-off-by: Andrew Thornton <art27@cantab.net> * Reduce duplication * As per @lunny Signed-off-by: Andrew Thornton <art27@cantab.net> * attempt to fix drone Signed-off-by: Andrew Thornton <art27@cantab.net> * fix test-tags Signed-off-by: Andrew Thornton <art27@cantab.net> * default to use no-go-git variants and add gogit build tag Signed-off-by: Andrew Thornton <art27@cantab.net> * placate lint Signed-off-by: Andrew Thornton <art27@cantab.net> * as per @6543 Signed-off-by: Andrew Thornton <art27@cantab.net> Co-authored-by: 6543 <6543@obermui.de> Co-authored-by: techknowlogick <techknowlogick@gitea.io>
2020-12-17 14:00:47 +00:00
"io"
"strings"
Use native git variants by default with go-git variants as build tag (#13673) * Move last commit cache back into modules/git Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove go-git from the interface for last commit cache Signed-off-by: Andrew Thornton <art27@cantab.net> * move cacheref to last_commit_cache Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove go-git from routers/private/hook Signed-off-by: Andrew Thornton <art27@cantab.net> * Move FindLFSFiles to pipeline Signed-off-by: Andrew Thornton <art27@cantab.net> * Make no-go-git variants Signed-off-by: Andrew Thornton <art27@cantab.net> * Submodule RefID Signed-off-by: Andrew Thornton <art27@cantab.net> * fix issue with GetCommitsInfo Signed-off-by: Andrew Thornton <art27@cantab.net> * fix GetLastCommitForPaths Signed-off-by: Andrew Thornton <art27@cantab.net> * Improve efficiency Signed-off-by: Andrew Thornton <art27@cantab.net> * More efficiency Signed-off-by: Andrew Thornton <art27@cantab.net> * even faster Signed-off-by: Andrew Thornton <art27@cantab.net> * Reduce duplication * As per @lunny Signed-off-by: Andrew Thornton <art27@cantab.net> * attempt to fix drone Signed-off-by: Andrew Thornton <art27@cantab.net> * fix test-tags Signed-off-by: Andrew Thornton <art27@cantab.net> * default to use no-go-git variants and add gogit build tag Signed-off-by: Andrew Thornton <art27@cantab.net> * placate lint Signed-off-by: Andrew Thornton <art27@cantab.net> * as per @6543 Signed-off-by: Andrew Thornton <art27@cantab.net> Co-authored-by: 6543 <6543@obermui.de> Co-authored-by: techknowlogick <techknowlogick@gitea.io>
2020-12-17 14:00:47 +00:00
"code.gitea.io/gitea/modules/analyze"
"code.gitea.io/gitea/modules/log"
Use native git variants by default with go-git variants as build tag (#13673) * Move last commit cache back into modules/git Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove go-git from the interface for last commit cache Signed-off-by: Andrew Thornton <art27@cantab.net> * move cacheref to last_commit_cache Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove go-git from routers/private/hook Signed-off-by: Andrew Thornton <art27@cantab.net> * Move FindLFSFiles to pipeline Signed-off-by: Andrew Thornton <art27@cantab.net> * Make no-go-git variants Signed-off-by: Andrew Thornton <art27@cantab.net> * Submodule RefID Signed-off-by: Andrew Thornton <art27@cantab.net> * fix issue with GetCommitsInfo Signed-off-by: Andrew Thornton <art27@cantab.net> * fix GetLastCommitForPaths Signed-off-by: Andrew Thornton <art27@cantab.net> * Improve efficiency Signed-off-by: Andrew Thornton <art27@cantab.net> * More efficiency Signed-off-by: Andrew Thornton <art27@cantab.net> * even faster Signed-off-by: Andrew Thornton <art27@cantab.net> * Reduce duplication * As per @lunny Signed-off-by: Andrew Thornton <art27@cantab.net> * attempt to fix drone Signed-off-by: Andrew Thornton <art27@cantab.net> * fix test-tags Signed-off-by: Andrew Thornton <art27@cantab.net> * default to use no-go-git variants and add gogit build tag Signed-off-by: Andrew Thornton <art27@cantab.net> * placate lint Signed-off-by: Andrew Thornton <art27@cantab.net> * as per @6543 Signed-off-by: Andrew Thornton <art27@cantab.net> Co-authored-by: 6543 <6543@obermui.de> Co-authored-by: techknowlogick <techknowlogick@gitea.io>
2020-12-17 14:00:47 +00:00
"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
}
var checker *CheckAttributeReader
if CheckGitVersionAtLeast("1.7.8") == nil {
indexFilename, workTree, deleteTemporaryFile, err := repo.ReadTreeToTemporaryIndex(commitID)
if err == nil {
defer deleteTemporaryFile()
checker = &CheckAttributeReader{
Attributes: []string{"linguist-vendored", "linguist-generated", "linguist-language", "gitlab-language"},
Repo: repo,
IndexFile: indexFilename,
WorkTree: workTree,
}
ctx, cancel := context.WithCancel(DefaultContext)
if err := checker.Init(ctx); err != nil {
log.Error("Unable to open checker for %s. Error: %v", commitID, err)
} else {
go func() {
err = checker.Run()
if err != nil {
log.Error("Unable to open checker for %s. Error: %v", commitID, err)
cancel()
}
}()
}
defer cancel()
}
}
Use native git variants by default with go-git variants as build tag (#13673) * Move last commit cache back into modules/git Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove go-git from the interface for last commit cache Signed-off-by: Andrew Thornton <art27@cantab.net> * move cacheref to last_commit_cache Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove go-git from routers/private/hook Signed-off-by: Andrew Thornton <art27@cantab.net> * Move FindLFSFiles to pipeline Signed-off-by: Andrew Thornton <art27@cantab.net> * Make no-go-git variants Signed-off-by: Andrew Thornton <art27@cantab.net> * Submodule RefID Signed-off-by: Andrew Thornton <art27@cantab.net> * fix issue with GetCommitsInfo Signed-off-by: Andrew Thornton <art27@cantab.net> * fix GetLastCommitForPaths Signed-off-by: Andrew Thornton <art27@cantab.net> * Improve efficiency Signed-off-by: Andrew Thornton <art27@cantab.net> * More efficiency Signed-off-by: Andrew Thornton <art27@cantab.net> * even faster Signed-off-by: Andrew Thornton <art27@cantab.net> * Reduce duplication * As per @lunny Signed-off-by: Andrew Thornton <art27@cantab.net> * attempt to fix drone Signed-off-by: Andrew Thornton <art27@cantab.net> * fix test-tags Signed-off-by: Andrew Thornton <art27@cantab.net> * default to use no-go-git variants and add gogit build tag Signed-off-by: Andrew Thornton <art27@cantab.net> * placate lint Signed-off-by: Andrew Thornton <art27@cantab.net> * as per @6543 Signed-off-by: Andrew Thornton <art27@cantab.net> Co-authored-by: 6543 <6543@obermui.de> Co-authored-by: techknowlogick <techknowlogick@gitea.io>
2020-12-17 14:00:47 +00:00
sizes := make(map[string]int64)
err = tree.Files().ForEach(func(f *object.File) error {
if f.Size == 0 {
return nil
}
notVendored := false
notGenerated := false
if checker != nil {
attrs, err := checker.CheckPath(f.Name)
if err == nil {
if vendored, has := attrs["linguist-vendored"]; has {
if vendored == "set" || vendored == "true" {
return nil
}
notVendored = vendored == "false"
}
if generated, has := attrs["linguist-generated"]; has {
if generated == "set" || generated == "true" {
return nil
}
notGenerated = generated == "false"
}
if language, has := attrs["linguist-language"]; has && language != "unspecified" && language != "" {
// group languages, such as Pug -> HTML; SCSS -> CSS
group := enry.GetLanguageGroup(language)
if len(group) != 0 {
language = group
}
sizes[language] += f.Size
return nil
} else if language, has := attrs["gitlab-language"]; has && language != "unspecified" && language != "" {
// strip off a ? if present
if idx := strings.IndexByte(language, '?'); idx >= 0 {
language = language[:idx]
}
if len(language) != 0 {
// group languages, such as Pug -> HTML; SCSS -> CSS
group := enry.GetLanguageGroup(language)
if len(group) != 0 {
language = group
}
sizes[language] += f.Size
return nil
}
}
}
}
if (!notVendored && analyze.IsVendor(f.Name)) || enry.IsDotFile(f.Name) ||
Use native git variants by default with go-git variants as build tag (#13673) * Move last commit cache back into modules/git Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove go-git from the interface for last commit cache Signed-off-by: Andrew Thornton <art27@cantab.net> * move cacheref to last_commit_cache Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove go-git from routers/private/hook Signed-off-by: Andrew Thornton <art27@cantab.net> * Move FindLFSFiles to pipeline Signed-off-by: Andrew Thornton <art27@cantab.net> * Make no-go-git variants Signed-off-by: Andrew Thornton <art27@cantab.net> * Submodule RefID Signed-off-by: Andrew Thornton <art27@cantab.net> * fix issue with GetCommitsInfo Signed-off-by: Andrew Thornton <art27@cantab.net> * fix GetLastCommitForPaths Signed-off-by: Andrew Thornton <art27@cantab.net> * Improve efficiency Signed-off-by: Andrew Thornton <art27@cantab.net> * More efficiency Signed-off-by: Andrew Thornton <art27@cantab.net> * even faster Signed-off-by: Andrew Thornton <art27@cantab.net> * Reduce duplication * As per @lunny Signed-off-by: Andrew Thornton <art27@cantab.net> * attempt to fix drone Signed-off-by: Andrew Thornton <art27@cantab.net> * fix test-tags Signed-off-by: Andrew Thornton <art27@cantab.net> * default to use no-go-git variants and add gogit build tag Signed-off-by: Andrew Thornton <art27@cantab.net> * placate lint Signed-off-by: Andrew Thornton <art27@cantab.net> * as per @6543 Signed-off-by: Andrew Thornton <art27@cantab.net> Co-authored-by: 6543 <6543@obermui.de> Co-authored-by: techknowlogick <techknowlogick@gitea.io>
2020-12-17 14:00:47 +00:00
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 !notGenerated && enry.IsGenerated(f.Name, content) {
Use native git variants by default with go-git variants as build tag (#13673) * Move last commit cache back into modules/git Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove go-git from the interface for last commit cache Signed-off-by: Andrew Thornton <art27@cantab.net> * move cacheref to last_commit_cache Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove go-git from routers/private/hook Signed-off-by: Andrew Thornton <art27@cantab.net> * Move FindLFSFiles to pipeline Signed-off-by: Andrew Thornton <art27@cantab.net> * Make no-go-git variants Signed-off-by: Andrew Thornton <art27@cantab.net> * Submodule RefID Signed-off-by: Andrew Thornton <art27@cantab.net> * fix issue with GetCommitsInfo Signed-off-by: Andrew Thornton <art27@cantab.net> * fix GetLastCommitForPaths Signed-off-by: Andrew Thornton <art27@cantab.net> * Improve efficiency Signed-off-by: Andrew Thornton <art27@cantab.net> * More efficiency Signed-off-by: Andrew Thornton <art27@cantab.net> * even faster Signed-off-by: Andrew Thornton <art27@cantab.net> * Reduce duplication * As per @lunny Signed-off-by: Andrew Thornton <art27@cantab.net> * attempt to fix drone Signed-off-by: Andrew Thornton <art27@cantab.net> * fix test-tags Signed-off-by: Andrew Thornton <art27@cantab.net> * default to use no-go-git variants and add gogit build tag Signed-off-by: Andrew Thornton <art27@cantab.net> * placate lint Signed-off-by: Andrew Thornton <art27@cantab.net> * as per @6543 Signed-off-by: Andrew Thornton <art27@cantab.net> Co-authored-by: 6543 <6543@obermui.de> Co-authored-by: techknowlogick <techknowlogick@gitea.io>
2020-12-17 14:00:47 +00:00
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 io.ReadAll(r)
Use native git variants by default with go-git variants as build tag (#13673) * Move last commit cache back into modules/git Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove go-git from the interface for last commit cache Signed-off-by: Andrew Thornton <art27@cantab.net> * move cacheref to last_commit_cache Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove go-git from routers/private/hook Signed-off-by: Andrew Thornton <art27@cantab.net> * Move FindLFSFiles to pipeline Signed-off-by: Andrew Thornton <art27@cantab.net> * Make no-go-git variants Signed-off-by: Andrew Thornton <art27@cantab.net> * Submodule RefID Signed-off-by: Andrew Thornton <art27@cantab.net> * fix issue with GetCommitsInfo Signed-off-by: Andrew Thornton <art27@cantab.net> * fix GetLastCommitForPaths Signed-off-by: Andrew Thornton <art27@cantab.net> * Improve efficiency Signed-off-by: Andrew Thornton <art27@cantab.net> * More efficiency Signed-off-by: Andrew Thornton <art27@cantab.net> * even faster Signed-off-by: Andrew Thornton <art27@cantab.net> * Reduce duplication * As per @lunny Signed-off-by: Andrew Thornton <art27@cantab.net> * attempt to fix drone Signed-off-by: Andrew Thornton <art27@cantab.net> * fix test-tags Signed-off-by: Andrew Thornton <art27@cantab.net> * default to use no-go-git variants and add gogit build tag Signed-off-by: Andrew Thornton <art27@cantab.net> * placate lint Signed-off-by: Andrew Thornton <art27@cantab.net> * as per @6543 Signed-off-by: Andrew Thornton <art27@cantab.net> Co-authored-by: 6543 <6543@obermui.de> Co-authored-by: techknowlogick <techknowlogick@gitea.io>
2020-12-17 14:00:47 +00:00
}
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
}