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>
2025-10-29 10:57:44 +09:00 · 2020-12-17 14:00:47 +00:00
parent 0851a89581
commit 511f6138d4
81 changed files with 3952 additions and 1492 deletions
--- a/modules/git/repo_language_stats_gogit.go
+++ b/modules/git/repo_language_stats_gogit.go
@@ -0,0 +1,113 @@
+// 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 || enry.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
+}