1
0
Fork 0
mirror of https://codeberg.org/forgejo/forgejo.git synced 2024-12-10 11:25:56 -05:00
forgejo/modules/git/repo_language_stats_gogit.go
Gergely Nagy ae0635fd61
Correctly support linguist-documentation=false
If a documentation file is marked with a `linguist-documentation=false`
attribute, include it in language stats.

However, make sure that we do *not* include documentation languages as
fallback.

Added a new test case to exercise the formerly buggy behaviour.

Problem discovered while reviewing @KN4CK3R's tests from gitea#29267.

Signed-off-by: Gergely Nagy <forgejo@gergo.csillger.hu>
2024-02-26 14:18:33 +01:00

194 lines
5.3 KiB
Go

// Copyright 2020 The Gitea Authors. All rights reserved.
// Copyright 2024 The Forgejo Authors c/o Codeberg e.V.. All rights reserved.
// SPDX-License-Identifier: MIT
//go:build gogit
package git
import (
"bytes"
"io"
"strings"
"code.gitea.io/gitea/modules/analyze"
"code.gitea.io/gitea/modules/optional"
"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
}
checker, deferable := repo.CheckAttributeReader(commitID)
defer deferable()
// sizes contains the current calculated size of all files by language
sizes := make(map[string]int64)
// by default we will only count the sizes of programming languages or markup languages
// unless they are explicitly set using linguist-language
includedLanguage := map[string]bool{}
// or if there's only one language in the repository
firstExcludedLanguage := ""
firstExcludedLanguageSize := int64(0)
isTrue := func(v optional.Option[bool]) bool {
return v.ValueOrDefault(false)
}
isFalse := func(v optional.Option[bool]) bool {
return !v.ValueOrDefault(true)
}
err = tree.Files().ForEach(func(f *object.File) error {
if f.Size == 0 {
return nil
}
isVendored := optional.None[bool]()
isGenerated := optional.None[bool]()
isDocumentation := optional.None[bool]()
isDetectable := optional.None[bool]()
if checker != nil {
attrs, err := checker.CheckPath(f.Name)
if err == nil {
isVendored = attributeToBool(attrs, "linguist-vendored")
isGenerated = attributeToBool(attrs, "linguist-generated")
isDocumentation = attributeToBool(attrs, "linguist-documentation")
isDetectable = attributeToBool(attrs, "linguist-detectable")
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
}
// this language will always be added to the size
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
}
// this language will always be added to the size
sizes[language] += f.Size
return nil
}
}
}
}
if isFalse(isDetectable) || isTrue(isVendored) || isTrue(isDocumentation) ||
(!isFalse(isVendored) && analyze.IsVendor(f.Name)) ||
enry.IsDotFile(f.Name) ||
enry.IsConfiguration(f.Name) ||
(!isFalse(isDocumentation) && enry.IsDocumentation(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 !isTrue(isGenerated) && 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
}
included, checked := includedLanguage[language]
langType := enry.GetLanguageType(language)
if !checked {
included = langType == enry.Programming || langType == enry.Markup
if !included && (isTrue(isDetectable) || (langType == enry.Prose && isFalse(isDocumentation))) {
included = true
}
includedLanguage[language] = included
}
if included {
sizes[language] += f.Size
} else if len(sizes) == 0 && (firstExcludedLanguage == "" || firstExcludedLanguage == language) {
// Only consider Programming or Markup languages as fallback
if !(langType == enry.Programming || langType == enry.Markup) {
return nil
}
firstExcludedLanguage = language
firstExcludedLanguageSize += f.Size
}
return nil
})
if err != nil {
return nil, err
}
// If there are no included languages add the first excluded language
if len(sizes) == 0 && firstExcludedLanguage != "" {
sizes[firstExcludedLanguage] = firstExcludedLanguageSize
}
return mergeLanguageStats(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)
}
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
}