forgejo/modules/git/commit_info.go
Lunny Xiao 0ca13c5eae
[PORT] Refactor the usage of batch catfile (gitea#31754)
When opening a repository, it will call `ensureValidRepository` and also
`CatFileBatch`. But sometimes these will not be used until repository
closed. So it's a waste of CPU to invoke 3 times git command for every
open repository.

This PR removed all of these from `OpenRepository` but only kept
checking whether the folder exists. When a batch is necessary, the
necessary functions will be invoked.

---
Conflict resolution: Because of the removal of go-git in (#4941)
`_nogogit.go` files were either renamed or merged into the 'common'
file. Git does handle the renames correctly, but for those that were
merged has to be manually copied pasted over. The patch looks the same,
201 additions 90 deletions as the original patch.

(cherry picked from commit c03baab678ba5b2e9d974aea147e660417f5d3f7)
2024-08-26 03:48:51 +02:00

179 lines
4.6 KiB
Go

// Copyright 2017 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package git
import (
"context"
"fmt"
"io"
"path"
"sort"
"code.gitea.io/gitea/modules/log"
)
// CommitInfo describes the first commit with the provided entry
type CommitInfo struct {
Entry *TreeEntry
Commit *Commit
SubModuleFile *SubModuleFile
}
// GetCommitsInfo gets information of all commits that are corresponding to these entries
func (tes Entries) GetCommitsInfo(ctx context.Context, commit *Commit, treePath string) ([]CommitInfo, *Commit, error) {
entryPaths := make([]string, len(tes)+1)
// Get the commit for the treePath itself
entryPaths[0] = ""
for i, entry := range tes {
entryPaths[i+1] = entry.Name()
}
var err error
var revs map[string]*Commit
if commit.repo.LastCommitCache != nil {
var unHitPaths []string
revs, unHitPaths, err = getLastCommitForPathsByCache(commit.ID.String(), treePath, entryPaths, commit.repo.LastCommitCache)
if err != nil {
return nil, nil, err
}
if len(unHitPaths) > 0 {
sort.Strings(unHitPaths)
commits, err := GetLastCommitForPaths(ctx, commit, treePath, unHitPaths)
if err != nil {
return nil, nil, err
}
for pth, found := range commits {
revs[pth] = found
}
}
} else {
sort.Strings(entryPaths)
revs, err = GetLastCommitForPaths(ctx, commit, treePath, entryPaths)
}
if err != nil {
return nil, nil, err
}
commitsInfo := make([]CommitInfo, len(tes))
for i, entry := range tes {
commitsInfo[i] = CommitInfo{
Entry: entry,
}
// Check if we have found a commit for this entry in time
if entryCommit, ok := revs[entry.Name()]; ok {
commitsInfo[i].Commit = entryCommit
} else {
log.Debug("missing commit for %s", entry.Name())
}
// If the entry if a submodule add a submodule file for this
if entry.IsSubModule() {
subModuleURL := ""
var fullPath string
if len(treePath) > 0 {
fullPath = treePath + "/" + entry.Name()
} else {
fullPath = entry.Name()
}
if subModule, err := commit.GetSubModule(fullPath); err != nil {
return nil, nil, err
} else if subModule != nil {
subModuleURL = subModule.URL
}
subModuleFile := NewSubModuleFile(commitsInfo[i].Commit, subModuleURL, entry.ID.String())
commitsInfo[i].SubModuleFile = subModuleFile
}
}
// Retrieve the commit for the treePath itself (see above). We basically
// get it for free during the tree traversal and it's used for listing
// pages to display information about newest commit for a given path.
var treeCommit *Commit
var ok bool
if treePath == "" {
treeCommit = commit
} else if treeCommit, ok = revs[""]; ok {
treeCommit.repo = commit.repo
}
return commitsInfo, treeCommit, nil
}
func getLastCommitForPathsByCache(commitID, treePath string, paths []string, cache *LastCommitCache) (map[string]*Commit, []string, error) {
var unHitEntryPaths []string
results := make(map[string]*Commit)
for _, p := range paths {
lastCommit, err := cache.Get(commitID, path.Join(treePath, p))
if err != nil {
return nil, nil, err
}
if lastCommit != nil {
results[p] = lastCommit
continue
}
unHitEntryPaths = append(unHitEntryPaths, p)
}
return results, unHitEntryPaths, nil
}
// GetLastCommitForPaths returns last commit information
func GetLastCommitForPaths(ctx context.Context, commit *Commit, treePath string, paths []string) (map[string]*Commit, error) {
// We read backwards from the commit to obtain all of the commits
revs, err := WalkGitLog(ctx, commit.repo, commit, treePath, paths...)
if err != nil {
return nil, err
}
batchStdinWriter, batchReader, cancel, err := commit.repo.CatFileBatch(ctx)
if err != nil {
return nil, err
}
defer cancel()
commitsMap := map[string]*Commit{}
commitsMap[commit.ID.String()] = commit
commitCommits := map[string]*Commit{}
for path, commitID := range revs {
c, ok := commitsMap[commitID]
if ok {
commitCommits[path] = c
continue
}
if len(commitID) == 0 {
continue
}
_, err := batchStdinWriter.Write([]byte(commitID + "\n"))
if err != nil {
return nil, err
}
_, typ, size, err := ReadBatchLine(batchReader)
if err != nil {
return nil, err
}
if typ != "commit" {
if err := DiscardFull(batchReader, size+1); err != nil {
return nil, err
}
return nil, fmt.Errorf("unexpected type: %s for commit id: %s", typ, commitID)
}
c, err = CommitFromReader(commit.repo, MustIDFromString(commitID), io.LimitReader(batchReader, size))
if err != nil {
return nil, err
}
if _, err := batchReader.Discard(1); err != nil {
return nil, err
}
commitCommits[path] = c
}
return commitCommits, nil
}