bench-forgejo/modules/git/repo_commit.go

458 lines
14 KiB
Go
Raw Normal View History

2016-11-04 03:46:01 +05:30
// Copyright 2015 The Gogs Authors. All rights reserved.
Improve listing performance by using go-git (#6478) * Use go-git for tree reading and commit info lookup. Signed-off-by: Filip Navara <navara@emclient.com> * Use TreeEntry.IsRegular() instead of ObjectType that was removed. Signed-off-by: Filip Navara <navara@emclient.com> * Use the treePath to optimize commit info search. Signed-off-by: Filip Navara <navara@emclient.com> * Extract the latest commit at treePath along with the other commits. Signed-off-by: Filip Navara <navara@emclient.com> * Fix listing commit info for a directory that was created in one commit and never modified after. Signed-off-by: Filip Navara <navara@emclient.com> * Avoid nearly all external 'git' invocations when doing directory listing (.editorconfig code path is still hit). Signed-off-by: Filip Navara <navara@emclient.com> * Use go-git for reading blobs. Signed-off-by: Filip Navara <navara@emclient.com> * Make SHA1 type alias for plumbing.Hash in go-git. Signed-off-by: Filip Navara <navara@emclient.com> * Make Signature type alias for object.Signature in go-git. Signed-off-by: Filip Navara <navara@emclient.com> * Fix GetCommitsInfo for repository with only one commit. Signed-off-by: Filip Navara <navara@emclient.com> * Fix PGP signature verification. Signed-off-by: Filip Navara <navara@emclient.com> * Fix issues with walking commit graph across merges. Signed-off-by: Filip Navara <navara@emclient.com> * Fix typo in condition. Signed-off-by: Filip Navara <navara@emclient.com> * Speed up loading branch list by keeping the repository reference (and thus all the loaded packfile indexes). Signed-off-by: Filip Navara <navara@emclient.com> * Fix lising submodules. Signed-off-by: Filip Navara <navara@emclient.com> * Fix build Signed-off-by: Filip Navara <navara@emclient.com> * Add back commit cache because of name-rev Signed-off-by: Filip Navara <navara@emclient.com> * Fix tests Signed-off-by: Filip Navara <navara@emclient.com> * Fix code style * Fix spelling * Address PR feedback Signed-off-by: Filip Navara <navara@emclient.com> * Update vendor module list Signed-off-by: Filip Navara <navara@emclient.com> * Fix getting trees by commit id Signed-off-by: Filip Navara <navara@emclient.com> * Fix remaining unit test failures * Fix GetTreeBySHA * Avoid running `git name-rev` if not necessary Signed-off-by: Filip Navara <navara@emclient.com> * Move Branch code to git module * Clean up GPG signature verification and fix it for tagged commits * Address PR feedback (import formatting, copyright headers) * Make blob lookup by SHA working * Update tests to use public API * Allow getting content from any type of object through the blob interface * Change test to actually expect the object content that is in the GIT repository * Change one more test to actually expect the object content that is in the GIT repository * Add comments
2019-04-19 17:47:27 +05:30
// Copyright 2019 The Gitea Authors. All rights reserved.
2016-11-04 03:46:01 +05:30
// Use of this source code is governed by a MIT-style
// license that can be found in the LICENSE file.
package git
import (
"bytes"
"encoding/hex"
"fmt"
"io"
2016-11-04 03:46:01 +05:30
"strconv"
"strings"
"code.gitea.io/gitea/modules/cache"
"code.gitea.io/gitea/modules/setting"
2016-11-04 03:46:01 +05:30
)
// GetBranchCommitID returns last commit ID string of given branch.
func (repo *Repository) GetBranchCommitID(name string) (string, error) {
return repo.GetRefCommitID(BranchPrefix + name)
2016-11-04 03:46:01 +05:30
}
// GetTagCommitID returns last commit ID string of given tag.
func (repo *Repository) GetTagCommitID(name string) (string, error) {
return repo.GetRefCommitID(TagPrefix + name)
2016-11-04 03:46:01 +05:30
}
// GetCommit returns commit object of by ID string.
func (repo *Repository) GetCommit(commitID string) (*Commit, error) {
id, err := repo.ConvertToSHA1(commitID)
2016-11-04 03:46:01 +05:30
if err != nil {
return nil, err
}
return repo.getCommit(id)
}
// GetBranchCommit returns the last commit of given branch.
func (repo *Repository) GetBranchCommit(name string) (*Commit, error) {
commitID, err := repo.GetBranchCommitID(name)
if err != nil {
return nil, err
}
return repo.GetCommit(commitID)
}
2016-12-22 15:00:52 +05:30
// GetTagCommit get the commit of the specific tag via name
2016-11-04 03:46:01 +05:30
func (repo *Repository) GetTagCommit(name string) (*Commit, error) {
commitID, err := repo.GetTagCommitID(name)
if err != nil {
return nil, err
}
return repo.GetCommit(commitID)
}
2016-12-22 15:00:52 +05:30
func (repo *Repository) getCommitByPathWithID(id SHA1, relpath string) (*Commit, error) {
2016-11-04 03:46:01 +05:30
// File name starts with ':' must be escaped.
if relpath[0] == ':' {
relpath = `\` + relpath
}
stdout, _, runErr := NewCommand(repo.Ctx, "log", "-1", prettyLogFormat, id.String(), "--", relpath).RunStdString(&RunOpts{Dir: repo.Path})
if runErr != nil {
return nil, runErr
2016-11-04 03:46:01 +05:30
}
id, err := NewIDFromString(stdout)
2016-11-04 03:46:01 +05:30
if err != nil {
return nil, err
}
return repo.getCommit(id)
}
// GetCommitByPath returns the last commit of relative path.
func (repo *Repository) GetCommitByPath(relpath string) (*Commit, error) {
stdout, _, runErr := NewCommand(repo.Ctx, "log", "-1", prettyLogFormat, "--", relpath).RunStdBytes(&RunOpts{Dir: repo.Path})
if runErr != nil {
return nil, runErr
2016-11-04 03:46:01 +05:30
}
commits, err := repo.parsePrettyFormatLogToList(stdout)
if err != nil {
return nil, err
}
return commits[0], nil
2016-11-04 03:46:01 +05:30
}
func (repo *Repository) commitsByRange(id SHA1, page, pageSize int) ([]*Commit, error) {
stdout, _, err := NewCommand(repo.Ctx, "log", id.String(), "--skip="+strconv.Itoa((page-1)*pageSize),
"--max-count="+strconv.Itoa(pageSize), prettyLogFormat).RunStdBytes(&RunOpts{Dir: repo.Path})
2016-11-04 03:46:01 +05:30
if err != nil {
return nil, err
}
return repo.parsePrettyFormatLogToList(stdout)
}
func (repo *Repository) searchCommits(id SHA1, opts SearchCommitsOptions) ([]*Commit, error) {
// create new git log command with limit of 100 commis
cmd := NewCommand(repo.Ctx, "log", id.String(), "-100", prettyLogFormat)
// ignore case
args := []string{"-i"}
// add authors if present in search query
if len(opts.Authors) > 0 {
for _, v := range opts.Authors {
args = append(args, "--author="+v)
}
}
// add committers if present in search query
if len(opts.Committers) > 0 {
for _, v := range opts.Committers {
args = append(args, "--committer="+v)
}
}
// add time constraints if present in search query
if len(opts.After) > 0 {
args = append(args, "--after="+opts.After)
}
if len(opts.Before) > 0 {
args = append(args, "--before="+opts.Before)
}
// pretend that all refs along with HEAD were listed on command line as <commis>
// https://git-scm.com/docs/git-log#Documentation/git-log.txt---all
// note this is done only for command created above
if opts.All {
cmd.AddArguments("--all")
}
// add remaining keywords from search string
// note this is done only for command created above
if len(opts.Keywords) > 0 {
for _, v := range opts.Keywords {
cmd.AddArguments("--grep=" + v)
}
}
// search for commits matching given constraints and keywords in commit msg
cmd.AddArguments(args...)
stdout, _, err := cmd.RunStdBytes(&RunOpts{Dir: repo.Path})
2016-11-04 03:46:01 +05:30
if err != nil {
return nil, err
}
if len(stdout) != 0 {
stdout = append(stdout, '\n')
}
// if there are any keywords (ie not committer:, author:, time:)
// then let's iterate over them
if len(opts.Keywords) > 0 {
for _, v := range opts.Keywords {
2022-10-17 20:10:37 +05:30
// ignore anything not matching a valid sha pattern
if IsValidSHAPattern(v) {
// create new git log command with 1 commit limit
hashCmd := NewCommand(repo.Ctx, "log", "-1", prettyLogFormat)
// add previous arguments except for --grep and --all
hashCmd.AddArguments(args...)
// add keyword as <commit>
hashCmd.AddDynamicArguments(v)
// search with given constraints for commit matching sha hash of v
hashMatching, _, err := hashCmd.RunStdBytes(&RunOpts{Dir: repo.Path})
if err != nil || bytes.Contains(stdout, hashMatching) {
continue
}
stdout = append(stdout, hashMatching...)
stdout = append(stdout, '\n')
}
}
}
return repo.parsePrettyFormatLogToList(bytes.TrimSuffix(stdout, []byte{'\n'}))
2016-11-04 03:46:01 +05:30
}
func (repo *Repository) getFilesChanged(id1, id2 string) ([]string, error) {
stdout, _, err := NewCommand(repo.Ctx, "diff", "--name-only", id1, id2).RunStdBytes(&RunOpts{Dir: repo.Path})
2016-11-04 03:46:01 +05:30
if err != nil {
return nil, err
}
return strings.Split(string(stdout), "\n"), nil
}
// FileChangedBetweenCommits Returns true if the file changed between commit IDs id1 and id2
// You must ensure that id1 and id2 are valid commit ids.
func (repo *Repository) FileChangedBetweenCommits(filename, id1, id2 string) (bool, error) {
stdout, _, err := NewCommand(repo.Ctx, "diff", "--name-only", "-z", id1, id2, "--", filename).RunStdBytes(&RunOpts{Dir: repo.Path})
if err != nil {
return false, err
}
return len(strings.TrimSpace(string(stdout))) > 0, nil
}
// FileCommitsCount return the number of files at a revision
2016-11-04 03:46:01 +05:30
func (repo *Repository) FileCommitsCount(revision, file string) (int64, error) {
return CommitsCountFiles(repo.Ctx, repo.Path, []string{revision}, []string{file})
2016-11-04 03:46:01 +05:30
}
// CommitsByFileAndRange return the commits according revision file and the page
func (repo *Repository) CommitsByFileAndRange(revision, file string, page int) ([]*Commit, error) {
skip := (page - 1) * setting.Git.CommitsRangeSize
stdoutReader, stdoutWriter := io.Pipe()
defer func() {
_ = stdoutReader.Close()
_ = stdoutWriter.Close()
}()
go func() {
stderr := strings.Builder{}
gitCmd := NewCommand(repo.Ctx, "rev-list",
"--max-count="+strconv.Itoa(setting.Git.CommitsRangeSize*page),
"--skip="+strconv.Itoa(skip),
)
gitCmd.AddDynamicArguments(revision)
gitCmd.AddArguments("--", file)
err := gitCmd.Run(&RunOpts{
Dir: repo.Path,
Stdout: stdoutWriter,
Stderr: &stderr,
})
if err != nil {
_ = stdoutWriter.CloseWithError(ConcatenateError(err, (&stderr).String()))
} else {
_ = stdoutWriter.Close()
}
}()
commits := []*Commit{}
shaline := [41]byte{}
var sha1 SHA1
for {
n, err := io.ReadFull(stdoutReader, shaline[:])
if err != nil || n < 40 {
if err == io.EOF {
err = nil
}
return commits, err
}
n, err = hex.Decode(sha1[:], shaline[0:40])
if n != 20 {
err = fmt.Errorf("invalid sha %q", string(shaline[:40]))
}
if err != nil {
return nil, err
}
commit, err := repo.getCommit(sha1)
if err != nil {
return nil, err
}
commits = append(commits, commit)
}
}
2016-12-22 15:00:52 +05:30
// FilesCountBetween return the number of files changed between two commits
2016-11-04 03:46:01 +05:30
func (repo *Repository) FilesCountBetween(startCommitID, endCommitID string) (int, error) {
stdout, _, err := NewCommand(repo.Ctx, "diff", "--name-only", startCommitID+"..."+endCommitID).RunStdString(&RunOpts{Dir: repo.Path})
if err != nil && strings.Contains(err.Error(), "no merge base") {
// git >= 2.28 now returns an error if startCommitID and endCommitID have become unrelated.
// previously it would return the results of git diff --name-only startCommitID endCommitID so let's try that...
stdout, _, err = NewCommand(repo.Ctx, "diff", "--name-only", startCommitID, endCommitID).RunStdString(&RunOpts{Dir: repo.Path})
}
2016-11-04 03:46:01 +05:30
if err != nil {
return 0, err
}
return len(strings.Split(stdout, "\n")) - 1, nil
}
// CommitsBetween returns a list that contains commits between [before, last).
// If before is detached (removed by reset + push) it is not included.
func (repo *Repository) CommitsBetween(last, before *Commit) ([]*Commit, error) {
var stdout []byte
var err error
if before == nil {
stdout, _, err = NewCommand(repo.Ctx, "rev-list", last.ID.String()).RunStdBytes(&RunOpts{Dir: repo.Path})
} else {
stdout, _, err = NewCommand(repo.Ctx, "rev-list", before.ID.String()+".."+last.ID.String()).RunStdBytes(&RunOpts{Dir: repo.Path})
if err != nil && strings.Contains(err.Error(), "no merge base") {
// future versions of git >= 2.28 are likely to return an error if before and last have become unrelated.
// previously it would return the results of git rev-list before last so let's try that...
stdout, _, err = NewCommand(repo.Ctx, "rev-list", before.ID.String(), last.ID.String()).RunStdBytes(&RunOpts{Dir: repo.Path})
}
}
if err != nil {
return nil, err
}
return repo.parsePrettyFormatLogToList(bytes.TrimSpace(stdout))
}
// CommitsBetweenLimit returns a list that contains at most limit commits skipping the first skip commits between [before, last)
func (repo *Repository) CommitsBetweenLimit(last, before *Commit, limit, skip int) ([]*Commit, error) {
var stdout []byte
var err error
if before == nil {
stdout, _, err = NewCommand(repo.Ctx, "rev-list", "--max-count", strconv.Itoa(limit), "--skip", strconv.Itoa(skip), last.ID.String()).RunStdBytes(&RunOpts{Dir: repo.Path})
} else {
stdout, _, err = NewCommand(repo.Ctx, "rev-list", "--max-count", strconv.Itoa(limit), "--skip", strconv.Itoa(skip), before.ID.String()+".."+last.ID.String()).RunStdBytes(&RunOpts{Dir: repo.Path})
if err != nil && strings.Contains(err.Error(), "no merge base") {
// future versions of git >= 2.28 are likely to return an error if before and last have become unrelated.
// previously it would return the results of git rev-list --max-count n before last so let's try that...
stdout, _, err = NewCommand(repo.Ctx, "rev-list", "--max-count", strconv.Itoa(limit), "--skip", strconv.Itoa(skip), before.ID.String(), last.ID.String()).RunStdBytes(&RunOpts{Dir: repo.Path})
}
}
2017-10-23 19:06:14 +05:30
if err != nil {
return nil, err
2016-11-04 03:46:01 +05:30
}
2017-10-23 19:06:14 +05:30
return repo.parsePrettyFormatLogToList(bytes.TrimSpace(stdout))
2016-11-04 03:46:01 +05:30
}
2016-12-22 15:00:52 +05:30
// CommitsBetweenIDs return commits between twoe commits
func (repo *Repository) CommitsBetweenIDs(last, before string) ([]*Commit, error) {
2016-11-04 03:46:01 +05:30
lastCommit, err := repo.GetCommit(last)
if err != nil {
return nil, err
}
if before == "" {
return repo.CommitsBetween(lastCommit, nil)
}
2016-11-04 03:46:01 +05:30
beforeCommit, err := repo.GetCommit(before)
if err != nil {
return nil, err
}
return repo.CommitsBetween(lastCommit, beforeCommit)
}
2016-12-22 15:00:52 +05:30
// CommitsCountBetween return numbers of commits between two commits
2016-11-04 03:46:01 +05:30
func (repo *Repository) CommitsCountBetween(start, end string) (int64, error) {
count, err := CommitsCountFiles(repo.Ctx, repo.Path, []string{start + ".." + end}, []string{})
if err != nil && strings.Contains(err.Error(), "no merge base") {
// future versions of git >= 2.28 are likely to return an error if before and last have become unrelated.
// previously it would return the results of git rev-list before last so let's try that...
return CommitsCountFiles(repo.Ctx, repo.Path, []string{start, end}, []string{})
}
return count, err
2016-11-04 03:46:01 +05:30
}
2016-12-22 15:00:52 +05:30
// commitsBefore the limit is depth, not total number of returned commits.
func (repo *Repository) commitsBefore(id SHA1, limit int) ([]*Commit, error) {
cmd := NewCommand(repo.Ctx, "log")
2017-12-11 07:53:34 +05:30
if limit > 0 {
2018-05-28 00:17:34 +05:30
cmd.AddArguments("-"+strconv.Itoa(limit), prettyLogFormat, id.String())
2017-12-11 07:53:34 +05:30
} else {
cmd.AddArguments(prettyLogFormat, id.String())
2016-11-04 03:46:01 +05:30
}
stdout, _, runErr := cmd.RunStdBytes(&RunOpts{Dir: repo.Path})
if runErr != nil {
return nil, runErr
2016-11-04 03:46:01 +05:30
}
2017-12-11 07:53:34 +05:30
formattedLog, err := repo.parsePrettyFormatLogToList(bytes.TrimSpace(stdout))
if err != nil {
return nil, err
2016-11-04 03:46:01 +05:30
}
commits := make([]*Commit, 0, len(formattedLog))
for _, commit := range formattedLog {
2017-12-11 07:53:34 +05:30
branches, err := repo.getBranches(commit, 2)
2016-11-04 03:46:01 +05:30
if err != nil {
2017-12-11 07:53:34 +05:30
return nil, err
2016-11-04 03:46:01 +05:30
}
2017-12-11 07:53:34 +05:30
if len(branches) > 1 {
break
2016-11-04 03:46:01 +05:30
}
2017-12-11 07:53:34 +05:30
commits = append(commits, commit)
2016-11-04 03:46:01 +05:30
}
2017-12-11 07:53:34 +05:30
return commits, nil
2016-11-04 03:46:01 +05:30
}
func (repo *Repository) getCommitsBefore(id SHA1) ([]*Commit, error) {
2017-12-11 07:53:34 +05:30
return repo.commitsBefore(id, 0)
2016-11-04 03:46:01 +05:30
}
func (repo *Repository) getCommitsBeforeLimit(id SHA1, num int) ([]*Commit, error) {
2017-12-11 07:53:34 +05:30
return repo.commitsBefore(id, num)
}
func (repo *Repository) getBranches(commit *Commit, limit int) ([]string, error) {
if CheckGitVersionAtLeast("2.7.0") == nil {
stdout, _, err := NewCommand(repo.Ctx, "for-each-ref", "--count="+strconv.Itoa(limit), "--format=%(refname:strip=2)", "--contains", commit.ID.String(), BranchPrefix).RunStdString(&RunOpts{Dir: repo.Path})
2018-05-28 00:17:34 +05:30
if err != nil {
return nil, err
}
branches := strings.Fields(stdout)
return branches, nil
}
stdout, _, err := NewCommand(repo.Ctx, "branch", "--contains", commit.ID.String()).RunStdString(&RunOpts{Dir: repo.Path})
2017-12-11 07:53:34 +05:30
if err != nil {
return nil, err
}
refs := strings.Split(stdout, "\n")
2018-05-28 00:17:34 +05:30
var max int
if len(refs) > limit {
max = limit
} else {
max = len(refs) - 1
}
branches := make([]string, max)
for i, ref := range refs[:max] {
parts := strings.Fields(ref)
branches[i] = parts[len(parts)-1]
2017-12-11 07:53:34 +05:30
}
return branches, nil
2016-11-04 03:46:01 +05:30
}
// GetCommitsFromIDs get commits from commit IDs
func (repo *Repository) GetCommitsFromIDs(commitIDs []string) []*Commit {
commits := make([]*Commit, 0, len(commitIDs))
for _, commitID := range commitIDs {
commit, err := repo.GetCommit(commitID)
if err == nil && commit != nil {
commits = append(commits, commit)
}
}
return commits
}
// IsCommitInBranch check if the commit is on the branch
func (repo *Repository) IsCommitInBranch(commitID, branch string) (r bool, err error) {
stdout, _, err := NewCommand(repo.Ctx, "branch", "--contains", commitID, branch).RunStdString(&RunOpts{Dir: repo.Path})
if err != nil {
return false, err
}
return len(stdout) > 0, err
}
func (repo *Repository) AddLastCommitCache(cacheKey, fullName, sha string) error {
if repo.LastCommitCache == nil {
commitsCount, err := cache.GetInt64(cacheKey, func() (int64, error) {
commit, err := repo.GetCommit(sha)
if err != nil {
return 0, err
}
return commit.CommitsCount()
})
if err != nil {
return err
}
repo.LastCommitCache = NewLastCommitCache(commitsCount, fullName, repo, cache.GetCache())
}
return nil
}