1
1
Fork 1
mirror of https://github.com/go-gitea/gitea.git synced 2024-04-28 11:35:07 +02:00
gitea/routers/web/repo/lfs.go
wxiaoguang 6bc3079c00
Refactor git command package to improve security and maintainability (#22678)
This PR follows #21535 (and replace #22592)

## Review without space diff

https://github.com/go-gitea/gitea/pull/22678/files?diff=split&w=1

## Purpose of this PR

1. Make git module command completely safe (risky user inputs won't be
passed as argument option anymore)
2. Avoid low-level mistakes like
https://github.com/go-gitea/gitea/pull/22098#discussion_r1045234918
3. Remove deprecated and dirty `CmdArgCheck` function, hide the `CmdArg`
type
4. Simplify code when using git command

## The main idea of this PR

* Move the `git.CmdArg` to the `internal` package, then no other package
except `git` could use it. Then developers could never do
`AddArguments(git.CmdArg(userInput))` any more.
* Introduce `git.ToTrustedCmdArgs`, it's for user-provided and already
trusted arguments. It's only used in a few cases, for example: use git
arguments from config file, help unit test with some arguments.
* Introduce `AddOptionValues` and `AddOptionFormat`, they make code more
clear and simple:
    * Before: `AddArguments("-m").AddDynamicArguments(message)`
    * After: `AddOptionValues("-m", message)`
    * -
* Before: `AddArguments(git.CmdArg(fmt.Sprintf("--author='%s <%s>'",
sig.Name, sig.Email)))`
* After: `AddOptionFormat("--author='%s <%s>'", sig.Name, sig.Email)`

## FAQ

### Why these changes were not done in #21535 ?

#21535 is mainly a search&replace, it did its best to not change too
much logic.

Making the framework better needs a lot of changes, so this separate PR
is needed as the second step.


### The naming of `AddOptionXxx`

According to git's manual, the `--xxx` part is called `option`.

### How can it guarantee that `internal.CmdArg` won't be not misused?

Go's specification guarantees that. Trying to access other package's
internal package causes compilation error.

And, `golangci-lint` also denies the git/internal package. Only the
`git/command.go` can use it carefully.

### There is still a `ToTrustedCmdArgs`, will it still allow developers
to make mistakes and pass untrusted arguments?

Generally speaking, no. Because when using `ToTrustedCmdArgs`, the code
will be very complex (see the changes for examples). Then developers and
reviewers can know that something might be unreasonable.

### Why there was a `CmdArgCheck` and why it's removed?

At the moment of #21535, to reduce unnecessary changes, `CmdArgCheck`
was introduced as a hacky patch. Now, almost all code could be written
as `cmd := NewCommand(); cmd.AddXxx(...)`, then there is no need for
`CmdArgCheck` anymore.


### Why many codes for `signArg == ""` is deleted?

Because in the old code, `signArg` could never be empty string, it's
either `-S[key-id]` or `--no-gpg-sign`. So the `signArg == ""` is just
dead code.

---------

Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
2023-02-04 10:30:43 +08:00

556 lines
15 KiB
Go

// Copyright 2019 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package repo
import (
"bytes"
"fmt"
gotemplate "html/template"
"io"
"net/http"
"net/url"
"path"
"strconv"
"strings"
git_model "code.gitea.io/gitea/models/git"
"code.gitea.io/gitea/modules/base"
"code.gitea.io/gitea/modules/charset"
"code.gitea.io/gitea/modules/container"
"code.gitea.io/gitea/modules/context"
"code.gitea.io/gitea/modules/git"
"code.gitea.io/gitea/modules/git/pipeline"
"code.gitea.io/gitea/modules/lfs"
"code.gitea.io/gitea/modules/log"
repo_module "code.gitea.io/gitea/modules/repository"
"code.gitea.io/gitea/modules/setting"
"code.gitea.io/gitea/modules/storage"
"code.gitea.io/gitea/modules/typesniffer"
"code.gitea.io/gitea/modules/util"
)
const (
tplSettingsLFS base.TplName = "repo/settings/lfs"
tplSettingsLFSLocks base.TplName = "repo/settings/lfs_locks"
tplSettingsLFSFile base.TplName = "repo/settings/lfs_file"
tplSettingsLFSFileFind base.TplName = "repo/settings/lfs_file_find"
tplSettingsLFSPointers base.TplName = "repo/settings/lfs_pointers"
)
// LFSFiles shows a repository's LFS files
func LFSFiles(ctx *context.Context) {
if !setting.LFS.StartServer {
ctx.NotFound("LFSFiles", nil)
return
}
page := ctx.FormInt("page")
if page <= 1 {
page = 1
}
total, err := git_model.CountLFSMetaObjects(ctx, ctx.Repo.Repository.ID)
if err != nil {
ctx.ServerError("LFSFiles", err)
return
}
ctx.Data["Total"] = total
pager := context.NewPagination(int(total), setting.UI.ExplorePagingNum, page, 5)
ctx.Data["Title"] = ctx.Tr("repo.settings.lfs")
ctx.Data["PageIsSettingsLFS"] = true
lfsMetaObjects, err := git_model.GetLFSMetaObjects(ctx, ctx.Repo.Repository.ID, pager.Paginater.Current(), setting.UI.ExplorePagingNum)
if err != nil {
ctx.ServerError("LFSFiles", err)
return
}
ctx.Data["LFSFiles"] = lfsMetaObjects
ctx.Data["Page"] = pager
ctx.HTML(http.StatusOK, tplSettingsLFS)
}
// LFSLocks shows a repository's LFS locks
func LFSLocks(ctx *context.Context) {
if !setting.LFS.StartServer {
ctx.NotFound("LFSLocks", nil)
return
}
ctx.Data["LFSFilesLink"] = ctx.Repo.RepoLink + "/settings/lfs"
page := ctx.FormInt("page")
if page <= 1 {
page = 1
}
total, err := git_model.CountLFSLockByRepoID(ctx, ctx.Repo.Repository.ID)
if err != nil {
ctx.ServerError("LFSLocks", err)
return
}
ctx.Data["Total"] = total
pager := context.NewPagination(int(total), setting.UI.ExplorePagingNum, page, 5)
ctx.Data["Title"] = ctx.Tr("repo.settings.lfs_locks")
ctx.Data["PageIsSettingsLFS"] = true
lfsLocks, err := git_model.GetLFSLockByRepoID(ctx, ctx.Repo.Repository.ID, pager.Paginater.Current(), setting.UI.ExplorePagingNum)
if err != nil {
ctx.ServerError("LFSLocks", err)
return
}
ctx.Data["LFSLocks"] = lfsLocks
if len(lfsLocks) == 0 {
ctx.Data["Page"] = pager
ctx.HTML(http.StatusOK, tplSettingsLFSLocks)
return
}
// Clone base repo.
tmpBasePath, err := repo_module.CreateTemporaryPath("locks")
if err != nil {
log.Error("Failed to create temporary path: %v", err)
ctx.ServerError("LFSLocks", err)
return
}
defer func() {
if err := repo_module.RemoveTemporaryPath(tmpBasePath); err != nil {
log.Error("LFSLocks: RemoveTemporaryPath: %v", err)
}
}()
if err := git.Clone(ctx, ctx.Repo.Repository.RepoPath(), tmpBasePath, git.CloneRepoOptions{
Bare: true,
Shared: true,
}); err != nil {
log.Error("Failed to clone repository: %s (%v)", ctx.Repo.Repository.FullName(), err)
ctx.ServerError("LFSLocks", fmt.Errorf("failed to clone repository: %s (%w)", ctx.Repo.Repository.FullName(), err))
return
}
gitRepo, err := git.OpenRepository(ctx, tmpBasePath)
if err != nil {
log.Error("Unable to open temporary repository: %s (%v)", tmpBasePath, err)
ctx.ServerError("LFSLocks", fmt.Errorf("failed to open new temporary repository in: %s %w", tmpBasePath, err))
return
}
defer gitRepo.Close()
filenames := make([]string, len(lfsLocks))
for i, lock := range lfsLocks {
filenames[i] = lock.Path
}
if err := gitRepo.ReadTreeToIndex(ctx.Repo.Repository.DefaultBranch); err != nil {
log.Error("Unable to read the default branch to the index: %s (%v)", ctx.Repo.Repository.DefaultBranch, err)
ctx.ServerError("LFSLocks", fmt.Errorf("unable to read the default branch to the index: %s (%w)", ctx.Repo.Repository.DefaultBranch, err))
return
}
name2attribute2info, err := gitRepo.CheckAttribute(git.CheckAttributeOpts{
Attributes: []string{"lockable"},
Filenames: filenames,
CachedOnly: true,
})
if err != nil {
log.Error("Unable to check attributes in %s (%v)", tmpBasePath, err)
ctx.ServerError("LFSLocks", err)
return
}
lockables := make([]bool, len(lfsLocks))
for i, lock := range lfsLocks {
attribute2info, has := name2attribute2info[lock.Path]
if !has {
continue
}
if attribute2info["lockable"] != "set" {
continue
}
lockables[i] = true
}
ctx.Data["Lockables"] = lockables
filelist, err := gitRepo.LsFiles(filenames...)
if err != nil {
log.Error("Unable to lsfiles in %s (%v)", tmpBasePath, err)
ctx.ServerError("LFSLocks", err)
return
}
fileset := make(container.Set[string], len(filelist))
fileset.AddMultiple(filelist...)
linkable := make([]bool, len(lfsLocks))
for i, lock := range lfsLocks {
linkable[i] = fileset.Contains(lock.Path)
}
ctx.Data["Linkable"] = linkable
ctx.Data["Page"] = pager
ctx.HTML(http.StatusOK, tplSettingsLFSLocks)
}
// LFSLockFile locks a file
func LFSLockFile(ctx *context.Context) {
if !setting.LFS.StartServer {
ctx.NotFound("LFSLocks", nil)
return
}
originalPath := ctx.FormString("path")
lockPath := originalPath
if len(lockPath) == 0 {
ctx.Flash.Error(ctx.Tr("repo.settings.lfs_invalid_locking_path", originalPath))
ctx.Redirect(ctx.Repo.RepoLink + "/settings/lfs/locks")
return
}
if lockPath[len(lockPath)-1] == '/' {
ctx.Flash.Error(ctx.Tr("repo.settings.lfs_invalid_lock_directory", originalPath))
ctx.Redirect(ctx.Repo.RepoLink + "/settings/lfs/locks")
return
}
lockPath = path.Clean("/" + lockPath)[1:]
if len(lockPath) == 0 {
ctx.Flash.Error(ctx.Tr("repo.settings.lfs_invalid_locking_path", originalPath))
ctx.Redirect(ctx.Repo.RepoLink + "/settings/lfs/locks")
return
}
_, err := git_model.CreateLFSLock(ctx, ctx.Repo.Repository, &git_model.LFSLock{
Path: lockPath,
OwnerID: ctx.Doer.ID,
})
if err != nil {
if git_model.IsErrLFSLockAlreadyExist(err) {
ctx.Flash.Error(ctx.Tr("repo.settings.lfs_lock_already_exists", originalPath))
ctx.Redirect(ctx.Repo.RepoLink + "/settings/lfs/locks")
return
}
ctx.ServerError("LFSLockFile", err)
return
}
ctx.Redirect(ctx.Repo.RepoLink + "/settings/lfs/locks")
}
// LFSUnlock forcibly unlocks an LFS lock
func LFSUnlock(ctx *context.Context) {
if !setting.LFS.StartServer {
ctx.NotFound("LFSUnlock", nil)
return
}
_, err := git_model.DeleteLFSLockByID(ctx, ctx.ParamsInt64("lid"), ctx.Repo.Repository, ctx.Doer, true)
if err != nil {
ctx.ServerError("LFSUnlock", err)
return
}
ctx.Redirect(ctx.Repo.RepoLink + "/settings/lfs/locks")
}
// LFSFileGet serves a single LFS file
func LFSFileGet(ctx *context.Context) {
if !setting.LFS.StartServer {
ctx.NotFound("LFSFileGet", nil)
return
}
ctx.Data["LFSFilesLink"] = ctx.Repo.RepoLink + "/settings/lfs"
oid := ctx.Params("oid")
p := lfs.Pointer{Oid: oid}
if !p.IsValid() {
ctx.NotFound("LFSFileGet", nil)
return
}
ctx.Data["Title"] = oid
ctx.Data["PageIsSettingsLFS"] = true
meta, err := git_model.GetLFSMetaObjectByOid(ctx, ctx.Repo.Repository.ID, oid)
if err != nil {
if err == git_model.ErrLFSObjectNotExist {
ctx.NotFound("LFSFileGet", nil)
return
}
ctx.ServerError("LFSFileGet", err)
return
}
ctx.Data["LFSFile"] = meta
dataRc, err := lfs.ReadMetaObject(meta.Pointer)
if err != nil {
ctx.ServerError("LFSFileGet", err)
return
}
defer dataRc.Close()
buf := make([]byte, 1024)
n, err := util.ReadAtMost(dataRc, buf)
if err != nil {
ctx.ServerError("Data", err)
return
}
buf = buf[:n]
st := typesniffer.DetectContentType(buf)
ctx.Data["IsTextFile"] = st.IsText()
isRepresentableAsText := st.IsRepresentableAsText()
fileSize := meta.Size
ctx.Data["FileSize"] = meta.Size
ctx.Data["RawFileLink"] = fmt.Sprintf("%s%s/%s.git/info/lfs/objects/%s/%s", setting.AppURL, url.PathEscape(ctx.Repo.Repository.OwnerName), url.PathEscape(ctx.Repo.Repository.Name), url.PathEscape(meta.Oid), "direct")
switch {
case isRepresentableAsText:
if st.IsSvgImage() {
ctx.Data["IsImageFile"] = true
}
if fileSize >= setting.UI.MaxDisplayFileSize {
ctx.Data["IsFileTooLarge"] = true
break
}
rd := charset.ToUTF8WithFallbackReader(io.MultiReader(bytes.NewReader(buf), dataRc))
// Building code view blocks with line number on server side.
escapedContent := &bytes.Buffer{}
ctx.Data["EscapeStatus"], _ = charset.EscapeControlReader(rd, escapedContent, ctx.Locale)
var output bytes.Buffer
lines := strings.Split(escapedContent.String(), "\n")
// Remove blank line at the end of file
if len(lines) > 0 && lines[len(lines)-1] == "" {
lines = lines[:len(lines)-1]
}
for index, line := range lines {
line = gotemplate.HTMLEscapeString(line)
if index != len(lines)-1 {
line += "\n"
}
output.WriteString(fmt.Sprintf(`<li class="L%d" rel="L%d">%s</li>`, index+1, index+1, line))
}
ctx.Data["FileContent"] = gotemplate.HTML(output.String())
output.Reset()
for i := 0; i < len(lines); i++ {
output.WriteString(fmt.Sprintf(`<span id="L%d">%d</span>`, i+1, i+1))
}
ctx.Data["LineNums"] = gotemplate.HTML(output.String())
case st.IsPDF():
ctx.Data["IsPDFFile"] = true
case st.IsVideo():
ctx.Data["IsVideoFile"] = true
case st.IsAudio():
ctx.Data["IsAudioFile"] = true
case st.IsImage() && (setting.UI.SVG.Enabled || !st.IsSvgImage()):
ctx.Data["IsImageFile"] = true
}
ctx.HTML(http.StatusOK, tplSettingsLFSFile)
}
// LFSDelete disassociates the provided oid from the repository and if the lfs file is no longer associated with any repositories - deletes it
func LFSDelete(ctx *context.Context) {
if !setting.LFS.StartServer {
ctx.NotFound("LFSDelete", nil)
return
}
oid := ctx.Params("oid")
p := lfs.Pointer{Oid: oid}
if !p.IsValid() {
ctx.NotFound("LFSDelete", nil)
return
}
count, err := git_model.RemoveLFSMetaObjectByOid(ctx, ctx.Repo.Repository.ID, oid)
if err != nil {
ctx.ServerError("LFSDelete", err)
return
}
// FIXME: Warning: the LFS store is not locked - and can't be locked - there could be a race condition here
// Please note a similar condition happens in models/repo.go DeleteRepository
if count == 0 {
oidPath := path.Join(oid[0:2], oid[2:4], oid[4:])
err = storage.LFS.Delete(oidPath)
if err != nil {
ctx.ServerError("LFSDelete", err)
return
}
}
ctx.Redirect(ctx.Repo.RepoLink + "/settings/lfs")
}
// LFSFileFind guesses a sha for the provided oid (or uses the provided sha) and then finds the commits that contain this sha
func LFSFileFind(ctx *context.Context) {
if !setting.LFS.StartServer {
ctx.NotFound("LFSFind", nil)
return
}
oid := ctx.FormString("oid")
size := ctx.FormInt64("size")
if len(oid) == 0 || size == 0 {
ctx.NotFound("LFSFind", nil)
return
}
sha := ctx.FormString("sha")
ctx.Data["Title"] = oid
ctx.Data["PageIsSettingsLFS"] = true
var hash git.SHA1
if len(sha) == 0 {
pointer := lfs.Pointer{Oid: oid, Size: size}
hash = git.ComputeBlobHash([]byte(pointer.StringContent()))
sha = hash.String()
} else {
hash = git.MustIDFromString(sha)
}
ctx.Data["LFSFilesLink"] = ctx.Repo.RepoLink + "/settings/lfs"
ctx.Data["Oid"] = oid
ctx.Data["Size"] = size
ctx.Data["SHA"] = sha
results, err := pipeline.FindLFSFile(ctx.Repo.GitRepo, hash)
if err != nil && err != io.EOF {
log.Error("Failure in FindLFSFile: %v", err)
ctx.ServerError("LFSFind: FindLFSFile.", err)
return
}
ctx.Data["Results"] = results
ctx.HTML(http.StatusOK, tplSettingsLFSFileFind)
}
// LFSPointerFiles will search the repository for pointer files and report which are missing LFS files in the content store
func LFSPointerFiles(ctx *context.Context) {
if !setting.LFS.StartServer {
ctx.NotFound("LFSFileGet", nil)
return
}
ctx.Data["PageIsSettingsLFS"] = true
ctx.Data["LFSFilesLink"] = ctx.Repo.RepoLink + "/settings/lfs"
var err error
err = func() error {
pointerChan := make(chan lfs.PointerBlob)
errChan := make(chan error, 1)
go lfs.SearchPointerBlobs(ctx, ctx.Repo.GitRepo, pointerChan, errChan)
numPointers := 0
var numAssociated, numNoExist, numAssociatable int
type pointerResult struct {
SHA string
Oid string
Size int64
InRepo bool
Exists bool
Accessible bool
Associatable bool
}
results := []pointerResult{}
contentStore := lfs.NewContentStore()
repo := ctx.Repo.Repository
for pointerBlob := range pointerChan {
numPointers++
result := pointerResult{
SHA: pointerBlob.Hash,
Oid: pointerBlob.Oid,
Size: pointerBlob.Size,
}
if _, err := git_model.GetLFSMetaObjectByOid(ctx, repo.ID, pointerBlob.Oid); err != nil {
if err != git_model.ErrLFSObjectNotExist {
return err
}
} else {
result.InRepo = true
}
result.Exists, err = contentStore.Exists(pointerBlob.Pointer)
if err != nil {
return err
}
if result.Exists {
if !result.InRepo {
// Can we fix?
// OK well that's "simple"
// - we need to check whether current user has access to a repo that has access to the file
result.Associatable, err = git_model.LFSObjectAccessible(ctx, ctx.Doer, pointerBlob.Oid)
if err != nil {
return err
}
if !result.Associatable {
associated, err := git_model.ExistsLFSObject(ctx, pointerBlob.Oid)
if err != nil {
return err
}
result.Associatable = !associated
}
}
}
result.Accessible = result.InRepo || result.Associatable
if result.InRepo {
numAssociated++
}
if !result.Exists {
numNoExist++
}
if result.Associatable {
numAssociatable++
}
results = append(results, result)
}
err, has := <-errChan
if has {
return err
}
ctx.Data["Pointers"] = results
ctx.Data["NumPointers"] = numPointers
ctx.Data["NumAssociated"] = numAssociated
ctx.Data["NumAssociatable"] = numAssociatable
ctx.Data["NumNoExist"] = numNoExist
ctx.Data["NumNotAssociated"] = numPointers - numAssociated
return nil
}()
if err != nil {
ctx.ServerError("LFSPointerFiles", err)
return
}
ctx.HTML(http.StatusOK, tplSettingsLFSPointers)
}
// LFSAutoAssociate auto associates accessible lfs files
func LFSAutoAssociate(ctx *context.Context) {
if !setting.LFS.StartServer {
ctx.NotFound("LFSAutoAssociate", nil)
return
}
oids := ctx.FormStrings("oid")
metas := make([]*git_model.LFSMetaObject, len(oids))
for i, oid := range oids {
idx := strings.IndexRune(oid, ' ')
if idx < 0 || idx+1 > len(oid) {
ctx.ServerError("LFSAutoAssociate", fmt.Errorf("illegal oid input: %s", oid))
return
}
var err error
metas[i] = &git_model.LFSMetaObject{}
metas[i].Size, err = strconv.ParseInt(oid[idx+1:], 10, 64)
if err != nil {
ctx.ServerError("LFSAutoAssociate", fmt.Errorf("illegal oid input: %s %w", oid, err))
return
}
metas[i].Oid = oid[:idx]
// metas[i].RepositoryID = ctx.Repo.Repository.ID
}
if err := git_model.LFSAutoAssociate(ctx, metas, ctx.Doer, ctx.Repo.Repository.ID); err != nil {
ctx.ServerError("LFSAutoAssociate", err)
return
}
ctx.Redirect(ctx.Repo.RepoLink + "/settings/lfs")
}