0
Fork 0
mirror of https://codeberg.org/forgejo/forgejo.git synced 2024-12-30 11:23:56 -05:00
forgejo/modules/git/tree_nogogit.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

133 lines
3.1 KiB
Go

// Copyright 2020 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
//go:build !gogit
package git
import (
"io"
"math"
"strings"
)
// Tree represents a flat directory listing.
type Tree struct {
ID SHA1
ResolvedID SHA1
repo *Repository
// parent tree
ptree *Tree
entries Entries
entriesParsed bool
entriesRecursive Entries
entriesRecursiveParsed bool
}
// ListEntries returns all entries of current tree.
func (t *Tree) ListEntries() (Entries, error) {
if t.entriesParsed {
return t.entries, nil
}
if t.repo != nil {
wr, rd, cancel := t.repo.CatFileBatch(t.repo.Ctx)
defer cancel()
_, _ = wr.Write([]byte(t.ID.String() + "\n"))
_, typ, sz, err := ReadBatchLine(rd)
if err != nil {
return nil, err
}
if typ == "commit" {
treeID, err := ReadTreeID(rd, sz)
if err != nil && err != io.EOF {
return nil, err
}
_, _ = wr.Write([]byte(treeID + "\n"))
_, typ, sz, err = ReadBatchLine(rd)
if err != nil {
return nil, err
}
}
if typ == "tree" {
t.entries, err = catBatchParseTreeEntries(t, rd, sz)
if err != nil {
return nil, err
}
t.entriesParsed = true
return t.entries, nil
}
// Not a tree just use ls-tree instead
for sz > math.MaxInt32 {
discarded, err := rd.Discard(math.MaxInt32)
sz -= int64(discarded)
if err != nil {
return nil, err
}
}
for sz > 0 {
discarded, err := rd.Discard(int(sz))
sz -= int64(discarded)
if err != nil {
return nil, err
}
}
}
stdout, _, runErr := NewCommand(t.repo.Ctx, "ls-tree", "-l").AddDynamicArguments(t.ID.String()).RunStdBytes(&RunOpts{Dir: t.repo.Path})
if runErr != nil {
if strings.Contains(runErr.Error(), "fatal: Not a valid object name") || strings.Contains(runErr.Error(), "fatal: not a tree object") {
return nil, ErrNotExist{
ID: t.ID.String(),
}
}
return nil, runErr
}
var err error
t.entries, err = parseTreeEntries(stdout, t)
if err == nil {
t.entriesParsed = true
}
return t.entries, err
}
// listEntriesRecursive returns all entries of current tree recursively including all subtrees
// extraArgs could be "-l" to get the size, which is slower
func (t *Tree) listEntriesRecursive(extraArgs TrustedCmdArgs) (Entries, error) {
if t.entriesRecursiveParsed {
return t.entriesRecursive, nil
}
stdout, _, runErr := NewCommand(t.repo.Ctx, "ls-tree", "-t", "-r").
AddArguments(extraArgs...).
AddDynamicArguments(t.ID.String()).
RunStdBytes(&RunOpts{Dir: t.repo.Path})
if runErr != nil {
return nil, runErr
}
var err error
t.entriesRecursive, err = parseTreeEntries(stdout, t)
if err == nil {
t.entriesRecursiveParsed = true
}
return t.entriesRecursive, err
}
// ListEntriesRecursiveFast returns all entries of current tree recursively including all subtrees, no size
func (t *Tree) ListEntriesRecursiveFast() (Entries, error) {
return t.listEntriesRecursive(nil)
}
// ListEntriesRecursiveWithSize returns all entries of current tree recursively including all subtrees, with size
func (t *Tree) ListEntriesRecursiveWithSize() (Entries, error) {
return t.listEntriesRecursive(TrustedCmdArgs{"--long"})
}