forgejo/modules/gitgraph/graph.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

117 lines
2.7 KiB
Go

// Copyright 2016 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package gitgraph
import (
"bufio"
"bytes"
"context"
"os"
"strings"
"code.gitea.io/gitea/modules/git"
"code.gitea.io/gitea/modules/setting"
)
// GetCommitGraph return a list of commit (GraphItems) from all branches
func GetCommitGraph(r *git.Repository, page, maxAllowedColors int, hidePRRefs bool, branches, files []string) (*Graph, error) {
format := "DATA:%D|%H|%ad|%h|%s"
if page == 0 {
page = 1
}
graphCmd := git.NewCommand(r.Ctx, "log", "--graph", "--date-order", "--decorate=full")
if hidePRRefs {
graphCmd.AddArguments("--exclude=" + git.PullPrefix + "*")
}
if len(branches) == 0 {
graphCmd.AddArguments("--all")
}
graphCmd.AddArguments("-C", "-M", "--date=iso").
AddOptionFormat("-n %d", setting.UI.GraphMaxCommitNum*page).
AddOptionFormat("--pretty=format:%s", format)
if len(branches) > 0 {
graphCmd.AddDynamicArguments(branches...)
}
if len(files) > 0 {
graphCmd.AddDashesAndList(files...)
}
graph := NewGraph()
stderr := new(strings.Builder)
stdoutReader, stdoutWriter, err := os.Pipe()
if err != nil {
return nil, err
}
commitsToSkip := setting.UI.GraphMaxCommitNum * (page - 1)
scanner := bufio.NewScanner(stdoutReader)
if err := graphCmd.Run(&git.RunOpts{
Dir: r.Path,
Stdout: stdoutWriter,
Stderr: stderr,
PipelineFunc: func(ctx context.Context, cancel context.CancelFunc) error {
_ = stdoutWriter.Close()
defer stdoutReader.Close()
parser := &Parser{}
parser.firstInUse = -1
parser.maxAllowedColors = maxAllowedColors
if maxAllowedColors > 0 {
parser.availableColors = make([]int, maxAllowedColors)
for i := range parser.availableColors {
parser.availableColors[i] = i + 1
}
} else {
parser.availableColors = []int{1, 2}
}
for commitsToSkip > 0 && scanner.Scan() {
line := scanner.Bytes()
dataIdx := bytes.Index(line, []byte("DATA:"))
if dataIdx < 0 {
dataIdx = len(line)
}
starIdx := bytes.IndexByte(line, '*')
if starIdx >= 0 && starIdx < dataIdx {
commitsToSkip--
}
parser.ParseGlyphs(line[:dataIdx])
}
row := 0
// Skip initial non-commit lines
for scanner.Scan() {
line := scanner.Bytes()
if bytes.IndexByte(line, '*') >= 0 {
if err := parser.AddLineToGraph(graph, row, line); err != nil {
cancel()
return err
}
break
}
parser.ParseGlyphs(line)
}
for scanner.Scan() {
row++
line := scanner.Bytes()
if err := parser.AddLineToGraph(graph, row, line); err != nil {
cancel()
return err
}
}
return scanner.Err()
},
}); err != nil {
return graph, err
}
return graph, nil
}