forked from gitea/gitea
1
0
Fork 0
gitea/modules/git/repo_stats.go

148 lines
3.8 KiB
Go
Raw Normal View History

// Copyright 2019 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package git
import (
"bufio"
"context"
"fmt"
"os"
"sort"
"strconv"
"strings"
"time"
"code.gitea.io/gitea/modules/container"
)
// CodeActivityStats represents git statistics data
type CodeActivityStats struct {
AuthorCount int64
CommitCount int64
ChangedFiles int64
Additions int64
Deletions int64
CommitCountInAllBranches int64
Authors []*CodeActivityAuthor
}
// CodeActivityAuthor represents git statistics data for commit authors
type CodeActivityAuthor struct {
Name string
Email string
Commits int64
}
// GetCodeActivityStats returns code statistics for activity page
func (repo *Repository) GetCodeActivityStats(fromTime time.Time, branch string) (*CodeActivityStats, error) {
stats := &CodeActivityStats{}
since := fromTime.Format(time.RFC3339)
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
stdout, _, runErr := NewCommand(repo.Ctx, "rev-list", "--count", "--no-merges", "--branches=*", "--date=iso").AddOptionFormat("--since='%s'", since).RunStdString(&RunOpts{Dir: repo.Path})
if runErr != nil {
return nil, runErr
}
c, err := strconv.ParseInt(strings.TrimSpace(stdout), 10, 64)
if err != nil {
return nil, err
}
stats.CommitCountInAllBranches = c
stdoutReader, stdoutWriter, err := os.Pipe()
if err != nil {
return nil, err
}
defer func() {
_ = stdoutReader.Close()
_ = stdoutWriter.Close()
}()
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
gitCmd := NewCommand(repo.Ctx, "log", "--numstat", "--no-merges", "--pretty=format:---%n%h%n%aN%n%aE%n", "--date=iso").AddOptionFormat("--since='%s'", since)
if len(branch) == 0 {
gitCmd.AddArguments("--branches=*")
} else {
gitCmd.AddArguments("--first-parent").AddDynamicArguments(branch)
}
stderr := new(strings.Builder)
err = gitCmd.Run(&RunOpts{
Env: []string{},
Dir: repo.Path,
Stdout: stdoutWriter,
Stderr: stderr,
PipelineFunc: func(ctx context.Context, cancel context.CancelFunc) error {
_ = stdoutWriter.Close()
scanner := bufio.NewScanner(stdoutReader)
scanner.Split(bufio.ScanLines)
stats.CommitCount = 0
stats.Additions = 0
stats.Deletions = 0
authors := make(map[string]*CodeActivityAuthor)
files := make(container.Set[string])
var author string
p := 0
for scanner.Scan() {
l := strings.TrimSpace(scanner.Text())
if l == "---" {
p = 1
} else if p == 0 {
continue
} else {
p++
}
if p > 4 && len(l) == 0 {
continue
}
switch p {
case 1: // Separator
case 2: // Commit sha-1
stats.CommitCount++
case 3: // Author
author = l
case 4: // E-mail
email := strings.ToLower(l)
if _, ok := authors[email]; !ok {
authors[email] = &CodeActivityAuthor{Name: author, Email: email, Commits: 0}
}
authors[email].Commits++
default: // Changed file
if parts := strings.Fields(l); len(parts) >= 3 {
if parts[0] != "-" {
if c, err := strconv.ParseInt(strings.TrimSpace(parts[0]), 10, 64); err == nil {
stats.Additions += c
}
}
if parts[1] != "-" {
if c, err := strconv.ParseInt(strings.TrimSpace(parts[1]), 10, 64); err == nil {
stats.Deletions += c
}
}
files.Add(parts[2])
}
}
}
a := make([]*CodeActivityAuthor, 0, len(authors))
for _, v := range authors {
a = append(a, v)
}
// Sort authors descending depending on commit count
sort.Slice(a, func(i, j int) bool {
return a[i].Commits > a[j].Commits
})
stats.AuthorCount = int64(len(authors))
stats.ChangedFiles = int64(len(files))
stats.Authors = a
_ = stdoutReader.Close()
return nil
},
})
if err != nil {
return nil, fmt.Errorf("Failed to get GetCodeActivityStats for repository.\nError: %w\nStderr: %s", err, stderr)
}
return stats, nil
}