首页 > 解决方案 > Dulwich 备忘单:如何重现“git ls-files”?

问题描述

亲爱的社区成员,

我正在开发一个代码分析系统,并想用 Dulwich 模块替换对 CLI Git 应用程序的调用。作为第一步,我需要将“git ls-files”命令替换为 Dulwich 等效命令。我是通过以下方式做到的:

import os
import stat
import subprocess
from tempfile import TemporaryDirectory

from dulwich import porcelain
from dulwich.repo import Repo
from dulwich.objects import Commit, Tree

def _flatten_git_tree(r, object_sha, prefix=b'', sep=b'/'):

    result=[]

    git_object=r.get_object(object_sha)

    if git_object.type_name==b'tree':

        for item in git_object.iteritems():
            if stat.S_ISREG(item.mode):
                result.append(sep.join([prefix, item.path]))
            if stat.S_ISDIR(item.mode):
                result.extend(_flatten_git_tree(r, item.sha, prefix+sep+item.path, sep))

    if git_object.type_name==b'commit':

        result.extend(_flatten_git_tree(r, git_object.tree, prefix, sep))

    return result

def _run_git_cmd(git_arguments):

    return subprocess.Popen(git_arguments, stdout=subprocess.PIPE).communicate()[0]

with TemporaryDirectory() as temp_dir:

    git_clone_url=r"https://github.com/dulwich/dulwich.git"
    repo=porcelain.clone(git_clone_url, temp_dir, checkout=True)
    dulwich_ls_files=_flatten_git_tree(repo, repo.head())

    git_ls_files=_run_git_cmd(['git', '-C', os.path.join(temp_dir, 'dulwich'), 'ls-files'])
    git_ls_files=git_ls_files.decode('utf-8').splitlines()

assert len(dulwich_ls_files)==len(git_ls_files)

快速断言显示输出不同。可能是什么原因?

在@jelmer 的帮助下回答我自己的问题。问题的原因在于我评论的那一行。现在输出匹配。

import os
import subprocess
from tempfile import TemporaryDirectory

from dulwich import porcelain
from dulwich.repo import Repo

def _run_git_cmd(git_arguments):

    return subprocess.Popen(git_arguments, stdout=subprocess.PIPE).communicate()[0]

with TemporaryDirectory() as temp_dir:

    git_clone_url=r"https://github.com/dulwich/dulwich.git"
    repo=porcelain.clone(git_clone_url, temp_dir)
    dulwich_ls_files=[path.decode('utf-8') for path in sorted(repo.open_index())]

    #git_ls_files=_run_git_cmd(['git', '-C', os.path.join(temp_dir, 'dulwich'), 'ls-files'])
    git_ls_files=_run_git_cmd(['git', '-C', temp_dir, 'ls-files'])
    git_ls_files=git_ls_files.decode('utf-8').splitlines()

print(len(dulwich_ls_files), len(git_ls_files))

标签: pythongitdulwichgit-ls-files

解决方案


像这样的东西:

from dulwich.repo import Repo
r = Repo('.')
index = r.open_index()
for path in sorted(index):
    print(path)

推荐阅读