【Python】快速判断两个commit 是否存在cherry-pick 关系

判断两个提交是否有 cherry-pick 关系的 Python 脚本，可以基于以下三种常见情况进行优化：

Commit Hash 一致：如果两个提交的 hash 完全相同，那么它们是相同的提交。
Commit Title 存在关联：如果两个提交的 commit message 提及了相同的原始提交，例如 cherry picked from commit <hash>，可以通过解析提交信息来确定关联。
Commit 变更内容一致：即使 hash 和 title 不同，如果两个提交的代码变更完全一致，则可能是 cherry-pick 关系。

另外，还有可能存在其他场景，比如提交的父节点不同，但内容一致，这也是一种 cherry-pick 的表现。

基于以上情况，下面是一个优化的 Python 脚本：

Python 脚本

V1版本

import subprocess
import redef run_git_command(args):"""运行 Git 命令并返回输出结果。"""try:result = subprocess.run(args, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)if result.returncode != 0:print(f"Error running command {args}: {result.stderr}")return Nonereturn result.stdout.strip()except Exception as e:print(f"An error occurred: {e}")return Nonedef get_commit_message(commit_hash):"""获取提交信息（commit message）。"""return run_git_command(["git", "log", "-1", "--pretty=%B", commit_hash])def get_diff(commit_hash):"""获取提交的代码差异（diff）。"""return run_git_command(["git", "diff-tree", "--no-commit-id", "--patch", "-r", commit_hash])def check_cherry_pick_message(commit1_message, commit2_message):"""检查提交信息中是否提到 cherry-pick 的关联。"""cherry_pick_pattern = re.compile(r'cherry\s+picked\s+from\s+commit\s+([a-f0-9]{40})')# 检查第一个提交信息是否提到 cherry-pick 的原始提交match1 = cherry_pick_pattern.search(commit1_message)match2 = cherry_pick_pattern.search(commit2_message)if match1 and match2 and match1.group(1) == match2.group(1):return True# 或者检查一个提交是否提到另一个提交if match1 and match1.group(1) in commit2_message:return Trueif match2 and match2.group(1) in commit1_message:return Truereturn Falsedef compare_commit_diffs(commit1, commit2):"""比较两个提交的代码变更是否一致。"""diff1 = get_diff(commit1)diff2 = get_diff(commit2)if diff1 is None or diff2 is None:return Falsereturn diff1 == diff2def compare_commits(commit1, commit2):"""综合比较两个提交是否有 cherry-pick 关系。"""# 1. 检查 commit hash 是否相同if commit1 == commit2:print(f"Commits {commit1} and {commit2} are identical (same hash).")return True# 2. 检查 commit message 是否提到 cherry-pick 关系commit1_message = get_commit_message(commit1)commit2_message = get_commit_message(commit2)if commit1_message is None or commit2_message is None:print("Failed to get commit messages.")return Falseif check_cherry_pick_message(commit1_message, commit2_message):print(f"Commits {commit1} and {commit2} have a cherry-pick relation based on commit message.")return True# 3. 检查代码变更是否完全一致if compare_commit_diffs(commit1, commit2):print(f"Commits {commit1} and {commit2} have identical code changes (cherry-pick relation likely).")return Trueprint(f"Commits {commit1} and {commit2} do not have a clear cherry-pick relation.")return Falseif __name__ == "__main__":# 输入需要比较的两个 commit hashcommit_hash_1 = input("Enter the first commit hash: ")commit_hash_2 = input("Enter the second commit hash: ")if compare_commits(commit_hash_1, commit_hash_2):print(f"Commits {commit_hash_1} and {commit_hash_2} are related (cherry-pick detected).")else:print(f"Commits {commit_hash_1} and {commit_hash_2} are not related (no cherry-pick detected).")

如果存在编码错误

可以使用下方脚本尝试

V2版本

import subprocess
import redef run_git_command(args):"""运行 Git 命令并返回输出结果。"""try:result = subprocess.run(args, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, encoding='utf-8')if result.returncode != 0:print(f"Error running command {args}: {result.stderr}")return Nonereturn result.stdout.strip()except Exception as e:print(f"An error occurred: {e}")return Nonedef get_commit_message(commit_hash):"""获取提交信息（commit message）。"""return run_git_command(["git", "log", "-1", "--pretty=%B", commit_hash])def get_diff(commit_hash):"""获取提交的代码差异（diff）。"""try:return run_git_command(["git", "diff-tree", "--no-commit-id", "--patch", "-r", commit_hash])except Exception as e:print(f"An error occurred while getting diff for {commit_hash}: {e}")return Nonedef check_cherry_pick_message(commit1_message, commit2_message):"""检查提交信息中是否提到 cherry-pick 的关联。"""cherry_pick_pattern = re.compile(r'cherry\s+picked\s+from\s+commit\s+([a-f0-9]{40})')match1 = cherry_pick_pattern.search(commit1_message)match2 = cherry_pick_pattern.search(commit2_message)if match1 and match2 and match1.group(1) == match2.group(1):return Trueif match1 and match1.group(1) in commit2_message:return Trueif match2 and match2.group(1) in commit1_message:return Truereturn Falsedef compare_commit_diffs(commit1, commit2):"""比较两个提交的代码变更是否一致。"""diff1 = get_diff(commit1)diff2 = get_diff(commit2)if diff1 is None or diff2 is None:return Falsereturn diff1 == diff2def compare_commits(commit1, commit2):"""综合比较两个提交是否有 cherry-pick 关系。"""if commit1 == commit2:print(f"Commits {commit1} and {commit2} are identical (same hash).")return Truecommit1_message = get_commit_message(commit1)commit2_message = get_commit_message(commit2)if commit1_message is None or commit2_message is None:print("Failed to get commit messages.")return Falseif check_cherry_pick_message(commit1_message, commit2_message):print(f"Commits {commit1} and {commit2} have a cherry-pick relation based on commit message.")return Trueif compare_commit_diffs(commit1, commit2):print(f"Commits {commit1} and {commit2} have identical code changes (cherry-pick relation likely).")return Trueprint(f"Commits {commit1} and {commit2} do not have a clear cherry-pick relation.")return Falsedef validate_commit_hash(commit_hash):"""验证提交 hash 是否是有效的 SHA-1 hash。"""if re.fullmatch(r'[a-fA-F0-9]{40}', commit_hash):return Trueelse:print(f"Invalid commit hash: {commit_hash}")return Falseif __name__ == "__main__":commit_hash_1 = input("Enter the first commit hash: ")commit_hash_2 = input("Enter the second commit hash: ")if validate_commit_hash(commit_hash_1) and validate_commit_hash(commit_hash_2):if compare_commits(commit_hash_1, commit_hash_2):print(f"Commits {commit_hash_1} and {commit_hash_2} are related (cherry-pick detected).")else:print(f"Commits {commit_hash_1} and {commit_hash_2} are not related (no cherry-pick detected).")else:print("Please enter valid commit hashes.")

脚本的工作原理

Commit Hash 一致：脚本首先检查两个提交的 hash 是否完全相同。如果相同，它们肯定是相同的提交。
Commit Title 存在关联：通过正则表达式匹配 commit message 中的 cherry picked from commit <hash> 字符串，检查一个提交是否从另一个提交进行了 cherry-pick。如果 commit message 中存在这样的引用，则说明它们有 cherry-pick 关系。