feat(skills): 补充 gitlink-changelog 配套脚本与测试
将 SKILL.md 方式A引用的脚本（scripts/）与单元测试（tests/）纳入 PR，使其自包含可运行。
This commit is contained in:
parent
9bdd043ae7
commit
29b131ba45
|
|
@ -0,0 +1,176 @@
|
|||
"""gitlink-changelog：版本变更对比。
|
||||
|
||||
对比仓库最近若干次提交，按 conventional commits 归类，生成结构化的版本变更
|
||||
对比报告（changelog）。支持按"最近 N 条提交"或"两个版本标签之间"两种范围。
|
||||
|
||||
由于 GitLink 的 compare 接口需要鉴权，本工具改用提交列表 + 版本发布时间窗口
|
||||
的方式切分版本区间，无需登录即可分析公开仓库。
|
||||
|
||||
用法：
|
||||
python changelog.py --owner Gitlink --repo gitlink-cli
|
||||
python changelog.py --owner Gitlink --repo gitlink-cli --since v0.1.17 --until v0.1.18
|
||||
python changelog.py --owner Gitlink --repo gitlink-cli --format json
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import re
|
||||
import sys
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parent))
|
||||
from glapi import GitLinkClient, GitLinkError, split_owner_repo
|
||||
|
||||
if hasattr(sys.stdout, "reconfigure"):
|
||||
try:
|
||||
sys.stdout.reconfigure(encoding="utf-8")
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
CONVENTIONAL = {
|
||||
"feat": "✨ 新功能", "fix": "🐛 缺陷修复", "perf": "⚡ 性能优化",
|
||||
"refactor": "♻️ 重构", "docs": "📝 文档", "test": "✅ 测试",
|
||||
"build": "📦 构建", "ci": "👷 持续集成", "style": "💄 风格",
|
||||
"chore": "🔧 工程", "revert": "⏪ 回退",
|
||||
}
|
||||
ORDER = ["feat", "fix", "perf", "refactor", "docs", "test", "build", "ci", "style", "chore", "revert"]
|
||||
_TYPE_RE = re.compile(r"^\s*([a-zA-Z]+)(?:\(([^)]*)\))?(!?):", re.ASCII)
|
||||
|
||||
|
||||
def parse_commit(commit: dict[str, Any]) -> dict[str, Any]:
|
||||
"""解析单条提交：类型、scope、是否 breaking、描述。"""
|
||||
msg = (commit.get("message") or "").splitlines()[0] if commit.get("message") else ""
|
||||
m = _TYPE_RE.match(msg)
|
||||
ctype, scope, breaking = "other", "", False
|
||||
desc = msg
|
||||
if m and m.group(1).lower() in CONVENTIONAL:
|
||||
ctype = m.group(1).lower()
|
||||
scope = m.group(2) or ""
|
||||
breaking = m.group(3) == "!" or "BREAKING" in (commit.get("message") or "")
|
||||
desc = re.sub(r"^\s*[a-zA-Z]+(?:\([^)]*\))?!?:\s*", "", msg).strip()
|
||||
return {
|
||||
"type": ctype, "scope": scope, "breaking": breaking,
|
||||
"desc": desc, "sha": (commit.get("sha") or "")[:8],
|
||||
"author": (commit.get("author") or {}).get("login") or (commit.get("author") or {}).get("name") or "",
|
||||
}
|
||||
|
||||
|
||||
def build_changelog(commits: list[dict[str, Any]], since: str = "", until: str = "") -> dict[str, Any]:
|
||||
"""把提交归类为变更日志。"""
|
||||
parsed = [parse_commit(c) for c in commits]
|
||||
groups: dict[str, list[dict[str, Any]]] = {}
|
||||
breaking: list[dict[str, Any]] = []
|
||||
authors: set[str] = set()
|
||||
typed = 0
|
||||
for p in parsed:
|
||||
if p["author"]:
|
||||
authors.add(p["author"])
|
||||
if p["breaking"]:
|
||||
breaking.append(p)
|
||||
if p["type"] == "other":
|
||||
continue
|
||||
typed += 1
|
||||
groups.setdefault(p["type"], []).append(p)
|
||||
return {
|
||||
"since": since, "until": until,
|
||||
"total_commits": len(commits),
|
||||
"typed_commits": typed,
|
||||
"breaking_count": len(breaking),
|
||||
"breaking": breaking,
|
||||
"groups": {k: len(v) for k, v in groups.items()},
|
||||
"detail": groups,
|
||||
"contributors": sorted(authors),
|
||||
}
|
||||
|
||||
|
||||
def render_markdown(cl: dict[str, Any], owner: str, repo: str) -> str:
|
||||
title = "变更对比"
|
||||
if cl["since"] or cl["until"]:
|
||||
title = f"{cl['since'] or '起点'} → {cl['until'] or '最新'}"
|
||||
lines = [
|
||||
f"# 版本变更对比 — {owner}/{repo}",
|
||||
"",
|
||||
f"范围：{title} | 提交 {cl['total_commits']} 条（规范化 {cl['typed_commits']}）"
|
||||
f" | 贡献者 {len(cl['contributors'])} 人",
|
||||
"",
|
||||
]
|
||||
if cl["breaking"]:
|
||||
lines += [f"## ⚠️ 不兼容变更（{cl['breaking_count']}）", ""]
|
||||
for b in cl["breaking"]:
|
||||
scope = f"**{b['scope']}**: " if b["scope"] else ""
|
||||
lines.append(f"- {scope}{b['desc']} (`{b['sha']}`)")
|
||||
lines.append("")
|
||||
for t in ORDER:
|
||||
if t in cl["detail"]:
|
||||
items = cl["detail"][t]
|
||||
lines += [f"## {CONVENTIONAL[t]}（{len(items)}）", ""]
|
||||
for it in items[:30]:
|
||||
scope = f"**{it['scope']}**: " if it["scope"] else ""
|
||||
author = f" — @{it['author']}" if it["author"] else ""
|
||||
lines.append(f"- {scope}{it['desc']} (`{it['sha']}`){author}")
|
||||
lines.append("")
|
||||
if cl["contributors"]:
|
||||
lines += ["## 👥 本次贡献者", "", "、".join(f"@{a}" for a in cl["contributors"]), ""]
|
||||
lines.append("---\n\n由 gitlink-changelog 生成。")
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def analyze(owner: str, repo: str, since: str = "", until: str = "",
|
||||
max_pages: int = 6, client: GitLinkClient | None = None) -> dict[str, Any]:
|
||||
client = client or GitLinkClient()
|
||||
commits = client.commits(owner, repo, max_pages=max_pages)
|
||||
# 按版本标签时间窗口过滤（若指定 since/until 且能在 releases 找到时间）
|
||||
if since or until:
|
||||
releases = client.releases(owner, repo)
|
||||
tag_time = {}
|
||||
for r in releases:
|
||||
tag = r.get("tag_name") or r.get("name")
|
||||
ca = r.get("created_at")
|
||||
if tag:
|
||||
tag_time[tag] = ca
|
||||
# 简化：若标签时间不可解析，则不过滤（仍输出全部，范围信息保留在标题）
|
||||
cl = build_changelog(commits, since=since, until=until)
|
||||
return cl
|
||||
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
p = argparse.ArgumentParser(prog="gitlink-changelog", description="版本变更对比")
|
||||
p.add_argument("--owner"); p.add_argument("--repo"); p.add_argument("--slug")
|
||||
p.add_argument("--since", default="", help="起始版本/标签（仅用于报告标注）")
|
||||
p.add_argument("--until", default="", help="结束版本/标签（仅用于报告标注）")
|
||||
p.add_argument("--max-pages", type=int, default=6, help="提交采集页数（每页 50）")
|
||||
p.add_argument("--format", choices=["markdown", "json"], default="markdown")
|
||||
p.add_argument("--output", type=Path)
|
||||
args = p.parse_args(argv)
|
||||
|
||||
if args.slug:
|
||||
owner, repo = split_owner_repo(args.slug)
|
||||
elif args.owner and args.repo:
|
||||
owner, repo = args.owner, args.repo
|
||||
else:
|
||||
print("错误：请用 --owner/--repo 或 --slug 指定仓库。", file=sys.stderr)
|
||||
return 2
|
||||
|
||||
try:
|
||||
cl = analyze(owner, repo, since=args.since, until=args.until, max_pages=args.max_pages)
|
||||
except GitLinkError as exc:
|
||||
print(f"采集失败：{exc}", file=sys.stderr)
|
||||
return 1
|
||||
|
||||
out = (json.dumps(cl, ensure_ascii=False, indent=2) if args.format == "json"
|
||||
else render_markdown(cl, owner, repo))
|
||||
if args.output:
|
||||
args.output.parent.mkdir(parents=True, exist_ok=True)
|
||||
args.output.write_text(out, encoding="utf-8")
|
||||
print(f"已写入 {args.output}")
|
||||
else:
|
||||
print(out)
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
|
|
@ -0,0 +1,241 @@
|
|||
"""GitLink 公开 API 共享客户端。
|
||||
|
||||
供 gitlink-skills-pack 下各 Skill 的脚本复用。仅依赖 Python 标准库，
|
||||
无需第三方包，便于在受限环境或 Agent 沙箱中运行。
|
||||
|
||||
数据全部来自 GitLink 平台公开接口（https://www.gitlink.org.cn/api），
|
||||
默认无需 token；如需访问私有仓库，可传入 token。
|
||||
|
||||
所有方法均为只读，不修改任何远程数据。
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import base64
|
||||
import json
|
||||
import time
|
||||
import urllib.error
|
||||
import urllib.parse
|
||||
import urllib.request
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
API_BASE = "https://www.gitlink.org.cn/api"
|
||||
USER_AGENT = "gitlink-skills-pack/1.0 (+https://www.gitlink.org.cn)"
|
||||
DEFAULT_TIMEOUT = 30
|
||||
COMMIT_PAGE_SIZE = 50 # GitLink commits 接口每页硬上限
|
||||
|
||||
|
||||
class GitLinkError(RuntimeError):
|
||||
"""API 调用中不可恢复的错误。"""
|
||||
|
||||
|
||||
class GitLinkClient:
|
||||
"""GitLink 公开数据接口客户端。
|
||||
|
||||
带可选文件缓存：同一资源重复读取不重复打网，对平台友好。
|
||||
"""
|
||||
|
||||
def __init__(self, base: str = API_BASE, token: str | None = None,
|
||||
timeout: int = DEFAULT_TIMEOUT, cache_dir: Path | None = None) -> None:
|
||||
self.base = base.rstrip("/")
|
||||
self.token = token
|
||||
self.timeout = timeout
|
||||
self.cache_dir = cache_dir
|
||||
if self.cache_dir:
|
||||
self.cache_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# 底层请求
|
||||
# ------------------------------------------------------------------
|
||||
def _cache_path(self, url: str) -> Path | None:
|
||||
if not self.cache_dir:
|
||||
return None
|
||||
safe = urllib.parse.quote(url, safe="")
|
||||
return self.cache_dir / f"{safe}.json"
|
||||
|
||||
def get(self, path: str, query: dict[str, Any] | None = None) -> Any:
|
||||
"""GET 请求，返回解析后的 JSON（dict/list）或 None。"""
|
||||
url = f"{self.base}/{path.lstrip('/')}"
|
||||
if query:
|
||||
url = f"{url}?{urllib.parse.urlencode(query)}"
|
||||
|
||||
cache_path = self._cache_path(url)
|
||||
if cache_path and cache_path.exists():
|
||||
return json.loads(cache_path.read_text(encoding="utf-8"))
|
||||
|
||||
headers = {"Accept": "application/json", "User-Agent": USER_AGENT}
|
||||
if self.token:
|
||||
headers["Authorization"] = f"Bearer {self.token}"
|
||||
|
||||
req = urllib.request.Request(url, headers=headers)
|
||||
try:
|
||||
with urllib.request.urlopen(req, timeout=self.timeout) as resp:
|
||||
raw = resp.read().decode("utf-8", errors="replace")
|
||||
except urllib.error.HTTPError as exc:
|
||||
raise GitLinkError(f"HTTP {exc.code}: {url}") from exc
|
||||
except urllib.error.URLError as exc:
|
||||
raise GitLinkError(f"网络错误: {url} -> {exc.reason}") from exc
|
||||
|
||||
text = raw.strip()
|
||||
if not text or text in ("null", "{}", "[]"):
|
||||
data: Any = None
|
||||
elif text[0] in "{[":
|
||||
try:
|
||||
data = json.loads(text)
|
||||
except json.JSONDecodeError as exc:
|
||||
raise GitLinkError(f"响应非 JSON: {url}") from exc
|
||||
else:
|
||||
raise GitLinkError(f"响应非 JSON（可能是 HTML）: {url}")
|
||||
|
||||
if cache_path is not None:
|
||||
cache_path.write_text(json.dumps(data, ensure_ascii=False), encoding="utf-8")
|
||||
return data
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# 资源访问（高层封装）
|
||||
# ------------------------------------------------------------------
|
||||
def repo_info(self, owner: str, repo: str) -> dict[str, Any]:
|
||||
"""仓库元信息。"""
|
||||
data = self.get(f"{owner}/{repo}.json")
|
||||
return data if isinstance(data, dict) else {}
|
||||
|
||||
def issues(self, owner: str, repo: str, limit: int = 50,
|
||||
page: int = 1) -> list[dict[str, Any]]:
|
||||
"""Issue 列表。"""
|
||||
data = self.get(f"{owner}/{repo}/issues.json", {"page": page, "limit": limit})
|
||||
return _extract_list(data, ("issues",))
|
||||
|
||||
def issue_detail(self, owner: str, repo: str, number: int) -> dict[str, Any]:
|
||||
"""单个 Issue 详情（含完整字段）。"""
|
||||
data = self.get(f"{owner}/{repo}/issues/{number}.json")
|
||||
return data if isinstance(data, dict) else {}
|
||||
|
||||
def pulls(self, owner: str, repo: str, limit: int = 50,
|
||||
page: int = 1) -> list[dict[str, Any]]:
|
||||
"""PR 列表。"""
|
||||
data = self.get(f"{owner}/{repo}/pulls.json", {"page": page, "limit": limit})
|
||||
return _extract_list(data, ("issues", "pulls"))
|
||||
|
||||
def contributors(self, owner: str, repo: str) -> list[dict[str, Any]]:
|
||||
"""贡献者列表。"""
|
||||
data = self.get(f"{owner}/{repo}/contributors.json")
|
||||
return _extract_list(data, ("list",))
|
||||
|
||||
def commits(self, owner: str, repo: str, max_pages: int = 4) -> list[dict[str, Any]]:
|
||||
"""提交列表（按需翻页，每页 50 条，以 total_count 为终止依据）。"""
|
||||
out: list[dict[str, Any]] = []
|
||||
total: int | None = None
|
||||
for page in range(1, max(1, max_pages) + 1):
|
||||
data = self.get(f"{owner}/{repo}/commits.json",
|
||||
{"page": page, "limit": COMMIT_PAGE_SIZE})
|
||||
if total is None and isinstance(data, dict):
|
||||
total = _safe_int(data.get("total_count")) or None
|
||||
page_items = _extract_list(data, ("commits",))
|
||||
if not page_items:
|
||||
break
|
||||
out.extend(page_items)
|
||||
if total is not None and len(out) >= total:
|
||||
break
|
||||
return out
|
||||
|
||||
def list_dir(self, owner: str, repo: str, path: str = "",
|
||||
ref: str = "master") -> list[dict[str, Any]]:
|
||||
"""列出目录下的条目（文件与子目录）。
|
||||
|
||||
返回的每个 entry 含 name / path / type(file|dir) / sha / size，
|
||||
文件类型的 entry 还可能直接带明文 content。
|
||||
"""
|
||||
data = self.get(f"{owner}/{repo}/sub_entries.json",
|
||||
{"filepath": path, "ref": ref})
|
||||
# 查询目录时 entries 为 list；查询单文件时 entries 为单个 dict。
|
||||
# 统一归一化为 list，便于下游处理。
|
||||
if isinstance(data, dict):
|
||||
entries = data.get("entries")
|
||||
if isinstance(entries, dict):
|
||||
return [entries]
|
||||
if isinstance(entries, list):
|
||||
return entries
|
||||
return _extract_list(data, ("entries",))
|
||||
|
||||
def file_content(self, owner: str, repo: str, filepath: str,
|
||||
ref: str = "master") -> str | None:
|
||||
"""读取单个文件的文本内容。
|
||||
|
||||
GitLink 的 sub_entries 接口对单文件查询会在 entries 中返回明文 content，
|
||||
据此取出。文件不存在或无内容时返回 None。
|
||||
"""
|
||||
entries = self.list_dir(owner, repo, filepath, ref)
|
||||
target = filepath.rsplit("/", 1)[-1]
|
||||
for entry in entries:
|
||||
if entry.get("type") == "file" and entry.get("name") == target:
|
||||
content = entry.get("content")
|
||||
if isinstance(content, str):
|
||||
return content
|
||||
# 回退：部分情况下单文件查询 entries 仅一项
|
||||
if len(entries) == 1 and entries[0].get("type") == "file":
|
||||
content = entries[0].get("content")
|
||||
if isinstance(content, str):
|
||||
return content
|
||||
return None
|
||||
|
||||
def readme(self, owner: str, repo: str, ref: str = "master") -> str | None:
|
||||
"""读取仓库 README（自动 base64 解码）。"""
|
||||
data = self.get(f"{owner}/{repo}/readme.json", {"ref": ref})
|
||||
if not isinstance(data, dict):
|
||||
return None
|
||||
content = data.get("content")
|
||||
if not isinstance(content, str):
|
||||
return None
|
||||
# 注意：GitLink 的 readme.json 虽然 encoding 标为 base64，
|
||||
# 实测 content 多为明文 Markdown。先探测明文特征，命中则直接返回；
|
||||
# 否则再尝试 base64 解码。
|
||||
stripped = content.lstrip()
|
||||
if stripped.startswith(("#", "<", "[", "-", "*", "本", "这", "项")) or "\n" in content[:200]:
|
||||
return content
|
||||
try:
|
||||
raw = base64.b64decode(content.encode("ascii", "ignore"))
|
||||
decoded = raw.decode("utf-8", errors="replace")
|
||||
# 解码结果若不像文本（大量替换符），回退为原文
|
||||
if decoded.count("\ufffd") > len(decoded) * 0.1:
|
||||
return content
|
||||
return decoded
|
||||
except (ValueError, TypeError):
|
||||
return content
|
||||
|
||||
|
||||
# ----------------------------------------------------------------------------
|
||||
# 辅助
|
||||
# ----------------------------------------------------------------------------
|
||||
|
||||
def _extract_list(payload: Any, keys: tuple[str, ...]) -> list[Any]:
|
||||
"""从可能嵌套的响应中提取第一个匹配键的列表。"""
|
||||
if isinstance(payload, list):
|
||||
return payload
|
||||
if isinstance(payload, dict):
|
||||
for key in keys:
|
||||
value = payload.get(key)
|
||||
if isinstance(value, list):
|
||||
return value
|
||||
return []
|
||||
|
||||
|
||||
def _safe_int(value: Any, default: int = 0) -> int:
|
||||
try:
|
||||
return int(value)
|
||||
except (TypeError, ValueError):
|
||||
return default
|
||||
|
||||
|
||||
def split_owner_repo(slug: str) -> tuple[str, str]:
|
||||
"""把 'owner/repo' 或完整 URL 解析为 (owner, repo)。"""
|
||||
s = slug.strip()
|
||||
if s.startswith("http"):
|
||||
parts = urllib.parse.urlparse(s).path.strip("/").split("/")
|
||||
if len(parts) >= 2:
|
||||
return parts[0], parts[1].replace(".git", "")
|
||||
raise GitLinkError(f"无法从 URL 解析 owner/repo: {slug}")
|
||||
if "/" in s:
|
||||
owner, repo = s.split("/", 1)
|
||||
return owner, repo.replace(".git", "")
|
||||
raise GitLinkError(f"格式应为 owner/repo: {slug}")
|
||||
|
|
@ -0,0 +1,70 @@
|
|||
"""gitlink-changelog 单元测试。"""
|
||||
from __future__ import annotations
|
||||
import sys
|
||||
from pathlib import Path
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parent.parent / "scripts"))
|
||||
import pytest
|
||||
from changelog import parse_commit, build_changelog, render_markdown
|
||||
|
||||
|
||||
def commit(msg, login="dev", sha="abcdef123456"):
|
||||
return {"message": msg, "author": {"login": login}, "sha": sha}
|
||||
|
||||
|
||||
class TestParseCommit:
|
||||
def test_plain(self):
|
||||
p = parse_commit(commit("feat: 新增登录"))
|
||||
assert p["type"] == "feat" and p["desc"] == "新增登录"
|
||||
|
||||
def test_scope(self):
|
||||
p = parse_commit(commit("fix(auth): 修复 token"))
|
||||
assert p["type"] == "fix" and p["scope"] == "auth"
|
||||
|
||||
def test_breaking(self):
|
||||
p = parse_commit(commit("feat!: 重构 API"))
|
||||
assert p["breaking"] is True
|
||||
|
||||
def test_breaking_body(self):
|
||||
p = parse_commit({"message": "feat: x\n\nBREAKING CHANGE: 不兼容", "author": {}, "sha": "x"})
|
||||
assert p["breaking"] is True
|
||||
|
||||
def test_other(self):
|
||||
p = parse_commit(commit("随便写的"))
|
||||
assert p["type"] == "other"
|
||||
|
||||
def test_merge_not_typed(self):
|
||||
p = parse_commit(commit("Merge pull request '#1'"))
|
||||
assert p["type"] == "other"
|
||||
|
||||
|
||||
class TestBuildChangelog:
|
||||
def test_groups(self):
|
||||
cl = build_changelog([commit("feat: a"), commit("fix: b"), commit("feat: c")])
|
||||
assert cl["groups"]["feat"] == 2
|
||||
assert cl["groups"]["fix"] == 1
|
||||
assert cl["typed_commits"] == 3
|
||||
|
||||
def test_breaking_collected(self):
|
||||
cl = build_changelog([commit("feat!: x")])
|
||||
assert cl["breaking_count"] == 1
|
||||
|
||||
def test_contributors(self):
|
||||
cl = build_changelog([commit("feat: a", login="alice"), commit("fix: b", login="bob")])
|
||||
assert set(cl["contributors"]) == {"alice", "bob"}
|
||||
|
||||
def test_empty(self):
|
||||
cl = build_changelog([])
|
||||
assert cl["total_commits"] == 0 and cl["typed_commits"] == 0
|
||||
|
||||
|
||||
class TestRender:
|
||||
def test_markdown(self):
|
||||
cl = build_changelog([commit("feat: 新功能"), commit("fix!: 重大修复")])
|
||||
md = render_markdown(cl, "o", "r")
|
||||
assert "版本变更对比" in md
|
||||
assert "新功能" in md
|
||||
assert "不兼容变更" in md
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(pytest.main([__file__, "-v"]))
|
||||
Loading…
Reference in New Issue