diff --git a/skills/gitlink-newcomer/SKILL.md b/skills/gitlink-newcomer/SKILL.md new file mode 100644 index 0000000..fadabe0 --- /dev/null +++ b/skills/gitlink-newcomer/SKILL.md @@ -0,0 +1,112 @@ +--- +name: gitlink-newcomer +version: 1.0.0 +description: "新人引导:识别 good-first-issue、评估上手难度与友好度、为候选 Issue 生成个性化引导评论、产出新手任务看板,降低新贡献者参与门槛。当用户提到「适合新人的 Issue」「good first issue」「新手任务」「引导新贡献者」「降低参与门槛」「new contributor」时触发。" +metadata: + requires: + bins: ["gitlink-cli"] + optional_bins: ["python"] + cliHelp: "gitlink-cli issue --help" +--- + +# gitlink-newcomer(新人引导) + +**CRITICAL — 开始前先阅读 [`../gitlink-shared/SKILL.md`](../gitlink-shared/SKILL.md),其中包含认证、权限处理和 API 注意事项。** +**CRITICAL — GitLink 操作只能用 `gitlink-cli`。禁止用 `gh`(GitHub CLI)操作 GitLink 资源。`gh` 仅适用于 GitHub 平台。** +**CRITICAL — 发布引导评论属于写操作,执行前必须征得用户确认。本技能默认只生成评论内容,不自动发布。** + +> **前置条件:** 先阅读 [`../gitlink-shared/SKILL.md`](../gitlink-shared/SKILL.md) 了解认证与全局参数。 + +## 何时使用本技能 + +- 维护者想为新贡献者整理一份「适合上手的 Issue」清单 +- 用户问「这个项目有哪些 good first issue / 新手任务」 +- 想为某个简单 Issue 自动生成欢迎与引导评论,降低新人门槛 +- 需要评估某个 Issue 对新手的友好程度 + +## 何时不使用 + +- 只是普通地列出全部 Issue → 用 `gitlink-issue` +- 复杂的项目健康度/协作分析 → 用 `gitlink-health` / `gitlink-insight` + +## 能力概览 + +| 能力 | 说明 | +|------|------| +| good-first-issue 识别 | 综合标签、标题/正文关键词、描述长度、讨论热度等多信号识别 | +| 友好度评分 | 为每个 Issue 输出 0-100 的新手友好度分与难度等级(入门/较易/中等/进阶) | +| 个性化引导 | 为候选 Issue 生成包含上手步骤、Fork/PR 流程的欢迎评论 | +| 新手任务看板 | 汇总候选 Issue 为 Markdown 看板,可贴到 Wiki 或 README | + +## 工作流 1:生成新手任务看板 + +### 方式 A:用配套脚本(推荐,一步到位) + +```bash +# 扫描仓库 Issue,输出新手任务看板(Markdown) +python scripts/newcomer.py --owner Gitlink --repo gitlink-cli + +# 输出 JSON 供 Agent 进一步处理(含每个候选的引导文案) +python scripts/newcomer.py --owner Gitlink --repo gitlink-cli --format json + +# 写入文件 +python scripts/newcomer.py --owner Gitlink --repo gitlink-cli --output board.md +``` + +参数说明: + +| 参数 | 类型 | 必填 | 说明 | +|------|------|:----:|------| +| `--owner` | string | 是* | 仓库所有者(*或用 `--slug`) | +| `--repo` | string | 是* | 仓库名称 | +| `--slug` | string | 否 | `owner/repo` 或完整 URL,替代 owner/repo | +| `--issue` | int | 否 | 只为指定 Issue 编号(web 序号)生成引导 | +| `--limit` | int | 否 | 扫描 Issue 数量上限,默认 50 | +| `--format` | string | 否 | `markdown`(默认)或 `json` | +| `--output` | string | 否 | 输出文件路径,缺省打印到标准输出 | + +### 方式 B:用 gitlink-cli 命令手动采集 + +当无法运行脚本时,Agent 可用以下命令采集数据后自行分析: + +```bash +# 1. 获取开放 Issue 列表 +gitlink-cli issue +list --owner Gitlink --repo gitlink-cli --state open --format json + +# 2. 查看某个 Issue 详情(--number 用 web 序号,不是全局 id) +gitlink-cli issue +view --owner Gitlink --repo gitlink-cli --number 12 --format json + +# 3. 查看仓库标签,确认是否有 good first issue 类标签 +gitlink-cli label +list --owner Gitlink --repo gitlink-cli --format json +``` + +识别规则建议: +- 带 `good first issue` / `beginner` / `新手` 等标签 → 强新手信号 +- 标题/正文含 `typo` / `docs` / `文档` / `test` / `翻译` 等 → 易上手信号 +- 含 `refactor` / `架构` / `并发` / `性能` 等 → 高难度信号 + +## 工作流 2:为单个 Issue 生成引导评论 + +```bash +# 生成引导文案(不发布) +python scripts/newcomer.py --owner Gitlink --repo gitlink-cli --issue 12 + +# 确认文案后,由用户决定是否发布为评论(写操作,需确认) +gitlink-cli issue +comment --owner Gitlink --repo gitlink-cli --number 12 -b "<引导文案>" +``` + +## API 注意事项 + +- **ID 混淆**:GitLink 的 Issue 列表接口(`issue +list`)通常只返回全局数据库 `id`,不含 web 序号。发评论 / 关联 Issue 时,`issue +comment` 的 `--number` 需要 web 序号(URL 中显示的编号),不要把全局 id 当 web 序号用。 +- **写操作确认**:`issue +comment` 会真实发布评论,执行前务必向用户确认内容与目标 Issue。 +- 数据采集全程只读,脚本默认不发布任何内容。 + +## 输出示例 + +参见 [`examples/`](examples/) 目录下的真实运行产物(新手看板、单 Issue 引导)。 + +## References + +- [api-reference.md](references/api-reference.md) — 采集的接口、字段与 ID 混淆说明 +- [scoring.md](references/scoring.md) — 新手友好度评分规则与信号词表 +- [gitlink-shared](../gitlink-shared/SKILL.md) — 认证、全局参数、安全规则 diff --git a/skills/gitlink-newcomer/references/api-reference.md b/skills/gitlink-newcomer/references/api-reference.md new file mode 100644 index 0000000..1e37d2e --- /dev/null +++ b/skills/gitlink-newcomer/references/api-reference.md @@ -0,0 +1,64 @@ +# gitlink-newcomer API 参考 + +> **前置条件:** 先阅读 [`../../gitlink-shared/SKILL.md`](../../gitlink-shared/SKILL.md) 了解认证、全局参数和安全规则。 + +本技能识别 good-first-issue 所依赖的 GitLink 接口与字段。数据采集全程只读。 + +## 采集的接口 + +### Issue 列表 + +``` +GET /:owner/:repo/issues.json?page={page}&limit={limit} +# 或经 gitlink-cli: +gitlink-cli issue +list --owner --repo --state open --format json +``` + +返回的 `issues[]` 中本技能使用的字段: + +| 字段 | 说明 | 用途 | +|------|------|------| +| `id` | 全局数据库 ID | 去重、展示(**非** web 序号) | +| `name` / `subject` | Issue 标题 | 关键词分析、展示 | +| `description` | 正文 | 关键词分析、长度评估 | +| `issue_tags` / `labels` | 标签 | good-first-issue 标签信号 | +| `comment_journals_count` / `journals_count` | 评论数 | 讨论热度评估 | +| `author_login` / `author_name` | 作者 | 展示 | + +### Issue 详情(单个) + +``` +GET /:owner/:repo/issues/{number}.json +# 或: +gitlink-cli issue +view --owner --repo --number {number} --format json +``` + +`{number}` 为 web 序号(URL 中的编号)。详情接口可拿到更完整的字段。 + +## ID 混淆(重要) + +GitLink 存在两种 ID: + +| 名称 | 来源 | 用途 | +|------|------|------| +| 全局数据库 `id` | Issue 列表接口 | 仅去重 / 内部引用 | +| web 序号(`project_issues_index` / `number`) | 单 Issue 详情、web URL | 发评论、PR 关联、`issue +comment --number` | + +本技能的处理: +- 列表接口只返回全局 `id` 时,看板以 `id:xxx` 形式标注,**不**伪装成 web 序号; +- 生成引导评论时,若无可靠 web 序号则用 Issue 标题引用,避免误导; +- 发布评论用 `gitlink-cli issue +comment --number `。 + +## 写操作 + +发布引导评论是写操作: + +``` +gitlink-cli issue +comment --owner --repo --number -b "<引导文案>" +``` + +执行前必须征得用户确认;本技能默认只生成文案,不自动发布。 + +## 错误处理 + +沿用 gitlink-shared 的错误码(401 重新登录 / 403 权限 / 404 检查 owner/repo)。采集失败时脚本返回非零退出码并打印原因。 diff --git a/skills/gitlink-newcomer/references/scoring.md b/skills/gitlink-newcomer/references/scoring.md new file mode 100644 index 0000000..9971e5a --- /dev/null +++ b/skills/gitlink-newcomer/references/scoring.md @@ -0,0 +1,42 @@ +# 新手友好度评分规则 + +本技能用一套可解释的规则为每个 Issue 打出 0-100 的新手友好度分,不依赖大模型。 + +## 评分模型 + +基准分 **50**,在此基础上根据信号加减: + +| 信号 | 分值 | 说明 | +|------|:----:|------| +| 命中新手友好标签 | +35 | `good first issue` / `beginner` / `新手` / `easy` 等 | +| 命中高难度标签 | -30 | `hard` / `complex` / `advanced` / `困难` 等 | +| 命中易上手关键词 | +7/词(上限 +20) | `typo` / `docs` / `文档` / `test` / `翻译` 等 | +| 命中高难度关键词 | -10/词(上限 -25) | `refactor` / `架构` / `并发` / `性能` / `安全` 等 | +| 描述长度适中(30-600) | +5 | 适中描述更易上手 | +| 描述过长(>1500) | -8 | 往往较复杂 | +| 讨论过多(评论 >15) | -8 | 可能存在分歧 | + +最终分数裁剪到 [0, 100]。 + +## 难度等级 + +| 友好度分 | 难度等级 | +|:--------:|:--------:| +| ≥ 75 | 入门 | +| 55 - 74 | 较易 | +| 40 - 54 | 中等 | +| < 40 | 进阶 | + +友好度 ≥ 55 的 Issue 被列为新手候选(`is_good_first = true`)。 + +## 信号词表(节选) + +**新手友好标签**:good first issue、good-first-issue、first-timers-only、beginner、beginner-friendly、easy、starter、新手、新手友好、入门、简单 + +**易上手关键词**:typo、document、docs、readme、comment、translation、rename、format、lint、test、example、i18n、文档、注释、拼写、翻译、示例、格式 + +**高难度关键词**:refactor、architecture、performance、concurrency、race、security、deadlock、memory leak、breaking change、重构、架构、性能、并发、安全、死锁、内存 + +## 可调整性 + +词表与阈值集中在 `scripts/newcomer.py` 顶部常量(`GOOD_FIRST_LABELS` / `EASY_KEYWORDS` / `HARD_KEYWORDS` / `HARD_LABELS`),可按项目习惯调整。 diff --git a/skills/gitlink-newcomer/scripts/glapi.py b/skills/gitlink-newcomer/scripts/glapi.py new file mode 100644 index 0000000..41db09d --- /dev/null +++ b/skills/gitlink-newcomer/scripts/glapi.py @@ -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}") diff --git a/skills/gitlink-newcomer/scripts/newcomer.py b/skills/gitlink-newcomer/scripts/newcomer.py new file mode 100644 index 0000000..3cb70cb --- /dev/null +++ b/skills/gitlink-newcomer/scripts/newcomer.py @@ -0,0 +1,333 @@ +"""gitlink-newcomer:新人引导分析。 + +识别一个 GitLink 仓库中适合新贡献者上手的 Issue,评估上手难度与友好度, +为每个候选 Issue 生成个性化引导评论,并产出新手任务看板。 + +数据来自 GitLink 公开 API(只读),无需登录。生成的引导评论仅作为建议输出, +是否发布由用户通过 gitlink-cli 自行决定。 + +用法: + python newcomer.py --owner Gitlink --repo gitlink-cli + python newcomer.py --owner Gitlink --repo gitlink-cli --format json + python newcomer.py --owner Gitlink --repo gitlink-cli --issue 12 # 只为某个 Issue 生成引导 +""" + +from __future__ import annotations + +import argparse +import json +import re +import sys +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 + +# Windows 控制台默认 GBK,直接打印含 emoji 的 Markdown 会抛 UnicodeEncodeError。 +# 重配置 stdout 为 UTF-8,确保跨平台正常输出。 +if hasattr(sys.stdout, "reconfigure"): + try: + sys.stdout.reconfigure(encoding="utf-8") + except Exception: + pass + +# --------------------------------------------------------------------------- +# 识别规则 +# --------------------------------------------------------------------------- + +# good-first-issue 的标签信号(不同项目命名习惯) +GOOD_FIRST_LABELS = { + "good first issue", "good-first-issue", "goodfirstissue", + "good first", "first-timers-only", "first timers only", + "beginner", "beginner-friendly", "easy", "starter", + "新手", "新手友好", "新人", "入门", "简单", +} + +# 标题/正文中暗示「适合新手」的关键词 +EASY_KEYWORDS = [ + "typo", "document", "docs", "readme", "comment", "translation", "translate", + "rename", "format", "lint", "test", "example", "i18n", + "文档", "注释", "拼写", "翻译", "示例", "格式", "重命名", +] + +# 暗示「难度较高、不适合新手」的关键词 +HARD_KEYWORDS = [ + "refactor", "architecture", "performance", "concurrency", "race", + "security", "deadlock", "memory leak", "breaking change", + "重构", "架构", "性能", "并发", "安全", "死锁", "内存", +] + +# 难度高的标签 +HARD_LABELS = {"hard", "complex", "advanced", "epic", "困难", "复杂"} + + +def _text_of(issue: dict[str, Any]) -> str: + """合并 Issue 的标题与正文用于关键词分析。""" + title = issue.get("name") or issue.get("subject") or issue.get("title") or "" + body = issue.get("description") or issue.get("body") or "" + return f"{title}\n{body}".lower() + + +def _labels_of(issue: dict[str, Any]) -> list[str]: + """提取 Issue 标签名(兼容多种字段结构)。""" + labels: list[str] = [] + raw = issue.get("issue_tags") or issue.get("labels") or issue.get("tags") + if isinstance(raw, list): + for item in raw: + if isinstance(item, dict): + name = item.get("name") or item.get("title") + if name: + labels.append(str(name).lower()) + elif item: + labels.append(str(item).lower()) + return labels + + +def _issue_number(issue: dict[str, Any]) -> int | None: + """提取仓库内 Issue 序号(web URL 中显示的编号)。 + + 注意:GitLink 的 Issue 列表接口通常只返回全局数据库 id,不含 web 序号; + 只有单 Issue 详情或带 number/index 字段时才有可靠序号。取不到返回 None, + 避免把全局 id 误当作 web 序号引用。 + """ + for key in ("number", "index"): + val = issue.get(key) + if isinstance(val, int): + return val + return None + + +def _issue_gid(issue: dict[str, Any]) -> int | None: + """全局数据库 id(仅用于去重/展示,不可用于 web 链接 / PR 关联)。""" + val = issue.get("id") + return val if isinstance(val, int) else None + + +def score_issue(issue: dict[str, Any]) -> dict[str, Any]: + """评估单个 Issue 的新手友好度。 + + 返回友好度评分(0-100)、难度等级、命中的信号, + 评分越高越适合新人上手。 + """ + text = _text_of(issue) + labels = _labels_of(issue) + signals: list[str] = [] + score = 50 # 基准分 + + # 标签信号(最强) + if any(lb in GOOD_FIRST_LABELS for lb in labels): + score += 35 + signals.append("带有新手友好标签") + if any(lb in HARD_LABELS for lb in labels): + score -= 30 + signals.append("带有高难度标签") + + # 关键词信号 + easy_hits = [k for k in EASY_KEYWORDS if k in text] + if easy_hits: + score += min(20, len(easy_hits) * 7) + signals.append(f"内容涉及易上手主题({', '.join(easy_hits[:3])})") + hard_hits = [k for k in HARD_KEYWORDS if k in text] + if hard_hits: + score -= min(25, len(hard_hits) * 10) + signals.append(f"内容涉及高难度主题({', '.join(hard_hits[:3])})") + + # 描述长度:太长往往复杂 + body = issue.get("description") or issue.get("body") or "" + if len(body) > 1500: + score -= 8 + signals.append("描述较长,可能较复杂") + elif 30 <= len(body) <= 600: + score += 5 + signals.append("描述长度适中") + + # 评论数:讨论太多可能有争议或难度大 + comments = issue.get("comment_journals_count") or issue.get("journals_count") or 0 + if isinstance(comments, int) and comments > 15: + score -= 8 + signals.append("讨论较多,可能存在分歧") + + score = max(0, min(100, score)) + if score >= 75: + difficulty = "入门" + elif score >= 55: + difficulty = "较易" + elif score >= 40: + difficulty = "中等" + else: + difficulty = "进阶" + + return { + "number": _issue_number(issue), + "gid": _issue_gid(issue), + "title": issue.get("name") or issue.get("subject") or issue.get("title") or "(无标题)", + "labels": labels, + "friendliness": score, + "difficulty": difficulty, + "signals": signals, + "author": issue.get("author_login") or issue.get("author_name"), + "comments": comments if isinstance(comments, int) else 0, + "is_good_first": score >= 55, + } + + +def build_guidance(scored: dict[str, Any], owner: str, repo: str) -> str: + """为一个候选 Issue 生成个性化的新手引导评论。""" + num = scored.get("number") + title = scored["title"] + diff = scored["difficulty"] + # 有可靠 web 序号时用 #num 引用,否则用标题引用(不误用全局 id) + ref = f"#{num}" if num else f"《{title}》" + + lines = [ + f"👋 欢迎!这个 Issue({ref})被 gitlink-newcomer 评估为 **{diff}** 难度,适合作为参与本项目的起点。", + "", + "如果你想认领它,建议按以下步骤上手:", + "", + f"1. 阅读项目的 `README` 和 `CONTRIBUTING`(如有),了解开发与提交规范。", + f"2. Fork 本仓库并克隆你的 Fork:`gitlink-cli repo +fork --owner {owner} --repo {repo}`", + "3. 新建一个分支进行修改,保持改动聚焦于本 Issue。", + f"4. 完成后从你的 Fork 向 `{owner}/{repo}` 提交 PR,并在描述里关联本 Issue。", + "", + ] + + if "文档" in str(scored["signals"]) or "docs" in str(scored["signals"]).lower(): + lines.append("> 提示:这看起来是一个文档/文本类改动,通常不需要改动核心逻辑,很适合第一次贡献。") + if scored["comments"] > 8: + lines.append("> 提示:该 Issue 已有较多讨论,动手前建议先通读评论,确认当前结论与分工。") + lines.append("") + lines.append("有任何问题都可以在本 Issue 下留言,社区很乐意帮助新人。祝贡献顺利!🚀") + return "\n".join(lines) + + +def analyze(owner: str, repo: str, limit: int = 50, + client: GitLinkClient | None = None) -> dict[str, Any]: + """分析仓库的 Issue,识别并排序新手友好的候选。""" + client = client or GitLinkClient() + issues = client.issues(owner, repo, limit=limit) + scored = [score_issue(i) for i in issues] + candidates = [s for s in scored if s["is_good_first"]] + candidates.sort(key=lambda s: s["friendliness"], reverse=True) + + return { + "owner": owner, + "repo": repo, + "total_issues": len(issues), + "candidate_count": len(candidates), + "candidates": candidates, + "all_scored": scored, + } + + +def render_board(result: dict[str, Any], owner: str, repo: str) -> str: + """渲染新手任务看板(Markdown)。""" + lines = [ + f"# 新手任务看板 — {owner}/{repo}", + "", + f"由 gitlink-newcomer 生成。共扫描 {result['total_issues']} 个开放 Issue," + f"识别出 **{result['candidate_count']}** 个适合新贡献者上手的任务。", + "", + ] + if not result["candidates"]: + lines += [ + "暂未发现明显适合新手的 Issue。建议维护者:", + "", + "- 为简单任务打上 `good first issue` 标签", + "- 在 Issue 描述里补充清晰的上手说明与验收标准", + "", + ] + return "\n".join(lines) + + lines += [ + "| 推荐度 | 难度 | Issue | 标题 | 命中信号 |", + "|:------:|:----:|:-----:|------|----------|", + ] + for c in result["candidates"]: + stars = "⭐" * max(1, round(c["friendliness"] / 20)) + signal = c["signals"][0] if c["signals"] else "-" + title = c["title"][:40] + # 有 web 序号用 #num,否则标注全局 id(gid)以便定位 + if c.get("number"): + ref = f"#{c['number']}" + elif c.get("gid"): + ref = f"id:{c['gid']}" + else: + ref = "-" + lines.append( + f"| {stars} | {c['difficulty']} | {ref} | {title} | {signal} |" + ) + lines += [ + "", + "## 建议行动", + "", + "1. 为上述 Issue 添加引导评论,欢迎新贡献者认领(见各 Issue 的引导文案)。", + "2. 确认这些 Issue 的描述包含足够的上手信息。", + "3. 可在仓库 README 中链接本看板,方便新人发现。", + "", + ] + return "\n".join(lines) + + +def main(argv: list[str] | None = None) -> int: + p = argparse.ArgumentParser( + prog="gitlink-newcomer", + description="识别 good-first-issue 并生成新手引导", + ) + p.add_argument("--owner", help="仓库所有者,如 Gitlink") + p.add_argument("--repo", help="仓库名称,如 gitlink-cli") + p.add_argument("--slug", help="owner/repo 形式,或完整仓库 URL") + p.add_argument("--issue", type=int, help="只为指定 Issue 编号生成引导评论") + p.add_argument("--limit", type=int, default=50, help="扫描的 Issue 数量上限(默认 50)") + p.add_argument("--format", choices=["markdown", "json"], default="markdown", + help="输出格式(默认 markdown)") + p.add_argument("--output", type=Path, help="输出文件路径,缺省打印到标准输出") + 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 + + client = GitLinkClient() + try: + # 单 Issue 引导模式 + if args.issue is not None: + detail = client.issue_detail(owner, repo, args.issue) + if not detail: + print(f"未找到 Issue #{args.issue}", file=sys.stderr) + return 1 + scored = score_issue(detail) + guidance = build_guidance(scored, owner, repo) + if args.format == "json": + out = json.dumps({"issue": scored, "guidance": guidance}, + ensure_ascii=False, indent=2) + else: + out = guidance + else: + result = analyze(owner, repo, limit=args.limit, client=client) + if args.format == "json": + # 为每个候选附上引导文案 + for c in result["candidates"]: + c["guidance"] = build_guidance(c, owner, repo) + out = json.dumps(result, ensure_ascii=False, indent=2) + else: + out = render_board(result, owner, repo) + except GitLinkError as exc: + print(f"采集失败:{exc}", file=sys.stderr) + return 1 + + 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()) diff --git a/skills/gitlink-newcomer/tests/test_newcomer.py b/skills/gitlink-newcomer/tests/test_newcomer.py new file mode 100644 index 0000000..bfaaeb4 --- /dev/null +++ b/skills/gitlink-newcomer/tests/test_newcomer.py @@ -0,0 +1,128 @@ +"""gitlink-newcomer 单元测试。 + +覆盖 good-first-issue 识别、友好度评分、ID 区分、引导生成与看板渲染。 +使用合成数据,不触网,可离线运行: + + python -m pytest tests/ -v +""" + +from __future__ import annotations + +import sys +from pathlib import Path + +sys.path.insert(0, str(Path(__file__).resolve().parent.parent / "scripts")) + +import pytest + +from newcomer import ( + score_issue, build_guidance, render_board, + _issue_number, _issue_gid, _labels_of, +) + + +def issue(name="", body="", labels=None, comments=0, number=None, gid=None): + d = {"name": name, "description": body, "comment_journals_count": comments} + if labels is not None: + d["issue_tags"] = [{"name": x} for x in labels] + if number is not None: + d["number"] = number + if gid is not None: + d["id"] = gid + return d + + +class TestLabels: + def test_extract_dict_labels(self): + assert _labels_of(issue(labels=["Bug", "good first issue"])) == ["bug", "good first issue"] + + def test_no_labels(self): + assert _labels_of(issue()) == [] + + +class TestIdDistinction: + def test_web_number_preferred(self): + assert _issue_number(issue(number=12)) == 12 + + def test_no_web_number_returns_none(self): + # 列表接口只有全局 id,不应被当作 web 序号 + assert _issue_number(issue(gid=140801)) is None + + def test_gid_extracted(self): + assert _issue_gid(issue(gid=140801)) == 140801 + + +class TestScoreIssue: + def test_good_first_label_boosts(self): + s = score_issue(issue(name="fix typo", labels=["good first issue"])) + assert s["friendliness"] >= 75 + assert s["is_good_first"] is True + assert "新手友好标签" in str(s["signals"]) + + def test_hard_keyword_lowers(self): + s = score_issue(issue(name="refactor concurrency architecture", + body="needs deep refactor of the core")) + assert s["friendliness"] < 55 + assert s["is_good_first"] is False + + def test_easy_keyword(self): + s = score_issue(issue(name="update docs and fix typo in readme")) + assert s["friendliness"] > 50 + assert any("易上手" in sig for sig in s["signals"]) + + def test_hard_label(self): + s = score_issue(issue(name="something", labels=["hard"])) + assert "高难度标签" in str(s["signals"]) + + def test_difficulty_levels(self): + easy = score_issue(issue(name="docs typo", labels=["good first issue"])) + hard = score_issue(issue(name="refactor architecture performance concurrency")) + assert easy["difficulty"] in ("入门", "较易") + assert hard["difficulty"] in ("中等", "进阶") + + def test_score_bounded(self): + s = score_issue(issue(name="good first " * 10, labels=["good first issue", "beginner"])) + assert 0 <= s["friendliness"] <= 100 + + def test_long_body_penalty(self): + short = score_issue(issue(name="task", body="x" * 100)) + long = score_issue(issue(name="task", body="x" * 2000)) + assert long["friendliness"] <= short["friendliness"] + + +class TestGuidance: + def test_uses_number_when_available(self): + g = build_guidance(score_issue(issue(name="fix", number=12)), "o", "r") + assert "#12" in g + + def test_uses_title_when_no_number(self): + s = score_issue(issue(name="修复文档错别字", gid=999)) + g = build_guidance(s, "o", "r") + # 无 web 序号时用标题引用,不出现 #999 + assert "#999" not in g + assert "修复文档错别字" in g + + def test_contains_fork_flow(self): + g = build_guidance(score_issue(issue(name="task", number=1)), "Gitlink", "gitlink-cli") + assert "repo +fork" in g + assert "Gitlink" in g + + +class TestBoard: + def test_empty_candidates(self): + result = {"owner": "o", "repo": "r", "total_issues": 3, + "candidate_count": 0, "candidates": [], "all_scored": []} + board = render_board(result, "o", "r") + assert "暂未发现" in board + + def test_board_with_candidates(self): + cand = score_issue(issue(name="fix typo in docs", labels=["good first issue"], gid=100)) + result = {"owner": "o", "repo": "r", "total_issues": 5, + "candidate_count": 1, "candidates": [cand], "all_scored": [cand]} + board = render_board(result, "o", "r") + assert "新手任务看板" in board + assert "id:100" in board # 无 web 序号时标注全局 id + + +if __name__ == "__main__": + sys.exit(pytest.main([__file__, "-v"]))