xiaoxia-saas/scripts/generate_changelog.py

#!/usr/bin/env python3
"""
自动生成 CHANGELOG 条目。

用法:
    python3 scripts/generate_changelog.py v0.1.128 v0.1.129
    python3 scripts/generate_changelog.py v0.1.128 HEAD
"""
from __future__ import annotations

import os
import re
import sys
import json
import urllib.request
import urllib.error
from datetime import datetime

GITEA_URL = os.environ.get("GITEA_URL", "https://git.xiaoxiajianji.com")
REPO = os.environ.get("GITEA_REPO", "xiaoxia/xiaoxia-saas")
TOKEN = os.environ.get("GITEA_TOKEN", "")


def gitea_api(path: str) -> dict | list:
    url = f"{GITEA_URL}/api/v1{path}"
    req = urllib.request.Request(url)
    if TOKEN:
        req.add_header("Authorization", f"token {TOKEN}")
    try:
        with urllib.request.urlopen(req, timeout=30) as resp:
            return json.loads(resp.read().decode())
    except urllib.error.HTTPError as e:
        print(f"API Error: {e.code} {e.reason}", file=sys.stderr)
        raise


def get_tag_date(tag: str) -> str:
    try:
        info = gitea_api(f"/repos/{REPO}/git/refs/tags/{tag}")
        if isinstance(info, dict):
            sha = info.get("object", {}).get("sha", "")
            if sha:
                commit = gitea_api(f"/repos/{REPO}/git/commits/{sha}")
                if isinstance(commit, dict):
                    return commit.get("committer", {}).get("date", "")[:10]
    except Exception:
        pass
    return ""


def get_merged_prs_between(from_tag: str, to_tag: str) -> list[dict]:
    all_prs: list[dict] = []
    page = 1
    while True:
        prs = gitea_api(
            f"/repos/{REPO}/pulls?state=closed&sort=merged&direction=desc"
            f"&per_page=50&page={page}"
        )
        if not isinstance(prs, list) or not prs:
            break
        all_prs.extend(prs)
        if len(prs) < 50:
            break
        page += 1
        if page > 10:
            break

    merged = [pr for pr in all_prs if pr.get("merged_at")]
    from_date = get_tag_date(from_tag)
    to_date = get_tag_date(to_tag) if not to_tag.startswith("HEAD") else datetime.now().strftime("%Y-%m-%d")

    if not from_date:
        return merged[:50]

    result = []
    for pr in merged:
        merged_at = pr.get("merged_at", "")[:10]
        if from_date <= merged_at <= to_date:
            result.append(pr)
    return result


def categorize_pr(title: str) -> tuple[str, str]:
    title = title.strip()
    lower = title.lower()

    m = re.match(r"^(feat|fix|chore|perf|docs|refactor|test|ci|style|build|security)\s*[:：]", title)
    if m:
        prefix = m.group(1)
        clean_title = title[m.end():].strip()
    else:
        prefix = ""
        clean_title = title

    if prefix in ("feat", "feature"):
        return "✨ 功能", clean_title
    elif prefix == "fix":
        return "🐛 Bug 修复", clean_title
    elif prefix in ("refactor", "chore", "style"):
        return "🔄 重构与清理", clean_title
    elif prefix in ("perf", "performance"):
        return "⚡ 性能优化", clean_title
    elif prefix == "security":
        return "🔒 安全修复", clean_title
    elif prefix == "docs":
        return "📝 文档", clean_title
    elif prefix == "test":
        return "🧪 测试", clean_title
    elif prefix in ("ci", "build"):
        return "🚀 CI/CD & 基础设施", clean_title
    else:
        if any(k in lower for k in ["安全", "security", "cve", "漏洞"]):
            return "🔒 安全修复", clean_title
        elif any(k in lower for k in ["修复", "bug"]):
            return "🐛 Bug 修复", clean_title
        elif any(k in lower for k in ["新增", "添加", "feat", "功能"]):
            return "✨ 功能", clean_title
        elif any(k in lower for k in ["ci", "构建", "workflow", "pipeline"]):
            return "🚀 CI/CD & 基础设施", clean_title
        elif any(k in lower for k in ["测试", "test", "e2e"]):
            return "🧪 测试", clean_title
        else:
            return "📌 其他", clean_title


def generate_changelog(from_tag: str, to_tag: str, version: str = "") -> str:
    if not version:
        version = to_tag

    prs = get_merged_prs_between(from_tag, to_tag)

    categories: dict[str, list[tuple[int, str]]] = {}
    for pr in prs:
        cat, title = categorize_pr(pr["title"])
        pr_num = pr["number"]
        categories.setdefault(cat, []).append((pr_num, title))

    order = ["🔒 安全修复", "✨ 功能", "🐛 Bug 修复", "⚡ 性能优化",
             "🔄 重构与清理", "📝 文档", "🧪 测试", "🚀 CI/CD & 基础设施", "📌 其他"]

    date_str = get_tag_date(to_tag) if not to_tag.startswith("HEAD") else datetime.now().strftime("%Y-%m-%d")
    lines = [f"## [{version}] - {date_str}", ""]

    for cat in order:
        items = categories.get(cat, [])
        if not items:
            continue
        lines.append(f"### {cat}")
        lines.append("")
        for num, title in sorted(items, key=lambda x: x[0]):
            short_title = title.split(" — ")[0].split(" - ")[0]
            if len(short_title) > 80:
                short_title = short_title[:77] + "..."
            lines.append(f"- #{num} {short_title}")
        lines.append("")

    lines.append("---")
    lines.append("")
    return "\n".join(lines)


def main():
    if len(sys.argv) < 3:
        print(f"用法: {sys.argv[0]} <from_tag> <to_tag> [version]")
        sys.exit(1)

    from_tag = sys.argv[1]
    to_tag = sys.argv[2]
    version = sys.argv[3] if len(sys.argv) > 3 else ""

    changelog = generate_changelog(from_tag, to_tag, version)
    print(changelog)


if __name__ == "__main__":
    main()