#!/bin/sh
# CI 公共步骤：Checkout 代码（流式下载+解压，带重试）
# 用法：直接 source 或调用，需要 GITHUB_TOKEN 环境变量
set -eu

python3 - <<'PY'
import io, os, sys, tarfile, time, urllib.request, urllib.error

url = f"{os.environ['GITHUB_API_URL']}/repos/{os.environ['GITHUB_REPOSITORY']}/archive/{os.environ['GITHUB_SHA']}.tar.gz"
request = urllib.request.Request(url, headers={"Authorization": f"token {os.environ['GITHUB_TOKEN']}"})
last_err = None

for attempt in range(5):
    try:
        with urllib.request.urlopen(request, timeout=120) as response:
            # 流式读取：先读少量数据确认连接成功，再大块读取
            first_chunk = response.read(8192)
            buf = io.BytesIO()
            buf.write(first_chunk)
            while True:
                chunk = response.read(65536)
                if not chunk:
                    break
                buf.write(chunk)
            buf.seek(0)
            with tarfile.open(fileobj=buf, mode='r:gz') as tar:
                root_prefix = tar.getmembers()[0].name.split('/', 1)[0] + '/'
                for member in tar.getmembers():
                    name = member.name
                    if name == root_prefix[:-1]:
                        continue
                    if name.startswith(root_prefix):
                        member.name = name[len(root_prefix):]
                    if member.name:
                        tar.extract(member, '.')
            break
    except urllib.error.HTTPError as e:
        last_err = e
        if e.code >= 500 and attempt < 4:
            wait = 2 ** attempt
            print(f"Checkout HTTP {e.code}, retrying in {wait}s (attempt {attempt+1}/5)...")
            time.sleep(wait)
            continue
        raise
    except Exception as e:
        last_err = e
        if attempt < 4:
            wait = 2 ** attempt
            print(f"Checkout error: {e}, retrying in {wait}s (attempt {attempt+1}/5)...")
            time.sleep(wait)
            continue
        raise
else:
    raise last_err
PY
# CI pipeline speedup batch 1