#!/usr/bin/env python3
"""自动测试文章列表：链接可用性 → 摘要 → 学习"""

import sys, os
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
import json, time, urllib.request, urllib.error

BASE = "http://127.0.0.1:5000"

def test_url(title, url):
    """测试链接是否可访问"""
    try:
        req = urllib.request.Request(url, headers={
            'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7)'
        })
        with urllib.request.urlopen(req, timeout=15) as resp:
            return resp.status, len(resp.read())
    except urllib.error.HTTPError as e:
        return e.code, 0
    except Exception as e:
        return str(e), 0

def api_post(path, data):
    """调 Flask API"""
    req = urllib.request.Request(f"{BASE}{path}",
        data=json.dumps(data).encode(),
        headers={'Content-Type': 'application/json'},
        method='POST')
    with urllib.request.urlopen(req, timeout=10) as resp:
        return json.loads(resp.read())

def api_get(path):
    with urllib.request.urlopen(f"{BASE}{path}", timeout=10) as resp:
        return json.loads(resp.read())

# ── Step 1: 获取文章列表 ──
print("=" * 60)
print("Step 1: 获取文章列表")
print("=" * 60)
articles = api_get("/api/articles")
data = articles.get("data", [])
print(f"共 {len(data)} 篇文章\n")

# ── Step 2: 测试链接可用性 ──
print("=" * 60)
print("Step 2: 测试链接（前10篇）")
print("=" * 60)
bad = []
for i, a in enumerate(data[:10]):
    status, size = test_url(a['title'], a['url'])
    status_str = f"HTTP {status}" if isinstance(status, int) else f"ERR: {status}"
    ok = isinstance(status, int) and 200 <= status < 400
    mark = "✅" if ok else "❌"
    print(f"  {mark} [{i+1}] {a['title'][:50]}...")
    print(f"       {status_str} | {size}B")
    if not ok:
        bad.append(a)
    time.sleep(0.5)

if bad:
    print(f"\n⚠️  {len(bad)} 篇链接有问题")
else:
    print(f"\n✅ 全部链接正常")

# ── Step 3: 测试摘要（前3篇） ──
print("\n" + "=" * 60)
print("Step 3: 测试摘要（前3篇）")
print("=" * 60)
for i, a in enumerate(data[:3]):
    print(f"\n  [{i+1}] 提交摘要: {a['title'][:50]}...")
    r = api_post("/api/articles/summarize", {"title": a['title'], "url": a['url']})
    print(f"      API: OK={r['ok']}, status={r['data']['status']}")
    time.sleep(2)

print("\n⏳ 等待 Hermes 子进程完成（最多 120s）...")
for attempt in range(24):
    time.sleep(5)
    reports = api_get("/api/reports")
    summary_reports = [r for r in reports['data'] if r.get('report_date') == 'summary']
    if len(summary_reports) >= 3:
        print(f"\n✅ 3 篇摘要已生成！")
        for sr in summary_reports[:3]:
            print(f"   #{sr['id']} {sr['chatroom_name'][:40]}: {len(sr.get('summary','') or '')} 字")
        break
    if attempt % 4 == 3:
        print(f"   等待中... ({len(summary_reports)}/3)")

# ── Step 4: 测试学习（前2篇） ──
print("\n" + "=" * 60)
print("Step 4: 测试学习（前2篇）")
print("=" * 60)
for i, a in enumerate(data[:2]):
    print(f"\n  [{i+1}] 提交学习: {a['title'][:50]}...")
    r = api_post("/api/articles/learn", {"title": a['title'], "url": a['url']})
    print(f"      API: OK={r['ok']}, status={r['data']['status']}")
    time.sleep(2)

print("\n⏳ 等待 Hermes 子进程完成（最多 300s）...")
for attempt in range(60):
    time.sleep(5)
    reports = api_get("/api/reports")
    learn_reports = [r for r in reports['data'] if r.get('report_date') == 'learn']
    if len(learn_reports) >= 2:
        print(f"\n✅ 2 篇学习结果已生成！")
        for lr in learn_reports[:2]:
            print(f"   #{lr['id']} {lr['chatroom_name'][:40]}: {len(lr.get('summary','') or '')} 字")
        break
    if attempt % 6 == 5:
        print(f"   等待中... ({len(learn_reports)}/2)")

print("\n" + "=" * 60)
print("测试完成！")
print("=" * 60)
print(f"链接: {len(data) - len(bad)}/{len(data[:10])} 正常")
print(f"摘要: 已提交 3 篇")
print(f"学习: 已提交 2 篇")
print(f"查看结果: {BASE}/reports")