2308

scripts/subset-font-safe.py

@@ -50,6 +50,92 @@ def extract_chars_from_files(directories, extensions=('.html', '.md', '.css')):
 
     return chars
 
+def extract_chars_from_json(json_files):
+    """从JSON数据文件中提取字符（用于友链、朋友圈等动态内容）"""
+    chars = set()
+    
+    import json
+
+    for json_file in json_files:
+        if not os.path.exists(json_file):
+            print(f"⚠️  JSON文件不存在，跳过: {json_file}")
+            continue
+
+        print(f"🔍 扫描JSON文件: {json_file}")
+
+        try:
+            with open(json_file, 'r', encoding='utf-8') as f:
+                data = json.load(f)
+
+                # 将整个JSON转换为字符串，提取所有字符
+                content = json.dumps(data, ensure_ascii=False)
+                
+                # 提取中文字符
+                chinese_chars = re.findall(r'[一-鿿]', content)
+                chars.update(chinese_chars)
+
+                # 提取中文标点
+                cjk_punct = re.findall(r'[　-〿＀-￯]', content)
+                chars.update(cjk_punct)
+
+                # 提取英文和数字
+                ascii_chars = re.findall(r'[a-zA-Z0-9]', content)
+                chars.update(ascii_chars)
+
+                print(f"   ✅ 从 {json_file} 提取了 {len(chinese_chars)} 个中文字符")
+
+        except Exception as e:
+            print(f"⚠️  读取JSON文件失败 {json_file}: {e}")
+
+    return chars
+
+def fetch_and_extract_chars_from_api(urls):
+    """从API接口获取数据并提取字符（用于动态内容如友链、朋友圈）"""
+    chars = set()
+    
+    try:
+        import urllib.request
+        import json
+        import ssl
+        
+        # 创建不验证SSL的上下文（用于内网或自签名证书）
+        context = ssl._create_unverified_context()
+        
+        for url in urls:
+            print(f"🌐 尝试从API获取: {url}")
+            try:
+                req = urllib.request.Request(
+                    url,
+                    headers={
+                        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
+                    }
+                )
+                
+                with urllib.request.urlopen(req, context=context, timeout=15) as response:
+                    data = response.read().decode('utf-8')
+                    
+                    try:
+                        json_data = json.loads(data)
+                        content = json.dumps(json_data, ensure_ascii=False)
+                        
+                        # 提取中文字符
+                        chinese_chars = re.findall(r'[一-鿿]', content)
+                        chars.update(chinese_chars)
+                        
+                        print(f"   ✅ 从API提取了 {len(chinese_chars)} 个中文字符")
+                    except json.JSONDecodeError:
+                        print(f"   ⚠️  响应不是有效的JSON，跳过")
+            
+            except urllib.error.URLError as e:
+                print(f"   ❌ API请求失败: {e}")
+            except Exception as e:
+                print(f"   ❌ 处理API响应失败: {e}")
+                
+    except ImportError:
+        print("⚠️  urllib不可用，跳过API扫描")
+    
+    return chars
+
 def subset_font(input_font_path, output_font_path, chars):
     """生成子集字体"""
     print(f"\n📦 加载字体: {input_font_path}")
@@ -177,10 +263,50 @@ def main():
 
     print(f"\n🔍 扫描目录: {', '.join(scan_dirs)}")
 
-    # 提取字符
+    # 提取字符（静态文件）
     new_chars = extract_chars_from_files(scan_dirs)
     print(f"\n📝 从文件中提取了 {len(new_chars)} 个唯一字符")
 
+    # 扫描动态数据文件（友链、朋友圈等）
+    json_data_files = [
+        "themes/Ying/static/json/link_lite.json",           # 友链数据
+        "themes/Ying/static/json/friend_circle_data.json",  # 朋友圈数据
+        "themes/Ying/data/links.yaml",                      # 友链配置
+        "themes/Ying/data/links.yml",                       # 友链配置（备用）
+    ]
+
+    print(f"\n{'='*50}")
+    print(f"🔄 扫描动态数据文件（友链、朋友圈等）")
+    dynamic_chars = extract_chars_from_json(json_data_files)
+    print(f"📝 从动态数据中提取了 {len(dynamic_chars)} 个唯一字符")
+
+    # 从API获取动态数据（用于CI环境）
+    api_urls = [
+        "https://api.usj.cc/api/links?all=1",           # 友链列表
+        "https://api.usj.cc/api/feeds",                   # 订阅源列表
+        "https://api.usj.cc/api/articles?limit=50",      # 朋友圈文章
+    ]
+    
+    # 如果有环境变量，追加额外的API地址
+    if os.environ.get('FONT_SUBSET_API_URLS'):
+        extra_urls = os.environ['FONT_SUBSET_API_URLS'].split(',')
+        api_urls.extend(extra_urls)
+        print(f"\n{'='*50}")
+        print(f"🌐 从环境变量获取额外API地址")
+        print(f"   额外URLs: {', '.join(extra_urls)}")
+    
+    print(f"\n{'='*50}")
+    print(f"🌐 扫描远程API（友链、朋友圈等）")
+    print(f"   共 {len(api_urls)} 个API端点")
+    
+    api_chars = fetch_and_extract_chars_from_api(api_urls)
+    print(f"📝 从API提取了 {len(api_chars)} 个唯一字符")
+    dynamic_chars = dynamic_chars | api_chars
+
+    # 合并静态和动态字符
+    new_chars = new_chars | dynamic_chars
+    print(f"\n📊 合并后总字符数: {len(new_chars)}")
+
     # 合并字符（保留现有字符 + 新提取的字符）
     all_chars = existing_chars | new_chars
     print(f"📊 合并后字符数: {len(all_chars)}")