Update: 忽略文档和索引目录

- 增加多种编码尝试
- 支持无扩展名文件识别
- 增强文件读取容错性

.gitignore

@@ -2,4 +2,5 @@ instance/
 *.db
 __pycache__/
 *.pyc
-.env
+.envdocuments/
+indexes/

services.py

@@ -272,6 +272,16 @@ class DocumentIndexer:
         """读取文档内容"""
         ext = os.path.splitext(filepath)[1].lower()
         
+        # 尝试读取文本文件（包括没有扩展名的）
+        try:
+            with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:
+                content = f.read()
+                if content.strip():  # 如果能读取到内容
+                    return content
+        except:
+            pass
+        
+        # 按扩展名处理特定格式
         if ext in ['.txt', '.md', '.json', '.html']:
             with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:
                 return f.read()
@@ -295,6 +305,19 @@ class DocumentIndexer:
             except:
                 pass
         
+        # 最后尝试以二进制方式读取并解码
+        try:
+            with open(filepath, 'rb') as f:
+                content = f.read()
+                # 尝试多种编码
+                for encoding in ['utf-8', 'gbk', 'gb2312', 'latin-1']:
+                    try:
+                        return content.decode(encoding)
+                    except:
+                        continue
+        except:
+            pass
+        
         return None
     
     def _split_content(self, content):