refactor: centralize configuration management with type-safe schema

Major changes:
- Add dataclass-based configuration schema with validation (config/schema.py)
- Create centralized config loader and default values (config/defaults.py, config/loader.py)
- Remove duplicate database_config.py, merge into unified structure
- Consolidate browser settings into ERP config
- Add batch_size parameter support to extractor

Bug fixes:
- Fix settings save error by updating config paths (browser.* → erp.*)
- Fix batch_size not being applied in data extraction

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

gui/config_manager.py

@@ -5,11 +5,15 @@
 
 负责加载、保存和管理用户配置。
 """
-
-import json
 import os
-from typing import Any, Dict
-from config.user_settings import DEFAULT_SETTINGS
+from typing import TYPE_CHECKING
+from config.loader import ConfigLoader
+from config.schema import AppConfig
+from config.defaults import DEFAULT_SETTINGS_DICT
+
+# 类型提示时导入，避免循环引用
+if TYPE_CHECKING:
+    from config.schema import ERPConfig, DatabaseConfig, PathConfig, ExtractionConfig
 
 
 class ConfigManager:
@@ -23,54 +27,25 @@ class ConfigManager:
             config_file: 配置文件路径
         """
         self.config_file = config_file
-        self.settings = self.load()
+        self.config: AppConfig = ConfigLoader.load(config_file)
 
-    def load(self) -> Dict[str, Any]:
-        """
-        加载配置文件
+        # 验证配置
+        errors = self.config.validate()
+        if errors:
+            print("配置验证失败：")
+            for error in errors:
+                print(f"  - {error}")
 
-        Returns:
-            配置字典，如果文件不存在则返回默认配置
-        """
-        if os.path.exists(self.config_file):
-            try:
-                with open(self.config_file, 'r', encoding='utf-8') as f:
-                    loaded_settings = json.load(f)
-                # 合并默认配置，确保所有必需的键都存在
-                return self._merge_settings(DEFAULT_SETTINGS, loaded_settings)
-            except (json.JSONDecodeError, IOError) as e:
-                print(f"加载配置文件失败: {e}")
-                return DEFAULT_SETTINGS.copy()
-        else:
-            # 首次运行，创建默认配置文件
-            self.save(DEFAULT_SETTINGS.copy())
-            return DEFAULT_SETTINGS.copy()
-
-    def save(self, settings: Dict[str, Any] = None) -> bool:
+    def save(self) -> bool:
         """
         保存配置到文件
 
-        Args:
-            settings: 要保存的配置字典，如果为 None 则保存当前配置
-
         Returns:
             保存是否成功
         """
-        if settings is not None:
-            self.settings = settings
+        return ConfigLoader.save(self.config, self.config_file)
 
-        try:
-            # 确保配置目录存在
-            os.makedirs(os.path.dirname(self.config_file), exist_ok=True)
-
-            with open(self.config_file, 'w', encoding='utf-8') as f:
-                json.dump(self.settings, f, ensure_ascii=False, indent=2)
-            return True
-        except IOError as e:
-            print(f"保存配置文件失败: {e}")
-            return False
-
-    def get(self, key: str, default=None) -> Any:
+    def get(self, key: str, default=None):
         """
         获取配置项
 
@@ -84,17 +59,16 @@ class ConfigManager:
             配置值
         """
         keys = key.split('.')
-        value = self.settings
+        value = self.config
 
-        for k in keys:
-            if isinstance(value, dict) and k in value:
-                value = value[k]
-            else:
-                return default
+        try:
+            for k in keys:
+                value = getattr(value, k)
+            return value
+        except (AttributeError, TypeError):
+            return default
 
-        return value
-
-    def set(self, key: str, value: Any) -> None:
+    def set(self, key: str, value) -> None:
         """
         设置配置项
 
@@ -105,37 +79,40 @@ class ConfigManager:
             value: 配置值
         """
         keys = key.split('.')
-        settings = self.settings
+        obj = self.config
 
+        # 导航到父对象
         for k in keys[:-1]:
-            if k not in settings:
-                settings[k] = {}
-            settings = settings[k]
+            obj = getattr(obj, k)
 
-        settings[keys[-1]] = value
+        # 设置最终值
+        setattr(obj, keys[-1], value)
 
     def reset_to_defaults(self) -> None:
         """重置为默认配置"""
-        self.settings = DEFAULT_SETTINGS.copy()
+        self.config = ConfigLoader.load("default")  # 重新加载默认配置
         self.save()
 
-    def _merge_settings(self, defaults: Dict, loaded: Dict) -> Dict:
-        """
-        合并默认配置和加载的配置
+    @property
+    def erp(self):
+        """获取 ERP 配置"""
+        return self.config.erp
 
-        Args:
-            defaults: 默认配置
-            loaded: 加载的配置
+    @property
+    def database(self):
+        """获取数据库配置"""
+        return self.config.database
 
-        Returns:
-            合并后的配置
-        """
-        result = defaults.copy()
+    @property
+    def paths(self):
+        """获取路径配置"""
+        return self.config.paths
 
-        for key, value in loaded.items():
-            if key in result and isinstance(result[key], dict) and isinstance(value, dict):
-                result[key] = self._merge_settings(result[key], value)
-            else:
-                result[key] = value
+    @property
+    def extraction(self):
+        """获取提取配置"""
+        return self.config.extraction
 
-        return result
+
+# 为了向后兼容，保留旧版本的导入
+DEFAULT_SETTINGS = DEFAULT_SETTINGS_DICT

gui/data_extraction_tab.py

@@ -114,7 +114,7 @@ class DataExtractionTab(ttk.Frame):
         self.verbose_var = tk.BooleanVar(value=self.config.get('extraction.verbose', True))
         ttk.Checkbutton(options_group, text="详细日志", variable=self.verbose_var).grid(row=0, column=0, sticky="w", padx=5)
 
-        self.headless_var = tk.BooleanVar(value=self.config.get('browser.headless', True))
+        self.headless_var = tk.BooleanVar(value=self.config.get('erp.headless', True))
         ttk.Checkbutton(options_group, text="无头模式 (不显示浏览器)", variable=self.headless_var).grid(row=0, column=1, sticky="w", padx=5)
 
         # 进度显示
@@ -200,7 +200,8 @@ class DataExtractionTab(ttk.Frame):
                 username=self.config.get('erp.username'),
                 password=self.config.get('erp.password'),
                 headless=self.headless_var.get(),
-                verbose=self.verbose_var.get()
+                verbose=self.verbose_var.get(),
+                batch_size=self.config.get('extraction.batch_size', 100)
             )
 
             # 创建实时输出流，每次写入立即更新 GUI

gui/material_validation_tab.py

@@ -253,7 +253,7 @@ class MaterialValidationTab(ttk.Frame):
             validator = MaterialStatusValidator(
                 username=self.config.get('erp.username'),
                 password=self.config.get('erp.password'),
-                headless=self.config.get('browser.headless', True),
+                headless=self.config.get('erp.headless', True),
                 verbose=True
             )
 

gui/settings_tab.py

@@ -198,10 +198,10 @@ class SettingsTab(ttk.Frame):
         self.db_username_var.set(self.config.get('database.username', ''))
         self.db_password_var.set(self.config.get('database.password', ''))
 
-        # 浏览器设置
-        self.browser_headless_var.set(self.config.get('browser.headless', True))
-        self.browser_ignore_https_var.set(self.config.get('browser.ignore_https_errors', True))
-        self.browser_auto_close_var.set(self.config.get('browser.auto_close', True))
+        # 浏览器设置（已合并到 ERP 配置中）
+        self.browser_headless_var.set(self.config.get('erp.headless', True))
+        self.browser_ignore_https_var.set(self.config.get('erp.ignore_https_errors', True))
+        self.browser_auto_close_var.set(self.config.get('erp.auto_close_browser', True))
 
         # 路径设置
         self.data_dir_selector.set(self.config.get('paths.data_dir', ''))
@@ -226,10 +226,10 @@ class SettingsTab(ttk.Frame):
         self.config.set('database.username', self.db_username_var.get())
         self.config.set('database.password', self.db_password_var.get())
 
-        # 浏览器设置
-        self.config.set('browser.headless', self.browser_headless_var.get())
-        self.config.set('browser.ignore_https_errors', self.browser_ignore_https_var.get())
-        self.config.set('browser.auto_close', self.browser_auto_close_var.get())
+        # 浏览器设置（已合并到 ERP 配置中）
+        self.config.set('erp.headless', self.browser_headless_var.get())
+        self.config.set('erp.ignore_https_errors', self.browser_ignore_https_var.get())
+        self.config.set('erp.auto_close_browser', self.browser_auto_close_var.get())
 
         # 路径设置
         self.config.set('paths.data_dir', self.data_dir_selector.get())