diff --git a/utils/prompt_manager.py b/utils/prompt_manager.py index 1064fd5..fe9b465 100644 --- a/utils/prompt_manager.py +++ b/utils/prompt_manager.py @@ -113,10 +113,32 @@ class PromptManager: if os.path.exists(path): filename = os.path.basename(path) # print(filename) - content = ResourceLoader.load_all_refer_files(path, 1) - if content: - self._refer_cache[filename] = content - # print(content) + # 检测是否为JSON文件 + if filename.lower().endswith('.json'): + # 直接加载和解析JSON文件 + try: + with open(path, 'r', encoding='utf-8') as f: + content = f.read() + # 移除可能的BOM头 + if content.startswith('\ufeff'): + content = content[1:] + # 解析JSON + json_data = json.loads(content) + # 存储解析后的对象 + self._refer_cache[filename] = json_data + logging.info(f"预加载并解析JSON参考文件: {filename}") + except Exception as e: + logging.error(f"预加载JSON文件{filename}失败: {str(e)}") + # 失败时尝试以普通文本加载 + content = ResourceLoader.load_file_content(path) + if content: + self._refer_cache[filename] = content + else: + # 非JSON文件使用普通加载方式 + content = ResourceLoader.load_all_refer_files(path, 1) + if content: + self._refer_cache[filename] = content + logging.info(f"预加载普通参考文件: {filename}") def find_directory_fuzzy_match(self, name, directory=None, files=None): """ @@ -304,6 +326,73 @@ class PromptManager: logging.warning(f"未能找到Demand文件: '{demand_name}'，尝试过以下位置: 缓存, {self.prompts_dir}/Demand/") return None + def _get_refer_content(self, refer_dir): + """从Refer目录加载JSON和文本参考文件 + + Args: + refer_dir: Refer目录路径 + + Returns: + dict: 文件名到内容的映射 + """ + results = {} + if not os.path.isdir(refer_dir): + return results + + # 列出所有文件 + refer_files = [f for f in os.listdir(refer_dir) if os.path.isfile(os.path.join(refer_dir, f))] + + for refer_file in refer_files: + refer_path = os.path.join(refer_dir, refer_file) + content = None + + # 对JSON文件特殊处理 + if refer_file.lower().endswith('.json'): + try: + with open(refer_path, 'r', encoding='utf-8') as f: + content = f.read() + # 移除可能的BOM头 + if content.startswith('\ufeff'): + content = content[1:] + + # 验证是否为有效的JSON + try: + json.loads(content) # 只验证，不存储结果 + logging.info(f"成功验证JSON文件: {refer_file}") + except json.JSONDecodeError as e: + logging.warning(f"文件{refer_file}内容不是有效的JSON: {str(e)}") + except Exception as e: + logging.error(f"读取JSON文件{refer_file}时出错: {str(e)}") + content = None + else: + # 使用ResourceLoader加载非JSON文件 + content = ResourceLoader.load_file_content(refer_path) + + if content: + results[refer_file] = content + + return results + + def _load_and_parse_json(self, file_path): + """安全地加载和解析JSON文件 + + Args: + file_path: JSON文件路径 + + Returns: + dict or None: 解析后的JSON对象，解析失败则返回None + """ + try: + with open(file_path, 'r', encoding='utf-8') as f: + content = f.read() + # 移除可能的BOM头 + if content.startswith('\ufeff'): + content = content[1:] + return json.loads(content) + except Exception as e: + logging.error(f"加载和解析JSON文件{file_path}时出错: {str(e)}") + return None + def _get_all_refer_contents(self, random_sample=True): """获取所有Refer文件内容，可选择随机抽样文件内容 @@ -318,56 +407,55 @@ class PromptManager: # 初始化结果字符串 refer_content_all = "" - # 准备处理所有文件 - all_refer_files = {} - - # 1. 从缓存中获取文件 - if self._refer_cache: - all_refer_files.update(self._refer_cache) - - # 2. 从本地目录获取其他文件（如果有的话） - if self.prompts_dir: + # 如果缓存为空，尝试加载文件 + if not self._refer_cache and self.prompts_dir: refer_dir = os.path.join(self.prompts_dir, "Refer") if os.path.isdir(refer_dir): - dir_files = [f for f in os.listdir(refer_dir) if os.path.isfile(os.path.join(refer_dir, f))] - for refer_file in dir_files: - if refer_file not in all_refer_files: - refer_path = os.path.join(refer_dir, refer_file) - content = ResourceLoader.load_file_content(refer_path) + refer_files = [f for f in os.listdir(refer_dir) if os.path.isfile(os.path.join(refer_dir, f))] + for refer_file in refer_files: + file_path = os.path.join(refer_dir, refer_file) + + # 对JSON文件特殊处理 + if refer_file.lower().endswith('.json'): + try: + with open(file_path, 'r', encoding='utf-8') as f: + content = f.read() + # 移除可能的BOM头 + if content.startswith('\ufeff'): + content = content[1:] + # 解析并存储JSON对象 + json_data = json.loads(content) + self._refer_cache[refer_file] = json_data + logging.info(f"加载并解析JSON参考文件: {refer_file}") + except Exception as e: + logging.error(f"加载JSON文件{refer_file}失败: {str(e)}") + # 失败时尝试以普通文本加载 + content = ResourceLoader.load_file_content(file_path) + if content: + self._refer_cache[refer_file] = content + else: + # 非JSON文件使用普通加载方式 + content = ResourceLoader.load_file_content(file_path) if content: - all_refer_files[refer_file] = content - # 保存到缓存 self._refer_cache[refer_file] = content - if not all_refer_files: + if not self._refer_cache: logging.warning("没有找到任何Refer文件") return refer_content_all - logging.info(f"找到{len(all_refer_files)}个Refer文件") + logging.info(f"找到{len(self._refer_cache)}个Refer文件") - # 3. 处理所有文件 - for filename, content in all_refer_files.items(): - # 检查是否为JSON格式，尝试解析 - is_json = False - json_data = None - - if filename.lower().endswith('.json'): - try: - json_data = json.loads(content) - is_json = True - logging.info(f"成功解析JSON格式的refer文件: {filename}") - except json.JSONDecodeError as e: - logging.warning(f"文件{filename}扩展名为.json但内容不是有效的JSON格式: {str(e)}") - logging.info(f"将以文本格式处理文件: {filename}") - + # 处理所有文件 + for filename, content in self._refer_cache.items(): # 添加文件头部信息 refer_content_all += f"--- Refer File: {filename} ---\n" - if is_json and json_data: - # 处理JSON格式文件 - title = json_data.get("title", "未命名参考资料") - description = json_data.get("description", "") - examples = json_data.get("examples", []) + # 检查内容类型 + if isinstance(content, dict) and 'title' in content and 'examples' in content: + # 已解析的JSON对象 + title = content.get("title", "未命名参考资料") + description = content.get("description", "") + examples = content.get("examples", []) refer_content_all += f"标题: {title}\n" refer_content_all += f"描述: {description}\n\n" @@ -390,8 +478,8 @@ class PromptManager: for idx, example in enumerate(examples, 1): content_text = example.get("content", "") refer_content_all += f"{idx}. {content_text}\n" - else: - # 处理普通文本文件 + elif isinstance(content, str): + # 文本内容 if random_sample: lines = content.split('\n') if len(lines) > 10: # 只对较长的内容进行抽样 @@ -408,6 +496,9 @@ class PromptManager: else: # 不进行抽样 refer_content_all += f"{content}\n" + else: + # 内容是其他类型 + refer_content_all += f"未知内容类型: {type(content)}\n" # 添加文件之间的分隔 refer_content_all += "\n"