Fix the Error "'ReportTask' object has no attribute 'ir_file_path'" When Exporting PDF and Ensure that Pango Dependencies are not Missing

Dockerfile

@@ -9,7 +9,7 @@ ENV PYTHONDONTWRITEBYTECODE=1 \
     PATH="/root/.local/bin:${PATH}" \
     PLAYWRIGHT_BROWSERS_PATH=/ms-playwright
 
-# Install system dependencies required by scientific Python stack, Playwright, and Streamlit
+# Install system dependencies required by scientific Python stack, Playwright, Streamlit, and WeasyPrint PDF
 RUN apt-get update && apt-get install -y --no-install-recommends \
     build-essential \
     curl \
@@ -19,6 +19,10 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     libgtk-3-0 \
     libpango-1.0-0 \
     libpangocairo-1.0-0 \
+    libpangoft2-1.0-0 \
+    libgdk-pixbuf2.0-0 \
+    libffi-dev \
+    libcairo2 \
     libatk1.0-0 \
     libatk-bridge2.0-0 \
     libxcb1 \

ReportEngine/flask_interface.py

@@ -160,6 +160,14 @@ def initialize_report_engine():
     try:
         report_agent = create_agent()
         logger.info("Report Engine初始化成功")
+
+        # 检测 PDF 生成依赖（Pango）
+        try:
+            from .utils.dependency_check import log_dependency_status
+            log_dependency_status()
+        except Exception as dep_err:
+            logger.warning(f"依赖检测失败: {dep_err}")
+
         return True
     except Exception as e:
         logger.exception(f"Report Engine初始化失败: {str(e)}")
@@ -198,6 +206,8 @@ class ReportTask:
         self.report_file_name = ""
         self.state_file_path = ""
         self.state_file_relative_path = ""
+        self.ir_file_path = ""
+        self.ir_file_relative_path = ""
         # ====== 流式事件缓存与并发保护 ======
         # 使用deque保存最近的事件，结合锁保证多线程下的安全访问
         self.event_history: deque = deque(maxlen=1000)
@@ -248,7 +258,9 @@ class ReportTask:
             'report_file_name': self.report_file_name,
             'report_file_path': self.report_file_relative_path or self.report_file_path,
             'state_file_ready': bool(self.state_file_path),
-            'state_file_path': self.state_file_relative_path or self.state_file_path
+            'state_file_path': self.state_file_relative_path or self.state_file_path,
+            'ir_file_ready': bool(self.ir_file_path),
+            'ir_file_path': self.ir_file_relative_path or self.ir_file_path
         }
 
     def publish_event(self, event_type: str, payload: Dict[str, Any]) -> None:
@@ -431,6 +443,8 @@ def run_report_generation(task: ReportTask, query: str, custom_template: str = "
             task.report_file_name = generation_result.get('report_filename', '')
             task.state_file_path = generation_result.get('state_filepath', '')
             task.state_file_relative_path = generation_result.get('state_relative_path', '')
+            task.ir_file_path = generation_result.get('ir_filepath', '')
+            task.ir_file_relative_path = generation_result.get('ir_relative_path', '')
         task.publish_event('html_ready', {
             'message': 'HTML渲染完成，可刷新预览',
             'report_file': task.report_file_relative_path or task.report_file_path,
@@ -1027,6 +1041,17 @@ def export_pdf(task_id: str):
         Response: PDF文件流或错误信息
     """
     try:
+        # 检测 Pango 依赖
+        from .utils.dependency_check import check_pango_available
+        pango_available, pango_message = check_pango_available()
+        if not pango_available:
+            return jsonify({
+                'success': False,
+                'error': 'PDF 导出功能不可用：缺少 Pango 系统依赖',
+                'details': '请查看 requirements.txt 文件中的 "===== PDF生成 =====" 部分了解如何安装 Pango',
+                'system_message': pango_message
+            }), 503
+
         # 获取任务信息
         task = tasks_registry.get(task_id)
         if not task:
@@ -1104,6 +1129,17 @@ def export_pdf_from_ir():
         Response: PDF文件流或错误信息
     """
     try:
+        # 检测 Pango 依赖
+        from .utils.dependency_check import check_pango_available
+        pango_available, pango_message = check_pango_available()
+        if not pango_available:
+            return jsonify({
+                'success': False,
+                'error': 'PDF 导出功能不可用：缺少 Pango 系统依赖',
+                'details': '请查看 requirements.txt 文件中的 "===== PDF生成 =====" 部分了解如何安装 Pango',
+                'system_message': pango_message
+            }), 503
+
         data = request.get_json()
 
         if not data or 'document_ir' not in data:

ReportEngine/utils/dependency_check.py

@@ -0,0 +1,62 @@
+"""
+检测系统依赖工具
+用于检测 PDF 生成所需的系统依赖
+"""
+import sys
+from loguru import logger
+
+
+def check_pango_available():
+    """
+    检测 Pango 库是否可用
+
+    Returns:
+        tuple: (is_available: bool, message: str)
+    """
+    try:
+        # 尝试导入 weasyprint 并初始化 Pango
+        from weasyprint import HTML
+        from weasyprint.text.ffi import ffi, pango
+
+        # 尝试调用 Pango 函数来确认库可用
+        pango.pango_version()
+
+        return True, "✓ Pango 依赖检测通过，PDF 导出功能可用"
+    except OSError as e:
+        # Pango 库未安装或无法加载
+        error_msg = str(e)
+        if 'pango' in error_msg.lower():
+            return False, (
+                "⚠ Pango 依赖未安装或无法加载，PDF 导出功能将不可用（其他功能不受影响）\n"
+                "  请查看 requirements.txt 文件中的 PDF 生成部分，了解如何安装 Pango 依赖"
+            )
+        return False, f"⚠ PDF 依赖加载失败: {error_msg}"
+    except ImportError as e:
+        # weasyprint 未安装
+        return False, f"⚠ WeasyPrint 未安装: {e}"
+    except Exception as e:
+        # 其他未知错误
+        return False, f"⚠ PDF 依赖检测失败: {e}"
+
+
+def log_dependency_status():
+    """
+    记录系统依赖状态到日志
+    """
+    is_available, message = check_pango_available()
+
+    if is_available:
+        logger.success(message)
+    else:
+        logger.warning(message)
+        logger.info("提示：PDF 导出功能需要 Pango 库支持，但不影响系统其他功能的正常使用")
+        logger.info("安装说明请参考：requirements.txt 文件中的 '===== PDF生成 =====' 部分")
+
+    return is_available
+
+
+if __name__ == "__main__":
+    # 用于独立测试
+    is_available, message = check_pango_available()
+    print(message)
+    sys.exit(0 if is_available else 1)