Merge pull request 'chore: 提交除 const.py 外的所有修改' (#6) from qiaoxinjiu into master

Reviewed-on: #6

app/api/service/documentSourceService.py

@@ -225,15 +225,21 @@ class DocumentSourceService:
     def _extract_content_from_pdf(pdf_path):
         """提取PDF内容"""
         try:
+            from flask import current_app
             from PyPDF2 import PdfReader
+            file_size = os.path.getsize(pdf_path) if os.path.exists(pdf_path) else 0
+            current_app.logger.info(f'开始提取PDF内容: path={pdf_path}, size={file_size}')
             reader = PdfReader(pdf_path)
             content = ''
             for page in reader.pages:
                 page_content = page.extract_text()
                 if page_content:
                     content += page_content + '\n'
+            current_app.logger.info(f'PDF内容提取完成: path={pdf_path}, pages={len(reader.pages)}, content_length={len(content)}')
             return content
-        except Exception:
+        except Exception as e:
+            from flask import current_app
+            current_app.logger.exception(f'PDF内容提取失败: path={pdf_path}, error={str(e)}')
             return ''
     
     @staticmethod
@@ -269,7 +275,8 @@ class DocumentSourceService:
                 # 提取PDF内容
                 content = DocumentSourceService._extract_content_from_pdf(pdf_path)
                 if not content:
-                    failed_docs.append({'documentId': doc_id, 'error': 'PDF内容为空'})
+                    file_size = os.path.getsize(pdf_path) if os.path.exists(pdf_path) else 0
+                    failed_docs.append({'documentId': doc_id, 'error': f'PDF内容为空，文件大小：{file_size} bytes。请检查服务器是否安装PyPDF2、文件是否为扫描件或加密PDF'})
                     continue
                 
                 # 更新文档内容

requirements.txt

@@ -7,6 +7,9 @@ PyMySQL~=0.10.0
 psycopg2-binary~=2.9.9
 python-jenkins~=1.7.0
 requests~=2.26.0
+openai~=1.30.0
+httpx~=0.27.0
+PyPDF2~=3.0.1
 Flask-Docs~=0.6.4
 flask_redis~=0.4.0
 jira~=3.0.1