优化简历提取相关

app/services/resume_service.py

@@ -19,7 +19,7 @@ from app.models.user_resume_education import UserResumeEducation
 from app.models.user_resume_internship import UserResumeInternship
 from app.models.user_resume_project import UserResumeProject
 from app.models.user_resume_work import UserResumeWork
-from app.tool.file_parser import parse_to_text
+from app.tool.file_parser import parse_to_segments
 from app.tool.snowflake import next_id
 
 
@@ -28,13 +28,13 @@ class ResumeService:
     async def parse_and_extract(self, filename: str, content: bytes) -> dict:
         """文件解析 + AI 两阶段并行结构化，不涉及数据库操作"""
         log.info(f"开始解析简历文件: {filename}")
-        text = await asyncio.to_thread(parse_to_text, filename, content)
-        if not text or not text.strip():
+        segments = await asyncio.to_thread(parse_to_segments, filename, content)
+        if not segments:
             raise ValueError("文件内容为空，无法解析")
-        log.info(f"文件解析完成，文本长度: {len(text)}")
+        log.info(f"文件解析完成，文本单元数: {len(segments)}")
 
         log.info("开始AI两阶段并行结构化提取")
-        parsed = await extract_all(text)
+        parsed = await extract_all(segments)
         log.info("AI两阶段并行结构化提取完成")
         return parsed