Merge branch 'dev' of http://106.13.42.156:33077/lei_y601/yj_resume

db/sql_db.py

@@ -4,7 +4,7 @@ from sqlalchemy.orm import declarative_base, sessionmaker
 Base = declarative_base()
 from decouple import config
 
-DB_PATH = config('DB_PATH', default='D://PycharmProject//yj_resume//main.sqlite3')
+DB_PATH = config('DB_PATH', default='E://pyptoject//yj_resume//main.sqlite3')
 
 
 class DBTASK(Base):

main.py

@@ -2,7 +2,7 @@ from fastapi import FastAPI
 import uvicorn
 from fastapi import FastAPI, File, UploadFile, HTTPException
 from typing import List
-from service.file_service import check_and_create_directory, upload_and_save_file,fetch_files
+from service.file_service import check_and_create_directory, upload_and_save_file, fetch_files
 from service import excel_service
 from service.db_service import get_task_list
 from fastapi.responses import FileResponse
@@ -14,7 +14,8 @@ logger = logging.getLogger(__name__)
 
 app = FastAPI()
 
-
+import concurrent.futures
+executor = concurrent.futures.ThreadPoolExecutor(max_workers=10)
 @app.get("/api/v1/hw")
 def read_root():
     return {"Hello": "World"}
@@ -26,11 +27,12 @@ async def create_upload_files(files: List[UploadFile] = File(...)):
     dir_id = check_and_create_directory(files)
     if not dir_id:
         return {"result": False, "code": 500, "message": "create directory failed"}
-    flag, message= await upload_and_save_file(dir_id, files)
+    flag, message = await upload_and_save_file(dir_id, files)
     logger.info(f"flag is {flag}")
     if flag:
-       flag,message = await fetch_files(dir_id)
-    return {"result": flag, "message": message,"task_id": dir_id}
+        #flag, message = await fetch_files(dir_id)
+        executor.submit(fetch_files, dir_id)
+    return {"result": flag, "message": message, "task_id": dir_id}
 
 
 @app.get("/export_task_data_to_excel")
@@ -52,4 +54,5 @@ def parse_task_list():
 
 
 if __name__ == '__main__':
-    uvicorn.run(app, host="127.0.0.1", port=3006)
+    logger.info("start server")
+    uvicorn.run(app, host="0.0.0.0", port=3006)

service/excel_service.py

@@ -4,8 +4,8 @@ import pandas as pd
 import pathlib
 from decouple import config
 
-# BASE_PATH = config('BASE_PATH', default='E://pyptoject//yj_resume//')
-BASE_PATH = config('BASE_PATH', default='D://PycharmProject//yj_resume//')
+BASE_PATH = config('BASE_PATH', default='E://pyptoject//yj_resume//')
+#BASE_PATH = config('BASE_PATH', default='D://PycharmProject//yj_resume//uploads//')
 
 
 # 导出数据到excel

service/file_service.py

@@ -16,15 +16,16 @@ import logging
 from service.parse_resume2_doc import extra_resume
 
 logger = logging.getLogger(__name__)
-BASE_PATH = config('BASE_PATH', default='D://PycharmProject//yj_resume//')
-
+#BASE_PATH = config('BASE_PATH', default='D://PycharmProject//yj_resume//uploads//')
 
+BASE_PATH = config('BASE_PATH', default='E://pyptoject//yj_resume//')
 
 
 def check_and_create_directory(files):
     logger.info("check_and_create_directory in service")
     # 先创建一个task
     if not files or len(files) == 0:
+        logger.warning("check_and_create_directory is empty")
         return None
     id = str(uuid.uuid4())
     current_time = datetime.now()
@@ -68,17 +69,17 @@ async def upload_and_save_file(dir_id, files: List[UploadFile]) -> (bool, str):
     except Exception as e:
         print(f"Failed to save DBRESUME  error {e}")
         session.rollback()
-        return False, f"Failed to save DBRESUME  error {e}",[]
+        return False, f"Failed to save DBRESUME  error {e}"
     finally:
         session.close()
     return True, "success"
 
-async def fetch_files(dir_id) -> (bool, str):
+def fetch_files(dir_id) -> (bool, str):
 
     logger.info(f"start fetching files task {dir_id} in service")
     if not os.path.exists(BASE_PATH):
         logger.info(f"目录{BASE_PATH}不存在")
-        return None
+        return False, f"Failed to fetch file 目录{BASE_PATH}不存在"
     file_extensions = ['.docx', '.doc']
     files_list = []
     dir_path = pathlib.Path(BASE_PATH).joinpath(dir_id)

service/parse_resume2_doc.py

@@ -124,10 +124,12 @@ class EnhancedDocxExtractor:
             spec_coll = ['全日制教育','在职教育']
             if current_key_cell['text'].replace('\n','') in spec_coll :
                 if not value_cell['text']:
-                    value_cell['text'] = 'False'
+                    value_cell['text'] = "否"
                 else:
-                    value_cell['text'] = 'True'
+                    value_cell['text'] = '是'
 
+            if not value_cell['text']:
+                value_cell['text'] = "None"
             if value_cell['text'] and (key_row, key_col + 1) not in visited:
                 # 检查这个值是否与前一个键提取的值相同（可能是合并单元格）
                 if not self._is_key_duplicate_merged_cell(structure[key_row][key_col]['text'], kv_pairs):