Update cv_quality.py

cv_quality.py

@@ -1,51 +1,38 @@
-from pdf2image import convert_from_path
-import os 
-from paddleocr import PaddleOCR
-from ftlangdetect import detect
-import re 
-from helpers import get_email,get_number 
-from langchain_community.document_loaders import UnstructuredPDFLoader,CSVLoader,PyPDFium2Loader,PyMuPDFLoader, Docx2txtLoader
-from langchain_community.llms import HuggingFaceEndpoint
+import os
+from langchain_community.document_loaders import CSVLoader, PyMuPDFLoader, Docx2txtLoader
 from dotenv import load_dotenv
-from langchain import hub
-import json
 from yolo_text_extraction import pdf_to_text
-from cv_analyser import analyse_cv
+from cv_analyzer import analyze_cv
 
 load_dotenv()
 
-
-class CV(): 
-    
-    def __init__(self,file_name):
-
-        self.file_name=file_name
-        
-        self.doc_loader = {".csv":CSVLoader(self.file_name),".pdf":PyMuPDFLoader(self.file_name),
-                           ".docx": Docx2txtLoader(file_name)}
-        
+class CV:
+    def __init__(self, file_name):
+        self.file_name = file_name
+        self.doc_loader = {
+            ".csv": CSVLoader(self.file_name),
+            ".pdf": PyMuPDFLoader(self.file_name),
+            ".docx": Docx2txtLoader(file_name)
+        }
 
     def get_cv_text(self):
-        
         _, ext = os.path.splitext(self.file_name)
         if ext in self.doc_loader.keys():
             loader = self.doc_loader[ext]
             data = loader.load()
             if len(data) != 0:
-                text = "\n".join([ page.page_content for page in data])
-                if len(text.split()) ==0 : 
+                text = "\n".join([page.page_content for page in data])
+                if len(text.split()) == 0:
                     text = pdf_to_text(self.file_name)
-                
                 return text
-
+            else:
+                text = pdf_to_text(self.file_name)
+                return text
         else:
             text = pdf_to_text(self.file_name)
-            
             return text
 
     def analyse_cv_quality(self):
-          cv_text=self.get_cv_text()
-          result=analyse_cv(cv_text)
-          return result
-    
-       
+        cv_text = self.get_cv_text()
+        result = analyze_cv(cv_text)
+        return result