Phase2/HuyDN: update cv_matching and question_test_retrieval

app/modules/crud_cvs/models/crud_cvs.py

@@ -1,5 +1,7 @@
 import uuid
 from app.configs.database import firebase_bucket, firebase_db
+import io
+from docx import Document
 
 # CRUD operation
 def upload_file_cvs(file):
@@ -16,11 +18,22 @@ def remove_file_cvs(file_url):
     blob.delete()
     return True
 
-def download_file_cvs(file_url):
+def file_cv_doc2text(file_url):
     # download file from firebase storage using "gs://" link
     blob = firebase_bucket.blob(file_url.split(f"gs://{firebase_bucket.name}/")[1])
     # download file and return string in file
-    return blob.download_as_text()
+    file_bytes = blob.download_as_bytes()
+    # Create a BytesIO object from the file bytes
+    file_stream = io.BytesIO(file_bytes)
+    # Read the .docx file from the BytesIO object
+    doc = Document(file_stream)
+    # Extract text from the .docx file
+    text = ""
+    for paragraph in doc.paragraphs:
+        text += paragraph.text + "\n"
+    
+    return text
+
 
 def get_all_cvs():
     # Get all documents from the collection

app/modules/crud_jds/models/crud_jds.py

@@ -17,7 +17,7 @@ def remove_file_jds(file_url):
     blob.delete()
     return True
 
-def download_file_jds(file_url):
+def file_jd_txt2text(file_url):
     # download file from firebase storage using "gs://" link
     blob = firebase_bucket.blob(file_url.split(f"gs://{firebase_bucket.name}/")[1])
     # download file and return string in file

app/modules/matching_cv/__init__.py

@@ -1,9 +1,11 @@
 import docx
 
 from fastapi import APIRouter
-from app.modules.matching_cv.models.match_cv_jd_model import Match_JD_CV_Model
+# from app.modules.matching_cv.models.match_cv_jd_model import Match_JD_CV_Model
 
 from app.modules.matching_cv.models.matching_cv_logic import result_matching_cv_jd
+from app.modules.crud_jds.models.crud_jds import get_jd_by_id, file_jd_txt2text
+from app.modules.crud_cvs.models.crud_cvs import get_cv_by_id, file_cv_doc2text
 
 cvmatching_router = APIRouter(prefix="/cvmatching", tags=["cvmatching"])
 
@@ -15,7 +17,28 @@ async def index():
 # only upload .pdf or .docx file
 async def matching_cv_jd(id_jd: str, id_cv:str):
     try:
-        pass
+        # get jd and cv by id
+        jd_document = get_jd_by_id(id_jd)
+        cv_document = get_cv_by_id(id_cv)
+
+        # download file from firebase storage
+        jd_url = jd_document["jd_url"]
+        cv_url = cv_document["cv_url"]
+
+        # get type file cv from cv_url "gs://bucket_name/file_name"
+        cv_type = cv_url.split(".")[-1]
+        if cv_type == "pdf":
+            return {"message": "This feature is not available yet"}
+        elif cv_type == "docx":
+            cv_text = file_cv_doc2text(cv_url)
+        else:
+            return {"message": "Please upload only .pdf or .docx file for CV"}
+
+        # get jd_text from jd_url "gs://bucket_name/file_name"
+        jd_text = file_jd_txt2text(jd_url)
+
+        result = result_matching_cv_jd(cv_text, jd_text)
+        return {"result": result}
         # # take jd_upload and cv_upload type file
         # jd_upload_type = jd_upload.filename.split(".")[-1]
         # cv_upload_type = cv_upload.filename.split(".")[-1]

app/modules/question_tests_retrieval/__init__.py

@@ -3,7 +3,7 @@ from typing import Annotated
 
 from app.modules.question_tests_retrieval.models.jd2text import jobdes2text
 from app.modules.question_tests_retrieval.models.question_tests_logic import get_question_tests
-from app.modules.crud_jds.models.crud_jds import get_jd_by_id, download_file_jds
+from app.modules.crud_jds.models.crud_jds import get_jd_by_id, file_jd_txt2text
 
 qtretrieval_router = APIRouter(prefix="/qtretrieval", tags=["qtretrieval"])
 
@@ -17,7 +17,7 @@ async def send_jd_to_get_question(id_jd: str):
     try:
         jd_document = get_jd_by_id(id_jd)
         # download jd file from firebase storage
-        jd_file_string = download_file_jds(jd_document["jd_url"])
+        jd_file_string = file_jd_txt2text(jd_document["jd_url"])
         sumaryjd_text = jobdes2text(jd_file_string)
         if get_question_tests(sumaryjd_text):
             return {"message": "Send JD successfully and get question test successfully",