update - route of uploading students list - add additional handling with potential errors

backend/app/__init__.py

@@ -9,6 +9,7 @@ from .dependencies import db, ma
 from .commands.startapp import startapp
 from .utils import import_models
 from .api import api_bp
+from .errors import request_entity_too_large
 
 
 def create_app(config_name: str = None) -> Flask:
@@ -35,4 +36,7 @@ def create_app(config_name: str = None) -> Flask:
     # register commands
     app.cli.add_command(startapp)
 
+    # register errors
+    app.register_error_handler(413, request_entity_too_large)
+
     return app

backend/app/base/utils.py

@@ -1,5 +1,6 @@
 from typing import TypedDict, Tuple
 
+from flask import current_app
 from flask_sqlalchemy import BaseQuery
 from sqlalchemy import desc
 
@@ -36,3 +37,8 @@ def paginate_models(page: str, query: BaseQuery) -> PaginationResponse or Tuple[
         'items': query.items,
         'max_pages': query.pages
     }
+
+
+def is_allowed_extensions(filename: str):
+    return '.' in filename and \
+           filename.rsplit('.', 1)[1].lower() in current_app.config['ALLOWED_EXTENSIONS']

backend/app/config.py

@@ -8,8 +8,12 @@ class Config:
     BASE_DIR = Path(__file__).resolve().parent.parent
     SRC_DIR = BASE_DIR / "app"
     EXCLUDED_DIRS = ["__pycache__", "commands"]
+
     ENABLE_CORS = os.environ.get('ENABLE_CORS') or False
 
+    ALLOWED_EXTENSIONS = {'csv'}
+    MAX_CONTENT_LENGTH = 10 * 1024 * 1024  # 10 MB
+
     SQLALCHEMY_TRACK_MODIFICATIONS = False
     SQLALCHEMY_DATABASE_URI = f'sqlite:///{BASE_DIR / "db.sqlite"}'
 

backend/app/coordinator/routes/students.py

@@ -1,8 +1,10 @@
 from typing import Tuple
 from random import randint
+from itertools import islice
 
 from flask import Blueprint, request, Response
 from marshmallow import ValidationError
+from sqlalchemy.exc import IntegrityError
 from flask_sqlalchemy import get_debug_queries
 
 from ...students.models import Student
@@ -10,7 +12,7 @@ from ..schemas import StudentSchema, StudentEditSchema, StudentCreateSchema
 from ...dependencies import db
 from ..utils import parse_csv
 from ..exceptions import InvalidNameOrTypeHeaderException
-from ...base.utils import paginate_models
+from ...base.utils import paginate_models, is_allowed_extensions
 
 bp = Blueprint("students", __name__, url_prefix="/students")
 
@@ -30,7 +32,7 @@ def list_students() -> Tuple[dict, int]:
     response = paginate_models(page, student_query)
     if isinstance(response, tuple):
         return response
-    print(get_debug_queries()[0])
+    # print(get_debug_queries()[0])
     return {"students": students_schema.dump(response['items']), "max_pages": response['max_pages']}, 200
 
 
@@ -100,15 +102,29 @@ def create_student() -> Tuple[dict, int] or Response:
 @bp.route("/upload/", methods=["POST"])
 def upload_students() -> Tuple[dict, int]:
     """Maybe in the future move to celery workers"""
-    if (uploaded_file := request.files.get('file')) is None:
+    if (uploaded_file := request.files.get('file')) is None or uploaded_file.filename == '':
         return {"error": "You didn't attach a csv file!"}, 400
 
+    if uploaded_file and is_allowed_extensions(uploaded_file.filename):
         try:
             students = parse_csv(uploaded_file)
         except InvalidNameOrTypeHeaderException:
             return {"error": "Invalid format of csv file!"}, 400
 
-    for student in students:
+        try:
-        db.session.add(student)
+            while True:
+                sliced_students = islice(students, 5)
+                list_of_students = list(sliced_students)
+
+                if len(list_of_students) == 0:
+                    break
+                db.session.add_all(list_of_students)
                 db.session.commit()
+        except IntegrityError as e:
+            # print(e)
+            # in the future create sql query checks index and add only these students, which didn't exist in db
+            return {"error": "These students have already exist!"}, 400
+    else:
+        return {"error": "Invalid extension of file"}, 400
+
     return {"message": "Students was created by uploading csv file!"}, 200

backend/app/coordinator/utils.py

@@ -1,4 +1,4 @@
-from typing import List
+from typing import Generator, Any
 from random import randint
 
 import pandas as pd
@@ -7,31 +7,29 @@ from .exceptions import InvalidNameOrTypeHeaderException
 from ..students.models import Student
 
 
-def check_columns(df: pd.DataFrame, columns: List[str]) -> bool:
+def check_columns(df: pd.DataFrame) -> bool:
+    headers = set(df.keys().values)
+    columns = ['first_name', 'last_name', 'index', 'mode']
+    if len(headers - set(columns)) != 0:
+        return False
+
     flag = True
     col_types = ['object', 'object', 'int', 'int']
-    print(df.dtypes['first_name'])
+
     for name, col_type in zip(columns, col_types):
-        if name not in df and df.dtypes[name].startswith(col_type):
+        if not str(df.dtypes[name]).startswith(col_type):
             flag = False
             break
 
     return flag
 
 
-def parse_csv(file) -> List[Student]:
+def parse_csv(file) -> Generator[Student, Any, None]:
     df = pd.read_csv(file)
-    columns = ['first_name', 'last_name', 'index', 'mode']
 
-    if not check_columns(df, columns):
+    if not check_columns(df):
         raise InvalidNameOrTypeHeaderException
 
-    students = []
+    students = (Student(**dict(item.items(), email=f'student{randint(1, 300_000)}@gmail.com'))
-    for _, item in df.iterrows():
+                for _, item in df.iterrows())
-        data = {}
-        for c in columns:
-            data[c] = item[c]
-        data['email'] = f'student{randint(1, 300_000)}@gmail.com'
-        students.append(Student(**data))
-
     return students

backend/app/errors.py

@@ -0,0 +1,7 @@
+from typing import Tuple
+
+from werkzeug.exceptions import RequestEntityTooLarge
+
+
+def request_entity_too_large(error: RequestEntityTooLarge) -> Tuple[dict, int]:
+    return {'error': 'File too large!'}, 413