Merge pull request #68 from DocShow-AI/add_flake8

Add flake8

.github/workflows/python-black.yml → .github/workflows/python-quality.yml

@@ -1,4 +1,4 @@
-name: Python Black Formatting Check
+name: Python Code Quality Check
 
 on: 
   pull_request:
@@ -15,10 +15,13 @@ jobs:
     - name: Set up Python
       uses: actions/setup-python@v2
       with:
-        python-version: '3.8'  # Specify the Python version
+        python-version: '3.8'
 
     - name: Install Black
-      run: pip install black
+      run: pip install black flake8
 
     - name: Check Python code formatting with Black
       run: black --check backend/
+
+    - name: Check Python code style with Flake8
+      run: flake8 backend/

.pre-commit-config.yaml

@@ -1,7 +1,12 @@
 repos:
 -   repo: https://github.com/psf/black
-    rev: 23.11.0  # Use a specific version or 'stable' for the latest stable release
+    rev: 23.11.0  
     hooks:
     -   id: black
         language_version: python3  # Ensure black uses the correct version of Python
         files: ^backend/  # Run black only on files in the backend/ directory
+-   repo: https://github.com/PyCQA/flake8
+    rev: 6.1.0
+    hooks:
+    -   id: flake8
+        files: ^backend/  # Run flake8 only on files in the backend/ directory

backend/databases/data_profile_manager.py

@@ -1,4 +1,3 @@
-from sqlalchemy.orm import Session
 from models.data_profile import DataProfile
 
 

backend/envs/dev/utils.py

@@ -1,6 +1,3 @@
-from sqlalchemy import MetaData, Table
-from sqlalchemy.schema import CreateTable
-
 from databases.database_manager import DatabaseManager
 from databases.sql_executor import SQLExecutor
 from databases.table_manager import TableManager
@@ -36,7 +33,7 @@ def seed_db():
     # Create sample table if it doesn't exist
     table_manager = TableManager()
     if "sample_sales" not in existing_tables:
-        df = pd.read_csv(f"envs/dev/sample_data/sample_sales_data.csv")
+        df = pd.read_csv("envs/dev/sample_data/sample_sales_data.csv")
         df.columns = map(str.lower, df.columns)
         table_manager.create_table_from_df(df, "sample_sales")
 
@@ -47,38 +44,41 @@ def seed_db():
                 table_name="sample_sales",
                 create_query="""
                     CREATE TABLE sample_sales (
-                        ordernumber BIGINT, 
-                        quantityordered BIGINT, 
-                        priceeach DOUBLE PRECISION, 
-                        orderlinenumber BIGINT, 
-                        sales DOUBLE PRECISION, 
-                        orderdate TEXT, 
-                        status TEXT, 
-                        qtr_id BIGINT, 
-                        month_id BIGINT, 
-                        year_id BIGINT, 
-                        productline TEXT, 
-                        msrp BIGINT, 
-                        productcode TEXT, 
-                        customername TEXT, 
-                        phone TEXT, 
-                        addressline1 TEXT, 
-                        addressline2 TEXT, 
-                        city TEXT, 
-                        state TEXT, 
-                        postalcode TEXT, 
-                        country TEXT, 
-                        territory TEXT, 
-                        contactlastname TEXT, 
-                        contactfirstname TEXT, 
+                        ordernumber BIGINT,
+                        quantityordered BIGINT,
+                        priceeach DOUBLE PRECISION,
+                        orderlinenumber BIGINT,
+                        sales DOUBLE PRECISION,
+                        orderdate TEXT,
+                        status TEXT,
+                        qtr_id BIGINT,
+                        month_id BIGINT,
+                        year_id BIGINT,
+                        productline TEXT,
+                        msrp BIGINT,
+                        productcode TEXT,
+                        customername TEXT,
+                        phone TEXT,
+                        addressline1 TEXT,
+                        addressline2 TEXT,
+                        city TEXT,
+                        state TEXT,
+                        postalcode TEXT,
+                        country TEXT,
+                        territory TEXT,
+                        contactlastname TEXT,
+                        contactfirstname TEXT,
                         dealsize TEXT)
                 """,
                 description="""
-                    The sample_sales table is designed for storing detailed sales transaction records. 
-                    It includes fields for order details (order number, quantity ordered, price per item, line number, total sales), date and status of the order, and temporal identifiers (quarter, month, and year). 
-                    Product information is detailed through product line, manufacturer's suggested retail price (MSRP), and product code. 
-                    Customer information is comprehensive, encompassing name, contact details, and address (with provisions for a second address line), along with geographical data like city, state, postal code, country, and sales territory. 
-                    Additional fields for contact person's name and the size of the deal are also included. 
-                    This table is suitable for categorizing detailed sales transactions and can support queries for sales analytics, customer segmentation, geographical sales trends, and time-based sales performance.
+                    The sample_sales table is designed for storing detailed sales transaction records.
+                    It includes fields for order details (order number, quantity ordered, price per item, line number, total sales), date and status of the order, and temporal identifiers
+                    (quarter, month, and year).
+                    Product information is detailed through product line, manufacturer's suggested retail price (MSRP), and product code.
+                    Customer information is comprehensive, encompassing name, contact details, and address (with provisions for a second address line),
+                    along with geographical data like city, state, postal code, country, and sales territory.
+                    Additional fields for contact person's name and the size of the deal are also included.
+                    This table is suitable for categorizing detailed sales transactions and can support queries for sales analytics, customer segmentation, geographical sales trends,
+                    and time-based sales performance.
                 """,
             )

backend/llms/base.py

@@ -21,9 +21,6 @@ def generate_table_desc(
     ) -> str:
         raise NotImplementedError
 
-    def generate_text(self, input_text):
-        raise NotImplementedError
-
     def fetch_table_name_from_sample(
         self, sample_content: str, extra_desc: str, table_metadata: str
     ):

backend/models/data_profile.py

@@ -1,5 +1,4 @@
-from sqlalchemy import Boolean, Column, DateTime, Integer, String, ForeignKey
-from sqlalchemy.sql import func
+from sqlalchemy import Column, Integer, String, ForeignKey
 from pydantic import BaseModel
 
 from .base import Base

backend/routes/auth_routes.py

@@ -135,7 +135,8 @@ async def register(response: Response, user: UserCreate):
     """
     Register a new user and set a JWT token in a cookie upon successful registration.
 
-    This endpoint registers a new user with the provided details. It checks for the uniqueness of the username and email. If the registration is successful, it creates a JWT token, sets it in a secure, HttpOnly cookie in the response, and returns a success message.
+    This endpoint registers a new user with the provided details. It checks for the uniqueness of the username and email. If the registration is successful, it creates a JWT token,
+    sets it in a secure, HttpOnly cookie in the response, and returns a success message.
 
     Args:
         user (UserCreate): Pydantic model containing the user's registration details, such as username, email, and password.
@@ -165,7 +166,7 @@ async def register(response: Response, user: UserCreate):
 
         # Generate access token
         access_token_expires = timedelta(minutes=ACCESS_TOKEN_EXPIRE_MINUTES)
-        access_token = create_access_token(
+        access_token = create_token(
             data={"sub": user.username}, expires_delta=access_token_expires
         )
 

backend/routes/table_routes.py

@@ -1,6 +1,5 @@
 from fastapi import APIRouter, Depends
 from security import get_current_user
-from typing import Annotated
 
 from databases.database_manager import DatabaseManager
 from databases.sql_executor import SQLExecutor

backend/routes/user_routes.py

@@ -1,6 +1,5 @@
 from fastapi import APIRouter, Depends, HTTPException
-from security import get_current_admin_user, get_current_user, oauth2_scheme
-from typing import Annotated
+from security import get_current_admin_user, get_current_user
 
 from models.user import User, UserOut, UserRole, UserUpdate
 from databases.database_manager import DatabaseManager

backend/security.py

@@ -3,7 +3,6 @@
 from fastapi.security import OAuth2PasswordBearer
 from jose import jwt, JWTError
 from passlib.context import CryptContext
-from typing import Annotated
 
 from databases.database_manager import DatabaseManager
 from databases.user_manager import UserManager

backend/utils/nivo_assistant.py

@@ -98,7 +98,8 @@ def get_bar_params(self):
                 "string | (value: number) => string | number optional",
                 "Optional formatter for values.",
                 "The formatted value can then be used for labels & tooltips.",
-                "Under the hood, nivo uses d3-format, please have a look at it for available formats, you can also pass a function which will receive the raw value and should return the formatted one.",
+                "Under the hood, nivo uses d3-format, please have a look at it for available formats, you can also pass a function which will receive the raw value and should return the \
+                 formatted one.",
             ],
             "padding": [
                 "number optional default:0.1",
@@ -159,14 +160,17 @@ def get_bar_params(self):
                 "Defines the order of layers.",
                 "support svg canvas",
                 "Defines the order of layers, available layers are: grid, axes, bars, markers, legends, annotations. The markers layer is not available in the canvas flavor.",
-                "You can also use this to insert extra layers to the chart, this extra layer must be a function which will receive the chart computed data and must return a valid SVG element.",
+                "You can also use this to insert extra layers to the chart, this extra layer must be a function which will receive the chart computed data and must return a valid SVG \
+                 element.",
             ],
             "enableLabel": ["boolean optional default:true", "Enable/disable labels."],
             "label": [
                 "string | Function optional default:'formattedValue'",
                 "Define how bar labels are computed.",
                 "By default it will use the bar's value. It accepts a string which will be used to access a specific bar data property, such as 'value' or 'id'.",
-                "You can also use a funtion if you want to add more logic, this function will receive the current bar's data and must return the computed label which, depending on the context, should return a string or an svg element (Bar) or a string (BarCanvas). For example let's say you want to use a label with both the id and the value, you can achieve this with: label={d => `${d.id}: ${d.value}`}",
+                "You can also use a funtion if you want to add more logic, this function will receive the current bar's data and must return the computed label which, depending on the \
+                 context, should return a string or an svg element (Bar) or a string (BarCanvas). For example let's say you want to use a label with both the id and the value, you can \
+                 achieve this with: label={d => `${d.id}: ${d.value}`}",
             ],
             "labelSkipWidth": [
                 "number optional default:0",
@@ -200,7 +204,8 @@ def get_bar_params(self):
                 "Function optional",
                 "Tooltip custom component",
                 "support svg canvas",
-                "A function allowing complete tooltip customisation, it must return a valid HTML element and will receive the following data: {bar: {id:             string | number,value:          number,formattedValue: string,index:          number,indexValue:     string | number,// datum associated to the current index (raw data)data:           object},color: string,label: string}",
+                "A function allowing complete tooltip customisation, it must return a valid HTML element and will receive the following data: {bar: {id: string | number,value: number,\
+                 formattedValue: string,index: number,indexValue: string | number,// datum associated to the current index (raw data)data: object},color: string,label: string}",
             ],
             "legends": ["object[] optional", "Optional chart's legends."],
         }