Add django

app/asgi.py

@@ -0,0 +1,16 @@
+"""
+ASGI config for app project.
+
+It exposes the ASGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/4.2/howto/deployment/asgi/
+"""
+
+import os
+
+from django.core.asgi import get_asgi_application
+
+os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'app.settings')
+
+application = get_asgi_application()

app/settings.py

@@ -0,0 +1,123 @@
+"""
+Django settings for app project.
+
+Generated by 'django-admin startproject' using Django 4.2.4.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/4.2/topics/settings/
+
+For the full list of settings and their values, see
+https://docs.djangoproject.com/en/4.2/ref/settings/
+"""
+
+from pathlib import Path
+
+# Build paths inside the project like this: BASE_DIR / 'subdir'.
+BASE_DIR = Path(__file__).resolve().parent.parent
+
+
+# Quick-start development settings - unsuitable for production
+# See https://docs.djangoproject.com/en/4.2/howto/deployment/checklist/
+
+# SECURITY WARNING: keep the secret key used in production secret!
+SECRET_KEY = 'django-insecure-qqr#f(i3uf%m8%8u35vn=ov-uk(*8!a&1t-hxa%ev2^t1%j&sm'
+
+# SECURITY WARNING: don't run with debug turned on in production!
+DEBUG = True
+
+ALLOWED_HOSTS = []
+
+
+# Application definition
+
+INSTALLED_APPS = [
+    'django.contrib.admin',
+    'django.contrib.auth',
+    'django.contrib.contenttypes',
+    'django.contrib.sessions',
+    'django.contrib.messages',
+    'django.contrib.staticfiles',
+]
+
+MIDDLEWARE = [
+    'django.middleware.security.SecurityMiddleware',
+    'django.contrib.sessions.middleware.SessionMiddleware',
+    'django.middleware.common.CommonMiddleware',
+    'django.middleware.csrf.CsrfViewMiddleware',
+    'django.contrib.auth.middleware.AuthenticationMiddleware',
+    'django.contrib.messages.middleware.MessageMiddleware',
+    'django.middleware.clickjacking.XFrameOptionsMiddleware',
+]
+
+ROOT_URLCONF = 'app.urls'
+
+TEMPLATES = [
+    {
+        'BACKEND': 'django.template.backends.django.DjangoTemplates',
+        'DIRS': [],
+        'APP_DIRS': True,
+        'OPTIONS': {
+            'context_processors': [
+                'django.template.context_processors.debug',
+                'django.template.context_processors.request',
+                'django.contrib.auth.context_processors.auth',
+                'django.contrib.messages.context_processors.messages',
+            ],
+        },
+    },
+]
+
+WSGI_APPLICATION = 'app.wsgi.application'
+
+
+# Database
+# https://docs.djangoproject.com/en/4.2/ref/settings/#databases
+
+DATABASES = {
+    'default': {
+        'ENGINE': 'django.db.backends.sqlite3',
+        'NAME': BASE_DIR / 'db.sqlite3',
+    }
+}
+
+
+# Password validation
+# https://docs.djangoproject.com/en/4.2/ref/settings/#auth-password-validators
+
+AUTH_PASSWORD_VALIDATORS = [
+    {
+        'NAME': 'django.contrib.auth.password_validation.UserAttributeSimilarityValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.MinimumLengthValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.CommonPasswordValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.NumericPasswordValidator',
+    },
+]
+
+
+# Internationalization
+# https://docs.djangoproject.com/en/4.2/topics/i18n/
+
+LANGUAGE_CODE = 'en-us'
+
+TIME_ZONE = 'UTC'
+
+USE_I18N = True
+
+USE_TZ = True
+
+
+# Static files (CSS, JavaScript, Images)
+# https://docs.djangoproject.com/en/4.2/howto/static-files/
+
+STATIC_URL = 'static/'
+
+# Default primary key field type
+# https://docs.djangoproject.com/en/4.2/ref/settings/#default-auto-field
+
+DEFAULT_AUTO_FIELD = 'django.db.models.BigAutoField'

app/urls.py

@@ -0,0 +1,22 @@
+"""
+URL configuration for app project.
+
+The `urlpatterns` list routes URLs to views. For more information please see:
+    https://docs.djangoproject.com/en/4.2/topics/http/urls/
+Examples:
+Function views
+    1. Add an import:  from my_app import views
+    2. Add a URL to urlpatterns:  path('', views.home, name='home')
+Class-based views
+    1. Add an import:  from other_app.views import Home
+    2. Add a URL to urlpatterns:  path('', Home.as_view(), name='home')
+Including another URLconf
+    1. Import the include() function: from django.urls import include, path
+    2. Add a URL to urlpatterns:  path('blog/', include('blog.urls'))
+"""
+from django.contrib import admin
+from django.urls import path
+
+urlpatterns = [
+    path('admin/', admin.site.urls),
+]

app/wsgi.py

@@ -0,0 +1,16 @@
+"""
+WSGI config for app project.
+
+It exposes the WSGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/4.2/howto/deployment/wsgi/
+"""
+
+import os
+
+from django.core.wsgi import get_wsgi_application
+
+os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'app.settings')
+
+application = get_wsgi_application()

manage.py

@@ -0,0 +1,22 @@
+#!/usr/bin/env python
+"""Django's command-line utility for administrative tasks."""
+import os
+import sys
+
+
+def main():
+    """Run administrative tasks."""
+    os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'app.settings')
+    try:
+        from django.core.management import execute_from_command_line
+    except ImportError as exc:
+        raise ImportError(
+            "Couldn't import Django. Are you sure it's installed and "
+            "available on your PYTHONPATH environment variable? Did you "
+            "forget to activate a virtual environment?"
+        ) from exc
+    execute_from_command_line(sys.argv)
+
+
+if __name__ == '__main__':
+    main()

poetry.lock

@@ -387,6 +387,27 @@ files = [
     {file = "cymem-2.0.7.tar.gz", hash = "sha256:e6034badb5dd4e10344211c81f16505a55553a7164adc314c75bd80cf07e57a8"},
 ]
 
+[[package]]
+name = "django"
+version = "4.2.4"
+description = "A high-level Python web framework that encourages rapid development and clean, pragmatic design."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "Django-4.2.4-py3-none-any.whl", hash = "sha256:860ae6a138a238fc4f22c99b52f3ead982bb4b1aad8c0122bcd8c8a3a02e409d"},
+    {file = "Django-4.2.4.tar.gz", hash = "sha256:7e4225ec065e0f354ccf7349a22d209de09cc1c074832be9eb84c51c1799c432"},
+]
+
+[package.dependencies]
+asgiref = ">=3.6.0,<4"
+sqlparse = ">=0.3.1"
+tzdata = {version = "*", markers = "sys_platform == \"win32\""}
+
+[package.extras]
+argon2 = ["argon2-cffi (>=19.1.0)"]
+bcrypt = ["bcrypt"]
+
 [[package]]
 name = "exceptiongroup"
 version = "1.1.1"
@@ -1687,6 +1708,23 @@ files = [
     {file = "spacy_loggers-1.0.4-py3-none-any.whl", hash = "sha256:e050bf2e63208b2f096b777e494971c962ad7c1dc997641c8f95c622550044ae"},
 ]
 
+[[package]]
+name = "sqlparse"
+version = "0.4.4"
+description = "A non-validating SQL parser."
+category = "main"
+optional = false
+python-versions = ">=3.5"
+files = [
+    {file = "sqlparse-0.4.4-py3-none-any.whl", hash = "sha256:5430a4fe2ac7d0f93e66f1efc6e1338a41884b7ddf2a350cedd20ccc4d9d28f3"},
+    {file = "sqlparse-0.4.4.tar.gz", hash = "sha256:d446183e84b8349fa3061f0fe7f06ca94ba65b426946ffebe6e3e8295332420c"},
+]
+
+[package.extras]
+dev = ["build", "flake8"]
+doc = ["sphinx"]
+test = ["pytest", "pytest-cov"]
+
 [[package]]
 name = "srsly"
 version = "2.4.6"
@@ -1890,6 +1928,18 @@ files = [
     {file = "typing_extensions-4.5.0.tar.gz", hash = "sha256:5cb5f4a79139d699607b3ef622a1dedafa84e115ab0024e0d9c044a9479ca7cb"},
 ]
 
+[[package]]
+name = "tzdata"
+version = "2023.3"
+description = "Provider of IANA time zone data"
+category = "main"
+optional = false
+python-versions = ">=2"
+files = [
+    {file = "tzdata-2023.3-py2.py3-none-any.whl", hash = "sha256:7e65763eef3120314099b6939b5546db7adce1e7d6f2e179e3df563c70511eda"},
+    {file = "tzdata-2023.3.tar.gz", hash = "sha256:11ef1e08e54acb0d4f95bdb1be05da659673de4acbd21bf9c69e94cc5e907a3a"},
+]
+
 [[package]]
 name = "ujson"
 version = "4.3.0"
@@ -2069,9 +2119,9 @@ cffi = {version = ">=1.11", markers = "platform_python_implementation == \"PyPy\
 cffi = ["cffi (>=1.11)"]
 
 [extras]
-indexer = ["ujson", "warcio", "idna", "beautifulsoup4", "lxml", "jusText", "langdetect", "pyarrow", "pyspark", "Levenshtein"]
+indexer = ["ujson", "warcio", "idna", "beautifulsoup4", "lxml", "langdetect", "pyarrow", "pyspark", "Levenshtein"]
 
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.10,<3.11"
-content-hash = "65eb26c5a9dda0e504632fa433334157fe5c1cbe19135ab18d59c74f47249a0b"
+content-hash = "b40fcb8fc85427fe91b9ba334eaa21bc58c746471650121fbf0846c859c6999e"

pyproject.toml

@@ -33,6 +33,7 @@ langdetect = {version= "==1.0.9", optional = true}
 pyarrow = {version= "==6.0.0", optional = true}
 pyspark = {version= "==3.2.0", optional = true}
 Levenshtein = {version= "==0.16.0", optional = true}
+django = "^4.2.4"
 
 [tool.poetry.extras]
 indexer = [