Add social authentication and enhance database configuration

- Integrated social_django for Google OAuth2 authentication.
- Updated database settings to include MySQL alongside SQLite.
- Implemented logout functionality and adjusted URL routing.
- Enhanced author admin display with additional fields.
- Added search hierarchy functionality in views.
- Created a new home page template with user authentication checks.
- Established API endpoint for search functionality.
- Implemented cursor pagination in OpenAlex data scraping.
- Added database routing logic for core app.

BridgeMentor/routers.py

@@ -0,0 +1,21 @@
+class AppRouter:
+    def db_for_read(self, model, **hints):
+        if model._meta.app_label == 'core':
+            return 'sqlite'
+        return 'default'
+
+    def db_for_write(self, model, **hints):
+        if model._meta.app_label == 'core':
+            return 'sqlite'
+        return 'default'
+
+    def allow_relation(self, obj1, obj2, **hints):
+        # Allow relations if both models are in the same DB
+        db_obj1 = self.db_for_read(obj1)
+        db_obj2 = self.db_for_read(obj2)
+        return db_obj1 == db_obj2
+
+    def allow_migrate(self, db, app_label, model_name=None, **hints):
+        if app_label == 'core':
+            return db == 'sqlite'
+        return db == 'default'

BridgeMentor/settings.py

@@ -39,6 +39,7 @@ INSTALLED_APPS = [
     'django.contrib.staticfiles',
     'django_filters',
     'graphene_django',
+    'social_django',
     'core',
 ]
 
@@ -57,15 +58,19 @@ ROOT_URLCONF = 'BridgeMentor.urls'
 TEMPLATES = [
     {
         'BACKEND': 'django.template.backends.django.DjangoTemplates',
-        'DIRS': [],
+        'DIRS': ['core/templates'],
         'APP_DIRS': True,
         'OPTIONS': {
             'context_processors': [
+                'social_django.context_processors.backends',
+                'social_django.context_processors.login_redirect',
                 'django.template.context_processors.debug',
                 'django.template.context_processors.request',
                 'django.contrib.auth.context_processors.auth',
                 'django.contrib.messages.context_processors.messages',
+
             ],
+
         },
     },
 ]
@@ -77,12 +82,31 @@ WSGI_APPLICATION = 'BridgeMentor.wsgi.application'
 # https://docs.djangoproject.com/en/4.2/ref/settings/#databases
 
 DATABASES = {
-    'default': {
+    'sqlite': {
         'ENGINE': 'django.db.backends.sqlite3',
         'NAME': BASE_DIR / 'db.sqlite3',
-    }
+    },
+    'default': {
+        'ENGINE': 'django.db.backends.mysql',
+        'NAME': 'cybersan_bridgementor',
+        'USER': 'cybersan_bridgementor',
+        'PASSWORD': 'bridgementor',
+        'HOST': '192.250.235.27',  # or your MariaDB host
+        'PORT': '3306',        # default MariaDB port
+        'OPTIONS': {
+            'init_command': "SET sql_mode='STRICT_TRANS_TABLES'",
+        },
+    },
 }
 
+DATABASE_ROUTERS = ['BridgeMentor.routers.AppRouter']
+
+AUTHENTICATION_BACKENDS = (
+    'social_core.backends.open_id.OpenIdAuth',
+    'social_core.backends.google.GoogleOAuth2',
+    'social_core.backends.twitter.TwitterOAuth',
+    'django.contrib.auth.backends.ModelBackend',
+)
 
 # Password validation
 # https://docs.djangoproject.com/en/4.2/ref/settings/#auth-password-validators
@@ -128,3 +152,10 @@ DEFAULT_AUTO_FIELD = 'django.db.models.BigAutoField'
 GRAPHENE = {
     "SCHEMA": "core.schema.schema"  # Adjust to match your project
 }
+
+# SOCIAL_AUTH_REQUIRE_POST = True
+SOCIAL_AUTH_URL_NAMESPACE = 'social'
+
+SOCIAL_AUTH_GOOGLE_OAUTH2_KEY = '556457523-2d180pkqq6srm7rvg5veidjteqat3mvs.apps.googleusercontent.com'
+SOCIAL_AUTH_GOOGLE_OAUTH2_SECRET = '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'
+LOGIN_REDIRECT_URL = '/'

BridgeMentor/urls.py

@@ -16,10 +16,24 @@ Including another URLconf
 """
 from graphene_django.views import GraphQLView
 from django.contrib import admin
+from django.contrib.auth import logout
 from django.urls import path
+from django.urls import include
+from django.shortcuts import redirect
+
+
+def logout_view(request):
+    logout(request)
+    return redirect('/')
+
 
 urlpatterns = [
     path('admin/', admin.site.urls),
     path("graphql/", GraphQLView.as_view(graphiql=True)),
+    path("", include('social_django.urls', namespace="social")),
+    path('', include('core.urls')),  # routes '' to your home app
+    # routes '' to your home app
+    path('logout', logout_view, name='logout'),
+
 
 ]

core/admin.py

@@ -20,7 +20,7 @@ class InstitutionAdmin(admin.ModelAdmin):
 @admin.register(Author)
 class AuthorAdmin(admin.ModelAdmin):
     list_display = ('id', 'name', 'orcid', 'h_index',
-                    'i10_index', 'cited_by_count', 'works_count')
+                    'i10_index', 'cited_by_count', 'works_count', 'updated_at', 'created_at')
     search_fields = ('name', 'orcid')
     list_filter = ('h_index',)
 

core/templates/home.html

@@ -0,0 +1,48 @@
+<!-- home/templates/home/home.html -->
+<!DOCTYPE html>
+<html>
+  <head>
+    <title>My Home Page</title>
+  </head>
+
+  <body>
+    {% if user.is_authenticated %}
+      <span>Welcome, {{ user.first_name }}!</span> <a href="{% url 'logout' %}">Logout</a>
+    {% else %}
+      <a href="{% url 'social:begin' 'google-oauth2' %}">Login With Google</a>
+    {% endif %}
+
+    <h2>Search Domains</h2>
+    <input type="text" id="search-input" placeholder="Type something..." autocomplete="off" />
+    <ul id="results-list"></ul>
+
+    <script>
+      const input = document.getElementById('search-input')
+      const resultsList = document.getElementById('results-list')
+      
+      input.addEventListener('input', async () => {
+        const query = input.value.trim()
+        if (!query) {
+          resultsList.innerHTML = ''
+          return
+        }
+      
+        const res = await fetch(`/api/search/?q=${encodeURIComponent(query)}`)
+        const data = await res.json()
+      
+        resultsList.innerHTML = ''
+        data.results.forEach((item) => {
+          const li = document.createElement('li')
+      
+          const link = document.createElement('a')
+          link.href = `/${item.type.toLowerCase()}/${item.id}/`
+          link.textContent = item.text
+          link.style.textDecoration = 'none'
+          link.style.color = 'black'
+          li.appendChild(link)
+          resultsList.appendChild(li)
+        })
+      })
+    </script>
+  </body>
+</html>

core/urls.py

@@ -0,0 +1,7 @@
+from django.urls import path
+from .views import home_page, search_hierarchy
+
+urlpatterns = [
+    path('', home_page, name='home'),
+    path("api/search/", search_hierarchy, name="search-hierarchy"),
+]

core/views.py

@@ -1,3 +1,29 @@
+from .models import Domain, Field, Subfield, Topic
+from django.http import JsonResponse
 from django.shortcuts import render
 
-# Create your views here.
+
+def home_page(request):
+    return render(request, 'home.html')
+
+
+def search_hierarchy(request):
+    q = request.GET.get("q", "").strip()
+    if not q:
+        return JsonResponse({"results": []})
+
+    results = []
+
+    results += [{"id": d.id, "text": d.name, "type": "Domain"}
+                for d in Domain.objects.filter(name__icontains=q)]
+
+    results += [{"id": f.id, "text": f"{f.domain.name} > {f.name}", "type": "Field"}
+                for f in Field.objects.select_related("domain").filter(name__icontains=q)]
+
+    results += [{"id": s.id, "text": f"{s.field.domain.name} > {s.field.name} > {s.name}", "type": "Subfield"}
+                for s in Subfield.objects.select_related("field__domain").filter(name__icontains=q)]
+
+    results += [{"id": t.id, "text": f"{t.subfield.field.domain.name} > {t.subfield.field.name} > {t.subfield.name} > {t.name}", "type": "Topic"}
+                for t in Topic.objects.select_related("subfield__field__domain").filter(name__icontains=q)]
+
+    return JsonResponse({"results": sorted(results, key=lambda x: x["text"].lower())[:10]})

populate_user.py

@@ -20,7 +20,7 @@ def add_author(user_info, updated_date):
     author, _ = Author.objects.update_or_create(
         id=author_id,
         defaults={
-            "name": max(user_info['display_name_alternatives'], key=lambda name: len(name)),
+            "name": max(user_info['display_name_alternatives'] + [user_info['display_name']], key=lambda name: len(name)),
             "orcid": parse_id_from_url(user_info["orcid"]) if user_info.get("orcid") else None,
             "h_index": user_info["summary_stats"]["h_index"],
             "i10_index": user_info["summary_stats"]["i10_index"],
@@ -42,7 +42,7 @@ def add_institution(inst_data):
             "name": inst_data["display_name"],
             "ror_id": parse_id_from_url(inst_data["ror"]),
             "country_code": 'N/A' or inst_data.get("country_code"),
-            "institution_type": inst_data["type"]
+            "institution_type": 'N/A' or inst_data.get("institution_type")
         }
     )
     return inst

requirements.txt

@@ -1,3 +1,4 @@
 django==4.2.20
 graphene-django
-django-filter
+django-filter
+mysqlclient?

scrap_openalex.py

@@ -7,32 +7,41 @@ from time import sleep
 BASE_URL = "https://api.openalex.org/authors"
 FILTER = "last_known_institutions.country_code:NO,x_concepts.id:C41008148"
 PER_PAGE = 200
-TOTAL_RESULTS = 86500
-TOTAL_PAGES = (TOTAL_RESULTS + PER_PAGE - 1) // PER_PAGE  # Ceiling division
 
-# Output directory
 OUTPUT_DIR = "C41008148_authors"
 os.makedirs(OUTPUT_DIR, exist_ok=True)
 
-# Loop through pages
-for page in range(50, TOTAL_PAGES + 1):
-    url = f"{BASE_URL}?filter={FILTER}&per-page={PER_PAGE}&page={page}"
+# Initialize cursor
+cursor = "*"
+page_count = 1  # Track page numbers for saving files
+
+while cursor:
+    url = f"{BASE_URL}?filter={FILTER}&per-page={PER_PAGE}&cursor={cursor}"
     try:
-        print(f"Fetching page {page}...")
+        print(f"Fetching page {page_count} with cursor...")
         response = requests.get(url)
         response.raise_for_status()
         data = response.json()
 
-        filename = os.path.join(OUTPUT_DIR, f"{page:010}.json")
-        # skip if exists
+        filename = os.path.join(OUTPUT_DIR, f"{page_count:010}.json")
         if os.path.exists(filename):
             print(f"File {filename} already exists, skipping...")
+            cursor = data.get("meta", {}).get("next_cursor")
+            page_count += 1
             continue
+
         with open(filename, 'w', encoding='utf-8') as f:
             json.dump(data, f, ensure_ascii=False, indent=2)
-        sleep(1)  # Rate-limiting to avoid hitting the server too hard
+
+        cursor = data.get("meta", {}).get("next_cursor")
+        if not cursor:
+            print("No more results.")
+            break
+
+        page_count += 1
+        sleep(1)  # Rate-limiting
     except Exception as e:
-        print(f"Error on page {page}: {e}")
+        print(f"Error on page {page_count}: {e}")
         break
 
-print("Download complete.")
+print("Download complete using cursor pagination.")

sql_test.py

@@ -0,0 +1,27 @@
+import pymysql
+
+try:
+    print("Connecting to MariaDB...")
+    conn = pymysql.connect(
+        host="192.250.235.27",       # or your DB host, e.g. "127.0.0.1"
+        port=3306,
+        user="cybersan_bridgementor",   # replace with your MySQL username
+        password="bridgementor",  # replace with your MySQL password
+        database="cybersan_bridgementor",   # replace with your database name
+    )
+    print("Connected successfully.")
+
+    cursor = conn.cursor()
+    print("Fetching table list...")
+    cursor.execute("SHOW TABLES")
+
+    print("Tables in the database:")
+    for (table_name,) in cursor.fetchall():
+        print(f"- {table_name}")
+
+    cursor.close()
+    conn.close()
+    print("Connection closed.")
+
+except pymysql.MySQLError as e:
+    print(f"MariaDB connection error: {e}")