From 024145b6a103b18c61db91164897d421dea6bfbe Mon Sep 17 00:00:00 2001
From: mithilP007 <mithil1323@gmail.com>
Date: Mon, 18 May 2026 10:57:41 +0530
Subject: [PATCH] fix: resolve broken external links and missing target
 handling in learning resources (#245)

---
 routes/main_routes.py  |  9 ++++++++
 templates/project.html | 11 +++++-----
 tests/test_basic.py    | 30 +++++++++++++++++++++++++++
 utils/link_helper.py   | 47 ++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 91 insertions(+), 6 deletions(-)
 create mode 100644 utils/link_helper.py

diff --git a/routes/main_routes.py b/routes/main_routes.py
index 4cce046..2d03e37 100644
--- a/routes/main_routes.py
+++ b/routes/main_routes.py
@@ -9,10 +9,19 @@
 from utils.data_loader import find_project_by_id, get_project_stats
 from utils.file_server import read_starter_code, resolve_starter_file, get_starter_code_dir
 
+from utils.link_helper import parse_external_link
+
 # Create the Blueprint that app.py will register
 main = Blueprint("main", __name__)
 
 
+@main.app_template_filter("parse_resource")
+def parse_resource_filter(resource_str):
+    """Jinja filter to parse a resource string into a standardized dict."""
+    return parse_external_link(resource_str)
+
+
+
 @main.route("/")
 def index():
     """Render the homepage with the skill input form and dynamic stats."""
diff --git a/templates/project.html b/templates/project.html
index 21e3ae6..cb65e95 100644
--- a/templates/project.html
+++ b/templates/project.html
@@ -136,15 +136,14 @@ <h2>Learning Resources</h2>
             <ul class="resource-list">
               {% for resource in project.resources %}
               <li class="resource-item">
-                <!-- Parse the "Label: URL" format stored in the data -->
-                {% set parts = resource.split(": http") %}
-                {% if parts|length > 1 %}
-                  <a href="http{{ parts[1] }}" target="_blank" rel="noopener noreferrer" class="resource-link">
-                    <span>{{ parts[0] }}</span>
+                {% set link_info = resource | parse_resource %}
+                {% if link_info.is_link %}
+                  <a href="{{ link_info.url }}" target="_blank" rel="noopener noreferrer" class="resource-link">
+                    <span>{{ link_info.label }}</span>
                     <svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2.5" stroke-linecap="round" stroke-linejoin="round"><path d="M18 13v6a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2V8a2 2 0 0 1 2-2h6"/><polyline points="15 3 21 3 21 9"/><line x1="10" y1="14" x2="21" y2="3"/></svg>
                   </a>
                 {% else %}
-                  <span class="resource-plain">{{ resource }}</span>
+                  <span class="resource-plain">{{ link_info.label }}</span>
                 {% endif %}
               </li>
               {% endfor %}
diff --git a/tests/test_basic.py b/tests/test_basic.py
index 6bef8ab..48f5390 100644
--- a/tests/test_basic.py
+++ b/tests/test_basic.py
@@ -23,6 +23,7 @@
     parse_skills,
     score_single_project,
 )
+from utils.link_helper import parse_external_link
 from app import app, internal_server_error
 
 
@@ -73,6 +74,35 @@ def test_find_project_by_id_missing():
 # Recommender utility tests
 # ============================================================
 
+def test_parse_external_link():
+    """parse_external_link should correctly identify and split links and labels."""
+    assert parse_external_link("Python docs: https://docs.python.org") == {
+        "label": "Python docs",
+        "url": "https://docs.python.org",
+        "is_link": True
+    }
+    assert parse_external_link("Real Python - https://realpython.com") == {
+        "label": "Real Python",
+        "url": "https://realpython.com",
+        "is_link": True
+    }
+    assert parse_external_link("https://docs.python.org") == {
+        "label": "https://docs.python.org",
+        "url": "https://docs.python.org",
+        "is_link": True
+    }
+    assert parse_external_link("Some non-link text description") == {
+        "label": "Some non-link text description",
+        "url": None,
+        "is_link": False
+    }
+    assert parse_external_link("") == {
+        "label": "",
+        "url": None,
+        "is_link": False
+    }
+
+
 def test_parse_skills_basic():
     """parse_skills should split on commas and lowercase each entry."""
     result = parse_skills("Python, HTML, CSS")
diff --git a/utils/link_helper.py b/utils/link_helper.py
new file mode 100644
index 0000000..925aa39
--- /dev/null
+++ b/utils/link_helper.py
@@ -0,0 +1,47 @@
+# utils/link_helper.py
+# Reusable helper to parse and standardize external link handling.
+
+import re
+
+def parse_external_link(resource):
+    """
+    Safely parses a resource string which might contain an external URL.
+    
+    Supports:
+      - "Label: https://url"
+      - "Label - https://url"
+      - "https://url" (plain URL)
+      - Plain text (no URL)
+      
+    Returns a dict:
+      {
+        "label": str,
+        "url": str or None,
+        "is_link": bool
+      }
+    """
+    if not resource:
+        return {"label": "", "url": None, "is_link": False}
+
+    resource_str = str(resource).strip()
+    
+    # Regex to find a standard http/https URL
+    url_match = re.search(r'https?://[^\s]+', resource_str)
+    if not url_match:
+        return {"label": resource_str, "url": None, "is_link": False}
+    
+    url = url_match.group(0)
+    
+    # The label is whatever is before the URL, stripped of colons, dashes, and spaces
+    label_part = resource_str[:url_match.start()].strip()
+    if label_part:
+        # Remove trailing colons, dashes, or spaces
+        label = re.sub(r'[:\-–—\s]+$', '', label_part).strip()
+    else:
+        label = url
+        
+    return {
+        "label": label,
+        "url": url,
+        "is_link": True
+    }