fix: correctly escape internal/external links in README

Author: omar-besbes

scripts/CSES/README.template.md

@@ -6,7 +6,7 @@ Accepted solutions of [CSES problemset](https://cses.fi/problemset).
 
 {% for category, problems in categories.items() %}
 
-- [{{ category }}](#{{ category | lower | replace(' ', '-') }})
+- [{{ category }}](#{{ category | escape_internal_link }})
   {% endfor %}
 
 ---
@@ -29,7 +29,7 @@ Accepted solutions of [CSES problemset](https://cses.fi/problemset).
                 {{ problem.id }}
             </td>
             <td>
-                <a href="{{ category | replace(' ', '%20') }}/{{ problem.id }}%20-%20{{ problem.title | replace(' ', '%20') }}.cpp">
+                <a href="{{ category | escape_external_link }}/{{ problem.id }}%20-%20{{ problem.title | escape_external_link }}.cpp">
                     💻 {{ problem.title }}
                 </a>
             </td>

scripts/CSES/generate.py

@@ -1,12 +1,15 @@
-import os
 import logging
+import os
+import re
+import urllib.parse
 
-from jinja2 import Template
+from jinja2 import Environment, FileSystemLoader
 
 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
 
 CSES_SOLUTIONS_DIR = 'solutions/CSES'
-TEMPLATE_FILE = 'scripts/CSES/README.template.md'
+TEMPLATE_FILE = 'README.template.md'
+TEMPLATE_DIR = 'scripts/CSES'
 
 def generate_data_from_folder(path):
     data = {}
@@ -33,11 +36,29 @@ def generate_data_from_folder(path):
 
     return data
 
+def escape_internal_link(text):
+    # Trim leading/trailing spaces
+    text = text.strip()
+    # Convert to lowercase
+    text = text.lower()
+    # Remove characters that are not word characters, hyphens, or spaces
+    text = re.sub(r'[^\w\- ]+', '', text)
+    # Replace spaces with hyphens
+    text = re.sub(r'\s', '-', text.strip())
+    # Remove trailing hyphens
+    text = re.sub(r'\-+$', '', text)
+    return text
+
+def escape_external_link(text):
+    return urllib.parse.quote(text)
+
 if __name__ == '__main__':
     # Load the template
     logging.info('Loading the template')
-    with open(TEMPLATE_FILE, 'r') as file:
-        template = Template(file.read())
+    env = Environment(loader=FileSystemLoader(TEMPLATE_DIR))
+    env.filters['escape_internal_link'] = escape_internal_link
+    env.filters['escape_external_link'] = escape_external_link
+    template = env.get_template(TEMPLATE_FILE)
 
     # Generate the data from the folder structure
     logging.info('Starting content generation')

scripts/France-IOI/README.template.md

@@ -5,9 +5,9 @@ Accepted solutions of [France-IOI problemset](https://www.france-ioi.org/algo/ch
 ## Table of Contents
 
 {% for level, chapters in levels.items() %}
-- [{{ level }}](#{{ level | lower | replace(' ', '-') }})
+- [{{ level }}](#{{ level | escape_internal_link }})
 {% for chapter, problems in chapters.items() %} 
-    - [{{ chapter }}](#{{ chapter | lower | replace(' ', '-') }})
+    - [{{ chapter }}](#{{ chapter | escape_internal_link }})
 {% endfor %}
 {% endfor %}
 
@@ -22,15 +22,15 @@ Accepted solutions of [France-IOI problemset](https://www.france-ioi.org/algo/ch
 ### {{ chapter }}
 
 {% for problem in content.problems %}
-1. <a href="{{ level | replace(' ', '%20') }}/{{ chapter | replace(' ', '%20') }}/{{ problem.title | replace(' ', '%20') }}.{{ problem.extension }}"> 💻 {{ problem.title }} </a>
+1. <a href="{{ level | escape_external_link }}/{{ chapter | escape_external_link }}/{{ problem.title | escape_external_link }}.{{ problem.extension }}"> 💻 {{ problem.title }} </a>
 {% endfor %}
 
 {% for part in content.parts %}
 
 1. **{{ part.part }}**
 
 {% for subproblem in part.problems %}
-    1. <a href="{{ level | replace(' ', '%20') }}/{{ chapter | replace(' ', '%20') }}/{{ part.part | replace(' ', '%20') }}/{{ subproblem.title | replace(' ', '%20') }}.{{ subproblem.extension }}"> 💻 {{ subproblem.title }} </a>
+    1. <a href="{{ level | escape_external_link }}/{{ chapter | escape_external_link }}/{{ part.part | escape_external_link }}/{{ subproblem.title | escape_external_link }}.{{ subproblem.extension }}"> 💻 {{ subproblem.title }} </a>
 {% endfor %}
 
 {% endfor %}

scripts/France-IOI/generate.py

@@ -1,12 +1,15 @@
-import os
 import logging
+import os
+import re
+import urllib.parse
 
-from jinja2 import Template
+from jinja2 import Environment, FileSystemLoader
 
 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
 
 FRANCE_IOI_SOLUTIONS_DIR = 'solutions/France-IOI'
-TEMPLATE_FILE = 'scripts/France-IOI/README.template.md'
+TEMPLATE_FILE = 'README.template.md'
+TEMPLATE_DIR = 'scripts/France-IOI'
 
 def generate_data_from_folder(path):
     data = {}
@@ -59,11 +62,29 @@ def generate_data_from_folder(path):
 
     return data
 
+def escape_internal_link(text):
+    # Trim leading/trailing spaces
+    text = text.strip()
+    # Convert to lowercase
+    text = text.lower()
+    # Remove characters that are not word characters, hyphens, or spaces
+    text = re.sub(r'[^\w\- ]+', '', text)
+    # Replace spaces with hyphens
+    text = re.sub(r'\s', '-', text.strip())
+    # Remove trailing hyphens
+    text = re.sub(r'\-+$', '', text)
+    return text
+
+def escape_external_link(text):
+    return urllib.parse.quote(text)
+
 if __name__ == '__main__':
     # Load the template
     logging.info('Loading the template')
-    with open(TEMPLATE_FILE, 'r') as file:
-        template = Template(file.read())
+    env = Environment(loader=FileSystemLoader(TEMPLATE_DIR))
+    env.filters['escape_internal_link'] = escape_internal_link
+    env.filters['escape_external_link'] = escape_external_link
+    template = env.get_template(TEMPLATE_FILE)
 
     # Generate the data from the folder structure
     logging.info('Starting content generation')