nordabiz/utils/helpers.py
Maciej Pienczyn e718d96a7d
Some checks are pending
NordaBiz Tests / Unit & Integration Tests (push) Waiting to run
NordaBiz Tests / E2E Tests (Playwright) (push) Blocked by required conditions
NordaBiz Tests / Smoke Tests (Production) (push) Blocked by required conditions
NordaBiz Tests / Send Failure Notification (push) Blocked by required conditions
fix(security): Resolve 1 HIGH and 7 MEDIUM vulnerabilities from code review
- HIGH: Fix SQL injection in ZOPK knowledge service (3 functions) — replace f-strings with parameterized queries
- MEDIUM: Sanitize tsquery/LIKE input in SearchService to prevent injection
- MEDIUM: Add @login_required + @role_required(ADMIN) to /health/full endpoint
- MEDIUM: Add @role_required(ADMIN) to ZOPK knowledge search API
- MEDIUM: Add bleach HTML sanitization on write for announcements, events, board proceedings (stored XSS via |safe)
- MEDIUM: Remove partial API key from Gemini service logs
- MEDIUM: Remove @csrf.exempt from chat endpoints, add X-CSRFToken headers in JS
- MEDIUM: Add missing CSRF tokens to 3 POST forms (data_request, benefits_form, benefits_list)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-06 05:25:18 +01:00

124 lines
2.7 KiB
Python

"""
Helper Functions
================
Common utility functions used across blueprints.
"""
import re
import logging
import bleach
logger = logging.getLogger(__name__)
# Allowed HTML tags and attributes for rich-text content (announcements, events, proceedings)
_ALLOWED_TAGS = ['p', 'br', 'strong', 'em', 'b', 'i', 'a', 'ul', 'ol', 'li', 'h3', 'h4', 'blockquote']
_ALLOWED_ATTRS = {'a': ['href', 'target', 'rel']}
def sanitize_html(content):
"""
Sanitize HTML content to prevent stored XSS.
Strips all tags except a safe whitelist.
Args:
content: HTML string to sanitize
Returns:
Sanitized HTML string
"""
if not content:
return content
return bleach.clean(content, tags=_ALLOWED_TAGS, attributes=_ALLOWED_ATTRS, strip=True)
def sanitize_input(text, max_length=1000):
"""
Sanitize user input - remove potentially dangerous characters.
Args:
text: Input string to sanitize
max_length: Maximum allowed length (default 1000)
Returns:
Sanitized string
"""
if not text:
return ""
# Remove null bytes
text = text.replace('\x00', '')
# Trim to max length
text = text[:max_length]
# Strip whitespace
text = text.strip()
return text
def validate_email(email):
"""
Validate email format.
Args:
email: Email address to validate
Returns:
bool: True if valid, False otherwise
"""
if not email or len(email) > 255:
return False
# RFC 5322 compliant email regex (simplified)
pattern = r'^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$'
return re.match(pattern, email) is not None
def validate_password(password):
"""
Validate password strength.
Requirements:
- Minimum 8 characters
- At least one uppercase letter
- At least one lowercase letter
- At least one digit
Args:
password: Password to validate
Returns:
tuple: (is_valid: bool, message: str)
"""
if not password or len(password) < 8:
return False, "Hasło musi mieć minimum 8 znaków"
if not re.search(r'[A-Z]', password):
return False, "Hasło musi zawierać przynajmniej jedną wielką literę"
if not re.search(r'[a-z]', password):
return False, "Hasło musi zawierać przynajmniej jedną małą literę"
if not re.search(r'\d', password):
return False, "Hasło musi zawierać przynajmniej jedną cyfrę"
return True, "OK"
def ensure_url(url):
"""
Ensure URL has http:// or https:// scheme.
Args:
url: URL string
Returns:
URL with https:// prefix if no scheme present
"""
if url and not url.startswith(('http://', 'https://')):
return f'https://{url}'
return url