court_string_collision_test.py

from courts_db import courts

# Get all citation strings
court_strings = [c['citation_string'] for c in courts if c['citation_string'] != '']

# How many existing collisions are there?
len(court_strings) - len(set(court_strings))  # Returns 148

# Remove the existing collisions
court_strings = list(set(court_strings))

# Strip out whitespace from each string
court_strings_stripped = [c.replace(' ','') for c in court_strings]

# Test for new collisions
len(set(court_strings_stripped)) == len(court_strings)  # Returns True, i.e., no new collisions