def parse_gfwlist()

in core/gfwlist/parse.py [0:0]

• 23 lines of code
• 10 McCabe index (conditional complexity)

def parse_gfwlist(content):
    gfwlist = content.splitlines(False)
    domains = set()
    for line in gfwlist:
        if line.find('.*') >= 0:
            continue
        elif line.find('*') >= 0:
            line = line.replace('*', '/')
        if line.startswith('!'):
            continue
        elif line.startswith('['):
            continue
        elif line.startswith('@'):
            # ignore white list
            continue
        elif line.startswith('||'):
            add_domain_to_set(domains, line.lstrip('||'))
        elif line.startswith('|'):
            add_domain_to_set(domains, line.lstrip('|'))
        elif line.startswith('.'):
            add_domain_to_set(domains, line.lstrip('.'))
        else:
            add_domain_to_set(domains, line)
    # TODO: reduce ['www.google.com', 'google.com'] to ['google.com']
    return domains