def test_find_unique_urls() -> None:
from pajbot.modules.linkchecker import find_unique_urls
assert find_unique_urls("pajlada.se test http://pajlada.se") == {"http://pajlada.se"}
assert find_unique_urls("pajlada.se pajlada.com foobar.se") == {
"http://pajlada.se",
"http://pajlada.com",
"http://foobar.se",
}
assert find_unique_urls("foobar.com foobar.com") == {"http://foobar.com"}
assert find_unique_urls("foobar.com foobar.se"), {"http://foobar.com" == "http://foobar.se"}
assert find_unique_urls("www.foobar.com foobar.se"), {"http://www.foobar.com" == "http://foobar.se"}
# TODO: Edge case, this behaviour should probably be changed. These URLs should be considered the same.
# Use is_same_url method?
assert find_unique_urls("pajlada.se/ pajlada.se"), {"http://pajlada.se/" == "http://pajlada.se"}
# TODO: The protocol of a URL is entirely thrown away, this behaviour should probably be changed.
assert find_unique_urls("https://pajlada.se/ https://pajlada.se") == {
"https://pajlada.se/",
"https://pajlada.se",
}
assert find_unique_urls("foo 192.168.0.1 bar") == {
"http://192.168.0.1",
}
assert find_unique_urls("omg this isn't chatting, this is meme-ing...my vanity") == set()
assert find_unique_urls("foo 1.40 bar") == set()
def test_find_unique_urls(self):
from pajbot.modules.linkchecker import find_unique_urls
from pajbot.bot import Bot
import re
regex = re.compile(Bot.url_regex_str, re.IGNORECASE)
self.assertEqual(
find_unique_urls(regex, 'pajlada.se test http://pajlada.se'),
{'http://pajlada.se'})
self.assertEqual(
find_unique_urls(regex, 'pajlada.se pajlada.com foobar.se'),
{'http://pajlada.se', 'http://pajlada.com', 'http://foobar.se'})
self.assertEqual(find_unique_urls(regex, 'foobar.com foobar.com'),
{'http://foobar.com'})
self.assertEqual(find_unique_urls(regex, 'foobar.com foobar.se'),
{'http://foobar.com', 'http://foobar.se'})
self.assertEqual(find_unique_urls(regex, 'www.foobar.com foobar.se'),
{'http://www.foobar.com', 'http://foobar.se'})
# TODO: Edge case, this behaviour should probably be changed. These URLs should be considered the same.
# Use is_same_url method?
self.assertEqual(find_unique_urls(regex, 'pajlada.se/ pajlada.se'),
{'http://pajlada.se/', 'http://pajlada.se'})
# TODO: The protocol of a URL is entirely thrown away, this behaviour should probably be changed.
self.assertEqual(
find_unique_urls(regex, 'https://pajlada.se/ https://pajlada.se'),
{'http://pajlada.se/', 'http://pajlada.se'})
def test_find_unique_urls():
from pajbot.modules.linkchecker import find_unique_urls
from pajbot.bot import URL_REGEX
assert find_unique_urls(
URL_REGEX,
"pajlada.se test http://pajlada.se") == {"http://pajlada.se"}
assert find_unique_urls(URL_REGEX, "pajlada.se pajlada.com foobar.se") == {
"http://pajlada.se",
"http://pajlada.com",
"http://foobar.se",
}
assert find_unique_urls(URL_REGEX,
"foobar.com foobar.com") == {"http://foobar.com"}
assert find_unique_urls(URL_REGEX, "foobar.com foobar.se"), {
"http://foobar.com" == "http://foobar.se"
}
assert find_unique_urls(URL_REGEX, "www.foobar.com foobar.se"), {
"http://www.foobar.com" == "http://foobar.se"
}
# TODO: Edge case, this behaviour should probably be changed. These URLs should be considered the same.
# Use is_same_url method?
assert find_unique_urls(URL_REGEX, "pajlada.se/ pajlada.se"), {
"http://pajlada.se/" == "http://pajlada.se"
}
# TODO: The protocol of a URL is entirely thrown away, this behaviour should probably be changed.
assert find_unique_urls(URL_REGEX,
"https://pajlada.se/ https://pajlada.se") == {
"https://pajlada.se/",
"https://pajlada.se",
}
def ab(bot, source, message, **rest):
if not message:
return False
# check if there is a link in the message
check_message = find_unique_urls(URL_REGEX, message)
if len(check_message) > 0:
return False
msg_parts = message.split(" ")
if len(msg_parts) >= 2:
outer_str = msg_parts[0]
inner_str = f" {outer_str} ".join(msg_parts[1:] if len(msg_parts) >= 3 else msg_parts[1])
bot.say(f"{source}, {outer_str} {inner_str} {outer_str}")
def ab(self, **options):
bot = options['bot']
message = options['message']
source = options['source']
if message:
""" check if there is a link in the message """
check_message = find_unique_urls(bot.url_regex, message)
if check_message == set():
msg_parts = message.split(' ')
if len(msg_parts) >= 2:
outer_str = msg_parts[0]
inner_str = ' {} '.format(outer_str).join(msg_parts[1:] if len(msg_parts) >= 3 else msg_parts[1])
bot.say('{0}, {1} {2} {1}'.format(source.username_raw, outer_str, inner_str))
return True
return
def ab(**options):
bot = options["bot"]
message = options["message"]
source = options["source"]
if message:
""" check if there is a link in the message """
check_message = find_unique_urls(URL_REGEX, message)
if check_message == set():
msg_parts = message.split(" ")
if len(msg_parts) >= 2:
outer_str = msg_parts[0]
inner_str = " {} ".format(outer_str).join(msg_parts[1:] if len(msg_parts) >= 3 else msg_parts[1])
bot.say("{0}, {1} {2} {1}".format(source.username_raw, outer_str, inner_str))
return True
return
def ab(self, **options):
bot = options['bot']
message = options['message']
source = options['source']
if message:
""" check if there is a link in the message """
check_message = find_unique_urls(bot.url_regex, message)
if check_message == set():
msg_parts = message.split(' ')
if len(msg_parts) >= 2:
outer_str = msg_parts[0]
inner_str = ' {} '.format(outer_str).join(
msg_parts[1:] if len(msg_parts) >= 3 else msg_parts[1])
bot.say('{0}, {1} {2} {1}'.format(source.username_raw,
outer_str, inner_str))
return True
return
def test_find_unique_urls(self):
from pajbot.modules.linkchecker import find_unique_urls
from pajbot.bot import Bot
import re
regex = re.compile(Bot.url_regex_str, re.IGNORECASE)
self.assertEqual(find_unique_urls(regex, 'pajlada.se test http://pajlada.se'), {'http://pajlada.se'})
self.assertEqual(find_unique_urls(regex, 'pajlada.se pajlada.com foobar.se'), {'http://pajlada.se', 'http://pajlada.com', 'http://foobar.se'})
self.assertEqual(find_unique_urls(regex, 'foobar.com foobar.com'), {'http://foobar.com'})
self.assertEqual(find_unique_urls(regex, 'foobar.com foobar.se'), {'http://foobar.com', 'http://foobar.se'})
self.assertEqual(find_unique_urls(regex, 'www.foobar.com foobar.se'), {'http://www.foobar.com', 'http://foobar.se'})
# TODO: Edge case, this behaviour should probably be changed. These URLs should be considered the same.
# Use is_same_url method?
self.assertEqual(find_unique_urls(regex, 'pajlada.se/ pajlada.se'), {'http://pajlada.se/', 'http://pajlada.se'})
# TODO: The protocol of a URL is entirely thrown away, this behaviour should probably be changed.
self.assertEqual(find_unique_urls(regex, 'https://pajlada.se/ https://pajlada.se'), {'https://pajlada.se/', 'https://pajlada.se'})
def find_unique_urls(self, message):
from pajbot.modules.linkchecker import find_unique_urls
return find_unique_urls(self.url_regex, message)
def find_unique_urls(self, message):
from pajbot.modules.linkchecker import find_unique_urls
return find_unique_urls(URL_REGEX, message)
def find_unique_urls(self, message):
from pajbot.modules.linkchecker import find_unique_urls
return find_unique_urls(self.url_regex, message)
def find_unique_urls(self, message: str) -> Set[str]:
from pajbot.modules.linkchecker import find_unique_urls
return find_unique_urls(message)
