Cache suitable regular expressions

This speeds up TestAllURLsMatching.test_no_duplicates by about 8000% at the cost of minimal memory overhead.
This commit is contained in:
Philipp Hagemeister 2013-08-21 04:06:46 +02:00
parent 87f78946a5
commit 79cb25776f

View File

@ -77,7 +77,13 @@ def __init__(self, downloader=None):
@classmethod @classmethod
def suitable(cls, url): def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE.""" """Receives a URL and returns True if suitable for this IE."""
return re.match(cls._VALID_URL, url) is not None
# This does not use has/getattr intentionally - we want to know whether
# we have cached the regexp for *this* class, whereas getattr would also
# match the superclass
if '_VALID_URL_RE' not in cls.__dict__:
cls._VALID_URL_RE = re.compile(cls._VALID_URL)
return cls._VALID_URL_RE.match(url) is not None
@classmethod @classmethod
def working(cls): def working(cls):