def __init__(self, use_unicode=True, ignore_case=False, titles=None):
"""
:param use_unicode: whether to use `titles` as unicode or bytestrings
:param ignore_case: if True ignore case in all matches
:param titles: if given, overrides default `load_titles()` values
"""
titles = titles if titles else load_titles()
titles = (titles if use_unicode else
(s.encode('ascii') for s in titles))
builder = AcoraBuilder()
builder.update(titles)
self.ac = builder.build(ignore_case=ignore_case)
def __init__(self, content: List[str], ignore_case: bool):
"""
Acora matcher factory
:param content: a list of items to search
:param ignore_case: True to match any case
:return: a built matcher
"""
# start with a string in case content is empty
# otherwise it builds a binary Acora matcher
builder = AcoraBuilder("!@#$%%^&*")
if len(content) > 0:
builder.update(content)
self.matcher = builder.build(ignore_case=ignore_case)
def __init__(self, keywords: Optional[Iterable[str]] = []):
non_empty_keywords = []
if keywords is not None:
for w in keywords:
if w.strip() != "":
non_empty_keywords.append(w)
self._keywords = set(non_empty_keywords)
if len(self._keywords) > 0:
ac_builder = AcoraBuilder()
ac_builder.update(keywords)
self._finder = ac_builder.build()
else:
self._finder = None
def test_acora_python(self):
builder = AcoraBuilder()
builder.update([s for (s,) in SQL_ERRORS])
ac = builder.build(acora=PyAcora)
i = 0
#
# This takes around 9 seconds in my workstation.
#
for j in xrange(self.ITERATIONS):
for _ in ac.finditer(HTTP_RESPONSE):
i += 1
self.assertEqual(i, self.ITERATIONS * 2)