def __init__(self):
Ruleset.__init__(self, 'Sample ruleset')
self.tokenizer = nltk.data.load('tokenizers/punkt/english.pickle')
self.rules = [
ShortSentencesRule(self),
LongSentencesRule(self),
AllSentencesRule(self)
]
def __init__(self, data, uid):
Ruleset.__init__(self, data['ruleset'], data.get('comments', []), {
'prefix': data.get('prefix', ''),
'suffix': data.get('suffix', ''),
})
self.uid = str(uid).replace(u'\\', u'/')
self.data = data
self.flags = process_flags(data.get('flags', ''), DEFAULT_FLAGS)
self.replace = data.get('replace', {})
self.rules = [
RegularExpressionRule(self, self.props, d, self.flags,
self.replace) for d in data['rules']
]
def __init__(self, data, uid):
Ruleset.__init__(self,
data['ruleset'],
data.get('comments', []),
{
'prefix': data.get('prefix', ''),
'suffix': data.get('suffix', ''),
}
)
self.uid = unicode(uid).replace(u'\\', u'/')
self.data = data
self.flags = process_flags(data.get('flags', ''), DEFAULT_FLAGS)
self.replace = data.get('replace', {})
self.rules = [
RegularExpressionRule(self, self.props, d, self.flags, self.replace)
for d in data['rules']
]
