def splitTerms(self, text, categories=None):
"""Split text into terms
"""
terms = []
for sentence in lexicon.splitSentence(text):
if sentence:
for mixed in lexicon.iterMixTerms(sentence):
# English term
if mixed.startswith('E'):
terms.append(mixed)
# Chinese sentence
else:
terms.extend(self.db.splitTerms(mixed, categories))
return terms
def splitTerms(self, text, categories=None):
"""Split text into terms
"""
terms = []
for sentence in lexicon.splitSentence(text):
if sentence:
for mixed in lexicon.iterMixTerms(sentence):
# English term
if mixed.startswith('E'):
terms.append(mixed)
# Chinese sentence
else:
terms.extend(self.db.splitTerms(mixed, categories))
return terms
def splitNgramTerms(self, text):
"""Split text into 1 to n gram terms
"""
terms = []
for sentence in lexicon.splitSentence(text):
if sentence:
for mixed in lexicon.iterMixTerms(sentence):
# English term
if mixed.startswith('E'):
terms.append(mixed)
# Chinese sentence
else:
for n in xrange(1, self.ngram+1):
terms.extend(lexicon.iterTerms(n, mixed, False))
return terms
def splitNgramTerms(self, text):
"""Split text into 1 to n gram terms
"""
terms = []
for sentence in lexicon.splitSentence(text):
if sentence:
for mixed in lexicon.iterMixTerms(sentence):
# English term
if mixed.startswith('E'):
terms.append(mixed)
# Chinese sentence
else:
for n in xrange(1, self.ngram + 1):
terms.extend(lexicon.iterTerms(n, mixed, False))
return terms
def splitSentence(self, text):
"""Split text into sentence
"""
return lexicon.splitSentence(text)
def splitSentence(self, text):
"""Split text into sentence
"""
return lexicon.splitSentence(text)
def splitSentence(self, text):
'''Split text into sentence
'''
return lexicon.splitSentence(text)