def parse(self, sentence):
"""Strips XML tags first.
@param s: the sentence to be parsed, as a string
@return: a Sentence object
"""
sentence = self.TAG.sub('', sentence)
tokens = [unicode(x) for x in self.tokenize(sentence)]
parse = self.lp.apply(Sentence.toWordList(tokens))
return PySentence(self, parse)
def parse_wordlist(self, wordList):
"""Strips XML tags first.
@param s: the sentence to be parsed, as a string
@return: a Sentence object
"""
sent = []
[sent.append(token.replace(u'\xa0', ' ').decode('utf-8')) for token in wordList]
parse = self.lp.apply(Sentence.toWordList(sent))
return PySentence(self, parse)
def parse_xml(self, text):
"""Tokenise the XML text, remember XML positions, and then parse it.
"""
# build a plain-text token list and remember tag positions
xml_tags = {}
sent = []
for token in self.tokenize(text):
token = unicode(token).replace(u'\xa0', ' ')
if token.startswith('<'):
cur_size = len(sent)
xml_tags[cur_size] = xml_tags.get(cur_size, [])
xml_tags[cur_size].append(token)
else:
sent.append(token)
# parse
parse = self.lp.apply(Sentence.toWordList(sent))
return PySentence(self, parse, xml_tags)
def get_parse(self, sentence):
tokens = [unicode(x) for x in self.tokenize(sentence)]
parse = self.lp.apply(Sentence.toWordList(tokens))
return parse
def get_parse(self, sentence):
tokens = [unicode(x) for x in self.tokenize(sentence)]
parse = self.lp.apply(Sentence.toWordList(tokens))
return parse
