def _main(): analysis = Analyzer() analysis.set_analysis_type(NOUN_EXTRACTOR) for line in sys.stdin: if not line.strip(): continue line = line.decode('utf-8') line = analysis.filtering_by_tag(line) line = filter(filtering_stopword, line) sys.stdout.write(' '.join(line)) sys.stdout.write('\n')
# -*- coding: utf-8 -*- import sys, os.path sys.path.append(os.path.join(os.path.dirname(__file__), '..')) from pyHannanum.morpheme import Analyzer, NOUN_EXTRACTOR if __name__ == '__main__': analysis = Analyzer() analysis.set_analysis_type(NOUN_EXTRACTOR) for line in sys.stdin: if not line.strip(): continue line = line.decode('utf-8') line = analysis.filtering_by_tag(line) sys.stdout.write(' '.join(line)) sys.stdout.write('\n')
# -*- coding: utf-8 -*- import sys,os.path sys.path.append(os.path.join(os.path.dirname(__file__), '..')) from pyHannanum.morpheme import Analyzer, NOUN_EXTRACTOR if __name__ == '__main__': analysis = Analyzer() analysis.set_analysis_type(NOUN_EXTRACTOR) for line in sys.stdin: if not line.strip(): continue line = line.decode('utf-8') line = analysis.filtering_by_tag(line) sys.stdout.write(' '.join(line)) sys.stdout.write('\n')
def setUp(self): self.analyzer = Analyzer()
def __test_noun_extractor(self): analyzer = Analyzer() analyzer.set_analysis_type(NOUN_EXTRACTOR) s = u'롯데마트가 판매하고 있는 흑마늘 양념 치킨이 논란이 되고 있다.' self.assertEquals(['롯데마트', '판매', '흑마늘', '양념', '치킨', '논란'], analyzer.analysis(s))
def test_filtering_by_tag(self): analyzer = Analyzer() analyzer.set_analysis_type(POS_TAGGER) s = u'롯데마트가 판매하고 있는 흑마늘 양념 치킨이 논란이 되고 있다.' self.assertEquals(['롯데마트', '판매', '흑마늘', '양념', '치킨', '논란'], analyzer.analysis(s, tags=['ncpa', 'ncn']))
def __test_pos_simple_09(self): analyzer = Analyzer() analyzer.set_analysis_type(POS_SIMPLE_09) s = u'학교에 가다.' self.assertEquals(['학교에', '가다', '.'], analyzer.get_words(s))