はてなブックマーク

def tokenize2 sentence,h list = @tknizer.tokenize(sentence) list.extend JavaIterator list.each do |x| if x.surface_form =~ /^\w$/ then #アルファベット1字の除去 next end if x.surface_form =~ /^\d/ then #先頭が数字 next end if x.surface_form =~ /\.|\@|\// then #記号の除外 next end if x.surface_form =~ /^([ぁ-ん]|[ァ-ヴ])$/ then #ひらがな一文字のみの除外 next end puts x.surface_form puts x.part_of_speech if /名詞/ =~ x.all_features then h