示例#1
0
def genia_line_IIH(inf, outf):
    lines = tools.line_stripper(inf)
    for sublines in tools.blank_line_splitter(lines):
        sublines = [line.split('\t') for line in sublines]
        word, lemma, tag, chunk, _ = zip(*sublines)
        chunk = chunk_BII2IIH(chunk)
        with contextlib.redirect_stdout(outf):
            print(*word, end='\t')
            print(*lemma, end='\t')
            print(*tag, end='\t')
            print(*chunk)
示例#2
0
 def run(self):
     with self.input().open('r') as in_file, self.output().open(
         'w') as out_file:
         lines = tools.line_stripper(in_file)
         for sublines in tools.blank_line_splitter(lines):
             sublines = [line.split('\t') for line in sublines]
             word, lemma, tag, chunk, _ = zip(*sublines)
             chunk = chunk_BII2IIH(chunk)
             print(*word, end='\t', file=out_file)
             print(*lemma, end='\t', file=out_file)
             print(*tag, end='\t', file=out_file)
             print(*chunk, file=out_file)