4e144c9f842d7415d8be5bdbb5912d88ae32cced,pycorrector/seq2seq/corpus_reader.py,CGEDReader,read_samples_by_string,#CGEDReader#Any#,80

Before Change

                    childNodes[0].data.strip()
                target_text = doc.getElementsByTagName("CORRECTION")[0]. \
                    childNodes[0].data.strip()
                source = segment(source_text, cut_type="char")
                target = segment(target_text, cut_type="char")
                yield source, target

    def unknown_token(self):

After Change

                if not line_src or len(line_src) < 5:
                    break
                source = line_src.lower()[5:].strip().split()
                target = line_dst.lower()[5:].strip().split()
                yield source, target

Instances