43a50ab6a3f717c738c8abba16779be59878bf4b,src/fonduer/parser/preprocessors/hocr_doc_preprocessor.py,HOCRDocPreprocessor,_parse_file,#HOCRDocPreprocessor#,45

Before Change

                            word.string.replace_with("".join(tokens))
                    word.unwrap()
            for parent in root.find_all(attrs={"fonduer": "1"}):
                if self.space:
                    parent.string.replace_with(" ".join(parent.stripped_strings))
                else:
                    parent.string.replace_with("".join(parent.stripped_strings))
                // Rmove the mark
                del parent["fonduer"]
        name = os.path.basename(fp)[: os.path.basename(fp).rfind(".")]
        stable_id = self._get_stable_id(name)
        yield Document(

After Change

                        if child.strip() == "":  // remove if space or linebreak
                            child.extract()
                        else:
                            tmp = re.sub(r"[\n\s]+", " " if self.space else "", child)
                            n = NavigableString(tmp.strip())
                            child.replace_with(n)
                del parent["fonduer"]

        name = os.path.basename(fp)[: os.path.basename(fp).rfind(".")]

Instances