3b8bb2c905e58655fa58fcc49d387e2a9fe0a42f,src/fonduer/parser/preprocessors/hocr_doc_preprocessor.py,HOCRDocPreprocessor,_parse_file,#HOCRDocPreprocessor#,45

Before Change

                if self.space:
                    parent.string = parent.text.replace("\n", " ").strip()
                else:
                    parent.string = parent.text.replace("\n", "").strip()
                // Rmove the mark
                del parent["fonduer"]
        name = os.path.basename(fp)[: os.path.basename(fp).rfind(".")]
        stable_id = self._get_stable_id(name)

After Change

                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(".")]

Instances