1c0cd03712f95fb5966968abc2a39313175594c6,src/fonduer/parser/preprocessors/html_doc_preprocessor.py,HTMLDocPreprocessor,parse_file,#HTMLDocPreprocessor#Any#Any#,13

Before Change

                    stable_id=stable_id,
                    text=str(text),
                    meta={"file_name": file_name},
                ), str(text)

    def _can_read(self, fpath):
        return fpath.lower().endswith("html")  // includes both .html and .xhtml

After Change

        with codecs.open(fp, encoding=self.encoding) as f:
            soup = BeautifulSoup(f, "lxml")
            all_html_elements = soup.find_all("html")
            if len(all_html_elements) != 1:
                raise NotImplementedError("Expecting one html element per html file")
            text = all_html_elements[0]
            name = os.path.basename(fp)[: os.path.basename(fp).rfind(".")]
            stable_id = self.get_stable_id(name)
            yield Document(

Instances