b5a9d8e3c23b73f0050cff9f426260bd709d0a75,robotreviewer/textprocessing/pdfreader.py,PdfReader,parse_xml,#PdfReader#Any#,119

Before Change

        output.grobid["text"] = "\n".join(full_text_bits)
        output.grobid["authors"] = author_list
        log.info("author list: %s" % author_list)
        
        return output

    def _extract_text(self, elem):

After Change

                    full_text_bits.extend([self._extract_text(elem), "\n"])
                elif elem.tag=="{http://www.tei-c.org/ns/1.0}persName" and "{http://www.tei-c.org/ns/1.0}fileDesc" in path:
                    forenames = [e.text for e in elem.findall("{http://www.tei-c.org/ns/1.0}forename")]
                    lastnames = [e.text for e in elem.findall("{http://www.tei-c.org/ns/1.0}surname")]
                    initials = [f[0] for f in forenames]
                    // NB the format below is identical to that used in pubmed_robot.py
                    author_list.append({"initials": u"".join(initials),
                                        "forename": u" ".join(forenames),
                                        "lastname": u" ".join(lastnames)})
                    
                path.pop()

        output.grobid["text"] = "\n".join(full_text_bits)

Instances