90bbf47abab22b01d073f6565f57097cd6c16a66,nala/bootstrapping/utils.py,DownloadArticle,download,#DownloadArticle#Any#,81

Before Change

            counter = 0

            // for now only include title and abstract
            for elem in xml.findall(".//ArticleTitle"):
                doc.parts["part_{}".format(counter)] = Part(elem.text)
                counter += 1
            for elem in xml.findall(".//AbstractText"):
                doc.parts["part_{}".format(counter)] = Part(elem.text)
                counter += 1

After Change

            doc = Document()

            if self.one_part:
                joined_text = "\n".join(element.text for element in
                                        chain(xml.findall(".//ArticleTitle"), xml.findall(".//AbstractText")))
                doc.parts["title_and_abstract"] = Part(joined_text)
            else:
                counter = 0
                // for now only include title and abstract
                for elem in xml.findall(".//ArticleTitle"):
                    doc.parts["part_{}".format(counter)] = Part(elem.text)
                    counter += 1
                for elem in xml.findall(".//AbstractText"):
                    doc.parts["part_{}".format(counter)] = Part(elem.text)
                    counter += 1

            // yield the document but only if you found anything
            if len(doc.parts) > 0:
                yield pmid, doc

Instances