Python Paper.from_bare方法代码示例

# 需要导入模块: from papers.models import Paper [as 别名]
# 或者: from papers.models.Paper import from_bare [as 别名]
    def fetch_and_save_new_records(self, starting_cursor='*', batch_time=datetime.timedelta(days=1)):
        """
        Fetches and stores all new Crossref records updated since the
        last update time of the associated OaiSource.
        """
        source = OaiSource.objects.get(identifier='crossref')

        # We substract one day to 'until-update-date' parameter as it is inclusive
        one_day = datetime.timedelta(days=1)

        while source.last_update + batch_time < timezone.now():
            last_updated = source.last_update

            until_date = (last_updated + batch_time - one_day).date()

            to_update = self.fetch_all_records(
                filters={'from-update-date':last_updated.date().isoformat(),
                         'until-update-date':until_date.isoformat()},
                    cursor=starting_cursor)
            for record in to_update:
                try:
                    bare_paper = self.save_doi_metadata(record)
                    p = Paper.from_bare(bare_paper)
                    p.update_index()
                except ValueError as e:
                    logger.info(record.get('DOI', 'unkown DOI') + ': %s' % e)

            logger.info("Updated up to" + until_date.isoformat())
            source.last_update += batch_time
            source.save()

# 需要导入模块: from papers.models import Paper [as 别名]
# 或者: from papers.models.Paper import from_bare [as 别名]
    def fetch_and_save(self, researcher, incremental=False):
        """
        Fetch papers and save them to the database.

        :param incremental: When set to true, papers are clustered
            and commited one after the other. This is useful when
            papers are fetched on the fly for an user.
        """
        if self.ccf is None:
            raise ValueError('Clustering context factory not provided')

        for p in self.fetch_bare(researcher):        
            # Save the paper as non-bare
            p = Paper.from_bare(p)

            # If clustering happens incrementally, cluster the researcher
            if incremental:
                self.ccf.clusterPendingAuthorsForResearcher(researcher)
                researcher.update_stats()

            # Check whether this paper is associated with an ORCID id
            # for the target researcher
            if researcher.orcid:
                matches = filter(lambda a: a.orcid == researcher.orcid, p.authors)
                if matches:
                    self.update_empty_orcid(researcher, False)

           
            if self.max_results is not None and count >= self.max_results:
                break

# 需要导入模块: from papers.models import Paper [as 别名]
# 或者: from papers.models.Paper import from_bare [as 别名]
 def test_fetch(self):
     profile = OrcidProfileStub('0000-0002-8612-8827', instance='orcid.org')
     papers = list(self.source.fetch_papers(self.researcher, profile=profile))
     for paper in papers:
         paper = Paper.from_bare(paper)
     self.assertTrue(len(papers) > 1)
     self.check_papers(papers)

# 需要导入模块: from papers.models import Paper [as 别名]
# 或者: from papers.models.Paper import from_bare [as 别名]
 def test_update_paper_statuses(self):
     p = self.cr_api.create_paper_by_doi("10.1016/j.bmc.2005.06.035")
     p = Paper.from_bare(p)
     self.assertEqual(p.pdf_url, None)
     pdf_url = 'https://www.youtube.com/watch?v=dQw4w9WgXcQ'
     OaiRecord.new(source=self.arxiv,
                   identifier='oai:arXiv.org:aunrisste',
                   about=p,
                   splash_url='http://www.perdu.com/',
                   pdf_url=pdf_url)
     update_paper_statuses()
     self.assertEqual(Paper.objects.get(pk=p.pk).pdf_url, pdf_url)

# 需要导入模块: from papers.models import Paper [as 别名]
# 或者: from papers.models.Paper import from_bare [as 别名]
    def save_paper(self, bare_paper, researcher, incremental=False):
        # Save the paper as non-bare
        p = Paper.from_bare(bare_paper)

        # If clustering happens incrementally, cluster the researcher
        if incremental:
            self.ccf.clusterPendingAuthorsForResearcher(researcher)
            researcher.update_stats()

        # Check whether this paper is associated with an ORCID id
        # for the target researcher
        if researcher.orcid:
            matches = filter(lambda a: a.orcid == researcher.orcid, p.authors)
            if matches:
                self.update_empty_orcid(researcher, False)

        return p

# 需要导入模块: from papers.models import Paper [as 别名]
# 或者: from papers.models.Paper import from_bare [as 别名]
    def process_record(self, header, metadata, format):
        """
        Saves the record given by the header and metadata (as returned by
        pyoai) into a Paper, or None if anything failed.
        """
        translator = self.translators.get(format)
        if translator is None:
            logger.warning("Unknown metadata format %s, skipping" % header.format())
            return

        paper = translator.translate(header, metadata)
        if paper is not None:
            try:
                with transaction.atomic():
                    saved = Paper.from_bare(paper)
                return saved
            except ValueError:
                logger.exception("Ignoring invalid paper with header %s" % header.identifier())

# 需要导入模块: from papers.models import Paper [as 别名]
# 或者: from papers.models.Paper import from_bare [as 别名]
    def save_paper(self, bare_paper, researcher):
        # Save the paper as non-bare
        p = Paper.from_bare(bare_paper)

        # Associate known ORCIDs to the corresponding researchers
        for idx, author in enumerate(p.authors_list):
            if author['orcid']:
                try:
                    researcher = Researcher.objects.get(orcid=author['orcid'])
                    p.set_researcher(idx, researcher.id)
                except Researcher.DoesNotExist:
                    p.set_researcher(idx, None)
            else:
                p.set_researcher(idx, None)

        p.save()
        p.update_index()

        return p

# 需要导入模块: from papers.models import Paper [as 别名]
# 或者: from papers.models.Paper import from_bare [as 别名]
    def ingest_dump(self, filename, start_doi=None, update_index=True):
        """
        Imports a dump of Crossref metadata records stored as a bz2'ed
        file where each line is a JSON record.
        """
        for record in self.read_dump(filename, start_doi=start_doi):
            bare_paper = self.save_doi_metadata(record)
            p = Paper.from_bare(bare_paper)

            if not update_index:
                continue

            for i in range(3):
                try:
                    p.update_index()
                    break
                except ConnectionTimeout as e:
                    logger.warning(e)
                    sleep(10*i)
                except (MetadataSourceException, ValueError):
                    logger.info((record.get('DOI') or 'unknown DOI'))

# 需要导入模块: from papers.models import Paper [as 别名]
# 或者: from papers.models.Paper import from_bare [as 别名]
 def test_fetch(self):
     papers = list(self.source.fetch_papers(self.researcher))
     for paper in papers:
         paper = Paper.from_bare(paper)
     self.assertTrue(len(papers) > 1)
     self.check_papers(papers)