def test_basic(self): out = queries_for_authors('') self.assertIsInstance(out, list) self.assertListEqual(out, []) out = queries_for_authors('Fred') self.assertIsInstance(out, list) self.assertListEqual(out, [('Fred', 'Fred')]) out = queries_for_authors('J. R. Webb') self.assertIsInstance(out, list) self.assertListEqual(out, [('J. R. Webb', 'Webb, J R')]) out = queries_for_authors('J. R. Webb, Fred') self.assertIsInstance(out, list) self.assertListEqual(out, [('J. R. Webb', 'Webb, J R'), ', ', ('Fred', 'Fred')]) out = queries_for_authors("Fred Blogs (a), Jim Smith (b) (c)") self.assertListEqual(out, [('Fred Blogs', 'Blogs, F'), ' (a)', ', ', ('Jim Smith', 'Smith, J'), ' (b)', ' (c)']) out = queries_for_authors("Francesca von Braun-Bates") self.assertListEqual( out, [("Francesca von Braun-Bates", 'von Braun-Bates, F')]) out = queries_for_authors("Fritz Moritz von Rohrscheidt") self.assertListEqual( out, [("Fritz Moritz von Rohrscheidt", "von Rohrscheidt, F M")]) out = queries_for_authors("C. de la Fuente Marcos") self.assertListEqual( out, [('C. de la Fuente Marcos', 'de la Fuente Marcos, C')])
def get_tb_page(arxiv_id: str) -> Response: """Get the data needed to display the trackback page for an arXiv article. Parameters ---------- arxiv_id : str Returns ------- dict Response data. int HTTP status code. dict Headers to add to the response. Raises ------ InternalServerError Raised when there was an unexpected problem executing the query. TrackbackNotFound Raised when trackbacks for an article cannot be found, either because the identifier is invalid or the article metadata is not available. """ response_data: Dict[str, Any] = {} response_headers: Dict[str, Any] = {} if not arxiv_id: raise TrackbackNotFound(data={'missing_id': True}) try: arxiv_identifier = Identifier(arxiv_id=arxiv_id) redirect = check_supplied_identifier(arxiv_identifier, 'browse.tb') if redirect: return redirect response_data['arxiv_identifier'] = arxiv_identifier abs_meta = metadata.get_abs(arxiv_identifier.id) if abs_meta: response_data['abs_meta'] = abs_meta trackback_pings = get_paper_trackback_pings(arxiv_identifier.id) response_data['trackback_pings'] = trackback_pings if len(trackback_pings) > 0: response_data['author_links'] = \ split_long_author_list(queries_for_authors( abs_meta.authors.raw), truncate_author_list_size) response_status = status.HTTP_200_OK except AbsNotFoundException: raise TrackbackNotFound(data={'arxiv_id': arxiv_id, 'not_found': True}) except (AbsException, IdentifierException): raise TrackbackNotFound(data={'arxiv_id': arxiv_id}) except Exception as ex: logger.warning(f'Error getting trackbacks: {ex}') raise InternalServerError from ex return response_data, response_status, response_headers
def test_split_long_author_list(self): f1 = path_of_for_test( 'data/abs_files/ftp/arxiv/papers/1411/1411.4413.abs') meta: metadata = AbsMetaSession.parse_abs_file(filename=f1) alst = split_long_author_list(queries_for_authors(str(meta.authors)), 20) self.assertIs(type(alst), tuple) self.assertIs(len(alst), 3) self.assertIs(type(alst[0]), list) self.assertIs(type(alst[1]), list) self.assertGreater(len(alst[1]), 0) self.assertIs(type(alst[2]), int)
def test_split_with_collaboration(self): f1 = path_of_for_test( 'data/abs_files/ftp/arxiv/papers/0808/0808.4142.abs') meta: metadata = AbsMetaSession.parse_abs_file(filename=f1) split = split_authors(str(meta.authors)) self.assertListEqual( split, ['D0 Collaboration', ':', 'V. Abazov', ',', 'et al']) alst = queries_for_authors(str(meta.authors)) self.assertListEqual(alst, [('D0 Collaboration', 'D0 Collaboration'), ': ', ('V. Abazov', 'Abazov, V'), ', ', 'et al'])
def test_split_strange_author_list(self): """Test odd author list that shows '0 additional authors' ARXIVNG-2083""" f1 = path_of_for_test( 'data/abs_files/ftp/arxiv/papers/1902/1902.05884.abs') meta: metadata = AbsMetaSession.parse_abs_file(filename=f1) alst = split_long_author_list(queries_for_authors(str(meta.authors)), 100) self.assertIs(type(alst), tuple) self.assertIs(len(alst), 3) self.assertIs(type(alst[0]), list) self.assertIs(type(alst[1]), list) self.assertIs(type(alst[2]), int) self.assertEqual( len(list(filter(lambda x: isinstance(x, tuple), alst[0]))), 101) self.assertEqual(len(alst[1]), 0, "Back list on 1902.05884 should be empty") self.assertEqual(alst[2], 0, "Back list size on 1902.05884 should be empty")
def get_abs_page(arxiv_id: str) -> Response: """Get abs page data from the document metadata service. Parameters ---------- arxiv_id : str The arXiv identifier as provided in the request. download_format_pref: str Download format preference. Returns ------- dict Search result response data. int HTTP status code. dict Headers to add to the response. Raises ------ :class:`.InternalServerError` Raised when there was an unexpected problem executing the query. """ response_data: Dict[str, Any] = {} response_headers: Dict[str, Any] = {} try: arxiv_id = _check_legacy_id_params(arxiv_id) arxiv_identifier = Identifier(arxiv_id=arxiv_id) redirect = check_supplied_identifier(arxiv_identifier, 'browse.abstract') if redirect: return redirect abs_meta = metadata.get_abs(arxiv_id) response_data['requested_id'] = arxiv_identifier.idv \ if arxiv_identifier.has_version else arxiv_identifier.id response_data['abs_meta'] = abs_meta response_data['meta_tags'] = meta_tag_metadata(abs_meta) response_data['author_links'] = \ split_long_author_list(queries_for_authors( abs_meta.authors.raw), truncate_author_list_size) response_data['url_for_author_search'] = \ lambda author_query: url_for('search_archive', searchtype='author', archive=abs_meta.primary_archive.id, query=author_query) # Dissemination formats for download links download_format_pref = request.cookies.get('xxx-ps-defaults') add_sciencewise_ping = _check_sciencewise_ping(abs_meta.arxiv_id_v) response_data['formats'] = metadata.get_dissemination_formats( abs_meta, download_format_pref, add_sciencewise_ping) # Following are less critical and template must display without them # try: _non_critical_abs_data(abs_meta, arxiv_identifier, response_data) # except Exception: # logger.warning("Error getting non-critical abs page data", # exc_info=app.debug) except AbsNotFoundException: if arxiv_identifier.is_old_id and arxiv_identifier.archive \ in taxonomy.definitions.ARCHIVES: archive_name = taxonomy.definitions.ARCHIVES[ arxiv_identifier.archive]['name'] raise AbsNotFound( data={ 'reason': 'old_id_not_found', 'arxiv_id': arxiv_id, 'archive_id': arxiv_identifier.archive, 'archive_name': archive_name }) raise AbsNotFound(data={'reason': 'not_found', 'arxiv_id': arxiv_id}) except AbsVersionNotFoundException: raise AbsNotFound( data={ 'reason': 'version_not_found', 'arxiv_id': arxiv_identifier.idv, 'arxiv_id_latest': arxiv_identifier.id }) except AbsDeletedException as e: raise AbsNotFound( data={ 'reason': 'deleted', 'arxiv_id_latest': arxiv_identifier.id, 'message': e }) except IdentifierIsArchiveException as e: raise AbsNotFound(data={ 'reason': 'is_archive', 'arxiv_id': arxiv_id, 'archive_name': e }) except IdentifierException: raise AbsNotFound(data={'arxiv_id': arxiv_id}) except AbsException as e: raise InternalServerError( 'There was a problem. If this problem persists, please contact ' '[email protected].') from e response_status = status.HTTP_200_OK not_modified = _check_request_headers(abs_meta, response_data, response_headers) if not_modified: return {}, status.HTTP_304_NOT_MODIFIED, response_headers return response_data, response_status, response_headers
def author_links(abs_meta: DocMetadata) -> Tuple[AuthorList, AuthorList, int]: """Creates author list links in a very similar way to abs page.""" return split_long_author_list(queries_for_authors(abs_meta.authors.raw), truncate_author_list_size)