def test_page_count(self): # verify %pc outputs page_count properly formatted = [u'Yang, Huihui and Chen, Hongshan. (2017). 71, 191, 9 pp.\n', u'Knapp, Wilfried and Thuemen, Chris. (2017). 13, 25, 6 pp.\n'] custom_format = CustomFormat(custom_format=r'%A. (%Y). %q, %V, %p, %pc pp.') custom_format.set_json_from_solr(solrdata.data_8) assert (custom_format.get().get('export', '') == ''.join(formatted))
def custom_format_export(): try: payload = request.get_json(force=True) # post data in json except: payload = dict(request.form) # post data in form encoding if not payload: return return_response({'error': 'no information received'}, 400) if 'bibcode' not in payload: return return_response( { 'error': 'no bibcode found in payload (parameter name is `bibcode`)' }, 400) if 'format' not in payload: return return_response( { 'error': 'no custom format found in payload (parameter name is `format`)' }, 400) if 'sort' in payload: if type(payload['sort']) is list: sort = payload['sort'][0] else: sort = payload['sort'] else: sort = 'date desc, bibcode desc' bibcodes = payload['bibcode'] try: if type(payload['format']) is list: custom_format_str = payload['format'][0] else: custom_format_str = payload['format'] except Exception as e: return return_response({'error': 'unable to read custom format'}, 400) current_app.logger.info( 'received request with bibcodes={bibcodes} to export in a custom format: {custom_format_str} style using sort order={sort}' .format(bibcodes=','.join(bibcodes), custom_format_str=custom_format_str.encode('utf8'), sort=sort)) if (len(bibcodes) == 0) or (len(custom_format_str) == 0): return return_response( {'error': 'not all the needed information received'}, 400) # pass the user defined format to CustomFormat to parse and we would be able to get which fields # in Solr we need to query on custom_export = CustomFormat(custom_format=custom_format_str) fields = custom_export.get_solr_fields() # now get the required data from Solr and send it to customFormat for formatting solr_data = get_solr_data(bibcodes=bibcodes, fields=fields, sort=sort) if (solr_data is not None): if ('error' in solr_data): return return_response({'error': 'unable to query solr'}, 400) custom_export.set_json_from_solr(solr_data) return return_response(custom_export.get(), 200, 'POST') return return_response({'error': 'no result from solr'}, 404)
def test_custom(self): # format the stubdata using the code custom_format = CustomFormat(custom_format=r'%ZEncoding:latex\\bibitem[%2.1m\\(%Y)]{%2H%Y}\ %5.3l\ %Y\,%j\,%V\,%p ') custom_format.set_json_from_solr(solrdata.data) # now compare it with an already formatted data that we know is correct assert (custom_format.get() == customTest.data) # verify correct solr fields are fetched assert (custom_format.get_solr_fields() == 'author,year,pub,volume,page,page_range,bibcode,bibstem')
def test_get_affiliation_list_limit(self): custom_format = CustomFormat(custom_format=r'%2F') custom_format.set_json_from_solr(solrdata.data_3) # with only 2 affiliations a_doc = solrdata.data_3['response'].get('docs')[0] expected_aff_list = "AA(Department of Physics, Queen's University, Kingston, Ontario, K7L 3N6, Canada; Space Telescope Science Institute, Baltimore, MD); " \ "AB(Department of Physics and Astronomy, University of Calgary, Calgary, Alberta, T2N 1N4, Canada)" assert (custom_format._CustomFormat__get_affiliation_list(a_doc) == expected_aff_list)
def test_author_sep(self): # verify when missing it is False custom_format = CustomFormat(custom_format=r'%ZEncoding:latex %ZHeader:"at the top of the page" %ZFooter:"at the bottom of the page" %ZLinelength:100 %zn\\item %N,%Y,{\\em %J\}, \{\\bf %V\}, %p--%P (%c citations)\n') custom_format._CustomFormat__parse_command() assert (len(custom_format.author_sep) == 0) # verify when the parameter is defined, comma is replaced by the defined seprator custom_format = CustomFormat(custom_format=r'%ZAuthorSep:"; " %A') custom_format.set_json_from_solr(solrdata.data_3) author_list_with_new_sep = u'English, Jayanne; Taylor, A. R.; Mashchenko, S. Y.; Irwin, Judith A.; Basu, Shantanu; and Johnstone, Doug' assert (custom_format._CustomFormat__get_author_list('%A', index=0) == author_list_with_new_sep)
def test_add_clean_pub_raw(self): custom_format = CustomFormat(custom_format=r'') custom_format.set_json_from_solr(solrdata.data) # need clean up a_doc = solrdata.data['response'].get('docs')[16] assert (custom_format._CustomFormat__add_clean_pub_raw(a_doc) == 'American Astronomical Society Meeting 210, id.21.04') # no change required a_doc = solrdata.data['response'].get('docs')[17] assert (custom_format._CustomFormat__add_clean_pub_raw(a_doc) == 'Research Journal of Physics, vol. 1, issue 1, pp. 35-41')
def test_get_keywords(self): custom_format = CustomFormat(custom_format=r'') custom_format.set_json_from_solr(solrdata.data_3) # with keywords a_doc = solrdata.data_3['response'].get('docs')[0] expected_keywords = "GALAXY: HALO, GALAXY: STRUCTURE, ISM: BUBBLES, ISM: INDIVIDUAL: ALPHANUMERIC: GW 123.4-1.5, ISM: STRUCTURE, Astrophysics" assert (custom_format._CustomFormat__get_keywords(a_doc) == expected_keywords) # without keywords a_doc = dict(a_doc) a_doc.pop('keyword') assert (custom_format._CustomFormat__get_keywords(a_doc) == '')
def test_get_publication(self): custom_format = CustomFormat(custom_format=r'') custom_format.set_json_from_solr(solrdata.data_3) publication_format = { '%J':'The Astrophysical Journal', '%j':'\\apjl', '%Q':'The Astrophysical Journal, Volume 533, Issue 1, pp. L25-L28.', '%q':'ApJL', '%%':'', } a_doc = solrdata.data_3['response'].get('docs')[0] for key, value in publication_format.iteritems(): assert (custom_format._CustomFormat__get_publication(key, a_doc) == value)
def custom_format_export(): try: payload = request.get_json(force=True) # post data in json except: payload = dict(request.form) # post data in form encoding if not payload: return return_response({'error': 'no information received'}, 400) if 'bibcode' not in payload: return return_response( { 'error': 'no bibcode found in payload (parameter name is `bibcode`)' }, 400) if 'format' not in payload: return return_response( { 'error': 'no custom format found in payload (parameter name is `format`)' }, 400) bibcodes = payload['bibcode'] custom_format_str = payload['format'] current_app.logger.debug( 'received request with bibcodes={bibcodes} to export in a custom format: {custom_format_str}' .format(bibcodes=''.join(bibcodes), custom_format_str=custom_format_str)) if (len(bibcodes) == 0) or (len(custom_format_str) == 0): return return_response( {'error': 'not all the needed information received'}, 400) # pass the user defined format to CustomFormat to parse and we would be able to get which fields # in Solr we need to query on custom_export = CustomFormat(custom_format=custom_format_str) fields = custom_export.get_solr_fields() # now get the required data from Solr and send it to customFormat for formatting solr_data = get_solr_data(bibcodes=bibcodes, fields=fields) if (solr_data is not None): if ('error' in solr_data): return return_response({'error': 'unable to query solr'}, 400) custom_export.set_json_from_solr(solr_data) return return_response(custom_export.get(), 200) return return_response({'error': 'no result from solr'}, 404)
def test_get_affiliation_list(self): custom_format = CustomFormat(custom_format=r'') custom_format.set_json_from_solr(solrdata.data_3) # with affiliation a_doc = solrdata.data_3['response'].get('docs')[0] expected_aff_list = u"AA(Department of Physics, Queen's University, Kingston, Ontario, K7L 3N6, Canada; Space Telescope Science Institute, Baltimore, MD); " \ u"AB(Department of Physics and Astronomy, University of Calgary, Calgary, Alberta, T2N 1N4, Canada); " \ u"AC(Department de Physique, Université de Montréal, Montréal, Québec, H3C 3J7, Canada); " \ u"AD(Department of Physics, Queen's University, Kingston, Ontario, K7L 3N6, Canada); " \ u"AE(Department of Physics and Astronomy, University of Western Ontario, London, Ontario, N6A 3K7, Canada); " \ u"AF(University of Toronto, 60 St. George Street, Toronto, Ontario, M5S 3H8, Canada)" assert (custom_format._CustomFormat__get_affiliation_list(a_doc) == expected_aff_list) # without affiliation a_doc = dict(a_doc) a_doc.pop('aff') assert (custom_format._CustomFormat__get_affiliation_list(a_doc) == '')
def test_field_encoding(self): # latex field encoding custom_format = CustomFormat(custom_format=r'%\A') custom_format.set_json_from_solr(solrdata.data_4) author_list_encoded = u'Ryan, R.~E. and McCullough, P.~R.' assert (custom_format._CustomFormat__encode(value=custom_format._CustomFormat__get_author_list(format=r'%\A', index=0), field='author', field_format=r'%\A') == author_list_encoded) # html field encoding abstract = u"We present a large grid of stellar evolutionary tracks, which are suitable to modelling star clusters and galaxies by means of population synthesis. The tracks are presented for the initial chemical compositions [Z=0.0004, Y=0.23], [Z=0.001, Y=0.23], [Z=0.004, Y=0.24], [Z=0.008, Y=0.25], [Z=0.019, Y=0.273] (solar composition), and [Z=0.03, Y=0.30]. They are computed with updated opacities and equation of state, and a moderate amount of convective overshoot. The range of initial masses goes from 0.15 M<SUB>sun</SUB> to 7 M<SUB>sun</SUB>, and the evolutionary phases extend from the zero age main sequence (ZAMS) till either the thermally pulsing AGB regime or carbon ignition. We also present an additional set of models with solar composition, computed using the classical Schwarzschild criterion for convective boundaries. From all these tracks, we derive the theoretical isochrones in the Johnson-Cousins UBVRIJHK broad-band photometric system." abstract_html = "We present a large grid of stellar evolutionary tracks, which are suitable to modelling star clusters and galaxies by means of population synthesis. The tracks are presented for the initial chemical compositions [Z=0.0004, Y=0.23], [Z=0.001, Y=0.23], [Z=0.004, Y=0.24], [Z=0.008, Y=0.25], [Z=0.019, Y=0.273] (solar composition), and [Z=0.03, Y=0.30]. They are computed with updated opacities and equation of state, and a moderate amount of convective overshoot. The range of initial masses goes from 0.15 M<SUB>sun</SUB> to 7 M<SUB>sun</SUB>, and the evolutionary phases extend from the zero age main sequence (ZAMS) till either the thermally pulsing AGB regime or carbon ignition. We also present an additional set of models with solar composition, computed using the classical Schwarzschild criterion for convective boundaries. From all these tracks, we derive the theoretical isochrones in the Johnson-Cousins UBVRIJHK broad-band photometric system." assert (custom_format._CustomFormat__encode(value=abstract, field='abstract', field_format='%>B') == abstract_html) # hex field encoding # url field encoding url = '<a href="http://adsabs.harvard.edu/abs/1997AAS...190.1403E">1997AAS...190.1403E</a>' url_encoded = '<a+href=%22http://adsabs.harvard.edu/abs/1997AAS...190.1403E%22>1997AAS...190.1403E</a>' assert (custom_format._CustomFormat__encode(value=url, field='url', field_format='%/U') == url_encoded)
def test_end_record_insert(self): # verify string specified with %ZEOL gets inserted after each record # no EOL string custom_format = CustomFormat(custom_format=r'%ZEOL:"" %R') custom_format.set_json_from_solr(solrdata.data_6) assert (custom_format.get().get('export', ''), "2020AAS...23528705A2019EPSC...13.1911A2015scop.confE...3A2019AAS...23338108A2019AAS...23320704A2018EPJWC.18608001A2018AAS...23221409A2017ASPC..512...45A2018AAS...23136217A2018AAS...23130709A") # do not specify EOL string, and default linefeed is added in custom_format = CustomFormat(custom_format=r'%R') custom_format.set_json_from_solr(solrdata.data_6) assert (custom_format.get().get('export', ''), "2020AAS...23528705A\n2019EPSC...13.1911A\n2015scop.confE...3A\n2019AAS...23338108A\n2019AAS...23320704A\n2018EPJWC.18608001A\n2018AAS...23221409A\n2017ASPC..512...45A\n2018AAS...23136217A\n2018AAS...23130709A\n") # specify EOL string custom_format = CustomFormat(custom_format=r'%ZEOL:"--END" %R') custom_format.set_json_from_solr(solrdata.data_6) assert (custom_format.get().get('export', ''), "2020AAS...23528705A--END2019EPSC...13.1911A--END2015scop.confE...3A--END2019AAS...23338108A--END2019AAS...23320704A--END2018EPJWC.18608001A--END2018AAS...23221409A--END2017ASPC..512...45A--END2018AAS...23136217A--END2018AAS...23130709A--END")
def test_get_author_list(self): # Optional parameters for author field: n.m # If the number of authors in the list is larger than n, the list will be truncated and m authors are returned custom_format = CustomFormat(custom_format=r'%A,%3.2A,%a,%3.2a,%G,%3.2G,%g,%3.2g,%H,%3.2H,%2.1H,%h,%3.2h,%I,%3.2I,%i,%3.2i,' r'%L,%3.2L,%l,%3.2l,%M,%3.2M,%m,%3.2m,%N,%3.2N,%n,%3.2n,%i,%3.2i,%e,%3.2e,%f,%3.2f' r'%^A,%^a,%^G,%^g,%^H,%^h,%^I,%^i,%^L,%^l,%^M,%^m,%^N,%^n,%^e,%^f' ) custom_format.set_json_from_solr(solrdata.data_3) # acutal data from solr: ['English, Jayanne', 'Taylor, A. R.', 'Mashchenko, S. Y.', 'Irwin, Judith A.', 'Basu, Shantanu', 'Johnstone, Doug'] author_format = OrderedDict([ ('%A', 'English, Jayanne, Taylor, A. R., Mashchenko, S. Y., Irwin, Judith A., Basu, Shantanu, and Johnstone, Doug'), ('%3.2A', 'English, Jayanne, Taylor, A. R., and 4 colleagues'), ('%a', 'English, Jayanne, Taylor, A. R., Mashchenko, S. Y., Irwin, Judith A., Basu, Shantanu, & Johnstone, Doug'), ('%3.2a', 'English, Jayanne, Taylor, A. R., et al.'), ('%G', 'English, J., Taylor, A. R., Mashchenko, S. Y., Irwin, J. A., Basu, S., Johnstone, D.'), ('%3.2G', 'English, J., Taylor, A. R., et al.'), ('%g', 'English J., Taylor A. R., Mashchenko S. Y., Irwin J. A., Basu S., Johnstone D.'), ('%3.2g', 'English J., Taylor A. R., et al.'), ('%H', 'English'), ('%3.2H', 'English Taylor'), ('%2.1H', 'English'), ('%h', 'English'), ('%3.2h', 'English Taylor'), ('%I', 'English, J., A. R. Taylor, S. Y. Mashchenko, J. A. Irwin, S. Basu, and D. Johnstone'), ('%3.2I', 'English, J., A. R. Taylor, and 4 colleagues'), ('%i', 'English, J., A. R. Taylor, S. Y. Mashchenko, J. A. Irwin, S. Basu, & D. Johnstone'), ('%3.2i', 'English, J., A. R. Taylor, et al.'), ('%L', 'English, J., Taylor, A. R., Mashchenko, S. Y., Irwin, J. A., Basu, S., and Johnstone, D.'), ('%3.2L', 'English, J., Taylor, A. R., and 4 colleagues'), ('%l', 'English, J., Taylor, A. R., Mashchenko, S. Y., Irwin, J. A., Basu, S., & Johnstone, D.'), ('%3.2l', 'English, J., Taylor, A. R., et al.'), ('%M', 'English, Taylor, Mashchenko, Irwin, Basu, and Johnstone'), ('%3.2M', 'English, Taylor et al.'), ('%m', 'English, Taylor, Mashchenko, Irwin, Basu, & Johnstone'), ('%3.2m', 'English, Taylor et al.'), ('%N', 'English, J., Taylor, A. R., Mashchenko, S. Y., Irwin, J. A., Basu, S., Johnstone, D.'), ('%3.2N', 'English, J., Taylor, A. R., and 4 colleagues'), ('%n', 'English,+'), ('%3.2n', 'English,+'), ('%e', 'English, J., Taylor, A.R., Mashchenko, S.Y., Irwin, J.A., Basu, S., and Johnstone, D.'), ('%3.2e', 'English, J., Taylor, A.R., and 4 colleagues'), ('%f', 'English, Taylor, Mashchenko, Irwin, Basu, and Johnstone'), ('%3.2f', 'English, Taylor \emph{et al.}'), ('%^A', 'English, Jayanne'), ('%^a', 'English, Jayanne'), ('%^G', 'English, J.'), ('%^g', 'English J.'), ('%^H', 'English'), ('%^h', 'English'), ('%^I', 'English, J.'), ('%^i', 'English, J.'), ('%^L', 'English, J.'), ('%^l', 'English, J.'), ('%^M', 'English'), ('%^m', 'English'), ('%^N', 'English, J.'), ('%^n', 'English'), ('%^e', 'English, J.'), ('%^f', 'English'), ]) for key, value in author_format.iteritems(): assert (custom_format._CustomFormat__get_author_list(format=key, index=0) == value)