class TestPubMatcher:
def __init__(self):
self.matcher = PubMatcher()
#
# Test
#
def test_matchPub(self):
self.extractor = Extractor().getInstance()
pubdao = PublicationDao()
person_id = 13419
person_name = 'jie tang'
# Read sources from files
all_models = {}
for page in range(0, 3):
filename = "".join((person_name, '_page_', str(page), '.html'))
f = file(os.path.join(self.settings.source_dir, filename), 'r')
html = f.read()
models = self.extractor.extract_from_source(html)
if models is not None:
self.extractor._Extractor__merge_into_extractedmap(
all_models, models)
print 'Total found DEBUG %s items.' % len(all_models)
# part 2
pubs = pubdao.getPublicationByPerson(person_id,
self.settings.generation)
printout = False
if printout:
for key, models in all_models.items():
print key, " --> ", models
print '==================='
for pub in pubs:
print pub
(pubs_matched, pubs_not_matched) = self.matchPub(pubs, all_models)
print '- test done -', len(pubs_matched), len(pubs_not_matched)
return pubs_not_matched
def test_fetchByPubs(self, pubs):
'''Test use a list of pubs that not found in person search'''
print '-- test fetchByPubs %s pubs', len(pubs)
new_pubs = []
for pub in pubs:
new_pubs.append((pub, 'jie tang'))
extractor = Extractor()
extractor.getNodesByPubs(new_pubs)
print '- test done -'
def test_match_with_authors(self):
data_test = ((
'… DeSmedt, W Du, W <b>Kent</b>, MA Ketabchi, WA … - …, 1991 - doi.ieeecomputersociety.org',
'Rafi Ahmed,Philippe De Smedt,Weimin Du,William Kent,Mohammad A. Ketabchi,Witold Litwin,Abbas Rafii,Ming-Chien Shan'
), (
'R Ahmed, P DeSmedt, W Du, W Kent, MA … - …, 1991 - doi.ieeecomputersociety.org',
'Rafi Ahmed,Philippe De Smedt,Weimin Du,William Kent,Mohammad A. Ketabchi,Witold Litwin,Abbas Rafii,Ming-Chien Shan'
), (
'P Lyngbaek, W Kent - … on the 1986 international workshop on Object …, 1986 - portal.acm.org',
'Peter Lyngbak,William Kent'
), (
'W Kent - Proceedings of the 8th Bristish National …, 1990 - fog.hpl.external.hp.com',
'William Kent'
), (
'DE Neiman, DW Hildum, VR Lessef, T …',
'Daniel E. Neiman,David W. Hildum,Victor R. Lesser,Tuomas Sandholm'
), (
'M Esmaili, R Safavi-Naini, J Pieprzyk',
'Mansour Esmaili,Reihaneh Safavi-Naini,Josef Pieprzyk'
), ('DH Fishman, J Annevelink, E Chow, T …',
'Daniel H. Fishman,Jurgen Annevelink,David Beech,E. C. Chow,Tim Connors,J. W. Davis,Waqar Hasan,C. G. Hoch,William Kent,S. Leichner,Peter Lyngbak,Brom Mahbod,Marie-Anne Neimat,Tore Risch,Ming-Chien Shan,W. Kevin Wilkinson'
))
data_debug = ((
'DH Fishman, J Annevelink, E Chow, T …',
'Daniel H. Fishman,Jurgen Annevelink,David Beech,E. C. Chow,Tim Connors,J. W. Davis,Waqar Hasan,C. G. Hoch,William Kent,S. Leichner,Peter Lyngbak,Brom Mahbod,Marie-Anne Neimat,Tore Risch,Ming-Chien Shan,W. Kevin Wilkinson'
), )
for ga, da in data_debug:
print "match: %s \n with: %s \n is: %s" % (ga, da, \
self.matcher.matchAuthors(ga, da, debug_output=True))
class TestPubMatcher:
def __init__(self):
self.matcher = PubMatcher()
#
# Test
#
def test_matchPub(self):
self.extractor = Extractor().getInstance()
pubdao = PublicationDao()
person_id = 13419
person_name = 'jie tang'
# Read sources from files
all_models = {}
for page in range(0, 3):
filename = "".join((person_name, '_page_', str(page), '.html'))
f = file(os.path.join(self.settings.source_dir, filename), 'r')
html = f.read()
models = self.extractor.extract_from_source(html)
if models is not None:
self.extractor._Extractor__merge_into_extractedmap(all_models, models)
print 'Total found DEBUG %s items.' % len(all_models)
# part 2
pubs = pubdao.getPublicationByPerson(person_id, self.settings.generation)
printout = False
if printout:
for key, models in all_models.items():
print key, " --> ", models
print '==================='
for pub in pubs:
print pub
(pubs_matched, pubs_not_matched) = self.matchPub(pubs, all_models)
print '- test done -', len(pubs_matched), len(pubs_not_matched)
return pubs_not_matched
def test_fetchByPubs(self, pubs):
'''Test use a list of pubs that not found in person search'''
print '-- test fetchByPubs %s pubs', len(pubs)
new_pubs = []
for pub in pubs:
new_pubs.append((pub, 'jie tang'))
extractor = Extractor()
extractor.getNodesByPubs(new_pubs)
print '- test done -'
def test_match_with_authors(self):
data_test = (
('… DeSmedt, W Du, W <b>Kent</b>, MA Ketabchi, WA … - …, 1991 - doi.ieeecomputersociety.org',
'Rafi Ahmed,Philippe De Smedt,Weimin Du,William Kent,Mohammad A. Ketabchi,Witold Litwin,Abbas Rafii,Ming-Chien Shan'),
('R Ahmed, P DeSmedt, W Du, W Kent, MA … - …, 1991 - doi.ieeecomputersociety.org',
'Rafi Ahmed,Philippe De Smedt,Weimin Du,William Kent,Mohammad A. Ketabchi,Witold Litwin,Abbas Rafii,Ming-Chien Shan'),
('P Lyngbaek, W Kent - … on the 1986 international workshop on Object …, 1986 - portal.acm.org',
'Peter Lyngbak,William Kent'),
('W Kent - Proceedings of the 8th Bristish National …, 1990 - fog.hpl.external.hp.com',
'William Kent'),
('DE Neiman, DW Hildum, VR Lessef, T …',
'Daniel E. Neiman,David W. Hildum,Victor R. Lesser,Tuomas Sandholm'),
('M Esmaili, R Safavi-Naini, J Pieprzyk',
'Mansour Esmaili,Reihaneh Safavi-Naini,Josef Pieprzyk'),
('DH Fishman, J Annevelink, E Chow, T …',
'Daniel H. Fishman,Jurgen Annevelink,David Beech,E. C. Chow,Tim Connors,J. W. Davis,Waqar Hasan,C. G. Hoch,William Kent,S. Leichner,Peter Lyngbak,Brom Mahbod,Marie-Anne Neimat,Tore Risch,Ming-Chien Shan,W. Kevin Wilkinson')
)
data_debug = (
('DH Fishman, J Annevelink, E Chow, T …',
'Daniel H. Fishman,Jurgen Annevelink,David Beech,E. C. Chow,Tim Connors,J. W. Davis,Waqar Hasan,C. G. Hoch,William Kent,S. Leichner,Peter Lyngbak,Brom Mahbod,Marie-Anne Neimat,Tore Risch,Ming-Chien Shan,W. Kevin Wilkinson'),
)
for ga, da in data_debug:
print "match: %s \n with: %s \n is: %s" % (ga, da, \
self.matcher.matchAuthors(ga, da, debug_output=True))
