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_getNodesByPersonName(self):
'''Test method getNodesByPersonName.'''
print '-TEST-:', self.test_extractFromPage.__doc__.strip()
e = Extractor()
models = e.getNodesByPersonName('jie tang')
for model in models:
print model
print '-END TEST-'
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 __init__(self):
self.extractor = Extractor().getInstance()
def __init__(self):
self.extractor = Extractor().getInstance()
self.settings = Settings.getInstance()
