class TestReferenceValidator(unittest.TestCase):
def setUp(self):
self.rv = ReferenceValidator(weights={'title':0.75, 'author':0.25})
def tearDown(self):
pass
def test_validate_correct_reference(self):
correct_ref = Reference()
correct_ref.set_field('author', [{'first_name':'Jose-Luis',
'last_name':'Sancho',
'middle_name':''}], True)
correct_ref.set_field('title', ('Class separability estimation and '
'incremental learning using boundary methods'), True)
self.rv.validate(correct_ref)
self.failUnless(correct_ref.validity == 1.0)
def test_validate_incorrect_reference(self):
incorrect_ref = Reference()
incorrect_ref.set_field('title', ('some arbitrary text'), False)
incorrect_ref.set_field('author', [{'first_name':'Jose-Luis',
'last_name':'Sancho',
'middle_name':''}], True)
self.rv.validate(incorrect_ref)
self.failUnless(incorrect_ref.validity < 0.5)
class TestReferenceValidator(unittest.TestCase):
def setUp(self):
self.rv = ReferenceValidator(weights={'title': 0.75, 'author': 0.25})
def tearDown(self):
pass
def test_validate_correct_reference(self):
correct_ref = Reference()
correct_ref.set_field('author', [{
'first_name': 'Jose-Luis',
'last_name': 'Sancho',
'middle_name': ''
}], True)
correct_ref.set_field('title',
('Class separability estimation and '
'incremental learning using boundary methods'),
True)
self.rv.validate(correct_ref)
self.failUnless(correct_ref.validity == 1.0)
def test_validate_incorrect_reference(self):
incorrect_ref = Reference()
incorrect_ref.set_field('title', ('some arbitrary text'), False)
incorrect_ref.set_field('author', [{
'first_name': 'Jose-Luis',
'last_name': 'Sancho',
'middle_name': ''
}], True)
self.rv.validate(incorrect_ref)
self.failUnless(incorrect_ref.validity < 0.5)
def make_reference(self, file, target_format):
"""
Uses the controllers to extract the content of a file, get some query
strings, retrieve results from a search engine, and extract the
reference.
"""
extraction = Extraction()
extraction.file_path = file
extraction.target_format = target_format
log.info("Making reference for file: %s" % file) #@UndefinedVariable
rce = RCEController(self.factory)
raw_text = rce.extract_content(file, FileFormat.TXT)
if not raw_text:
return extraction
extraction.query_strings = rce.get_query_strings(raw_text)
if not extraction.query_strings:
log.error('No query strings extracted') #@UndefinedVariable
return extraction
log.debug("Query strings %s" % str(extraction.query_strings)) #@UndefinedVariable
ir = IRController(self.factory)
extraction.top_results, extraction.used_query = (
ir.get_top_results(extraction.query_strings))
if not extraction.top_results:
log.error('No top results to use with the available wrappers ' #@UndefinedVariable
'after trying %d queries' %
len(extraction.query_strings))
return extraction
extraction.query_strings.remove(extraction.used_query)
log.debug("Used query %s" % str(extraction.used_query)) #@UndefinedVariable
log.debug("Query returned %d top results" % len(extraction.top_results)) #@UndefinedVariable
ie = IEController(self.factory, target_format)
extraction.entries, extraction.used_result = (
ie.extract_reference(extraction.top_results, raw_text))
extraction.top_results.remove(extraction.used_result)
log.info("Used result: %s" % str(extraction.used_result)) #@UndefinedVariable
validator = ReferenceValidator(FIELD_WEIGHTS)
for entry in extraction.entries:
validator.validate(entry, raw_text)
return extraction
def setUp(self):
self.rv = ReferenceValidator(weights={'title':0.75, 'author':0.25})
def setUp(self):
self.rv = ReferenceValidator(weights={'title': 0.75, 'author': 0.25})
