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
class TestRCEController(unittest.TestCase):
some_text = """Neurocomputing 35 (2000) 3}26
Class separability estimation and incremental learning using
boundary methods Jose-Luis Sancho *, William E. Pierson ,
Batu Ulug , H AnmH bal R. Figueiras-Vidal , Stanley C. Ahalt
ATSC-DI, Escuela Politecnica Superior. Universidad Carlos III
Leganes-Madrid, Spain & & Department of Electrical Engineering,
he Ohio State University Columbus, OH 43210, USA Received 7
January 1999; revised 5 April 1999; accepted 10 April 2000
Abstract In this paper we discuss the use of boundary methods
(BMs) for distribution analysis. We view these methods as tools
which can be used to extract useful information from sample
distributions. We believe that the information thus extracted has
utility for a number of applications, but in particular we discuss
the use of BMs as a mechanism for class separability estimation and
as an aid to constructing robust and e$cient neural networks (NNs)
to solve classi"cation problems. In the "rst case, BMs can
establish the utili...
"""
def setUp(self):
factory = UtilFactory()
self.rcec = RCEController(factory)
self.pdf = normpath(join(dirname(__file__), ('../../../../tests/'
'fixtures/extraction/article.pdf')))
def tearDown(self):
pass
def test_extract_content_from_non_existent_file(self):
content = self.rcec.extract_content('somefile.pdf', FileFormat.TXT)
self.failUnless(content is None)
def test_extract_content_to_invalid_target_format(self):
content = self.rcec.extract_content(self.pdf, 'invalid format')
self.failUnless(content is None)
def test_extract_content_from_pdf(self):
content = self.rcec.extract_content(self.pdf, FileFormat.TXT)
self.failUnless(content is not None)
def test_get_query_strings(self):
strings = self.rcec.get_query_strings(self.some_text)
self.failUnless(len(strings) > 0)
class TestRCEController(unittest.TestCase):
some_text = """Neurocomputing 35 (2000) 3}26
Class separability estimation and incremental learning using
boundary methods Jose-Luis Sancho *, William E. Pierson ,
Batu Ulug , H AnmH bal R. Figueiras-Vidal , Stanley C. Ahalt
ATSC-DI, Escuela Politecnica Superior. Universidad Carlos III
Leganes-Madrid, Spain & & Department of Electrical Engineering,
he Ohio State University Columbus, OH 43210, USA Received 7
January 1999; revised 5 April 1999; accepted 10 April 2000
Abstract In this paper we discuss the use of boundary methods
(BMs) for distribution analysis. We view these methods as tools
which can be used to extract useful information from sample
distributions. We believe that the information thus extracted has
utility for a number of applications, but in particular we discuss
the use of BMs as a mechanism for class separability estimation and
as an aid to constructing robust and e$cient neural networks (NNs)
to solve classi"cation problems. In the "rst case, BMs can
establish the utili...
"""
def setUp(self):
factory = UtilFactory()
self.rcec = RCEController(factory)
self.pdf = normpath(join(dirname(__file__), ("../../../../tests/" "fixtures/extraction/article.pdf")))
def tearDown(self):
pass
def test_extract_content_from_non_existent_file(self):
content = self.rcec.extract_content("somefile.pdf", FileFormat.TXT)
self.failUnless(content is None)
def test_extract_content_to_invalid_target_format(self):
content = self.rcec.extract_content(self.pdf, "invalid format")
self.failUnless(content is None)
def test_extract_content_from_pdf(self):
content = self.rcec.extract_content(self.pdf, FileFormat.TXT)
self.failUnless(content is not None)
def test_get_query_strings(self):
strings = self.rcec.get_query_strings(self.some_text)
self.failUnless(len(strings) > 0)
def setUp(self):
factory = UtilFactory()
self.rcec = RCEController(factory)
self.pdf = normpath(join(dirname(__file__), ("../../../../tests/" "fixtures/extraction/article.pdf")))
def setUp(self):
factory = UtilFactory()
self.rcec = RCEController(factory)
self.pdf = normpath(join(dirname(__file__), ('../../../../tests/'
'fixtures/extraction/article.pdf')))
