class TestEventExtractor(unittest.TestCase):
def setUp(self):
self.doc_dir = join(ROOT_PATH, "testdocs", "event", "1_pt-br.pdf")
self.preparator = Preparator(self.doc_dir)
self.extractor = EventExtractor(self.doc_dir)
self.parse = Parser("event.xml")
self.xml_template_metadata = self.parse.xml_template_metadata()
def test_metadata_extractor_generates_metadata_dict(self):
self.extractor.all_metadata() | should_not | be_empty
def test_event_document_has_an_abstract_metadata_pattern_found_by_regex(self):
doc = self.extractor._clean_onepage_doc
matches = re.search(r"resumo:* (.*?) (palavr(a|as)(.|\s)chav(e|es).|unitermos|descritores)", doc)
matches.group() | should | start_with("resumo")
self.extractor._abstract_metadata | should_not | equal_to("")
def test_event_document_has_author_type_metadata(self):
self.extractor._author_metadata() | should_not | be_empty
def test_event_document_has_title_type_metadata(self):
self.extractor._title_metadata() | should_not | be_empty
