def test_cleaned_resume_data_should_not_have_present_job_information(self):
(names, job_titles, labels_list) = clean_data_and_extract_job_titles("1.txt", self.paths, [], [], [])
present_job_title = job_titles[0]
plaintext_filename = labels_list[0][0]
plaintext_data = open(self.plaintext_directory + '/' + plaintext_filename).read()
assert_false(present_job_title in plaintext_data)
def test_cleaned_resume_data_should_not_have_candidate_contact(self):
(names, job_titles, labels_list) = clean_data_and_extract_job_titles("1.txt", self.paths, [], [], [])
resume_xml = etree.parse(self.xml_files_path + '/1.txt')
candidate_phone = resume_xml.xpath('//phone/text()')[0]
plaintext_filename = labels_list[0][0]
plaintext_data = open(self.plaintext_directory + '/' + plaintext_filename).read()
assert_false(candidate_phone in plaintext_data)
def test_cleaned_resume_data_should_not_have_candidate_name(self):
(names, job_titles, labels_list) = clean_data_and_extract_job_titles("1.txt", self.paths, [], [], [])
candidate_name = names[0].split()
plaintext_filename = labels_list[0][0]
plaintext_data = open(self.plaintext_directory + '/' + plaintext_filename).read()
for n in candidate_name:
assert_false(n in plaintext_data)
def test_present_job_title_should_match_resume_label(self):
(names, job_titles, labels_list) = clean_data_and_extract_job_titles("1.txt", self.paths, [], [], [])
present_job_title = job_titles[0]
resume_label = labels_list[0][1]
assert_equals(present_job_title, resume_label)
