def test_get_main_article_with_references(self):
article_paragraphs = parse_elife_xml.get_main_article(self.soup,
keep_references=True)
text_with_article_ref = 'removed by the proteasome (Finley, 2009). The barrel-shaped core peptidase'
text_found_in_paragraph = text_with_article_ref in article_paragraphs[0]
self.assertTrue(text_found_in_paragraph)
def test_get_main_article_returns_correct_text(self):
article_paragraphs = parse_elife_xml.get_main_article(self.soup)
first_paragraph_start_text = 'The eukaryotic 26S proteasome is a large multi-enzyme'
last_paragraph_end_text = 'been deposited under accession ID: 3JCK in the PDB.'
correct_beginning = article_paragraphs[0].startswith(first_paragraph_start_text)
correct_ending = article_paragraphs[-1].endswith(last_paragraph_end_text)
self.assertTrue(correct_beginning)
self.assertTrue(correct_ending)
def test_get_main_article_with_references(self):
article_paragraphs = parse_elife_xml.get_main_article(
self.soup, keep_references=True)
text_with_article_ref = 'removed by the proteasome (Finley, 2009). The barrel-shaped core peptidase'
text_found_in_paragraph = text_with_article_ref in article_paragraphs[
0]
self.assertTrue(text_found_in_paragraph)
def test_get_main_article_returns_correct_text(self):
article_paragraphs = parse_elife_xml.get_main_article(self.soup)
first_paragraph_start_text = 'The eukaryotic 26S proteasome is a large multi-enzyme'
last_paragraph_end_text = 'been deposited under accession ID: 3JCK in the PDB.'
correct_beginning = article_paragraphs[0].startswith(
first_paragraph_start_text)
correct_ending = article_paragraphs[-1].endswith(
last_paragraph_end_text)
self.assertTrue(correct_beginning)
self.assertTrue(correct_ending)
def test_get_main_article_without_references_figure_ref_removed(self):
''' Checks that figure references were correctly removed from text
'''
article_paragraphs = parse_elife_xml.get_main_article(
self.soup, keep_references=False)
text_with_figure_ref = 'determined by cryo-electron microscopy (cryoEM), revealing the molecular'
text_found_in_paragraph = text_with_figure_ref in article_paragraphs[3]
self.assertTrue(text_found_in_paragraph)
def test_get_main_article_without_references_figure_ref_removed(self):
''' Checks that figure references were correctly removed from text
'''
article_paragraphs = parse_elife_xml.get_main_article(self.soup,
keep_references=False)
text_with_figure_ref = 'determined by cryo-electron microscopy (cryoEM), revealing the molecular'
text_found_in_paragraph = text_with_figure_ref in article_paragraphs[3]
self.assertTrue(text_found_in_paragraph)
def test_get_main_article_without_references_article_ref_removed(self):
''' Checks that article references were correctly removed from text
'''
article_paragraphs = parse_elife_xml.get_main_article(self.soup,
keep_references=False)
text_with_article_ref = 'removed by the proteasome. The barrel-shaped core peptidase'
text_found_in_paragraph = text_with_article_ref in article_paragraphs[0]
self.assertTrue(text_found_in_paragraph)
def test_get_main_article_without_references_article_ref_removed(self):
''' Checks that article references were correctly removed from text
'''
article_paragraphs = parse_elife_xml.get_main_article(
self.soup, keep_references=False)
text_with_article_ref = 'removed by the proteasome. The barrel-shaped core peptidase'
text_found_in_paragraph = text_with_article_ref in article_paragraphs[
0]
self.assertTrue(text_found_in_paragraph)
def test_get_correct_number_of_main_article_paragraphs(self):
article_paragraphs = parse_elife_xml.get_main_article(self.soup,
keep_references=True)
self.assertEqual(len(article_paragraphs), 59)
def test_get_correct_number_of_main_article_paragraphs(self):
article_paragraphs = parse_elife_xml.get_main_article(
self.soup, keep_references=True)
self.assertEqual(len(article_paragraphs), 59)