def test_external_link_with_background_img(self):
s = ('<a href="https://somewhere/foo"><span>'
'<div style="background-image: url(\'some.png\')"></div>'
'</span></a>')
output = parse_links(s)
self.assertIn('external-site', output)
self.assertNotIn('cf-icon-svg', output)
def test_rich_text_links_get_expanded(self):
page = CFGOVPage(title='foo bar', slug='foo-bar')
publish_page(page)
link = f'<body><a id="{page.id}" linktype="page">foo bar</a></body>'
output = parse_links(link)
self.assertEqual('<body><a href="/foo-bar/">foo bar</a></body>',
output)
def test_with_svg_not_at_the_end_still_gets_svg(self):
s = ('<a href="https://external.gov">'
'<span><svg>something</svg> Text after icon</span>'
'</a>')
output = parse_links(s)
soup = BeautifulSoup(output, 'html.parser')
self.assertEqual(len(soup.find_all('svg')), 2)
def test_files_get_download_icon(self):
file_types = ['pdf', 'doc', 'docx', 'xls', 'xlsx', 'csv', 'zip']
for file_type in file_types:
link = '<a href="/something.{}">link</a>'.format(
file_type
).encode('utf-8')
output = parse_links(link)
self.assertIn(b'cf-icon-svg', output)
def test_external_link_outside_body_with_attributes(self):
s = '''
<a href="https://somewhere/foo">Link</a>
<body class="test">
</body>
'''
output = parse_links(s)
self.assertNotIn('external-site', output)
self.assertNotIn('cf-icon-svg', output)
def test_external_link_with_attribute(self):
s = '''
<body>
<a href="https://somewhere" data-thing="something">Link</a>
</body>
'''
output = parse_links(s)
self.assertIn('external-site', output)
self.assertIn('cf-icon-svg', output)
def test_multiline_external_gov_link(self):
s = '''<a class="m-list_link a-link"
href="https://usa.gov/">
<span>
USA
.gov</span>
</a>
'''
output = parse_links(s)
self.assertIn('cf-icon-svg', output)
def test_internal_link(self):
"""Internal links get neither icon nor redirect."""
link = '''
<body>
<a href="https://www.consumerfinance.gov/foo">cfpb link</a>
</body>
'''
output = parse_links(link)
self.assertNotIn('external-site', output)
self.assertNotIn('cf-icon-svg', output)
def test_multiple_links(self):
s = '''
<body>
<a href="https://first.com">one</a>
<a href="https://second.com">two</a>
</body>
'''
output = parse_links(s)
soup = BeautifulSoup(output, 'html.parser')
self.assertEqual(len(soup.find_all('a')), 2)
def test_external_link_with_img(self):
s = '<body><a href="https://somewhere"><img src="some.png"></a></body>'
output = parse_links(s)
self.assertIn('external-site', output)
self.assertNotIn('cf-icon-svg', output)
def test_external_link_with_header(self):
s = '<body><a href="https://somewhere"><h3>Header</h3></a></body>'
output = parse_links(s)
self.assertIn('external-site', output)
self.assertNotIn('cf-icon-svg', output)
def test_different_case_pdf_link_gets_download_icon(self):
link = '<a href="/something.PDF">link</a>'
output = parse_links(link)
self.assertIn('cf-icon-svg', output)
def check_after_parse_links_has_a_single_svg(self, s):
output = parse_links(s)
soup = BeautifulSoup(output, 'html.parser')
self.assertEqual(len(soup.find_all('svg')), 1)
def test_relative_link_remains_unmodified(self):
self.assertEqual(
parse_links('<body><a href="/something">text</a></body>'),
'<body><a href="/something">text</a></body>')
def test_relative_link_remains_unmodified(self):
self.assertEqual(
parse_links('<a href="/something">text</a>'),
'<a href="/something">text</a>'
)
def test_rich_text_links_get_expanded(self):
page = CFGOVPage(title='foo bar', slug='foo-bar')
publish_page(page)
link = b'<a id="{}" linktype="page">foo bar</a>'.format(page.id)
output = parse_links(link)
self.assertEqual(b'<a href="/foo-bar/">foo bar</a>', output)
def test_different_case_pdf_link_gets_download_icon(self):
link = '<body><a href="/something.PDF">link</a></body>'
output = parse_links(link)
self.assertIn('cf-icon-svg', output)
def test_internal_link(self):
"""Internal links get neither icon nor redirect."""
link = '<a href="https://www.consumerfinance.gov/foo">cfpb link</a>'
output = parse_links(link)
self.assertNotIn('external-site', output)
self.assertNotIn('cf-icon-svg', output)
def test_non_gov_link(self):
"""Non gov links get external link icon and redirect."""
link = '<body><a href="https://google.com">external link</a></body>'
output = parse_links(link)
self.assertIn('external-site', output)
self.assertIn('cf-icon-svg', output)
def test_gov_link(self):
"""Gov links get external link icon but not redirect."""
link = '<a href="https://www.fdic.gov/bar">gov link</a>'
output = parse_links(link)
self.assertIn('cf-icon-svg', output)
def test_non_gov_link(self):
"""Non gov links get external link icon and redirect."""
link = '<a href="https://wwww.google.com">external link</a>'
output = parse_links(link)
self.assertIn('external-site', output)
self.assertIn('cf-icon-svg', output)
def test_works_properly_on_bytestrings(self):
self.assertEqual(
parse_links(b'<a href="/something">text</a>'),
'<a href="/something">text</a>'
)
def check_after_parse_links_has_this_many_svgs(self, count, s):
output = parse_links(s)
soup = BeautifulSoup(output, 'html.parser')
self.assertEqual(len(soup.find_all('svg')), count)
def test_rich_text_links_get_expanded(self):
page = CFGOVPage(title='foo bar', slug='foo-bar')
publish_page(page)
link = '<a id="{}" linktype="page">foo bar</a>'.format(page.id)
output = parse_links(link)
self.assertEqual('<a href="/foo-bar/">foo bar</a>', output)
def test_in_page_anchor_links_have_current_path_stripped(self):
s = '<body><a href="/foo/bar/#anchor">Anchor</a></body>'
output = parse_links(s, request_path='/foo/bar/')
self.assertNotIn('/foo/bar/', output)
self.assertIn('href="#anchor"', output)
def test_non_default_encoding(self):
s = '<body><a href="/something">哈哈</a></body>'
encoding = 'gb2312'
parsed = parse_links(s.encode(encoding), encoding=encoding)
self.assertEqual(parsed, s)
def test_works_properly_on_bytestrings(self):
self.assertEqual(
parse_links(b'<body><a href="/something">text</a></body>'),
'<body><a href="/something">text</a></body>')
def test_non_default_encoding(self):
s = '<a href="/something">哈哈</a>'
encoding = 'gb2312'
parsed = parse_links(s.encode(encoding), encoding=encoding)
self.assertEqual(parsed, s)
def test_gov_link(self):
"""Gov links get external link icon but not redirect."""
link = '<body><a href="https://www.fdic.gov/bar">gov link</a></body>'
output = parse_links(link)
self.assertIn('cf-icon-svg', output)
def test_files_get_download_icon(self):
file_types = ['pdf', 'doc', 'docx', 'xls', 'xlsx', 'csv', 'zip']
for file_type in file_types:
link = f'<body><a href="/something.{file_type}">link</a></body>'
output = parse_links(link)
self.assertIn('cf-icon-svg', output)