def test_parse_html_entities(self):
e = '<script></script>'
p = '<p>Test %s</p>' % e
self.assertEqual(test_pr.parse_html(p), p)
a = '<p>http://google.com %s</p>' % e
self.assertEqual(
test_pr.parse_html(a),
'<p><a href="http://google.com">http://google.com</a>'
' %s</p>' % e)
h = ('<p><a href="http://foo.com">http://foo.com</a> http://bar.com '
'<span>http://baz.com <script> '
'<b>http://nug.com <i>X <foo></i></b></span></p>')
self.assertEqual(test_pr.parse_html(h), (
'<p><a href="http://foo.com">http://foo.com</a> '
'<a href="http://bar.com">http://bar.com</a> '
'<span><a href="http://baz.com">http://baz.com</a> <script> '
'<b><a href="http://nug.com">http://nug.com</a> '
'<i>X <foo></i></b></span></p>'))
h = ('<p><a href="http://foo.com">http://foo.com</a> http://bar.com '
'<script> http://baz.com </script>\n'
'http://baze.com\n<foo></p>')
self.assertEqual(
test_pr.parse_html(h),
('<p><a href="http://foo.com">http://foo.com</a> '
'<a href="http://bar.com">http://bar.com</a> <script> '
'<a href="http://baz.com">http://baz.com</a> </script>\n'
'<a href="http://baze.com">http://baze.com</a>\n'
'<foo></p>'))
def test_parse_text(self):
for url, expected in self.inline_pairs.items():
parsed = test_pr.parse_text('this is inline: %s' % url)
self.assertHTMLEqual(parsed, 'this is inline: %s' % expected)
# if the link comes on its own line it gets included in full
for url, expected in self.full_pairs.items():
parsed = test_pr.parse_text(url)
self.assertHTMLEqual(parsed, expected)
# links inside block tags will render as inline
frame = '<p>Testing %s</p>'
for url, expected in self.inline_pairs.items():
parsed = test_pr.parse_html(frame % (url))
self.assertHTMLEqual(parsed, frame % (expected))
# links inside <a> tags won't change at all
frame = '<p><a href="%s">%s</a></p>'
for url, expected in self.inline_pairs.items():
parsed = test_pr.parse_html(frame % (url, url))
self.assertHTMLEqual(parsed, frame % (url, url))
# links within tags within a tags are fine too
frame = '<p><a href="%s"><span>%s</span></a></p>'
for url, expected in self.inline_pairs.items():
parsed = test_pr.parse_html(frame % (url, url))
self.assertHTMLEqual(parsed, frame % (url, url))
def test_multiline(self):
for url, expected in self.full_pairs.items():
expected_inline = self.inline_pairs[url]
frame = 'this is inline: %s\n%s\nand yet another %s'
test_str = frame % (url, url, url)
parsed = test_pr.parse_text(test_str)
self.assertHTMLEqual(
parsed, frame % (expected_inline, expected, expected_inline))
# On multi-line text, if we specify block_handler=None, only standalone
# links will be handled.
for url, expected in self.full_pairs.items():
frame = 'this is inline: %s\n%s\nand yet another %s'
test_str = frame % (url, url, url)
parsed = test_pr.parse_text(test_str, block_handler=None)
self.assertHTMLEqual(parsed, frame % (url, expected, url))
for url, expected in self.full_pairs.items():
expected_inline = self.inline_pairs[url]
frame = '%s\nthis is inline: %s\n%s'
test_str = frame % (url, url, url)
parsed = test_pr.parse_text(test_str)
self.assertHTMLEqual(parsed,
frame % (expected, expected_inline, expected))
# test mixing multiline with p tags
for url, expected in self.full_pairs.items():
expected_inline = self.inline_pairs[url]
frame = '<p>%s</p>\n<p>this is inline: %s</p>\n<p>\n%s\n</p><p>last test\n%s\n</p>'
test_str = frame % (url, url, url, url)
parsed = test_pr.parse_html(test_str)
self.assertHTMLEqual(
parsed,
frame % (expected, expected_inline, expected, expected_inline))
for url, expected in self.full_pairs.items():
expected_inline = self.inline_pairs[url]
frame = '<p><a href="#foo">%s</a></p>\n<p>this is inline: %s</p>\n<p>last test\n%s\n</p>'
test_str = frame % (url, url, url)
parsed = test_pr.parse_html(test_str)
self.assertHTMLEqual(
parsed, frame % (url, expected_inline, expected_inline))
def test_urlize(self):
blank = 'http://fapp.io/foo/'
blank_e = '<a href="http://fapp.io/foo/">http://fapp.io/foo/</a>'
for url, expected in self.full_pairs.items():
expected_inline = self.inline_pairs[url]
frame = 'test %s\n%s\n%s\nand finally %s'
test_str = frame % (url, blank, url, blank)
parsed = test_pr.parse_text(test_str)
self.assertHTMLEqual(
parsed, frame % (expected_inline, blank_e, expected, blank_e))
parsed = test_pr.parse_text(test_str, urlize_all=False)
self.assertHTMLEqual(
parsed, frame % (expected_inline, blank, expected, blank))
parsed = test_pr.parse_text_full(test_str)
self.assertHTMLEqual(
parsed, frame % (expected, blank_e, expected, blank_e))
parsed = test_pr.parse_text_full(test_str, urlize_all=False)
self.assertHTMLEqual(parsed,
frame % (expected, blank, expected, blank))
parsed = test_pr.parse_html(test_str)
self.assertHTMLEqual(
parsed,
frame % (expected_inline, blank_e, expected_inline, blank_e))
parsed = test_pr.parse_html(test_str, urlize_all=False)
self.assertHTMLEqual(
parsed,
frame % (expected_inline, blank, expected_inline, blank))
frame = '<p>test %s</p>\n<a href="foo">%s</a>\n<a href="foo2">%s</a>\n<p>and finally %s</p>'
test_str = frame % (url, blank, url, blank)
parsed = test_pr.parse_html(test_str)
self.assertHTMLEqual(
parsed, frame % (expected_inline, blank, url, blank_e))
parsed = test_pr.parse_html(test_str, urlize_all=False)
self.assertHTMLEqual(parsed,
frame % (expected_inline, blank, url, blank))
def test_multiline(self):
for url, expected in self.full_pairs.items():
expected_inline = self.inline_pairs[url]
frame = 'this is inline: %s\n%s\nand yet another %s'
test_str = frame % (url, url, url)
parsed = test_pr.parse_text(test_str)
self.assertHTMLEqual(
parsed, frame % (expected_inline, expected, expected_inline))
for url, expected in self.full_pairs.items():
expected_inline = self.inline_pairs[url]
frame = '%s\nthis is inline: %s\n%s'
test_str = frame % (url, url, url)
parsed = test_pr.parse_text(test_str)
self.assertHTMLEqual(parsed,
frame % (expected, expected_inline, expected))
# test mixing multiline with p tags
for url, expected in self.full_pairs.items():
expected_inline = self.inline_pairs[url]
frame = '<p>%s</p>\n<p>this is inline: %s</p>\n<p>\n%s\n</p><p>last test\n%s\n</p>'
test_str = frame % (url, url, url, url)
parsed = test_pr.parse_html(test_str)
self.assertHTMLEqual(
parsed,
frame % (expected, expected_inline, expected, expected_inline))
for url, expected in self.full_pairs.items():
expected_inline = self.inline_pairs[url]
frame = '<p><a href="#foo">%s</a></p>\n<p>this is inline: %s</p>\n<p>last test\n%s\n</p>'
test_str = frame % (url, url, url)
parsed = test_pr.parse_html(test_str)
self.assertHTMLEqual(
parsed, frame % (url, expected_inline, expected_inline))
def test_parse_text_full(self):
for url, expected in self.full_pairs.items():
parsed = test_pr.parse_text_full(url)
self.assertHTMLEqual(parsed, expected)
# the parse_text_full will replace even inline content
for url, expected in self.full_pairs.items():
parsed = test_pr.parse_text_full('this is inline: %s' % url)
self.assertHTMLEqual(parsed, 'this is inline: %s' % expected)
for url, expected in self.full_pairs.items():
parsed = test_pr.parse_html('<p>%s</p>' % url)
self.assertHTMLEqual(parsed, '<p>%s</p>' % expected)
def test_parse_text(self):
for url, expected in self.inline_pairs.items():
parsed = test_pr.parse_text('this is inline: %s' % url)
self.assertHTMLEqual(parsed, 'this is inline: %s' % expected)
# We can disable parsing inline links by specifying block_handler=None.
for url, expected in self.inline_pairs.items():
parsed = test_pr.parse_text('this is inline: %s' % url,
block_handler=None)
self.assertEqual(parsed, 'this is inline: %s' % url)
# if the link comes on its own line it gets included in full
for url, expected in self.full_pairs.items():
parsed = test_pr.parse_text(url)
self.assertHTMLEqual(parsed, expected)
# Specifying block_handler=None only applies to inline links, so
# the behavior is the same for standalone links.
parsed = test_pr.parse_text(url, block_handler=None)
self.assertHTMLEqual(parsed, expected)
# links inside block tags will render as inline
frame = '<p>Testing %s</p>'
for url, expected in self.inline_pairs.items():
parsed = test_pr.parse_html(frame % (url))
self.assertHTMLEqual(parsed, frame % (expected))
# links inside <a> tags won't change at all
frame = '<p><a href="%s">%s</a></p>'
for url, expected in self.inline_pairs.items():
parsed = test_pr.parse_html(frame % (url, url))
self.assertHTMLEqual(parsed, frame % (url, url))
# links within tags within a tags are fine too
frame = '<p><a href="%s"><span>%s</span></a></p>'
for url, expected in self.inline_pairs.items():
parsed = test_pr.parse_html(frame % (url, url))
self.assertHTMLEqual(parsed, frame % (url, url))
def test_urlize_params(self):
text = 'test http://foo.com/'
urlize_params = {'target': '_blank', 'rel': 'nofollow'}
exp = ('test <a href="http://foo.com/" rel="nofollow" target="_blank">'
'http://foo.com/</a>')
result = test_pr.parse_text(text, urlize_params=urlize_params)
self.assertEqual(result, exp)
result = test_pr.parse_text_full(text, urlize_params=urlize_params)
self.assertEqual(result, exp)
result = test_pr.parse_html(text, urlize_params=urlize_params)
self.assertEqual(result, exp)
def test_html_entities(self):
frame_html = '<p>test %s</p><p><a href="foo">%s</a></p>'
for url, expected in self.data_pairs.items():
esc_url = url.replace('&', '&')
html = frame_html % (esc_url, esc_url)
all_urls, extracted = test_pr.extract_html(html)
self.assertEqual(all_urls, [url])
if 'url' not in expected:
expected['url'] = url
if 'title' not in expected:
expected['title'] = expected['url']
self.assertEqual(extracted, {url: expected})
rendered = test_pr.parse_html('<p>%s</p>' % esc_url)
self.assertHTMLEqual(rendered, '<p>%s</p>' % self.full_pairs[url])
def test_outside_of_markup(self):
frame = '%s<p>testing</p>'
for url, expected in self.full_pairs.items():
parsed = test_pr.parse_html(frame % (url))
self.assertHTMLEqual(parsed, frame % (expected))
