github/pelican
1
0
Fork 1
mirror of https://github.com/getpelican/pelican.git synced 2025-10-15 20:28:56 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Rewrite pelican.utils.truncate_html_words() to use an HTML parser instead of regular expressions.

Browse source
This commit is contained in:
Andrea Corbellini 2015-07-30 21:04:28 +02:00
commit 379f8666c1
2 changed files with 84 additions and 49 deletions
Download patch file Download diff file Expand all files Collapse all files

26
pelican/tests/test_utils.py
View file

@ -144,6 +144,32 @@ class TestUtils(LoggedTestCase):
for value, expected in samples:
self.assertEqual(utils.get_relative_path(value), expected)
def test_truncate_html_words(self):
self.assertEqual(
utils.truncate_html_words('short string', 20),
'short string')
self.assertEqual(
utils.truncate_html_words('word ' * 100, 20),
'word ' * 20 + '...')
self.assertEqual(
utils.truncate_html_words('<p>' + 'word ' * 100 + '</p>', 20),
'<p>' + 'word ' * 20 + '...</p>')
self.assertEqual(
utils.truncate_html_words(
'<span\nstyle="\n...\n">' + 'word ' * 100 + '</span>', 20),
'<span\nstyle="\n...\n">' + 'word ' * 20 + '...</span>')
self.assertEqual(
utils.truncate_html_words('<br>' + 'word ' * 100, 20),
'<br>' + 'word ' * 20 + '...')
self.assertEqual(
utils.truncate_html_words('<!-- comment -->' + 'word ' * 100, 20),
'<!-- comment -->' + 'word ' * 20 + '...')
def test_process_translations(self):
# create a bunch of articles
# 1: no translation metadata