Ticket #10931: 10931-utils_text-r10651.patch

django/utils/text.py

@@ -61 +61 @@
         return u''
     html4_singlets = ('br', 'col', 'link', 'base', 'img', 'param', 'area', 'hr', 'input')
     # Set up regular expressions
-    re_words = re.compile(r'&.*?;|<.*?>|(\w[\w-]*)', re.U)
-    re_tag = re.compile(r'<(/)?([^ ]+?)(?: (/)| .*?)?>')
+    re_words = re.compile(r'&.*?;|<.*?>|(\w[\w-]*)', re.U|re.S)
+    re_tag = re.compile(r'<(/)?([^ ]+?)(?: (/)| .*?)?>', re.S)
     # Count non-HTML words and keep note of open tags
     pos = 0
     ellipsis_pos = 0

tests/regressiontests/utils/tests.py

@@ -9 +9 @@
 import timesince
 import datastructures
 import itercompat
+import text
 from decorators import DecoratorFromMiddlewareTests
 
 # We need this because "datastructures" uses sorted() and the tests are run in
@@ -23 +24 @@
     'timesince': timesince,
     'datastructures': datastructures,
     'itercompat': itercompat,
+    'text': text,
 }
 
 class TestUtilsHtml(TestCase):

tests/regressiontests/utils/text.py

@@ +1 @@
+"""
+>>> from django.utils.text import truncate_html_words
+
+>>> a = "It is a long established fact that a reader will be distracted by the readable content of a page when looking at its layout."
+>>> truncate_html_words(a, 8)
+u'It is a long established fact that a ...'
+
+>>> a = "It is a long \\nestablished fact that a reader will be distracted by the readable content of  a page when looking at its layout."
+>>> truncate_html_words(a, 8)
+u'It is a long \\nestablished fact that a ...'
+
+>>> a = 'It is a <a href="xyz.html"\\nid="xyz">long established fact that a reader will be distracted by the readable content</a> of a page when looking at its layout.'
+>>> truncate_html_words(a, 8)
+u'It is a <a href="xyz.html"\\nid="xyz">long established fact that a ...</a>'
+
+>>> a = 'Fact: Python > Ruby. It is a long established fact that a reader will be distracted by the readable content of a page when looking at its layout.'
+>>> truncate_html_words(a, 8)
+u'Fact: Python > Ruby. It is a long established ...'
+
+>>> a = 'Fact: Ruby < <strong>Python</strong>.<br /> <a href="xyz.html" id="xyz">It <em>is</em> a long established fact that a reader will be distracted</a> bythe readable content of a page when looking at its layout.'
+>>> truncate_html_words(a, 8)
+u'Fact: Ruby < <strong>Python</strong>.<br /> <a href="xyz.html" id="xyz">It <em>is</em> a long established ...</a>'
+
+>>> a = 'Fact: Ruby < <strong>Python</strong>.<br /> <a href="xyz.html"\\nid="xyz">It <em>is</em> a long established fact that a reader will be distracted</a> by the readable content of a page when looking at its layout.'
+>>> truncate_html_words(a, 8)
+u'Fact: Ruby < <strong>Python</strong>.<br /> <a href="xyz.html"\\nid="xyz">It <em>is</em> a long established ...</a>'
+
+>>> a = 'Fact: Ruby < <strong>Python</strong>.<br /> <a href="xyz.html"\\nid="xyz">It > <em>is</em> a long established fact that a reader will be distracted</a> by the readable content of a page when looking at its layout.'
+>>> truncate_html_words(a, 8)
+u'Fact: Ruby < <strong>Python</strong>.<br /> <a href="xyz.html"\\nid="xyz">It > <em>is</em> a long established ...</a>'
+
+# Oops. Not smart enough after all. But proper behavior according to code.
+>>> a = 'It is a <long established fact> that a reader will be distracted by the readable content of a page when looking at its layout.'
+>>> truncate_html_words(a, 8)
+u'It is a <long established fact> that a reader will be ...</long>'
+"""
+
+if __name__ == "__main__":
+    import doctest
+    doctest.testmod()