From 6cff86ce6de27fbd4f9fc07716fb1205b14ffae4 Mon Sep 17 00:00:00 2001 From: Per Andersson Date: Thu, 30 Jan 2014 01:25:11 +0100 Subject: Imported Upstream version 1.4 --- bleach/tests/test_links.py | 241 +++++++++++++++++++++++++++++---------------- 1 file changed, 155 insertions(+), 86 deletions(-) (limited to 'bleach/tests/test_links.py') diff --git a/bleach/tests/test_links.py b/bleach/tests/test_links.py index ac593c4..abf889d 100644 --- a/bleach/tests/test_links.py +++ b/bleach/tests/test_links.py @@ -1,18 +1,20 @@ -import urllib +try: + from urllib.parse import quote_plus +except ImportError: + from urllib import quote_plus from html5lib.tokenizer import HTMLTokenizer from nose.tools import eq_ from bleach import linkify, url_re, DEFAULT_CALLBACKS as DC - - +from bleach.tests.tools import in_ def test_url_re(): def no_match(s): match = url_re.search(s) if match: - assert not match, 'matched %s' % s[slice(*match.span())] + assert not match, 'matched {0!s}'.format(s[slice(*match.span())]) yield no_match, 'just what i am looking for...it' @@ -21,36 +23,48 @@ def test_empty(): def test_simple_link(): - eq_('a http://example.com' + in_(('a http://example.com' ' link', + 'a http://example.com' + ' link'), linkify('a http://example.com link')) - eq_('a https://example.com' + in_(('a https://example.com' ' link', + 'a https://example.com' + ' link'), linkify('a https://example.com link')) - eq_('an example.com link', - linkify('an example.com link')) + in_(('a example.com link', + 'a example.com link'), + linkify('a example.com link')) def test_trailing_slash(): - eq_('http://example.com/', - linkify('http://example.com/')) - eq_('' - 'http://example.com/foo/', - linkify('http://example.com/foo/')) - eq_('' - 'http://example.com/foo/bar/', - linkify('http://example.com/foo/bar/')) + in_(('http://examp.com/', + 'http://examp.com/'), + linkify('http://examp.com/')) + in_(('' + 'http://example.com/foo/', + '' + 'http://example.com/foo/'), + linkify('http://example.com/foo/')) + in_(('' + 'http://example.com/foo/bar/', + '' + 'http://example.com/foo/bar/'), + linkify('http://example.com/foo/bar/')) def test_mangle_link(): """We can muck with the href attribute of the link.""" def filter_url(attrs, new=False): - attrs['href'] = (u'http://bouncer/?u=%s' % - urllib.quote_plus(attrs['href'])) + quoted = quote_plus(attrs['href']) + attrs['href'] = 'http://bouncer/?u={0!s}'.format(quoted) return attrs - eq_('' - 'http://example.com', + in_(('' + 'http://example.com', + '' + 'http://example.com'), linkify('http://example.com', DC + [filter_url])) @@ -76,13 +90,19 @@ def test_email_link(): 'james@example.com.au mailto', True, 'aussie james@example.com.au mailto'), # This is kind of a pathological case. I guess we do our best here. - ('email to ' - 'james@example.com', True, - 'email to james@example.com'), + (('email to ' + 'james@example.com', + 'email to ' + 'james@example.com'), + True, + 'email to james@example.com'), ) def _check(o, p, i): - eq_(o, linkify(i, parse_email=p)) + if isinstance(o, (list, tuple)): + in_(o, linkify(i, parse_email=p)) + else: + eq_(o, linkify(i, parse_email=p)) for (o, p, i) in tests: yield _check, o, p, i @@ -151,7 +171,8 @@ def test_set_attrs(): attrs['rev'] = 'canonical' return attrs - eq_('ex.mp', + in_(('ex.mp', + 'ex.mp'), linkify('ex.mp', [set_attr])) @@ -179,15 +200,19 @@ def test_stop_email(): def test_tlds(): - eq_('example.com', + in_(('example.com', + 'example.com'), linkify('example.com')) - eq_('example.co.uk', + in_(('example.co.uk', + 'example.co.uk'), linkify('example.co.uk')) - eq_('example.edu', + in_(('example.edu', + 'example.edu'), linkify('example.edu')) eq_('example.xxx', linkify('example.xxx')) eq_(' brie', linkify(' brie')) - eq_('bit.ly/fun', + in_(('bit.ly/fun', + 'bit.ly/fun'), linkify('bit.ly/fun')) @@ -197,61 +222,81 @@ def test_escaping(): def test_nofollow_off(): eq_('example.com', - linkify(u'example.com', [])) + linkify('example.com', [])) def test_link_in_html(): - eq_('http://yy.com', + in_(('http://yy.com', + 'http://yy.com'), linkify('http://yy.com')) - eq_('http://xx.com' - '', + + in_(('http://xx.com' + '', + 'http://xx.com' + ''), linkify('http://xx.com')) def test_links_https(): - eq_('https://yy.com', + in_(('https://yy.com', + 'https://yy.com'), linkify('https://yy.com')) def test_add_rel_nofollow(): """Verify that rel="nofollow" is added to an existing link""" - eq_('http://yy.com', + in_(('http://yy.com', + 'http://yy.com'), linkify('http://yy.com')) def test_url_with_path(): - eq_('' - 'http://example.com/path/to/file', + in_(('' + 'http://example.com/path/to/file', + '' + 'http://example.com/path/to/file'), linkify('http://example.com/path/to/file')) def test_link_ftp(): - eq_('' - 'ftp://ftp.mozilla.org/some/file', + in_(('' + 'ftp://ftp.mozilla.org/some/file', + '' + 'ftp://ftp.mozilla.org/some/file'), linkify('ftp://ftp.mozilla.org/some/file')) def test_link_query(): - eq_('' + in_(('' 'http://xx.com/?test=win', + '' + 'http://xx.com/?test=win'), linkify('http://xx.com/?test=win')) - eq_('' + in_(('' 'xx.com/?test=win', + '' + 'xx.com/?test=win'), linkify('xx.com/?test=win')) - eq_('' + in_(('' 'xx.com?test=win', + '' + 'xx.com?test=win'), linkify('xx.com?test=win')) def test_link_fragment(): - eq_('' - 'http://xx.com/path#frag', + in_(('' + 'http://xx.com/path#frag', + '' + 'http://xx.com/path#frag'), linkify('http://xx.com/path#frag')) def test_link_entities(): - eq_('' + in_(('' 'http://xx.com/?a=1&b=2', + '' + 'http://xx.com/?a=1&b=2'), linkify('http://xx.com/?a=1&b=2')) @@ -262,9 +307,12 @@ def test_escaped_html(): def test_link_http_complete(): - eq_('' 'https://user:pass@ftp.mozilla.org/x/y.exe?a=b&c=d&e#f', + '' + 'https://user:pass@ftp.mozilla.org/x/y.exe?a=b&c=d&e#f'), linkify('https://user:pass@ftp.mozilla.org/x/y.exe?a=b&c=d&e#f')) @@ -282,8 +330,10 @@ def test_javascript_url(): def test_unsafe_url(): """Any unsafe char ({}[]<>, etc.) in the path should end URL scanning.""" - eq_('All your{"xx.yy.com/grover.png"}base are', + in_(('All your{"xx.yy.com/grover.png"}base are', + 'All your{"xx.yy.com/grover.png"}base are'), linkify('All your{"xx.yy.com/grover.png"}base are')) @@ -291,17 +341,23 @@ def test_skip_pre(): """Skip linkification in 
 tags."""
     simple = 'http://xx.com 
http://xx.com
'
     linked = ('http://xx.com '
+              '
http://xx.com
',
+              'http://xx.com '
               '
http://xx.com
')
     all_linked = ('http://xx.com '
                   '
http://xx.com'
+                  '
',
+                  'http://xx.com '
+                  '
http://xx.com'
                   '
')
-    eq_(linked, linkify(simple, skip_pre=True))
-    eq_(all_linked, linkify(simple))
+    in_(linked, linkify(simple, skip_pre=True))
+    in_(all_linked, linkify(simple))
 
     already_linked = '
xx
'
-    nofollowed = '
xx
'
-    eq_(nofollowed, linkify(already_linked))
-    eq_(nofollowed, linkify(already_linked, skip_pre=True))
+    nofollowed = ('
xx
',
+                  '
xx
')
+    in_(nofollowed, linkify(already_linked))
+    in_(nofollowed, linkify(already_linked, skip_pre=True))
 
 
 def test_libgl():
@@ -311,11 +367,13 @@ def test_libgl():
 
 def test_end_of_sentence():
     """example.com. should match."""
-    out = u'%s%s'
-    in_ = u'%s%s'
+    outs = ('{0!s}{1!s}',
+            '{0!s}{1!s}')
+    intxt = '{0!s}{1!s}'
 
     def check(u, p):
-        eq_(out % (u, u, p), linkify(in_ % (u, p)))
+        in_([out.format(u, p) for out in outs],
+            linkify(intxt.format(u, p)))
 
     tests = (
         ('example.com', '.'),
@@ -330,49 +388,50 @@ def test_end_of_sentence():
 
 def test_end_of_clause():
     """example.com/foo, shouldn't include the ,"""
-    eq_('ex.com/foo, bar',
+    in_(('ex.com/foo, bar',
+         'ex.com/foo, bar'),
         linkify('ex.com/foo, bar'))
 
 
 def test_sarcasm():
     """Jokes should crash."""
-    dirty = u'Yeah right '
-    clean = u'Yeah right <sarcasm/>'
+    dirty = 'Yeah right '
+    clean = 'Yeah right <sarcasm/>'
     eq_(clean, linkify(dirty))
 
 
 def test_wrapping_parentheses():
     """URLs wrapped in parantheses should not include them."""
-    out = u'%s%s%s'
+    outs = ('{0!s}{2!s}{3!s}',
+            '{0!s}{2!s}{3!s}')
 
     tests = (
-        ('(example.com)', out % ('(', 'example.com', 'example.com', ')')),
-        ('(example.com/)', out % ('(', 'example.com/', 'example.com/', ')')),
-        ('(example.com/foo)', out % ('(', 'example.com/foo',
-                                     'example.com/foo', ')')),
-        ('(((example.com/))))', out % ('(((', 'example.com/)',
-                                       'example.com/)', ')))')),
-        ('example.com/))', out % ('', 'example.com/))',
-                                  'example.com/))', '')),
+        ('(example.com)', ('(', 'example.com', 'example.com', ')')),
+        ('(example.com/)', ('(', 'example.com/', 'example.com/', ')')),
+        ('(example.com/foo)', ('(', 'example.com/foo',
+         'example.com/foo', ')')),
+        ('(((example.com/))))', ('(((', 'example.com/)',
+         'example.com/)', ')))')),
+        ('example.com/))', ('', 'example.com/))', 'example.com/))', '')),
         ('http://en.wikipedia.org/wiki/Test_(assessment)',
-            out % ('', 'en.wikipedia.org/wiki/Test_(assessment)',
-                   'http://en.wikipedia.org/wiki/Test_(assessment)', '')),
+         ('', 'en.wikipedia.org/wiki/Test_(assessment)',
+          'http://en.wikipedia.org/wiki/Test_(assessment)', '')),
         ('(http://en.wikipedia.org/wiki/Test_(assessment))',
-            out % ('(', 'en.wikipedia.org/wiki/Test_(assessment)',
-                   'http://en.wikipedia.org/wiki/Test_(assessment)', ')')),
+         ('(', 'en.wikipedia.org/wiki/Test_(assessment)',
+          'http://en.wikipedia.org/wiki/Test_(assessment)', ')')),
         ('((http://en.wikipedia.org/wiki/Test_(assessment))',
-            out % ('((', 'en.wikipedia.org/wiki/Test_(assessment',
-                   'http://en.wikipedia.org/wiki/Test_(assessment', '))')),
+         ('((', 'en.wikipedia.org/wiki/Test_(assessment',
+          'http://en.wikipedia.org/wiki/Test_(assessment', '))')),
         ('(http://en.wikipedia.org/wiki/Test_(assessment)))',
-            out % ('(', 'en.wikipedia.org/wiki/Test_(assessment))',
-                   'http://en.wikipedia.org/wiki/Test_(assessment))', ')')),
+         ('(', 'en.wikipedia.org/wiki/Test_(assessment))',
+          'http://en.wikipedia.org/wiki/Test_(assessment))', ')')),
         ('(http://en.wikipedia.org/wiki/)Test_(assessment',
-            out % ('(', 'en.wikipedia.org/wiki/)Test_(assessment',
-                   'http://en.wikipedia.org/wiki/)Test_(assessment', '')),
+         ('(', 'en.wikipedia.org/wiki/)Test_(assessment',
+          'http://en.wikipedia.org/wiki/)Test_(assessment', '')),
     )
 
     def check(test, expected_output):
-        eq_(expected_output, linkify(test))
+        in_([o.format(*expected_output) for o in outs], linkify(test))
 
     for test, expected_output in tests:
         yield check, test, expected_output
@@ -389,7 +448,9 @@ def test_ports():
     )
 
     def check(test, output):
-        eq_(u'{0}{1}'.format(*output),
+        outs = ('{0}{1}',
+                '{0}{1}')
+        in_([out.format(*output) for out in outs],
             linkify(test))
 
     for test, output in tests:
@@ -406,8 +467,9 @@ def test_tokenizer():
 def test_ignore_bad_protocols():
     eq_('foohttp://bar',
         linkify('foohttp://bar'))
-    eq_('foohttp://exampl.com',
-        linkify('foohttp://exampl.com'))
+    in_(('fohttp://exampl.com',
+         'fohttp://exampl.com'),
+        linkify('fohttp://exampl.com'))
 
 
 def test_max_recursion_depth():
@@ -419,22 +481,29 @@ def test_max_recursion_depth():
 def test_link_emails_and_urls():
     """parse_email=True shouldn't prevent URLs from getting linkified."""
     output = (''
+              'http://example.com '
+              'person@example.com',
+              ''
               'http://example.com '
               'person@example.com')
-    eq_(output, linkify('http://example.com person@example.com',
+    in_(output, linkify('http://example.com person@example.com',
                         parse_email=True))
 
 
 def test_links_case_insensitive():
     """Protocols and domain names are case insensitive."""
     expect = (''
+              'HTTP://EXAMPLE.COM',
+              ''
               'HTTP://EXAMPLE.COM')
-    eq_(expect, linkify('HTTP://EXAMPLE.COM'))
+    in_(expect, linkify('HTTP://EXAMPLE.COM'))
 
 
 def test_elements_inside_links():
-    eq_(u'hello
',
+    in_(('hello
',
+         'hello
'),
         linkify('hello
'))
 
-    eq_(u'bold hello
',
+    in_(('bold hello
',
+         'bold hello
'),
         linkify('bold hello
'))
-- 
cgit v1.2.3