RomanNum3ral
/
scrapy
mirror of https://github.com/scrapy/scrapy.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fixed markup tests. Those functions must always work with unicode objects. 

--HG--
extra : convert_revision : svn%3Ab85faa78-f9eb-468e-a121-7cced6da292c%40544
This commit is contained in:
elpolilla 2008-12-23 23:27:53 +00:00
parent f4cecafc02
commit e2b0870957
1 changed files with 0 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
scrapy/trunk/scrapy/tests/test_utils_markup.py
View File

@ -7,10 +7,6 @@ from scrapy.utils.markup import unquote_markup
class UtilsMarkupTest(unittest.TestCase):
def test_remove_entities(self):
# make sure it always return uncode
assert isinstance(remove_entities('no entities'), unicode)
assert isinstance(remove_entities('Price: £100!'), unicode)
# regular conversions
self.assertEqual(remove_entities(u'As low as £100!'),
u'As low as \xa3100!')
@ -31,9 +27,6 @@ class UtilsMarkupTest(unittest.TestCase):
def test_replace_tags(self):
# make sure it always return uncode
assert isinstance(replace_tags('no entities'), unicode)
self.assertEqual(replace_tags(u'This text contains <a>some tag</a>'),
u'This text contains some tag')
@ -45,10 +38,6 @@ class UtilsMarkupTest(unittest.TestCase):
u'Click here')
def test_remove_comments(self):
# make sure it always return unicode
assert isinstance(remove_comments('without comments'), unicode)
assert isinstance(remove_comments('<!-- with comments -->'), unicode)
# text without comments
self.assertEqual(remove_comments(u'text without comments'), u'text without comments')
@ -57,13 +46,6 @@ class UtilsMarkupTest(unittest.TestCase):
self.assertEqual(remove_comments(u'Hello<!--World-->'),u'Hello')
def test_remove_tags(self):
# make sure it always return unicode
assert isinstance(remove_tags('no tags'), unicode)
assert isinstance(remove_tags('no tags', which_ones=('p',)), unicode)
assert isinstance(remove_tags('<p>one tag</p>'), unicode)
assert isinstance(remove_tags('<p>one tag</p>', which_ones=('p')), unicode)
assert isinstance(remove_tags('<a>link</a>', which_ones=('b',)), unicode)
# text without tags
self.assertEqual(remove_tags(u'no tags'), u'no tags')
self.assertEqual(remove_tags(u'no tags', which_ones=('p','b',)), u'no tags')
@ -81,12 +63,6 @@ class UtilsMarkupTest(unittest.TestCase):
u'<p align="center" class="one">texty</p>')
def test_remove_tags_with_content(self):
# make sure it always return unicode
assert isinstance(remove_tags_with_content('no tags'), unicode)
assert isinstance(remove_tags_with_content('no tags', which_ones=('p',)), unicode)
assert isinstance(remove_tags_with_content('<p>one tag</p>', which_ones=('p',)), unicode)
assert isinstance(remove_tags_with_content('<a>link</a>', which_ones=('b',)), unicode)
# text without tags
self.assertEqual(remove_tags_with_content(u'no tags'), u'no tags')
self.assertEqual(remove_tags_with_content(u'no tags', which_ones=('p','b',)), u'no tags')
@ -99,10 +75,6 @@ class UtilsMarkupTest(unittest.TestCase):
u'<b>not will removed</b>')
def test_remove_escape_chars(self):
# make sure it always return unicode
assert isinstance(remove_escape_chars('no ec'), unicode)
assert isinstance(remove_escape_chars('no ec', which_ones=('\n','\t',)), unicode)
# text without escape chars
self.assertEqual(remove_escape_chars(u'no ec'), u'no ec')
self.assertEqual(remove_escape_chars(u'no ec', which_ones=('\n',)), u'no ec')
@ -118,10 +90,6 @@ class UtilsMarkupTest(unittest.TestCase):
sample_txt2 = u'<node2>blah&amp;blah<![CDATA[blahblahblah!&pound;]]>moreblah&lt;&gt;</node2>'
sample_txt3 = u'something&pound;&amp;more<node3><![CDATA[things, stuff, and such]]>what&quot;ever</node3><node4'
# make sure it always return unicode
assert isinstance(unquote_markup(sample_txt1.encode('latin-1')), unicode)
assert isinstance(unquote_markup(sample_txt2), unicode)
self.assertEqual(unquote_markup(sample_txt1), u"""<node1>hi, this is sample text with entities: & \xa9
although this is inside a cdata! &amp; &quot;</node1>""")