Skip to content

fix a unicode_literals regression in ihatexml.py #51

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 3 commits into from
Closed

fix a unicode_literals regression in ihatexml.py #51

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7399617
fix a unicode_literals regression in ihatexml.py
ambv May 16, 2013
9cc84af
fixup! fix a unicode_literals regression in ihatexml.py
ambv May 16, 2013
add2c55
fixup! fix a unicode_literals regression in ihatexml.py
ambv May 16, 2013
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion html5lib/ihatexml.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -260,7 +260,7 @@ def fromXmlName(self, name):
return name

def escapeChar(self, char):
replacement = "U" + hex(ord(char))[2:].upper().rjust(5, "0")
replacement = "U%05X" % ord(char)
self.replaceCache[char] = replacement
return replacement

Expand Down
19 changes: 18 additions & 1 deletion html5lib/tests/test_parser2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,11 @@
from __future__ import absolute_import, division, unicode_literals

import io
import warnings

from . import support # flake8: noqa
from html5lib import html5parser
from html5lib.constants import namespaces
from html5lib.constants import namespaces, DataLossWarning
from html5lib import treebuilders

import unittest
Expand All @@ -16,6 +17,10 @@ class MoreParserTests(unittest.TestCase):

def setUp(self):
self.dom_tree = treebuilders.getTreeBuilder("dom")
try:
self.lxml_tree = treebuilders.getTreeBuilder("lxml")
except ImportError:
self.lxml_tree = None

def test_assertDoctypeCloneable(self):
parser = html5parser.HTMLParser(tree=self.dom_tree)
Expand All @@ -27,6 +32,18 @@ def test_line_counter(self):
parser = html5parser.HTMLParser(tree=self.dom_tree)
parser.parse("<pre>\nx\n&gt;\n</pre>")

def test_ihatexml(self):
if not self.lxml_tree:
return
parser = html5parser.HTMLParser(tree=self.lxml_tree)
with warnings.catch_warnings(record=True) as w:
warnings.simplefilter("always")

parser.parse(b'<p xml:lang="pl">Witam wszystkich')

self.assertEqual(len(w), 1)
self.assertTrue(issubclass(w[-1].category, DataLossWarning))

def test_namespace_html_elements_0_dom(self):
parser = html5parser.HTMLParser(tree=self.dom_tree, namespaceHTMLElements=True)
doc = parser.parse("<html></html>")
Expand Down