mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-04 17:08:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 13

bpo-39011: Preserve line endings within ElementTree attributes (GH-18468)

Browse source 
* bpo-39011: Preserve line endings within attributes

Line endings within attributes were previously normalized to "\n" in Py3.7/3.8.
This patch removes that normalization, as line endings which were
replaced by entity numbers should be preserved in original form.
This commit is contained in:
mefistotelis 2020-04-12 14:51:58 +02:00 • committed by GitHub
parent 8f87eefe7f
commit 5fd8123dfd
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 22 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

5
Lib/test/test_xml_etree.py
View file

@ -430,13 +430,14 @@ class ElementTreeTest(unittest.TestCase):
self.assertEqual(ET.tostring(elem),
b'<test testa="testval" testb="test1" testc="test2">aa</test>')
# Test preserving white space chars in attributes
elem = ET.Element('test')
elem.set('a', '\r')
elem.set('b', '\r\n')
elem.set('c', '\t\n\r ')
elem.set('d', '\n\n')
elem.set('d', '\n\n\r\r\t\t ')
self.assertEqual(ET.tostring(elem),
b'<test a="&#10;" b="&#10;" c="&#09;&#10;&#10; " d="&#10;&#10;" />')
b'<test a="&#13;" b="&#13;&#10;" c="&#09;&#10;&#13; " d="&#10;&#10;&#13;&#13;&#09;&#09; " />')
def test_makeelement(self):
# Test makeelement handling.

14
Lib/xml/etree/ElementTree.py
View file

@ -1057,15 +1057,15 @@ def _escape_attrib(text):
text = text.replace(">", "&gt;")
if "\"" in text:
text = text.replace("\"", "&quot;")
# The following business with carriage returns is to satisfy
# Section 2.11 of the XML specification, stating that
# CR or CR LN should be replaced with just LN
# Although section 2.11 of the XML specification states that CR or
# CR LN should be replaced with just LN, it applies only to EOLNs
# which take part of organizing file into lines. Within attributes,
# we are replacing these with entity numbers, so they do not count.
# http://www.w3.org/TR/REC-xml/#sec-line-ends
if "\r\n" in text:
text = text.replace("\r\n", "\n")
# The current solution, contained in following six lines, was
# discussed in issue 17582 and 39011.
if "\r" in text:
text = text.replace("\r", "\n")
#The following four lines are issue 17582
text = text.replace("\r", "&#13;")
if "\n" in text:
text = text.replace("\n", "&#10;")
if "\t" in text: