[Python-checkins] cpython (merge 3.4 -> 3.5): Issue #25047: Merge Element Tree encoding from 3.4 into 3.5
martin.panter
python-checkins at python.org
Wed Sep 23 04:08:28 CEST 2015
https://hg.python.org/cpython/rev/9c248233754c
changeset: 98202:9c248233754c
branch: 3.5
parent: 98199:4d0d987bf6a8
parent: 98201:ff7aba08ada6
user: Martin Panter <vadmium+py at gmail.com>
date: Wed Sep 23 01:43:08 2015 +0000
summary:
Issue #25047: Merge Element Tree encoding from 3.4 into 3.5
files:
Lib/test/test_xml_etree.py | 21 ++++++++++++++-------
Lib/xml/etree/ElementTree.py | 9 ++++-----
Misc/NEWS | 4 ++++
3 files changed, 22 insertions(+), 12 deletions(-)
diff --git a/Lib/test/test_xml_etree.py b/Lib/test/test_xml_etree.py
--- a/Lib/test/test_xml_etree.py
+++ b/Lib/test/test_xml_etree.py
@@ -2396,14 +2396,21 @@
elem = ET.Element("tag")
elem.text = "abc"
self.assertEqual(serialize(elem), '<tag>abc</tag>')
- self.assertEqual(serialize(elem, encoding="utf-8"),
- b'<tag>abc</tag>')
- self.assertEqual(serialize(elem, encoding="us-ascii"),
- b'<tag>abc</tag>')
+ for enc in ("utf-8", "us-ascii"):
+ with self.subTest(enc):
+ self.assertEqual(serialize(elem, encoding=enc),
+ b'<tag>abc</tag>')
+ self.assertEqual(serialize(elem, encoding=enc.upper()),
+ b'<tag>abc</tag>')
for enc in ("iso-8859-1", "utf-16", "utf-32"):
- self.assertEqual(serialize(elem, encoding=enc),
- ("<?xml version='1.0' encoding='%s'?>\n"
- "<tag>abc</tag>" % enc).encode(enc))
+ with self.subTest(enc):
+ self.assertEqual(serialize(elem, encoding=enc),
+ ("<?xml version='1.0' encoding='%s'?>\n"
+ "<tag>abc</tag>" % enc).encode(enc))
+ upper = enc.upper()
+ self.assertEqual(serialize(elem, encoding=upper),
+ ("<?xml version='1.0' encoding='%s'?>\n"
+ "<tag>abc</tag>" % upper).encode(enc))
elem = ET.Element("tag")
elem.text = "<&\"\'>"
diff --git a/Lib/xml/etree/ElementTree.py b/Lib/xml/etree/ElementTree.py
--- a/Lib/xml/etree/ElementTree.py
+++ b/Lib/xml/etree/ElementTree.py
@@ -752,14 +752,13 @@
encoding = "utf-8"
else:
encoding = "us-ascii"
- else:
- encoding = encoding.lower()
- with _get_writer(file_or_filename, encoding) as write:
+ enc_lower = encoding.lower()
+ with _get_writer(file_or_filename, enc_lower) as write:
if method == "xml" and (xml_declaration or
(xml_declaration is None and
- encoding not in ("utf-8", "us-ascii", "unicode"))):
+ enc_lower not in ("utf-8", "us-ascii", "unicode"))):
declared_encoding = encoding
- if encoding == "unicode":
+ if enc_lower == "unicode":
# Retrieve the default encoding for the xml declaration
import locale
declared_encoding = locale.getpreferredencoding()
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -18,6 +18,10 @@
Library
-------
+- Issue #25047: The XML encoding declaration written by Element Tree now
+ respects the letter case given by the user. This restores the ability to
+ write encoding names in uppercase like "UTF-8", which worked in Python 2.
+
- Issue #19143: platform module now reads Windows version from kernel32.dll to
avoid compatibility shims.
--
Repository URL: https://hg.python.org/cpython
More information about the Python-checkins
mailing list