Issue #25047: Respect case writing XML encoding declarations
This restores the ability to write encoding names in uppercase like "UTF-8",
which worked in Python 2.
diff --git a/Lib/test/test_xml_etree.py b/Lib/test/test_xml_etree.py
index 1c6a939..b87b098 100644
--- 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
index a8585b6..97eba8b 100644
--- a/Lib/xml/etree/ElementTree.py
+++ b/Lib/xml/etree/ElementTree.py
@@ -756,14 +756,13 @@
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
index 90d9e1f..347dd6f 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -81,6 +81,10 @@
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.