From eaf399e3355e6d62b1bb5810b66ad4ff431ece57 Mon Sep 17 00:00:00 2001 From: Victor Stinner Date: Thu, 30 Jun 2011 18:10:14 +0200 Subject: Issue #12451: The XInclude default loader of xml.etree now decodes files from UTF-8 instead of the locale encoding if the encoding is not specified. It now also opens XML files for the parser in binary mode instead of the text mode to avoid encoding issues. --- Lib/xml/etree/ElementInclude.py | 9 +++++---- Misc/NEWS | 5 +++++ 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/Lib/xml/etree/ElementInclude.py b/Lib/xml/etree/ElementInclude.py index 84fd754..6cc1b44 100644 --- a/Lib/xml/etree/ElementInclude.py +++ b/Lib/xml/etree/ElementInclude.py @@ -67,7 +67,7 @@ class FatalIncludeError(SyntaxError): # # @param href Resource reference. # @param parse Parse mode. Either "xml" or "text". -# @param encoding Optional text encoding. +# @param encoding Optional text encoding (UTF-8 by default for "text"). # @return The expanded resource. If the parse mode is "xml", this # is an ElementTree instance. If the parse mode is "text", this # is a Unicode string. If the loader fails, it can return None @@ -75,13 +75,14 @@ class FatalIncludeError(SyntaxError): # @throws IOError If the loader fails to load the resource. def default_loader(href, parse, encoding=None): - file = open(href) if parse == "xml": + file = open(href, 'rb') data = ElementTree.parse(file).getroot() else: + if not encoding: + encoding = 'UTF-8' + file = open(href, 'r', encoding=encoding) data = file.read() - if encoding: - data = data.decode(encoding) file.close() return data diff --git a/Misc/NEWS b/Misc/NEWS index e6c1293..5fa463a 100644 --- a/Misc/NEWS +++ b/Misc/NEWS @@ -25,6 +25,11 @@ Core and Builtins Library ------- +- Issue #12451: The XInclude default loader of xml.etree now decodes files from + UTF-8 instead of the locale encoding if the encoding is not specified. It now + also opens XML files for the parser in binary mode instead of the text mode + to avoid encoding issues. + - Issue #12451: doctest.debug_script() doesn't create a temporary file anymore to avoid encoding issues. -- cgit v0.12