From 076366c2a52b1446eb684806f95e10c91366094a Mon Sep 17 00:00:00 2001 From: Raymond Hettinger Date: Sun, 11 Sep 2016 23:18:03 -0700 Subject: [PATCH] Issue #17582: xml.etree.ElementTree nows preserves whitespaces in attributes (Patch by Duane Griffin. Reviewed and approved by Stefan Behnel.) --- Lib/test/test_xml_etree.py | 8 ++++++++ Lib/xml/etree/ElementTree.py | 11 +++++++++++ Misc/NEWS | 3 +++ 3 files changed, 22 insertions(+) diff --git a/Lib/test/test_xml_etree.py b/Lib/test/test_xml_etree.py index bc1dd1461be..fbfc0b0250d 100644 --- a/Lib/test/test_xml_etree.py +++ b/Lib/test/test_xml_etree.py @@ -405,6 +405,14 @@ class ElementTreeTest(unittest.TestCase): self.assertEqual(ET.tostring(elem), b'aa') + elem = ET.Element('test') + elem.set('a', '\r') + elem.set('b', '\r\n') + elem.set('c', '\t\n\r ') + elem.set('d', '\n\n') + self.assertEqual(ET.tostring(elem), + b'') + def test_makeelement(self): # Test makeelement handling. diff --git a/Lib/xml/etree/ElementTree.py b/Lib/xml/etree/ElementTree.py index 6d1b0ab864c..92821c57062 100644 --- a/Lib/xml/etree/ElementTree.py +++ b/Lib/xml/etree/ElementTree.py @@ -1083,8 +1083,19 @@ def _escape_attrib(text): text = text.replace(">", ">") if "\"" in text: text = text.replace("\"", """) + # 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 + # http://www.w3.org/TR/REC-xml/#sec-line-ends + if "\r\n" in text: + text = text.replace("\r\n", "\n") + if "\r" in text: + text = text.replace("\r", "\n") + #The following four lines are issue 17582 if "\n" in text: text = text.replace("\n", " ") + if "\t" in text: + text = text.replace("\t", " ") return text except (TypeError, AttributeError): _raise_serialization_error(text) diff --git a/Misc/NEWS b/Misc/NEWS index 43f8f25ed51..1dc5ad898ca 100644 --- a/Misc/NEWS +++ b/Misc/NEWS @@ -83,6 +83,9 @@ Library - Issue #24594: Validates persist parameter when opening MSI database +- Issue #17582: xml.etree.ElementTree nows preserves whitespaces in attributes + (Patch by Duane Griffin. Reviewed and approved by Stefan Behnel.) + - Issue #28047: Fixed calculation of line length used for the base64 CTE in the new email policies.