xmlwriter: move collect_attributes() back to a Python implementation

This reverts f345916405d94829696985 and related. The commit states that
both versions are about the same in performance, but the C version is more code and
harder to maintain. It also states that the behaviour re invalid control
characters is better with the C version which produces entities. But those
make any Python xml parser fail, which given that most of our tooling is Python,
doesn't seem better to me, see #135.

1 files changed, 11 insertions, 2 deletions

diff --git a/tests/scanner/test_xmlwriter.py b/tests/scanner/test_xmlwriter.py
index e24923bd..c6748c00 100644
--- a/tests/scanner/test_xmlwriter.py
+++ b/tests/scanner/test_xmlwriter.py
@@ -40,10 +40,16 @@ class TestXMLWriter(unittest.TestCase):
         self.assertEqual(res, '<tag attr="utf8"/>')
 
         res = build_xml_tag('tag', [('attr', 'foo\nbar')])
-        self.assertEqual(res, '<tag attr="foo\nbar"/>')
+        self.assertEqual(res, '<tag attr="foo&#10;bar"/>')
+
+        res = build_xml_tag('tag', [('attr', 'foo\tbar')])
+        self.assertEqual(res, '<tag attr="foo&#9;bar"/>')
 
         res = build_xml_tag('tag', [('attr', '\004')])
-        self.assertEqual(res, '<tag attr="&#x4;"/>')
+        self.assertEqual(res, '<tag attr="\x04"/>')
+
+        res = build_xml_tag('tag', [('attr', 'limba1\t\034')])
+        self.assertEqual(res, '<tag attr="limba1&#9;\034"/>')
 
         res = build_xml_tag('tag', [('attr', '')])
         self.assertEqual(res, '<tag attr=""/>')
@@ -57,6 +63,9 @@ class TestXMLWriter(unittest.TestCase):
         res = build_xml_tag('tag', [('a', 'b'), ('c', 'd')])
         self.assertEqual(res, '<tag a="b" c="d"/>')
 
+        res = build_xml_tag('tag', [('foo', None), ('bar', 'quux')])
+        self.assertEqual(res, '<tag bar="quux"/>')
+
     def test_build_xml_tag_data(self):
         res = build_xml_tag('tag', [], b'foo')
         self.assertEqual(res, '<tag>foo</tag>')