Author: Alex Gaynor <alex.gay...@gmail.com>
Branch: stdlib-2.7.8
Changeset: r73106:4f71852efa78
Date: 2014-08-27 16:18 -0700
http://bitbucket.org/pypy/pypy/changeset/4f71852efa78/
Log: (alex, dreid): fixed a bug in the utf7 decoder where unconsumed
characters would still be returned
diff --git a/rpython/rlib/runicode.py b/rpython/rlib/runicode.py
--- a/rpython/rlib/runicode.py
+++ b/rpython/rlib/runicode.py
@@ -906,7 +906,7 @@
elif inShift:
pos = shiftOutStartPos # back off output
- return result.build(), pos
+ return result.build()[:pos], pos
def unicode_encode_utf_7(s, size, errors, errorhandler=None):
if size == 0:
diff --git a/rpython/rlib/test/test_runicode.py
b/rpython/rlib/test/test_runicode.py
--- a/rpython/rlib/test/test_runicode.py
+++ b/rpython/rlib/test/test_runicode.py
@@ -231,6 +231,8 @@
assert decode(s, 4, None) == (u'a+-', 4)
assert decode(s, 5, None) == (u'a+-b', 5)
+ assert decode((27 * u"\u3042" + "\n").encode('utf7')[:28], 28, None)
== (u'', 0)
+
def test_utf7_surrogates(self):
encode = self.getencoder('utf-7')
u = u'\U000abcde'
_______________________________________________
pypy-commit mailing list
pypy-commit@python.org
https://mail.python.org/mailman/listinfo/pypy-commit
