Backport of r77429. Not merged/blocked as svnmerge.py is not liking me right now.
diff --git a/Lib/test/test_pyexpat.py b/Lib/test/test_pyexpat.py
index 4947c8b..72795be 100644
--- a/Lib/test/test_pyexpat.py
+++ b/Lib/test/test_pyexpat.py
@@ -510,6 +510,24 @@
parser.Parse(xml2, 1)
self.assertEquals(self.n, 4)
+class MalformedInputText(unittest.TestCase):
+ def test1(self):
+ xml = "\0\r\n"
+ parser = expat.ParserCreate()
+ try:
+ parser.Parse(xml, True)
+ self.fail()
+ except expat.ExpatError as e:
+ self.assertEquals(str(e), 'no element found: line 2, column 1')
+
+ def test2(self):
+ xml = "<?xml version\xc2\x85='1.0'?>\r\n"
+ parser = expat.ParserCreate()
+ try:
+ parser.Parse(xml, True)
+ self.fail()
+ except expat.ExpatError as e:
+ self.assertEquals(str(e), 'XML declaration not well-formed: line 1, column 14')
def test_main():
run_unittest(SetAttributeTest,
@@ -520,7 +538,8 @@
HandlerExceptionTest,
PositionTest,
sf1296433Test,
- ChardataBufferTest)
+ ChardataBufferTest,
+ MalformedInputText)
if __name__ == "__main__":
test_main()
diff --git a/Misc/ACKS b/Misc/ACKS
index a580f22..e4086bd 100644
--- a/Misc/ACKS
+++ b/Misc/ACKS
@@ -184,6 +184,7 @@
Dima Dorfman
Cesar Douady
Dean Draayer
+Fred L. Drake, Jr.
John DuBois
Paul Dubois
Graham Dumpleton
@@ -372,7 +373,6 @@
Lucas de Jonge
John Jorgensen
Jens B. Jorgensen
-Fred L. Drake, Jr.
Andreas Jung
Tattoo Mabonzo K.
Bob Kahn
@@ -409,6 +409,7 @@
Michael Kremer
Fabian Kreutz
Hannu Krosing
+Ivan Krstić
Andrew Kuchling
Vladimir Kushnir
Cameron Laird
diff --git a/Misc/NEWS b/Misc/NEWS
index e115695..86ffa55 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -122,6 +122,8 @@
Extension Modules
-----------------
+- Fix a segfault that could be triggered by expat with specially formed input.
+
- Issue #6561: '\d' in a regex now matches only characters with
Unicode category 'Nd' (Number, Decimal Digit). Previously it also
matched characters with category 'No'.
diff --git a/Modules/expat/xmltok_impl.c b/Modules/expat/xmltok_impl.c
index 0ee57ab..f793a6b 100644
--- a/Modules/expat/xmltok_impl.c
+++ b/Modules/expat/xmltok_impl.c
@@ -1741,7 +1741,7 @@
const char *end,
POSITION *pos)
{
- while (ptr != end) {
+ while (ptr < end) {
switch (BYTE_TYPE(enc, ptr)) {
#define LEAD_CASE(n) \
case BT_LEAD ## n: \