Issue #23215: Multibyte codecs with custom error handlers that ignores errors
consumed too much memory and raised SystemError or MemoryError.
Original patch by Aleksi Torhamo.
diff --git a/Lib/test/test_multibytecodec.py b/Lib/test/test_multibytecodec.py
index ce267dd..2929f98 100644
--- a/Lib/test/test_multibytecodec.py
+++ b/Lib/test/test_multibytecodec.py
@@ -44,6 +44,13 @@
self.assertRaises(IndexError, dec,
b'apple\x92ham\x93spam', 'test.cjktest')
+ def test_errorcallback_custom_ignore(self):
+ # Issue #23215: MemoryError with custom error handlers and multibyte codecs
+ data = 100 * "\udc00"
+ codecs.register_error("test.ignore", codecs.ignore_errors)
+ for enc in ALL_CJKENCODINGS:
+ self.assertEqual(data.encode(enc, "test.ignore"), b'')
+
def test_codingspec(self):
try:
for enc in ALL_CJKENCODINGS:
diff --git a/Misc/NEWS b/Misc/NEWS
index bcabefa..f1426d2 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -13,6 +13,10 @@
Library
-------
+- Issue #23215: Multibyte codecs with custom error handlers that ignores errors
+ consumed too much memory and raised SystemError or MemoryError.
+ Original patch by Aleksi Torhamo.
+
- Issue #5700: io.FileIO() called flush() after closing the file.
flush() was not called in close() if closefd=False.
diff --git a/Modules/cjkcodecs/multibytecodec.c b/Modules/cjkcodecs/multibytecodec.c
index 087ae9b..435529f 100644
--- a/Modules/cjkcodecs/multibytecodec.c
+++ b/Modules/cjkcodecs/multibytecodec.c
@@ -182,8 +182,10 @@
orgsize = PyBytes_GET_SIZE(buf->outobj);
incsize = (esize < (orgsize >> 1) ? (orgsize >> 1) | 1 : esize);
- if (orgsize > PY_SSIZE_T_MAX - incsize)
+ if (orgsize > PY_SSIZE_T_MAX - incsize) {
+ PyErr_NoMemory();
return -1;
+ }
if (_PyBytes_Resize(&buf->outobj, orgsize + incsize) == -1)
return -1;
@@ -194,11 +196,11 @@
return 0;
}
-#define REQUIRE_ENCODEBUFFER(buf, s) { \
- if ((s) < 1 || (buf)->outbuf + (s) > (buf)->outbuf_end) \
+#define REQUIRE_ENCODEBUFFER(buf, s) do { \
+ if ((s) < 0 || (s) > (buf)->outbuf_end - (buf)->outbuf) \
if (expand_encodebuffer(buf, s) == -1) \
goto errorexit; \
-}
+} while(0)
/**
@@ -332,10 +334,11 @@
assert(PyBytes_Check(retstr));
retstrsize = PyBytes_GET_SIZE(retstr);
- REQUIRE_ENCODEBUFFER(buf, retstrsize);
-
- memcpy(buf->outbuf, PyBytes_AS_STRING(retstr), retstrsize);
- buf->outbuf += retstrsize;
+ if (retstrsize > 0) {
+ REQUIRE_ENCODEBUFFER(buf, retstrsize);
+ memcpy(buf->outbuf, PyBytes_AS_STRING(retstr), retstrsize);
+ buf->outbuf += retstrsize;
+ }
newpos = PyLong_AsSsize_t(PyTuple_GET_ITEM(retobj, 1));
if (newpos < 0 && !PyErr_Occurred())