Thanks to visit codestin.com
Credit goes to github.com

Skip to content

[3.9] bpo-43260: io: Prevent large data remains in textio buffer. (GH-24592) #24617

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Feb 22, 2021
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
27 changes: 27 additions & 0 deletions Lib/test/test_io.py
Original file line number Diff line number Diff line change
Expand Up @@ -3747,6 +3747,33 @@ def test_del__CHUNK_SIZE_SystemError(self):
with self.assertRaises(AttributeError):
del t._CHUNK_SIZE

def test_internal_buffer_size(self):
# bpo-43260: TextIOWrapper's internal buffer should not store
# data larger than chunk size.
chunk_size = 8192 # default chunk size, updated later

class MockIO(self.MockRawIO):
def write(self, data):
if len(data) > chunk_size:
raise RuntimeError
return super().write(data)

buf = MockIO()
t = self.TextIOWrapper(buf, encoding="ascii")
chunk_size = t._CHUNK_SIZE
t.write("abc")
t.write("def")
# default chunk size is 8192 bytes so t don't write data to buf.
self.assertEqual([], buf._write_stack)

with self.assertRaises(RuntimeError):
t.write("x"*(chunk_size+1))

self.assertEqual([b"abcdef"], buf._write_stack)
t.write("ghi")
t.write("x"*chunk_size)
self.assertEqual([b"abcdef", b"ghi", b"x"*chunk_size], buf._write_stack)


class PyTextIOWrapperTest(TextIOWrapperTest):
io = pyio
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
Fix TextIOWrapper can not flush internal buffer forever after very large
text is written.
20 changes: 17 additions & 3 deletions Modules/_io/textio.c
Original file line number Diff line number Diff line change
Expand Up @@ -1602,6 +1602,8 @@ _textiowrapper_writeflush(textio *self)
ret = PyObject_CallMethodOneArg(self->buffer, _PyIO_str_write, b);
} while (ret == NULL && _PyIO_trap_eintr());
Py_DECREF(b);
// NOTE: We cleared buffer but we don't know how many bytes are actually written
// when an error occurred.
if (ret == NULL)
return -1;
Py_DECREF(ret);
Expand Down Expand Up @@ -1659,7 +1661,10 @@ _io_TextIOWrapper_write_impl(textio *self, PyObject *text)

/* XXX What if we were just reading? */
if (self->encodefunc != NULL) {
if (PyUnicode_IS_ASCII(text) && is_asciicompat_encoding(self->encodefunc)) {
if (PyUnicode_IS_ASCII(text) &&
// See bpo-43260
PyUnicode_GET_LENGTH(text) <= self->chunk_size &&
is_asciicompat_encoding(self->encodefunc)) {
b = text;
Py_INCREF(b);
}
Expand All @@ -1668,8 +1673,9 @@ _io_TextIOWrapper_write_impl(textio *self, PyObject *text)
}
self->encoding_start_of_stream = 0;
}
else
else {
b = PyObject_CallMethodOneArg(self->encoder, _PyIO_str_encode, text);
}

Py_DECREF(text);
if (b == NULL)
Expand All @@ -1694,6 +1700,14 @@ _io_TextIOWrapper_write_impl(textio *self, PyObject *text)
self->pending_bytes_count = 0;
self->pending_bytes = b;
}
else if (self->pending_bytes_count + bytes_len > self->chunk_size) {
// Prevent to concatenate more than chunk_size data.
if (_textiowrapper_writeflush(self) < 0) {
Py_DECREF(b);
return NULL;
}
self->pending_bytes = b;
}
else if (!PyList_CheckExact(self->pending_bytes)) {
PyObject *list = PyList_New(2);
if (list == NULL) {
Expand All @@ -1713,7 +1727,7 @@ _io_TextIOWrapper_write_impl(textio *self, PyObject *text)
}

self->pending_bytes_count += bytes_len;
if (self->pending_bytes_count > self->chunk_size || needflush ||
if (self->pending_bytes_count >= self->chunk_size || needflush ||
text_needflush) {
if (_textiowrapper_writeflush(self) < 0)
return NULL;
Expand Down