https://github.com/python/cpython/commit/cde976d85c6632a908dde1ff8695ac5cafd879b6 commit: cde976d85c6632a908dde1ff8695ac5cafd879b6 branch: 3.12 author: Miss Islington (bot) <[email protected]> committer: kumaraditya303 <[email protected]> date: 2024-06-19T10:23:29Z summary:
[3.12] gh-119506: fix `_io.TextIOWrapper.write()` write during flush (GH-119507) (#119965) gh-119506: fix `_io.TextIOWrapper.write()` write during flush (GH-119507) (cherry picked from commit 52586f930f62bd80374f0f240a4ecce0c0238174) Co-authored-by: Radislav Chugunov <[email protected]> Co-authored-by: Inada Naoki <[email protected]> files: A Misc/NEWS.d/next/Library/2024-05-24-14-32-24.gh-issue-119506.-nMNqq.rst M Lib/test/test_io.py M Modules/_io/textio.c diff --git a/Lib/test/test_io.py b/Lib/test/test_io.py index daa40a6ba365b9..8b68653779e733 100644 --- a/Lib/test/test_io.py +++ b/Lib/test/test_io.py @@ -4066,6 +4066,28 @@ def write(self, data): t.write("x"*chunk_size) self.assertEqual([b"abcdef", b"ghi", b"x"*chunk_size], buf._write_stack) + def test_issue119506(self): + chunk_size = 8192 + + class MockIO(self.MockRawIO): + written = False + def write(self, data): + if not self.written: + self.written = True + t.write("middle") + return super().write(data) + + buf = MockIO() + t = self.TextIOWrapper(buf) + t.write("abc") + t.write("def") + # writing data which size >= chunk_size cause flushing buffer before write. + t.write("g" * chunk_size) + t.flush() + + self.assertEqual([b"abcdef", b"middle", b"g"*chunk_size], + buf._write_stack) + class PyTextIOWrapperTest(TextIOWrapperTest): io = pyio diff --git a/Misc/NEWS.d/next/Library/2024-05-24-14-32-24.gh-issue-119506.-nMNqq.rst b/Misc/NEWS.d/next/Library/2024-05-24-14-32-24.gh-issue-119506.-nMNqq.rst new file mode 100644 index 00000000000000..f9b764ae0c49b3 --- /dev/null +++ b/Misc/NEWS.d/next/Library/2024-05-24-14-32-24.gh-issue-119506.-nMNqq.rst @@ -0,0 +1 @@ +Fix :meth:`!io.TextIOWrapper.write` method breaks internal buffer when the method is called again during flushing internal buffer. diff --git a/Modules/_io/textio.c b/Modules/_io/textio.c index 14dd19d95c2498..4a1ba22d381a53 100644 --- a/Modules/_io/textio.c +++ b/Modules/_io/textio.c @@ -1723,16 +1723,26 @@ _io_TextIOWrapper_write_impl(textio *self, PyObject *text) bytes_len = PyBytes_GET_SIZE(b); } - if (self->pending_bytes == NULL) { - 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; + // We should avoid concatinating huge data. + // Flush the buffer before adding b to the buffer if b is not small. + // https://github.com/python/cpython/issues/87426 + if (bytes_len >= self->chunk_size) { + // _textiowrapper_writeflush() calls buffer.write(). + // self->pending_bytes can be appended during buffer->write() + // or other thread. + // We need to loop until buffer becomes empty. + // https://github.com/python/cpython/issues/118138 + // https://github.com/python/cpython/issues/119506 + while (self->pending_bytes != NULL) { + if (_textiowrapper_writeflush(self) < 0) { + Py_DECREF(b); + return NULL; + } } + } + + if (self->pending_bytes == NULL) { + assert(self->pending_bytes_count == 0); self->pending_bytes = b; } else if (!PyList_CheckExact(self->pending_bytes)) { @@ -1741,6 +1751,9 @@ _io_TextIOWrapper_write_impl(textio *self, PyObject *text) Py_DECREF(b); return NULL; } + // Since Python 3.12, allocating GC object won't trigger GC and release + // GIL. See https://github.com/python/cpython/issues/97922 + assert(!PyList_CheckExact(self->pending_bytes)); PyList_SET_ITEM(list, 0, self->pending_bytes); PyList_SET_ITEM(list, 1, b); self->pending_bytes = list; _______________________________________________ Python-checkins mailing list -- [email protected] To unsubscribe send an email to [email protected] https://mail.python.org/mailman3/lists/python-checkins.python.org/ Member address: [email protected]
