[3.10] bpo-45461: Fix IncrementalDecoder and StreamReader in the "unicode-escape" codec (GH-28939) (GH-28943)
They support now splitting escape sequences between input chunks.
Add the third parameter "final" in codecs.unicode_escape_decode().
It is True by default to match the former behavior.
(cherry picked from commit c96d1546b11b4c282a7e21737cb1f5d16349656d)
Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
diff --git a/Modules/_codecsmodule.c b/Modules/_codecsmodule.c
index 2e8cb97..fc74127 100644
--- a/Modules/_codecsmodule.c
+++ b/Modules/_codecsmodule.c
@@ -489,17 +489,20 @@ _codecs_utf_32_ex_decode_impl(PyObject *module, Py_buffer *data,
_codecs.unicode_escape_decode
data: Py_buffer(accept={str, buffer})
errors: str(accept={str, NoneType}) = None
+ final: bool(accept={int}) = True
/
[clinic start generated code]*/
static PyObject *
_codecs_unicode_escape_decode_impl(PyObject *module, Py_buffer *data,
- const char *errors)
-/*[clinic end generated code: output=3ca3c917176b82ab input=8328081a3a569bd6]*/
+ const char *errors, int final)
+/*[clinic end generated code: output=b284f97b12c635ee input=6154f039a9f7c639]*/
{
- PyObject *decoded = PyUnicode_DecodeUnicodeEscape(data->buf, data->len,
- errors);
- return codec_tuple(decoded, data->len);
+ Py_ssize_t consumed = data->len;
+ PyObject *decoded = _PyUnicode_DecodeUnicodeEscapeStateful(data->buf, data->len,
+ errors,
+ final ? NULL : &consumed);
+ return codec_tuple(decoded, consumed);
}
/*[clinic input]