diff options
| author | Serhiy Storchaka <storchaka@gmail.com> | 2013-11-26 19:25:15 (GMT) |
|---|---|---|
| committer | Serhiy Storchaka <storchaka@gmail.com> | 2013-11-26 19:25:15 (GMT) |
| commit | dafda9b042cb8a53e59a8d33a75692795097f154 (patch) | |
| tree | 667a88defb1e935c290ac77ee0dc63bd22fd39ff /Modules/_json.c | |
| parent | 60e361fe4209a418f1ba325fe69a9bdae1a5b831 (diff) | |
| download | cpython-dafda9b042cb8a53e59a8d33a75692795097f154.zip cpython-dafda9b042cb8a53e59a8d33a75692795097f154.tar.gz cpython-dafda9b042cb8a53e59a8d33a75692795097f154.tar.bz2 | |
Issue #11489: JSON decoder now accepts lone surrogates.
Diffstat (limited to 'Modules/_json.c')
| -rw-r--r-- | Modules/_json.c | 49 |
1 files changed, 13 insertions, 36 deletions
diff --git a/Modules/_json.c b/Modules/_json.c index 13f5816..eb4368a 100644 --- a/Modules/_json.c +++ b/Modules/_json.c @@ -524,16 +524,10 @@ scanstring_str(PyObject *pystr, Py_ssize_t end, char *encoding, int strict, Py_s } #ifdef Py_UNICODE_WIDE /* Surrogate pair */ - if ((c & 0xfc00) == 0xd800) { + if ((c & 0xfc00) == 0xd800 && end + 6 < len && + buf[next++] == '\\' && + buf[next++] == 'u') { Py_UNICODE c2 = 0; - if (end + 6 >= len) { - raise_errmsg("Unpaired high surrogate", pystr, end - 5); - goto bail; - } - if (buf[next++] != '\\' || buf[next++] != 'u') { - raise_errmsg("Unpaired high surrogate", pystr, end - 5); - goto bail; - } end += 6; /* Decode 4 hex digits */ for (; next < end; next++) { @@ -554,15 +548,10 @@ scanstring_str(PyObject *pystr, Py_ssize_t end, char *encoding, int strict, Py_s goto bail; } } - if ((c2 & 0xfc00) != 0xdc00) { - raise_errmsg("Unpaired high surrogate", pystr, end - 5); - goto bail; - } - c = 0x10000 + (((c - 0xd800) << 10) | (c2 - 0xdc00)); - } - else if ((c & 0xfc00) == 0xdc00) { - raise_errmsg("Unpaired low surrogate", pystr, end - 5); - goto bail; + if ((c2 & 0xfc00) == 0xdc00) + c = 0x10000 + (((c - 0xd800) << 10) | (c2 - 0xdc00)); + else + end -= 6; } #endif } @@ -703,16 +692,9 @@ scanstring_unicode(PyObject *pystr, Py_ssize_t end, int strict, Py_ssize_t *next } #ifdef Py_UNICODE_WIDE /* Surrogate pair */ - if ((c & 0xfc00) == 0xd800) { + if ((c & 0xfc00) == 0xd800 && end + 6 < len && + buf[next++] == '\\' && buf[next++] == 'u') { Py_UNICODE c2 = 0; - if (end + 6 >= len) { - raise_errmsg("Unpaired high surrogate", pystr, end - 5); - goto bail; - } - if (buf[next++] != '\\' || buf[next++] != 'u') { - raise_errmsg("Unpaired high surrogate", pystr, end - 5); - goto bail; - } end += 6; /* Decode 4 hex digits */ for (; next < end; next++) { @@ -733,15 +715,10 @@ scanstring_unicode(PyObject *pystr, Py_ssize_t end, int strict, Py_ssize_t *next goto bail; } } - if ((c2 & 0xfc00) != 0xdc00) { - raise_errmsg("Unpaired high surrogate", pystr, end - 5); - goto bail; - } - c = 0x10000 + (((c - 0xd800) << 10) | (c2 - 0xdc00)); - } - else if ((c & 0xfc00) == 0xdc00) { - raise_errmsg("Unpaired low surrogate", pystr, end - 5); - goto bail; + if ((c2 & 0xfc00) == 0xdc00) + c = 0x10000 + (((c - 0xd800) << 10) | (c2 - 0xdc00)); + else + end -= 6; } #endif } |