diff options
Diffstat (limited to 'simplejson/decoder.py')
| -rw-r--r-- | simplejson/decoder.py | 38 |
1 files changed, 17 insertions, 21 deletions
diff --git a/simplejson/decoder.py b/simplejson/decoder.py index 54ced0a..5ccb450 100644 --- a/simplejson/decoder.py +++ b/simplejson/decoder.py @@ -102,36 +102,32 @@ def py_scanstring(s, end, encoding=None, strict=True, # Unicode escape sequence msg = "Invalid \\uXXXX escape sequence" esc = s[end + 1:end + 5] - next_end = end + 5 - if len(esc) != 4: - raise JSONDecodeError(msg, s, end) + escX = esc[1:2] + if len(esc) != 4 or escX == 'x' or escX == 'X': + raise JSONDecodeError(msg, s, end - 1) try: uni = int(esc, 16) except ValueError: - raise JSONDecodeError(msg, s, end) + raise JSONDecodeError(msg, s, end - 1) + end += 5 # Check for surrogate pair on UCS-4 systems - if _maxunicode > 65535: - unimask = uni & 0xfc00 - if unimask == 0xd800: - msg = "Unpaired high surrogate" - if not s[end + 5:end + 7] == '\\u': - raise JSONDecodeError(msg, s, end) - esc2 = s[end + 7:end + 11] - if len(esc2) != 4: - raise JSONDecodeError(msg, s, end) + # Note that this will join high/low surrogate pairs + # but will also pass unpaired surrogates through + if (_maxunicode > 65535 and + uni & 0xfc00 == 0xd800 and + s[end:end + 2] == '\\u'): + esc2 = s[end + 2:end + 6] + escX = esc2[1:2] + if len(esc2) == 4 and not (escX == 'x' or escX == 'X'): try: uni2 = int(esc2, 16) except ValueError: raise JSONDecodeError(msg, s, end) - if uni2 & 0xfc00 != 0xdc00: - raise JSONDecodeError(msg, s, end) - uni = 0x10000 + (((uni - 0xd800) << 10) | (uni2 - 0xdc00)) - next_end += 6 - elif unimask == 0xdc00: - msg = "Unpaired low surrogate" - raise JSONDecodeError(msg, s, end) + if uni2 & 0xfc00 == 0xdc00: + uni = 0x10000 + (((uni - 0xd800) << 10) | + (uni2 - 0xdc00)) + end += 6 char = unichr(uni) - end = next_end # Append the unescaped character _append(char) return _join(chunks), end |