diff options
| author | Wonsup Yoon <pusnow@me.com> | 2018-06-15 12:03:14 (GMT) |
|---|---|---|
| committer | Xiang Zhang <angwerzx@126.com> | 2018-06-15 12:03:14 (GMT) |
| commit | d134809cd3764c6a634eab7bb8995e3e2eff14d5 (patch) | |
| tree | 6bcc3ec615c093c71b96ce1ce52594bacdc75466 /Modules | |
| parent | ceeef10cdbc08561f9954e13bbed1cb2299a8c72 (diff) | |
| download | cpython-d134809cd3764c6a634eab7bb8995e3e2eff14d5.zip cpython-d134809cd3764c6a634eab7bb8995e3e2eff14d5.tar.gz cpython-d134809cd3764c6a634eab7bb8995e3e2eff14d5.tar.bz2 | |
bpo-29456: Fix bugs in unicodedata.normalize: u1176, u11a7 and u11c3 (GH-1958)
Hangul composition check boundaries are wrong for the second character
([0x1161, 0x1176) instead of [0x1161, 0x1176]) and third character ((0x11A7, 0x11C3)
instead of [0x11A7, 0x11C3]).
Diffstat (limited to 'Modules')
| -rw-r--r-- | Modules/unicodedata.c | 10 |
1 files changed, 7 insertions, 3 deletions
diff --git a/Modules/unicodedata.c b/Modules/unicodedata.c index 7a9a964..e8788f5 100644 --- a/Modules/unicodedata.c +++ b/Modules/unicodedata.c @@ -681,15 +681,19 @@ nfc_nfkc(PyObject *self, PyObject *input, int k) if (LBase <= code && code < (LBase+LCount) && i + 1 < len && VBase <= PyUnicode_READ(kind, data, i+1) && - PyUnicode_READ(kind, data, i+1) <= (VBase+VCount)) { + PyUnicode_READ(kind, data, i+1) < (VBase+VCount)) { + /* check L character is a modern leading consonant (0x1100 ~ 0x1112) + and V character is a modern vowel (0x1161 ~ 0x1175). */ int LIndex, VIndex; LIndex = code - LBase; VIndex = PyUnicode_READ(kind, data, i+1) - VBase; code = SBase + (LIndex*VCount+VIndex)*TCount; i+=2; if (i < len && - TBase <= PyUnicode_READ(kind, data, i) && - PyUnicode_READ(kind, data, i) <= (TBase+TCount)) { + TBase < PyUnicode_READ(kind, data, i) && + PyUnicode_READ(kind, data, i) < (TBase+TCount)) { + /* check T character is a modern trailing consonant + (0x11A8 ~ 0x11C2). */ code += PyUnicode_READ(kind, data, i)-TBase; i++; } |