diff --git a/Lib/test/test_unicodedata.py b/Lib/test/test_unicodedata.py index baa36cbf187..61a10318bb1 100644 --- a/Lib/test/test_unicodedata.py +++ b/Lib/test/test_unicodedata.py @@ -185,6 +185,11 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest): # The rest can be found in test_normalization.py # which requires an external file. + def test_pr29(self): + # http://www.unicode.org/review/pr-29.html + for text in (u"\u0b47\u0300\u0b3e", u"\u1100\u0300\u1161"): + self.assertEqual(self.db.normalize('NFC', text), text) + def test_east_asian_width(self): eaw = self.db.east_asian_width self.assertRaises(TypeError, eaw, 'a') diff --git a/Misc/NEWS b/Misc/NEWS index 96dbd20cb6d..6d438ca176b 100644 --- a/Misc/NEWS +++ b/Misc/NEWS @@ -21,6 +21,9 @@ Core and Builtins Library ------- +- Issue #1054943: Fix unicodedata.normalize('NFC', text) for the Public Review + Issue #29 + - Issue #7494: fix a crash in _lsprof (cProfile) after clearing the profiler, reset also the pointer to the current pointer context. diff --git a/Modules/unicodedata.c b/Modules/unicodedata.c index ad77651a26c..0e61877e022 100644 --- a/Modules/unicodedata.c +++ b/Modules/unicodedata.c @@ -681,7 +681,7 @@ nfc_nfkc(PyObject *self, PyObject *input, int k) comb = 0; while (i1 < end) { int comb1 = _getrecord_ex(*i1)->combining; - if (comb1 && comb == comb1) { + if (comb && (comb1 == 0 || comb == comb1)) { /* Character is blocked. */ i1++; continue;