Merged revisions 78647 via svnmerge from

svn+ssh://pythondev@svn.python.org/python/branches/py3k

................
  r78647 | victor.stinner | 2010-03-04 13:14:57 +0100 (jeu., 04 mars 2010) | 12 lines

  Merged revisions 78646 via svnmerge from
  svn+ssh://pythondev@svn.python.org/python/trunk

  ........
    r78646 | victor.stinner | 2010-03-04 13:09:33 +0100 (jeu., 04 mars 2010) | 5 lines

    Issue #1054943: Fix unicodedata.normalize('NFC', text) for the Public Review
    Issue #29.

    PR #29 was released in february 2004!
  ........
................

diff --git a/Lib/test/test_unicodedata.py b/Lib/test/test_unicodedata.py
index a658d7bd55e3158dcf2e755fbe1b634bd9c172e5..0f3fec89783ee6265401727d2b51f0a488d6cff0 100644 (file)
--- a/Lib/test/test_unicodedata.py
+++ b/Lib/test/test_unicodedata.py
@@ -186,6 +186,11 @@ 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, b'a')

diff --git a/Misc/NEWS b/Misc/NEWS
index 3e75f2218b689e0e1c83790a892259f59992977b..87a47b8836f0e4879ddd458f2543ac502fe4946f 100644 (file)
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -100,6 +100,9 @@ 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 2dddc488cfa18b44787aef5479c7043610109b9b..f7c329255f2ea459a0e576bfa51d265a44fbfe03 100644 (file)
--- a/Modules/unicodedata.c
+++ b/Modules/unicodedata.c
@@ -684,7 +684,7 @@ 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;