pylee
diff --git a/‎Doc/library/unicodedata.rst‎
Lines changed: 2 additions & 2 deletions b/‎Doc/library/unicodedata.rst‎
Lines changed: 2 additions & 2 deletions
diff --git a/‎Lib/test/test_unicodedata.py‎
Lines changed: 12 additions & 2 deletions b/‎Lib/test/test_unicodedata.py‎
Lines changed: 12 additions & 2 deletions
diff --git a/‎Misc/NEWS‎
Lines changed: 2 additions & 0 deletions b/‎Misc/NEWS‎
Lines changed: 2 additions & 0 deletions
diff --git a/‎Modules/unicodedata.c‎
Lines changed: 8 additions & 5 deletions b/‎Modules/unicodedata.c‎
Lines changed: 8 additions & 5 deletions
@@ -16,11 +16,11 @@
 
 This module provides access to the Unicode Character Database which defines
 character properties for all Unicode characters. The data in this database is
-based on the :file:`UnicodeData.txt` file version 4.1.0 which is publicly
+based on the :file:`UnicodeData.txt` file version 5.1.0 which is publicly
 available from ftp://ftp.unicode.org/.
 
 The module uses the same names and symbols as defined by the UnicodeData File
-Format 4.1.0 (see http://www.unicode.org/Public/4.1.0/ucd/UCD.html).  It defines
+Format 5.1.0 (see http://www.unicode.org/Public/5.1.0/ucd/UCD.html).  It defines
 the following functions:
 
 
 
@@ -16,7 +16,7 @@
 class UnicodeMethodsTest(unittest.TestCase):
 
     # update this, if the database changes
-    expectedchecksum = 'c198ed264497f108434b3f576d4107237221cc8a'
+    expectedchecksum = 'aef99984a58c8e1e5363a3175f2ff9608599a93e'
 
     def test_method_checksum(self):
         h = hashlib.sha1()
@@ -75,7 +75,7 @@ def tearDown(self):
 class UnicodeFunctionsTest(UnicodeDatabaseTest):
 
     # update this, if the database changes
-    expectedchecksum = '4e389f97e9f88b8b7ab743121fd643089116f9f2'
+    expectedchecksum = '3136d5afd787dc2bcb1bdcac95e385349fbebbca'
 
     def test_function_checksum(self):
         data = []
@@ -225,6 +225,16 @@ def test_digit_numeric_consistent(self):
     def test_bug_1704793(self):
         self.assertEquals(self.db.lookup("GOTHIC LETTER FAIHU"), u'\U00010346')
 
+    def test_ucd_510(self):
+        import unicodedata
+        # In UCD 5.1.0, a mirrored property changed wrt. UCD 3.2.0
+        self.assert_(unicodedata.mirrored(u"\u0f3a"))
+        self.assert_(not unicodedata.ucd_3_2_0.mirrored(u"\u0f3a"))
+        # Also, we now have two ways of representing
+        # the upper-case mapping: as delta, or as absolute value
+        self.assert_(u"a".upper()==u'A')
+        self.assert_(u"\u1d79".upper()==u'\ua77d')
+
 def test_main():
     test.test_support.run_unittest(
         UnicodeMiscTest,
 
@@ -68,6 +68,8 @@ C-API
 Library
 -------
 
+- Issue #3811: The Unicode database was updated to 5.1.
+
 - Issue #3809: Fixed spurious 'test.blah' file left behind by test_logging.
 
 - Issue 3781: Clean up the API for warnings.catch_warnings() by having it
 
@@ -1,8 +1,8 @@
 /* ------------------------------------------------------------------------
 
-   unicodedata -- Provides access to the Unicode 4.1 data base.
+   unicodedata -- Provides access to the Unicode 5.1 data base.
 
-   Data was extracted from the Unicode 4.1 UnicodeData.txt file.
+   Data was extracted from the Unicode 5.1 UnicodeData.txt file.
 
    Written by Marc-Andre Lemburg ([email protected]).
    Modified for Python 2.0 by Fredrik Lundh ([email protected])
@@ -34,6 +34,7 @@ typedef struct change_record {
     const unsigned char bidir_changed;
     const unsigned char category_changed;
     const unsigned char decimal_changed;
+    const unsigned char mirrored_changed;
     const int numeric_changed;
 } change_record;
 
@@ -354,6 +355,8 @@ unicodedata_mirrored(PyObject *self, PyObject *args)
         const change_record *old = get_old_record(self, c);
         if (old->category_changed == 0)
             index = 0; /* unassigned */
+        else if (old->mirrored_changed != 0xFF)
+            index = old->mirrored_changed;
     }
     return PyInt_FromLong(index);
 }
@@ -1177,11 +1180,11 @@ PyDoc_STRVAR(unicodedata_docstring,
 "This module provides access to the Unicode Character Database which\n\
 defines character properties for all Unicode characters. The data in\n\
 this database is based on the UnicodeData.txt file version\n\
-4.1.0 which is publically available from ftp://ftp.unicode.org/.\n\
+5.1.0 which is publically available from ftp://ftp.unicode.org/.\n\
 \n\
 The module uses the same names and symbols as defined by the\n\
-UnicodeData File Format 4.1.0 (see\n\
-http://www.unicode.org/Public/4.1.0/ucd/UCD.html).");
+UnicodeData File Format 5.1.0 (see\n\
+http://www.unicode.org/Public/5.1.0/ucd/UCD.html).");
 
 PyMODINIT_FUNC
 initunicodedata(void)