update to Unicode 6.1

Lib/test/test_unicodedata.py

@@ -21,7 +21,7 @@ errors = 'surrogatepass'
 class UnicodeMethodsTest(unittest.TestCase):
 
     # update this, if the database changes
-    expectedchecksum = 'df0b3ca6785a070b21f837b227dbdbdff3c2e921'
+    expectedchecksum = 'bf7a78f1a532421b5033600102e23a92044dbba9'
 
     def test_method_checksum(self):
         h = hashlib.sha1()
@@ -80,7 +80,7 @@ class UnicodeDatabaseTest(unittest.TestCase):
 class UnicodeFunctionsTest(UnicodeDatabaseTest):
 
     # update this, if the database changes
-    expectedchecksum = 'c23dfc0b5eaf3ca2aad32d733de96bb182ccda50'
+    expectedchecksum = '17fe2f12b788e4fff5479b469c4404bb6ecf841f'
     def test_function_checksum(self):
         data = []
         h = hashlib.sha1()

Misc/NEWS

@@ -10,6 +10,8 @@ What's New in Python 3.3 Alpha 1?
 Core and Builtins
 -----------------
 
+- Upgrade Unicode data to Unicode 6.1.
+
 - Issue #14040: Remove rarely used file name suffixes for C extensions
   (under POSIX mainly).
 

Modules/unicodedata.c

@@ -921,7 +921,7 @@ is_unified_ideograph(Py_UCS4 code)
 {
     return
         (0x3400 <= code && code <= 0x4DB5)   || /* CJK Ideograph Extension A */
-        (0x4E00 <= code && code <= 0x9FCB)   || /* CJK Ideograph */
+        (0x4E00 <= code && code <= 0x9FCC)   || /* CJK Ideograph */
         (0x20000 <= code && code <= 0x2A6D6) || /* CJK Ideograph Extension B */
         (0x2A700 <= code && code <= 0x2B734) || /* CJK Ideograph Extension C */
         (0x2B740 <= code && code <= 0x2B81D);   /* CJK Ideograph Extension D */

Tools/unicode/makeunicodedata.py

@@ -38,7 +38,7 @@ SCRIPT = sys.argv[0]
 VERSION = "3.2"
 
 # The Unicode Database
-UNIDATA_VERSION = "6.0.0"
+UNIDATA_VERSION = "6.1.0"
 UNICODE_DATA = "UnicodeData%s.txt"
 COMPOSITION_EXCLUSIONS = "CompositionExclusions%s.txt"
 EASTASIAN_WIDTH = "EastAsianWidth%s.txt"
@@ -58,7 +58,7 @@ PUA_16 = range(0x100000, 0x10FFFE)
 
 # we use this ranges of PUA_15 to store name aliases and named sequences
 NAME_ALIASES_START = 0xF0000
-NAMED_SEQUENCES_START = 0xF0100
+NAMED_SEQUENCES_START = 0xF0200
 
 old_versions = ["3.2.0"]
 
@@ -95,7 +95,7 @@ EXTENDED_CASE_MASK = 0x4000
 # these ranges need to match unicodedata.c:is_unified_ideograph
 cjk_ranges = [
     ('3400', '4DB5'),
-    ('4E00', '9FCB'),
+    ('4E00', '9FCC'),
     ('20000', '2A6D6'),
     ('2A700', '2B734'),
     ('2B740', '2B81D')
@@ -958,7 +958,7 @@ class UnicodeData:
                     s = s.strip()
                     if not s or s.startswith('#'):
                         continue
-                    char, name = s.split(';')
+                    char, name, abbrev = s.split(';')
                     char = int(char, 16)
                     self.aliases.append((name, char))
                     # also store the name in the PUA 1
@@ -971,6 +971,7 @@ class UnicodeData:
             # in order to take advantage of the compression and lookup
             # algorithms used for the other characters.
 
+            assert pua_index < NAMED_SEQUENCES_START
             pua_index = NAMED_SEQUENCES_START
             with open_data(NAMED_SEQUENCES, version) as file:
                 for s in file: