upgrade to UCD 6.2

Doc/library/unicodedata.rst

@@ -15,8 +15,8 @@
 
 This module provides access to the Unicode Character Database (UCD) which
 defines character properties for all Unicode characters. The data contained in
-this database is compiled from the `UCD version 6.1.0
-<http://www.unicode.org/Public/6.1.0/ucd>`_.
+this database is compiled from the `UCD version 6.2.0
+<http://www.unicode.org/Public/6.2.0/ucd>`_.
 
 The module uses the same names and symbols as defined by Unicode
 Standard Annex #44, `"Unicode Character Database"

Lib/test/test_unicodedata.py

@@ -80,7 +80,7 @@ class UnicodeDatabaseTest(unittest.TestCase):
 class UnicodeFunctionsTest(UnicodeDatabaseTest):
 
     # update this, if the database changes
-    expectedchecksum = '17fe2f12b788e4fff5479b469c4404bb6ecf841f'
+    expectedchecksum = 'ebd64e81553c9cb37f424f5616254499fcd8849e'
     def test_function_checksum(self):
         data = []
         h = hashlib.sha1()

Misc/NEWS

@@ -10,6 +10,8 @@ What's New in Python 3.4.0 Alpha 1?
 Core and Builtins
 -----------------
 
+- Upgrade Unicode data (UCD) to version 6.2.
+
 Library
 -------
 

Objects/unicodetype_db.h

@@ -1919,7 +1919,7 @@ static unsigned short index2[] = {
     246, 247, 248, 249, 250, 251, 5, 5, 5, 5, 5, 95, 245, 26, 22, 23, 246, 
     247, 248, 249, 250, 251, 5, 5, 5, 5, 5, 0, 95, 95, 95, 95, 95, 95, 95, 
     95, 95, 95, 95, 95, 95, 0, 0, 0, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 
-    5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
+    5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
     0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 
     25, 25, 25, 6, 6, 6, 6, 25, 6, 6, 6, 25, 25, 25, 25, 25, 25, 25, 25, 25, 
     25, 25, 25, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 5, 5, 113, 5, 5, 
@@ -2593,10 +2593,10 @@ static unsigned short index2[] = {
     0, 0, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 
     141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 
     141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 
-    141, 141, 141, 141, 141, 141, 141, 141, 141, 252, 252, 141, 141, 141, 
     141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 
     141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 
-    141, 141, 141, 252, 252, 141, 141, 141, 141, 141, 141, 141, 141, 141, 
+    141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 
+    141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 141, 
     141, 141, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 5, 5, 5, 5, 0, 0, 0, 0, 
     0, 0, 0, 0, 0, 0, 0, 0, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 
     55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 
@@ -2925,6 +2925,9 @@ static unsigned short index2[] = {
 double _PyUnicode_ToNumeric(Py_UCS4 ch)
 {
     switch (ch) {
+    case 0x12456:
+    case 0x12457:
+        return (double) -1.0;
     case 0x0F33:
         return (double) -1.0/2.0;
     case 0x0030:
@@ -3427,6 +3430,8 @@ double _PyUnicode_ToNumeric(Py_UCS4 ch)
         return (double) 20000.0;
     case 0x3251:
         return (double) 21.0;
+    case 0x12432:
+        return (double) 216000.0;
     case 0x3252:
         return (double) 22.0;
     case 0x3253:
@@ -3721,6 +3726,8 @@ double _PyUnicode_ToNumeric(Py_UCS4 ch)
         return (double) 42.0;
     case 0x32B8:
         return (double) 43.0;
+    case 0x12433:
+        return (double) 432000.0;
     case 0x32B9:
         return (double) 44.0;
     case 0x32BA:

Tools/unicode/makeunicodedata.py

@@ -37,7 +37,7 @@ SCRIPT = sys.argv[0]
 VERSION = "3.2"
 
 # The Unicode Database
-UNIDATA_VERSION = "6.1.0"
+UNIDATA_VERSION = "6.2.0"
 UNICODE_DATA = "UnicodeData%s.txt"
 COMPOSITION_EXCLUSIONS = "CompositionExclusions%s.txt"
 EASTASIAN_WIDTH = "EastAsianWidth%s.txt"