upgrade to Unicode 8.0.0

Doc/library/stdtypes.rst

@@ -354,7 +354,7 @@ Notes:
    The numeric literals accepted include the digits ``0`` to ``9`` or any
    Unicode equivalent (code points with the ``Nd`` property).
 
-   See http://www.unicode.org/Public/7.0.0/ucd/extracted/DerivedNumericType.txt
+   See http://www.unicode.org/Public/8.0.0/ucd/extracted/DerivedNumericType.txt
    for a complete list of code points with the ``Nd`` property.
 
 

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 7.0.0
-<http://www.unicode.org/Public/7.0.0/ucd>`_.
+this database is compiled from the `UCD version 8.0.0
+<http://www.unicode.org/Public/8.0.0/ucd>`_.
 
 The module uses the same names and symbols as defined by Unicode
 Standard Annex #44, `"Unicode Character Database"
@@ -166,6 +166,6 @@ Examples:
 
 .. rubric:: Footnotes
 
-.. [#] http://www.unicode.org/Public/7.0.0/ucd/NameAliases.txt
+.. [#] http://www.unicode.org/Public/8.0.0/ucd/NameAliases.txt
 
-.. [#] http://www.unicode.org/Public/7.0.0/ucd/NamedSequences.txt
+.. [#] http://www.unicode.org/Public/8.0.0/ucd/NamedSequences.txt

Doc/reference/lexical_analysis.rst

@@ -311,7 +311,7 @@ The Unicode category codes mentioned above stand for:
 * *Nd* - decimal numbers
 * *Pc* - connector punctuations
 * *Other_ID_Start* - explicit list of characters in `PropList.txt
-  <http://www.unicode.org/Public/7.0.0/ucd/PropList.txt>`_ to support backwards
+  <http://www.unicode.org/Public/8.0.0/ucd/PropList.txt>`_ to support backwards
   compatibility
 * *Other_ID_Continue* - likewise
 
@@ -727,4 +727,4 @@ occurrence outside string literals and comments is an unconditional error::
 
 .. rubric:: Footnotes
 
-.. [#] http://www.unicode.org/Public/7.0.0/ucd/NameAliases.txt
+.. [#] http://www.unicode.org/Public/8.0.0/ucd/NameAliases.txt

Doc/whatsnew/3.5.rst

@@ -755,6 +755,13 @@ urllib
   control the encoding of query parts if needed.  (Contributed by Samwyse and
   Arnon Yaari in :issue:`13866`.)
 
+unicodedata
+-----------
+
+* The :mod:`unicodedata` module now uses data from `Unicode 8.0.0
+<http://unicode.org/versions/Unicode8.0.0/>`_.
+
+
 wsgiref
 -------
 

Lib/test/test_unicodedata.py

@@ -21,7 +21,7 @@ errors = 'surrogatepass'
 class UnicodeMethodsTest(unittest.TestCase):
 
     # update this, if the database changes
-    expectedchecksum = '618e2c1a22ee79d2235319709f16c50f987ee21f'
+    expectedchecksum = '5971760872b2f98bb9c701e6c0db3273d756b3ec'
 
     def test_method_checksum(self):
         h = hashlib.sha1()
@@ -81,7 +81,7 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest):
 
     # Update this if the database changes. Make sure to do a full rebuild
     # (e.g. 'make distclean && make') to get the correct checksum.
-    expectedchecksum = '585302895deead0c1c8478c51da9241d4efedca9'
+    expectedchecksum = '5e74827cd07f9e546a30f34b7bcf6cc2eac38c8c'
     def test_function_checksum(self):
         data = []
         h = hashlib.sha1()

Misc/NEWS

@@ -10,6 +10,8 @@ Release date: 2015-07-05
 Core and Builtins
 -----------------
 
+- Upgrade to Unicode 8.0.0.
+
 - Issue #24345: Add Py_tp_finalize slot for the stable ABI.
 
 - Issue #24400: Introduce a distinct type for PEP 492 coroutines; add

Modules/unicodedata.c

@@ -921,10 +921,11 @@ is_unified_ideograph(Py_UCS4 code)
 {
     return
         (0x3400 <= code && code <= 0x4DB5)   || /* CJK Ideograph Extension A */
-        (0x4E00 <= code && code <= 0x9FCC)   || /* CJK Ideograph */
+        (0x4E00 <= code && code <= 0x9FD5)   || /* 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 */
+        (0x2B740 <= code && code <= 0x2B81D) || /* CJK Ideograph Extension D */
+        (0x2B820 <= code && code <= 0x2CEA1);   /* CJK Ideograph Extension E */
 }
 
 /* macros used to determine if the given code point is in the PUA range that

Tools/unicode/makeunicodedata.py

@@ -42,7 +42,7 @@ VERSION = "3.2"
 #   * Doc/library/stdtypes.rst, and
 #   * Doc/library/unicodedata.rst
 #   * Doc/reference/lexical_analysis.rst (two occurrences)
-UNIDATA_VERSION = "7.0.0"
+UNIDATA_VERSION = "8.0.0"
 UNICODE_DATA = "UnicodeData%s.txt"
 COMPOSITION_EXCLUSIONS = "CompositionExclusions%s.txt"
 EASTASIAN_WIDTH = "EastAsianWidth%s.txt"
@@ -99,10 +99,11 @@ EXTENDED_CASE_MASK = 0x4000
 # these ranges need to match unicodedata.c:is_unified_ideograph
 cjk_ranges = [
     ('3400', '4DB5'),
-    ('4E00', '9FCC'),
+    ('4E00', '9FD5'),
     ('20000', '2A6D6'),
     ('2A700', '2B734'),
-    ('2B740', '2B81D')
+    ('2B740', '2B81D'),
+    ('2B820', '2CEA1'),
 ]
 
 def maketables(trace=0):