closes bpo-39926: Update Unicode to 13.0.0. (GH-18910)

python · Mar 11, 2020 · 051b9d0 · 051b9d0
1 parent 76d5877
commit 051b9d0
Show file tree

Hide file tree

Showing 11 changed files with 29,772 additions and 28,737 deletions.
diff --git a/Doc/library/stdtypes.rst b/Doc/library/stdtypes.rst
@@ -352,7 +352,7 @@ 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/12.1.0/ucd/extracted/DerivedNumericType.txt
+   See http://www.unicode.org/Public/13.0.0/ucd/extracted/DerivedNumericType.txt
    for a complete list of code points with the ``Nd`` property.
 
 

diff --git a/Doc/library/unicodedata.rst b/Doc/library/unicodedata.rst
@@ -17,8 +17,8 @@
 
 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 12.1.0
-<http://www.unicode.org/Public/12.1.0/ucd>`_.
+this database is compiled from the `UCD version 13.0.0
+<http://www.unicode.org/Public/13.0.0/ucd>`_.
 
 The module uses the same names and symbols as defined by Unicode
 Standard Annex #44, `"Unicode Character Database"
@@ -175,6 +175,6 @@ Examples:
 
 .. rubric:: Footnotes
 
-.. [#] http://www.unicode.org/Public/12.1.0/ucd/NameAliases.txt
+.. [#] http://www.unicode.org/Public/13.0.0/ucd/NameAliases.txt
 
-.. [#] http://www.unicode.org/Public/12.1.0/ucd/NamedSequences.txt
+.. [#] http://www.unicode.org/Public/13.0.0/ucd/NamedSequences.txt
diff --git a/Doc/reference/lexical_analysis.rst b/Doc/reference/lexical_analysis.rst
@@ -316,7 +316,7 @@ 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/12.1.0/ucd/PropList.txt>`_ to support backwards
+  <http://www.unicode.org/Public/13.0.0/ucd/PropList.txt>`_ to support backwards
   compatibility
 * *Other_ID_Continue* - likewise
 

diff --git a/Doc/whatsnew/3.9.rst b/Doc/whatsnew/3.9.rst
@@ -372,6 +372,11 @@ types with context-specific metadata and new ``include_extras`` parameter to
 :func:`typing.get_type_hints` to access the metadata at runtime. (Contributed
 by Till Varoquaux and Konstantin Kashin.)
 
+unicodedata
+-----------
+
+The Unicode database has been updated to version 13.0.0. (:issue:`39926`).
+
 venv
 ----
 

diff --git a/Lib/test/test_ucn.py b/Lib/test/test_ucn.py
@@ -99,6 +99,7 @@ def test_cjk_unified_ideographs(self):
         self.checkletter("CJK UNIFIED IDEOGRAPH-2B734", "\U0002B734")
         self.checkletter("CJK UNIFIED IDEOGRAPH-2B740", "\U0002B740")
         self.checkletter("CJK UNIFIED IDEOGRAPH-2B81D", "\U0002B81D")
+        self.checkletter("CJK UNIFIED IDEOGRAPH-3134A", "\U0003134A")
 
     def test_bmp_characters(self):
         for code in range(0x10000):

diff --git a/Misc/NEWS.d/next/Core and Builtins/2020-03-10-19-14-42.bpo-39926.H19bAa.rst b/Misc/NEWS.d/next/Core and Builtins/2020-03-10-19-14-42.bpo-39926.H19bAa.rst
@@ -0,0 +1 @@
+Update Unicode database to Unicode version 13.0.0.
diff --git a/Modules/unicodedata.c b/Modules/unicodedata.c
@@ -1031,13 +1031,14 @@ static int
 is_unified_ideograph(Py_UCS4 code)
 {
     return
-        (0x3400 <= code && code <= 0x4DB5)   || /* CJK Ideograph Extension A */
-        (0x4E00 <= code && code <= 0x9FEF)   || /* CJK Ideograph */
-        (0x20000 <= code && code <= 0x2A6D6) || /* CJK Ideograph Extension B */
+        (0x3400 <= code && code <= 0x4DBF)   || /* CJK Ideograph Extension A */
+        (0x4E00 <= code && code <= 0x9FFC)   || /* CJK Ideograph */
+        (0x20000 <= code && code <= 0x2A6DD) || /* CJK Ideograph Extension B */
         (0x2A700 <= code && code <= 0x2B734) || /* CJK Ideograph Extension C */
         (0x2B740 <= code && code <= 0x2B81D) || /* CJK Ideograph Extension D */
         (0x2B820 <= code && code <= 0x2CEA1) || /* CJK Ideograph Extension E */
-        (0x2CEB0 <= code && code <= 0x2EBEF);   /* CJK Ideograph Extension F */
+        (0x2CEB0 <= code && code <= 0x2EBE0) || /* CJK Ideograph Extension F */
+        (0x30000 <= code && code <= 0x3134A);   /* CJK Ideograph Extension G */
 }
 
 /* macros used to determine if the given code point is in the PUA range that

diff --git a/Modules/unicodedata_db.h b/Modules/unicodedata_db.h
diff --git a/Modules/unicodename_db.h b/Modules/unicodename_db.h
diff --git a/Objects/unicodetype_db.h b/Objects/unicodetype_db.h
diff --git a/Tools/unicode/makeunicodedata.py b/Tools/unicode/makeunicodedata.py
@@ -44,7 +44,7 @@
 #   * Doc/library/stdtypes.rst, and
 #   * Doc/library/unicodedata.rst
 #   * Doc/reference/lexical_analysis.rst (two occurrences)
-UNIDATA_VERSION = "12.1.0"
+UNIDATA_VERSION = "13.0.0"
 UNICODE_DATA = "UnicodeData%s.txt"
 COMPOSITION_EXCLUSIONS = "CompositionExclusions%s.txt"
 EASTASIAN_WIDTH = "EastAsianWidth%s.txt"
@@ -100,13 +100,14 @@
 
 # these ranges need to match unicodedata.c:is_unified_ideograph
 cjk_ranges = [
-    ('3400', '4DB5'),
-    ('4E00', '9FEF'),
-    ('20000', '2A6D6'),
+    ('3400', '4DBF'),
+    ('4E00', '9FFC'),
+    ('20000', '2A6DD'),
     ('2A700', '2B734'),
     ('2B740', '2B81D'),
     ('2B820', '2CEA1'),
     ('2CEB0', '2EBE0'),
+    ('30000', '3134A'),
 ]