closes bpo-45190: Update Unicode data to version 14.0.0. (GH-28336)

benjaminp · web-flow · commit 024fda47d40b · 2021-09-14T11:00:38.000-07:00
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 https://www.unicode.org/Public/13.0.0/ucd/extracted/DerivedNumericType.txt
+   See https://www.unicode.org/Public/14.0.0/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 13.0.0
-<https://www.unicode.org/Public/13.0.0/ucd>`_.
+this database is compiled from the `UCD version 14.0.0
+<https://www.unicode.org/Public/14.0.0/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
 
-.. [#] https://www.unicode.org/Public/13.0.0/ucd/NameAliases.txt
+.. [#] https://www.unicode.org/Public/14.0.0/ucd/NameAliases.txt
 
-.. [#] https://www.unicode.org/Public/13.0.0/ucd/NamedSequences.txt
+.. [#] https://www.unicode.org/Public/14.0.0/ucd/NamedSequences.txt
diff --git a/Doc/reference/lexical_analysis.rst b/Doc/reference/lexical_analysis.rst
@@ -316,16 +316,16 @@ The Unicode category codes mentioned above stand for:
 * *Nd* - decimal numbers
 * *Pc* - connector punctuations
 * *Other_ID_Start* - explicit list of characters in `PropList.txt
-  <https://www.unicode.org/Public/13.0.0/ucd/PropList.txt>`_ to support backwards
+  <https://www.unicode.org/Public/14.0.0/ucd/PropList.txt>`_ to support backwards
   compatibility
 * *Other_ID_Continue* - likewise
 
 All identifiers are converted into the normal form NFKC while parsing; comparison
 of identifiers is based on NFKC.
 
 A non-normative HTML file listing all valid identifier characters for Unicode
-4.1 can be found at
-https://www.unicode.org/Public/13.0.0/ucd/DerivedCoreProperties.txt
+14.0.0 can be found at
+https://www.unicode.org/Public/14.0.0/ucd/DerivedCoreProperties.txt
 
 
 .. _keywords:
diff --git a/Doc/whatsnew/3.11.rst b/Doc/whatsnew/3.11.rst
@@ -239,6 +239,11 @@ time
   interval specified with nanosecond precision.
   (Contributed by Livius and Victor Stinner in :issue:`21302`.)
 
+unicodedata
+-----------
+
+* The Unicode database has been updated to version 14.0.0. (:issue:`45190`).
+
 
 Removed
 =======
diff --git a/Lib/test/test_unicodedata.py b/Lib/test/test_unicodedata.py
@@ -18,7 +18,7 @@
 class UnicodeMethodsTest(unittest.TestCase):
 
     # update this, if the database changes
-    expectedchecksum = 'fbdf8106a3c7c242086b0a9efa03ad4d30d5b85d'
+    expectedchecksum = '4739770dd4d0e5f1b1677accfc3552ed3c8ef326'
 
     @requires_resource('cpu')
     def test_method_checksum(self):
@@ -71,7 +71,7 @@ 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 = 'd1e37a2854df60ac607b47b51189b9bf1b54bfdb'
+    expectedchecksum = '98d602e1f69d5c5bb8a5910c40bbbad4e18e8370'
 
     @requires_resource('cpu')
     def test_function_checksum(self):
diff --git a/Misc/NEWS.d/next/Core and Builtins/2021-09-14-10-02-12.bpo-45190.ZFRgSj.rst b/Misc/NEWS.d/next/Core and Builtins/2021-09-14-10-02-12.bpo-45190.ZFRgSj.rst
@@ -0,0 +1 @@
+Update Unicode databases to Unicode 14.0.0.
diff --git a/Modules/unicodedata.c b/Modules/unicodedata.c
@@ -1045,9 +1045,9 @@ is_unified_ideograph(Py_UCS4 code)
 {
     return
         (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 */
+        (0x4E00 <= code && code <= 0x9FFF)   || /* CJK Ideograph */
+        (0x20000 <= code && code <= 0x2A6DF) || /* CJK Ideograph Extension B */
+        (0x2A700 <= code && code <= 0x2B738) || /* CJK Ideograph Extension C */
         (0x2B740 <= code && code <= 0x2B81D) || /* CJK Ideograph Extension D */
         (0x2B820 <= code && code <= 0x2CEA1) || /* CJK Ideograph Extension E */
         (0x2CEB0 <= code && code <= 0x2EBE0) || /* CJK Ideograph Extension F */
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 = "13.0.0"
+UNIDATA_VERSION = "14.0.0"
 UNICODE_DATA = "UnicodeData%s.txt"
 COMPOSITION_EXCLUSIONS = "CompositionExclusions%s.txt"
 EASTASIAN_WIDTH = "EastAsianWidth%s.txt"
@@ -101,9 +101,9 @@
 # these ranges need to match unicodedata.c:is_unified_ideograph
 cjk_ranges = [
     ('3400', '4DBF'),
-    ('4E00', '9FFC'),
-    ('20000', '2A6DD'),
-    ('2A700', '2B734'),
+    ('4E00', '9FFF'),
+    ('20000', '2A6DF'),
+    ('2A700', '2B738'),
     ('2B740', '2B81D'),
     ('2B820', '2CEA1'),
     ('2CEB0', '2EBE0'),

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1 @@`
	`1`	`+Update Unicode databases to Unicode 14.0.0.`