closes gh-124016: update Unicode to 16.0.0 (#124017)

benjaminp · web-flow · commit bb904e063d0c · 2024-09-13T07:47:04.000-07:00
diff --git a/Doc/library/stdtypes.rst b/Doc/library/stdtypes.rst
@@ -1679,7 +1679,7 @@ expression support in the :mod:`re` module).
 
    The casefolding algorithm is
    `described in section 3.13 'Default Case Folding' of the Unicode Standard
-   <https://www.unicode.org/versions/Unicode15.1.0/ch03.pdf>`__.
+   <https://www.unicode.org/versions/Unicode16.0.0/core-spec/chapter-3/#G33992>`__.
 
    .. versionadded:: 3.3
 
@@ -1843,7 +1843,7 @@ expression support in the :mod:`re` module).
    property being one of "Lm", "Lt", "Lu", "Ll", or "Lo".  Note that this is different
    from the `Alphabetic property defined in the section 4.10 'Letters, Alphabetic, and
    Ideographic' of the Unicode Standard
-   <https://www.unicode.org/versions/Unicode15.1.0/ch04.pdf>`_.
+   <https://www.unicode.org/versions/Unicode16.0.0/core-spec/chapter-4/#G91002>`_.
 
 
 .. method:: str.isascii()
@@ -1979,7 +1979,7 @@ expression support in the :mod:`re` module).
 
    The lowercasing algorithm used is
    `described in section 3.13 'Default Case Folding' of the Unicode Standard
-   <https://www.unicode.org/versions/Unicode15.1.0/ch03.pdf>`__.
+   <https://www.unicode.org/versions/Unicode16.0.0/core-spec/chapter-3/#G33992>`__.
 
 
 .. method:: str.lstrip([chars])
@@ -2331,7 +2331,7 @@ expression support in the :mod:`re` module).
 
    The uppercasing algorithm used is
    `described in section 3.13 'Default Case Folding' of the Unicode Standard
-   <https://www.unicode.org/versions/Unicode15.1.0/ch03.pdf>`__.
+   <https://www.unicode.org/versions/Unicode16.0.0/core-spec/chapter-3/#G33992>`__.
 
 
 .. method:: str.zfill(width)
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 15.1.0
-<https://www.unicode.org/Public/15.1.0/ucd>`_.
+this database is compiled from the `UCD version 16.0.0
+<https://www.unicode.org/Public/16.0.0/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/15.1.0/ucd/NameAliases.txt
+.. [#] https://www.unicode.org/Public/16.0.0/ucd/NameAliases.txt
 
-.. [#] https://www.unicode.org/Public/15.1.0/ucd/NamedSequences.txt
+.. [#] https://www.unicode.org/Public/16.0.0/ucd/NamedSequences.txt
diff --git a/Doc/reference/lexical_analysis.rst b/Doc/reference/lexical_analysis.rst
@@ -314,16 +314,16 @@ 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/15.1.0/ucd/PropList.txt>`_ to support backwards
+  <https://www.unicode.org/Public/16.0.0/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
-15.1.0 can be found at
-https://www.unicode.org/Public/15.1.0/ucd/DerivedCoreProperties.txt
+16.0.0 can be found at
+https://www.unicode.org/Public/16.0.0/ucd/DerivedCoreProperties.txt
 
 
 .. _keywords:
@@ -1044,4 +1044,4 @@ occurrence outside string literals and comments is an unconditional error:
 
 .. rubric:: Footnotes
 
-.. [#] https://www.unicode.org/Public/15.1.0/ucd/NameAliases.txt
+.. [#] https://www.unicode.org/Public/16.0.0/ucd/NameAliases.txt
diff --git a/Doc/whatsnew/3.14.rst b/Doc/whatsnew/3.14.rst
@@ -253,6 +253,11 @@ symtable
 
   (Contributed by Bénédikt Tran in :gh:`120029`.)
 
+unicodedata
+-----------
+
+* The Unicode database has been updated to Unicode 16.0.0.
+
 .. Add improved modules above alphabetically, not here at the end.
 
 Optimizations
diff --git a/Lib/test/string_tests.py b/Lib/test/string_tests.py
@@ -1132,8 +1132,8 @@ def test_capitalize_nonascii(self):
         self.checkequal('\u2160\u2171\u2172',
                         '\u2170\u2171\u2172', 'capitalize')
         # check with Ll chars with no upper - nothing changes here
-        self.checkequal('\u019b\u1d00\u1d86\u0221\u1fb7',
-                        '\u019b\u1d00\u1d86\u0221\u1fb7', 'capitalize')
+        self.checkequal('\u1d00\u1d86\u0221\u1fb7',
+                        '\u1d00\u1d86\u0221\u1fb7', 'capitalize')
 
     def test_startswith(self):
         self.checkequal(True, 'hello', 'startswith', 'he')
diff --git a/Lib/test/test_str.py b/Lib/test/test_str.py
@@ -2430,8 +2430,10 @@ def __repr__(self):
         self.assertEqual(repr(s1()), '\\n')
 
     def test_printable_repr(self):
-        self.assertEqual(repr('\U00010000'), "'%c'" % (0x10000,)) # printable
-        self.assertEqual(repr('\U00014000'), "'\\U00014000'")     # nonprintable
+        # printable
+        self.assertEqual(repr('\U00010000'), "'%c'" % (0x10000,))
+        # nonprintable (private use area)
+        self.assertEqual(repr('\U00100001'), "'\\U00100001'")
 
     # This test only affects 32-bit platforms because expandtabs can only take
     # an int as the max value, not a 64-bit C long.  If expandtabs is changed
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 = '63aa77dcb36b0e1df082ee2a6071caeda7f0955e'
+    expectedchecksum = '9e43ee3929471739680c0e705482b4ae1c4122e4'
 
     @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 = '232affd2a50ec4bd69d2482aa0291385cbdefaba'
+    expectedchecksum = '23ab09ed4abdf93db23b97359108ed630dd8311d'
 
     @requires_resource('cpu')
     def test_function_checksum(self):
diff --git a/Misc/NEWS.d/next/Library/2024-09-12-10-55-19.gh-issue-124016.ncs0hd.rst b/Misc/NEWS.d/next/Library/2024-09-12-10-55-19.gh-issue-124016.ncs0hd.rst
@@ -0,0 +1 @@
+Update :mod:`unicodedata` database to Unicode 16.0.0.
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

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1 @@`
	`1`	+Update :mod:`unicodedata` database to Unicode 16.0.0.