gh-156289: Update Unicode to 18.0.0

Doc/library/re.rst

@@ -614,7 +614,7 @@ character ``'$'``.
 
       Matches ``[0-9]`` if the :py:const:`~re.ASCII` flag is used.
 
-      __ https://www.unicode.org/versions/Unicode17.0.0/core-spec/chapter-4/#G124142
+      __ https://www.unicode.org/versions/Unicode18.0.0/core-spec/chapter-4/#G124142
 
    For 8-bit (bytes) patterns:
       Matches any decimal digit in the ASCII character set;

Doc/library/stdtypes.rst

@@ -2157,7 +2157,7 @@ expression support in the :mod:`re` module).
 
    The casefolding algorithm is `described in section 3.13.3 'Default Case
    Folding' of the Unicode Standard
-   <https://www.unicode.org/versions/Unicode17.0.0/core-spec/chapter-3/#G53253>`__.
+   <https://www.unicode.org/versions/Unicode18.0.0/core-spec/chapter-3/#G53253>`__.
 
    .. versionadded:: 3.3
 
@@ -2398,7 +2398,7 @@ 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 section 4.10 'Letters, Alphabetic, and
    Ideographic' of the Unicode Standard
-   <https://www.unicode.org/versions/Unicode17.0.0/core-spec/chapter-4/#G91002>`__.
+   <https://www.unicode.org/versions/Unicode18.0.0/core-spec/chapter-4/#G91002>`__.
    For example:
 
    .. doctest::
@@ -2664,7 +2664,7 @@ expression support in the :mod:`re` module).
 
    The lowercasing algorithm used is `described in section 3.13.2 'Default Case
    Conversion' of the Unicode Standard
-   <https://www.unicode.org/versions/Unicode17.0.0/core-spec/chapter-3/#G34078>`__.
+   <https://www.unicode.org/versions/Unicode18.0.0/core-spec/chapter-3/#G34078>`__.
 
 
 .. method:: str.lstrip(chars=None, /)
@@ -3176,7 +3176,7 @@ expression support in the :mod:`re` module).
 
    The uppercasing algorithm used is `described in section 3.13.2 'Default Case
    Conversion' of the Unicode Standard
-   <https://www.unicode.org/versions/Unicode17.0.0/core-spec/chapter-3/#G34078>`__.
+   <https://www.unicode.org/versions/Unicode18.0.0/core-spec/chapter-3/#G34078>`__.
 
 
 .. method:: str.zfill(width, /)

Doc/library/unicodedata.rst

@@ -13,8 +13,8 @@
 
 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 17.0.0
-<https://www.unicode.org/Public/17.0.0/ucd>`_.
+this database is compiled from the `UCD version 18.0.0
+<https://www.unicode.org/Public/18.0.0/ucd>`_.
 
 The module uses the same names and symbols as defined by Unicode
 Standard Annex #44, `"Unicode Character Database"
@@ -170,7 +170,7 @@ Standard Annex #44, `"Unicode Character Database"
 .. function:: block(chr, /)
 
    Returns the `block
-   <https://www.unicode.org/versions/Unicode17.0.0/core-spec/chapter-3/#G64189>`_
+   <https://www.unicode.org/versions/Unicode18.0.0/core-spec/chapter-3/#G64189>`_
    assigned to the character *chr*. For example::
 
       >>> unicodedata.block('S')
@@ -326,6 +326,6 @@ In addition, the module exposes the following constants:
 
 .. rubric:: Footnotes
 
-.. [#] https://www.unicode.org/Public/17.0.0/ucd/NameAliases.txt
+.. [#] https://www.unicode.org/Public/18.0.0/ucd/NameAliases.txt
 
-.. [#] https://www.unicode.org/Public/17.0.0/ucd/NamedSequences.txt
+.. [#] https://www.unicode.org/Public/18.0.0/ucd/NamedSequences.txt

Doc/reference/lexical_analysis.rst

@@ -602,8 +602,8 @@ Unicode categories use the version of the Unicode Character Database as
 included in the :mod:`unicodedata` module.
 
 .. _UAX-31: https://www.unicode.org/reports/tr31/
-.. _PropList.txt: https://www.unicode.org/Public/17.0.0/ucd/PropList.txt
-.. _DerivedCoreProperties.txt: https://www.unicode.org/Public/17.0.0/ucd/DerivedCoreProperties.txt
+.. _PropList.txt: https://www.unicode.org/Public/18.0.0/ucd/PropList.txt
+.. _DerivedCoreProperties.txt: https://www.unicode.org/Public/18.0.0/ucd/DerivedCoreProperties.txt
 .. _normalization form: https://www.unicode.org/reports/tr15/#Norm_Forms
 
 .. seealso::
@@ -916,7 +916,7 @@ with the given *name*::
 This sequence cannot appear in :ref:`bytes literals <bytes-literal>`.
 
 .. versionchanged:: 3.3
-   Support for `name aliases <https://www.unicode.org/Public/17.0.0/ucd/NameAliases.txt>`__
+   Support for `name aliases <https://www.unicode.org/Public/18.0.0/ucd/NameAliases.txt>`__
    has been added.
 
 .. _string-escape-long-hex:

Lib/re/_properties.py

@@ -100,7 +100,7 @@
 # CATEGORY_DIGIT matches Nd (but, like \d, is restricted to ASCII under the
 # ASCII flag).  The gc group memberships (L = Lu|Ll|Lt|Lm|Lo, N = Nd|Nl|No)
 # are given by the Unicode Standard 4.5, Table 4-4 "General_Category Values"
-# (https://www.unicode.org/versions/Unicode17.0.0/core-spec/chapter-4/#G124142)
+# (https://www.unicode.org/versions/Unicode18.0.0/core-spec/chapter-4/#G124142)
 # and listed in
 # https://www.unicode.org/Public/UCD/latest/ucd/PropertyValueAliases.txt
 # The compound categories Lu, N, Lm, Nl, No, Cf, Z, Zs, C and Cn are
@@ -127,7 +127,7 @@
 # (private use) and the single code points Zl and Zp.  Cc, Cs and Co are the
 # control codes, surrogate and private-use areas, fixed by the Unicode
 # Standard 23.1, 23.6 and 23.5:
-# https://www.unicode.org/versions/Unicode17.0.0/core-spec/chapter-23/
+# https://www.unicode.org/versions/Unicode18.0.0/core-spec/chapter-23/
 # All five are listed in
 # https://www.unicode.org/Public/UCD/latest/ucd/extracted/DerivedGeneralCategory.txt
 _CC_RANGES = [(0x00, 0x1F), (0x7F, 0x9F)]
@@ -174,7 +174,7 @@ def _analytic_ranges():
     # normalised.
     # Noncharacter_Code_Point: U+FDD0..FDEF and the last two of every plane,
     # permanently reserved (the Unicode Standard 23.7, "Noncharacters":
-    # https://www.unicode.org/versions/Unicode17.0.0/core-spec/chapter-23/).
+    # https://www.unicode.org/versions/Unicode18.0.0/core-spec/chapter-23/).
     noncharacter = [(0xFDD0, 0xFDEF)]
     noncharacter += [(plane | 0xFFFE, plane | 0xFFFF)
                      for plane in range(0, MAXUNICODE + 1, 0x10000)]

Lib/stringprep.py

@@ -9,7 +9,7 @@
 # when unicodedata is modified to ensure conformant behavior.
 import unicodedata
 
-assert unicodedata.unidata_version == '17.0.0'
+assert unicodedata.unidata_version == '18.0.0'
 
 from unicodedata import ucd_3_2_0 as unicodedata_320
 

Lib/test/test_unicodedata.py

@@ -55,9 +55,9 @@ def download_test_data_file(filename):
 class UnicodeMethodsTest(unittest.TestCase):
 
     # update this, if the database changes
-    expectedchecksum = ('47a99fa654ef1f50e89d2e9697b7b041fccb5a05'
+    expectedchecksum = ('2bb59305a65254fee9cd6ef981cc3cab7551c60e'
                         if quicktest else
-                        '8b2615a9fc627676cbc0b6fac0191177df97ef5f')
+                        'bb69894a259aee5971445eca8e617a1686a432e2')
 
     def test_method_checksum(self):
         h = hashlib.sha1()
@@ -345,6 +345,9 @@ def test_bidirectional(self):
         # New in 17.0.0
         self.assertEqual(self.db.bidirectional('\u088f'), '' if self.old else 'AL')
         self.assertEqual(self.db.bidirectional('\U0001fbfa'), '' if self.old else 'ON')
+        # New in 18.0.0
+        self.assertEqual(self.db.bidirectional('\U00001b3a'), '' if self.old else 'L')
+        self.assertEqual(self.db.bidirectional('\U00001b3c'), '' if self.old else 'L')
 
         self.assertRaises(TypeError, self.db.bidirectional)
         self.assertRaises(TypeError, self.db.bidirectional, 'xx')
@@ -377,6 +380,8 @@ def test_decomposition(self):
         self.assertEqual(self.db.decomposition('\U0001CCD6'), '' if self.old else '<font> 0041')
         # New in 17.0.0
         self.assertEqual(self.db.decomposition('\uA7F1'), '' if self.old else '<super> 0053')
+        # New in 18.0.0
+        self.assertEqual(self.db.decomposition('\u0558'), '' if self.old else '<super> 0567')
 
         # Hangul characters
         self.assertEqual(self.db.decomposition('\uAC00'), '1100 1161')
@@ -428,6 +433,8 @@ def test_combining(self):
         self.assertEqual(self.db.combining('\u0897'), 0 if self.old else 230)
         # New in 17.0.0
         self.assertEqual(self.db.combining('\u1ACF'), 0 if self.old else 230)
+        # New in 18.0.0
+        self.assertEqual(self.db.combining('\U0001d127'), 0 if self.old else 220)
 
         self.assertRaises(TypeError, self.db.combining)
         self.assertRaises(TypeError, self.db.combining, 'xx')
@@ -696,11 +703,13 @@ def test_east_asian_width(self):
         self.assertEqual(eaw('\U0001FAE9'), 'N' if self.old else 'W')
         # New in 17.0.0
         self.assertEqual(eaw('\U00016FF2'), 'N' if self.old else 'W')
+        # New in 18.0.0
+        self.assertEqual(eaw('\U0001F7DA'), 'N' if self.old else 'W')
 
     def test_east_asian_width_unassigned(self):
         eaw = self.db.east_asian_width
         # unassigned
-        for char in '\u0530\u0ecf\u10c6\u20fc\uaaca\U000107bd\U000115f2':
+        for char in '\u0530\u0ecf\u10c6\u20fc\uaaca\U000115f2':
             self.assertEqual(eaw(char), 'N')
             self.assertIs(self.db.name(char, None), None)
 
@@ -721,9 +730,9 @@ class UnicodeFunctionsTest(unittest.TestCase, BaseUnicodeFunctionsTest):
 
     # Update this if the database changes. Make sure to do a full rebuild
     # (e.g. 'make distclean && make') to get the correct checksum.
-    expectedchecksum = ('00b13fa975a60b1d3f490f1fc8c126ab24990c75'
+    expectedchecksum = ('04a01eac45fd6ca3cfa5aafe90f278c1f7d62aa2'
                         if quicktest else
-                        'ebfc9dd281c2226998fd435744dd2e9321899beb')
+                        'f5354bfdd674d0229dbec9f8f038a86b31cf6b4b')
 
     @requires_resource('network')
     def test_all_names(self):
@@ -882,6 +891,9 @@ def test_grapheme_cluster_break(self):
         # New in 17.0.0
         self.assertEqual(gcb('\u1AEB'), 'Extend')
         self.assertEqual(gcb('\U00011B67'), 'SpacingMark')
+        # New in 18.0.0
+        self.assertEqual(gcb('\U00011DF0'), 'Extend')
+        self.assertEqual(gcb('\U0001D25F'), 'Extend')
 
         self.assertRaises(TypeError, gcb)
         self.assertRaises(TypeError, gcb, b'x')
@@ -910,6 +922,8 @@ def test_indic_conjunct_break(self):
         self.assertEqual(incb('\u1000'), 'Consonant')
         self.assertEqual(incb('\U00011F33'), 'Consonant')
         self.assertEqual(incb('\U0001E6F5'), 'Extend')
+        # New in 18.0.0
+        self.assertEqual(incb('\U00011A3A'), 'Linker')
 
         self.assertRaises(TypeError, incb)
         self.assertRaises(TypeError, incb, b'x')
@@ -930,6 +944,8 @@ def test_extended_pictographic(self):
         # New in 17.0.0
         self.assertIs(ext_pict('\u2388'), False)
         self.assertIs(ext_pict('\U0001FA6D'), False)
+        # New in 18.0.0
+        self.assertIs(ext_pict('\U0001F6D9'), True)
 
         self.assertRaises(TypeError, ext_pict)
         self.assertRaises(TypeError, ext_pict, b'x')
@@ -1087,6 +1103,14 @@ def test_block(self):
         # New in 17.0.0
         self.assertEqual(self.db.block('\u1AEB'), 'Combining Diacritical Marks Extended')
         self.assertEqual(self.db.block('\U00011B67'), 'Sharada Supplement')
+        # New in 18.0.0
+        self.assertEqual(self.db.block('\U00011DF2'), 'Bengali Supplement')
+        self.assertEqual(self.db.block('\U000125F2'), 'Archaic Cuneiform Numerals')
+        self.assertEqual(self.db.block('\U00018EF2'), 'Jurchen')
+        self.assertEqual(self.db.block('\U000191A2'), 'Jurchen Radicals')
+        self.assertEqual(self.db.block('\U0001D252'), 'Musical Symbols Supplement')
+        self.assertEqual(self.db.block('\U0001DB52'), 'Miscellaneous Symbols and Arrows Extended')
+        self.assertEqual(self.db.block('\U0003DB52'), 'Seal')
         # Unassigned
         self.assertEqual(self.db.block('\U00100000'), 'Supplementary Private Use Area-B')
         self.assertEqual(self.db.block('\U0010FFFF'), 'Supplementary Private Use Area-B')
@@ -1104,7 +1128,7 @@ class Unicode_3_2_0_FunctionsTest(unittest.TestCase, BaseUnicodeFunctionsTest):
     old = True
     expectedchecksum = ('883824cb6c0ccf994e4451ebf281e2d6d479af47'
                         if quicktest else
-                        '68cd01e2c680b851c1fcab012efb5635b2229c2b')
+                        '677542db0fed40ddbd491b95622cb649a4b7fca0')
 
 
 class UnicodeMiscTest(unittest.TestCase):

Misc/NEWS.d/next/Library/2026-08-23-14-23-40.gh-issue-156289.YFwnPi.rst

@@ -0,0 +1 @@
+Update Unicode to 18.0.0