mirror of
https://github.com/python/cpython
synced 2024-09-05 00:05:39 +00:00
closes bpo-45190: Update Unicode data to version 14.0.0. (GH-28336)
This commit is contained in:
parent
797c8eb9ef
commit
024fda47d4
|
@ -352,7 +352,7 @@ Notes:
|
||||||
The numeric literals accepted include the digits ``0`` to ``9`` or any
|
The numeric literals accepted include the digits ``0`` to ``9`` or any
|
||||||
Unicode equivalent (code points with the ``Nd`` property).
|
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.
|
for a complete list of code points with the ``Nd`` property.
|
||||||
|
|
||||||
|
|
||||||
|
|
|
@ -17,8 +17,8 @@
|
||||||
|
|
||||||
This module provides access to the Unicode Character Database (UCD) which
|
This module provides access to the Unicode Character Database (UCD) which
|
||||||
defines character properties for all Unicode characters. The data contained in
|
defines character properties for all Unicode characters. The data contained in
|
||||||
this database is compiled from the `UCD version 13.0.0
|
this database is compiled from the `UCD version 14.0.0
|
||||||
<https://www.unicode.org/Public/13.0.0/ucd>`_.
|
<https://www.unicode.org/Public/14.0.0/ucd>`_.
|
||||||
|
|
||||||
The module uses the same names and symbols as defined by Unicode
|
The module uses the same names and symbols as defined by Unicode
|
||||||
Standard Annex #44, `"Unicode Character Database"
|
Standard Annex #44, `"Unicode Character Database"
|
||||||
|
@ -175,6 +175,6 @@ Examples:
|
||||||
|
|
||||||
.. rubric:: Footnotes
|
.. 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
|
||||||
|
|
|
@ -316,7 +316,7 @@ The Unicode category codes mentioned above stand for:
|
||||||
* *Nd* - decimal numbers
|
* *Nd* - decimal numbers
|
||||||
* *Pc* - connector punctuations
|
* *Pc* - connector punctuations
|
||||||
* *Other_ID_Start* - explicit list of characters in `PropList.txt
|
* *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
|
compatibility
|
||||||
* *Other_ID_Continue* - likewise
|
* *Other_ID_Continue* - likewise
|
||||||
|
|
||||||
|
@ -324,8 +324,8 @@ All identifiers are converted into the normal form NFKC while parsing; compariso
|
||||||
of identifiers is based on NFKC.
|
of identifiers is based on NFKC.
|
||||||
|
|
||||||
A non-normative HTML file listing all valid identifier characters for Unicode
|
A non-normative HTML file listing all valid identifier characters for Unicode
|
||||||
4.1 can be found at
|
14.0.0 can be found at
|
||||||
https://www.unicode.org/Public/13.0.0/ucd/DerivedCoreProperties.txt
|
https://www.unicode.org/Public/14.0.0/ucd/DerivedCoreProperties.txt
|
||||||
|
|
||||||
|
|
||||||
.. _keywords:
|
.. _keywords:
|
||||||
|
|
|
@ -239,6 +239,11 @@ time
|
||||||
interval specified with nanosecond precision.
|
interval specified with nanosecond precision.
|
||||||
(Contributed by Livius and Victor Stinner in :issue:`21302`.)
|
(Contributed by Livius and Victor Stinner in :issue:`21302`.)
|
||||||
|
|
||||||
|
unicodedata
|
||||||
|
-----------
|
||||||
|
|
||||||
|
* The Unicode database has been updated to version 14.0.0. (:issue:`45190`).
|
||||||
|
|
||||||
|
|
||||||
Removed
|
Removed
|
||||||
=======
|
=======
|
||||||
|
|
|
@ -18,7 +18,7 @@
|
||||||
class UnicodeMethodsTest(unittest.TestCase):
|
class UnicodeMethodsTest(unittest.TestCase):
|
||||||
|
|
||||||
# update this, if the database changes
|
# update this, if the database changes
|
||||||
expectedchecksum = 'fbdf8106a3c7c242086b0a9efa03ad4d30d5b85d'
|
expectedchecksum = '4739770dd4d0e5f1b1677accfc3552ed3c8ef326'
|
||||||
|
|
||||||
@requires_resource('cpu')
|
@requires_resource('cpu')
|
||||||
def test_method_checksum(self):
|
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
|
# Update this if the database changes. Make sure to do a full rebuild
|
||||||
# (e.g. 'make distclean && make') to get the correct checksum.
|
# (e.g. 'make distclean && make') to get the correct checksum.
|
||||||
expectedchecksum = 'd1e37a2854df60ac607b47b51189b9bf1b54bfdb'
|
expectedchecksum = '98d602e1f69d5c5bb8a5910c40bbbad4e18e8370'
|
||||||
|
|
||||||
@requires_resource('cpu')
|
@requires_resource('cpu')
|
||||||
def test_function_checksum(self):
|
def test_function_checksum(self):
|
||||||
|
|
|
@ -0,0 +1 @@
|
||||||
|
Update Unicode databases to Unicode 14.0.0.
|
|
@ -1045,9 +1045,9 @@ is_unified_ideograph(Py_UCS4 code)
|
||||||
{
|
{
|
||||||
return
|
return
|
||||||
(0x3400 <= code && code <= 0x4DBF) || /* CJK Ideograph Extension A */
|
(0x3400 <= code && code <= 0x4DBF) || /* CJK Ideograph Extension A */
|
||||||
(0x4E00 <= code && code <= 0x9FFC) || /* CJK Ideograph */
|
(0x4E00 <= code && code <= 0x9FFF) || /* CJK Ideograph */
|
||||||
(0x20000 <= code && code <= 0x2A6DD) || /* CJK Ideograph Extension B */
|
(0x20000 <= code && code <= 0x2A6DF) || /* CJK Ideograph Extension B */
|
||||||
(0x2A700 <= code && code <= 0x2B734) || /* CJK Ideograph Extension C */
|
(0x2A700 <= code && code <= 0x2B738) || /* 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 */
|
(0x2B820 <= code && code <= 0x2CEA1) || /* CJK Ideograph Extension E */
|
||||||
(0x2CEB0 <= code && code <= 0x2EBE0) || /* CJK Ideograph Extension F */
|
(0x2CEB0 <= code && code <= 0x2EBE0) || /* CJK Ideograph Extension F */
|
||||||
|
|
7335
Modules/unicodedata_db.h
generated
7335
Modules/unicodedata_db.h
generated
File diff suppressed because it is too large
Load diff
56106
Modules/unicodename_db.h
generated
56106
Modules/unicodename_db.h
generated
File diff suppressed because it is too large
Load diff
3120
Objects/unicodetype_db.h
generated
3120
Objects/unicodetype_db.h
generated
File diff suppressed because it is too large
Load diff
|
@ -44,7 +44,7 @@
|
||||||
# * Doc/library/stdtypes.rst, and
|
# * Doc/library/stdtypes.rst, and
|
||||||
# * Doc/library/unicodedata.rst
|
# * Doc/library/unicodedata.rst
|
||||||
# * Doc/reference/lexical_analysis.rst (two occurrences)
|
# * Doc/reference/lexical_analysis.rst (two occurrences)
|
||||||
UNIDATA_VERSION = "13.0.0"
|
UNIDATA_VERSION = "14.0.0"
|
||||||
UNICODE_DATA = "UnicodeData%s.txt"
|
UNICODE_DATA = "UnicodeData%s.txt"
|
||||||
COMPOSITION_EXCLUSIONS = "CompositionExclusions%s.txt"
|
COMPOSITION_EXCLUSIONS = "CompositionExclusions%s.txt"
|
||||||
EASTASIAN_WIDTH = "EastAsianWidth%s.txt"
|
EASTASIAN_WIDTH = "EastAsianWidth%s.txt"
|
||||||
|
@ -101,9 +101,9 @@
|
||||||
# these ranges need to match unicodedata.c:is_unified_ideograph
|
# these ranges need to match unicodedata.c:is_unified_ideograph
|
||||||
cjk_ranges = [
|
cjk_ranges = [
|
||||||
('3400', '4DBF'),
|
('3400', '4DBF'),
|
||||||
('4E00', '9FFC'),
|
('4E00', '9FFF'),
|
||||||
('20000', '2A6DD'),
|
('20000', '2A6DF'),
|
||||||
('2A700', '2B734'),
|
('2A700', '2B738'),
|
||||||
('2B740', '2B81D'),
|
('2B740', '2B81D'),
|
||||||
('2B820', '2CEA1'),
|
('2B820', '2CEA1'),
|
||||||
('2CEB0', '2EBE0'),
|
('2CEB0', '2EBE0'),
|
||||||
|
|
Loading…
Reference in a new issue