diff options
| author | robot-piglet <[email protected]> | 2025-10-08 09:57:44 +0300 |
|---|---|---|
| committer | robot-piglet <[email protected]> | 2025-10-08 10:11:25 +0300 |
| commit | 94c10d61d66a7b6d830dbcb419ad44b330066765 (patch) | |
| tree | 421761b447c002ffbdc753aebf3d812f38f9d9e1 /contrib/python/wcwidth | |
| parent | 0f3f07ccb038beab419ba7ac850d95885f624989 (diff) | |
Intermediate changes
commit_hash:572d11de7e4c4fd16eeb91e832abea46ff94a4f2
Diffstat (limited to 'contrib/python/wcwidth')
| -rw-r--r-- | contrib/python/wcwidth/py3/.dist-info/METADATA | 38 | ||||
| -rw-r--r-- | contrib/python/wcwidth/py3/README.rst | 18 | ||||
| -rw-r--r-- | contrib/python/wcwidth/py3/tests/test_core.py | 96 | ||||
| -rw-r--r-- | contrib/python/wcwidth/py3/tests/test_emojis.py | 85 | ||||
| -rw-r--r-- | contrib/python/wcwidth/py3/tests/test_table_integrity.py | 5 | ||||
| -rw-r--r-- | contrib/python/wcwidth/py3/tests/test_ucslevel.py | 13 | ||||
| -rw-r--r-- | contrib/python/wcwidth/py3/wcwidth/__init__.py | 2 | ||||
| -rw-r--r-- | contrib/python/wcwidth/py3/wcwidth/table_vs15.py | 103 | ||||
| -rw-r--r-- | contrib/python/wcwidth/py3/wcwidth/table_vs16.py | 4 | ||||
| -rw-r--r-- | contrib/python/wcwidth/py3/wcwidth/table_wide.py | 262 | ||||
| -rw-r--r-- | contrib/python/wcwidth/py3/wcwidth/table_zero.py | 711 | ||||
| -rw-r--r-- | contrib/python/wcwidth/py3/wcwidth/unicode_versions.py | 4 | ||||
| -rw-r--r-- | contrib/python/wcwidth/py3/wcwidth/wcwidth.py | 49 | ||||
| -rw-r--r-- | contrib/python/wcwidth/py3/ya.make | 3 |
14 files changed, 1216 insertions, 177 deletions
diff --git a/contrib/python/wcwidth/py3/.dist-info/METADATA b/contrib/python/wcwidth/py3/.dist-info/METADATA index f7f7fcdcc85..95adb5715ec 100644 --- a/contrib/python/wcwidth/py3/.dist-info/METADATA +++ b/contrib/python/wcwidth/py3/.dist-info/METADATA @@ -1,6 +1,6 @@ -Metadata-Version: 2.1 +Metadata-Version: 2.4 Name: wcwidth -Version: 0.2.13 +Version: 0.2.14 Summary: Measures the displayed width of unicode strings in a terminal Home-page: https://github.com/jquast/wcwidth Author: Jeff Quast @@ -13,8 +13,6 @@ Classifier: Development Status :: 5 - Production/Stable Classifier: Environment :: Console Classifier: License :: OSI Approved :: MIT License Classifier: Operating System :: POSIX -Classifier: Programming Language :: Python :: 2.7 -Classifier: Programming Language :: Python :: 3.5 Classifier: Programming Language :: Python :: 3.6 Classifier: Programming Language :: Python :: 3.7 Classifier: Programming Language :: Python :: 3.8 @@ -22,12 +20,24 @@ Classifier: Programming Language :: Python :: 3.9 Classifier: Programming Language :: Python :: 3.10 Classifier: Programming Language :: Python :: 3.11 Classifier: Programming Language :: Python :: 3.12 +Classifier: Programming Language :: Python :: 3.13 +Classifier: Programming Language :: Python :: 3.14 Classifier: Topic :: Software Development :: Libraries Classifier: Topic :: Software Development :: Localization Classifier: Topic :: Software Development :: Internationalization Classifier: Topic :: Terminals +Requires-Python: >=3.6 License-File: LICENSE -Requires-Dist: backports.functools-lru-cache >=1.2.1 ; python_version < "3.2" +Dynamic: author +Dynamic: author-email +Dynamic: classifier +Dynamic: description +Dynamic: home-page +Dynamic: keywords +Dynamic: license +Dynamic: license-file +Dynamic: requires-python +Dynamic: summary |pypi_downloads| |codecov| |license| @@ -126,7 +136,7 @@ Briefly, return values of function ``wcwidth()`` are: Function ``wcswidth()`` simply returns the sum of all values for each character along a string, or ``-1`` when it occurs anywhere along a string. -Full API Documentation at https://wcwidth.readthedocs.org +Full API Documentation at https://wcwidth.readthedocs.io ========== Developing @@ -136,9 +146,9 @@ Install wcwidth in editable mode:: pip install -e . -Execute unit tests using tox_:: +Execute unit tests using tox_ for all supported Python versions:: - tox -e py27,py35,py36,py37,py38,py39,py310,py311,py312 + tox -e py36,py37,py38,py39,py310,py311,py312,py313,py314 Updating Unicode Version ------------------------ @@ -248,6 +258,13 @@ Other Languages History ======= +0.2.14 *2025-09-22* + * **Drop Support** for Python 2.7 and 3.5. `PR #117`_. + * **Update** tables to include Unicode Specifications 16.0.0 and 17.0.0. + `PR #146`_. + * **Bugfix** U+00AD SOFT HYPHEN should measure as 1, versions 0.2.9 through + 0.2.13 measured as 0. `PR #149`_. + 0.2.13 *2024-01-06* * **Bugfix** zero-width support for Hangul Jamo (Korean) @@ -290,7 +307,7 @@ History Environment variable ``UNICODE_VERSION``, such as ``13.0``, or ``6.3.0``. See the `jquast/ucs-detect`_ CLI utility for automatic detection. * **Enhancement**: - API Documentation is published to readthedocs.org. + API Documentation is published to readthedocs.io. * **Updated** tables for *all* Unicode Specifications with files published in a programmatically consumable format, versions 4.1.0 through 13.0 @@ -368,6 +385,9 @@ https://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c:: .. _`PR #97`: https://github.com/jquast/wcwidth/pull/97 .. _`PR #98`: https://github.com/jquast/wcwidth/pull/98 .. _`PR #100`: https://github.com/jquast/wcwidth/pull/100 +.. _`PR #117`: https://github.com/jquast/wcwidth/pull/117 +.. _`PR #146`: https://github.com/jquast/wcwidth/pull/146 +.. _`PR #149`: https://github.com/jquast/wcwidth/pull/149 .. _`Issue #101`: https://github.com/jquast/wcwidth/issues/101 .. _`jquast/blessed`: https://github.com/jquast/blessed .. _`selectel/pyte`: https://github.com/selectel/pyte diff --git a/contrib/python/wcwidth/py3/README.rst b/contrib/python/wcwidth/py3/README.rst index 65df2081b8d..1b92ef4ca03 100644 --- a/contrib/python/wcwidth/py3/README.rst +++ b/contrib/python/wcwidth/py3/README.rst @@ -95,7 +95,7 @@ Briefly, return values of function ``wcwidth()`` are: Function ``wcswidth()`` simply returns the sum of all values for each character along a string, or ``-1`` when it occurs anywhere along a string. -Full API Documentation at https://wcwidth.readthedocs.org +Full API Documentation at https://wcwidth.readthedocs.io ========== Developing @@ -105,9 +105,9 @@ Install wcwidth in editable mode:: pip install -e . -Execute unit tests using tox_:: +Execute unit tests using tox_ for all supported Python versions:: - tox -e py27,py35,py36,py37,py38,py39,py310,py311,py312 + tox -e py36,py37,py38,py39,py310,py311,py312,py313,py314 Updating Unicode Version ------------------------ @@ -217,6 +217,13 @@ Other Languages History ======= +0.2.14 *2025-09-22* + * **Drop Support** for Python 2.7 and 3.5. `PR #117`_. + * **Update** tables to include Unicode Specifications 16.0.0 and 17.0.0. + `PR #146`_. + * **Bugfix** U+00AD SOFT HYPHEN should measure as 1, versions 0.2.9 through + 0.2.13 measured as 0. `PR #149`_. + 0.2.13 *2024-01-06* * **Bugfix** zero-width support for Hangul Jamo (Korean) @@ -259,7 +266,7 @@ History Environment variable ``UNICODE_VERSION``, such as ``13.0``, or ``6.3.0``. See the `jquast/ucs-detect`_ CLI utility for automatic detection. * **Enhancement**: - API Documentation is published to readthedocs.org. + API Documentation is published to readthedocs.io. * **Updated** tables for *all* Unicode Specifications with files published in a programmatically consumable format, versions 4.1.0 through 13.0 @@ -337,6 +344,9 @@ https://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c:: .. _`PR #97`: https://github.com/jquast/wcwidth/pull/97 .. _`PR #98`: https://github.com/jquast/wcwidth/pull/98 .. _`PR #100`: https://github.com/jquast/wcwidth/pull/100 +.. _`PR #117`: https://github.com/jquast/wcwidth/pull/117 +.. _`PR #146`: https://github.com/jquast/wcwidth/pull/146 +.. _`PR #149`: https://github.com/jquast/wcwidth/pull/149 .. _`Issue #101`: https://github.com/jquast/wcwidth/issues/101 .. _`jquast/blessed`: https://github.com/jquast/blessed .. _`selectel/pyte`: https://github.com/selectel/pyte diff --git a/contrib/python/wcwidth/py3/tests/test_core.py b/contrib/python/wcwidth/py3/tests/test_core.py index 60ed6b1cde7..206bbdcab38 100644 --- a/contrib/python/wcwidth/py3/tests/test_core.py +++ b/contrib/python/wcwidth/py3/tests/test_core.py @@ -1,4 +1,3 @@ -# coding: utf-8 """Core tests for wcwidth module. isort:skip_file""" try: # std import @@ -10,13 +9,6 @@ except ImportError: # local import wcwidth -try: - # python 2 - _ = unichr -except NameError: - # python 3 - unichr = chr - def test_package_version(): """wcwidth.__version__ is expected value.""" @@ -70,7 +62,7 @@ def basic_string_type(): def test_hello_jp(): - u""" + """ Width of Japanese phrase: コンニチハ, セカイ! Given a phrase of 5 and 3 Katakana ideographs, joined with @@ -78,7 +70,7 @@ def test_hello_jp(): phrase consumes 19 cells of a terminal emulator. """ # given, - phrase = u'コンニチハ, セカイ!' + phrase = 'コンニチハ, セカイ!' expect_length_each = (2, 2, 2, 2, 2, 1, 1, 2, 2, 2, 1) expect_length_phrase = sum(expect_length_each) @@ -99,7 +91,7 @@ def test_wcswidth_substr(): to stop counting length. """ # given, - phrase = u'コンニチハ, セカイ!' + phrase = 'コンニチハ, セカイ!' end = 7 expect_length_each = (2, 2, 2, 2, 2, 1, 1,) expect_length_phrase = sum(expect_length_each) @@ -116,7 +108,7 @@ def test_wcswidth_substr(): def test_null_width_0(): """NULL (0) reports width 0.""" # given, - phrase = u'abc\x00def' + phrase = 'abc\x00def' expect_length_each = (1, 1, 1, 0, 1, 1, 1) expect_length_phrase = sum(expect_length_each) @@ -140,7 +132,7 @@ def test_control_c0_width_negative_1(): any string containing the C1 control character \x1b (ESC). """ # given, - phrase = u'\x1b[0m' + phrase = '\x1b[0m' expect_length_each = (-1, 1, 1, 1) expect_length_phrase = -1 @@ -156,7 +148,7 @@ def test_control_c0_width_negative_1(): def test_combining_width(): """Simple test combining reports total width of 4.""" # given, - phrase = u'--\u05bf--' + phrase = '--\u05bf--' expect_length_each = (1, 1, 0, 1, 1) expect_length_phrase = 4 @@ -170,8 +162,8 @@ def test_combining_width(): def test_combining_cafe(): - u"""Phrase cafe + COMBINING ACUTE ACCENT is café of length 4.""" - phrase = u"cafe\u0301" + """Phrase cafe + COMBINING ACUTE ACCENT is café of length 4.""" + phrase = "cafe\u0301" expect_length_each = (1, 1, 1, 1, 0) expect_length_phrase = 4 @@ -185,8 +177,8 @@ def test_combining_cafe(): def test_combining_enclosing(): - u"""CYRILLIC CAPITAL LETTER A + COMBINING CYRILLIC HUNDRED THOUSANDS SIGN is of length 1.""" - phrase = u"\u0410\u0488" + """CYRILLIC CAPITAL LETTER A + COMBINING CYRILLIC HUNDRED THOUSANDS SIGN is of length 1.""" + phrase = "\u0410\u0488" expect_length_each = (1, 0) expect_length_phrase = 1 @@ -200,16 +192,16 @@ def test_combining_enclosing(): def test_balinese_script(): - u""" + """ Balinese kapal (ship) is length 3. This may be an example that is not yet correctly rendered by any terminal so far, like devanagari. """ - phrase = (u"\u1B13" # Category 'Lo', EAW 'N' -- BALINESE LETTER KA - u"\u1B28" # Category 'Lo', EAW 'N' -- BALINESE LETTER PA KAPAL - u"\u1B2E" # Category 'Lo', EAW 'N' -- BALINESE LETTER LA - u"\u1B44") # Category 'Mc', EAW 'N' -- BALINESE ADEG ADEG + phrase = ("\u1B13" # Category 'Lo', EAW 'N' -- BALINESE LETTER KA + "\u1B28" # Category 'Lo', EAW 'N' -- BALINESE LETTER PA KAPAL + "\u1B2E" # Category 'Lo', EAW 'N' -- BALINESE LETTER LA + "\u1B44") # Category 'Mc', EAW 'N' -- BALINESE ADEG ADEG expect_length_each = (1, 1, 1, 0) expect_length_phrase = 3 @@ -237,8 +229,8 @@ def test_kr_jamo(): # and not by independent display, like other zero-width characters that may # only combine with an appropriate preceding character. phrase = ( - u"\u1100" # ᄀ HANGUL CHOSEONG KIYEOK (consonant) - u"\u1161" # ᅡ HANGUL JUNGSEONG A (vowel) + "\u1100" # ᄀ HANGUL CHOSEONG KIYEOK (consonant) + "\u1161" # ᅡ HANGUL JUNGSEONG A (vowel) ) expect_length_each = (2, 0) expect_length_phrase = 2 @@ -253,14 +245,14 @@ def test_kr_jamo(): def test_kr_jamo_filler(): - u""" + """ Jamo filler is 0 width. Example from https://www.unicode.org/L2/L2006/06310-hangul-decompose9.pdf """ phrase = ( - u"\u1100" # HANGUL CHOSEONG KIYEOK (consonant) - u"\u1160" # HANGUL JUNGSEONG FILLER (vowel) + "\u1100" # HANGUL CHOSEONG KIYEOK (consonant) + "\u1160" # HANGUL JUNGSEONG FILLER (vowel) ) expect_length_each = (2, 0) expect_length_phrase = 2 @@ -305,10 +297,10 @@ def test_devanagari_script(): # as a sum of each individual width, as this library currently performs with exception of # ZWJ, but I think it incorrectly gestures what a stateless call to wcwidth.wcwidth of # each codepoint *should* return. - phrase = (u"\u0915" # Akhand, Category 'Lo', East Asian Width property 'N' -- DEVANAGARI LETTER KA - u"\u094D" # Joiner, Category 'Mn', East Asian Width property 'N' -- DEVANAGARI SIGN VIRAMA - u"\u0937" # Fused, Category 'Lo', East Asian Width property 'N' -- DEVANAGARI LETTER SSA - u"\u093F") # MatraL, Category 'Mc', East Asian Width property 'N' -- DEVANAGARI VOWEL SIGN I + phrase = ("\u0915" # Akhand, Category 'Lo', East Asian Width property 'N' -- DEVANAGARI LETTER KA + "\u094D" # Joiner, Category 'Mn', East Asian Width property 'N' -- DEVANAGARI SIGN VIRAMA + "\u0937" # Fused, Category 'Lo', East Asian Width property 'N' -- DEVANAGARI LETTER SSA + "\u093F") # MatraL, Category 'Mc', East Asian Width property 'N' -- DEVANAGARI VOWEL SIGN I # 23107-terminal-suppt.pdf suggests wcwidth.wcwidth should return (2, 0, 0, 1) expect_length_each = (1, 0, 1, 0) # I believe the final width *should* be 3. @@ -325,10 +317,10 @@ def test_devanagari_script(): def test_tamil_script(): # This test adapted from https://www.unicode.org/L2/L2023/23107-terminal-suppt.pdf - phrase = (u"\u0b95" # Akhand, Category 'Lo', East Asian Width property 'N' -- TAMIL LETTER KA - u"\u0bcd" # Joiner, Category 'Mn', East Asian Width property 'N' -- TAMIL SIGN VIRAMA - u"\u0bb7" # Fused, Category 'Lo', East Asian Width property 'N' -- TAMIL LETTER SSA - u"\u0bcc") # MatraLR, Category 'Mc', East Asian Width property 'N' -- TAMIL VOWEL SIGN AU + phrase = ("\u0b95" # Akhand, Category 'Lo', East Asian Width property 'N' -- TAMIL LETTER KA + "\u0bcd" # Joiner, Category 'Mn', East Asian Width property 'N' -- TAMIL SIGN VIRAMA + "\u0bb7" # Fused, Category 'Lo', East Asian Width property 'N' -- TAMIL LETTER SSA + "\u0bcc") # MatraLR, Category 'Mc', East Asian Width property 'N' -- TAMIL VOWEL SIGN AU # 23107-terminal-suppt.pdf suggests wcwidth.wcwidth should return (3, 0, 0, 4) expect_length_each = (1, 0, 1, 0) @@ -348,10 +340,10 @@ def test_kannada_script(): # This test adapted from https://www.unicode.org/L2/L2023/23107-terminal-suppt.pdf # |ರ್ಝೈ| # |123| - phrase = (u"\u0cb0" # Repha, Category 'Lo', East Asian Width property 'N' -- KANNADA LETTER RA - u"\u0ccd" # Joiner, Category 'Mn', East Asian Width property 'N' -- KANNADA SIGN VIRAMA - u"\u0c9d" # Base, Category 'Lo', East Asian Width property 'N' -- KANNADA LETTER JHA - u"\u0cc8") # MatraUR, Category 'Mc', East Asian Width property 'N' -- KANNADA VOWEL SIGN AI + phrase = ("\u0cb0" # Repha, Category 'Lo', East Asian Width property 'N' -- KANNADA LETTER RA + "\u0ccd" # Joiner, Category 'Mn', East Asian Width property 'N' -- KANNADA SIGN VIRAMA + "\u0c9d" # Base, Category 'Lo', East Asian Width property 'N' -- KANNADA LETTER JHA + "\u0cc8") # MatraUR, Category 'Mc', East Asian Width property 'N' -- KANNADA VOWEL SIGN AI # 23107-terminal-suppt.pdf suggests should be (2, 0, 3, 1) expect_length_each = (1, 0, 1, 0) # I believe the correct final width *should* be 3 or 4. @@ -370,10 +362,10 @@ def test_kannada_script_2(): # This test adapted from https://www.unicode.org/L2/L2023/23107-terminal-suppt.pdf # |ರ಼್ಚ| # |12| - phrase = (u"\u0cb0" # Base, Category 'Lo', East Asian Width property 'N' -- KANNADA LETTER RA - u"\u0cbc" # Nukta, Category 'Mn', East Asian Width property 'N' -- KANNADA SIGN NUKTA - u"\u0ccd" # Joiner, Category 'Lo', East Asian Width property 'N' -- KANNADA SIGN VIRAMA - u"\u0c9a") # Subjoin, Category 'Mc', East Asian Width property 'N' -- KANNADA LETTER CA + phrase = ("\u0cb0" # Base, Category 'Lo', East Asian Width property 'N' -- KANNADA LETTER RA + "\u0cbc" # Nukta, Category 'Mn', East Asian Width property 'N' -- KANNADA SIGN NUKTA + "\u0ccd" # Joiner, Category 'Lo', East Asian Width property 'N' -- KANNADA SIGN VIRAMA + "\u0c9a") # Subjoin, Category 'Mc', East Asian Width property 'N' -- KANNADA LETTER CA # 23107-terminal-suppt.pdf suggests wcwidth.wcwidth should return (2, 0, 0, 1) expect_length_each = (1, 0, 0, 1) # I believe the final width is correct, but maybe for the wrong reasons! @@ -392,11 +384,17 @@ def test_zero_wide_conflict(): # Test characters considered both "wide" and "zero" width # - (0x03000, 0x0303e,), # Ideographic Space ..Ideographic Variation In # + (0x03000, 0x03029,), # Ideographic Space ..Hangzhou Numeral Nine - assert wcwidth.wcwidth(unichr(0x03029), unicode_version='4.1.0') == 2 - assert wcwidth.wcwidth(unichr(0x0302a), unicode_version='4.1.0') == 0 + assert wcwidth.wcwidth(chr(0x03029), unicode_version='4.1.0') == 2 + assert wcwidth.wcwidth(chr(0x0302a), unicode_version='4.1.0') == 0 # - (0x03099, 0x030ff,), # Combining Katakana-hirag..Katakana Digraph Koto # + (0x0309b, 0x030ff,), # Katakana-hiragana Voiced..Katakana Digraph Koto - assert wcwidth.wcwidth(unichr(0x03099), unicode_version='4.1.0') == 0 - assert wcwidth.wcwidth(unichr(0x0309a), unicode_version='4.1.0') == 0 - assert wcwidth.wcwidth(unichr(0x0309b), unicode_version='4.1.0') == 2 + assert wcwidth.wcwidth(chr(0x03099), unicode_version='4.1.0') == 0 + assert wcwidth.wcwidth(chr(0x0309a), unicode_version='4.1.0') == 0 + assert wcwidth.wcwidth(chr(0x0309b), unicode_version='4.1.0') == 2 + +def test_soft_hyphen(): + # Test SOFT HYPHEN, category 'Cf' usually are zero-width, but most + # implementations agree to draw it was '1' cell, visually + # indistinguishable from a space, ' ' in Konsole, for example. + assert wcwidth.wcwidth(chr(0x000ad)) == 1 diff --git a/contrib/python/wcwidth/py3/tests/test_emojis.py b/contrib/python/wcwidth/py3/tests/test_emojis.py index 4f88e2330e5..310d0c3d44e 100644 --- a/contrib/python/wcwidth/py3/tests/test_emojis.py +++ b/contrib/python/wcwidth/py3/tests/test_emojis.py @@ -1,22 +1,14 @@ # std imports import os -import codecs # 3rd party import pytest -try: - # python 2 - _ = unichr -except NameError: - # python 3 - unichr = chr - # some tests cannot be done on some builds of python, where the internal # unicode structure is limited to 0x10000 for memory conservation, # "ValueError: unichr() arg not in range(0x10000) (narrow Python build)" try: - unichr(0x2fffe) + chr(0x2fffe) NARROW_ONLY = False except ValueError: NARROW_ONLY = True @@ -27,18 +19,18 @@ import wcwidth def make_sequence_from_line(line): # convert '002A FE0F ; ..' -> (0x2a, 0xfe0f) -> chr(0x2a) + chr(0xfe0f) - return ''.join(unichr(int(cp, 16)) for cp in line.split(';', 1)[0].strip().split()) + return ''.join(chr(int(cp, 16)) for cp in line.split(';', 1)[0].strip().split()) @pytest.mark.skipif(NARROW_ONLY, reason="Test cannot verify on python 'narrow' builds") def emoji_zwj_sequence(): - u""" + """ Emoji zwj sequence of four codepoints is just 2 cells. """ - phrase = (u"\U0001f469" # Base, Category So, East Asian Width property 'W' -- WOMAN - u"\U0001f3fb" # Modifier, Category Sk, East Asian Width property 'W' -- EMOJI MODIFIER FITZPATRICK TYPE-1-2 - u"\u200d" # Joiner, Category Cf, East Asian Width property 'N' -- ZERO WIDTH JOINER - u"\U0001f4bb") # Fused, Category So, East Asian Width peroperty 'W' -- PERSONAL COMPUTER + phrase = ("\U0001f469" # Base, Category So, East Asian Width property 'W' -- WOMAN + "\U0001f3fb" # Modifier, Category Sk, East Asian Width property 'W' -- EMOJI MODIFIER FITZPATRICK TYPE-1-2 + "\u200d" # Joiner, Category Cf, East Asian Width property 'N' -- ZERO WIDTH JOINER + "\U0001f4bb") # Fused, Category So, East Asian Width peroperty 'W' -- PERSONAL COMPUTER # This test adapted from https://www.unicode.org/L2/L2023/23107-terminal-suppt.pdf expect_length_each = (2, 0, 0, 2) expect_length_phrase = 2 @@ -54,12 +46,12 @@ def emoji_zwj_sequence(): @pytest.mark.skipif(NARROW_ONLY, reason="Test cannot verify on python 'narrow' builds") def test_unfinished_zwj_sequence(): - u""" + """ Ensure index-out-of-bounds does not occur for zero-width joiner without any following character """ - phrase = (u"\U0001f469" # Base, Category So, East Asian Width property 'W' -- WOMAN - u"\U0001f3fb" # Modifier, Category Sk, East Asian Width property 'W' -- EMOJI MODIFIER FITZPATRICK TYPE-1-2 - u"\u200d") # Joiner, Category Cf, East Asian Width property 'N' -- ZERO WIDTH JOINER + phrase = ("\U0001f469" # Base, Category So, East Asian Width property 'W' -- WOMAN + "\U0001f3fb" # Modifier, Category Sk, East Asian Width property 'W' -- EMOJI MODIFIER FITZPATRICK TYPE-1-2 + "\u200d") # Joiner, Category Cf, East Asian Width property 'N' -- ZERO WIDTH JOINER expect_length_each = (2, 0, 0) expect_length_phrase = 2 @@ -77,9 +69,9 @@ def test_non_recommended_zwj_sequence(): """ Verify ZWJ is measured as though successful with characters that cannot be joined, wcwidth does not verify """ - phrase = (u"\U0001f469" # Base, Category So, East Asian Width property 'W' -- WOMAN - u"\U0001f3fb" # Modifier, Category Sk, East Asian Width property 'W' -- EMOJI MODIFIER FITZPATRICK TYPE-1-2 - u"\u200d") # Joiner, Category Cf, East Asian Width property 'N' -- ZERO WIDTH JOINER + phrase = ("\U0001f469" # Base, Category So, East Asian Width property 'W' -- WOMAN + "\U0001f3fb" # Modifier, Category Sk, East Asian Width property 'W' -- EMOJI MODIFIER FITZPATRICK TYPE-1-2 + "\u200d") # Joiner, Category Cf, East Asian Width property 'N' -- ZERO WIDTH JOINER expect_length_each = (2, 0, 0) expect_length_phrase = 2 @@ -95,11 +87,11 @@ def test_non_recommended_zwj_sequence(): @pytest.mark.skipif(NARROW_ONLY, reason="Test cannot verify on python 'narrow' builds") def test_another_emoji_zwj_sequence(): phrase = ( - u"\u26F9" # PERSON WITH BALL - u"\U0001F3FB" # EMOJI MODIFIER FITZPATRICK TYPE-1-2 - u"\u200D" # ZERO WIDTH JOINER - u"\u2640" # FEMALE SIGN - u"\uFE0F") # VARIATION SELECTOR-16 + "\u26F9" # PERSON WITH BALL + "\U0001F3FB" # EMOJI MODIFIER FITZPATRICK TYPE-1-2 + "\u200D" # ZERO WIDTH JOINER + "\u2640" # FEMALE SIGN + "\uFE0F") # VARIATION SELECTOR-16 expect_length_each = (1, 0, 0, 1, 0) expect_length_phrase = 2 @@ -121,17 +113,17 @@ def test_longer_emoji_zwj_sequence(): in a single function call. """ # 'Category Code', 'East Asian Width property' -- 'description' - phrase = (u"\U0001F9D1" # 'So', 'W' -- ADULT - u"\U0001F3FB" # 'Sk', 'W' -- EMOJI MODIFIER FITZPATRICK TYPE-1-2 - u"\u200d" # 'Cf', 'N' -- ZERO WIDTH JOINER - u"\u2764" # 'So', 'N' -- HEAVY BLACK HEART - u"\uFE0F" # 'Mn', 'A' -- VARIATION SELECTOR-16 - u"\u200d" # 'Cf', 'N' -- ZERO WIDTH JOINER - u"\U0001F48B" # 'So', 'W' -- KISS MARK - u"\u200d" # 'Cf', 'N' -- ZERO WIDTH JOINER - u"\U0001F9D1" # 'So', 'W' -- ADULT - u"\U0001F3FD" # 'Sk', 'W' -- EMOJI MODIFIER FITZPATRICK TYPE-4 - ) * 2 + phrase = ("\U0001F9D1" # 'So', 'W' -- ADULT + "\U0001F3FB" # 'Sk', 'W' -- EMOJI MODIFIER FITZPATRICK TYPE-1-2 + "\u200d" # 'Cf', 'N' -- ZERO WIDTH JOINER + "\u2764" # 'So', 'N' -- HEAVY BLACK HEART + "\uFE0F" # 'Mn', 'A' -- VARIATION SELECTOR-16 + "\u200d" # 'Cf', 'N' -- ZERO WIDTH JOINER + "\U0001F48B" # 'So', 'W' -- KISS MARK + "\u200d" # 'Cf', 'N' -- ZERO WIDTH JOINER + "\U0001F9D1" # 'So', 'W' -- ADULT + "\U0001F3FD" # 'Sk', 'W' -- EMOJI MODIFIER FITZPATRICK TYPE-4 + ) * 2 # This test adapted from https://www.unicode.org/L2/L2023/23107-terminal-suppt.pdf expect_length_each = (2, 0, 0, 1, 0, 0, 2, 0, 2, 0) * 2 expect_length_phrase = 4 @@ -146,10 +138,10 @@ def test_longer_emoji_zwj_sequence(): def read_sequences_from_file(filename): - fp = codecs.open(os.path.join(os.path.dirname(__file__), filename), 'r', encoding='utf-8') + fp = open(os.path.join(os.path.dirname(__file__), filename), 'r', encoding='utf-8') lines = [line.strip() - for line in fp.readlines() - if not line.startswith('#') and line.strip()] + for line in fp.readlines() + if not line.startswith('#') and line.strip()] fp.close() sequences = [make_sequence_from_line(line) for line in lines] return lines, sequences @@ -212,8 +204,8 @@ def test_recommended_variation_16_sequences(): def test_unicode_9_vs16(): """Verify effect of VS-16 on unicode_version 9.0 and later""" - phrase = (u"\u2640" # FEMALE SIGN - u"\uFE0F") # VARIATION SELECTOR-16 + phrase = ("\u2640" # FEMALE SIGN + "\uFE0F") # VARIATION SELECTOR-16 expect_length_each = (1, 0) expect_length_phrase = 2 @@ -226,10 +218,11 @@ def test_unicode_9_vs16(): assert length_each == expect_length_each assert length_phrase == expect_length_phrase + def test_unicode_8_vs16(): """Verify that VS-16 has no effect on unicode_version 8.0 and earler""" - phrase = (u"\u2640" # FEMALE SIGN - u"\uFE0F") # VARIATION SELECTOR-16 + phrase = ("\u2640" # FEMALE SIGN + "\uFE0F") # VARIATION SELECTOR-16 expect_length_each = (1, 0) expect_length_phrase = 1 @@ -240,4 +233,4 @@ def test_unicode_8_vs16(): # verify. assert length_each == expect_length_each - assert length_phrase == expect_length_phrase
\ No newline at end of file + assert length_phrase == expect_length_phrase diff --git a/contrib/python/wcwidth/py3/tests/test_table_integrity.py b/contrib/python/wcwidth/py3/tests/test_table_integrity.py index 66e63ddbe3f..e680498162a 100644 --- a/contrib/python/wcwidth/py3/tests/test_table_integrity.py +++ b/contrib/python/wcwidth/py3/tests/test_table_integrity.py @@ -1,15 +1,18 @@ """ Executes verify-table-integrity.py as a unit test. """ +# std imports import os import sys import subprocess +# 3rd party import pytest + @pytest.mark.skipif(sys.version_info[:2] != (3, 12), reason='Test only with a single version of python') def test_verify_table_integrity(): subprocess.check_output([sys.executable, os.path.join(os.path.dirname(__file__), os.path.pardir, 'bin', - 'verify-table-integrity.py')])
\ No newline at end of file + 'verify-table-integrity.py')]) diff --git a/contrib/python/wcwidth/py3/tests/test_ucslevel.py b/contrib/python/wcwidth/py3/tests/test_ucslevel.py index 654e835fc72..b15fb5f5a71 100644 --- a/contrib/python/wcwidth/py3/tests/test_ucslevel.py +++ b/contrib/python/wcwidth/py3/tests/test_ucslevel.py @@ -1,4 +1,3 @@ -# coding: utf-8 """Unicode version level tests for wcwidth.""" # std imports import warnings @@ -37,7 +36,7 @@ def test_exact_410_str(): def test_exact_410_unicode(): """wcwidth._wcmatch_version(u'4.1.0') returns equal value (unicode).""" # given, - given = expected = u'4.1.0' + given = expected = '4.1.0' # exercise, result = wcwidth._wcmatch_version(given) @@ -61,7 +60,7 @@ def test_nearest_505_str(): def test_nearest_505_unicode(): """wcwidth._wcmatch_version(u'5.0.5') returns nearest u'5.0.0'. (unicode)""" # given - given, expected = u'5.0.5', u'5.0.0' + given, expected = '5.0.5', '5.0.0' # exercise result = wcwidth._wcmatch_version(given) @@ -89,7 +88,7 @@ def test_nearest_lowint40_str(): def test_nearest_lowint40_unicode(): """wcwidth._wcmatch_version(u'4.0') returns nearest u'4.1.0'.""" # given - given, expected = u'4.0', u'4.1.0' + given, expected = '4.0', '4.1.0' warnings.resetwarnings() wcwidth._wcmatch_version.cache_clear() @@ -117,7 +116,7 @@ def test_nearest_800_str(): def test_nearest_800_unicode(): """wcwidth._wcmatch_version(u'8') returns nearest u'8.0.0'.""" # given - given, expected = u'8', u'8.0.0' + given, expected = '8', '8.0.0' # exercise result = wcwidth._wcmatch_version(given) @@ -141,7 +140,7 @@ def test_nearest_999_str(): def test_nearest_999_unicode(): """wcwidth._wcmatch_version(u'999.0') returns nearest (latest).""" # given - given, expected = u'999.0', wcwidth.list_versions()[-1] + given, expected = '999.0', wcwidth.list_versions()[-1] # exercise result = wcwidth._wcmatch_version(given) @@ -153,7 +152,7 @@ def test_nearest_999_unicode(): def test_nonint_unicode(): """wcwidth._wcmatch_version(u'x.y.z') returns latest (unicode).""" # given - given, expected = u'x.y.z', wcwidth.list_versions()[-1] + given, expected = 'x.y.z', wcwidth.list_versions()[-1] warnings.resetwarnings() wcwidth._wcmatch_version.cache_clear() diff --git a/contrib/python/wcwidth/py3/wcwidth/__init__.py b/contrib/python/wcwidth/py3/wcwidth/__init__.py index d686b30e1b6..e4e81380913 100644 --- a/contrib/python/wcwidth/py3/wcwidth/__init__.py +++ b/contrib/python/wcwidth/py3/wcwidth/__init__.py @@ -26,4 +26,4 @@ __all__ = ('wcwidth', 'wcswidth', 'list_versions') # We also used pkg_resources to load unicode version tables from version.json, # generated by bin/update-tables.py, but some environments are unable to # import pkg_resources for one reason or another, yikes! -__version__ = '0.2.13' +__version__ = '0.2.14' diff --git a/contrib/python/wcwidth/py3/wcwidth/table_vs15.py b/contrib/python/wcwidth/py3/wcwidth/table_vs15.py new file mode 100644 index 00000000000..a5ede6f961e --- /dev/null +++ b/contrib/python/wcwidth/py3/wcwidth/table_vs15.py @@ -0,0 +1,103 @@ +""" +Exports VS15_WIDE_TO_NARROW table keyed by supporting unicode version level. + +This code generated by wcwidth/bin/update-tables.py on 2024-02-14 19:59:22 UTC. +""" +VS15_WIDE_TO_NARROW = { + '9.0.0': ( + # Source: 9.0.0 + # Date: 2023-02-01, 02:22:54 GMT + # + (0x0231a, 0x0231b,), # Watch ..Hourglass + (0x023e9, 0x023ec,), # Black Right-pointing Dou..Black Down-pointing Doub + (0x023f0, 0x023f0,), # Alarm Clock + (0x023f3, 0x023f3,), # Hourglass With Flowing Sand + (0x025fd, 0x025fe,), # White Medium Small Squar..Black Medium Small Squar + (0x02614, 0x02615,), # Umbrella With Rain Drops..Hot Beverage + (0x02648, 0x02653,), # Aries ..Pisces + (0x0267f, 0x0267f,), # Wheelchair Symbol + (0x02693, 0x02693,), # Anchor + (0x026a1, 0x026a1,), # High Voltage Sign + (0x026aa, 0x026ab,), # Medium White Circle ..Medium Black Circle + (0x026bd, 0x026be,), # Soccer Ball ..Baseball + (0x026c4, 0x026c5,), # Snowman Without Snow ..Sun Behind Cloud + (0x026ce, 0x026ce,), # Ophiuchus + (0x026d4, 0x026d4,), # No Entry + (0x026ea, 0x026ea,), # Church + (0x026f2, 0x026f3,), # Fountain ..Flag In Hole + (0x026f5, 0x026f5,), # Sailboat + (0x026fa, 0x026fa,), # Tent + (0x026fd, 0x026fd,), # Fuel Pump + (0x02705, 0x02705,), # White Heavy Check Mark + (0x0270a, 0x0270b,), # Raised Fist ..Raised Hand + (0x02728, 0x02728,), # Sparkles + (0x0274c, 0x0274c,), # Cross Mark + (0x0274e, 0x0274e,), # Negative Squared Cross Mark + (0x02753, 0x02755,), # Black Question Mark Orna..White Exclamation Mark O + (0x02757, 0x02757,), # Heavy Exclamation Mark Symbol + (0x02795, 0x02797,), # Heavy Plus Sign ..Heavy Division Sign + (0x027b0, 0x027b0,), # Curly Loop + (0x027bf, 0x027bf,), # Double Curly Loop + (0x02b1b, 0x02b1c,), # Black Large Square ..White Large Square + (0x02b50, 0x02b50,), # White Medium Star + (0x02b55, 0x02b55,), # Heavy Large Circle + (0x03030, 0x03030,), # Wavy Dash + (0x0303d, 0x0303d,), # Part Alternation Mark + (0x03297, 0x03297,), # Circled Ideograph Congratulation + (0x03299, 0x03299,), # Circled Ideograph Secret + (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon + (0x1f202, 0x1f202,), # Squared Katakana Sa + (0x1f21a, 0x1f21a,), # Squared Cjk Unified Ideograph-7121 + (0x1f22f, 0x1f22f,), # Squared Cjk Unified Ideograph-6307 + (0x1f237, 0x1f237,), # Squared Cjk Unified Ideograph-6708 + (0x1f30d, 0x1f30f,), # Earth Globe Europe-afric..Earth Globe Asia-austral + (0x1f315, 0x1f315,), # Full Moon Symbol + (0x1f31c, 0x1f31c,), # Last Quarter Moon With Face + (0x1f378, 0x1f378,), # Cocktail Glass + (0x1f393, 0x1f393,), # Graduation Cap + (0x1f3a7, 0x1f3a7,), # Headphone + (0x1f3ac, 0x1f3ae,), # Clapper Board ..Video Game + (0x1f3c2, 0x1f3c2,), # Snowboarder + (0x1f3c4, 0x1f3c4,), # Surfer + (0x1f3c6, 0x1f3c6,), # Trophy + (0x1f3ca, 0x1f3ca,), # Swimmer + (0x1f3e0, 0x1f3e0,), # House Building + (0x1f3ed, 0x1f3ed,), # Factory + (0x1f408, 0x1f408,), # Cat + (0x1f415, 0x1f415,), # Dog + (0x1f41f, 0x1f41f,), # Fish + (0x1f426, 0x1f426,), # Bird + (0x1f442, 0x1f442,), # Ear + (0x1f446, 0x1f449,), # White Up Pointing Backha..White Right Pointing Bac + (0x1f44d, 0x1f44e,), # Thumbs Up Sign ..Thumbs Down Sign + (0x1f453, 0x1f453,), # Eyeglasses + (0x1f46a, 0x1f46a,), # Family + (0x1f47d, 0x1f47d,), # Extraterrestrial Alien + (0x1f4a3, 0x1f4a3,), # Bomb + (0x1f4b0, 0x1f4b0,), # Money Bag + (0x1f4b3, 0x1f4b3,), # Credit Card + (0x1f4bb, 0x1f4bb,), # Personal Computer + (0x1f4bf, 0x1f4bf,), # Optical Disc + (0x1f4cb, 0x1f4cb,), # Clipboard + (0x1f4da, 0x1f4da,), # Books + (0x1f4df, 0x1f4df,), # Pager + (0x1f4e4, 0x1f4e6,), # Outbox Tray ..Package + (0x1f4ea, 0x1f4ed,), # Closed Mailbox With Lowe..Open Mailbox With Lowere + (0x1f4f7, 0x1f4f7,), # Camera + (0x1f4f9, 0x1f4fb,), # Video Camera ..Radio + (0x1f508, 0x1f508,), # Speaker + (0x1f50d, 0x1f50d,), # Left-pointing Magnifying Glass + (0x1f512, 0x1f513,), # Lock ..Open Lock + (0x1f550, 0x1f567,), # Clock Face One Oclock ..Clock Face Twelve-thirty + (0x1f610, 0x1f610,), # Neutral Face + (0x1f687, 0x1f687,), # Metro + (0x1f68d, 0x1f68d,), # Oncoming Bus + (0x1f691, 0x1f691,), # Ambulance + (0x1f694, 0x1f694,), # Oncoming Police Car + (0x1f698, 0x1f698,), # Oncoming Automobile + (0x1f6ad, 0x1f6ad,), # No Smoking Symbol + (0x1f6b2, 0x1f6b2,), # Bicycle + (0x1f6b9, 0x1f6ba,), # Mens Symbol ..Womens Symbol + (0x1f6bc, 0x1f6bc,), # Baby Symbol + ), +} diff --git a/contrib/python/wcwidth/py3/wcwidth/table_vs16.py b/contrib/python/wcwidth/py3/wcwidth/table_vs16.py index 3249262d981..1ca25c66368 100644 --- a/contrib/python/wcwidth/py3/wcwidth/table_vs16.py +++ b/contrib/python/wcwidth/py3/wcwidth/table_vs16.py @@ -1,12 +1,12 @@ """ Exports VS16_NARROW_TO_WIDE table keyed by supporting unicode version level. -This code generated by wcwidth/bin/update-tables.py on 2023-11-07 16:43:49 UTC. +This code generated by wcwidth/bin/update-tables.py on 2025-09-15 16:57:50 UTC. """ VS16_NARROW_TO_WIDE = { '9.0.0': ( # Source: 9.0.0 - # Date: 2023-02-01, 02:22:54 GMT + # Date: 2025-01-30, 21:48:29 GMT # (0x00023, 0x00023,), # Number Sign (0x0002a, 0x0002a,), # Asterisk diff --git a/contrib/python/wcwidth/py3/wcwidth/table_wide.py b/contrib/python/wcwidth/py3/wcwidth/table_wide.py index bd6dfdd82a0..5139b1f0d3b 100644 --- a/contrib/python/wcwidth/py3/wcwidth/table_wide.py +++ b/contrib/python/wcwidth/py3/wcwidth/table_wide.py @@ -1,7 +1,7 @@ """ Exports WIDE_EASTASIAN table keyed by supporting unicode version level. -This code generated by wcwidth/bin/update-tables.py on 2024-01-06 01:39:49 UTC. +This code generated by wcwidth/bin/update-tables.py on 2025-09-19 15:55:08 UTC. """ WIDE_EASTASIAN = { '4.1.0': ( @@ -1413,7 +1413,7 @@ WIDE_EASTASIAN = { (0x03105, 0x0312f,), # Bopomofo Letter B ..Bopomofo Letter Nn (0x03131, 0x0318e,), # Hangul Letter Kiyeok ..Hangul Letter Araeae (0x03190, 0x031e3,), # Ideographic Annotation L..Cjk Stroke Q - (0x031ef, 0x0321e,), # (nil) ..Parenthesized Korean Cha + (0x031ef, 0x0321e,), # Ideographic Description ..Parenthesized Korean Cha (0x03220, 0x03247,), # Parenthesized Ideograph ..Circled Ideograph Koto (0x03250, 0x04dbf,), # Partnership Sign ..Cjk Unified Ideograph-4d (0x04e00, 0x0a48c,), # Cjk Unified Ideograph-4e..Yi Syllable Yyr @@ -1490,4 +1490,262 @@ WIDE_EASTASIAN = { (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), + '16.0.0': ( + # Source: EastAsianWidth-16.0.0.txt + # Date: 2024-04-30, 21:48:20 GMT + # + (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler + (0x0231a, 0x0231b,), # Watch ..Hourglass + (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra + (0x023e9, 0x023ec,), # Black Right-pointing Dou..Black Down-pointing Doub + (0x023f0, 0x023f0,), # Alarm Clock + (0x023f3, 0x023f3,), # Hourglass With Flowing Sand + (0x025fd, 0x025fe,), # White Medium Small Squar..Black Medium Small Squar + (0x02614, 0x02615,), # Umbrella With Rain Drops..Hot Beverage + (0x02630, 0x02637,), # Trigram For Heaven ..Trigram For Earth + (0x02648, 0x02653,), # Aries ..Pisces + (0x0267f, 0x0267f,), # Wheelchair Symbol + (0x0268a, 0x0268f,), # Monogram For Yang ..Digram For Greater Yin + (0x02693, 0x02693,), # Anchor + (0x026a1, 0x026a1,), # High Voltage Sign + (0x026aa, 0x026ab,), # Medium White Circle ..Medium Black Circle + (0x026bd, 0x026be,), # Soccer Ball ..Baseball + (0x026c4, 0x026c5,), # Snowman Without Snow ..Sun Behind Cloud + (0x026ce, 0x026ce,), # Ophiuchus + (0x026d4, 0x026d4,), # No Entry + (0x026ea, 0x026ea,), # Church + (0x026f2, 0x026f3,), # Fountain ..Flag In Hole + (0x026f5, 0x026f5,), # Sailboat + (0x026fa, 0x026fa,), # Tent + (0x026fd, 0x026fd,), # Fuel Pump + (0x02705, 0x02705,), # White Heavy Check Mark + (0x0270a, 0x0270b,), # Raised Fist ..Raised Hand + (0x02728, 0x02728,), # Sparkles + (0x0274c, 0x0274c,), # Cross Mark + (0x0274e, 0x0274e,), # Negative Squared Cross Mark + (0x02753, 0x02755,), # Black Question Mark Orna..White Exclamation Mark O + (0x02757, 0x02757,), # Heavy Exclamation Mark Symbol + (0x02795, 0x02797,), # Heavy Plus Sign ..Heavy Division Sign + (0x027b0, 0x027b0,), # Curly Loop + (0x027bf, 0x027bf,), # Double Curly Loop + (0x02b1b, 0x02b1c,), # Black Large Square ..White Large Square + (0x02b50, 0x02b50,), # White Medium Star + (0x02b55, 0x02b55,), # Heavy Large Circle + (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap + (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified + (0x02f00, 0x02fd5,), # Kangxi Radical One ..Kangxi Radical Flute + (0x02ff0, 0x03029,), # Ideographic Description ..Hangzhou Numeral Nine + (0x03030, 0x0303e,), # Wavy Dash ..Ideographic Variation In + (0x03041, 0x03096,), # Hiragana Letter Small A ..Hiragana Letter Small Ke + (0x0309b, 0x030ff,), # Katakana-hiragana Voiced..Katakana Digraph Koto + (0x03105, 0x0312f,), # Bopomofo Letter B ..Bopomofo Letter Nn + (0x03131, 0x0318e,), # Hangul Letter Kiyeok ..Hangul Letter Araeae + (0x03190, 0x031e5,), # Ideographic Annotation L..(nil) + (0x031ef, 0x0321e,), # Ideographic Description ..Parenthesized Korean Cha + (0x03220, 0x03247,), # Parenthesized Ideograph ..Circled Ideograph Koto + (0x03250, 0x0a48c,), # Partnership Sign ..Yi Syllable Yyr + (0x0a490, 0x0a4c6,), # Yi Radical Qot ..Yi Radical Ke + (0x0a960, 0x0a97c,), # Hangul Choseong Tikeut-m..Hangul Choseong Ssangyeo + (0x0ac00, 0x0d7a3,), # Hangul Syllable Ga ..Hangul Syllable Hih + (0x0f900, 0x0faff,), # Cjk Compatibility Ideogr..(nil) + (0x0fe10, 0x0fe19,), # Presentation Form For Ve..Presentation Form For Ve + (0x0fe30, 0x0fe52,), # Presentation Form For Ve..Small Full Stop + (0x0fe54, 0x0fe66,), # Small Semicolon ..Small Equals Sign + (0x0fe68, 0x0fe6b,), # Small Reverse Solidus ..Small Commercial At + (0x0ff01, 0x0ff60,), # Fullwidth Exclamation Ma..Fullwidth Right White Pa + (0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign + (0x16fe0, 0x16fe3,), # Tangut Iteration Mark ..Old Chinese Iteration Ma + (0x17000, 0x187f7,), # (nil) + (0x18800, 0x18cd5,), # Tangut Component-001 ..Khitan Small Script Char + (0x18cff, 0x18d08,), # (nil) + (0x1aff0, 0x1aff3,), # Katakana Letter Minnan T..Katakana Letter Minnan T + (0x1aff5, 0x1affb,), # Katakana Letter Minnan T..Katakana Letter Minnan N + (0x1affd, 0x1affe,), # Katakana Letter Minnan N..Katakana Letter Minnan N + (0x1b000, 0x1b122,), # Katakana Letter Archaic ..Katakana Letter Archaic + (0x1b132, 0x1b132,), # Hiragana Letter Small Ko + (0x1b150, 0x1b152,), # Hiragana Letter Small Wi..Hiragana Letter Small Wo + (0x1b155, 0x1b155,), # Katakana Letter Small Ko + (0x1b164, 0x1b167,), # Katakana Letter Small Wi..Katakana Letter Small N + (0x1b170, 0x1b2fb,), # Nushu Character-1b170 ..Nushu Character-1b2fb + (0x1d300, 0x1d356,), # Monogram For Earth ..Tetragram For Fostering + (0x1d360, 0x1d376,), # Counting Rod Unit Digit ..Ideographic Tally Mark F + (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon + (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker + (0x1f18e, 0x1f18e,), # Negative Squared Ab + (0x1f191, 0x1f19a,), # Squared Cl ..Squared Vs + (0x1f200, 0x1f202,), # Square Hiragana Hoka ..Squared Katakana Sa + (0x1f210, 0x1f23b,), # Squared Cjk Unified Ideo..Squared Cjk Unified Ideo + (0x1f240, 0x1f248,), # Tortoise Shell Bracketed..Tortoise Shell Bracketed + (0x1f250, 0x1f251,), # Circled Ideograph Advant..Circled Ideograph Accept + (0x1f260, 0x1f265,), # Rounded Symbol For Fu ..Rounded Symbol For Cai + (0x1f300, 0x1f320,), # Cyclone ..Shooting Star + (0x1f32d, 0x1f335,), # Hot Dog ..Cactus + (0x1f337, 0x1f37c,), # Tulip ..Baby Bottle + (0x1f37e, 0x1f393,), # Bottle With Popping Cork..Graduation Cap + (0x1f3a0, 0x1f3ca,), # Carousel Horse ..Swimmer + (0x1f3cf, 0x1f3d3,), # Cricket Bat And Ball ..Table Tennis Paddle And + (0x1f3e0, 0x1f3f0,), # House Building ..European Castle + (0x1f3f4, 0x1f3f4,), # Waving Black Flag + (0x1f3f8, 0x1f3fa,), # Badminton Racquet And Sh..Amphora + (0x1f400, 0x1f43e,), # Rat ..Paw Prints + (0x1f440, 0x1f440,), # Eyes + (0x1f442, 0x1f4fc,), # Ear ..Videocassette + (0x1f4ff, 0x1f53d,), # Prayer Beads ..Down-pointing Small Red + (0x1f54b, 0x1f54e,), # Kaaba ..Menorah With Nine Branch + (0x1f550, 0x1f567,), # Clock Face One Oclock ..Clock Face Twelve-thirty + (0x1f57a, 0x1f57a,), # Man Dancing + (0x1f595, 0x1f596,), # Reversed Hand With Middl..Raised Hand With Part Be + (0x1f5a4, 0x1f5a4,), # Black Heart + (0x1f5fb, 0x1f64f,), # Mount Fuji ..Person With Folded Hands + (0x1f680, 0x1f6c5,), # Rocket ..Left Luggage + (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation + (0x1f6d0, 0x1f6d2,), # Place Of Worship ..Shopping Trolley + (0x1f6d5, 0x1f6d7,), # Hindu Temple ..Elevator + (0x1f6dc, 0x1f6df,), # Wireless ..Ring Buoy + (0x1f6eb, 0x1f6ec,), # Airplane Departure ..Airplane Arriving + (0x1f6f4, 0x1f6fc,), # Scooter ..Roller Skate + (0x1f7e0, 0x1f7eb,), # Large Orange Circle ..Large Brown Square + (0x1f7f0, 0x1f7f0,), # Heavy Equals Sign + (0x1f90c, 0x1f93a,), # Pinched Fingers ..Fencer + (0x1f93c, 0x1f945,), # Wrestlers ..Goal Net + (0x1f947, 0x1f9ff,), # First Place Medal ..Nazar Amulet + (0x1fa70, 0x1fa7c,), # Ballet Shoes ..Crutch + (0x1fa80, 0x1fa89,), # Yo-yo ..(nil) + (0x1fa8f, 0x1fac6,), # (nil) + (0x1face, 0x1fadc,), # Moose ..(nil) + (0x1fadf, 0x1fae9,), # (nil) + (0x1faf0, 0x1faf8,), # Hand With Index Finger A..Rightwards Pushing Hand + (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) + (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) + ), + '17.0.0': ( + # Source: EastAsianWidth-17.0.0.txt + # Date: 2025-07-24, 00:12:54 GMT + # + (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler + (0x0231a, 0x0231b,), # Watch ..Hourglass + (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra + (0x023e9, 0x023ec,), # Black Right-pointing Dou..Black Down-pointing Doub + (0x023f0, 0x023f0,), # Alarm Clock + (0x023f3, 0x023f3,), # Hourglass With Flowing Sand + (0x025fd, 0x025fe,), # White Medium Small Squar..Black Medium Small Squar + (0x02614, 0x02615,), # Umbrella With Rain Drops..Hot Beverage + (0x02630, 0x02637,), # Trigram For Heaven ..Trigram For Earth + (0x02648, 0x02653,), # Aries ..Pisces + (0x0267f, 0x0267f,), # Wheelchair Symbol + (0x0268a, 0x0268f,), # Monogram For Yang ..Digram For Greater Yin + (0x02693, 0x02693,), # Anchor + (0x026a1, 0x026a1,), # High Voltage Sign + (0x026aa, 0x026ab,), # Medium White Circle ..Medium Black Circle + (0x026bd, 0x026be,), # Soccer Ball ..Baseball + (0x026c4, 0x026c5,), # Snowman Without Snow ..Sun Behind Cloud + (0x026ce, 0x026ce,), # Ophiuchus + (0x026d4, 0x026d4,), # No Entry + (0x026ea, 0x026ea,), # Church + (0x026f2, 0x026f3,), # Fountain ..Flag In Hole + (0x026f5, 0x026f5,), # Sailboat + (0x026fa, 0x026fa,), # Tent + (0x026fd, 0x026fd,), # Fuel Pump + (0x02705, 0x02705,), # White Heavy Check Mark + (0x0270a, 0x0270b,), # Raised Fist ..Raised Hand + (0x02728, 0x02728,), # Sparkles + (0x0274c, 0x0274c,), # Cross Mark + (0x0274e, 0x0274e,), # Negative Squared Cross Mark + (0x02753, 0x02755,), # Black Question Mark Orna..White Exclamation Mark O + (0x02757, 0x02757,), # Heavy Exclamation Mark Symbol + (0x02795, 0x02797,), # Heavy Plus Sign ..Heavy Division Sign + (0x027b0, 0x027b0,), # Curly Loop + (0x027bf, 0x027bf,), # Double Curly Loop + (0x02b1b, 0x02b1c,), # Black Large Square ..White Large Square + (0x02b50, 0x02b50,), # White Medium Star + (0x02b55, 0x02b55,), # Heavy Large Circle + (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap + (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified + (0x02f00, 0x02fd5,), # Kangxi Radical One ..Kangxi Radical Flute + (0x02ff0, 0x03029,), # Ideographic Description ..Hangzhou Numeral Nine + (0x03030, 0x0303e,), # Wavy Dash ..Ideographic Variation In + (0x03041, 0x03096,), # Hiragana Letter Small A ..Hiragana Letter Small Ke + (0x0309b, 0x030ff,), # Katakana-hiragana Voiced..Katakana Digraph Koto + (0x03105, 0x0312f,), # Bopomofo Letter B ..Bopomofo Letter Nn + (0x03131, 0x0318e,), # Hangul Letter Kiyeok ..Hangul Letter Araeae + (0x03190, 0x031e5,), # Ideographic Annotation L..(nil) + (0x031ef, 0x0321e,), # Ideographic Description ..Parenthesized Korean Cha + (0x03220, 0x03247,), # Parenthesized Ideograph ..Circled Ideograph Koto + (0x03250, 0x0a48c,), # Partnership Sign ..Yi Syllable Yyr + (0x0a490, 0x0a4c6,), # Yi Radical Qot ..Yi Radical Ke + (0x0a960, 0x0a97c,), # Hangul Choseong Tikeut-m..Hangul Choseong Ssangyeo + (0x0ac00, 0x0d7a3,), # Hangul Syllable Ga ..Hangul Syllable Hih + (0x0f900, 0x0faff,), # Cjk Compatibility Ideogr..(nil) + (0x0fe10, 0x0fe19,), # Presentation Form For Ve..Presentation Form For Ve + (0x0fe30, 0x0fe52,), # Presentation Form For Ve..Small Full Stop + (0x0fe54, 0x0fe66,), # Small Semicolon ..Small Equals Sign + (0x0fe68, 0x0fe6b,), # Small Reverse Solidus ..Small Commercial At + (0x0ff01, 0x0ff60,), # Fullwidth Exclamation Ma..Fullwidth Right White Pa + (0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign + (0x16fe0, 0x16fe3,), # Tangut Iteration Mark ..Old Chinese Iteration Ma + (0x16ff2, 0x16ff6,), # (nil) + (0x17000, 0x18cd5,), # (nil) ..Khitan Small Script Char + (0x18cff, 0x18d1e,), # (nil) + (0x18d80, 0x18df2,), # (nil) + (0x1aff0, 0x1aff3,), # Katakana Letter Minnan T..Katakana Letter Minnan T + (0x1aff5, 0x1affb,), # Katakana Letter Minnan T..Katakana Letter Minnan N + (0x1affd, 0x1affe,), # Katakana Letter Minnan N..Katakana Letter Minnan N + (0x1b000, 0x1b122,), # Katakana Letter Archaic ..Katakana Letter Archaic + (0x1b132, 0x1b132,), # Hiragana Letter Small Ko + (0x1b150, 0x1b152,), # Hiragana Letter Small Wi..Hiragana Letter Small Wo + (0x1b155, 0x1b155,), # Katakana Letter Small Ko + (0x1b164, 0x1b167,), # Katakana Letter Small Wi..Katakana Letter Small N + (0x1b170, 0x1b2fb,), # Nushu Character-1b170 ..Nushu Character-1b2fb + (0x1d300, 0x1d356,), # Monogram For Earth ..Tetragram For Fostering + (0x1d360, 0x1d376,), # Counting Rod Unit Digit ..Ideographic Tally Mark F + (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon + (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker + (0x1f18e, 0x1f18e,), # Negative Squared Ab + (0x1f191, 0x1f19a,), # Squared Cl ..Squared Vs + (0x1f200, 0x1f202,), # Square Hiragana Hoka ..Squared Katakana Sa + (0x1f210, 0x1f23b,), # Squared Cjk Unified Ideo..Squared Cjk Unified Ideo + (0x1f240, 0x1f248,), # Tortoise Shell Bracketed..Tortoise Shell Bracketed + (0x1f250, 0x1f251,), # Circled Ideograph Advant..Circled Ideograph Accept + (0x1f260, 0x1f265,), # Rounded Symbol For Fu ..Rounded Symbol For Cai + (0x1f300, 0x1f320,), # Cyclone ..Shooting Star + (0x1f32d, 0x1f335,), # Hot Dog ..Cactus + (0x1f337, 0x1f37c,), # Tulip ..Baby Bottle + (0x1f37e, 0x1f393,), # Bottle With Popping Cork..Graduation Cap + (0x1f3a0, 0x1f3ca,), # Carousel Horse ..Swimmer + (0x1f3cf, 0x1f3d3,), # Cricket Bat And Ball ..Table Tennis Paddle And + (0x1f3e0, 0x1f3f0,), # House Building ..European Castle + (0x1f3f4, 0x1f3f4,), # Waving Black Flag + (0x1f3f8, 0x1f3fa,), # Badminton Racquet And Sh..Amphora + (0x1f400, 0x1f43e,), # Rat ..Paw Prints + (0x1f440, 0x1f440,), # Eyes + (0x1f442, 0x1f4fc,), # Ear ..Videocassette + (0x1f4ff, 0x1f53d,), # Prayer Beads ..Down-pointing Small Red + (0x1f54b, 0x1f54e,), # Kaaba ..Menorah With Nine Branch + (0x1f550, 0x1f567,), # Clock Face One Oclock ..Clock Face Twelve-thirty + (0x1f57a, 0x1f57a,), # Man Dancing + (0x1f595, 0x1f596,), # Reversed Hand With Middl..Raised Hand With Part Be + (0x1f5a4, 0x1f5a4,), # Black Heart + (0x1f5fb, 0x1f64f,), # Mount Fuji ..Person With Folded Hands + (0x1f680, 0x1f6c5,), # Rocket ..Left Luggage + (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation + (0x1f6d0, 0x1f6d2,), # Place Of Worship ..Shopping Trolley + (0x1f6d5, 0x1f6d8,), # Hindu Temple ..(nil) + (0x1f6dc, 0x1f6df,), # Wireless ..Ring Buoy + (0x1f6eb, 0x1f6ec,), # Airplane Departure ..Airplane Arriving + (0x1f6f4, 0x1f6fc,), # Scooter ..Roller Skate + (0x1f7e0, 0x1f7eb,), # Large Orange Circle ..Large Brown Square + (0x1f7f0, 0x1f7f0,), # Heavy Equals Sign + (0x1f90c, 0x1f93a,), # Pinched Fingers ..Fencer + (0x1f93c, 0x1f945,), # Wrestlers ..Goal Net + (0x1f947, 0x1f9ff,), # First Place Medal ..Nazar Amulet + (0x1fa70, 0x1fa7c,), # Ballet Shoes ..Crutch + (0x1fa80, 0x1fa8a,), # Yo-yo ..(nil) + (0x1fa8e, 0x1fac6,), # (nil) + (0x1fac8, 0x1fac8,), # (nil) + (0x1facd, 0x1fadc,), # (nil) + (0x1fadf, 0x1faea,), # (nil) + (0x1faef, 0x1faf8,), # (nil) ..Rightwards Pushing Hand + (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) + (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) + ), } diff --git a/contrib/python/wcwidth/py3/wcwidth/table_zero.py b/contrib/python/wcwidth/py3/wcwidth/table_zero.py index dd422915605..ef99d09e9f4 100644 --- a/contrib/python/wcwidth/py3/wcwidth/table_zero.py +++ b/contrib/python/wcwidth/py3/wcwidth/table_zero.py @@ -1,7 +1,7 @@ """ Exports ZERO_WIDTH table keyed by supporting unicode version level. -This code generated by wcwidth/bin/update-tables.py on 2024-01-04 07:14:52 UTC. +This code generated by wcwidth/bin/update-tables.py on 2025-09-18 07:49:05 UTC. """ ZERO_WIDTH = { '4.1.0': ( @@ -9,7 +9,6 @@ ZERO_WIDTH = { # Date: 2005-02-26, 02:35:50 GMT [MD] # (0x00000, 0x00000,), # (nil) - (0x000ad, 0x000ad,), # Soft Hyphen (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00486,), # Combining Cyrillic Titlo..Combining Cyrillic Psili (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli @@ -159,7 +158,6 @@ ZERO_WIDTH = { # Date: 2006-02-27, 23:41:27 GMT [MD] # (0x00000, 0x00000,), # (nil) - (0x000ad, 0x000ad,), # Soft Hyphen (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00486,), # Combining Cyrillic Titlo..Combining Cyrillic Psili (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli @@ -314,7 +312,6 @@ ZERO_WIDTH = { # Date: 2008-03-20, 17:54:57 GMT [MD] # (0x00000, 0x00000,), # (nil) - (0x000ad, 0x000ad,), # Soft Hyphen (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg @@ -492,7 +489,6 @@ ZERO_WIDTH = { # Date: 2009-08-22, 04:58:21 GMT [MD] # (0x00000, 0x00000,), # (nil) - (0x000ad, 0x000ad,), # Soft Hyphen (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg @@ -698,7 +694,6 @@ ZERO_WIDTH = { # Date: 2010-08-19, 00:48:09 GMT [MD] # (0x00000, 0x00000,), # (nil) - (0x000ad, 0x000ad,), # Soft Hyphen (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg @@ -910,7 +905,6 @@ ZERO_WIDTH = { # Date: 2011-11-27, 05:10:22 GMT [MD] # (0x00000, 0x00000,), # (nil) - (0x000ad, 0x000ad,), # Soft Hyphen (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg @@ -1133,7 +1127,6 @@ ZERO_WIDTH = { # Date: 2012-05-20, 00:42:34 GMT [MD] # (0x00000, 0x00000,), # (nil) - (0x000ad, 0x000ad,), # Soft Hyphen (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg @@ -1356,7 +1349,6 @@ ZERO_WIDTH = { # Date: 2013-07-05, 14:08:45 GMT [MD] # (0x00000, 0x00000,), # (nil) - (0x000ad, 0x000ad,), # Soft Hyphen (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg @@ -1580,7 +1572,6 @@ ZERO_WIDTH = { # Date: 2014-02-07, 18:42:12 GMT [MD] # (0x00000, 0x00000,), # (nil) - (0x000ad, 0x000ad,), # Soft Hyphen (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg @@ -1830,7 +1821,6 @@ ZERO_WIDTH = { # Date: 2015-02-13, 13:47:11 GMT [MD] # (0x00000, 0x00000,), # (nil) - (0x000ad, 0x000ad,), # Soft Hyphen (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg @@ -2088,7 +2078,6 @@ ZERO_WIDTH = { # Date: 2016-06-01, 10:34:26 GMT # (0x00000, 0x00000,), # (nil) - (0x000ad, 0x000ad,), # Soft Hyphen (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg @@ -2359,7 +2348,6 @@ ZERO_WIDTH = { # Date: 2017-03-08, 08:41:49 GMT # (0x00000, 0x00000,), # (nil) - (0x000ad, 0x000ad,), # Soft Hyphen (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg @@ -2643,7 +2631,6 @@ ZERO_WIDTH = { # Date: 2018-02-21, 05:34:04 GMT # (0x00000, 0x00000,), # (nil) - (0x000ad, 0x000ad,), # Soft Hyphen (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg @@ -2940,7 +2927,6 @@ ZERO_WIDTH = { # Date: 2019-01-22, 08:18:28 GMT # (0x00000, 0x00000,), # (nil) - (0x000ad, 0x000ad,), # Soft Hyphen (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg @@ -3243,7 +3229,6 @@ ZERO_WIDTH = { # Date: 2019-03-10, 10:53:08 GMT # (0x00000, 0x00000,), # (nil) - (0x000ad, 0x000ad,), # Soft Hyphen (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg @@ -3546,7 +3531,6 @@ ZERO_WIDTH = { # Date: 2019-10-21, 14:30:32 GMT # (0x00000, 0x00000,), # (nil) - (0x000ad, 0x000ad,), # Soft Hyphen (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg @@ -3859,7 +3843,6 @@ ZERO_WIDTH = { # Date: 2021-07-10, 00:35:08 GMT # (0x00000, 0x00000,), # (nil) - (0x000ad, 0x000ad,), # Soft Hyphen (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg @@ -4181,7 +4164,6 @@ ZERO_WIDTH = { # Date: 2022-04-26, 23:14:35 GMT # (0x00000, 0x00000,), # (nil) - (0x000ad, 0x000ad,), # Soft Hyphen (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg @@ -4513,7 +4495,6 @@ ZERO_WIDTH = { # Date: 2023-07-28, 23:34:02 GMT # (0x00000, 0x00000,), # (nil) - (0x000ad, 0x000ad,), # Soft Hyphen (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg @@ -4840,4 +4821,694 @@ ZERO_WIDTH = { (0xe0020, 0xe007f,), # Tag Space ..Cancel Tag (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 ), + '16.0.0': ( + # Source: DerivedGeneralCategory-16.0.0.txt + # Date: 2024-04-30, 21:48:17 GMT + # + (0x00000, 0x00000,), # (nil) + (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le + (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli + (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg + (0x005bf, 0x005bf,), # Hebrew Point Rafe + (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot + (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qatan + (0x00600, 0x00605,), # Arabic Number Sign ..Arabic Number Mark Above + (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra + (0x0061c, 0x0061c,), # Arabic Letter Mark + (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below + (0x00670, 0x00670,), # Arabic Letter Superscript Alef + (0x006d6, 0x006dd,), # Arabic Small High Ligatu..Arabic End Of Ayah + (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda + (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon + (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem + (0x0070f, 0x0070f,), # Syriac Abbreviation Mark + (0x00711, 0x00711,), # Syriac Letter Superscript Alaph + (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh + (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun + (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot + (0x007fd, 0x007fd,), # Nko Dantayalan + (0x00816, 0x00819,), # Samaritan Mark In ..Samaritan Mark Dagesh + (0x0081b, 0x00823,), # Samaritan Mark Epentheti..Samaritan Vowel Sign A + (0x00825, 0x00827,), # Samaritan Vowel Sign Sho..Samaritan Vowel Sign U + (0x00829, 0x0082d,), # Samaritan Vowel Sign Lon..Samaritan Mark Nequdaa + (0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark + (0x00890, 0x00891,), # Arabic Pound Mark Above ..Arabic Piastre Mark Abov + (0x00897, 0x0089f,), # (nil) ..Arabic Half Madda Over M + (0x008ca, 0x00903,), # Arabic Small High Farsi ..Devanagari Sign Visarga + (0x0093a, 0x0093c,), # Devanagari Vowel Sign Oe..Devanagari Sign Nukta + (0x0093e, 0x0094f,), # Devanagari Vowel Sign Aa..Devanagari Vowel Sign Aw + (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu + (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo + (0x00981, 0x00983,), # Bengali Sign Candrabindu..Bengali Sign Visarga + (0x009bc, 0x009bc,), # Bengali Sign Nukta + (0x009be, 0x009c4,), # Bengali Vowel Sign Aa ..Bengali Vowel Sign Vocal + (0x009c7, 0x009c8,), # Bengali Vowel Sign E ..Bengali Vowel Sign Ai + (0x009cb, 0x009cd,), # Bengali Vowel Sign O ..Bengali Sign Virama + (0x009d7, 0x009d7,), # Bengali Au Length Mark + (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal + (0x009fe, 0x009fe,), # Bengali Sandhi Mark + (0x00a01, 0x00a03,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Visarga + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta + (0x00a3e, 0x00a42,), # Gurmukhi Vowel Sign Aa ..Gurmukhi Vowel Sign Uu + (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai + (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat + (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash + (0x00a81, 0x00a83,), # Gujarati Sign Candrabind..Gujarati Sign Visarga + (0x00abc, 0x00abc,), # Gujarati Sign Nukta + (0x00abe, 0x00ac5,), # Gujarati Vowel Sign Aa ..Gujarati Vowel Sign Cand + (0x00ac7, 0x00ac9,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Cand + (0x00acb, 0x00acd,), # Gujarati Vowel Sign O ..Gujarati Sign Virama + (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca + (0x00afa, 0x00aff,), # Gujarati Sign Sukun ..Gujarati Sign Two-circle + (0x00b01, 0x00b03,), # Oriya Sign Candrabindu ..Oriya Sign Visarga + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3e, 0x00b44,), # Oriya Vowel Sign Aa ..Oriya Vowel Sign Vocalic + (0x00b47, 0x00b48,), # Oriya Vowel Sign E ..Oriya Vowel Sign Ai + (0x00b4b, 0x00b4d,), # Oriya Vowel Sign O ..Oriya Sign Virama + (0x00b55, 0x00b57,), # Oriya Sign Overline ..Oriya Au Length Mark + (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bbe, 0x00bc2,), # Tamil Vowel Sign Aa ..Tamil Vowel Sign Uu + (0x00bc6, 0x00bc8,), # Tamil Vowel Sign E ..Tamil Vowel Sign Ai + (0x00bca, 0x00bcd,), # Tamil Vowel Sign O ..Tamil Sign Virama + (0x00bd7, 0x00bd7,), # Tamil Au Length Mark + (0x00c00, 0x00c04,), # Telugu Sign Combining Ca..Telugu Sign Combining An + (0x00c3c, 0x00c3c,), # Telugu Sign Nukta + (0x00c3e, 0x00c44,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Vocali + (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai + (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama + (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark + (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali + (0x00c81, 0x00c83,), # Kannada Sign Candrabindu..Kannada Sign Visarga + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbe, 0x00cc4,), # Kannada Vowel Sign Aa ..Kannada Vowel Sign Vocal + (0x00cc6, 0x00cc8,), # Kannada Vowel Sign E ..Kannada Vowel Sign Ai + (0x00cca, 0x00ccd,), # Kannada Vowel Sign O ..Kannada Sign Virama + (0x00cd5, 0x00cd6,), # Kannada Length Mark ..Kannada Ai Length Mark + (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal + (0x00cf3, 0x00cf3,), # Kannada Sign Combining Anusvara Above Right + (0x00d00, 0x00d03,), # Malayalam Sign Combining..Malayalam Sign Visarga + (0x00d3b, 0x00d3c,), # Malayalam Sign Vertical ..Malayalam Sign Circular + (0x00d3e, 0x00d44,), # Malayalam Vowel Sign Aa ..Malayalam Vowel Sign Voc + (0x00d46, 0x00d48,), # Malayalam Vowel Sign E ..Malayalam Vowel Sign Ai + (0x00d4a, 0x00d4d,), # Malayalam Vowel Sign O ..Malayalam Sign Virama + (0x00d57, 0x00d57,), # Malayalam Au Length Mark + (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc + (0x00d81, 0x00d83,), # Sinhala Sign Candrabindu..Sinhala Sign Visargaya + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna + (0x00dcf, 0x00dd4,), # Sinhala Vowel Sign Aela-..Sinhala Vowel Sign Ketti + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga Paa-pilla + (0x00dd8, 0x00ddf,), # Sinhala Vowel Sign Gaett..Sinhala Vowel Sign Gayan + (0x00df2, 0x00df3,), # Sinhala Vowel Sign Diga ..Sinhala Vowel Sign Diga + (0x00e31, 0x00e31,), # Thai Character Mai Han-akat + (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu + (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan + (0x00eb4, 0x00ebc,), # Lao Vowel Sign I ..Lao Semivowel Sign Lo + (0x00ec8, 0x00ece,), # Lao Tone Mai Ek ..Lao Yamakkan + (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung Nyi Zla + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung Sgor Rtags + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru + (0x00f3e, 0x00f3f,), # Tibetan Sign Yar Tshes ..Tibetan Sign Mar Tshes + (0x00f71, 0x00f84,), # Tibetan Vowel Sign Aa ..Tibetan Mark Halanta + (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags + (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter + (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gdan + (0x0102b, 0x0103e,), # Myanmar Vowel Sign Tall ..Myanmar Consonant Sign M + (0x01056, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal + (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M + (0x01062, 0x01064,), # Myanmar Vowel Sign Sgaw ..Myanmar Tone Mark Sgaw K + (0x01067, 0x0106d,), # Myanmar Vowel Sign Weste..Myanmar Sign Western Pwo + (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah + (0x01082, 0x0108d,), # Myanmar Consonant Sign S..Myanmar Sign Shan Counci + (0x0108f, 0x0108f,), # Myanmar Sign Rumai Palaung Tone-5 + (0x0109a, 0x0109d,), # Myanmar Sign Khamti Tone..Myanmar Vowel Sign Aiton + (0x01160, 0x011ff,), # Hangul Jungseong Filler ..Hangul Jongseong Ssangni + (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin + (0x01712, 0x01715,), # Tagalog Vowel Sign I ..Tagalog Sign Pamudpod + (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod + (0x01752, 0x01753,), # Buhid Vowel Sign I ..Buhid Vowel Sign U + (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U + (0x017b4, 0x017d3,), # Khmer Vowel Inherent Aq ..Khmer Sign Bathamasat + (0x017dd, 0x017dd,), # Khmer Sign Atthacan + (0x0180b, 0x0180f,), # Mongolian Free Variation..Mongolian Free Variation + (0x01885, 0x01886,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga + (0x01920, 0x0192b,), # Limbu Vowel Sign A ..Limbu Subjoined Letter W + (0x01930, 0x0193b,), # Limbu Small Letter Ka ..Limbu Sign Sa-i + (0x01a17, 0x01a1b,), # Buginese Vowel Sign I ..Buginese Vowel Sign Ae + (0x01a55, 0x01a5e,), # Tai Tham Consonant Sign ..Tai Tham Consonant Sign + (0x01a60, 0x01a7c,), # Tai Tham Sign Sakot ..Tai Tham Sign Khuen-lue + (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot + (0x01ab0, 0x01ace,), # Combining Doubled Circum..Combining Latin Small Le + (0x01b00, 0x01b04,), # Balinese Sign Ulu Ricem ..Balinese Sign Bisah + (0x01b34, 0x01b44,), # Balinese Sign Rerekan ..Balinese Adeg Adeg + (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol + (0x01b80, 0x01b82,), # Sundanese Sign Panyecek ..Sundanese Sign Pangwisad + (0x01ba1, 0x01bad,), # Sundanese Consonant Sign..Sundanese Consonant Sign + (0x01be6, 0x01bf3,), # Batak Sign Tompi ..Batak Panongonan + (0x01c24, 0x01c37,), # Lepcha Subjoined Letter ..Lepcha Sign Nukta + (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha + (0x01cd4, 0x01ce8,), # Vedic Sign Yajurvedic Mi..Vedic Sign Visarga Anuda + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above + (0x01cf7, 0x01cf9,), # Vedic Sign Atikrama ..Vedic Tone Double Ring A + (0x01dc0, 0x01dff,), # Combining Dotted Grave A..Combining Right Arrowhea + (0x0200b, 0x0200f,), # Zero Width Space ..Right-to-left Mark + (0x02028, 0x0202e,), # Line Separator ..Right-to-left Override + (0x02060, 0x02064,), # Word Joiner ..Invisible Plus + (0x02066, 0x0206f,), # Left-to-right Isolate ..Nominal Digit Shapes + (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above + (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner + (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette + (0x0302a, 0x0302f,), # Ideographic Level Tone M..Hangul Double Dot Tone M + (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag + (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous + (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer + (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette + (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisvara + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusvara + (0x0a823, 0x0a827,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign + (0x0a82c, 0x0a82c,), # Syloti Nagri Sign Alternate Hasanta + (0x0a880, 0x0a881,), # Saurashtra Sign Anusvara..Saurashtra Sign Visarga + (0x0a8b4, 0x0a8c5,), # Saurashtra Consonant Sig..Saurashtra Sign Candrabi + (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig + (0x0a8ff, 0x0a8ff,), # Devanagari Vowel Sign Ay + (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop + (0x0a947, 0x0a953,), # Rejang Vowel Sign I ..Rejang Virama + (0x0a980, 0x0a983,), # Javanese Sign Panyangga ..Javanese Sign Wignyan + (0x0a9b3, 0x0a9c0,), # Javanese Sign Cecak Telu..Javanese Pangkon + (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw + (0x0aa29, 0x0aa36,), # Cham Vowel Sign Aa ..Cham Consonant Sign Wa + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Final Ng + (0x0aa4c, 0x0aa4d,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina + (0x0aa7b, 0x0aa7d,), # Myanmar Sign Pao Karen T..Myanmar Sign Tai Laing T + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang + (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U + (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia + (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho + (0x0aaeb, 0x0aaef,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign + (0x0aaf5, 0x0aaf6,), # Meetei Mayek Vowel Sign ..Meetei Mayek Virama + (0x0abe3, 0x0abea,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign + (0x0abec, 0x0abed,), # Meetei Mayek Lum Iyek ..Meetei Mayek Apun Iyek + (0x0d7b0, 0x0d7ff,), # Hangul Jungseong O-yeo ..(nil) + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spanish Varika + (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 + (0x0fe20, 0x0fe2f,), # Combining Ligature Left ..Combining Cyrillic Titlo + (0x0feff, 0x0feff,), # Zero Width No-break Space + (0x0fff9, 0x0fffb,), # Interlinear Annotation A..Interlinear Annotation T + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combining Oblique Stroke + (0x102e0, 0x102e0,), # Coptic Epact Thousands Mark + (0x10376, 0x1037a,), # Combining Old Permic Let..Combining Old Permic Let + (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo + (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O + (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga + (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo + (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x10ae5, 0x10ae6,), # Manichaean Abbreviation ..Manichaean Abbreviation + (0x10d24, 0x10d27,), # Hanifi Rohingya Sign Har..Hanifi Rohingya Sign Tas + (0x10d69, 0x10d6d,), # (nil) + (0x10eab, 0x10eac,), # Yezidi Combining Hamza M..Yezidi Combining Madda M + (0x10efc, 0x10eff,), # (nil) ..Arabic Small Low Word Ma + (0x10f46, 0x10f50,), # Sogdian Combining Dot Be..Sogdian Combining Stroke + (0x10f82, 0x10f85,), # Old Uyghur Combining Dot..Old Uyghur Combining Two + (0x11000, 0x11002,), # Brahmi Sign Candrabindu ..Brahmi Sign Visarga + (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama + (0x11070, 0x11070,), # Brahmi Sign Old Tamil Virama + (0x11073, 0x11074,), # Brahmi Vowel Sign Old Ta..Brahmi Vowel Sign Old Ta + (0x1107f, 0x11082,), # Brahmi Number Joiner ..Kaithi Sign Visarga + (0x110b0, 0x110ba,), # Kaithi Vowel Sign Aa ..Kaithi Sign Nukta + (0x110bd, 0x110bd,), # Kaithi Number Sign + (0x110c2, 0x110c2,), # Kaithi Vowel Sign Vocalic R + (0x110cd, 0x110cd,), # Kaithi Number Sign Above + (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga + (0x11127, 0x11134,), # Chakma Vowel Sign A ..Chakma Maayyaa + (0x11145, 0x11146,), # Chakma Vowel Sign Aa ..Chakma Vowel Sign Ei + (0x11173, 0x11173,), # Mahajani Sign Nukta + (0x11180, 0x11182,), # Sharada Sign Candrabindu..Sharada Sign Visarga + (0x111b3, 0x111c0,), # Sharada Vowel Sign Aa ..Sharada Sign Virama + (0x111c9, 0x111cc,), # Sharada Sandhi Mark ..Sharada Extra Short Vowe + (0x111ce, 0x111cf,), # Sharada Vowel Sign Prish..Sharada Sign Inverted Ca + (0x1122c, 0x11237,), # Khojki Vowel Sign Aa ..Khojki Sign Shadda + (0x1123e, 0x1123e,), # Khojki Sign Sukun + (0x11241, 0x11241,), # Khojki Vowel Sign Vocalic R + (0x112df, 0x112ea,), # Khudawadi Sign Anusvara ..Khudawadi Sign Virama + (0x11300, 0x11303,), # Grantha Sign Combining A..Grantha Sign Visarga + (0x1133b, 0x1133c,), # Combining Bindu Below ..Grantha Sign Nukta + (0x1133e, 0x11344,), # Grantha Vowel Sign Aa ..Grantha Vowel Sign Vocal + (0x11347, 0x11348,), # Grantha Vowel Sign Ee ..Grantha Vowel Sign Ai + (0x1134b, 0x1134d,), # Grantha Vowel Sign Oo ..Grantha Sign Virama + (0x11357, 0x11357,), # Grantha Au Length Mark + (0x11362, 0x11363,), # Grantha Vowel Sign Vocal..Grantha Vowel Sign Vocal + (0x11366, 0x1136c,), # Combining Grantha Digit ..Combining Grantha Digit + (0x11370, 0x11374,), # Combining Grantha Letter..Combining Grantha Letter + (0x113b8, 0x113c0,), # (nil) + (0x113c2, 0x113c2,), # (nil) + (0x113c5, 0x113c5,), # (nil) + (0x113c7, 0x113ca,), # (nil) + (0x113cc, 0x113d0,), # (nil) + (0x113d2, 0x113d2,), # (nil) + (0x113e1, 0x113e2,), # (nil) + (0x11435, 0x11446,), # Newa Vowel Sign Aa ..Newa Sign Nukta + (0x1145e, 0x1145e,), # Newa Sandhi Mark + (0x114b0, 0x114c3,), # Tirhuta Vowel Sign Aa ..Tirhuta Sign Nukta + (0x115af, 0x115b5,), # Siddham Vowel Sign Aa ..Siddham Vowel Sign Vocal + (0x115b8, 0x115c0,), # Siddham Vowel Sign E ..Siddham Sign Nukta + (0x115dc, 0x115dd,), # Siddham Vowel Sign Alter..Siddham Vowel Sign Alter + (0x11630, 0x11640,), # Modi Vowel Sign Aa ..Modi Sign Ardhacandra + (0x116ab, 0x116b7,), # Takri Sign Anusvara ..Takri Sign Nukta + (0x1171d, 0x1172b,), # Ahom Consonant Sign Medi..Ahom Sign Killer + (0x1182c, 0x1183a,), # Dogra Vowel Sign Aa ..Dogra Sign Nukta + (0x11930, 0x11935,), # Dives Akuru Vowel Sign A..Dives Akuru Vowel Sign E + (0x11937, 0x11938,), # Dives Akuru Vowel Sign A..Dives Akuru Vowel Sign O + (0x1193b, 0x1193e,), # Dives Akuru Sign Anusvar..Dives Akuru Virama + (0x11940, 0x11940,), # Dives Akuru Medial Ya + (0x11942, 0x11943,), # Dives Akuru Medial Ra ..Dives Akuru Sign Nukta + (0x119d1, 0x119d7,), # Nandinagari Vowel Sign A..Nandinagari Vowel Sign V + (0x119da, 0x119e0,), # Nandinagari Vowel Sign E..Nandinagari Sign Virama + (0x119e4, 0x119e4,), # Nandinagari Vowel Sign Prishthamatra E + (0x11a01, 0x11a0a,), # Zanabazar Square Vowel S..Zanabazar Square Vowel L + (0x11a33, 0x11a39,), # Zanabazar Square Final C..Zanabazar Square Sign Vi + (0x11a3b, 0x11a3e,), # Zanabazar Square Cluster..Zanabazar Square Cluster + (0x11a47, 0x11a47,), # Zanabazar Square Subjoiner + (0x11a51, 0x11a5b,), # Soyombo Vowel Sign I ..Soyombo Vowel Length Mar + (0x11a8a, 0x11a99,), # Soyombo Final Consonant ..Soyombo Subjoiner + (0x11c2f, 0x11c36,), # Bhaiksuki Vowel Sign Aa ..Bhaiksuki Vowel Sign Voc + (0x11c38, 0x11c3f,), # Bhaiksuki Vowel Sign E ..Bhaiksuki Sign Virama + (0x11c92, 0x11ca7,), # Marchen Subjoined Letter..Marchen Subjoined Letter + (0x11ca9, 0x11cb6,), # Marchen Subjoined Letter..Marchen Sign Candrabindu + (0x11d31, 0x11d36,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign + (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign E + (0x11d3c, 0x11d3d,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign + (0x11d3f, 0x11d45,), # Masaram Gondi Vowel Sign..Masaram Gondi Virama + (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara + (0x11d8a, 0x11d8e,), # Gunjala Gondi Vowel Sign..Gunjala Gondi Vowel Sign + (0x11d90, 0x11d91,), # Gunjala Gondi Vowel Sign..Gunjala Gondi Vowel Sign + (0x11d93, 0x11d97,), # Gunjala Gondi Vowel Sign..Gunjala Gondi Virama + (0x11ef3, 0x11ef6,), # Makasar Vowel Sign I ..Makasar Vowel Sign O + (0x11f00, 0x11f01,), # Kawi Sign Candrabindu ..Kawi Sign Anusvara + (0x11f03, 0x11f03,), # Kawi Sign Visarga + (0x11f34, 0x11f3a,), # Kawi Vowel Sign Aa ..Kawi Vowel Sign Vocalic + (0x11f3e, 0x11f42,), # Kawi Vowel Sign E ..Kawi Conjoiner + (0x11f5a, 0x11f5a,), # (nil) + (0x13430, 0x13440,), # Egyptian Hieroglyph Vert..Egyptian Hieroglyph Mirr + (0x13447, 0x13455,), # Egyptian Hieroglyph Modi..Egyptian Hieroglyph Modi + (0x1611e, 0x1612f,), # (nil) + (0x16af0, 0x16af4,), # Bassa Vah Combining High..Bassa Vah Combining High + (0x16b30, 0x16b36,), # Pahawh Hmong Mark Cim Tu..Pahawh Hmong Mark Cim Ta + (0x16f4f, 0x16f4f,), # Miao Sign Consonant Modifier Bar + (0x16f51, 0x16f87,), # Miao Sign Aspiration ..Miao Vowel Sign Ui + (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below + (0x16fe4, 0x16fe4,), # Khitan Small Script Filler + (0x16ff0, 0x16ff1,), # Vietnamese Alternate Rea..Vietnamese Alternate Rea + (0x1bc9d, 0x1bc9e,), # Duployan Thick Letter Se..Duployan Double Mark + (0x1bca0, 0x1bca3,), # Shorthand Format Letter ..Shorthand Format Up Step + (0x1cf00, 0x1cf2d,), # Znamenny Combining Mark ..Znamenny Combining Mark + (0x1cf30, 0x1cf46,), # Znamenny Combining Tonal..Znamenny Priznak Modifie + (0x1d165, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining + (0x1d16d, 0x1d182,), # Musical Symbol Combining..Musical Symbol Combining + (0x1d185, 0x1d18b,), # Musical Symbol Combining..Musical Symbol Combining + (0x1d1aa, 0x1d1ad,), # Musical Symbol Combining..Musical Symbol Combining + (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical + (0x1da00, 0x1da36,), # Signwriting Head Rim ..Signwriting Air Sucking + (0x1da3b, 0x1da6c,), # Signwriting Mouth Closed..Signwriting Excitement + (0x1da75, 0x1da75,), # Signwriting Upper Body Tilting From Hip Joints + (0x1da84, 0x1da84,), # Signwriting Location Head Neck + (0x1da9b, 0x1da9f,), # Signwriting Fill Modifie..Signwriting Fill Modifie + (0x1daa1, 0x1daaf,), # Signwriting Rotation Mod..Signwriting Rotation Mod + (0x1e000, 0x1e006,), # Combining Glagolitic Let..Combining Glagolitic Let + (0x1e008, 0x1e018,), # Combining Glagolitic Let..Combining Glagolitic Let + (0x1e01b, 0x1e021,), # Combining Glagolitic Let..Combining Glagolitic Let + (0x1e023, 0x1e024,), # Combining Glagolitic Let..Combining Glagolitic Let + (0x1e026, 0x1e02a,), # Combining Glagolitic Let..Combining Glagolitic Let + (0x1e08f, 0x1e08f,), # Combining Cyrillic Small Letter Byelorussian-ukr + (0x1e130, 0x1e136,), # Nyiakeng Puachue Hmong T..Nyiakeng Puachue Hmong T + (0x1e2ae, 0x1e2ae,), # Toto Sign Rising Tone + (0x1e2ec, 0x1e2ef,), # Wancho Tone Tup ..Wancho Tone Koini + (0x1e4ec, 0x1e4ef,), # Nag Mundari Sign Muhor ..Nag Mundari Sign Sutuh + (0x1e5ee, 0x1e5ef,), # (nil) + (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining + (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta + (0x1f3fb, 0x1f3ff,), # Emoji Modifier Fitzpatri..Emoji Modifier Fitzpatri + (0xe0001, 0xe0001,), # Language Tag + (0xe0020, 0xe007f,), # Tag Space ..Cancel Tag + (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 + ), + '17.0.0': ( + # Source: DerivedGeneralCategory-17.0.0.txt + # Date: 2025-07-24, 00:12:50 GMT + # + (0x00000, 0x00000,), # (nil) + (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le + (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli + (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg + (0x005bf, 0x005bf,), # Hebrew Point Rafe + (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot + (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qatan + (0x00600, 0x00605,), # Arabic Number Sign ..Arabic Number Mark Above + (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra + (0x0061c, 0x0061c,), # Arabic Letter Mark + (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below + (0x00670, 0x00670,), # Arabic Letter Superscript Alef + (0x006d6, 0x006dd,), # Arabic Small High Ligatu..Arabic End Of Ayah + (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda + (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon + (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem + (0x0070f, 0x0070f,), # Syriac Abbreviation Mark + (0x00711, 0x00711,), # Syriac Letter Superscript Alaph + (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh + (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun + (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot + (0x007fd, 0x007fd,), # Nko Dantayalan + (0x00816, 0x00819,), # Samaritan Mark In ..Samaritan Mark Dagesh + (0x0081b, 0x00823,), # Samaritan Mark Epentheti..Samaritan Vowel Sign A + (0x00825, 0x00827,), # Samaritan Vowel Sign Sho..Samaritan Vowel Sign U + (0x00829, 0x0082d,), # Samaritan Vowel Sign Lon..Samaritan Mark Nequdaa + (0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark + (0x00890, 0x00891,), # Arabic Pound Mark Above ..Arabic Piastre Mark Abov + (0x00897, 0x0089f,), # (nil) ..Arabic Half Madda Over M + (0x008ca, 0x00903,), # Arabic Small High Farsi ..Devanagari Sign Visarga + (0x0093a, 0x0093c,), # Devanagari Vowel Sign Oe..Devanagari Sign Nukta + (0x0093e, 0x0094f,), # Devanagari Vowel Sign Aa..Devanagari Vowel Sign Aw + (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu + (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo + (0x00981, 0x00983,), # Bengali Sign Candrabindu..Bengali Sign Visarga + (0x009bc, 0x009bc,), # Bengali Sign Nukta + (0x009be, 0x009c4,), # Bengali Vowel Sign Aa ..Bengali Vowel Sign Vocal + (0x009c7, 0x009c8,), # Bengali Vowel Sign E ..Bengali Vowel Sign Ai + (0x009cb, 0x009cd,), # Bengali Vowel Sign O ..Bengali Sign Virama + (0x009d7, 0x009d7,), # Bengali Au Length Mark + (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal + (0x009fe, 0x009fe,), # Bengali Sandhi Mark + (0x00a01, 0x00a03,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Visarga + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta + (0x00a3e, 0x00a42,), # Gurmukhi Vowel Sign Aa ..Gurmukhi Vowel Sign Uu + (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai + (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat + (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash + (0x00a81, 0x00a83,), # Gujarati Sign Candrabind..Gujarati Sign Visarga + (0x00abc, 0x00abc,), # Gujarati Sign Nukta + (0x00abe, 0x00ac5,), # Gujarati Vowel Sign Aa ..Gujarati Vowel Sign Cand + (0x00ac7, 0x00ac9,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Cand + (0x00acb, 0x00acd,), # Gujarati Vowel Sign O ..Gujarati Sign Virama + (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca + (0x00afa, 0x00aff,), # Gujarati Sign Sukun ..Gujarati Sign Two-circle + (0x00b01, 0x00b03,), # Oriya Sign Candrabindu ..Oriya Sign Visarga + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3e, 0x00b44,), # Oriya Vowel Sign Aa ..Oriya Vowel Sign Vocalic + (0x00b47, 0x00b48,), # Oriya Vowel Sign E ..Oriya Vowel Sign Ai + (0x00b4b, 0x00b4d,), # Oriya Vowel Sign O ..Oriya Sign Virama + (0x00b55, 0x00b57,), # Oriya Sign Overline ..Oriya Au Length Mark + (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bbe, 0x00bc2,), # Tamil Vowel Sign Aa ..Tamil Vowel Sign Uu + (0x00bc6, 0x00bc8,), # Tamil Vowel Sign E ..Tamil Vowel Sign Ai + (0x00bca, 0x00bcd,), # Tamil Vowel Sign O ..Tamil Sign Virama + (0x00bd7, 0x00bd7,), # Tamil Au Length Mark + (0x00c00, 0x00c04,), # Telugu Sign Combining Ca..Telugu Sign Combining An + (0x00c3c, 0x00c3c,), # Telugu Sign Nukta + (0x00c3e, 0x00c44,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Vocali + (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai + (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama + (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark + (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali + (0x00c81, 0x00c83,), # Kannada Sign Candrabindu..Kannada Sign Visarga + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbe, 0x00cc4,), # Kannada Vowel Sign Aa ..Kannada Vowel Sign Vocal + (0x00cc6, 0x00cc8,), # Kannada Vowel Sign E ..Kannada Vowel Sign Ai + (0x00cca, 0x00ccd,), # Kannada Vowel Sign O ..Kannada Sign Virama + (0x00cd5, 0x00cd6,), # Kannada Length Mark ..Kannada Ai Length Mark + (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal + (0x00cf3, 0x00cf3,), # Kannada Sign Combining Anusvara Above Right + (0x00d00, 0x00d03,), # Malayalam Sign Combining..Malayalam Sign Visarga + (0x00d3b, 0x00d3c,), # Malayalam Sign Vertical ..Malayalam Sign Circular + (0x00d3e, 0x00d44,), # Malayalam Vowel Sign Aa ..Malayalam Vowel Sign Voc + (0x00d46, 0x00d48,), # Malayalam Vowel Sign E ..Malayalam Vowel Sign Ai + (0x00d4a, 0x00d4d,), # Malayalam Vowel Sign O ..Malayalam Sign Virama + (0x00d57, 0x00d57,), # Malayalam Au Length Mark + (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc + (0x00d81, 0x00d83,), # Sinhala Sign Candrabindu..Sinhala Sign Visargaya + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna + (0x00dcf, 0x00dd4,), # Sinhala Vowel Sign Aela-..Sinhala Vowel Sign Ketti + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga Paa-pilla + (0x00dd8, 0x00ddf,), # Sinhala Vowel Sign Gaett..Sinhala Vowel Sign Gayan + (0x00df2, 0x00df3,), # Sinhala Vowel Sign Diga ..Sinhala Vowel Sign Diga + (0x00e31, 0x00e31,), # Thai Character Mai Han-akat + (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu + (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan + (0x00eb4, 0x00ebc,), # Lao Vowel Sign I ..Lao Semivowel Sign Lo + (0x00ec8, 0x00ece,), # Lao Tone Mai Ek ..Lao Yamakkan + (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung Nyi Zla + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung Sgor Rtags + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru + (0x00f3e, 0x00f3f,), # Tibetan Sign Yar Tshes ..Tibetan Sign Mar Tshes + (0x00f71, 0x00f84,), # Tibetan Vowel Sign Aa ..Tibetan Mark Halanta + (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags + (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter + (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gdan + (0x0102b, 0x0103e,), # Myanmar Vowel Sign Tall ..Myanmar Consonant Sign M + (0x01056, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal + (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M + (0x01062, 0x01064,), # Myanmar Vowel Sign Sgaw ..Myanmar Tone Mark Sgaw K + (0x01067, 0x0106d,), # Myanmar Vowel Sign Weste..Myanmar Sign Western Pwo + (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah + (0x01082, 0x0108d,), # Myanmar Consonant Sign S..Myanmar Sign Shan Counci + (0x0108f, 0x0108f,), # Myanmar Sign Rumai Palaung Tone-5 + (0x0109a, 0x0109d,), # Myanmar Sign Khamti Tone..Myanmar Vowel Sign Aiton + (0x01160, 0x011ff,), # Hangul Jungseong Filler ..Hangul Jongseong Ssangni + (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin + (0x01712, 0x01715,), # Tagalog Vowel Sign I ..Tagalog Sign Pamudpod + (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod + (0x01752, 0x01753,), # Buhid Vowel Sign I ..Buhid Vowel Sign U + (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U + (0x017b4, 0x017d3,), # Khmer Vowel Inherent Aq ..Khmer Sign Bathamasat + (0x017dd, 0x017dd,), # Khmer Sign Atthacan + (0x0180b, 0x0180f,), # Mongolian Free Variation..Mongolian Free Variation + (0x01885, 0x01886,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga + (0x01920, 0x0192b,), # Limbu Vowel Sign A ..Limbu Subjoined Letter W + (0x01930, 0x0193b,), # Limbu Small Letter Ka ..Limbu Sign Sa-i + (0x01a17, 0x01a1b,), # Buginese Vowel Sign I ..Buginese Vowel Sign Ae + (0x01a55, 0x01a5e,), # Tai Tham Consonant Sign ..Tai Tham Consonant Sign + (0x01a60, 0x01a7c,), # Tai Tham Sign Sakot ..Tai Tham Sign Khuen-lue + (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot + (0x01ab0, 0x01add,), # Combining Doubled Circum..(nil) + (0x01ae0, 0x01aeb,), # (nil) + (0x01b00, 0x01b04,), # Balinese Sign Ulu Ricem ..Balinese Sign Bisah + (0x01b34, 0x01b44,), # Balinese Sign Rerekan ..Balinese Adeg Adeg + (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol + (0x01b80, 0x01b82,), # Sundanese Sign Panyecek ..Sundanese Sign Pangwisad + (0x01ba1, 0x01bad,), # Sundanese Consonant Sign..Sundanese Consonant Sign + (0x01be6, 0x01bf3,), # Batak Sign Tompi ..Batak Panongonan + (0x01c24, 0x01c37,), # Lepcha Subjoined Letter ..Lepcha Sign Nukta + (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha + (0x01cd4, 0x01ce8,), # Vedic Sign Yajurvedic Mi..Vedic Sign Visarga Anuda + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above + (0x01cf7, 0x01cf9,), # Vedic Sign Atikrama ..Vedic Tone Double Ring A + (0x01dc0, 0x01dff,), # Combining Dotted Grave A..Combining Right Arrowhea + (0x0200b, 0x0200f,), # Zero Width Space ..Right-to-left Mark + (0x02028, 0x0202e,), # Line Separator ..Right-to-left Override + (0x02060, 0x02064,), # Word Joiner ..Invisible Plus + (0x02066, 0x0206f,), # Left-to-right Isolate ..Nominal Digit Shapes + (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above + (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner + (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette + (0x0302a, 0x0302f,), # Ideographic Level Tone M..Hangul Double Dot Tone M + (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag + (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous + (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer + (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette + (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisvara + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusvara + (0x0a823, 0x0a827,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign + (0x0a82c, 0x0a82c,), # Syloti Nagri Sign Alternate Hasanta + (0x0a880, 0x0a881,), # Saurashtra Sign Anusvara..Saurashtra Sign Visarga + (0x0a8b4, 0x0a8c5,), # Saurashtra Consonant Sig..Saurashtra Sign Candrabi + (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig + (0x0a8ff, 0x0a8ff,), # Devanagari Vowel Sign Ay + (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop + (0x0a947, 0x0a953,), # Rejang Vowel Sign I ..Rejang Virama + (0x0a980, 0x0a983,), # Javanese Sign Panyangga ..Javanese Sign Wignyan + (0x0a9b3, 0x0a9c0,), # Javanese Sign Cecak Telu..Javanese Pangkon + (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw + (0x0aa29, 0x0aa36,), # Cham Vowel Sign Aa ..Cham Consonant Sign Wa + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Final Ng + (0x0aa4c, 0x0aa4d,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina + (0x0aa7b, 0x0aa7d,), # Myanmar Sign Pao Karen T..Myanmar Sign Tai Laing T + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang + (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U + (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia + (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho + (0x0aaeb, 0x0aaef,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign + (0x0aaf5, 0x0aaf6,), # Meetei Mayek Vowel Sign ..Meetei Mayek Virama + (0x0abe3, 0x0abea,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign + (0x0abec, 0x0abed,), # Meetei Mayek Lum Iyek ..Meetei Mayek Apun Iyek + (0x0d7b0, 0x0d7ff,), # Hangul Jungseong O-yeo ..(nil) + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spanish Varika + (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 + (0x0fe20, 0x0fe2f,), # Combining Ligature Left ..Combining Cyrillic Titlo + (0x0feff, 0x0feff,), # Zero Width No-break Space + (0x0fff9, 0x0fffb,), # Interlinear Annotation A..Interlinear Annotation T + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combining Oblique Stroke + (0x102e0, 0x102e0,), # Coptic Epact Thousands Mark + (0x10376, 0x1037a,), # Combining Old Permic Let..Combining Old Permic Let + (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo + (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O + (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga + (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo + (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x10ae5, 0x10ae6,), # Manichaean Abbreviation ..Manichaean Abbreviation + (0x10d24, 0x10d27,), # Hanifi Rohingya Sign Har..Hanifi Rohingya Sign Tas + (0x10d69, 0x10d6d,), # (nil) + (0x10eab, 0x10eac,), # Yezidi Combining Hamza M..Yezidi Combining Madda M + (0x10efa, 0x10eff,), # (nil) ..Arabic Small Low Word Ma + (0x10f46, 0x10f50,), # Sogdian Combining Dot Be..Sogdian Combining Stroke + (0x10f82, 0x10f85,), # Old Uyghur Combining Dot..Old Uyghur Combining Two + (0x11000, 0x11002,), # Brahmi Sign Candrabindu ..Brahmi Sign Visarga + (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama + (0x11070, 0x11070,), # Brahmi Sign Old Tamil Virama + (0x11073, 0x11074,), # Brahmi Vowel Sign Old Ta..Brahmi Vowel Sign Old Ta + (0x1107f, 0x11082,), # Brahmi Number Joiner ..Kaithi Sign Visarga + (0x110b0, 0x110ba,), # Kaithi Vowel Sign Aa ..Kaithi Sign Nukta + (0x110bd, 0x110bd,), # Kaithi Number Sign + (0x110c2, 0x110c2,), # Kaithi Vowel Sign Vocalic R + (0x110cd, 0x110cd,), # Kaithi Number Sign Above + (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga + (0x11127, 0x11134,), # Chakma Vowel Sign A ..Chakma Maayyaa + (0x11145, 0x11146,), # Chakma Vowel Sign Aa ..Chakma Vowel Sign Ei + (0x11173, 0x11173,), # Mahajani Sign Nukta + (0x11180, 0x11182,), # Sharada Sign Candrabindu..Sharada Sign Visarga + (0x111b3, 0x111c0,), # Sharada Vowel Sign Aa ..Sharada Sign Virama + (0x111c9, 0x111cc,), # Sharada Sandhi Mark ..Sharada Extra Short Vowe + (0x111ce, 0x111cf,), # Sharada Vowel Sign Prish..Sharada Sign Inverted Ca + (0x1122c, 0x11237,), # Khojki Vowel Sign Aa ..Khojki Sign Shadda + (0x1123e, 0x1123e,), # Khojki Sign Sukun + (0x11241, 0x11241,), # Khojki Vowel Sign Vocalic R + (0x112df, 0x112ea,), # Khudawadi Sign Anusvara ..Khudawadi Sign Virama + (0x11300, 0x11303,), # Grantha Sign Combining A..Grantha Sign Visarga + (0x1133b, 0x1133c,), # Combining Bindu Below ..Grantha Sign Nukta + (0x1133e, 0x11344,), # Grantha Vowel Sign Aa ..Grantha Vowel Sign Vocal + (0x11347, 0x11348,), # Grantha Vowel Sign Ee ..Grantha Vowel Sign Ai + (0x1134b, 0x1134d,), # Grantha Vowel Sign Oo ..Grantha Sign Virama + (0x11357, 0x11357,), # Grantha Au Length Mark + (0x11362, 0x11363,), # Grantha Vowel Sign Vocal..Grantha Vowel Sign Vocal + (0x11366, 0x1136c,), # Combining Grantha Digit ..Combining Grantha Digit + (0x11370, 0x11374,), # Combining Grantha Letter..Combining Grantha Letter + (0x113b8, 0x113c0,), # (nil) + (0x113c2, 0x113c2,), # (nil) + (0x113c5, 0x113c5,), # (nil) + (0x113c7, 0x113ca,), # (nil) + (0x113cc, 0x113d0,), # (nil) + (0x113d2, 0x113d2,), # (nil) + (0x113e1, 0x113e2,), # (nil) + (0x11435, 0x11446,), # Newa Vowel Sign Aa ..Newa Sign Nukta + (0x1145e, 0x1145e,), # Newa Sandhi Mark + (0x114b0, 0x114c3,), # Tirhuta Vowel Sign Aa ..Tirhuta Sign Nukta + (0x115af, 0x115b5,), # Siddham Vowel Sign Aa ..Siddham Vowel Sign Vocal + (0x115b8, 0x115c0,), # Siddham Vowel Sign E ..Siddham Sign Nukta + (0x115dc, 0x115dd,), # Siddham Vowel Sign Alter..Siddham Vowel Sign Alter + (0x11630, 0x11640,), # Modi Vowel Sign Aa ..Modi Sign Ardhacandra + (0x116ab, 0x116b7,), # Takri Sign Anusvara ..Takri Sign Nukta + (0x1171d, 0x1172b,), # Ahom Consonant Sign Medi..Ahom Sign Killer + (0x1182c, 0x1183a,), # Dogra Vowel Sign Aa ..Dogra Sign Nukta + (0x11930, 0x11935,), # Dives Akuru Vowel Sign A..Dives Akuru Vowel Sign E + (0x11937, 0x11938,), # Dives Akuru Vowel Sign A..Dives Akuru Vowel Sign O + (0x1193b, 0x1193e,), # Dives Akuru Sign Anusvar..Dives Akuru Virama + (0x11940, 0x11940,), # Dives Akuru Medial Ya + (0x11942, 0x11943,), # Dives Akuru Medial Ra ..Dives Akuru Sign Nukta + (0x119d1, 0x119d7,), # Nandinagari Vowel Sign A..Nandinagari Vowel Sign V + (0x119da, 0x119e0,), # Nandinagari Vowel Sign E..Nandinagari Sign Virama + (0x119e4, 0x119e4,), # Nandinagari Vowel Sign Prishthamatra E + (0x11a01, 0x11a0a,), # Zanabazar Square Vowel S..Zanabazar Square Vowel L + (0x11a33, 0x11a39,), # Zanabazar Square Final C..Zanabazar Square Sign Vi + (0x11a3b, 0x11a3e,), # Zanabazar Square Cluster..Zanabazar Square Cluster + (0x11a47, 0x11a47,), # Zanabazar Square Subjoiner + (0x11a51, 0x11a5b,), # Soyombo Vowel Sign I ..Soyombo Vowel Length Mar + (0x11a8a, 0x11a99,), # Soyombo Final Consonant ..Soyombo Subjoiner + (0x11b60, 0x11b67,), # (nil) + (0x11c2f, 0x11c36,), # Bhaiksuki Vowel Sign Aa ..Bhaiksuki Vowel Sign Voc + (0x11c38, 0x11c3f,), # Bhaiksuki Vowel Sign E ..Bhaiksuki Sign Virama + (0x11c92, 0x11ca7,), # Marchen Subjoined Letter..Marchen Subjoined Letter + (0x11ca9, 0x11cb6,), # Marchen Subjoined Letter..Marchen Sign Candrabindu + (0x11d31, 0x11d36,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign + (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign E + (0x11d3c, 0x11d3d,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign + (0x11d3f, 0x11d45,), # Masaram Gondi Vowel Sign..Masaram Gondi Virama + (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara + (0x11d8a, 0x11d8e,), # Gunjala Gondi Vowel Sign..Gunjala Gondi Vowel Sign + (0x11d90, 0x11d91,), # Gunjala Gondi Vowel Sign..Gunjala Gondi Vowel Sign + (0x11d93, 0x11d97,), # Gunjala Gondi Vowel Sign..Gunjala Gondi Virama + (0x11ef3, 0x11ef6,), # Makasar Vowel Sign I ..Makasar Vowel Sign O + (0x11f00, 0x11f01,), # Kawi Sign Candrabindu ..Kawi Sign Anusvara + (0x11f03, 0x11f03,), # Kawi Sign Visarga + (0x11f34, 0x11f3a,), # Kawi Vowel Sign Aa ..Kawi Vowel Sign Vocalic + (0x11f3e, 0x11f42,), # Kawi Vowel Sign E ..Kawi Conjoiner + (0x11f5a, 0x11f5a,), # (nil) + (0x13430, 0x13440,), # Egyptian Hieroglyph Vert..Egyptian Hieroglyph Mirr + (0x13447, 0x13455,), # Egyptian Hieroglyph Modi..Egyptian Hieroglyph Modi + (0x1611e, 0x1612f,), # (nil) + (0x16af0, 0x16af4,), # Bassa Vah Combining High..Bassa Vah Combining High + (0x16b30, 0x16b36,), # Pahawh Hmong Mark Cim Tu..Pahawh Hmong Mark Cim Ta + (0x16f4f, 0x16f4f,), # Miao Sign Consonant Modifier Bar + (0x16f51, 0x16f87,), # Miao Sign Aspiration ..Miao Vowel Sign Ui + (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below + (0x16fe4, 0x16fe4,), # Khitan Small Script Filler + (0x16ff0, 0x16ff1,), # Vietnamese Alternate Rea..Vietnamese Alternate Rea + (0x1bc9d, 0x1bc9e,), # Duployan Thick Letter Se..Duployan Double Mark + (0x1bca0, 0x1bca3,), # Shorthand Format Letter ..Shorthand Format Up Step + (0x1cf00, 0x1cf2d,), # Znamenny Combining Mark ..Znamenny Combining Mark + (0x1cf30, 0x1cf46,), # Znamenny Combining Tonal..Znamenny Priznak Modifie + (0x1d165, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining + (0x1d16d, 0x1d182,), # Musical Symbol Combining..Musical Symbol Combining + (0x1d185, 0x1d18b,), # Musical Symbol Combining..Musical Symbol Combining + (0x1d1aa, 0x1d1ad,), # Musical Symbol Combining..Musical Symbol Combining + (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical + (0x1da00, 0x1da36,), # Signwriting Head Rim ..Signwriting Air Sucking + (0x1da3b, 0x1da6c,), # Signwriting Mouth Closed..Signwriting Excitement + (0x1da75, 0x1da75,), # Signwriting Upper Body Tilting From Hip Joints + (0x1da84, 0x1da84,), # Signwriting Location Head Neck + (0x1da9b, 0x1da9f,), # Signwriting Fill Modifie..Signwriting Fill Modifie + (0x1daa1, 0x1daaf,), # Signwriting Rotation Mod..Signwriting Rotation Mod + (0x1e000, 0x1e006,), # Combining Glagolitic Let..Combining Glagolitic Let + (0x1e008, 0x1e018,), # Combining Glagolitic Let..Combining Glagolitic Let + (0x1e01b, 0x1e021,), # Combining Glagolitic Let..Combining Glagolitic Let + (0x1e023, 0x1e024,), # Combining Glagolitic Let..Combining Glagolitic Let + (0x1e026, 0x1e02a,), # Combining Glagolitic Let..Combining Glagolitic Let + (0x1e08f, 0x1e08f,), # Combining Cyrillic Small Letter Byelorussian-ukr + (0x1e130, 0x1e136,), # Nyiakeng Puachue Hmong T..Nyiakeng Puachue Hmong T + (0x1e2ae, 0x1e2ae,), # Toto Sign Rising Tone + (0x1e2ec, 0x1e2ef,), # Wancho Tone Tup ..Wancho Tone Koini + (0x1e4ec, 0x1e4ef,), # Nag Mundari Sign Muhor ..Nag Mundari Sign Sutuh + (0x1e5ee, 0x1e5ef,), # (nil) + (0x1e6e3, 0x1e6e3,), # (nil) + (0x1e6e6, 0x1e6e6,), # (nil) + (0x1e6ee, 0x1e6ef,), # (nil) + (0x1e6f5, 0x1e6f5,), # (nil) + (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining + (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta + (0x1f3fb, 0x1f3ff,), # Emoji Modifier Fitzpatri..Emoji Modifier Fitzpatri + (0xe0001, 0xe0001,), # Language Tag + (0xe0020, 0xe007f,), # Tag Space ..Cancel Tag + (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 + ), } diff --git a/contrib/python/wcwidth/py3/wcwidth/unicode_versions.py b/contrib/python/wcwidth/py3/wcwidth/unicode_versions.py index 4e9ccbf7a71..4d140c181a7 100644 --- a/contrib/python/wcwidth/py3/wcwidth/unicode_versions.py +++ b/contrib/python/wcwidth/py3/wcwidth/unicode_versions.py @@ -1,7 +1,7 @@ """ Exports function list_versions() for unicode version level support. -This code generated by wcwidth/bin/update-tables.py on 2023-09-14 15:45:33 UTC. +This code generated by wcwidth/bin/update-tables.py on 2025-09-15 16:57:50 UTC. """ @@ -35,4 +35,6 @@ def list_versions(): "14.0.0", "15.0.0", "15.1.0", + "16.0.0", + "17.0.0", ) diff --git a/contrib/python/wcwidth/py3/wcwidth/wcwidth.py b/contrib/python/wcwidth/py3/wcwidth/wcwidth.py index e924020630c..92ca14afba1 100644 --- a/contrib/python/wcwidth/py3/wcwidth/wcwidth.py +++ b/contrib/python/wcwidth/py3/wcwidth/wcwidth.py @@ -60,12 +60,11 @@ http://www.unicode.org/unicode/reports/tr11/ Latest version: http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c """ -from __future__ import division # std imports import os -import sys import warnings +from functools import lru_cache # local from .table_vs16 import VS16_NARROW_TO_WIDE @@ -73,17 +72,6 @@ from .table_wide import WIDE_EASTASIAN from .table_zero import ZERO_WIDTH from .unicode_versions import list_versions -try: - # std imports - from functools import lru_cache -except ImportError: - # lru_cache was added in Python 3.2 - # 3rd party - from backports.functools_lru_cache import lru_cache - -# global cache -_PY3 = sys.version_info[0] >= 3 - def _bisearch(ucs, table): """ @@ -186,11 +174,11 @@ def wcswidth(pwcs, n=None, unicode_version='auto'): last_measured_char = None while idx < end: char = pwcs[idx] - if char == u'\u200D': + if char == '\u200D': # Zero Width Joiner, do not measure this or next character idx += 2 continue - if char == u'\uFE0F' and last_measured_char: + if char == '\uFE0F' and last_measured_char: # on variation selector 16 (VS16) following another character, # conditionally add '1' to the measured width if that character is # known to be converted from narrow to wide by the VS16 character. @@ -250,8 +238,7 @@ def _wcmatch_version(given_version): ``UNICODE_VERSION``. If the environment variable is not set, then the latest is used. :rtype: str - :returns: unicode string, or non-unicode ``str`` type for python 2 - when given ``version`` is also type ``str``. + :returns: unicode string. """ # Design note: the choice to return the same type that is given certainly # complicates it for python 2 str-type, but allows us to define an api that @@ -261,30 +248,24 @@ def _wcmatch_version(given_version): # That, along with the string-to-numeric and comparisons of earliest, # latest, matching, or nearest, greatly complicates this function. # Performance is somewhat curbed by memoization. - _return_str = not _PY3 and isinstance(given_version, str) - - if _return_str: - # avoid list-comprehension to work around a coverage issue: - # https://github.com/nedbat/coveragepy/issues/753 - unicode_versions = list(map(lambda ucs: ucs.encode(), list_versions())) - else: - unicode_versions = list_versions() + + unicode_versions = list_versions() latest_version = unicode_versions[-1] - if given_version in (u'auto', 'auto'): + if given_version == 'auto': given_version = os.environ.get( 'UNICODE_VERSION', - 'latest' if not _return_str else latest_version.encode()) + 'latest') - if given_version in (u'latest', 'latest'): + if given_version == 'latest': # default match, when given as 'latest', use the most latest unicode # version specification level supported. - return latest_version if not _return_str else latest_version.encode() + return latest_version if given_version in unicode_versions: # exact match, downstream has specified an explicit matching version # matching any value of list_versions(). - return given_version if not _return_str else given_version.encode() + return given_version # The user's version is not supported by ours. We return the newest unicode # version level that we support below their given value. @@ -298,7 +279,7 @@ def _wcmatch_version(given_version): "supported unicode version {latest_version!r} has been " "inferred.".format(given_version=given_version, latest_version=latest_version)) - return latest_version if not _return_str else latest_version.encode() + return latest_version # given version is less than any available version, return earliest # version. @@ -314,7 +295,7 @@ def _wcmatch_version(given_version): "version level, {earliest_version!r}".format( given_version=given_version, earliest_version=earliest_version)) - return earliest_version if not _return_str else earliest_version.encode() + return earliest_version # create list of versions which are less than our equal to given version, # and return the tail value, which is the highest level we may support, @@ -328,7 +309,7 @@ def _wcmatch_version(given_version): cmp_next_version = _wcversion_value(unicode_versions[idx + 1]) except IndexError: # at end of list, return latest version - return latest_version if not _return_str else latest_version.encode() + return latest_version # Maybe our given version has less parts, as in tuple(8, 0), than the # next compare version tuple(8, 0, 0). Test for an exact match by @@ -338,7 +319,7 @@ def _wcmatch_version(given_version): # Or, if any next value is greater than our given support level # version, return the current value in index. Even though it must - # be less than the given value, its our closest possible match. That + # be less than the given value, it's our closest possible match. That # is, 4.1 is returned for given 4.9.9, where 4.1 and 5.0 are available. if cmp_next_version > cmp_given: return unicode_version diff --git a/contrib/python/wcwidth/py3/ya.make b/contrib/python/wcwidth/py3/ya.make index 6d2ab552d88..7f889617c63 100644 --- a/contrib/python/wcwidth/py3/ya.make +++ b/contrib/python/wcwidth/py3/ya.make @@ -2,7 +2,7 @@ PY3_LIBRARY() -VERSION(0.2.13) +VERSION(0.2.14) LICENSE(MIT) @@ -11,6 +11,7 @@ NO_LINT() PY_SRCS( TOP_LEVEL wcwidth/__init__.py + wcwidth/table_vs15.py wcwidth/table_vs16.py wcwidth/table_wide.py wcwidth/table_zero.py |