Skip to content

ENH: add support for Unicode 17.0.0 #96

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
brunato merged 1 commit into from
Oct 19, 2025
Merged

ENH: add support for Unicode 17.0.0 #96

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 12 additions & 1 deletion elementpath/regex/unicode_blocks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
#
# Copyright (c), 2018-2024, SISSA (International School for Advanced Studies).
# Copyright (c), 2018-2025, SISSA (International School for Advanced Studies).
# All rights reserved.
# This file is distributed under the terms of the MIT License.
# See the file 'LICENSE' in the root directory of the present
Expand Down Expand Up @@ -448,3 +448,14 @@
'Symbols for Legacy Computing Supplement': '\U0001CC00-\U0001CEBF',
'Ol Onal': '\U0001E5D0-\U0001E5FF'
}

UPDATE_BLOCKS_VER_17_0_0 = {
'Sidetic': '\U00010940-\U0001095F',
'Sharada Supplement': '\U00011B60-\U00011B7F',
'Tolong Siki': '\U00011DB0-\U00011DEF',
'Beria Erfe': '\U00016EA0-\U00016EDF',
'Tangut Components Supplement': '\U00018D80-\U00018DFF',
'Miscellaneous Symbols Supplement': '\U0001CEC0-\U0001CEFF',
'Tai Yo': '\U0001E6C0-\U0001E6FF',
'CJK Unified Ideographs Extension J': '\U000323B0-\U0003347F'
}
99 changes: 97 additions & 2 deletions elementpath/regex/unicode_categories.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
#
# Copyright (c), 2018-2024, SISSA (International School for Advanced Studies).
# Copyright (c), 2018-2025, SISSA (International School for Advanced Studies).
# All rights reserved.
# This file is distributed under the terms of the MIT License.
# See the file 'LICENSE' in the root directory of the present
Expand All @@ -10,7 +10,7 @@
# --- Auto-generated code: don't edit this file ---
#
UNICODE_VERSIONS = [
'12.1.0', '13.0.0', '14.0.0', '15.0.0', '15.1.0', '16.0.0'
'12.1.0', '13.0.0', '14.0.0', '15.0.0', '15.1.0', '16.0.0', '17.0.0'
]

UNICODE_CATEGORIES = {
Expand Down Expand Up @@ -1452,3 +1452,98 @@
(129200, 129212), (129216, 129218), (129664, 129674), (129679, 129735),
(129742, 129757), (129759, 129770), (129940, 130032)])
}

DIFF_CATEGORIES_VER_17_0_0 = {
'C': ([(2191, 2199), (3163, 3165), (3287, 3293), (6863, 6912), (8385, 8400),
11158, (42958, 42960), 42962, 42964, (42973, 42994), (64451, 64467),
(64912, 64914), (64968, 64975), (67904, 67968), (69317, 69372),
(72458, 72640), (73130, 73440), (93851, 93952), (94194, 94208),
(100344, 100352), (101641, 110576), (118010, 118016), (118452, 118528),
(124416, 124896), (128728, 128732), (128887, 128891), (129218, 129280),
(129620, 129632), (129674, 129679), (129735, 129742), (129770, 129776),
(130042, 131072), (177978, 177984), (183970, 183984),
(205744, 917760)],
[(2192, 2199), 3163, (3287, 3292), (6878, 6880), (6892, 6912),
(8386, 8400), (42973, 42993), (67930, 67968), (69320, 69328),
(69337, 69370), (72458, 72544), (72552, 72640), (73130, 73136),
(73180, 73184), (73194, 73440), (93851, 93856), (93881, 93883),
(93908, 93952), (94199, 94208), (101663, 101760), (101875, 110576),
(118013, 118016), (118452, 118458), (118481, 118496), (118513, 118528),
(124416, 124608), 124639, (124662, 124670), (124672, 124896),
(128729, 128732), (129218, 129232), (129241, 129280), (129624, 129632),
(129675, 129678), 129735, (129737, 129741), (129771, 129775),
(130043, 131072), (183982, 183984), (210042, 917760)]),
'Cn': ([2191, (3163, 3165), (3287, 3293), (6863, 6912), (8385, 8400), 11158,
(42958, 42960), 42962, 42964, (42973, 42994), (64451, 64467),
(64912, 64914), (64968, 64975), (67904, 67968), (69317, 69372),
(72458, 72640), (73130, 73440), (93851, 93952), (94194, 94208),
(100344, 100352), (101641, 110576), (118010, 118016), (118452, 118528),
(124416, 124896), (128728, 128732), (128887, 128891), (129218, 129280),
(129620, 129632), (129674, 129679), (129735, 129742), (129770, 129776),
(130042, 131072), (177978, 177984), (183970, 183984),
(205744, 917505)],
[3163, (3287, 3292), (6878, 6880), (6892, 6912), (8386, 8400),
(42973, 42993), (67930, 67968), (69320, 69328), (69337, 69370),
(72458, 72544), (72552, 72640), (73130, 73136), (73180, 73184),
(73194, 73440), (93851, 93856), (93881, 93883), (93908, 93952),
(94199, 94208), (101663, 101760), (101875, 110576), (118013, 118016),
(118452, 118458), (118481, 118496), (118513, 118528), (124416, 124608),
124639, (124662, 124670), (124672, 124896), (128729, 128732),
(129218, 129232), (129241, 129280), (129624, 129632), (129675, 129678),
129735, (129737, 129741), (129771, 129775), (130043, 131072),
(183982, 183984), (210042, 917505)]),
'L': ([(2185, 2191), 3165, (3293, 3295), (42891, 42958), (42960, 42962), 42963,
(42965, 42973), (42994, 43010), (69314, 69317), (94208, 100344),
(100352, 101590), (101631, 101641), (173824, 177978), (177984, 178206),
(178208, 183970), (201552, 205744)],
[(2185, 2192), (3164, 3166), (3292, 3295), (42891, 42973),
(42993, 43010), (67904, 67930), (69314, 69320), (73136, 73180),
(93856, 93881), (93883, 93908), (94194, 94196), (94208, 101590),
(101631, 101663), (101760, 101875), (124608, 124639), (124640, 124643),
(124644, 124646), (124647, 124654), (124656, 124661), (124670, 124672),
(173824, 178206), (178208, 183982), (201552, 210042)]),
'Ll': ([(661, 688)], [(662, 688), 42959, (93883, 93908)]),
'Lm': ([(42994, 42997)],
[(42993, 42997), 69317, 73177, (94194, 94196), 124671]),
'Lo': ([660, (2185, 2191), 3165, (3293, 3295), (94208, 100344),
(100352, 101590), (101631, 101641), (173824, 177978), (177984, 178206),
(178208, 183970), (201552, 205744)],
[(660, 662), (2185, 2192), (3164, 3166), (3292, 3295), (67904, 67930),
(69318, 69320), (73136, 73177), (73178, 73180), (94208, 101590),
(101631, 101663), (101760, 101875), (124608, 124639), (124640, 124643),
(124644, 124646), (124647, 124654), (124656, 124661), 124670,
(173824, 178206), (178208, 183982), (201552, 210042)]),
'Lu': ([], [42958, 42962, 42964, (93856, 93881)]),
'M': ([(6832, 6863), (69372, 69376)],
[(6832, 6878), (6880, 6892), (69370, 69376), (72544, 72552), 124643,
124646, (124654, 124656), 124661]),
'Mc': ([], [72545, 72549, 72551]),
'Mn': ([(6847, 6863), (69372, 69376)],
[(6847, 6878), (6880, 6892), (69370, 69376), 72544, (72546, 72549),
72550, 124643, 124646, (124654, 124656), 124661]),
'N': ([], [(73184, 73194), (94196, 94199)]),
'Nd': ([], [(73184, 73194)]),
'Nl': ([], [(94196, 94199)]),
'P': ([], [69328]),
'Po': ([], [69328]),
'S': ([(8352, 8385), (11126, 11158), (11159, 11264), (64434, 64451), 64975,
(127744, 128728), (128768, 128887), (128891, 128986), (129280, 129620),
(129664, 129674), (129679, 129735), (129742, 129757), (129759, 129770),
(129776, 129785)],
[(8352, 8386), (11126, 11264), (64434, 64467), (64912, 64914),
(64968, 64976), (69329, 69337), (118010, 118013), (118458, 118481),
(118496, 118513), (127744, 128729), (128768, 128986), (129232, 129241),
(129280, 129624), (129664, 129675), (129678, 129735), 129736,
(129741, 129757), (129759, 129771), (129775, 129785), 130042]),
'Sc': ([(8352, 8385)], [(8352, 8386)]),
'Sm': ([], [118512, (129232, 129241)]),
'So': ([(11126, 11158), (11159, 11264), 64975, (128000, 128728),
(128768, 128887), (128891, 128986), (129280, 129620), (129664, 129674),
(129679, 129735), (129742, 129757), (129759, 129770),
(129776, 129785)],
[(11126, 11264), (64451, 64467), (64912, 64914), (64968, 64976),
(69329, 69337), (118010, 118013), (118458, 118481), (118496, 118512),
(128000, 128729), (128768, 128986), (129280, 129624), (129664, 129675),
(129678, 129735), 129736, (129741, 129757), (129759, 129771),
(129775, 129785), 130042])
}
3 changes: 2 additions & 1 deletion scripts/generate_codepoints.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,7 @@
UNICODE_DATA_BASE_URL = "https://www.unicode.org/Public/"

UNICODE_VERSIONS = {
'17.0.0': ('17.0.0/ucd/UnicodeData.txt', '17.0.0/ucd/Blocks.txt'),
'16.0.0': ('16.0.0/ucd/UnicodeData.txt', '16.0.0/ucd/Blocks.txt'),
'15.1.0': ('15.1.0/ucd/UnicodeData.txt', '15.1.0/ucd/Blocks.txt'),
'15.0.0': ('15.0.0/ucd/UnicodeData.txt', '15.0.0/ucd/Blocks.txt'),
Expand Down Expand Up @@ -85,7 +86,7 @@
)


DEFAULT_CATEGORIES_VERSIONS = ['12.1.0', '13.0.0', '14.0.0', '15.0.0', '15.1.0', '16.0.0']
DEFAULT_CATEGORIES_VERSIONS = ['12.1.0', '13.0.0', '14.0.0', '15.0.0', '15.1.0', '16.0.0', '17.0.0']


def version_number(value):
Expand Down