diff options
| author | dirkf <fieldhouse@gmx.net> | 2022-11-01 19:25:59 +0000 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2022-11-01 19:25:59 +0000 |
| commit | a874871801b8b05d06e8ffe52bed94fdfc26611e (patch) | |
| tree | 4502970c3207145a387528a066fb228842544ef6 | |
| parent | b7c25959f0f76aad4ee24e254f82e6c5cca2c1ff (diff) | |
| download | youtube-dl-a874871801b8b05d06e8ffe52bed94fdfc26611e.tar.gz youtube-dl-a874871801b8b05d06e8ffe52bed94fdfc26611e.tar.xz youtube-dl-a874871801b8b05d06e8ffe52bed94fdfc26611e.zip | |
[compat] Reformat casefold.py for easier updating
| -rw-r--r-- | youtube_dl/casefold.py | 24 |
1 files changed, 20 insertions, 4 deletions
diff --git a/youtube_dl/casefold.py b/youtube_dl/casefold.py index 546269a3c..7e91c3811 100644 --- a/youtube_dl/casefold.py +++ b/youtube_dl/casefold.py @@ -1,8 +1,20 @@ # coding: utf-8 from __future__ import unicode_literals -from .compat import compat_str +from .compat import ( + compat_str, + compat_chr, +) +# Below is included the text of icu/CaseFolding.txt retrieved from +# https://github.com/unicode-org/icu/blob/main/icu4c/source/data/unidata/CaseFolding.txt +# In case newly foldable Unicode characters are defined, paste the new version +# of the text inside the ''' marks. +# The text is expected to have only blank lines andlines with 1st character #, +# all ignored, and fold definitions like this: +# `from_hex_code; space_separated_to_hex_code_list; comment` + +_map_str = ''' # CaseFolding-15.0.0.txt # Date: 2022-02-02, 23:35:35 GMT # © 2022 Unicode®, Inc. @@ -65,7 +77,6 @@ from .compat import compat_str # have the value C for the status field, and the code point itself for the mapping field. # ================================================================= -_map_str = ''' 0041; C; 0061; # LATIN CAPITAL LETTER A 0042; C; 0062; # LATIN CAPITAL LETTER B 0043; C; 0063; # LATIN CAPITAL LETTER C @@ -1627,17 +1638,22 @@ FF3A; C; FF5A; # FULLWIDTH LATIN CAPITAL LETTER Z 1E920; C; 1E942; # ADLAM CAPITAL LETTER KPO 1E921; C; 1E943; # ADLAM CAPITAL LETTER SHA ''' + +_parse_unichr = lambda s: compat_chr(int(s, 16)) + _map = dict( - (unichr(int(from_, 16)), ''.join((unichr(int(v, 16)) for v in to_.split(' ')))) + (_parse_unichr(from_), ''.join(map(_parse_unichr, to_.split(' ')))) for from_, type_, to_, _ in ( - l.split('; ', 3) for l in _map_str.splitlines() if l) + l.split('; ', 3) for l in _map_str.splitlines() if l and not l[0] == '#') if type_ in ('C', 'F')) del _map_str + def casefold(s): assert isinstance(s, compat_str) return ''.join((_map.get(c, c) for c in s)) + __all__ = [ casefold ] |