RGBCube/serenity
1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-05-30 21:28:11 +00:00
Code Issues Activity Actions

LibUnicode: Parse and generate case folding code point data

Browse source 
Case folding rules have a similar mapping style as special casing rules,
where one code point may map to zero or more case folding rules. These
will be used for case-insensitive string comparisons. To see how case
folding can differ from other casing rules, consider "ß" (U+00DF):

    >>> "ß".lower()
    'ß'

    >>> "ß".upper()
    'SS'

    >>> "ß".title()
    'Ss'

    >>> "ß".casefold()
    'ss'
This commit is contained in:
Timothy Flynn 2023-01-17 08:34:38 -05:00 • committed by Linus Groh
parent 9226cf7272
commit 8f2589b3b0
7 changed files with 207 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

27
Tests/LibUnicode/TestUnicodeCharacterTypes.cpp
View file

@ -97,6 +97,33 @@ TEST_CASE(to_unicode_titlecase)
EXPECT_EQ(MUST(Unicode::to_unicode_titlecase_full("123dollars"sv)), "123Dollars"sv);
}
TEST_CASE(to_unicode_casefold)
{
for (u8 code_point = 0; code_point < 0x80; ++code_point) {
auto ascii = tolower(code_point);
auto unicode = MUST(Unicode::to_unicode_casefold_full({ reinterpret_cast<char const*>(&code_point), 1 }));
EXPECT_EQ(unicode.bytes_as_string_view().length(), 1u);
EXPECT_EQ(unicode.bytes_as_string_view()[0], ascii);
}
// LATIN SMALL LETTER SHARP S
auto result = MUST(Unicode::to_unicode_casefold_full("\u00DF"sv));
EXPECT_EQ(result, "\u0073\u0073"sv);
// GREEK SMALL LETTER ALPHA WITH YPOGEGRAMMENI
result = MUST(Unicode::to_unicode_casefold_full("\u1FB3"sv));
EXPECT_EQ(result, "\u03B1\u03B9"sv);
// GREEK SMALL LETTER ALPHA WITH PERISPOMENI
result = MUST(Unicode::to_unicode_casefold_full("\u1FB6"sv));
EXPECT_EQ(result, "\u03B1\u0342"sv);
// GREEK SMALL LETTER ALPHA WITH PERISPOMENI AND YPOGEGRAMMENI
result = MUST(Unicode::to_unicode_casefold_full("\u1FB7"sv));
EXPECT_EQ(result, "\u03B1\u0342\u03B9"sv);
}
TEST_CASE(to_unicode_lowercase_unconditional_special_casing)
{
// LATIN SMALL LETTER SHARP S