mirror of
https://github.com/php/php-src.git
synced 2026-04-18 21:41:22 +02:00
582a65b06f
Implement full case mapping according to SpecialCasing.txt and also full case folding according to CaseFolding.txt (F). There are a number of caveats: * Only language-agnostic and unconditional full case mapping is implemented. The only language-agnostic conditional case mapping rule relates to Greek sigma in final position (Final_Sigma). Correctly handling this requires both arbitrary lookahead and lookbehind, which would require some larger changes to how the case mapping is implemented. This is a possible future extension. * The only language-specific handling that is implemented is for Turkish dotted/undotted Is, if the ISO-8859-9 encoding is used. This matches the previous behavior and makes sure that no codepoints not supported by the encoding are produced. A future extension would be to also handle the Turkish mappings specified by SpecialCasing.txt based on the mbfl internal language. * Full case folding is implemented, but case-insensitive mb_* operations continue to use simple case folding. The reason is that full case folding of the haystack string may change the position at which a match occurred. This would have to be mapped back into the position in the original string. * mb_convert_case() exposes both the full and the simple case mapping / folding, where full is the default. The constants are: * MB_CASE_LOWER (used by mb_strtolower) * MB_CASE_UPPER (used by mb_strtolower) * MB_CASE_TITLE * MB_CASE_FOLD * MB_CASE_LOWER_SIMPLE * MB_CASE_UPPER_SIMPLE * MB_CASE_TITLE_SIMPLE * MB_CASE_FOLD_SIMPLE (used by case-insensitive operations)
110 lines
2.5 KiB
PHP
110 lines
2.5 KiB
PHP
--TEST--
|
|
Unicode case mapping
|
|
--FILE--
|
|
<?php
|
|
|
|
function toCases($str) {
|
|
echo "String: $str\n";
|
|
echo "Lower: ", mb_convert_case($str, MB_CASE_LOWER), "\n";
|
|
echo "Lower Simple: ", mb_convert_case($str, MB_CASE_LOWER_SIMPLE), "\n";
|
|
echo "Upper: ", mb_convert_case($str, MB_CASE_UPPER), "\n";
|
|
echo "Upper Simple: ", mb_convert_case($str, MB_CASE_UPPER_SIMPLE), "\n";
|
|
echo "Title: ", mb_convert_case($str, MB_CASE_TITLE), "\n";
|
|
echo "Title Simple: ", mb_convert_case($str, MB_CASE_TITLE_SIMPLE), "\n";
|
|
echo "Fold: ", mb_convert_case($str, MB_CASE_FOLD), "\n";
|
|
echo "Fold Simple: ", mb_convert_case($str, MB_CASE_FOLD_SIMPLE), "\n";
|
|
echo "\n";
|
|
}
|
|
|
|
toCases("ß");
|
|
toCases("ff");
|
|
toCases("İ");
|
|
|
|
// Make sure that case-conversion in Turkish still works correctly.
|
|
// Using the language-agnostic Unicode case mappins would result in
|
|
// characters that are illegal under ISO-8859-9.
|
|
mb_internal_encoding('ISO-8859-9');
|
|
|
|
// Capital I with dot (U+0130)
|
|
$str = "\xdd";
|
|
echo bin2hex(mb_convert_case($str, MB_CASE_LOWER)), "\n";
|
|
echo bin2hex(mb_convert_case($str, MB_CASE_LOWER_SIMPLE)), "\n";
|
|
echo bin2hex(mb_convert_case($str, MB_CASE_FOLD)), "\n";
|
|
echo bin2hex(mb_convert_case($str, MB_CASE_FOLD_SIMPLE)), "\n";
|
|
echo "\n";
|
|
|
|
// Lower i without dot (U+0131)
|
|
$str = "\xfd";
|
|
echo bin2hex(mb_convert_case($str, MB_CASE_UPPER)), "\n";
|
|
echo bin2hex(mb_convert_case($str, MB_CASE_UPPER_SIMPLE)), "\n";
|
|
echo bin2hex(mb_convert_case($str, MB_CASE_FOLD)), "\n";
|
|
echo bin2hex(mb_convert_case($str, MB_CASE_FOLD_SIMPLE)), "\n";
|
|
echo "\n";
|
|
|
|
// Capital I without dot (U+0049)
|
|
$str = "\x49";
|
|
echo bin2hex(mb_convert_case($str, MB_CASE_LOWER)), "\n";
|
|
echo bin2hex(mb_convert_case($str, MB_CASE_LOWER_SIMPLE)), "\n";
|
|
echo bin2hex(mb_convert_case($str, MB_CASE_FOLD)), "\n";
|
|
echo bin2hex(mb_convert_case($str, MB_CASE_FOLD_SIMPLE)), "\n";
|
|
echo "\n";
|
|
|
|
// Lower i with dot (U+0069)
|
|
$str = "\x69";
|
|
echo bin2hex(mb_convert_case($str, MB_CASE_UPPER)), "\n";
|
|
echo bin2hex(mb_convert_case($str, MB_CASE_UPPER_SIMPLE)), "\n";
|
|
echo bin2hex(mb_convert_case($str, MB_CASE_FOLD)), "\n";
|
|
echo bin2hex(mb_convert_case($str, MB_CASE_FOLD_SIMPLE)), "\n";
|
|
|
|
?>
|
|
--EXPECT--
|
|
String: ß
|
|
Lower: ß
|
|
Lower Simple: ß
|
|
Upper: SS
|
|
Upper Simple: ß
|
|
Title: Ss
|
|
Title Simple: ß
|
|
Fold: ss
|
|
Fold Simple: ß
|
|
|
|
String: ff
|
|
Lower: ff
|
|
Lower Simple: ff
|
|
Upper: FF
|
|
Upper Simple: ff
|
|
Title: Ff
|
|
Title Simple: ff
|
|
Fold: ff
|
|
Fold Simple: ff
|
|
|
|
String: İ
|
|
Lower: i̇
|
|
Lower Simple: i
|
|
Upper: İ
|
|
Upper Simple: İ
|
|
Title: İ
|
|
Title Simple: İ
|
|
Fold: i̇
|
|
Fold Simple: İ
|
|
|
|
69
|
|
69
|
|
69
|
|
69
|
|
|
|
49
|
|
49
|
|
fd
|
|
fd
|
|
|
|
fd
|
|
fd
|
|
fd
|
|
fd
|
|
|
|
dd
|
|
dd
|
|
69
|
|
69
|