mirror of
https://github.com/php/php-src.git
synced 2024-09-22 10:27:25 +00:00
d3933e0b6c
Some of the legacy text encodings which were used in this regression test are deprecated in PHP-8.2+. The deprecation warnings break the expected output. Since using these encodings in mbstring is now deprecated, I think there is little point in keeping them in this test. So they are now removed from it. Further, in219fff376b, I made a change to avoid a situation where the legacy UTF7-IMAP conversion code gets stuck in a wrong state when its attempt to emit a character fails. When a Base64-encoded section of input ended with -, the previous code would FIRST emit a character if necessary (using the CK or "check" macro, which causes the function to return immediately if the downstream filter function returns an error code), and THEN update its own state to indicate that it is now in ASCII rather than Base64 mode. If the downstream filter function returned an error code, the CK macro would then cause the UTF7-IMAP filter function to return immediately WITHOUT setting its own state to indicate that the Base64-encoded section was done. I fixed this by updating the filter state as needed BEFORE calling CK... but I missed updating the filter state in the case where the Base64 section ends normally and there is no need to emit anything. Again, in6d525a425e, I modified the legacy conversion code for ISO-2022-KR to try to comply more closely with the RFC for this text encoding. The RFC states that before any occurrence of 'Shift In' or 'Shift Out' codes in a ISO-2022-KR string, a special escape sequence must appear at least ONCE, at the beginning of a line. The previous code did not comply with this requirement. I made it comply by always emitting this escape sequence at the beginning of the first line. Since mb_strcut (wrongly) determines when it has consumed enough of the input string by looking at the length of its output in bytes, this extra escape sequence makes mb_strcut consume 4 bytes less of an ISO-2022-KR string than would otherwise be the case. When this strange behavior of mb_strcut is fixed, this test will have to be adjusted to restore the previous expected outputs for ISO-2022-KR.
170 lines
4.4 KiB
PHP
170 lines
4.4 KiB
PHP
--TEST--
|
|
GH-9535 (mb_strcut(): The behavior of mb_strcut in mbstring has been changed in PHP8.1)
|
|
--EXTENSIONS--
|
|
mbstring
|
|
--FILE--
|
|
<?php
|
|
$encodings = [
|
|
'UTF-16',
|
|
'UTF-16BE',
|
|
'UTF-16LE',
|
|
'UTF-7',
|
|
'UTF7-IMAP',
|
|
'ISO-2022-JP-MS',
|
|
'GB18030',
|
|
'HZ',
|
|
'ISO-2022-KR',
|
|
'ISO-2022-JP-MOBILE#KDDI',
|
|
'CP50220',
|
|
'CP50221',
|
|
'CP50222',
|
|
];
|
|
|
|
$input = '宛如繁星般宛如皎月般';
|
|
$bytes_length = 15;
|
|
foreach($encodings as $encoding) {
|
|
$converted_str = mb_convert_encoding($input, $encoding, mb_internal_encoding());
|
|
$cut_str = mb_strcut($converted_str, 0, $bytes_length, $encoding);
|
|
$reconverted_str = mb_convert_encoding($cut_str, mb_internal_encoding(), $encoding);
|
|
echo $encoding.': '.$reconverted_str.PHP_EOL;
|
|
}
|
|
|
|
echo PHP_EOL;
|
|
|
|
$input = '星のように月のように';
|
|
$bytes_length = 20;
|
|
foreach($encodings as $encoding) {
|
|
$converted_str = mb_convert_encoding($input, $encoding, mb_internal_encoding());
|
|
$cut_str = mb_strcut($converted_str, 0, $bytes_length, $encoding);
|
|
$reconverted_str = mb_convert_encoding($cut_str, mb_internal_encoding(), $encoding);
|
|
echo $encoding.': '.$reconverted_str.PHP_EOL;
|
|
}
|
|
|
|
echo PHP_EOL;
|
|
|
|
$input = 'あaいb';
|
|
$bytes_length = 10;
|
|
foreach($encodings as $encoding) {
|
|
$converted_str = mb_convert_encoding($input, $encoding, mb_internal_encoding());
|
|
$cut_str = mb_strcut($converted_str, 0, $bytes_length, $encoding);
|
|
$reconverted_str = mb_convert_encoding($cut_str, mb_internal_encoding(), $encoding);
|
|
echo $encoding.': '.$reconverted_str.PHP_EOL;
|
|
}
|
|
|
|
echo PHP_EOL;
|
|
|
|
$input = 'AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA';
|
|
$bytes_length = 10;
|
|
// For ISO-2022-KR, the initial escape sequence 'ESC $ ) C' will occupy 4 bytes of the output;
|
|
// this will make mb_strcut only pick out 6 'A' characters from the input string and not 10
|
|
foreach($encodings as $encoding) {
|
|
$converted_str = mb_convert_encoding($input, $encoding, mb_internal_encoding());
|
|
$cut_str = mb_strcut($converted_str, 0, $bytes_length, $encoding);
|
|
$reconverted_str = mb_convert_encoding($cut_str, mb_internal_encoding(), $encoding);
|
|
echo $encoding.': '.$reconverted_str.PHP_EOL;
|
|
}
|
|
|
|
echo PHP_EOL;
|
|
|
|
$input = '???';
|
|
$bytes_length = 2;
|
|
// ISO-2022-KR will be affected by the initial escape sequence as stated above
|
|
foreach($encodings as $encoding) {
|
|
$converted_str = mb_convert_encoding($input, $encoding, mb_internal_encoding());
|
|
$cut_str = mb_strcut($converted_str, 0, $bytes_length, $encoding);
|
|
$reconverted_str = mb_convert_encoding($cut_str, mb_internal_encoding(), $encoding);
|
|
echo $encoding.trim(': '.$reconverted_str).PHP_EOL;
|
|
}
|
|
|
|
echo PHP_EOL;
|
|
|
|
foreach($encodings as $encoding) {
|
|
echo $encoding.trim(': '.mb_strcut($input, 0, $bytes_length, $encoding)).PHP_EOL;
|
|
}
|
|
|
|
?>
|
|
--EXPECT--
|
|
UTF-16: 宛如繁星般宛如
|
|
UTF-16BE: 宛如繁星般宛如
|
|
UTF-16LE: 宛如繁星般宛如
|
|
UTF-7: 宛如繁星
|
|
UTF7-IMAP: 宛如繁星
|
|
ISO-2022-JP-MS: 宛如繁星
|
|
GB18030: 宛如繁星般宛如
|
|
HZ: 宛如繁星般
|
|
ISO-2022-KR: 宛如繁星
|
|
ISO-2022-JP-MOBILE#KDDI: 宛如繁星
|
|
CP50220: 宛如繁星
|
|
CP50221: 宛如繁星
|
|
CP50222: 宛如繁星
|
|
|
|
UTF-16: 星のように月のように
|
|
UTF-16BE: 星のように月のように
|
|
UTF-16LE: 星のように月のように
|
|
UTF-7: 星のように月
|
|
UTF7-IMAP: 星のように月
|
|
ISO-2022-JP-MS: 星のように月の
|
|
GB18030: 星のように月のように
|
|
HZ: 星のように月のよ
|
|
ISO-2022-KR: 星のように月の
|
|
ISO-2022-JP-MOBILE#KDDI: 星のように月の
|
|
CP50220: 星のように月の
|
|
CP50221: 星のように月の
|
|
CP50222: 星のように月の
|
|
|
|
UTF-16: あaいb
|
|
UTF-16BE: あaいb
|
|
UTF-16LE: あaいb
|
|
UTF-7: あa
|
|
UTF7-IMAP: あa
|
|
ISO-2022-JP-MS: あa
|
|
GB18030: あaいb
|
|
HZ: あa
|
|
ISO-2022-KR: あa
|
|
ISO-2022-JP-MOBILE#KDDI: あa
|
|
CP50220: あa
|
|
CP50221: あa
|
|
CP50222: あa
|
|
|
|
UTF-16: AAAAA
|
|
UTF-16BE: AAAAA
|
|
UTF-16LE: AAAAA
|
|
UTF-7: AAAAAAAAAA
|
|
UTF7-IMAP: AAAAAAAAAA
|
|
ISO-2022-JP-MS: AAAAAAAAAA
|
|
GB18030: AAAAAAAAAA
|
|
HZ: AAAAAAAAAA
|
|
ISO-2022-KR: AAAAAA
|
|
ISO-2022-JP-MOBILE#KDDI: AAAAAAAAAA
|
|
CP50220: AAAAAAAAAA
|
|
CP50221: AAAAAAAAAA
|
|
CP50222: AAAAAAAAAA
|
|
|
|
UTF-16: ?
|
|
UTF-16BE: ?
|
|
UTF-16LE: ?
|
|
UTF-7: ??
|
|
UTF7-IMAP: ??
|
|
ISO-2022-JP-MS: ??
|
|
GB18030: ??
|
|
HZ: ??
|
|
ISO-2022-KR:
|
|
ISO-2022-JP-MOBILE#KDDI: ??
|
|
CP50220: ??
|
|
CP50221: ??
|
|
CP50222: ??
|
|
|
|
UTF-16: ??
|
|
UTF-16BE: ??
|
|
UTF-16LE: ??
|
|
UTF-7: ??
|
|
UTF7-IMAP: ??
|
|
ISO-2022-JP-MS: ??
|
|
GB18030: ??
|
|
HZ: ??
|
|
ISO-2022-KR:
|
|
ISO-2022-JP-MOBILE#KDDI: ??
|
|
CP50220: ??
|
|
CP50221: ??
|
|
CP50222: ??
|