mirror of
https://github.com/php/php-src.git
synced 2026-04-05 07:02:33 +02:00
9308974f8c
The purpose of mbstring is for working with Unicode and legacy text encodings; but Base64, QPrint, etc. are not text encodings and don't really belong in mbstring. PHP already contains separate implementations of Base64, QPrint, and HTML entities. It will be better to eventually remove these non-encodings from mbstring. Regarding HTML entities... there is a bit more to say. mbstring's implementation of HTML entities is different from the other built-in implementation (htmlspecialchars and htmlentities). Those functions convert <, >, and & to HTML entities, but mbstring does not. It appears that the original author of mbstring intended for something to be done with <, >, and &. He used a table to identify which characters should be converted to HTML entities, and </>/& all have a special value in that table. However, nothing ever checks for that special value, so the characters are passed through unconverted. This seems like a very useless implementation of HTML entities. The most important characters which need to be expressed as entities in HTML documents are those three!
142 lines
4.5 KiB
PHP
142 lines
4.5 KiB
PHP
--TEST--
|
|
mb_convert_encoding()
|
|
--EXTENSIONS--
|
|
mbstring
|
|
--INI--
|
|
output_handler=
|
|
mbstring.language=Japanese
|
|
--FILE--
|
|
<?php
|
|
// TODO: Add more tests
|
|
|
|
// SJIS string (BASE64 encoded)
|
|
$sjis = base64_decode('k/qWe4zqg2WDTINYg2eCxYK3gUIwMTIzNIJUglWCVoJXgliBQg==');
|
|
// JIS string (BASE64 encoded)
|
|
$jis = base64_decode('GyRCRnxLXDhsJUYlLSU5JUgkRyQ5ISMbKEIwMTIzNBskQiM1IzYjNyM4IzkhIxsoQg==');
|
|
// EUC-JP string
|
|
$euc_jp = "\xC6\xFC\xCB\xDC\xB8\xEC\xA5\xC6\xA5\xAD\xA5\xB9\xA5\xC8\xA4\xC7\xA4\xB9\xA1\xA301234\xA3\xB5\xA3\xB6\xA3\xB7\xA3\xB8\xA3\xB9\xA1\xA3";
|
|
|
|
// Test with single "form encoding"
|
|
// Note: For some reason it complains, results are different. Not researched.
|
|
echo "== BASIC TEST ==\n";
|
|
$s = $sjis;
|
|
$s = bin2hex(mb_convert_encoding($s, 'EUC-JP', 'SJIS'));
|
|
print("EUC-JP: $s\n"); // EUC-JP
|
|
|
|
$s = $jis;
|
|
$s = bin2hex(mb_convert_encoding($s, 'EUC-JP', 'JIS'));
|
|
print("EUC-JP: $s\n"); // EUC-JP
|
|
|
|
$s = $euc_jp;
|
|
$s = mb_convert_encoding($s, 'SJIS', 'EUC-JP');
|
|
print("SJIS: ".base64_encode($s)."\n"); // SJIS
|
|
|
|
$s = $euc_jp;
|
|
$s = mb_convert_encoding($s, 'JIS', 'EUC-JP');
|
|
print("JIS: ".base64_encode($s)."\n"); // JIS
|
|
|
|
|
|
// Using Encoding List Array
|
|
echo "== STRING ENCODING LIST ==\n";
|
|
|
|
$a = 'JIS,UTF-8,EUC-JP,SJIS';
|
|
$s = $jis;
|
|
$s = bin2hex(mb_convert_encoding($s, 'EUC-JP', $a));
|
|
print("EUC-JP: $s\n"); // EUC-JP
|
|
|
|
$s = $euc_jp;
|
|
$s = mb_convert_encoding($s, 'SJIS', $a);
|
|
print("SJIS: ".base64_encode($s)."\n"); // SJIS
|
|
|
|
$s = $euc_jp;
|
|
$s = mb_convert_encoding($s, 'JIS', $a);
|
|
print("JIS: ".base64_encode($s)."\n"); // JIS
|
|
|
|
|
|
// Using Encoding List Array
|
|
echo "== ARRAY ENCODING LIST ==\n";
|
|
|
|
$a = array(0=>'JIS', 1=>'UTF-8', 2=>'EUC-JP', 3=>'SJIS');
|
|
$s = $jis;
|
|
$s = bin2hex(mb_convert_encoding($s, 'EUC-JP', $a));
|
|
print("EUC-JP: $s\n"); // EUC-JP
|
|
|
|
$s = $euc_jp;
|
|
$s = mb_convert_encoding($s, 'SJIS', $a);
|
|
print("SJIS: ".base64_encode($s)."\n"); // SJIS
|
|
|
|
$s = $euc_jp;
|
|
$s = mb_convert_encoding($s, 'JIS', $a);
|
|
print("JIS: ".base64_encode($s)."\n"); // JIS
|
|
|
|
|
|
// Using Detect Order
|
|
echo "== DETECT ORDER ==\n";
|
|
|
|
$s = $jis;
|
|
$s = bin2hex(mb_convert_encoding($s, 'EUC-JP', 'auto'));
|
|
print("EUC-JP: $s\n"); // EUC-JP
|
|
|
|
$s = $euc_jp;
|
|
$s = mb_convert_encoding($s, 'SJIS', 'auto');
|
|
print("SJIS: ".base64_encode($s)."\n"); // SJIS
|
|
|
|
$s = $euc_jp;
|
|
$s = mb_convert_encoding($s, 'JIS', 'auto');
|
|
print("JIS: ".base64_encode($s)."\n"); // JIS
|
|
|
|
echo "== INVALID PARAMETER ==\n";
|
|
|
|
$s = mb_convert_encoding(1234, 'EUC-JP');
|
|
print("INT: $s\n");
|
|
|
|
$s = mb_convert_encoding('', 'EUC-JP');
|
|
print("EUC-JP: $s\n"); // SJIS
|
|
|
|
function tryBadConversion($str, $encoding) {
|
|
try {
|
|
var_dump(mb_convert_encoding($str, $encoding));
|
|
} catch (ValueError $e) {
|
|
echo $e->getMessage(), "\n";
|
|
}
|
|
}
|
|
|
|
tryBadConversion($euc_jp, 'BAD');
|
|
|
|
tryBadConversion('abc', 'Quoted-Printable');
|
|
tryBadConversion('abc', 'BASE64');
|
|
tryBadConversion('abc', 'HTML-ENTITIES');
|
|
|
|
?>
|
|
--EXPECTF--
|
|
== BASIC TEST ==
|
|
EUC-JP: c6fccbdcb8eca5c6a5ada5b9a5c8a4c7a4b9a1a33031323334a3b5a3b6a3b7a3b8a3b9a1a3
|
|
EUC-JP: c6fccbdcb8eca5c6a5ada5b9a5c8a4c7a4b9a1a33031323334a3b5a3b6a3b7a3b8a3b9a1a3
|
|
SJIS: k/qWe4zqg2WDTINYg2eCxYK3gUIwMTIzNIJUglWCVoJXgliBQg==
|
|
JIS: GyRCRnxLXDhsJUYlLSU5JUgkRyQ5ISMbKEIwMTIzNBskQiM1IzYjNyM4IzkhIxsoQg==
|
|
== STRING ENCODING LIST ==
|
|
EUC-JP: c6fccbdcb8eca5c6a5ada5b9a5c8a4c7a4b9a1a33031323334a3b5a3b6a3b7a3b8a3b9a1a3
|
|
SJIS: k/qWe4zqg2WDTINYg2eCxYK3gUIwMTIzNIJUglWCVoJXgliBQg==
|
|
JIS: GyRCRnxLXDhsJUYlLSU5JUgkRyQ5ISMbKEIwMTIzNBskQiM1IzYjNyM4IzkhIxsoQg==
|
|
== ARRAY ENCODING LIST ==
|
|
EUC-JP: c6fccbdcb8eca5c6a5ada5b9a5c8a4c7a4b9a1a33031323334a3b5a3b6a3b7a3b8a3b9a1a3
|
|
SJIS: k/qWe4zqg2WDTINYg2eCxYK3gUIwMTIzNIJUglWCVoJXgliBQg==
|
|
JIS: GyRCRnxLXDhsJUYlLSU5JUgkRyQ5ISMbKEIwMTIzNBskQiM1IzYjNyM4IzkhIxsoQg==
|
|
== DETECT ORDER ==
|
|
EUC-JP: c6fccbdcb8eca5c6a5ada5b9a5c8a4c7a4b9a1a33031323334a3b5a3b6a3b7a3b8a3b9a1a3
|
|
SJIS: k/qWe4zqg2WDTINYg2eCxYK3gUIwMTIzNIJUglWCVoJXgliBQg==
|
|
JIS: GyRCRnxLXDhsJUYlLSU5JUgkRyQ5ISMbKEIwMTIzNBskQiM1IzYjNyM4IzkhIxsoQg==
|
|
== INVALID PARAMETER ==
|
|
INT: 1234
|
|
EUC-JP:
|
|
mb_convert_encoding(): Argument #2 ($to_encoding) must be a valid encoding, "BAD" given
|
|
|
|
Deprecated: mb_convert_encoding(): Handling QPrint via mbstring is deprecated; use quoted_printable_encode/quoted_printable_decode instead in %s on line %d
|
|
string(3) "abc"
|
|
|
|
Deprecated: mb_convert_encoding(): Handling Base64 via mbstring is deprecated; use base64_encode/base64_decode instead in %s on line %d
|
|
string(4) "YWJj"
|
|
|
|
Deprecated: mb_convert_encoding(): Handling HTML entities via mbstring is deprecated; use htmlspecialchars, htmlentities, or mb_encode_numericentity/mb_decode_numericentity instead in %s on line %d
|
|
string(3) "abc"
|