1
0
Fork 0

Fix for #2613, when using php < 5.4 there was an unnecessary backslash before each utf-8 char. The problem was that the regexp matched all utf-8 encoded chars (included the ones that where escaped). The new regexp uses the lookbehind feature to check if the backslash isn't prefixed with an other backslash.

pull/2714/head
Sandy Pleyte 2014-02-17 13:54:35 +01:00
parent 9896abeb38
commit 7a902ed96d
2 changed files with 8 additions and 1 deletions

View File

@ -231,7 +231,7 @@ class JsonFile
if ($unescapeUnicode && function_exists('mb_convert_encoding')) {
// http://stackoverflow.com/questions/2934563/how-to-decode-unicode-escape-sequences-like-u00ed-to-proper-utf-8-encoded-cha
$buffer = preg_replace_callback('/\\\\u([0-9a-f]{4})/i', function($match) {
$buffer = preg_replace_callback('/(?<!\\\)\\\\u([0-9a-f]{4})/i', function($match) {
return mb_convert_encoding(pack('H*', $match[1]), 'UTF-8', 'UCS-2BE');
}, $buffer);
}

View File

@ -198,6 +198,13 @@ class JsonFileTest extends \PHPUnit_Framework_TestCase
$this->assertJsonFormat('"\\u018c"', $data, 0);
}
public function testDoubleEscapedUnicode()
{
$data = "Zdj\\u0119ciahl\\\\u0119kkjk";
$this->assertJsonFormat('"Zdj\\\\u0119ciahl\\\\\\\\u0119kkjk"', $data);
}
private function expectParseException($text, $json)
{
try {