I know this question is older but thought I'd lend my working–in–China to_json and to_utf8 functions — which includes some nice formatting (JSON_PRETTY_PRINT) when in development vs minified production. (Adapt to your own env/system)
Simple
// Produces JSON with Chinese Characters fully un-encoded.
// NOT RFC4627 compliant
json_encode($data, JSON_UNESCAPED_UNICODE|JSON_UNESCAPED_SLASHES);
to_json()
function to_json($data, $pretty=null, $inculde_security=false, $try_to_recover=true) {
// @Note: json_encode() *REQUIRES* data to be in valid UTF8 format BEFORE
// trying to json_encode and since we are working with Chinese
// characters, we need to make sure that we explicitly allow:
// JSON_UNESCAPED_UNICODE|JSON_UNESCAPED_SLASHES
// *Unless a mode is explicitly passed into the function
$json_encoded = '{}';
if ($pretty === null && is_env_prod()) { // @NOTE: Substitute with your own Production env check
$json_encoded = json_encode( $data, JSON_UNESCAPED_UNICODE|JSON_UNESCAPED_SLASHES );
} else if ($pretty === null && is_env_dev()){ // @NOTE: Substitute with your own Development env check
$json_encoded = json_encode( $data, JSON_PRETTY_PRINT|JSON_UNESCAPED_UNICODE|JSON_UNESCAPED_SLASHES );
} else {
// PRODUCTION
$json_encoded = json_encode( $data, $pretty );
}
// (1) Do not return an error if the inital data was empty
// (2) Return an error if json_encode() failed
if (json_last_error() > 0) {
if (!!$data || !empty($data)) {
if (!$json_encoded == false || empty($json_encoded) || $json_encoded == '{}') {
$json_encoded = json_encode([
'status' => false,
'error' => [
'json_last_error' => json_last_error(),
'json_last_error_msg' => json_last_error_msg()
]
]);
} else if (!!$try_to_recover) {
// there was data in $data so lets try to forensically recover a little? by removing $k => $v pairs that fail to be JSON encoded
foreach (((array) $data) as $k => $v) {
if (!json_encode([$k => $v])) {
if (is_array($data)) {
unset($data[$k]);
} else if (is_object($data)) {
unset($data->{$k});
}
}
}
// if the data still is not empty, and there is a status set in the data
// then set it to false and add a error message/data
// ONLY for Array & Objects
if (!empty($json_encoded) && count($json_encoded) < 1) {
if (!json_encode($data)) {
if (is_array($json_encoded)) {
$json_encoded['status'] = false;
$json_encoded['message'] = "json_encoding_error";
$json_encoded['error'] = [
'json_last_error' => json_last_error(),
'json_last_error_msg' => json_last_error_msg()
];
} else if (is_object($json_encoded)) {
$json_encoded->status = false;
$json_encoded->message = "json_encoding_error";
$json_encoded->error = [
'json_last_error' => json_last_error(),
'json_last_error_msg' => json_last_error_msg()
];
}
} else {
// We have removed the offending data
return to_json($data, $pretty, $include_security, $try_to_recover);
}
}
// we've cleaned out any data that was causing the problem, and included
// false to indicate this is a one-time recursion recovery.
return $this->to_json($pretty, $include_security, false);
}
} else { } // don't do anything as the value is already false
}
return ( ($inculde_security) ? ")]}',\n" : '' ) . $json_encoded;
}
Another funciton that might be usful is my recursive to_utf8() functionality:
to_utf8()
// @NOTE: Common Chinese GBK encoding: to_utf8($data, 'GB2312')
function to_utf8($in, $source_encoding='HTML-ENTITIES') {
if (is_string($in)) {
return mb_convert_encoding(
$in,
$source_encoding,
'UTF-8'
);
} else if (is_array($in) || is_object($in)) {
array_walk_recursive($in, function(&$item, &$key) {
$key = to_utf8($key);
if (is_object($item) || is_array($item)) {
$item = to_utf8($item);
} else {
if (!mb_detect_encoding($item, 'UTF-8', true)){
$item = utf8_encode($item);
}
}
});
$ret_object = is_object($in);
return ($ret_object) ? (object) $in : (array) $in;
}
return $in;
}
Validate RFC4627 (valid JSON)
$pcre_regex = '
/
(?(DEFINE)
(?<number> -? (?= [1-9]|0(?!\d) ) \d+ (\.\d+)? ([eE] [+-]? \d+)? )
(?<boolean> true | false | null )
(?<string> " ([^"\\\\]* | \\\\ ["\\\\bfnrt\/] | \\\\ u [0-9a-f]{4} )* " )
(?<array> \[ (?: (?&json) (?: , (?&json) )* )? \s* \] )
(?<pair> \s* (?&string) \s* : (?&json) )
(?<object> \{ (?: (?&pair) (?: , (?&pair) )* )? \s* \} )
(?<json> \s* (?: (?&number) | (?&boolean) | (?&string) | (?&array) | (?&object) ) \s* )
)
\A (?&json) \Z
/six
';
$matches = false;
preg_match($pcre_regex, trim($body), $matches);
var_dump('RFC4627 Verification (Regex) ', [
'has_passed' => (count($matches) == 1) ? 'YES' : 'NO',
'matches' => $matches
]);
is_json()
// One Liner
is_string($json_string) && !preg_match('/[^,:{}\\[\\]0-9.\\-+Eaeflnr-u \\n\\r\\t]/', preg_replace('/"(\\.|[^"\\\\])*"/', '', $json_string));
// Alt Function — more consistant
function is_json($json_string) {
if (!is_string($json_string) || is_numeric($json_string)) {
return false;
}
$val = @json_decode($json_string);
return ($val != null) && (json_last_error() === JSON_ERROR_NONE);
// Inconsistant results, reverted to json_decode() + JSON_ERROR_NONE check
// return is_string($json_string) && !preg_match('/[^,:{}\\[\\]0-9.\\-+Eaeflnr-u \\n\\r\\t]/', preg_replace('/"(\\.|[^"\\\\])*"/', '', $json_string));
}
is_utf8()
function is_utf8($str) {
if (is_array($str)) {
foreach ($str as $k=>$v) {
if (is_string($v) && !is_utf8($v)) {
return false;
}
}
}
return (is_string($str) && preg_match('//u', $str));
}
