Voting

The Note You're Voting On

1 year ago
idn_to_ascii and idn_to_utf8 functions don't properly handle full URLs (i.e. with schema and paths), so here's the helper functions which handles all URLs, including ones with path but without a scheme

<?php
/**
 * Converts URLS to punycode  
 * It doesn't url-encodes other parts
 * The initial code from snipp dor ru website, here is modified version that handles urls without scheme
 */
function punycode_encode($url)
{
    $no_scheme = false;
    if (!preg_match('/^.+?:\/\//', $url) && substr($url, 0, 2) !== '//') {
        $url = '//' . $url;
        $no_scheme = true;
    }

    $parts = parse_url($url);
 
    $out = '';
    if (!empty($parts['scheme']))   $out .= $parts['scheme'] . ':';
    if (!empty($parts['host']))     $out .= '//';
    if (!empty($parts['user']))     $out .= $parts['user'];
    if (!empty($parts['pass']))     $out .= ':' . $parts['pass'];
    if (!empty($parts['user']))     $out .= '@';
    if (!empty($parts['host']))     $out .= idn_to_ascii($parts['host']);
    if (!empty($parts['port']))     $out .= ':' . $parts['port'];
    if (!empty($parts['path']))     $out .= $parts['path'];
    if (!empty($parts['query']))    $out .= '?' . $parts['query'];
    if (!empty($parts['fragment'])) $out .= '#' . $parts['fragment'];

    if ($no_scheme) {
        $out = substr($out, 2);
    }
 
    return $out;
}

function punycode_decode($url)
{
    $no_scheme = false;
    if (!preg_match('/^.+?:\/\//', $url) && substr($url, 0, 2) !== '//') {
        $url = '//' . $url;
        $no_scheme = true;
    }

    $parts = parse_url($url);
    $out = '';
    if (!empty($parts['scheme']))   $out .= $parts['scheme'] . ':';
    if (!empty($parts['host']))     $out .= '//';
    if (!empty($parts['user']))     $out .= $parts['user'];
    if (!empty($parts['pass']))     $out .= ':' . $parts['pass'];
    if (!empty($parts['user']))     $out .= '@';
    if (!empty($parts['host']))     $out .= idn_to_utf8($parts['host']);
    if (!empty($parts['port']))     $out .= ':' . $parts['port'];
    if (!empty($parts['path']))     $out .= $parts['path'];
    if (!empty($parts['query']))    $out .= '?' . $parts['query'];
    if (!empty($parts['fragment'])) $out .= '#' . $parts['fragment'];
 
    if ($no_scheme) {
        $out = substr($out, 2);
    }
    
    return $out;
}
<< Back to user notes page