gsnedders

This is deprecated, and has known bugs. See here for a replacement.

There are plenty of cases for needing to resolve relative URLs - RFC 3986 (Generic URI Syntax) has a whole section on how to go about it. SimplePie has code for this, written by me in it's entirety (although based on the pseudo-code in RFC 3986), used to deal with relative URLs in feeds (which happens to be possible pretty much everywhere). As I am the soul author of it, I've rearranged it slightly into a single function (in SimplePie it's in several methods within a larger class, as most of the methods are also called in other places), and re-licensed it under the 3 clause BSD license, LGPL, and zlib/libpng license (although of course if you redistribute it you must attach the appropriate notice as stated by one of the above licenses).

Without further ado, here's the code:

<?phpfunction absolutize_url($relative, $base)
{
    $relative = trim($relative);
    $base = trim($base);
    if (!empty($relative))
    {
        preg_match('/^(([^:\/?#]+):)?(\/\/([^\/?#]*))?([^?#]*)(\?([^#]*))?(#(.*))?$/i', $relative, $match);
        for ($i = count($match); $i <= 9; $i++)
        {
            if (!isset($match[$i]))
            {
                $match[$i] = '';
            }
        }
        $relative = array('scheme' => $match[2], 'authority' => $match[4], 'path' => $match[5], 'query' => $match[7], 'fragment' => $match[9]);
        if (!empty($relative['scheme']))
        {
            $target = $relative;
        }
        else if (!empty($base))
        {
            preg_match('/^(([^:\/?#]+):)?(\/\/([^\/?#]*))?([^?#]*)(\?([^#]*))?(#(.*))?$/i', $base, $match);
            for ($i = count($match); $i <= 9; $i++)
            {
                if (!isset($match[$i]))
                {
                    $match[$i] = '';
                }
            }
            $base = array('scheme' => $match[2], 'authority' => $match[4], 'path' => $match[5], 'query' => $match[7], 'fragment' => $match[9]);
            $target = array('scheme' => '', 'authority' => '', 'path' => '', 'query' => '', 'fragment' => '');
            if (!empty($relative['authority']))
            {
                $target = $relative;
                $target['scheme'] = $base['scheme'];
            }
            else
            {
                $target['scheme'] = $base['scheme'];
                $target['authority'] = $base['authority'];
                if (!empty($relative['path']))
                {
                    if (strpos($relative['path'], '/') === 0)
                    {
                        $target['path'] = $relative['path'];
                    }
                    else
                    {
                        if ($base['path'] == '/' || empty($base['path']))
                        {
                            $target['path'] = '/' . $relative['path'];
                        }
                        else
                        {
                            $target['path'] = preg_replace('/^(.*)((\/)([^\/]*))?$/sU', '\\1', $base['path']) . '/' . $relative['path'];
                        }
                    }
                    if (!empty($relative['query']))
                    {
                        $target['query'] = $relative['query'];
                    }
                    $input = $target['path'];
                    while (!empty($input))
                    {
                        // A: If the input buffer begins with a prefix of "../" or "./", then remove that prefix from the input buffer; otherwise,
                        if (strpos($input, '../') === 0)
                        {
                            $input = substr($input, 3);
                        }
                        else if (strpos($input, './') === 0)
                        {
                            $input = substr($input, 2);
                        }
                        // B: if the input buffer begins with a prefix of "/./" or "/.", where "." is a complete path segment, then replace that prefix with "/" in the input buffer; otherwise,
                        else if (strpos($input, '/./') === 0)
                        {
                            $input = substr_replace($input, '/', 0, 3);
                        }
                        else if ($input == '/.')
                        {
                            $input = '/';
                        }
                        // C: if the input buffer begins with a prefix of "/../" or "/..", where ".." is a complete path segment, then replace that prefix with "/" in the input buffer and remove the last segment and its preceding "/" (if any) from the output buffer; otherwise,
                        else if (strpos($input, '/../') === 0)
                        {
                            $input = substr_replace($input, '/', 0, 4);
                            $target['path'] = preg_replace('/(\/)?([^\/]+)$/U', '', $target['path']);
                        }
                        else if ($input == '/..')
                        {
                            $input = '/';
                            $target['path'] = preg_replace('/(\/)?([^\/]+)$/U', '', $target['path']);
                        }
                        // D: if the input buffer consists only of "." or "..", then remove that from the input buffer; otherwise,
                        else if ($input == '.' || $input == '..')
                        {
                            $input = '';
                        }
                        // E: move the first path segment in the input buffer to the end of the output buffer, including the initial "/" character (if any) and any subsequent characters up to, but not including, the next "/" character or the end of the input buffer
                        else
                        {
                            if (preg_match('/^([^\/]+|(\/)[^\/]*)(\/|$)/', $input, $match))
                            {
                                $target['path'] .= $match[1];
                                $input = substr_replace($input, '', 0, strlen($match[1]));
                            }
                            else
                            {
                                // We've ended up in a recursive loop, so do what we otherwise never will: return false.
                                return false;
                            }
                        }
                    }
                }
                else
                {
                    if (!empty($base['path']))
                    {
                        $target['path'] = $base['path'];
                    }
                    else
                    {
                        $target['path'] = '/';
                    }
                    if (!empty($relative['query']))
                    {
                        $target['query'] = $relative['query'];
                    }
                    else if (!empty($base['query']))
                    {
                        $target['query'] = $base['query'];
                    }
                }
            }
            if (!empty($relative['fragment']))
            {
                $target['fragment'] = $relative['fragment'];
            }
        }
        else
        {
            // No base URL, just return the relative URL
            $target = $relative;
        }
        $return = '';
        if (!empty($target['scheme']))
        {
            $return .= "$target[scheme]:";
        }
        if (!empty($target['authority']))
        {
            $return .= "//$target[authority]";
        }
        if (!empty($target['path']))
        {
            $return .= $target['path'];
        }
        if (!empty($target['query']))
        {
            $return .= "?$target[query]";
        }
        if (!empty($target['fragment']))
        {
            $return .= "#$target[fragment]";
        }
    }
    else
    {
        $return = $base;
    }
    return $return;
}?>