TextformatterMakeLinks.module

<?php

/**
 * TextformatterMakeLinks for ProcessWire
 *
 * All credits go to flourishlib
 *
 * ProcessWire 2.x
 * Copyright (C) 2011 by Ryan Cramer
 * Licensed under GNU/GPL v2, see LICENSE.TXT
 *
 * http://www.processwire.com
 * http://www.ryancramer.com
 *
 */
class TextformatterMakeLinks extends Textformatter
{

    public static function getModuleInfo()
    {
        return array(
            'title' => __('Textformatter Make HTML Links', __FILE__),
            'summary' => __("Takes a block of text and converts all URLs into HTML links", __FILE__),
            'version' => 102,
            'href' => 'http://flourishlib.com/api/fHTML#makeLinks',
            'icon' => 'link',
        );
    }


    /**
     * Takes a block of text and converts all URLs into HTML links
     * @param  string  $content The content to parse for links
     */
    public function format(&$content)
    {
        /** @var integer $link_text_length
         * If non-zero, all link text will be truncated to this many characters
         */
        $link_text_length = 0;
        // Find all a tags with contents, individual HTML tags and HTML comments
        $reg_exp = "/<\s*a(?:\s+[\w:-]+(?:\s*=\s*(?:\"[^\"]*?\"|'[^']*?'|[^'\">\s]+))?)*\s*>.*?<\s*\/\s*a\s*>|<\s*\/?\s*[\w:-]+(?:\s+[\w:-]+(?:\s*=\s*(?:\"[^\"]*?\"|'[^']*?'|[^'\">\s]+))?)*\s*\/?\s*>|<\!--.*?-->/s";
        preg_match_all($reg_exp, $content, $html_matches, PREG_SET_ORDER);

        // Find all text
        $text_matches = preg_split($reg_exp, $content);

        // For each chunk of text and create the links
        foreach ($text_matches as $key => $text) {
            preg_match_all(
                '~
                  \b([a-z]{3,}://[a-z0-9%\$\-_.+!*;/?:@=&\'\#,]+[a-z0-9\$\-_+!*;/?:@=&\'\#,])\b\/?                           | # Fully URLs
                  \b(www\.(?:[a-z0-9\-]+\.)+[a-z]{2,}(?:/[a-z0-9%\$\-_.+!*;/?:@=&\'\#,]+[a-z0-9\$\-_+!*;/?:@=&\'\#,])?)\b\/? | # www. domains
                  \b([a-z0-9\\.+\'_\\-]+@(?:[a-z0-9\\-]+\.)+[a-z]{2,})\b                                                       # email addresses
                 ~ix',
                $text,
                $matches,
                PREG_SET_ORDER
            );

            // For each match we find the first occurrence, replace it and then
            // start from the end of that finding the next occurrence. This
            // prevents double linking of matches for http://www.example.com and
            // www.example.com
            $last_pos = 0;
            foreach ($matches as $match) {
                $match_pos = strpos($text, $match[0], $last_pos);
                $length = strlen($match[0]);
                $prefix = '';

                if (!empty($match[3])) {
                    $prefix = 'mailto:';
                } elseif (!empty($match[2])) {
                    $prefix = 'http://';
                }

                $replacement = '<a href="' . $prefix . $match[0] . '">';
                $replacement .= ($link_text_length && strlen($match[0]) > $link_text_length) ? substr($match[0], 0, $link_text_length) . "…" : $match[0];
                $replacement .= '</a>';

                $text = substr_replace(
                    $text,
                    $replacement,
                    $match_pos,
                    $length
                );

                $last_pos = $match_pos + strlen($replacement);
            }

            $text_matches[$key] = $text;
        }

        // Merge the text and html back together
        for ($i = 0; $i < sizeof($html_matches); $i++) {
            $text_matches[$i] .= $html_matches[$i][0];
        }

        $content = implode($text_matches);
    }

}