C:/xampp/htdocs/moodle/lib/html2text.php

Go to the documentation of this file.

<?php

// This file is part of Moodle - http://moodle.org/
//
// Moodle is free software: you can redistribute it and/or modify
// it under the terms of the GNU General Public License as published by
// the Free Software Foundation, either version 3 of the License, or
// (at your option) any later version.
//
// Moodle is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
// GNU General Public License for more details.
//
// You should have received a copy of the GNU General Public License
// along with Moodle.  If not, see <http://www.gnu.org/licenses/>.
//
// Author(s): Jon Abernathy <jon@chuggnutt.com>
// Copyright (c) 2005-2007 Jon Abernathy <jon@chuggnutt.com>

class html2text
{

    var $html;

    var $text;

    var $width = 70;

    var $search = array(
        "/\r/",                                  // Non-legal carriage return
        "/[\n\t]+/",                             // Newlines and tabs
        '/[ ]{2,}/',                             // Runs of spaces, pre-handling
        '/<script[^>]*>.*?<\/script>/i',         // <script>s -- which strip_tags supposedly has problems with
        '/<style[^>]*>.*?<\/style>/i',           // <style>s -- which strip_tags supposedly has problems with
        //'/<!-- .* -->/',                         // Comments -- which strip_tags might have problem a with
        '/<p[^>]*>/i',                           // <P>
        '/<br[^>]*>/i',                          // <br>
        '/<i[^>]*>(.*?)<\/i>/i',                 // <i>
        '/<em[^>]*>(.*?)<\/em>/i',               // <em>
        '/(<ul[^>]*>|<\/ul>)/i',                 // <ul> and </ul>
        '/(<ol[^>]*>|<\/ol>)/i',                 // <ol> and </ol>
        '/<li[^>]*>(.*?)<\/li>/i',               // <li> and </li>
        '/<li[^>]*>/i',                          // <li>
        '/<hr[^>]*>/i',                          // <hr>
        '/(<table[^>]*>|<\/table>)/i',           // <table> and </table>
        '/(<tr[^>]*>|<\/tr>)/i',                 // <tr> and </tr>
        '/<td[^>]*>(.*?)<\/td>/i',               // <td> and </td>
        '/&(nbsp|#160);/i',                      // Non-breaking space
        '/&(quot|rdquo|ldquo|#8220|#8221|#147|#148);/i',
                                                         // Double quotes
        '/&(apos|rsquo|lsquo|#8216|#8217);/i',   // Single quotes
        '/&gt;/i',                               // Greater-than
        '/&lt;/i',                               // Less-than
        '/&(amp|#38);/i',                        // Ampersand
        '/&(copy|#169);/i',                      // Copyright
        '/&(trade|#8482|#153);/i',               // Trademark
        '/&(reg|#174);/i',                       // Registered
        '/&(mdash|#151|#8212);/i',               // mdash
        '/&(ndash|minus|#8211|#8722);/i',        // ndash
        '/&(bull|#149|#8226);/i',                // Bullet
        '/&(pound|#163);/i',                     // Pound sign
        '/&(euro|#8364);/i',                     // Euro sign
        '/[ ]+([\n\t])/',                        // Trailing spaces before newline or tab
        '/[ ]{2,}/'                              // Runs of spaces, post-handling
    );

    var $replace = array(
        '',                                     // Non-legal carriage return
        ' ',                                    // Newlines and tabs
        ' ',                                    // Runs of spaces, pre-handling
        '',                                     // <script>s -- which strip_tags supposedly has problems with
        '',                                     // <style>s -- which strip_tags supposedly has problems with
        //'',                                     // Comments -- which strip_tags might have problem a with
        "\n\n",                               // <P>
        "\n",                                   // <br>
        '_\\1_',                                // <i>
        '_\\1_',                                // <em>
        "\n\n",                                 // <ul> and </ul>
        "\n\n",                                 // <ol> and </ol>
        "\t* \\1\n",                            // <li> and </li>
        "\n\t* ",                               // <li>
        "\n-------------------------\n",        // <hr>
        "\n\n",                                 // <table> and </table>
        "\n",                                   // <tr> and </tr>
        "\t\t\\1\n",                            // <td> and </td>
        ' ',                                    // Non-breaking space
        '"',                                    // Double quotes
        "'",                                    // Single quotes
        '>',
        '<',
        '&',
        '(c)',
        '(tm)',
        '(R)',
        '--',
        '-',
        '*',
        '£',
        'EUR',                                  // Euro sign. € ?
        '\\1',                                  // Trailing spaces before newline or tab
        ' '                                     // Runs of spaces, post-handling
    );

    var $callback_search = array(
        '/<(h)[123456][^>]*>(.*?)<\/h[123456]>/i', // H1 - H3
        '/<(b)[^>]*>(.*?)<\/b>/i',                 // <b>
        '/<(strong)[^>]*>(.*?)<\/strong>/i',       // <strong>
        '/<(a) [^>]*href=("|\')([^"\']+)\2[^>]*>(.*?)<\/a>/i',
                                                   // <a href="">
        '/<(th)[^>]*>(.*?)<\/th>/i',               // <th> and </th>
        '/<(img)[^>]*alt=\"([^>"]+)\"[^>]*>/i',    // <img> with alt
    );

    var $pre_search = array(
        "/\n/",
        "/\t/",
        '/ /',
        '/<pre[^>]*>/',
        '/<\/pre>/'
    );

    var $pre_replace = array(
        '<br>',
        '&nbsp;&nbsp;&nbsp;&nbsp;',
        '&nbsp;',
        '',
        ''
    );

    var $allowed_tags = '';

    var $url;

    var $_converted = false;

    var $_link_list = '';

    var $_link_count = 0;

    var $_do_links = true;

    function html2text( $source = '', $from_file = false, $do_links = true, $width = 75 )
    {
        if ($source !== '') {
            $this->set_html($source, $from_file);
        }

        $this->set_base_url();
        $this->_do_links = $do_links;
        $this->width = $width;
    }

    function set_html( $source, $from_file = false )
    {
        if ( $from_file && file_exists($source) ) {
            $this->html = file_get_contents($source);
        }
        else
            $this->html = $source;

        $this->_converted = false;
    }

    function get_text()
    {
        if ( !$this->_converted ) {
            $this->_convert();
        }

        return $this->text;
    }

    function print_text()
    {
        print $this->get_text();
    }

    function p()
    {
        print $this->get_text();
    }

    function set_allowed_tags( $allowed_tags = '' )
    {
        if ( !empty($allowed_tags) ) {
            $this->allowed_tags = $allowed_tags;
        }
    }

    function set_base_url( $url = '' )
    {
        if ( empty($url) ) {
                if ( !empty($_SERVER['HTTP_HOST']) ) {
                    $this->url = 'http://' . $_SERVER['HTTP_HOST'];
                } else {
                    $this->url = '';
                }
        } else {
            // Strip any trailing slashes for consistency (relative
            // URLs may already start with a slash like "/file.html")
            if ( substr($url, -1) == '/' ) {
                $url = substr($url, 0, -1);
            }
            $this->url = $url;
        }
    }

    function _convert()
    {
        // Variables used for building the link list
        $this->_link_count = 0;
        $this->_link_list = '';

        $text = trim($this->html);

        // Convert <PRE>
        $this->_convert_pre($text);

        // Run our defined search-and-replace
        $text = preg_replace($this->search, $this->replace, $text);
        $text = preg_replace_callback($this->callback_search, array('html2text', '_preg_callback'), $text);

        // Replace known html entities
        $text = html_entity_decode($text, ENT_COMPAT, 'UTF-8');

        // Remove unknown/unhandled entities (this cannot be done in search-and-replace block)
        $text = preg_replace('/&[^&;]+;/i', '', $text);

        // Strip any other HTML tags
        $text = strip_tags($text, $this->allowed_tags);

        // Bring down number of empty lines to 2 max
        $text = preg_replace("/\n\s+\n/", "\n\n", $text);
        $text = preg_replace("/[\n]{3,}/", "\n\n", $text);

        // Add link list
        if ( !empty($this->_link_list) ) {
            $text .= "\n\nLinks:\n------\n" . $this->_link_list;
        }

        // Wrap the text to a readable format
        // for PHP versions >= 4.0.2. Default width is 75
        // If width is 0 or less, don't wrap the text.
        if ( $this->width > 0 ) {
                $text = wordwrap($text, $this->width);
        }

        $this->text = $text;

        $this->_converted = true;
    }

    function _build_link_list( $link, $display )
    {
        if ( !$this->_do_links ) return $display;

        if ( substr($link, 0, 7) == 'http://' || substr($link, 0, 8) == 'https://' ||
             substr($link, 0, 7) == 'mailto:' ) {
            $this->_link_count++;
            $this->_link_list .= "[" . $this->_link_count . "] $link\n";
            $additional = ' [' . $this->_link_count . ']';
        } elseif ( substr($link, 0, 11) == 'javascript:' ) {
                // Don't count the link; ignore it
                $additional = '';
                // what about href="#anchor" ?
        } else {
            $this->_link_count++;
            $this->_link_list .= "[" . $this->_link_count . "] " . $this->url;
            if ( substr($link, 0, 1) != '/' ) {
                $this->_link_list .= '/';
            }
            $this->_link_list .= "$link\n";
            $additional = ' [' . $this->_link_count . ']';
        }

        return $display . $additional;
    }

    function _convert_pre(&$text)
    {
         while (preg_match('/<pre[^>]*>(.*)<\/pre>/ismU', $text, $matches)) {
            // convert the content
            $this->pre_content = sprintf('<div><br>%s<br></div>',
                preg_replace($this->pre_search, $this->pre_replace, $matches[1]));
            // replace the content (use callback because content can contain $0 variable)
            $text = preg_replace_callback('/<pre[^>]*>.*<\/pre>/ismU',
                array('html2text', '_preg_pre_callback'), $text, 1);
            // free memory
            $this->pre_content = '';
        }
    }

    function _preg_callback($matches)
    {
        switch($matches[1]) {
        case 'b':
        case 'strong':
            return $this->_strtoupper($matches[2]);
        case 'hr':
            return $this->_strtoupper("\t\t". $matches[2] ."\n");
        case 'h':
            return $this->_strtoupper("\n\n". $matches[2] ."\n\n");
        case 'a':
            return $this->_build_link_list($matches[3], $matches[4]);
        case 'img':
            return '[' . $matches[2] . ']';
        }
    }

    private function _preg_pre_callback($matches)
    {
        return $this->pre_content;
    }

    function _strtoupper($str)
    {
        $tl = textlib_get_instance();
        return $tl->strtoupper($str);
    }
}