+++ /dev/null
-<?php
-
-/*************************************************************************
- * *
- * class.html2text.inc *
- * *
- *************************************************************************
- * *
- * Converts HTML to formatted plain text *
- * *
- * Copyright (c) 2005-2007 Jon Abernathy <jon@chuggnutt.com> *
- * All rights reserved. *
- * *
- * This script 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 2 of the License, or *
- * (at your option) any later version. *
- * *
- * The GNU General Public License can be found at *
- * http://www.gnu.org/copyleft/gpl.html. *
- * *
- * This script 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. *
- * *
- * Author(s): Jon Abernathy <jon@chuggnutt.com> *
- * *
- * Last modified: 08/08/07 *
- * *
- *************************************************************************/
-
-if (!defined('RCMAIL_CHARSET')) {
- define('RCMAIL_CHARSET', 'UTF-8');
-}
-
-/**
- * Takes HTML and converts it to formatted, plain text.
- *
- * Thanks to Alexander Krug (http://www.krugar.de/) to pointing out and
- * correcting an error in the regexp search array. Fixed 7/30/03.
- *
- * Updated set_html() function's file reading mechanism, 9/25/03.
- *
- * Thanks to Joss Sanglier (http://www.dancingbear.co.uk/) for adding
- * several more HTML entity codes to the $search and $replace arrays.
- * Updated 11/7/03.
- *
- * Thanks to Darius Kasperavicius (http://www.dar.dar.lt/) for
- * suggesting the addition of $allowed_tags and its supporting function
- * (which I slightly modified). Updated 3/12/04.
- *
- * Thanks to Justin Dearing for pointing out that a replacement for the
- * <TH> tag was missing, and suggesting an appropriate fix.
- * Updated 8/25/04.
- *
- * Thanks to Mathieu Collas (http://www.myefarm.com/) for finding a
- * display/formatting bug in the _build_link_list() function: email
- * readers would show the left bracket and number ("[1") as part of the
- * rendered email address.
- * Updated 12/16/04.
- *
- * Thanks to Wojciech Bajon (http://histeria.pl/) for submitting code
- * to handle relative links, which I hadn't considered. I modified his
- * code a bit to handle normal HTTP links and MAILTO links. Also for
- * suggesting three additional HTML entity codes to search for.
- * Updated 03/02/05.
- *
- * Thanks to Jacob Chandler for pointing out another link condition
- * for the _build_link_list() function: "https".
- * Updated 04/06/05.
- *
- * Thanks to Marc Bertrand (http://www.dresdensky.com/) for
- * suggesting a revision to the word wrapping functionality; if you
- * specify a $width of 0 or less, word wrapping will be ignored.
- * Updated 11/02/06.
- *
- * *** Big housecleaning updates below:
- *
- * Thanks to Colin Brown (http://www.sparkdriver.co.uk/) for
- * suggesting the fix to handle </li> and blank lines (whitespace).
- * Christian Basedau (http://www.movetheweb.de/) also suggested the
- * blank lines fix.
- *
- * Special thanks to Marcus Bointon (http://www.synchromedia.co.uk/),
- * Christian Basedau, Norbert Laposa (http://ln5.co.uk/),
- * Bas van de Weijer, and Marijn van Butselaar
- * for pointing out my glaring error in the <th> handling. Marcus also
- * supplied a host of fixes.
- *
- * Thanks to Jeffrey Silverman (http://www.newtnotes.com/) for pointing
- * out that extra spaces should be compressed--a problem addressed with
- * Marcus Bointon's fixes but that I had not yet incorporated.
- *
- * Thanks to Daniel Schledermann (http://www.typoconsult.dk/) for
- * suggesting a valuable fix with <a> tag handling.
- *
- * Thanks to Wojciech Bajon (again!) for suggesting fixes and additions,
- * including the <a> tag handling that Daniel Schledermann pointed
- * out but that I had not yet incorporated. I haven't (yet)
- * incorporated all of Wojciech's changes, though I may at some
- * future time.
- *
- * *** End of the housecleaning updates. Updated 08/08/07.
- *
- * @author Jon Abernathy <jon@chuggnutt.com>
- * @version 1.0.0
- * @since PHP 4.0.2
- */
-class html2text
-{
-
- /**
- * Contains the HTML content to convert.
- *
- * @var string $html
- * @access public
- */
- var $html;
-
- /**
- * Contains the converted, formatted text.
- *
- * @var string $text
- * @access public
- */
- var $text;
-
- /**
- * Maximum width of the formatted text, in columns.
- *
- * Set this value to 0 (or less) to ignore word wrapping
- * and not constrain text to a fixed-width column.
- *
- * @var integer $width
- * @access public
- */
- var $width = 70;
-
- /**
- * List of preg* regular expression patterns to search for,
- * used in conjunction with $replace.
- *
- * @var array $search
- * @access public
- * @see $replace
- */
- var $search = array(
- "/\r/", // Non-legal carriage return
- "/[\n\t]+/", // Newlines and tabs
- '/<script[^>]*>.*?<\/script>/i', // <script>s -- which strip_tags supposedly has problems with
- '/<style[^>]*>.*?<\/style>/i', // <style>s -- which strip_tags supposedly has problems 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>
- '/<div[^>]*>/i', // <div>
- '/(<table[^>]*>|<\/table>)/i', // <table> and </table>
- '/(<tr[^>]*>|<\/tr>)/i', // <tr> and </tr>
- '/<td[^>]*>(.*?)<\/td>/i', // <td> and </td>
- );
-
- /**
- * List of pattern replacements corresponding to patterns searched.
- *
- * @var array $replace
- * @access public
- * @see $search
- */
- var $replace = array(
- '', // Non-legal carriage return
- ' ', // Newlines and tabs
- '', // <script>s -- which strip_tags supposedly has problems with
- '', // <style>s -- which strip_tags supposedly has problems 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>
- "<div>\n", // <div>
- "\n\n", // <table> and </table>
- "\n", // <tr> and </tr>
- "\t\t\\1\n", // <td> and </td>
- );
-
- /**
- * List of preg* regular expression patterns to search for,
- * used in conjunction with $ent_replace.
- *
- * @var array $ent_search
- * @access public
- * @see $ent_replace
- */
- var $ent_search = array(
- '/&(nbsp|#160);/i', // Non-breaking space
- '/&(quot|rdquo|ldquo|#8220|#8221|#147|#148);/i',
- // Double quotes
- '/&(apos|rsquo|lsquo|#8216|#8217);/i', // Single quotes
- '/>/i', // Greater-than
- '/</i', // Less-than
- '/&(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
- '/&(amp|#38);/i', // Ampersand: see _converter()
- '/[ ]{2,}/', // Runs of spaces, post-handling
- );
-
- /**
- * List of pattern replacements corresponding to patterns searched.
- *
- * @var array $ent_replace
- * @access public
- * @see $ent_search
- */
- var $ent_replace = array(
- ' ', // Non-breaking space
- '"', // Double quotes
- "'", // Single quotes
- '>',
- '<',
- '(c)',
- '(tm)',
- '(R)',
- '--',
- '-',
- '*',
- '£',
- 'EUR', // Euro sign. € ?
- '|+|amp|+|', // Ampersand: see _converter()
- ' ', // Runs of spaces, post-handling
- );
-
- /**
- * List of preg* regular expression patterns to search for
- * and replace using callback function.
- *
- * @var array $callback_search
- * @access public
- */
- var $callback_search = array(
- '/<(a) [^>]*href=("|\')([^"\']+)\2[^>]*>(.*?)<\/a>/i',
- // <a href="">
- '/<(h)[123456][^>]*>(.*?)<\/h[123456]>/i', // H1 - H3
- '/<(b)[^>]*>(.*?)<\/b>/i', // <b>
- '/<(strong)[^>]*>(.*?)<\/strong>/i', // <strong>
- '/<(th)[^>]*>(.*?)<\/th>/i', // <th> and </th>
- '/<(img)[^>]*alt=\"([^>"]+)\"[^>]*>/i', // <img> with alt
- );
-
- /**
- * List of preg* regular expression patterns to search for in PRE body,
- * used in conjunction with $pre_replace.
- *
- * @var array $pre_search
- * @access public
- * @see $pre_replace
- */
- var $pre_search = array(
- "/\n/",
- "/\t/",
- '/ /',
- '/<pre[^>]*>/',
- '/<\/pre>/'
- );
-
- /**
- * List of pattern replacements corresponding to patterns searched for PRE body.
- *
- * @var array $pre_replace
- * @access public
- * @see $pre_search
- */
- var $pre_replace = array(
- '<br>',
- ' ',
- ' ',
- '',
- ''
- );
-
- /**
- * Contains a list of HTML tags to allow in the resulting text.
- *
- * @var string $allowed_tags
- * @access public
- * @see set_allowed_tags()
- */
- var $allowed_tags = '';
-
- /**
- * Contains the base URL that relative links should resolve to.
- *
- * @var string $url
- * @access public
- */
- var $url;
-
- /**
- * Indicates whether content in the $html variable has been converted yet.
- *
- * @var boolean $_converted
- * @access private
- * @see $html, $text
- */
- var $_converted = false;
-
- /**
- * Contains URL addresses from links to be rendered in plain text.
- *
- * @var array $_link_list
- * @access private
- * @see _build_link_list()
- */
- var $_link_list = array();
-
- /**
- * Boolean flag, true if a table of link URLs should be listed after the text.
- *
- * @var boolean $_do_links
- * @access private
- * @see html2text()
- */
- var $_do_links = true;
-
- /**
- * Constructor.
- *
- * If the HTML source string (or file) is supplied, the class
- * will instantiate with that source propagated, all that has
- * to be done it to call get_text().
- *
- * @param string $source HTML content
- * @param boolean $from_file Indicates $source is a file to pull content from
- * @param boolean $do_links Indicate whether a table of link URLs is desired
- * @param integer $width Maximum width of the formatted text, 0 for no limit
- * @access public
- * @return void
- */
- 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;
- }
-
- /**
- * Loads source HTML into memory, either from $source string or a file.
- *
- * @param string $source HTML content
- * @param boolean $from_file Indicates $source is a file to pull content from
- * @access public
- * @return void
- */
- function set_html( $source, $from_file = false )
- {
- if ( $from_file && file_exists($source) ) {
- $this->html = file_get_contents($source);
- }
- else
- $this->html = $source;
-
- $this->_converted = false;
- }
-
- /**
- * Returns the text, converted from HTML.
- *
- * @access public
- * @return string
- */
- function get_text()
- {
- if ( !$this->_converted ) {
- $this->_convert();
- }
-
- return $this->text;
- }
-
- /**
- * Prints the text, converted from HTML.
- *
- * @access public
- * @return void
- */
- function print_text()
- {
- print $this->get_text();
- }
-
- /**
- * Alias to print_text(), operates identically.
- *
- * @access public
- * @return void
- * @see print_text()
- */
- function p()
- {
- print $this->get_text();
- }
-
- /**
- * Sets the allowed HTML tags to pass through to the resulting text.
- *
- * Tags should be in the form "<p>", with no corresponding closing tag.
- *
- * @access public
- * @return void
- */
- function set_allowed_tags( $allowed_tags = '' )
- {
- if ( !empty($allowed_tags) ) {
- $this->allowed_tags = $allowed_tags;
- }
- }
-
- /**
- * Sets a base URL to handle relative links.
- *
- * @access public
- * @return void
- */
- 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;
- }
- }
-
- /**
- * Workhorse function that does actual conversion (calls _converter() method).
- *
- * @access private
- * @return void
- */
- function _convert()
- {
- // Variables used for building the link list
- $this->_link_list = array();
-
- $text = trim($this->html);
-
- // Convert HTML to TXT
- $this->_converter($text);
-
- // Add link list
- if (!empty($this->_link_list)) {
- $text .= "\n\nLinks:\n------\n";
- foreach ($this->_link_list as $idx => $url) {
- $text .= '[' . ($idx+1) . '] ' . $url . "\n";
- }
- }
-
- $this->text = $text;
-
- $this->_converted = true;
- }
-
- /**
- * Workhorse function that does actual conversion.
- *
- * First performs custom tag replacement specified by $search and
- * $replace arrays. Then strips any remaining HTML tags, reduces whitespace
- * and newlines to a readable format, and word wraps the text to
- * $width characters.
- *
- * @param string Reference to HTML content string
- *
- * @access private
- * @return void
- */
- function _converter(&$text)
- {
- // Convert <BLOCKQUOTE> (before PRE!)
- $this->_convert_blockquotes($text);
-
- // Convert <PRE>
- $this->_convert_pre($text);
-
- // Run our defined tags search-and-replace
- $text = preg_replace($this->search, $this->replace, $text);
-
- // Run our defined tags search-and-replace with callback
- $text = preg_replace_callback($this->callback_search, array('html2text', '_preg_callback'), $text);
-
- // Strip any other HTML tags
- $text = strip_tags($text, $this->allowed_tags);
-
- // Run our defined entities/characters search-and-replace
- $text = preg_replace($this->ent_search, $this->ent_replace, $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('/&([a-zA-Z0-9]{2,6}|#[0-9]{2,4});/', '', $text);
-
- // Convert "|+|amp|+|" into "&", need to be done after handling of unknown entities
- // This properly handles situation of "&quot;" in input string
- $text = str_replace('|+|amp|+|', '&', $text);
-
- // 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);
-
- // remove leading empty lines (can be produced by eg. P tag on the beginning)
- $text = ltrim($text, "\n");
-
- // 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);
- }
- }
-
- /**
- * Helper function called by preg_replace() on link replacement.
- *
- * Maintains an internal list of links to be displayed at the end of the
- * text, with numeric indices to the original point in the text they
- * appeared. Also makes an effort at identifying and handling absolute
- * and relative links.
- *
- * @param string $link URL of the link
- * @param string $display Part of the text to associate number with
- * @access private
- * @return string
- */
- function _build_link_list( $link, $display )
- {
- if (!$this->_do_links || empty($link)) {
- return $display;
- }
-
- // Ignored link types
- if (preg_match('!^(javascript|mailto|#):!i', $link)) {
- return $display;
- }
-
- if (preg_match('!^(https?://)!i', $link)) {
- $url = $link;
- }
- else {
- $url = $this->url;
- if (substr($link, 0, 1) != '/') {
- $url .= '/';
- }
- $url .= "$link";
- }
-
- if (($index = array_search($url, $this->_link_list)) === false) {
- // Add the link to the list.
- $this->_link_list[] = $url;
- $index = count($this->_link_list);
- }
- else {
- // Use the index of the existing link in the list (we enumerate from 1, not from 0).
- $index++;
- }
-
- return $display . ' [' . ($index) . ']';
- }
-
- /**
- * Helper function for PRE body conversion.
- *
- * @param string HTML content
- * @access private
- */
- function _convert_pre(&$text)
- {
- // get the content of PRE element
- 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
- $this->pre_content = '';
- }
- }
-
- /**
- * Helper function for BLOCKQUOTE body conversion.
- *
- * @param string HTML content
- * @access private
- */
- function _convert_blockquotes(&$text)
- {
- if (preg_match_all('/<\/*blockquote[^>]*>/i', $text, $matches, PREG_OFFSET_CAPTURE)) {
- $level = 0;
- $diff = 0;
- foreach ($matches[0] as $m) {
- if ($m[0][0] == '<' && $m[0][1] == '/') {
- $level--;
- if ($level < 0) {
- $level = 0; // malformed HTML: go to next blockquote
- }
- else if ($level > 0) {
- // skip inner blockquote
- }
- else {
- $end = $m[1];
- $len = $end - $taglen - $start;
- // Get blockquote content
- $body = substr($text, $start + $taglen - $diff, $len);
-
- // Set text width
- $p_width = $this->width;
- if ($this->width > 0) $this->width -= 2;
- // Convert blockquote content
- $body = trim($body);
- $this->_converter($body);
- // Add citation markers and create PRE block
- $body = preg_replace('/((^|\n)>*)/', '\\1> ', trim($body));
- $body = '<pre>' . htmlspecialchars($body) . '</pre>';
- // Re-set text width
- $this->width = $p_width;
- // Replace content
- $text = substr($text, 0, $start - $diff)
- . $body . substr($text, $end + strlen($m[0]) - $diff);
-
- $diff = $len + $taglen + strlen($m[0]) - strlen($body);
- unset($body);
- }
- }
- else {
- if ($level == 0) {
- $start = $m[1];
- $taglen = strlen($m[0]);
- }
- $level ++;
- }
- }
- }
- }
-
- /**
- * Callback function for preg_replace_callback use.
- *
- * @param array PREG matches
- * @return string
- */
- private function _preg_callback($matches)
- {
- switch($matches[1]) {
- case 'b':
- case 'strong':
- return $this->_toupper($matches[2]);
- case 'th':
- return $this->_toupper("\t\t". $matches[2] ."\n");
- case 'h':
- return $this->_toupper("\n\n". $matches[2] ."\n\n");
- case 'a':
- // Remove spaces in URL (#1487805)
- $url = str_replace(' ', '', $matches[3]);
- return $this->_build_link_list($url, $matches[4]);
- case 'img':
- return '[' . $matches[2] . ']';
- }
- }
-
- /**
- * Callback function for preg_replace_callback use in PRE content handler.
- *
- * @param array PREG matches
- * @return string
- */
- private function _preg_pre_callback($matches)
- {
- return $this->pre_content;
- }
-
- /**
- * Strtoupper function with HTML tags and entities handling.
- *
- * @param string $str Text to convert
- * @return string Converted text
- */
- private function _toupper($str)
- {
- // string can containg HTML tags
- $chunks = preg_split('/(<[^>]*>)/', $str, null, PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE);
-
- // convert toupper only the text between HTML tags
- foreach ($chunks as $idx => $chunk) {
- if ($chunk[0] != '<') {
- $chunks[$idx] = $this->_strtoupper($chunk);
- }
- }
-
- return implode($chunks);
- }
-
- /**
- * Strtoupper multibyte wrapper function with HTML entities handling.
- *
- * @param string $str Text to convert
- * @return string Converted text
- */
- private function _strtoupper($str)
- {
- $str = html_entity_decode($str, ENT_COMPAT, RCMAIL_CHARSET);
-
- if (class_exists('core_text'))
- $str = core_text::strtoupper($str);
- else if (function_exists('mb_strtoupper'))
- $str = mb_strtoupper($str);
- else
- $str = strtoupper($str);
-
- $str = htmlspecialchars($str, ENT_COMPAT, RCMAIL_CHARSET);
-
- return $str;
- }
-}
--- /dev/null
+<?php
+
+/*
+ * Copyright (c) 2005-2007 Jon Abernathy <jon@chuggnutt.com>
+ *
+ * This script 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 2 of the License, or
+ * (at your option) any later version.
+ *
+ * The GNU General Public License can be found at
+ * http://www.gnu.org/copyleft/gpl.html.
+ *
+ * This script 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.
+ */
+
+namespace Html2Text;
+
+class Html2Text
+{
+ const ENCODING = 'UTF-8';
+
+ /**
+ * Contains the HTML content to convert.
+ *
+ * @type string
+ */
+ protected $html;
+
+ /**
+ * Contains the converted, formatted text.
+ *
+ * @type string
+ */
+ protected $text;
+
+ /**
+ * List of preg* regular expression patterns to search for,
+ * used in conjunction with $replace.
+ *
+ * @type array
+ * @see $replace
+ */
+ protected $search = array(
+ "/\r/", // Non-legal carriage return
+ "/[\n\t]+/", // Newlines and tabs
+ '/<head[^>]*>.*?<\/head>/i', // <head>
+ '/<script[^>]*>.*?<\/script>/i', // <script>s -- which strip_tags supposedly has problems with
+ '/<style[^>]*>.*?<\/style>/i', // <style>s -- which strip_tags supposedly has problems 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>
+ '/(<dl[^>]*>|<\/dl>)/i', // <dl> and </dl>
+ '/<li[^>]*>(.*?)<\/li>/i', // <li> and </li>
+ '/<dd[^>]*>(.*?)<\/dd>/i', // <dd> and </dd>
+ '/<dt[^>]*>(.*?)<\/dt>/i', // <dt> and </dt>
+ '/<li[^>]*>/i', // <li>
+ '/<hr[^>]*>/i', // <hr>
+ '/<div[^>]*>/i', // <div>
+ '/(<table[^>]*>|<\/table>)/i', // <table> and </table>
+ '/(<tr[^>]*>|<\/tr>)/i', // <tr> and </tr>
+ '/<td[^>]*>(.*?)<\/td>/i', // <td> and </td>
+ '/<span class="_html2text_ignore">.+?<\/span>/i', // <span class="_html2text_ignore">...</span>
+ '/<(img)[^>]*alt=\"([^>"]+)\"[^>]*>/i', // <img> with alt tag
+ );
+
+ /**
+ * List of pattern replacements corresponding to patterns searched.
+ *
+ * @type array
+ * @see $search
+ */
+ protected $replace = array(
+ '', // Non-legal carriage return
+ ' ', // Newlines and tabs
+ '', // <head>
+ '', // <script>s -- which strip_tags supposedly has problems with
+ '', // <style>s -- which strip_tags supposedly has problems with
+ "\n\n", // <P>
+ "\n", // <br>
+ '_\\1_', // <i>
+ '_\\1_', // <em>
+ "\n\n", // <ul> and </ul>
+ "\n\n", // <ol> and </ol>
+ "\n\n", // <dl> and </dl>
+ "\t* \\1\n", // <li> and </li>
+ " \\1\n", // <dd> and </dd>
+ "\t* \\1", // <dt> and </dt>
+ "\n\t* ", // <li>
+ "\n-------------------------\n", // <hr>
+ "<div>\n", // <div>
+ "\n\n", // <table> and </table>
+ "\n", // <tr> and </tr>
+ "\t\t\\1\n", // <td> and </td>
+ "", // <span class="_html2text_ignore">...</span>
+ '[\\2]', // <img> with alt tag
+ );
+
+ /**
+ * List of preg* regular expression patterns to search for,
+ * used in conjunction with $entReplace.
+ *
+ * @type array
+ * @see $entReplace
+ */
+ protected $entSearch = array(
+ '/™/i', // TM symbol in win-1252
+ '/—/i', // m-dash in win-1252
+ '/&(amp|#38);/i', // Ampersand: see converter()
+ '/[ ]{2,}/', // Runs of spaces, post-handling
+ );
+
+ /**
+ * List of pattern replacements corresponding to patterns searched.
+ *
+ * @type array
+ * @see $entSearch
+ */
+ protected $entReplace = array(
+ '™', // TM symbol
+ '—', // m-dash
+ '|+|amp|+|', // Ampersand: see converter()
+ ' ', // Runs of spaces, post-handling
+ );
+
+ /**
+ * List of preg* regular expression patterns to search for
+ * and replace using callback function.
+ *
+ * @type array
+ */
+ protected $callbackSearch = array(
+ '/<(h)[123456]( [^>]*)?>(.*?)<\/h[123456]>/i', // h1 - h6
+ '/<(b)( [^>]*)?>(.*?)<\/b>/i', // <b>
+ '/<(strong)( [^>]*)?>(.*?)<\/strong>/i', // <strong>
+ '/<(th)( [^>]*)?>(.*?)<\/th>/i', // <th> and </th>
+ '/<(a) [^>]*href=("|\')([^"\']+)\2([^>]*)>(.*?)<\/a>/i' // <a href="">
+ );
+
+ /**
+ * List of preg* regular expression patterns to search for in PRE body,
+ * used in conjunction with $preReplace.
+ *
+ * @type array
+ * @see $preReplace
+ */
+ protected $preSearch = array(
+ "/\n/",
+ "/\t/",
+ '/ /',
+ '/<pre[^>]*>/',
+ '/<\/pre>/'
+ );
+
+ /**
+ * List of pattern replacements corresponding to patterns searched for PRE body.
+ *
+ * @type array
+ * @see $preSearch
+ */
+ protected $preReplace = array(
+ '<br>',
+ ' ',
+ ' ',
+ '',
+ '',
+ );
+
+ /**
+ * Temporary workspace used during PRE processing.
+ *
+ * @type string
+ */
+ protected $preContent = '';
+
+ /**
+ * Contains the base URL that relative links should resolve to.
+ *
+ * @type string
+ */
+ protected $baseurl = '';
+
+ /**
+ * Indicates whether content in the $html variable has been converted yet.
+ *
+ * @type boolean
+ * @see $html, $text
+ */
+ protected $converted = false;
+
+ /**
+ * Contains URL addresses from links to be rendered in plain text.
+ *
+ * @type array
+ * @see buildlinkList()
+ */
+ protected $linkList = array();
+
+ /**
+ * Various configuration options (able to be set in the constructor)
+ *
+ * @type array
+ */
+ protected $options = array(
+ 'do_links' => 'inline', // 'none'
+ // 'inline' (show links inline)
+ // 'nextline' (show links on the next line)
+ // 'table' (if a table of link URLs should be listed after the text.
+
+ 'width' => 70, // Maximum width of the formatted text, in columns.
+ // Set this value to 0 (or less) to ignore word wrapping
+ // and not constrain text to a fixed-width column.
+ );
+
+ private function legacyConstruct($html = '', $fromFile = false, array $options = array())
+ {
+ $this->set_html($html, $fromFile);
+ $this->options = array_merge($this->options, $options);
+ }
+
+ /**
+ * @param string $html Source HTML
+ * @param array $options Set configuration options
+ */
+ public function __construct($html = '', $options = array())
+ {
+ // for backwards compatibility
+ if (!is_array($options)) {
+ return call_user_func_array(array($this, 'legacyConstruct'), func_get_args());
+ }
+
+ $this->html = $html;
+ $this->options = array_merge($this->options, $options);
+ }
+
+ /**
+ * Set the source HTML
+ *
+ * @param string $html HTML source content
+ */
+ public function setHtml($html)
+ {
+ $this->html = $html;
+ $this->converted = false;
+ }
+
+ /**
+ * @deprecated
+ */
+ public function set_html($html, $from_file = false)
+ {
+ if ($from_file) {
+ throw new \InvalidArgumentException("Argument from_file no longer supported");
+ }
+
+ return $this->setHtml($html);
+ }
+
+ /**
+ * Returns the text, converted from HTML.
+ *
+ * @return string
+ */
+ public function getText()
+ {
+ if (!$this->converted) {
+ $this->convert();
+ }
+
+ return $this->text;
+ }
+
+ /**
+ * @deprecated
+ */
+ public function get_text()
+ {
+ return $this->getText();
+ }
+
+ /**
+ * @deprecated
+ */
+ public function print_text()
+ {
+ print $this->getText();
+ }
+
+ /**
+ * @deprecated
+ */
+ public function p()
+ {
+ return $this->print_text();
+ }
+
+ /**
+ * Sets a base URL to handle relative links.
+ *
+ * @param string $baseurl
+ */
+ public function setBaseUrl($baseurl)
+ {
+ $this->baseurl = $baseurl;
+ }
+
+ /**
+ * @deprecated
+ */
+ public function set_base_url($baseurl)
+ {
+ return $this->setBaseUrl($baseurl);
+ }
+
+ protected function convert()
+ {
+ $this->linkList = array();
+
+ $text = trim($this->html);
+
+ $this->converter($text);
+
+ if ($this->linkList) {
+ $text .= "\n\nLinks:\n------\n";
+ foreach ($this->linkList as $i => $url) {
+ $text .= '[' . ($i + 1) . '] ' . $url . "\n";
+ }
+ }
+
+ $this->text = $text;
+
+ $this->converted = true;
+ }
+
+ protected function converter(&$text)
+ {
+ $this->convertBlockquotes($text);
+ $this->convertPre($text);
+ $text = preg_replace($this->search, $this->replace, $text);
+ $text = preg_replace_callback($this->callbackSearch, array($this, 'pregCallback'), $text);
+ $text = strip_tags($text);
+ $text = preg_replace($this->entSearch, $this->entReplace, $text);
+ $text = html_entity_decode($text, ENT_QUOTES, self::ENCODING);
+
+ // Remove unknown/unhandled entities (this cannot be done in search-and-replace block)
+ $text = preg_replace('/&([a-zA-Z0-9]{2,6}|#[0-9]{2,4});/', '', $text);
+
+ // Convert "|+|amp|+|" into "&", need to be done after handling of unknown entities
+ // This properly handles situation of "&quot;" in input string
+ $text = str_replace('|+|amp|+|', '&', $text);
+
+ // Normalise empty lines
+ $text = preg_replace("/\n\s+\n/", "\n\n", $text);
+ $text = preg_replace("/[\n]{3,}/", "\n\n", $text);
+
+ // remove leading empty lines (can be produced by eg. P tag on the beginning)
+ $text = ltrim($text, "\n");
+
+ if ($this->options['width'] > 0) {
+ $text = wordwrap($text, $this->options['width']);
+ }
+ }
+
+ /**
+ * Helper function called by preg_replace() on link replacement.
+ *
+ * Maintains an internal list of links to be displayed at the end of the
+ * text, with numeric indices to the original point in the text they
+ * appeared. Also makes an effort at identifying and handling absolute
+ * and relative links.
+ *
+ * @param string $link URL of the link
+ * @param string $display Part of the text to associate number with
+ * @param null $linkOverride
+ * @return string
+ */
+ protected function buildlinkList($link, $display, $linkOverride = null)
+ {
+ $linkMethod = ($linkOverride) ? $linkOverride : $this->options['do_links'];
+ if ($linkMethod == 'none') {
+ return $display;
+ }
+
+ // Ignored link types
+ if (preg_match('!^(javascript:|mailto:|#)!i', $link)) {
+ return $display;
+ }
+
+ if (preg_match('!^([a-z][a-z0-9.+-]+:)!i', $link)) {
+ $url = $link;
+ } else {
+ $url = $this->baseurl;
+ if (substr($link, 0, 1) != '/') {
+ $url .= '/';
+ }
+ $url .= $link;
+ }
+
+ if ($linkMethod == 'table') {
+ if (($index = array_search($url, $this->linkList)) === false) {
+ $index = count($this->linkList);
+ $this->linkList[] = $url;
+ }
+
+ return $display . ' [' . ($index + 1) . ']';
+ } elseif ($linkMethod == 'nextline') {
+ return $display . "\n[" . $url . ']';
+ } else { // link_method defaults to inline
+ return $display . ' [' . $url . ']';
+ }
+ }
+
+ protected function convertPre(&$text)
+ {
+ // get the content of PRE element
+ while (preg_match('/<pre[^>]*>(.*)<\/pre>/ismU', $text, $matches)) {
+ $this->preContent = $matches[1];
+
+ // Run our defined tags search-and-replace with callback
+ $this->preContent = preg_replace_callback(
+ $this->callbackSearch,
+ array($this, 'pregCallback'),
+ $this->preContent
+ );
+
+ // convert the content
+ $this->preContent = sprintf(
+ '<div><br>%s<br></div>',
+ preg_replace($this->preSearch, $this->preReplace, $this->preContent)
+ );
+
+ // replace the content (use callback because content can contain $0 variable)
+ $text = preg_replace_callback(
+ '/<pre[^>]*>.*<\/pre>/ismU',
+ array($this, 'pregPreCallback'),
+ $text,
+ 1
+ );
+
+ // free memory
+ $this->preContent = '';
+ }
+ }
+
+ /**
+ * Helper function for BLOCKQUOTE body conversion.
+ *
+ * @param string $text HTML content
+ */
+ protected function convertBlockquotes(&$text)
+ {
+ if (preg_match_all('/<\/*blockquote[^>]*>/i', $text, $matches, PREG_OFFSET_CAPTURE)) {
+ $start = 0;
+ $taglen = 0;
+ $level = 0;
+ $diff = 0;
+ foreach ($matches[0] as $m) {
+ if ($m[0][0] == '<' && $m[0][1] == '/') {
+ $level--;
+ if ($level < 0) {
+ $level = 0; // malformed HTML: go to next blockquote
+ } elseif ($level > 0) {
+ // skip inner blockquote
+ } else {
+ $end = $m[1];
+ $len = $end - $taglen - $start;
+ // Get blockquote content
+ $body = substr($text, $start + $taglen - $diff, $len);
+
+ // Set text width
+ $pWidth = $this->options['width'];
+ if ($this->options['width'] > 0) $this->options['width'] -= 2;
+ // Convert blockquote content
+ $body = trim($body);
+ $this->converter($body);
+ // Add citation markers and create PRE block
+ $body = preg_replace('/((^|\n)>*)/', '\\1> ', trim($body));
+ $body = '<pre>' . htmlspecialchars($body) . '</pre>';
+ // Re-set text width
+ $this->options['width'] = $pWidth;
+ // Replace content
+ $text = substr($text, 0, $start - $diff)
+ . $body . substr($text, $end + strlen($m[0]) - $diff);
+
+ $diff = $len + $taglen + strlen($m[0]) - strlen($body);
+ unset($body);
+ }
+ } else {
+ if ($level == 0) {
+ $start = $m[1];
+ $taglen = strlen($m[0]);
+ }
+ $level++;
+ }
+ }
+ }
+ }
+
+ /**
+ * Callback function for preg_replace_callback use.
+ *
+ * @param array $matches PREG matches
+ * @return string
+ */
+ protected function pregCallback($matches)
+ {
+ switch (strtolower($matches[1])) {
+ case 'b':
+ case 'strong':
+ return $this->toupper($matches[3]);
+ case 'th':
+ return $this->toupper("\t\t" . $matches[3] . "\n");
+ case 'h':
+ return $this->toupper("\n\n" . $matches[3] . "\n\n");
+ case 'a':
+ // override the link method
+ $linkOverride = null;
+ if (preg_match('/_html2text_link_(\w+)/', $matches[4], $linkOverrideMatch)) {
+ $linkOverride = $linkOverrideMatch[1];
+ }
+ // Remove spaces in URL (#1487805)
+ $url = str_replace(' ', '', $matches[3]);
+
+ return $this->buildlinkList($url, $matches[5], $linkOverride);
+ }
+
+ return '';
+ }
+
+ /**
+ * Callback function for preg_replace_callback use in PRE content handler.
+ *
+ * @param array $matches PREG matches
+ * @return string
+ */
+ protected function pregPreCallback(/** @noinspection PhpUnusedParameterInspection */ $matches)
+ {
+ return $this->preContent;
+ }
+
+ /**
+ * Strtoupper function with HTML tags and entities handling.
+ *
+ * @param string $str Text to convert
+ * @return string Converted text
+ */
+ protected function toupper($str)
+ {
+ // string can contain HTML tags
+ $chunks = preg_split('/(<[^>]*>)/', $str, null, PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE);
+
+ // convert toupper only the text between HTML tags
+ foreach ($chunks as $i => $chunk) {
+ if ($chunk[0] != '<') {
+ $chunks[$i] = $this->strtoupper($chunk);
+ }
+ }
+
+ return implode($chunks);
+ }
+
+ /**
+ * Strtoupper multibyte wrapper function with HTML entities handling.
+ *
+ * @param string $str Text to convert
+ * @return string Converted text
+ */
+ protected function strtoupper($str)
+ {
+ $str = html_entity_decode($str, ENT_COMPAT, self::ENCODING);
+
+ if (function_exists('mb_strtoupper')) {
+ $str = mb_strtoupper($str, self::ENCODING);
+ } else {
+ $str = strtoupper($str);
+ }
+
+ $str = htmlspecialchars($str, ENT_COMPAT, self::ENCODING);
+
+ return $str;
+ }
+}
--- /dev/null
+<?php
+// This file is part of Moodle - http://moodle.org/
+//
+// Moodle is free software: you can redistribute it and/or modify
+// it under the terms of the GNU General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// Moodle is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+// GNU General Public License for more details.
+//
+// You should have received a copy of the GNU General Public License
+// along with Moodle. If not, see <http://www.gnu.org/licenses/>.
+
+/**
+ * Wrapper for Html2Text
+ *
+ * This wrapper allows us to modify the upstream library without hacking it too much.
+ *
+ * @package core
+ * @copyright 2015 Andrew Nicols <andrew@nicols.uk>
+ * @license http://www.gnu.org/copyleft/gpl.html GNU GPL v3 or later
+ */
+
+defined('MOODLE_INTERNAL') || die();
+
+require_once($CFG->libdir . '/html2text/Html2Text.php');
+
+/**
+ * Wrapper for Html2Text
+ *
+ * This wrapper allows us to modify the upstream library without hacking it too much.
+ *
+ * @package core
+ * @copyright 2015 Andrew Nicols <andrew@nicols.uk>
+ * @license http://www.gnu.org/copyleft/gpl.html GNU GPL v3 or later
+ */
+class core_html2text extends \Html2Text\Html2Text {
+
+ /**
+ * Constructor.
+ *
+ * If the HTML source string (or file) is supplied, the class
+ * will instantiate with that source propagated, all that has
+ * to be done it to call get_text().
+ *
+ * @param string $html Source HTML
+ * @param array $options Set configuration options
+ */
+ function __construct($html = '', $options = array()) {
+ // Call the parent constructor.
+ parent::__construct($html, $options);
+
+ // MDL-27736: Trailing spaces before newline or tab.
+ $this->entSearch[] = '/[ ]+([\n\t])/';
+ $this->entReplace[] = '\\1';
+ }
+
+ /**
+ * Strtoupper multibyte wrapper function with HTML entities handling.
+ *
+ * @param string $str Text to convert
+ * @return string Converted text
+ */
+ protected function strtoupper($str) {
+ return core_text::strtoupper($str);
+ }
+}
--- /dev/null
+Description of Html2Text library import into Moodle
+
+Instructions
+------------
+1. Clone https://github.com/mtibben/html2text.git into an unrelated directory
+2. Copy /path/to/html2text/src/Html2Text.php to lib/html2text/
+
+Imported from: https://github.com/mtibben/html2text.git
+++ /dev/null
-Customised html2text.php from the RoundCube project:
-
- http://trac.roundcube.net/log/trunk/roundcubemail/program/lib/html2text.php
-
- -- Francois Marier <francois@catalyst.net.nz> 2009-05-22
-
-Modifications
---------------
-
-1. Don't just strip images, replace them with their alt text. (Tim Hunt 2010-08-04)
-2. No strip slashes, we do not use magic quotes any more in Moodle 2.0 or later
-3. Use core_text, not crappy functions that break UTF-8, in the _strtoupper method. (Tim Hunt 2010-11-02)
-4. Make sure html2text does not destroy '0'. (Tim Hunt 2011-09-21)
-5. define missing mail charset
-6. Fixed the links list enumeration (MDL-35206).
-
-
-Imported from: https://github.com/moodle/custom-html2text/tree/MOODLE_5886_1
'<br /> int i = 0;<br /> while (in_string[i] != \'\0\') {<br /> in_string[i] = \'X\';<br /> i++;<br /> }<br />'.
'}</span></pre>What would happen if a non-terminated string were input to this function?<br /><br />';
+ // Note, the spaces in the <pre> section are Unicode NBSPs - they may not be displayed in your editor.
$strconv = 'Consider the following function:
-void FillMeUp(char* in_string) {
- int i = 0;
- while (in_string[i] != \'\0\') {
- in_string[i] = \'X\';
- i++;
- }
+void FillMeUp(char* in_string) {
+ int i = 0;
+ while (in_string[i] != \'\0\') {
+ in_string[i] = \'X\';
+ i++;
+ }
}
What would happen if a non-terminated string were input to this function?
<location>html2text.php</location>
<name>HTML2Text</name>
<license>GPL</license>
- <version>1.0.0</version>
- <licenseversion>3.0+</licenseversion>
+ <version>3.0.0</version>
+ <licenseversion>2.0+</licenseversion>
</library>
<library>
<location>markdown</location>
* Less.php upgraded to 1.7.0.9
* The horde library has been updated to version 5.2.7.
* Google libraries (lib/google) updated to 1.1.5
+* Html2Text library has been updated to the latest version of the library.
* External functions x_is_allowed_from_ajax() methods have been deprecated. Define 'ajax' => true in db/services.php instead.
* External functions can be called without a session if they define 'loginrequired' => true in db/services.php.
* All plugins are required to declare their frankenstyle component name via
* @return string plain text equivalent of the HTML.
*/
function html_to_text($html, $width = 75, $dolinks = true) {
-
global $CFG;
- require_once($CFG->libdir .'/html2text.php');
+ require_once($CFG->libdir .'/html2text/lib.php');
+
+ $options = array(
+ 'width' => $width,
+ 'do_links' => 'table',
+ );
- $h2t = new html2text($html, false, $dolinks, $width);
- $result = $h2t->get_text();
+ if (empty($dolinks)) {
+ $options['do_links'] = 'none';
+ }
+ $h2t = new core_html2text($html, $options);
+ $result = $h2t->getText();
return $result;
}
