'/&(bull|#149|#8226);/i', // Bullet
'/&(pound|#163);/i', // Pound sign
'/&(euro|#8364);/i', // Euro sign
- '/&[^&;]+;/i', // Unknown/unhandled entities
'/[ ]{2,}/' // Runs of spaces, post-handling
);
"\n\n", // <ol> and </ol>
"\t* \\1\n", // <li> and </li>
"\n\t* ", // <li>
- "\n-------------------------\n", // <hr>
- "\n\n", // <table> and </table>
+ "\n-------------------------\n", // <hr>
+ "\n\n", // <table> and </table>
"\n", // <tr> and </tr>
"\t\t\\1\n", // <td> and </td>
' ', // Non-breaking space
'*',
'£',
'EUR', // Euro sign. \80 ?
- '', // Unknown/unhandled entities
' ' // Runs of spaces, post-handling
);
* @see $pre_replace
*/
var $pre_search = array(
- "/\n/",
- "/\t/",
- '/ /',
- '/<pre[^>]*>/',
- '/<\/pre>/'
+ "/\n/",
+ "/\t/",
+ '/ /',
+ '/<pre[^>]*>/',
+ '/<\/pre>/'
);
/**
* @see $pre_search
*/
var $pre_replace = array(
- '<br>',
- ' ',
- ' ',
- '',
- ''
+ '<br>',
+ ' ',
+ ' ',
+ '',
+ ''
);
/**
if ( !empty($source) ) {
$this->set_html($source, $from_file);
}
-
+
$this->set_base_url();
- $this->_do_links = $do_links;
- $this->width = $width;
+ $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);
+ $this->html = file_get_contents($source);
}
else
- $this->html = $source;
+ $this->html = $source;
$this->_converted = false;
}
$text = trim(stripslashes($this->html));
- // Convert <PRE>
+ // Convert <PRE>
$this->_convert_pre($text);
- // Replace known html entities
- $text = html_entity_decode($text, ENT_COMPAT, 'UTF-8');
-
// 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);
$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
- $additional = '';
+ } elseif ( substr($link, 0, 11) == 'javascript:' ) {
+ // Don't count the link; ignore it
+ $additional = '';
// what about href="#anchor" ?
} else {
$this->_link_count++;
*/
function _convert_pre(&$text)
{
- while(preg_match('/<pre[^>]*>(.*)<\/pre>/ismU', $text, $matches))
- {
- $result = preg_replace($this->pre_search, $this->pre_replace, $matches[1]);
- $text = preg_replace('/<pre[^>]*>.*<\/pre>/ismU', '<div><br>' . $result . '<br></div>', $text, 1);
- }
+ while(preg_match('/<pre[^>]*>(.*)<\/pre>/ismU', $text, $matches)) {
+ $result = preg_replace($this->pre_search, $this->pre_replace, $matches[1]);
+ $text = preg_replace('/<pre[^>]*>.*<\/pre>/ismU', '<div><br>' . $result . '<br></div>', $text, 1);
+ }
}
/**
*/
function _preg_callback($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], $matches[4]);
- }
+ switch($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], $matches[4]);
+ }
}
/**
*/
function _strtoupper($str)
{
- if (function_exists('mb_strtoupper'))
- return mb_strtoupper($str);
- else
- return strtoupper($str);
+ if (function_exists('mb_strtoupper'))
+ return mb_strtoupper($str);
+ else
+ return strtoupper($str);
}
}