Усечение функции переопределениятеги, как исправить? - PullRequest
0 голосов
/ 16 марта 2012

моя CMS использует эту функцию для усечения строк html.

/*
*
* @param string $text String to truncate.
* @param integer $length Length of returned string, including ellipsis.
* @param string $ending Ending to be appended to the trimmed string.
* @param boolean $exact If false, $text will not be cut mid-word
* @param boolean $considerHtml If true, HTML tags would be handled correctly
* @return string Trimmed string.
* http://dodona.wordpress.com/2009/04/05/how-do-i-truncate-an-html-string-without-breaking-the-html-code/
*/
function truncate($text, $length = 100, $ending = '...', $exact = false, $considerHtml = true)
{
    if ($considerHtml)
    {
        // if the plain text is shorter than the maximum length, return the whole text
        if (strlen(preg_replace('/<.*?>/', '', $text)) <= $length)
        {
            return $text;
        }
        // splits all html-tags to scanable lines
        preg_match_all('/(<.+?>)?([^<>]*)/s', $text, $lines, PREG_SET_ORDER);
        $total_length = strlen($ending);
        $open_tags = array();
        $truncate = '';
        foreach ($lines as $line_matchings)
        {
            // if there is any html-tag in this line, handle it and add it (uncounted) to the output
            if (!empty($line_matchings[1]))
            {
                // if it's an "empty element" with or without xhtml-conform closing slash
                if (preg_match('/^<(\s*.+?\/\s*|\s*(img|br|input|hr|area|base|basefont|col|frame|isindex|link|meta|param)(\s.+?)?)>$/is', $line_matchings[1]))
                {
                // do nothing
                // if tag is a closing tag
                }
                else if (preg_match('/^<\s*\/([^\s]+?)\s*>$/s', $line_matchings[1], $tag_matchings))
                {
                    // delete tag from $open_tags list
                    $pos = array_search($tag_matchings[1], $open_tags);
                    if ($pos !== false) 
                    {
                        unset($open_tags[$pos]);
                    }
                // if tag is an opening tag
                } 
                else if (preg_match('/^<\s*([^\s>!]+).*?>$/s', $line_matchings[1], $tag_matchings)) 
                {
                    // add tag to the beginning of $open_tags list
                    array_unshift($open_tags, strtolower($tag_matchings[1]));
                }
                // add html-tag to $truncate'd text
                $truncate .= $line_matchings[1];
            }
            // calculate the length of the plain text part of the line; handle entities as one character
            $content_length = strlen(preg_replace('/&[0-9a-z]{2,8};|&#[0-9]{1,7};|[0-9a-f]{1,6};/i', ' ', $line_matchings[2]));
            if ($total_length+$content_length> $length) 
            {
                // the number of characters which are left
                $left = $length - $total_length;
                $entities_length = 0;
                // search for html entities
                if (preg_match_all('/&[0-9a-z]{2,8};|&#[0-9]{1,7};|[0-9a-f]{1,6};/i', $line_matchings[2], $entities, PREG_OFFSET_CAPTURE)) 
                {
                    // calculate the real length of all entities in the legal range
                    foreach ($entities[0] as $entity) 
                    {
                        if ($entity[1]+1-$entities_length <= $left) 
                        {
                            $left--;
                            $entities_length += strlen($entity[0]);
                        } 
                        else 
                        {
                            // no more characters left
                            break;
                        }
                    }
                }
                $truncate .= substr($line_matchings[2], 0, $left+$entities_length);
                // maximum lenght is reached, so get off the loop
                break;
            } 
            else 
            {
                $truncate .= $line_matchings[2];
                $total_length += $content_length;
            }
            // if the maximum length is reached, get off the loop
            if($total_length>= $length) 
            {
                break;
            }
        }
    }
    else 
    {
        if (strlen($text) <= $length) 
        {
            return $text;
        } 
        else 
        {
            $truncate = substr($text, 0, $length - strlen($ending));
        }
    }
    // if the words shouldn't be cut in the middle...
    if (!$exact) 
    {
        // ...search the last occurance of a space...
        $spacepos = strrpos($truncate, ' ');
        if (isset($spacepos)) 
        {
            // ...and cut the text in this position
            $truncate = substr($truncate, 0, $spacepos);
        }
    }
    // add the defined ending to the text
    $truncate .= $ending;
    if($considerHtml) 
    {
        // close all unclosed html-tags
        foreach ($open_tags as $tag) 
        {
            $truncate .= '</' . $tag . '>';
        }
    }
    return $truncate;
}

единственная проблема, с которой я сталкиваюсь, связана с <br /> тегами ..

Пример:

inэлемент контента, который у меня есть что-то вроде:

This is just and example to illustrate what im talking about. As you can see this is the first paragraph of the feed iten content.
This is the second paragraph, as you can see, the second paragraph is separated by the first paragraph with a line break.

в моем посте CMS, созданном с использованием этого элемента контента, у меня есть все абзацы один за другим, без каких-либо разрывов строк и пробелов, что-то вроде:

This is just and example to illustrate what im talking about. As you can see this is the first paragraph of the feed iten **content.This** is the second paragraph, as you can see, the second paragraph is separated by the first paragraph with a line break.

Как видите, конец первого абзаца застрял с началом второго абзаца.Без разрыва строки и без пробела, разделяющего их (проверьте жирным шрифтом).

есть идеи, как это решить?

...