Created
July 3, 2014 18:08
-
-
Save mrwweb/69bec24ac577ace69d63 to your computer and use it in GitHub Desktop.
Improved version of text-truncating html string function to improve character count accuracy. Code found on oikos.org.uk/2013/02/tech-notes-a-wordpress-excerpt-with-html-tags/.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<? | |
/** | |
* Truncates text. | |
* | |
* Cuts a string to the length of $length and replaces the last characters | |
* with the ending if the text is longer than length. | |
* | |
* See: oikos.org.uk/2013/02/tech-notes-a-wordpress-excerpt-with-html-tags/ | |
* See also: wpengineer.com/2410/dont-use-strlen/ | |
* See also also: oikos.org.uk/2013/02/tech-notes-a-wordpress-excerpt-with-html-tags/#comment-1467093876 | |
* | |
* @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. | |
*/ | |
function prefix_me_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(utf8_decode(preg_replace( array( '/<.*?>/', '/\n/', '/&[0-9a-z]{2,8};|&#[0-9]{1,7};|&#x[0-9a-f]{1,6};/i' ), array( '', '', ' ' ), $text))) <= $length) { | |
return $text; | |
} | |
// splits all html-tags to scanable lines | |
preg_match_all('/(<.+?>)?([^<>]*)/s', $text, $lines, PREG_SET_ORDER); | |
$total_length = ( $ending === '…' ) ? 2 : strlen( utf8_decode($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 (f.e. <br/>) | |
if (preg_match('/^<(\s*.+?\/\s*|\s*(img|br|input|hr|area|base|basefont|col|frame|isindex|link|meta|param)(\s.+?)?)>$/is', $line_matchings[1])) { | |
// do nothing | |
// if tag is a closing tag (f.e. </b>) | |
} else if (preg_match('/^<\s*\/([^\s]+?)\s*>$/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 (f.e. <b>) | |
} 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(utf8_decode(preg_replace('/&[0-9a-z]{2,8};|&#[0-9]{1,7};|&#x[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};|&#x[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--; | |
$entities_length += strlen(utf8_decode($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 >= $length) { | |
break; | |
} | |
} | |
} else { | |
if (strlen(utf8_decode($text)) <= $length) { | |
return $text; | |
} else { | |
$truncate = substr($text, 0, $length - strlen(utf8_decode($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; | |
} |
Thanks so much for this code. Certainly helps out. I'm wondering how to alter this snippet to take into account whole words, instead of individual characters.
thanks for your code ... b've found a little bug
it does not work if the code cut in an style attr
for example in this case ;)
If someone has a hack ;)
$dsc = ('<div style="margin-left: 40px;">xxxxxxxx xxxxx,</div>');
echo '<textarea>'.prefix_me_truncate($dsc, 10, '...', false, true) .'</textarea>';
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hey @mrwweb! I found this Gist from your comment here on Oikos.org.
This function is exactly what I needed for my post excerpts. However, I am also trying to append the "Read More" permalink to the end of the truncated text. Specifically, I want to keep the link inline before the final closing P tag... instead of having the Read More link on a new line.
If you could find it in your heart to help me out I would be forever grateful. I can't figure out how to incorporate this within the function. Thanks!