/**
* Создание фрагмента для сниппета
*
* @param string $sText
* @param array $aSet
* @param int $nPos
* @param int $nLen
*
* @return string
*/
protected function _makeSnippetFragment($sText, $aSet, $nPos, $nLen)
{
$nLenWord = $nLen;
$nLenText = mb_strlen($sText);
$nShippetOffset = floor(($this->nShippetLength - $nLenWord) / 2);
// начало фрагмена
if ($nPos < $nShippetOffset) {
$nFragBegin = 0;
} else {
$nFragBegin = $nPos - $nShippetOffset;
}
// конец фрагмента
if ($nPos + $nLenWord + $nShippetOffset > $nLenText) {
$nFragEnd = $nLenText;
} else {
$nFragEnd = $nPos + $nLenWord + $nShippetOffset;
}
// Выравнивание по границе слов
$sPattern = '/' . $this->sPatternW . '+$/uisxSXU';
if ($nFragBegin > 0 && mb_preg_match($sPattern, mb_substr($sText, 0, $nFragBegin), $m, PREG_OFFSET_CAPTURE)) {
$nFragBegin -= mb_strlen($m[0][0]);
}
$sPattern = '/^' . $this->sPatternW . '+/uisxSXU';
if ($nFragEnd < $nLenText && mb_preg_match($sPattern, mb_substr($sText, $nFragEnd), $m, PREG_OFFSET_CAPTURE)) {
$nFragEnd += mb_strlen($m[0][0]) + $m[0][1];
}
// Обрезание по максимальной длине
if ($this->nShippetMaxLength > 0 && ($nOver = $nFragEnd - $nFragBegin - $this->nShippetMaxLength) > 0) {
$nFragBegin -= floor($nOver / 2);
if ($nFragBegin < 0) {
$nFragBegin = 0;
}
if ($nFragBegin > $nPos) {
$nFragBegin = $nPos;
}
$nFragEnd = $nFragBegin + $this->nShippetMaxLength;
if ($nFragEnd < $nPos + $nLenWord) {
$nFragEnd = $nPos + $nLenWord;
}
}
$sFragment = '';
// * Укладываем слова из одного сета в один фрагмент
$iBegin = $nFragBegin;
foreach ($aSet as $aWord) {
$iWordPos = $aWord['pos'];
$sFragment .= str_replace('>', '>', str_replace('<', '<', mb_substr($sText, $iBegin, $iWordPos - $iBegin)));
$sFragment .= $this->sSnippetBeforeMatch . $aWord['txt'] . $this->sSnippetAfterMatch;
$iBegin = $iWordPos + $aWord['len'];
}
$sFragment .= str_replace('>', '>', str_replace('<', '<', mb_substr($sText, $iBegin, $nFragEnd - $iBegin)));
$sFragment = ($nFragBegin > 0 ? '…' : '') . $sFragment . ($nFragEnd < $nLenText ? '…' : '');
$sFragment = str_replace('<br/>', '', $sFragment);
return $sFragment;
}
/** ************************************************************************************************************
* Function to truncate and shorten text
*
* @param string $html The html code which should be shortened
* @param int $length The length to which the text should be shortened
* @param bool skip If this value is true the truncate will be skipped (nothing will be done)
* @param bool perserve_tags Specifies if html tags should be preserved or if only the text should be shortened
***************************************************************************************************************/
public function truncate($html, $length, $skip = false, $preserve_tags = true)
{
mb_internal_encoding("UTF-8");
if (0 >= $length || mb_strlen($html) <= $length || $skip) {
// do nothing
return $html;
} elseif (!$preserve_tags) {
// only shorten text
return mb_substr($html, 0, $length);
} else {
// truncate with preserving html tags
$printedLength = 0;
$position = 0;
$tags = array();
$out = '';
while ($printedLength < $length && mb_preg_match('{</?([a-z]+\\d?)[^>]*>|&#?[a-zA-Z0-9]+;}', $html, $match, PREG_OFFSET_CAPTURE, $position)) {
list($tag, $tagPosition) = $match[0];
// Print text leading up to the tag
$str = mb_substr($html, $position, $tagPosition - $position);
if ($printedLength + mb_strlen($str) > $length) {
$out .= mb_substr($str, 0, $length - $printedLength);
$printedLength = $length;
break;
}
$out .= $str;
$printedLength += mb_strlen($str);
if ('&' == $tag[0]) {
// Handle the entity
$out .= $tag;
$printedLength++;
} else {
// Handle the tag
$tagName = $match[1][0];
if ('/' == $tag[1]) {
// This is a closing tag
$openingTag = array_pop($tags);
assert($openingTag == $tagName);
// check that tags are properly nested
$out .= $tag;
} else {
if ('/' == $tag[mb_strlen($tag) - 2]) {
// Self-closing tag
$out .= $tag;
} else {
// Opening tag
$out .= $tag;
$tags[] = $tagName;
}
}
}
// Continue after the tag
$position = $tagPosition + mb_strlen($tag);
}
// Print any remaining text
if ($printedLength < $length && $position < mb_strlen($html)) {
$out .= mb_substr($html, $position, $length - $printedLength);
}
// Print ellipsis ("...") if the html is not complete
if (mb_strlen($html) != $position) {
$out .= ' …';
}
// Close any open tags.
while (!empty($tags)) {
$out .= '</' . array_pop($tags) . '>';
}
return $out;
}
}
/** **************************************************************************************************
* Truncate HTML, close opened tags
*
* @param int $max_length The length (number of characters) to which the text will be
* shortened. With "0" the full text will be returned. With "auto"
* also the complete text will be used, but a wrapper div will be
* added which shortens the text to 1 full line via css.
* @param string $html The html code which should be shortened.
* @param string $wrapper_type Defines which kind of wrapper shall be added around the html code
* if a manual length shall be used. The possible values are "none",
* "div" and "span". With "none" no wrapper will be added, "div" and
* "span" are the 2 available wrapper types.
* If max_length is set to auto a div is mandatory and will be added
* always, independent of the given value.
* @param array $wrapper_attributes Additional attributes for the wrapper element. The array
* key defines the attribute name.
*****************************************************************************************************/
private function truncate($max_length, $html, $wrapper_type = 'none', $wrapper_attributes = array())
{
// Apply wrapper and add required css for autolength (if required)
$autolength = 'auto' == $max_length ? true : false;
if ($autolength) {
$wrapper_type = 'div';
} elseif ('div' != $wrapper_type && 'span' != $wrapper_type) {
$wrapper_type = 'none';
}
if ('none' != $wrapper_type) {
$wrapper_text = '<' . $wrapper_type;
foreach ($wrapper_attributes as $name => $value) {
$wrapper_text .= ' ' . $name . '="' . $value . '"';
}
if ($autolength) {
$wrapper_text .= ' style="white-space:nowrap; overflow:hidden; text-overflow:ellipsis"';
}
$html = $wrapper_text . '>' . $html . '</' . $wrapper_type . '>';
}
// Apply manual length
mb_internal_encoding("UTF-8");
if (is_numeric($max_length) && 0 < $max_length && mb_strlen($html) > $max_length) {
$printedLength = 0;
$position = 0;
$tags = array();
$out = '';
while ($printedLength < $max_length && mb_preg_match('{</?([a-z]+\\d?)[^>]*>|&#?[a-zA-Z0-9]+;}', $html, $match, PREG_OFFSET_CAPTURE, $position)) {
list($tag, $tagPosition) = $match[0];
// Print text leading up to the tag
$str = mb_substr($html, $position, $tagPosition - $position);
if ($printedLength + mb_strlen($str) > $max_length) {
$out .= mb_substr($str, 0, $max_length - $printedLength);
$printedLength = $max_length;
break;
}
$out .= $str;
$printedLength += mb_strlen($str);
if ('&' == $tag[0]) {
// Handle the entity
$out .= $tag;
$printedLength++;
} else {
// Handle the tag
$tagName = $match[1][0];
if ('/' == $tag[1]) {
// This is a closing tag
$openingTag = array_pop($tags);
assert($openingTag == $tagName);
// check that tags are properly nested
$out .= $tag;
} else {
if ('/' == $tag[mb_strlen($tag) - 2]) {
// Self-closing tag
$out .= $tag;
} else {
// Opening tag
$out .= $tag;
$tags[] = $tagName;
}
}
}
// Continue after the tag
$position = $tagPosition + mb_strlen($tag);
}
// Print any remaining text
if ($printedLength < $max_length && $position < mb_strlen($html)) {
$out .= mb_substr($html, $position, $max_length - $printedLength);
}
// Print ellipsis ("...") if the html is not complete
if (mb_strlen($html) != $position) {
$out .= ' …';
}
// Close any open tags.
while (!empty($tags)) {
$out .= '</' . array_pop($tags) . '>';
}
return $out;
}
return $html;
}
/**
* Создание фрагмента для сниппета
*/
protected function MakeSnippetFragment($text, $set, $pos, $len)
{
$fragment = '';
$lenWord = $len;
$lenText = mb_strlen($text);
$this->nShippetOffset = floor(($this->nShippetLength - $lenWord) / 2);
// начало фрагмена
if ($pos < $this->nShippetOffset) {
$fragBegin = 0;
} else {
$fragBegin = $pos - $this->nShippetOffset;
}
// конец фрагмента
if ($pos + $lenWord + $this->nShippetOffset > $lenText) {
$fragEnd = $lenText;
} else {
$fragEnd = $pos + $lenWord + $this->nShippetOffset;
}
// Выравнивание по границе слов
if ($fragBegin > 0 && mb_preg_match('/' . $this->sPatternW . '+$/uisxSX', mb_substr($text, 0, $fragBegin), $m)) {
$fragBegin -= mb_strlen($m[0][0]);
}
if ($fragEnd < $lenText && mb_preg_match('/' . $this->sPatternW . '+/uisxSX', mb_substr($text, $fragEnd), $m)) {
$fragEnd += mb_strlen($m[0][0]) + $m[0][1];
}
// Обрезание по максимальной длине
if ($this->nShippetMaxLength > 0 && ($nOver = $fragEnd - $fragBegin - $this->nShippetMaxLength) > 0) {
$fragBegin -= floor($nOver / 2);
if ($fragBegin > $pos) {
$fragBegin = $pos;
}
$fragEnd = $fragBegin + $this->nShippetMaxLength;
if ($fragEnd < $pos + $lenWord) {
$fragEnd = $pos + $lenWord;
}
}
$fragment = '';
// * Укладываем слова из одного сета в один фрагмент
$begin = $fragBegin;
foreach ($set as $word) {
$pos = $word['pos'];
$fragment .= str_replace('>', '>', str_replace('<', '<', mb_substr($text, $begin, $pos - $begin)));
$fragment .= $this->sSnippetBeforeMatch . $word['txt'] . $this->sSnippetAfterMatch;
$begin = $pos + $word['len'];
}
$fragment .= str_replace('>', '>', str_replace('<', '<', mb_substr($text, $begin, $fragEnd - $begin)));
$fragment = ($fragBegin > 0 ? '…' : '') . $fragment . ($fragEnd < $lenText ? '…' : '');
$fragment = str_replace('<br/>', '', $fragment);
return $fragment;
}
