/**
* get dom node's plain text
*
* @return string
*/
public function text()
{
if (isset($this->_[HDOM_INFO_INNER])) {
return $this->_[HDOM_INFO_INNER];
}
switch ($this->nodetype) {
case HDOM_TYPE_TEXT:
return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]);
case HDOM_TYPE_COMMENT:
return '';
case HDOM_TYPE_UNKNOWN:
return '';
}
if (strcasecmp($this->tag, 'script') === 0) {
return '';
}
if (strcasecmp($this->tag, 'style') === 0) {
return '';
}
$ret = '';
// In rare cases, (always node type 1 or HDOM_TYPE_ELEMENT - observed for some span tags, and some p tags) $this->nodes is set to NULL.
// NOTE: This indicates that there is a problem where it's set to NULL without a clear happening.
// WHY is this happening?
if (null !== $this->nodes) {
foreach ($this->nodes as $n) {
$ret .= $n->text();
}
// If this node is a span... add a space at the end of it so multiple spans don't run into each other. This is plaintext after all.
if ($this->tag == 'span') {
$ret .= $this->dom->default_span_text;
}
}
return $ret;
}
private function makeup()
{
// text, comment, unknown
if (isset($this->_[DomInfo::TEXT])) {
return $this->dom->restore_noise($this->_[DomInfo::TEXT]);
}
$ret = '<' . $this->tag;
$i = -1;
foreach ($this->attr as $key => $val) {
++$i;
// skip removed attribute
if ($val === null || $val === false) {
continue;
}
$ret .= $this->_[DomInfo::SPACE][$i][0];
//no value attr: nowrap, checked selected...
if ($val === true) {
$ret .= $key;
} else {
switch ($this->_[DomInfo::QUOTE][$i]) {
case QuoteType::DOUBLE:
$quote = '"';
break;
case QuoteType::SINGLE:
$quote = '\'';
break;
default:
$quote = '';
}
$ret .= $key . $this->_[DomInfo::SPACE][$i][1] . '=' . $this->_[DomInfo::SPACE][$i][2] . $quote . $val . $quote;
}
}
$ret = $this->dom->restore_noise($ret);
return $ret . $this->_[DomInfo::ENDSPACE] . '>';
}
