/**
* Convert HTML into Text.
*/
protected function convert()
{
$this->linkList = array();
$endSearchReplaceArrayKeys = array_keys($this->endSearchReplaceArray);
$endSearchReplaceArrayValues = array_values($this->endSearchReplaceArray);
// Clean the string from non-UTF8 chars & remove UTF8-BOM & normalize whitespace.
$text = UTF8::clean($this->html, true, true, false);
$this->converter($text);
// Normalize whitespace, once again.
$text = UTF8::normalize_whitespace($text);
// Add the link-list, if needed.
if (count($this->linkList) > 0) {
$text .= '[[_html2text_links]]';
foreach ($this->linkList as $i => $url) {
$text .= '[' . ($i + 1) . '] ' . $url . "\n";
}
}
// Trim every line.
$textArray = explode("\n", $text);
array_walk($textArray, array('self', 'trimCallback'));
$text = implode("\n", $textArray);
// Convert "space"-replacer into space.
$text = str_replace('|+|_html2text_space|+|', ' ', $text);
// Replace some placeholder at the end.
$text = preg_replace($endSearchReplaceArrayKeys, $endSearchReplaceArrayValues, $text);
// Normalise empty lines.
$text = preg_replace("/\n\\s+\n/", "\n\n", $text);
$text = preg_replace("/[\n]{3,}/", "\n\n", $text);
// If max length of line is defined, then use "wordwrap".
if ($this->options['width'] > 0) {
$text = UTF8::wordwrap($text, $this->options['width']);
}
// Remove leading/ending empty lines/spaces.
$text = trim($text);
$this->text = $text;
$this->converted = true;
}
/**
* convert HTML into Text
*/
protected function convert()
{
$this->linkList = array();
// clean the string from non-UTF8 chars
// & remove UTF8-BOM
// & normalize whitespace
$text = UTF8::clean($this->html, true, true, false);
$text = UTF8::trim(stripslashes($text));
$this->converter($text);
if (count($this->linkList) > 0) {
$text .= "\n\nLinks:\n------\n";
foreach ($this->linkList as $i => $url) {
$text .= '[' . ($i + 1) . '] ' . $url . "\n";
}
}
// normalize whitespace, again
$text = UTF8::normalize_whitespace($text);
// don't use tabs
$text = preg_replace("/\t/", ' ', $text);
// trim every line
$textArray = explode("\n", $text);
array_walk($textArray, array('self', 'trimCallback'));
$text = implode("\n", $textArray);
// remove leading/ending empty lines
$text = UTF8::trim($text, "\n");
$this->text = $text;
$this->converted = true;
}
/**
* Convert a string to e.g.: "snake_case"
*
* @return Stringy Object with $str in snake_case
*/
public function snakeize()
{
$str = $this->str;
$encoding = $this->encoding;
$str = UTF8::normalize_whitespace($str);
$str = str_replace('-', '_', $str);
$str = preg_replace_callback('/([\\d|A-Z])/u', function ($matches) use($encoding) {
$match = $matches[1];
$matchInt = (int) $match;
if ("{$matchInt}" == $match) {
return '_' . $match . '_';
} else {
return '_' . UTF8::strtolower($match, $encoding);
}
}, $str);
$str = preg_replace(array('/\\s+/', '/^\\s+|\\s+$/', '/_+/'), array('_', '', '_'), $str);
$str = UTF8::trim($str, '_');
// trim leading & trailing "_"
$str = UTF8::trim($str);
// trim leading & trailing whitespace
return static::create($str, $this->encoding);
}
