/**
* Tries to convert the given HTML into a plain text format - best suited for
* e-mail display, etc.
*
* <p>In particular, it tries to maintain the following features:
* <ul>
* <li>Links are maintained, with the 'href' copied over
* <li>Information in the <head> is lost
* </ul>
*
* @param html the input HTML
* @return the HTML converted, as best as possible, to text
*/
function convert_html_to_text($html, $width = 74)
{
$html = fix_newlines($html);
$doc = new DOMDocument('1.0', 'utf-8');
if (strpos($html, '<?xml ') === false) {
$html = '<?xml encoding="utf-8"?>' . $html;
}
# <?php (4vim)
if (!@$doc->loadHTML($html)) {
return $html;
}
// Thanks, http://us3.php.net/manual/en/domdocument.loadhtml.php#95251
// dirty fix -- remove the inserted processing instruction
foreach ($doc->childNodes as $item) {
if ($item->nodeType == XML_PI_NODE) {
$doc->removeChild($item);
// remove hack
break;
}
}
$elements = identify_node($doc);
// Add the default stylesheet
$elements->getRoot()->addStylesheet(HtmlStylesheet::fromArray(array('html' => array('white-space' => 'pre'), 'p' => array('margin-bottom' => '1em'), 'pre' => array('white-space' => 'pre'))));
$options = array();
if (is_object($elements)) {
$output = $elements->render($width, $options);
} else {
$output = $elements;
}
return trim($output);
}
/**
* Tries to convert the given HTML into a plain text format - best suited for
* e-mail display, etc.
*
* <p>In particular, it tries to maintain the following features:
* <ul>
* <li>Links are maintained, with the 'href' copied over
* <li>Information in the <head> is lost
* </ul>
*
* @param string html the input HTML
* @return string the HTML converted, as best as possible, to text
* @throws Html2TextException if the HTML could not be loaded as a {@link DOMDocument}
*/
function convert_html_to_text($html)
{
$html = fix_newlines($html);
$doc = new DOMDocument();
if (!$doc->loadHTML($html)) {
throw new Html2TextException("Could not load HTML - badly formed?", $html);
}
$output = iterate_over_node($doc);
// remove leading and trailing spaces on each line
$output = preg_replace("/[ \t]*\n[ \t]*/im", "\n", $output);
// remove leading and trailing whitespace
$output = trim($output);
return $output;
}
$passed = 0;
$failed = 0;
foreach ($tests as $test) {
echo "[test {$test}]\n";
if (!file_exists(__DIR__ . "/{$test}.html")) {
echo "FAILED: File '{$test}.html' did not exist\n\n";
$failed++;
continue;
}
if (!file_exists(__DIR__ . "/{$test}.txt")) {
echo "FAILED: File '{$test}.txt' did not exist\n\n";
$failed++;
continue;
}
$input = file_get_contents(__DIR__ . "/{$test}.html");
$expected = fix_newlines(file_get_contents(__DIR__ . "/{$test}.txt"));
$output = convert_html_to_text($input);
if ($output != $expected) {
file_put_contents(__DIR__ . "/{$test}.output", $output);
// mark whitespace
/*
$output = str_replace(" ", ".", $output);
$expected = str_replace(" ", ".", $expected);
$output = str_replace("\t", " -> ", $output);
$expected = str_replace("\t", " -> ", $expected);
$output = str_replace("\r", "\\r\r", $output);
$expected = str_replace("\r", "\\r\r", $expected);
$output = str_replace("\n", "\\n\n", $output);
$expected = str_replace("\n", "\\n\n", $expected);
*/
echo "FAILED: Expected:\n[{$expected}]\n\nGot:\n[{$output}]\n\n";
