function drupal_html_to_text
Transforms an HTML string into plain text, preserving its structure.
The output will be suitable for use as 'format=flowed; delsp=yes' text (RFC 3676) and can be passed directly to drupal_mail() for sending.
We deliberately use LF rather than CRLF, see drupal_mail().
This function provides suitable alternatives for the following tags: <a> <em> <i> <strong> <b> <br> <p> <blockquote> <ul> <ol> <li> <dl> <dt> <dd> <h1> <h2> <h3> <h4> <h5> <h6> <hr>
Parameters
$string: The string to be transformed.
$allowed_tags (optional): If supplied, a list of tags that will be transformed. If omitted, all all supported tags are transformed.
Return value
The transformed string.
7 calls to drupal_html_to_text()
- ContactSitewideTestCase::testAutoReply in modules/
contact/ contact.test - Tests auto-reply on the site-wide contact form.
- DefaultMailSystem::format in modules/
system/ system.mail.inc - Concatenate and wrap the e-mail body for plain-text mails.
- DrupalHtmlToTextTestCase::assertHtmlToText in modules/
simpletest/ tests/ mail.test - Helper function for testing drupal_html_to_text().
- DrupalHtmlToTextTestCase::testDrupalHtmlToTextBlockTagToNewline in modules/
simpletest/ tests/ mail.test - Test that text separated by block-level tags in HTML get separated by (at least) a newline in the plaintext version.
- DrupalHtmlToTextTestCase::testVeryLongLineWrap in modules/
simpletest/ tests/ mail.test - Tests that drupal_html_to_text() wraps before 1000 characters.
File
-
includes/
mail.inc, line 413
Code
function drupal_html_to_text($string, $allowed_tags = NULL) {
// Cache list of supported tags.
static $supported_tags;
if (empty($supported_tags)) {
$supported_tags = array(
'a',
'em',
'i',
'strong',
'b',
'br',
'p',
'blockquote',
'ul',
'ol',
'li',
'dl',
'dt',
'dd',
'h1',
'h2',
'h3',
'h4',
'h5',
'h6',
'hr',
);
}
// Make sure only supported tags are kept.
$allowed_tags = isset($allowed_tags) ? array_intersect($supported_tags, $allowed_tags) : $supported_tags;
// Make sure tags, entities and attributes are well-formed and properly nested.
$string = _filter_htmlcorrector(filter_xss($string, $allowed_tags));
// Apply inline styles.
$string = preg_replace('!</?(em|i)((?> +)[^>]*)?>!i', '/', $string);
$string = preg_replace('!</?(strong|b)((?> +)[^>]*)?>!i', '*', $string);
// Replace inline <a> tags with the text of link and a footnote.
// 'See <a href="http://drupal.org">the Drupal site</a>' becomes
// 'See the Drupal site [1]' with the URL included as a footnote.
_drupal_html_to_mail_urls(NULL, TRUE);
$pattern = '@(<a[^>]+?href="([^"]*)"[^>]*?>(.+?)</a>)@i';
$string = preg_replace_callback($pattern, '_drupal_html_to_mail_urls', $string);
$urls = _drupal_html_to_mail_urls();
$footnotes = '';
if (count($urls)) {
$footnotes .= "\n";
for ($i = 0, $max = count($urls); $i < $max; $i++) {
$footnotes .= '[' . ($i + 1) . '] ' . $urls[$i] . "\n";
}
}
// Split tags from text.
$split = preg_split('/<([^>]+?)>/', $string, -1, PREG_SPLIT_DELIM_CAPTURE);
// Note: PHP ensures the array consists of alternating delimiters and literals
// and begins and ends with a literal (inserting $null as required).
$tag = FALSE;
// Odd/even counter (tag or no tag)
$casing = NULL;
// Case conversion function
$output = '';
$indent = array();
// All current indentation string chunks
$lists = array();
// Array of counters for opened lists
foreach ($split as $value) {
$chunk = NULL;
// Holds a string ready to be formatted and output.
// Process HTML tags (but don't output any literally).
if ($tag) {
list($tagname) = explode(' ', strtolower($value), 2);
switch ($tagname) {
// List counters
case 'ul':
array_unshift($lists, '*');
break;
case 'ol':
array_unshift($lists, 1);
break;
case '/ul':
case '/ol':
array_shift($lists);
$chunk = '';
// Ensure blank new-line.
break;
// Quotation/list markers, non-fancy headers
case 'blockquote':
// Format=flowed indentation cannot be mixed with lists.
$indent[] = count($lists) ? ' "' : '>';
break;
case 'li':
$indent[] = isset($lists[0]) && is_numeric($lists[0]) ? ' ' . $lists[0]++ . ') ' : ' * ';
break;
case 'dd':
$indent[] = ' ';
break;
case 'h3':
$indent[] = '.... ';
break;
case 'h4':
$indent[] = '.. ';
break;
case '/blockquote':
if (count($lists)) {
// Append closing quote for inline quotes (immediately).
$output = rtrim($output, "> \n") . "\"\n";
$chunk = '';
// Ensure blank new-line.
}
// Fall-through
case '/li':
case '/dd':
array_pop($indent);
break;
case '/h3':
case '/h4':
array_pop($indent);
case '/h5':
case '/h6':
$chunk = '';
// Ensure blank new-line.
break;
// Fancy headers
case 'h1':
$indent[] = '======== ';
$casing = 'drupal_strtoupper';
break;
case 'h2':
$indent[] = '-------- ';
$casing = 'drupal_strtoupper';
break;
case '/h1':
case '/h2':
$casing = NULL;
// Pad the line with dashes.
$output = _drupal_html_to_text_pad($output, $tagname == '/h1' ? '=' : '-', ' ');
array_pop($indent);
$chunk = '';
// Ensure blank new-line.
break;
// Horizontal rulers
case 'hr':
// Insert immediately.
$output .= drupal_wrap_mail('', implode('', $indent)) . "\n";
$output = _drupal_html_to_text_pad($output, '-');
break;
// Paragraphs and definition lists
case '/p':
case '/dl':
$chunk = '';
// Ensure blank new-line.
break;
}
}
else {
// Convert inline HTML text to plain text; not removing line-breaks or
// white-space, since that breaks newlines when sanitizing plain-text.
$value = trim(decode_entities($value));
if (drupal_strlen($value)) {
$chunk = $value;
}
}
// See if there is something waiting to be output.
if (isset($chunk)) {
// Apply any necessary case conversion.
if (isset($casing)) {
$chunk = $casing($chunk);
}
// Format it and apply the current indentation.
$output .= drupal_wrap_mail($chunk, implode('', $indent)) . MAIL_LINE_ENDINGS;
// Remove non-quotation markers from indentation.
$indent = array_map('_drupal_html_to_text_clean', $indent);
}
$tag = !$tag;
}
return $output . $footnotes;
}
Buggy or inaccurate documentation? Please file an issue. Need support? Need help programming? Connect with the Drupal community.