<?php
-/*
-html2bbcode.php
-Converter for HTML to BBCode
-Made by: ike@piratenpartei.de
-Originally made for the syncom project: http://wiki.piratenpartei.de/Syncom
- https://github.com/annando/Syncom
-*/
+/**
+ * @file include/html2bbcode.php
+ * @brief Converter for HTML to BBCode
+ *
+ * Made by: ike@piratenpartei.de
+ * Originally made for the syncom project: http://wiki.piratenpartei.de/Syncom
+ * https://github.com/annando/Syncom
+ */
+
+use Friendica\Util\XML;
function node2bbcode(&$doc, $oldnode, $attributes, $startbb, $endbb)
{
$list = $xpath->query("//".$oldnode);
foreach ($list as $oldNode) {
-
$attr = array();
- if ($oldNode->attributes->length)
- foreach ($oldNode->attributes as $attribute)
+ if ($oldNode->attributes->length) {
+ foreach ($oldNode->attributes as $attribute) {
$attr[$attribute->name] = $attribute->value;
+ }
+ }
$replace = true;
$i = 0;
foreach ($attributes as $attribute => $value) {
-
$startbb = str_replace('\x01'.++$i, '$1', $startbb);
-
if (strpos('*'.$startbb, '$1') > 0) {
-
- if ($replace and (@$attr[$attribute] != '')) {
-
+ if ($replace && (@$attr[$attribute] != '')) {
$startbb = preg_replace($value, $startbb, $attr[$attribute], -1, $count);
// If nothing could be changed
- if ($count == 0)
+ if ($count == 0) {
$replace = false;
- } else
+ }
+ } else {
$replace = false;
+ }
} else {
- if (@$attr[$attribute] != $value)
+ if (@$attr[$attribute] != $value) {
$replace = false;
+ }
}
}
return($replace);
}
-if(!function_exists('deletenode')) {
-function deletenode(&$doc, $node)
-{
- $xpath = new DomXPath($doc);
- $list = $xpath->query("//".$node);
- foreach ($list as $child)
- $child->parentNode->removeChild($child);
-}}
-
-function _replace_code_cb($m){
- return "<code>".str_replace("\n","<br>\n",$m[1]). "</code>";
-}
-
-function html2bbcode($message)
+function html2bbcode($message, $basepath = '')
{
$message = str_replace("\r", "", $message);
- $message = preg_replace_callback("|<pre><code>([^<]*)</code></pre>|ism", "_replace_code_cb", $message);
+ // Removing code blocks before the whitespace removal processing below
+ $codeblocks = [];
+ $message = preg_replace_callback(
+ '#<pre><code(?: class="([^"]*)")?>(.*)</code></pre>#iUs',
+ function ($matches) use (&$codeblocks) {
+ $return = '[codeblock-' . count($codeblocks) . ']';
- $message = str_replace(array(
- "<li><p>",
- "</p></li>",
- ),
- array(
- "<li>",
- "</li>",
- ),
- $message);
+ $prefix = '[code]';
+ if ($matches[1] != '') {
+ $prefix = '[code=' . $matches[1] . ']';
+ }
+ $codeblocks[] = $prefix . trim($matches[2]) . '[/code]';
+ return $return;
+ },
+ $message
+ );
+
+ $message = str_replace(
+ array(
+ "<li><p>",
+ "</p></li>",
+ ),
+ array(
+ "<li>",
+ "</li>",
+ ),
+ $message
+ );
// remove namespaces
$message = preg_replace('=<(\w+):(.+?)>=', '<removeme>', $message);
@$doc->loadHTML($message);
- deletenode($doc, 'style');
- deletenode($doc, 'head');
- deletenode($doc, 'title');
- deletenode($doc, 'meta');
- deletenode($doc, 'xml');
- deletenode($doc, 'removeme');
+ XML::deleteNode($doc, 'style');
+ XML::deleteNode($doc, 'head');
+ XML::deleteNode($doc, 'title');
+ XML::deleteNode($doc, 'meta');
+ XML::deleteNode($doc, 'xml');
+ XML::deleteNode($doc, 'removeme');
$xpath = new DomXPath($doc);
$list = $xpath->query("//pre");
- foreach ($list as $node)
+ foreach ($list as $node) {
$node->nodeValue = str_replace("\n", "\r", $node->nodeValue);
+ }
$message = $doc->saveHTML();
$message = str_replace(array("\n<", ">\n", "\r", "\n", "\xC3\x82\xC2\xA0"), array("<", ">", "<br />", " ", ""), $message);
node2bbcode($doc, 'font', array('face'=>'/([\w ]+)/'), '[font=$1]', '[/font]');
node2bbcode($doc, 'font', array('size'=>'/(\d+)/'), '[size=$1]', '[/size]');
node2bbcode($doc, 'font', array('color'=>'/(.+)/'), '[color=$1]', '[/color]');
-*/
+ */
// Untested
//node2bbcode($doc, 'span', array('style'=>'/.*font-size:\s*(.+?)[,;].*font-family:\s*(.+?)[,;].*color:\s*(.+?)[,;].*/'), '[size=$1][font=$2][color=$3]', '[/color][/font][/size]');
//node2bbcode($doc, 'span', array('style'=>'/.*font-size:\s*(\d+)[,;].*/'), '[size=$1]', '[/size]');
node2bbcode($doc, 'audio', array('src'=>'/(.+)/'), '[audio]$1', '[/audio]');
node2bbcode($doc, 'iframe', array('src'=>'/(.+)/'), '[iframe]$1', '[/iframe]');
+ node2bbcode($doc, 'key', array(), '[code]', '[/code]');
node2bbcode($doc, 'code', array(), '[code]', '[/code]');
- node2bbcode($doc, 'key', array(), '[code]', '[/code]');
$message = $doc->saveHTML();
do {
$oldmessage = $message;
- $message = str_replace(array(
- "[/size]\n\n",
- "\n[hr]",
- "[hr]\n",
- "\n[list",
- "[/list]\n",
- "\n[/",
- "[list]\n",
- "[list=1]\n",
- "\n[*]"),
- array(
- "[/size]\n",
- "[hr]",
- "[hr]",
- "[list",
- "[/list]",
- "[/",
- "[list]",
- "[list=1]",
- "[*]"),
- $message);
+ $message = str_replace(
+ array(
+ "[/size]\n\n",
+ "\n[hr]",
+ "[hr]\n",
+ "\n[list",
+ "[/list]\n",
+ "\n[/",
+ "[list]\n",
+ "[list=1]\n",
+ "\n[*]"),
+ array(
+ "[/size]\n",
+ "[hr]",
+ "[hr]",
+ "[list",
+ "[/list]",
+ "[/",
+ "[list]",
+ "[list=1]",
+ "[*]"),
+ $message
+ );
} while ($message != $oldmessage);
- $message = str_replace(array('[b][b]', '[/b][/b]', '[i][i]', '[/i][/i]'),
- array('[b]', '[/b]', '[i]', '[/i]'), $message);
+ $message = str_replace(
+ array('[b][b]', '[/b][/b]', '[i][i]', '[/i][/i]'),
+ array('[b]', '[/b]', '[i]', '[/i]'),
+ $message
+ );
// Handling Yahoo style of mails
$message = str_replace('[hr][b]From:[/b]', '[quote][b]From:[/b]', $message);
- return(trim($message));
+ // Restore code blocks
+ $message = preg_replace_callback(
+ '#\[codeblock-([0-9]+)\]#iU',
+ function ($matches) use ($codeblocks) {
+ $return = '';
+ if (isset($codeblocks[intval($matches[1])])) {
+ $return = $codeblocks[$matches[1]];
+ }
+ return $return;
+ },
+ $message
+ );
+
+ $message = trim($message);
+
+ if ($basepath != '') {
+ $message = addHostname($message, $basepath);
+ }
+
+ return $message;
+}
+
+/**
+ * @brief Sub function to complete incomplete URL
+ *
+ * @param array $matches Result of preg_replace_callback
+ * @param string $basepath Basepath that is used to complete the URL
+ *
+ * @return string The expanded URL
+ */
+function addHostnameSub($matches, $basepath)
+{
+ $base = parse_url($basepath);
+ unset($base['query']);
+ unset($base['fragment']);
+
+ $link = $matches[0];
+ $url = $matches[1];
+
+ $parts = array_merge($base, parse_url($url));
+ $url2 = unParseUrl($parts);
+
+ return str_replace($url, $url2, $link);
+}
+
+/**
+ * @brief Complete incomplete URLs in BBCode
+ *
+ * @param string $body Body with URLs
+ * @param string $basepath Basepath that is used to complete the URL
+ *
+ * @return string Body with expanded URLs
+ */
+function addHostname($body, $basepath)
+{
+ $URLSearchString = "^\[\]";
+
+ $matches = array("/\[url\=([$URLSearchString]*)\].*?\[\/url\]/ism",
+ "/\[url\]([$URLSearchString]*)\[\/url\]/ism",
+ "/\[img\=[0-9]*x[0-9]*\](.*?)\[\/img\]/ism",
+ "/\[img\](.*?)\[\/img\]/ism",
+ "/\[zmg\=[0-9]*x[0-9]*\](.*?)\[\/img\]/ism",
+ "/\[zmg\](.*?)\[\/zmg\]/ism",
+ "/\[video\](.*?)\[\/video\]/ism",
+ "/\[audio\](.*?)\[\/audio\]/ism",
+ );
+
+ foreach ($matches as $match) {
+ $body = preg_replace_callback(
+ $match,
+ function ($match) use ($basepath) {
+ return addHostnameSub($match, $basepath);
+ },
+ $body
+ );
+ }
+ return $body;
}
-?>