From: Michael Vogel <icarus@dabo.de>
Date: Fri, 13 Jul 2012 21:39:51 +0000 (+0200)
Subject: Merge remote branch 'upstream/master'
X-Git-Url: https://git.mxchange.org/?a=commitdiff_plain;h=bfca7f47ef1f986ea8515d23c3c1962c7fe3a298;p=friendica.git

Merge remote branch 'upstream/master'

Conflicts:
	include/bb2diaspora.php
---

bfca7f47ef1f986ea8515d23c3c1962c7fe3a298
diff --cc include/bb2diaspora.php
index 4a82635e57,b5feacea8b..436412dbd4
--- a/include/bb2diaspora.php
+++ b/include/bb2diaspora.php
@@@ -104,45 -192,62 +192,29 @@@ function diaspora_ol($s) 
  
  function bb2diaspora($Text,$preserve_nl = false) {
  
 -//////////////////////
 -// An attempt was made to convert bbcode to html and then to markdown
 -// consisting of the following lines.
 -// I'm undoing this as we have a lot of bbcode constructs which
 -// were simply getting lost, for instance bookmark, vimeo, video, youtube, events, etc.
 -// We can try this again, but need a very good test sequence to verify
 -// all the major bbcode constructs that we use are getting through.
 -//////////////////////
 -/*
--	// bbcode() will convert "[*]" into "<li>" with no closing "</li>"
--	// Markdownify() is unable to handle these, as it makes each new
--	// "<li>" into a deeper nested element until it crashes. So pre-format
--	// the lists as Diaspora lists before sending the $Text to bbcode()
--	//
--	// Note that to get nested lists to work for Diaspora, we would need
--	// to define the closing tag for the list elements. So nested lists
--	// are going to be flattened out in Diaspora for now
- /*	$endlessloop = 0;
 -
 -	$endlessloop = 0;
--	while ((((strpos($Text, "[/list]") !== false) && (strpos($Text, "[list") !== false)) ||
--	       ((strpos($Text, "[/ol]") !== false) && (strpos($Text, "[ol]") !== false)) || 
--	       ((strpos($Text, "[/ul]") !== false) && (strpos($Text, "[ul]") !== false))) && (++$endlessloop < 20)) {
--		$Text = preg_replace_callback("/\[list\](.*?)\[\/list\]/is", 'diaspora_ul', $Text);
--		$Text = preg_replace_callback("/\[list=1\](.*?)\[\/list\]/is", 'diaspora_ol', $Text);
--		$Text = preg_replace_callback("/\[list=i\](.*?)\[\/list\]/s",'diaspora_ol', $Text);
--		$Text = preg_replace_callback("/\[list=I\](.*?)\[\/list\]/s", 'diaspora_ol', $Text);
--		$Text = preg_replace_callback("/\[list=a\](.*?)\[\/list\]/s", 'diaspora_ol', $Text);
--		$Text = preg_replace_callback("/\[list=A\](.*?)\[\/list\]/s", 'diaspora_ol', $Text);
--		$Text = preg_replace_callback("/\[ul\](.*?)\[\/ul\]/is", 'diaspora_ul', $Text);
--		$Text = preg_replace_callback("/\[ol\](.*?)\[\/ol\]/is", 'diaspora_ol', $Text);
--	}
 -
--*/
++	// Re-enabling the converter again.
++	// The bbcode parser now handles youtube-links (and the other stuff) correctly.
++	// Additionally the html code is now fixed so that lists are now working.
+ 
  	// Convert it to HTML - don't try oembed
 -//	$Text = bbcode($Text, $preserve_nl, false);
 +	$Text = bbcode($Text, $preserve_nl, false);
  
  	// Now convert HTML to Markdown
 -//	$md = new Markdownify(false, false, false);
 -//	$Text = $md->parseString($Text);
 +	$md = new Markdownify(false, false, false);
 +	$Text = $md->parseString($Text);
  
  	// If the text going into bbcode() has a plain URL in it, i.e.
  	// with no [url] tags around it, it will come out of parseString()
  	// looking like: <http://url.com>, which gets removed by strip_tags().
  	// So take off the angle brackets of any such URL
 -//	$Text = preg_replace("/<http(.*?)>/is", "http$1", $Text);
 +	$Text = preg_replace("/<http(.*?)>/is", "http$1", $Text);
  
  	// Remove all unconverted tags
 -//	$Text = strip_tags($Text);
 -
 -////// 
 -// end of bb->html->md conversion attempt
 -//////
 +	$Text = strip_tags($Text);
  
- /*
+ 
++/* Old routine
+ 
  	$ev = bbtoevent($Text);
  
  	// Replace any html brackets with HTML Entities to prevent executing HTML or script
@@@ -309,7 -421,7 +388,8 @@@
  	$Text = preg_replace("/\<(.*?)(src|href)=(.*?)\&amp\;(.*?)\>/ism",'<$1$2=$3&$4>',$Text);
  
  	$Text = preg_replace_callback('/\[(.*?)\]\((.*?)\)/ism','unescape_underscores_in_links',$Text);
+ 
 +*/
  
  	// Remove any leading or trailing whitespace, as this will mess up
  	// the Diaspora signature verification and cause the item to disappear
diff --cc include/bbcode.php
index e212ec4aed,63dd9695e7..4aac33f112
--- a/include/bbcode.php
+++ b/include/bbcode.php
@@@ -335,28 -386,10 +397,29 @@@ function bbcode($Text,$preserve_nl = fa
  
  	// fix any escaped ampersands that may have been converted into links
  	$Text = preg_replace("/\<(.*?)(src|href)=(.*?)\&amp\;(.*?)\>/ism",'<$1$2=$3&$4>',$Text);
- 	if(strlen($saved_image))
- 		$Text = str_replace('[$#saved_image#$]','<img src="' . $saved_image .'" alt="' . t('Image/photo') . '" />',$Text);
+ 
+ 	if($saved_image)
+ 		$Text = bb_replace_images($Text, $saved_image);
  
 +	// Clean up the HTML by loading and saving the HTML with the DOM
 +	// Only do it when it has to be done - for performance reasons
 +	if (!$tryoembed) {
 +		$doc = new DOMDocument();
 +		$doc->preserveWhiteSpace = false;
 +
 +		$Text = mb_convert_encoding($Text, 'HTML-ENTITIES', "UTF-8");
 +
 +		$doctype = '<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" "http://www.w3.org/TR/REC-html40/loose.dtd">';
 +		@$doc->loadHTML($doctype."<html><body>".$Text."</body></html>");
 +
 +		$Text = $doc->saveHTML();
 +		$Text = str_replace(array("<html><body>", "</body></html>", $doctype), array("", "", ""), $Text);
 +
 +		$Text = str_replace('<br></li>','</li>', $Text);
 +
 +		$Text = mb_convert_encoding($Text, "UTF-8", 'HTML-ENTITIES');
 +	}
 +
  	call_hooks('bbcode',$Text);
  
  	return $Text;
diff --cc include/items.php
index d888f314de,6d58bd182a..b81208f366
--- a/include/items.php
+++ b/include/items.php
@@@ -278,31 -280,100 +280,123 @@@ function construct_activity_target($ite
  	}
  
  	return '';
- } 
+ }
+ 
+ /* limit_body_size()
+  *
+  *		The purpose of this function is to apply system message length limits to
+  *		imported messages without including any embedded photos in the length
+  */
+ if(! function_exists('limit_body_size')) {
+ function limit_body_size($body) {
+ 
+ 	logger('limit_body_size: start', LOGGER_DEBUG);
+ 
+ 	$maxlen = get_max_import_size();
+ 
+ 	// If the length of the body, including the embedded images, is smaller
+ 	// than the maximum, then don't waste time looking for the images
+ 	if($maxlen && (strlen($body) > $maxlen)) {
+ 
+ 		logger('limit_body_size: the total body length exceeds the limit', LOGGER_DEBUG);
+ 
+ 		$orig_body = $body;
+ 		$new_body = '';
+ 		$textlen = 0;
+ 		$max_found = false;
+ 
+ 		$img_start = strpos($orig_body, '[img');
+ 		$img_st_close = ($img_start !== false ? strpos(substr($orig_body, $img_start), ']') : false);
+ 		$img_end = ($img_start !== false ? strpos(substr($orig_body, $img_start), '[/img]') : false);
+ 		while(($img_st_close !== false) && ($img_end !== false)) {
+ 
+ 			$img_st_close++; // make it point to AFTER the closing bracket
+ 			$img_end += $img_start;
+ 			$img_end += strlen('[/img]');
+ 
+ 			if(! strcmp(substr($orig_body, $img_start + $img_st_close, 5), 'data:')) {
+ 				// This is an embedded image
+ 
+ 				if( ($textlen + $img_start) > $maxlen ) {
+ 					if($textlen < $maxlen) {
+ 						logger('limit_body_size: the limit happens before an embedded image', LOGGER_DEBUG);
+ 						$new_body = $new_body . substr($orig_body, 0, $maxlen - $textlen);
+ 						$textlen = $maxlen;
+ 					}
+ 				}
+ 				else {
+ 					$new_body = $new_body . substr($orig_body, 0, $img_start);
+ 					$textlen += $img_start;
+ 				}
+ 
+ 				$new_body = $new_body . substr($orig_body, $img_start, $img_end - $img_start);
+ 			}
+ 			else {
+ 
+ 				if( ($textlen + $img_end) > $maxlen ) {
+ 					if($textlen < $maxlen) {
+ 						logger('limit_body_size: the limit happens before the end of a non-embedded image', LOGGER_DEBUG);
+ 						$new_body = $new_body . substr($orig_body, 0, $maxlen - $textlen);
+ 						$textlen = $maxlen;
+ 					}
+ 				}
+ 				else {
+ 					$new_body = $new_body . substr($orig_body, 0, $img_end);
+ 					$textlen += $img_end;
+ 				}
+ 			}
+ 			$orig_body = substr($orig_body, $img_end);
+ 
+ 			if($orig_body === false) // in case the body ends on a closing image tag
+ 				$orig_body = '';
+ 
+ 			$img_start = strpos($orig_body, '[img');
+ 			$img_st_close = ($img_start !== false ? strpos(substr($orig_body, $img_start), ']') : false);
+ 			$img_end = ($img_start !== false ? strpos(substr($orig_body, $img_start), '[/img]') : false);
+ 		}
+ 
+ 		if( ($textlen + strlen($orig_body)) > $maxlen) {
+ 			if($textlen < $maxlen) {
+ 				logger('limit_body_size: the limit happens after the end of the last image', LOGGER_DEBUG);
+ 				$new_body = $new_body . substr($orig_body, 0, $maxlen - $textlen);
+ 				$textlen = $maxlen;
+ 			}
+ 		}
+ 		else {
+ 			logger('limit_body_size: the text size with embedded images extracted did not violate the limit', LOGGER_DEBUG);
+ 			$new_body = $new_body . $orig_body;
+ 			$textlen += strlen($orig_body);
+ 		}
+ 
+ 		return $new_body;
+ 	}
+ 	else
+ 		return $body;
+ }}
  
 +function title_is_body($title, $body) {
 +
 +	$title = strip_tags($title);
 +	$title = trim($title);
 +	$title = str_replace(array("\n", "\r", "\t", " "), array("","","",""), $title);
 +
 +	$body = strip_tags($body);
 +	$body = trim($body);
 +	$body = str_replace(array("\n", "\r", "\t", " "), array("","","",""), $body);
 +
 +	if (strlen($title) < strlen($body))
 +		$body = substr($body, 0, strlen($title));
 +
 +	if (($title != $body) and (substr($title, -3) == "...")) {
 +		$pos = strrpos($title, "...");
 +		if ($pos > 0) {
 +			$title = substr($title, 0, $pos);
 +			$body = substr($body, 0, $pos);
 +		}
 +	}
 +
 +	return($title == $body);
 +}