From 3bf72994688ad9292bf37444d80ab5ab1a002748 Mon Sep 17 00:00:00 2001
From: Paweł Sroka <srokap@gmail.com>
Date: Sun, 4 Nov 2012 08:25:28 +0100
Subject: Fixes #1479 - Replaces WP autop with implementation from Steve Clay.

---
 engine/lib/output.php | 83 ++++++++++++++++++++++++++-------------------------
 1 file changed, 43 insertions(+), 40 deletions(-)

(limited to 'engine/lib/output.php')

diff --git a/engine/lib/output.php b/engine/lib/output.php
index 0069360f0..d50576b44 100644
--- a/engine/lib/output.php
+++ b/engine/lib/output.php
@@ -43,51 +43,25 @@ function parse_urls($text) {
 
 /**
  * Create paragraphs from text with line spacing
- * Borrowed from Wordpress.
  *
  * @param string $pee The string
- * @param bool   $br  Add BRs?
+ * @deprecated Use elgg_autop instead
  *
- * @todo Rewrite
  * @return string
  **/
-function autop($pee, $br = 1) {
-	$pee = $pee . "\n"; // just to make things a little easier, pad the end
-	$pee = preg_replace('|<br />\s*<br />|', "\n\n", $pee);
-	// Space things out a little
-	$allblocks = '(?:table|thead|tfoot|caption|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|form|map|area|blockquote|address|math|style|input|p|h[1-6]|hr)';
-	$pee = preg_replace('!(<' . $allblocks . '[^>]*>)!', "\n$1", $pee);
-	$pee = preg_replace('!(</' . $allblocks . '>)!', "$1\n\n", $pee);
-	$pee = str_replace(array("\r\n", "\r"), "\n", $pee); // cross-platform newlines
-	if (strpos($pee, '<object') !== false) {
-		$pee = preg_replace('|\s*<param([^>]*)>\s*|', "<param$1>", $pee); // no pee inside object/embed
-		$pee = preg_replace('|\s*</embed>\s*|', '</embed>', $pee);
-	}
-	$pee = preg_replace("/\n\n+/", "\n\n", $pee); // take care of duplicates
-	$pee = preg_replace('/\n?(.+?)(?:\n\s*\n|\z)/s', "<p>$1</p>\n", $pee); // make paragraphs, including one at the end
-	$pee = preg_replace('|<p>\s*?</p>|', '', $pee); // under certain strange conditions it could create a P of entirely whitespace
-	$pee = preg_replace('!<p>([^<]+)\s*?(</(?:div|address|form)[^>]*>)!', "<p>$1</p>$2", $pee);
-	$pee = preg_replace('|<p>|', "$1<p>", $pee);
-	$pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee); // don't pee all over a tag
-	$pee = preg_replace("|<p>(<li.+?)</p>|", "$1", $pee); // problem with nested lists
-	$pee = preg_replace('|<p><blockquote([^>]*)>|i', "<blockquote$1><p>", $pee);
-	$pee = str_replace('</blockquote></p>', '</p></blockquote>', $pee);
-	$pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)!', "$1", $pee);
-	$pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee);
-	if ($br) {
-		$pee = preg_replace_callback('/<(script|style).*?<\/\\1>/s', create_function('$matches', 'return str_replace("\n", "<WPPreserveNewline />", $matches[0]);'), $pee);
-		$pee = preg_replace('|(?<!<br />)\s*\n|', "<br />\n", $pee); // optionally make line breaks
-		$pee = str_replace('<WPPreserveNewline />', "\n", $pee);
-	}
-	$pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*<br />!', "$1", $pee);
-	$pee = preg_replace('!<br />(\s*</?(?:p|li|div|dl|dd|dt|th|pre|td|ul|ol)[^>]*>)!', '$1', $pee);
-	//if (strpos($pee, '<pre') !== false) {
-	//	mind the space between the ? and >.  Only there because of the comment.
-	//	$pee = preg_replace_callback('!(<pre.*? >)(.*?)</pre>!is', 'clean_pre', $pee );
-	//}
-	$pee = preg_replace("|\n</p>$|", '</p>', $pee);
-
-	return $pee;
+function autop($pee) {
+	return elgg_autop($pee);
+}
+
+/**
+ * Create paragraphs from text with line spacing
+ *
+ * @param string $pee The string
+ *
+ * @return string
+ **/
+function elgg_autop($pee) {
+	return ElggAutop::getInstance()->process($pee);
 }
 
 /**
@@ -398,3 +372,32 @@ function elgg_strip_tags($string) {
 
 	return $string;
 }
+
+/**
+ * Unit tests for Output
+ *
+ * @param sting  $hook   unit_test
+ * @param string $type   system
+ * @param mixed  $value  Array of tests
+ * @param mixed  $params Params
+ *
+ * @return array
+ * @access private
+ */
+function output_unit_test($hook, $type, $value, $params) {
+	global $CONFIG;
+	$value[] = $CONFIG->path . 'engine/tests/api/output.php';
+	return $value;
+}
+
+/**
+ * Initialise the Output subsystem.
+ *
+ * @return void
+ * @access private
+ */
+function output_init() {
+	elgg_register_plugin_hook_handler('unit_test', 'system', 'output_unit_test');
+}
+
+elgg_register_event_handler('init', 'system', 'output_init');
-- 
cgit v1.2.3


From 43a395ae735777bfb5474c4f6a37dc1cd0818a37 Mon Sep 17 00:00:00 2001
From: Brett Profitt <brett.profitt@gmail.com>
Date: Mon, 10 Dec 2012 15:50:25 -0500
Subject: Fixes #1479. Added ElggAutoP. Removing [\n\r] from test strings
 before compare to deal with differing whitespace between tags among PHP
 versions.

---
 engine/classes/ElggAutoP.php | 309 ++++++++++++++++++++++++++++++++++++++++++
 engine/classes/ElggAutop.php | 315 -------------------------------------------
 engine/lib/output.php        |  11 +-
 engine/tests/api/output.php  | 138 ++++++++++---------
 4 files changed, 389 insertions(+), 384 deletions(-)
 create mode 100644 engine/classes/ElggAutoP.php
 delete mode 100644 engine/classes/ElggAutop.php

(limited to 'engine/lib/output.php')

diff --git a/engine/classes/ElggAutoP.php b/engine/classes/ElggAutoP.php
new file mode 100644
index 000000000..89d77e583
--- /dev/null
+++ b/engine/classes/ElggAutoP.php
@@ -0,0 +1,309 @@
+<?php
+
+/**
+ * Create wrapper P and BR elements in HTML depending on newlines. Useful when
+ * users use newlines to signal line and paragraph breaks. In all cases output
+ * should be well-formed markup.
+ *
+ * In DIV elements, Ps are only added when there would be at
+ * least two of them.
+ */
+class ElggAutoP {
+
+	public $encoding = 'UTF-8';
+
+	/**
+	 * @var DOMDocument
+	 */
+	protected $_doc = null;
+
+	/**
+	 * @var DOMXPath
+	 */
+	protected $_xpath = null;
+
+	protected $_blocks = 'address article area aside blockquote caption col colgroup dd 
+		details div dl dt fieldset figure figcaption footer form h1 h2 h3 h4 h5 h6 header 
+		hr hgroup legend map math menu nav noscript p pre section select style summary
+		table tbody td tfoot th thead tr ul ol option li';
+
+	/**
+	 * @var array
+	 */
+	protected $_inlines = 'a abbr audio b button canvas caption cite code command datalist
+		del dfn em embed i iframe img input ins kbd keygen label map mark meter object
+		output progress q rp rt ruby s samp script select small source span strong style
+		sub sup textarea time var video wbr';
+
+	/**
+	 * Descend into these elements to add Ps
+	 *
+	 * @var array
+	 */
+	protected $_descendList = 'article aside blockquote body details div footer form
+		header section';
+
+	/**
+	 * Add Ps inside these elements
+	 *
+	 * @var array
+	 */
+	protected $_alterList = 'article aside blockquote body details div footer header
+		section';
+
+	protected $_unique = '';
+
+	public function __construct() {
+		$this->_blocks = preg_split('@\\s+@', $this->_blocks);
+		$this->_descendList = preg_split('@\\s+@', $this->_descendList);
+		$this->_alterList = preg_split('@\\s+@', $this->_alterList);
+		$this->_inlines = preg_split('@\\s+@', $this->_inlines);
+		$this->_unique = md5(__FILE__);
+	}
+
+	/**
+	 * Intance of class for singleton pattern.
+	 * @var ElggAutoP
+	 */
+	private static $instance;
+	
+	/**
+	 * Singleton pattern.
+	 * @return ElggAutoP
+	 */
+	public static function getInstance() {
+		$className = __CLASS__;
+		if (!(self::$instance instanceof $className)) {
+			self::$instance = new $className();
+		}
+		return self::$instance;
+	}
+	
+	/**
+	 * Create wrapper P and BR elements in HTML depending on newlines. Useful when
+	 * users use newlines to signal line and paragraph breaks. In all cases output
+	 * should be well-formed markup.
+	 *
+	 * In DIV, LI, TD, and TH elements, Ps are only added when their would be at
+	 * least two of them.
+	 *
+	 * @param string $html snippet
+	 * @return string|false output or false if parse error occurred
+	 */
+	public function process($html) {
+		// normalize whitespace
+		$html = str_replace(array("\r\n", "\r"), "\n", $html);
+
+		// allows preserving entities untouched
+		$html = str_replace('&', $this->_unique . 'AMP', $html);
+
+		$this->_doc = new DOMDocument();
+	   
+		// parse to DOM, suppressing loadHTML warnings
+		// http://www.php.net/manual/en/domdocument.loadhtml.php#95463
+		libxml_use_internal_errors(true);
+
+		if (!$this->_doc->loadHTML("<html><meta http-equiv='content-type' " 
+				. "content='text/html; charset={$this->encoding}'><body>{$html}</body>"
+				. "</html>")) {
+			return false;
+		}
+
+		$this->_xpath = new DOMXPath($this->_doc);
+		// start processing recursively at the BODY element
+		$nodeList = $this->_xpath->query('//body[1]');
+		$this->_addParagraphs($nodeList->item(0));
+
+		// serialize back to HTML
+		$html = $this->_doc->saveHTML();
+
+		// split AUTOPs into multiples at /\n\n+/
+		$html = preg_replace('/(' . $this->_unique . 'NL){2,}/', '</autop><autop>', $html);
+		$html = str_replace(array($this->_unique . 'BR', $this->_unique . 'NL', '<br>'), 
+				'<br />',
+				$html);
+		$html = str_replace('<br /></autop>', '</autop>', $html);
+
+		// re-parse so we can handle new AUTOP elements
+
+		if (!$this->_doc->loadHTML($html)) {
+			return false;
+		}
+		// must re-create XPath object after DOM load
+		$this->_xpath = new DOMXPath($this->_doc);
+
+		// strip AUTOPs that only have comments/whitespace
+		foreach ($this->_xpath->query('//autop') as $autop) {
+			$hasContent = false;
+			if (trim($autop->textContent) !== '') {
+				$hasContent = true;
+			} else {
+				foreach ($autop->childNodes as $node) {
+					if ($node->nodeType === XML_ELEMENT_NODE) {
+						$hasContent = true;
+						break;
+					}
+				}
+			}
+			if (!$hasContent) {
+				// strip w/ preg_replace later (faster than moving nodes out)
+				$autop->setAttribute("r", "1");
+			}
+		}
+
+		// remove a single AUTOP inside certain elements
+		foreach ($this->_xpath->query('//div') as $el) {
+			$autops = $this->_xpath->query('./autop', $el);
+			if ($autops->length === 1) {
+				// strip w/ preg_replace later (faster than moving nodes out)
+				$autops->item(0)->setAttribute("r", "1");
+			}
+		}
+
+		$html = $this->_doc->saveHTML();
+
+		// trim to the contents of BODY
+		$bodyStart = strpos($html, '<body>');
+		$bodyEnd = strpos($html, '</body>', $bodyStart + 6);
+		$html = substr($html, $bodyStart + 6, $bodyEnd - $bodyStart - 6);
+		
+		// strip AUTOPs that should be removed
+		$html = preg_replace('@<autop r="1">(.*?)</autop>@', '\\1', $html);
+
+		// commit to converting AUTOPs to Ps
+		$html = str_replace('<autop>', "\n<p>", $html);
+		$html = str_replace('</autop>', "</p>\n", $html);
+		
+		$html = str_replace('<br>', '<br />', $html);
+		$html = str_replace($this->_unique . 'AMP', '&', $html);
+		return $html;
+	}
+
+	/**
+	 * Add P and BR elements as necessary
+	 *
+	 * @param DOMElement $el
+	 */
+	protected function _addParagraphs(DOMElement $el) {
+		// no need to recurse, just queue up
+		$elsToProcess = array($el);
+		$inlinesToProcess = array();
+		while ($el = array_shift($elsToProcess)) {
+			// if true, we can alter all child nodes, if not, we'll just call
+			// _addParagraphs on each element in the descendInto list
+			$alterInline = in_array($el->nodeName, $this->_alterList);
+
+			// inside affected elements, we want to trim leading whitespace from
+			// the first text node
+			$ltrimFirstTextNode = true;
+
+			// should we open a new AUTOP element to move inline elements into?
+			$openP = true;
+			$autop = null;
+
+			// after BR, ignore a newline
+			$isFollowingBr = false;
+
+			$node = $el->firstChild;
+			while (null !== $node) {
+				if ($alterInline) {
+					if ($openP) {
+						$openP = false;
+						// create a P to move inline content into (this may be removed later)
+						$autop = $el->insertBefore($this->_doc->createElement('autop'), $node);
+					}
+				}
+
+				$isElement = ($node->nodeType === XML_ELEMENT_NODE);
+				if ($isElement) {
+					$elName = $node->nodeName;
+				}
+				$isBlock = ($isElement && in_array($elName, $this->_blocks));
+
+				if ($alterInline) {
+					$isInline = $isElement && ! $isBlock;
+					$isText = ($node->nodeType === XML_TEXT_NODE);
+					$isLastInline = (! $node->nextSibling
+								   || ($node->nextSibling->nodeType === XML_ELEMENT_NODE
+									   && in_array($node->nextSibling->nodeName, $this->_blocks)));
+					if ($isElement) {
+						$isFollowingBr = ($node->nodeName === 'br');
+					}
+
+					if ($isText) {
+						$nodeText = $node->nodeValue;
+						if ($ltrimFirstTextNode) {
+							$nodeText = ltrim($nodeText);
+							$ltrimFirstTextNode = false;
+						}
+						if ($isFollowingBr && preg_match('@^[ \\t]*\\n[ \\t]*@', $nodeText, $m)) {
+							// if a user ends a line with <br>, don't add a second BR
+							$nodeText = substr($nodeText, strlen($m[0]));
+						}
+						if ($isLastInline) {
+							$nodeText = rtrim($nodeText);
+						}
+						$nodeText = str_replace("\n", $this->_unique . 'NL', $nodeText);
+						$tmpNode = $node;
+						$node = $node->nextSibling; // move loop to next node
+
+						// alter node in place, then move into AUTOP
+						$tmpNode->nodeValue = $nodeText;
+						$autop->appendChild($tmpNode);
+
+						continue;
+					}
+				}
+				if ($isBlock || ! $node->nextSibling) {
+					if ($isBlock) {
+						if (in_array($node->nodeName, $this->_descendList)) {
+							$elsToProcess[] = $node;
+							//$this->_addParagraphs($node);
+						}
+					}
+					$openP = true;
+					$ltrimFirstTextNode = true;
+				}
+				if ($alterInline) {
+					if (! $isBlock) {
+						$tmpNode = $node;
+						if ($isElement && false !== strpos($tmpNode->textContent, "\n")) {
+							$inlinesToProcess[] = $tmpNode;
+						}
+						$node = $node->nextSibling;
+						$autop->appendChild($tmpNode);
+						continue;
+					}
+				}
+
+				$node = $node->nextSibling;
+			}
+		}
+
+		// handle inline nodes
+		// no need to recurse, just queue up
+		while ($el = array_shift($inlinesToProcess)) {
+			$ignoreLeadingNewline = false;
+			foreach ($el->childNodes as $node) {
+				if ($node->nodeType === XML_ELEMENT_NODE) {
+					if ($node->nodeValue === 'BR') {
+						$ignoreLeadingNewline = true;
+					} else {
+						$ignoreLeadingNewline = false;
+						if (false !== strpos($node->textContent, "\n")) {
+							$inlinesToProcess[] = $node;
+						}
+					}
+					continue;
+				} elseif ($node->nodeType === XML_TEXT_NODE) {
+					$text = $node->nodeValue;
+					if ($text[0] === "\n" && $ignoreLeadingNewline) {
+						$text = substr($text, 1);
+						$ignoreLeadingNewline = false;
+					}
+					$node->nodeValue = str_replace("\n", $this->_unique . 'BR', $text);
+				}
+			}
+		}
+	}
+}
diff --git a/engine/classes/ElggAutop.php b/engine/classes/ElggAutop.php
deleted file mode 100644
index fa0c34225..000000000
--- a/engine/classes/ElggAutop.php
+++ /dev/null
@@ -1,315 +0,0 @@
-<?php
-
-/**
- * Create wrapper P and BR elements in HTML depending on newlines. Useful when
- * users use newlines to signal line and paragraph breaks. In all cases output
- * should be well-formed markup.
- *
- * In DIV elements, Ps are only added when there would be at
- * least two of them.
- *
- * @author Steve Clay <steve@mrclay.org>
- * @license http://www.opensource.org/licenses/mit-license.php  MIT License
- */
-class ElggAutop {
-
-	public $encoding = 'UTF-8';
-
-	/**
-	 * @var DOMDocument
-	 */
-	protected $_doc = null;
-
-	/**
-	 * @var DOMXPath
-	 */
-	protected $_xpath = null;
-
-	protected $_blocks = 'address article area aside blockquote caption col colgroup dd 
-		details div dl dt fieldset figure figcaption footer form h1 h2 h3 h4 h5 h6 header 
-		hr hgroup legend map math menu nav noscript p pre section select style summary
-		table tbody td tfoot th thead tr ul ol option li';
-
-	/**
-	 * @var array
-	 */
-	protected $_inlines = 'a abbr audio b button canvas caption cite code command datalist
-		del dfn em embed i iframe img input ins kbd keygen label map mark meter object
-		output progress q rp rt ruby s samp script select small source span strong style
-		sub sup textarea time var video wbr';
-
-	/**
-	 * Descend into these elements to add Ps
-	 *
-	 * @var array
-	 */
-	protected $_descendList = 'article aside blockquote body details div footer form
-		header section';
-
-	/**
-	 * Add Ps inside these elements
-	 *
-	 * @var array
-	 */
-	protected $_alterList = 'article aside blockquote body details div footer header
-		section';
-
-	protected $_unique = '';
-
-	public function __construct()
-	{
-		$this->_blocks = preg_split('@\\s+@', $this->_blocks);
-		$this->_descendList = preg_split('@\\s+@', $this->_descendList);
-		$this->_alterList = preg_split('@\\s+@', $this->_alterList);
-		$this->_inlines = preg_split('@\\s+@', $this->_inlines);
-		$this->_unique = md5(__FILE__);
-	}
-
-	/**
-	 * Intance of class for singleton pattern.
-	 * @var ElggAutop
-	 */
-	private static $instance;
-	
-	/**
-	 * Singleton pattern.
-	 * @return ElggAutop
-	 */
-	public static function getInstance() {
-		$className = __CLASS__;
-		if (!(self::$instance instanceof $className)) {
-			self::$instance = new $className();
-		}
-		return self::$instance;
-	}
-	
-	/**
-	 * Create wrapper P and BR elements in HTML depending on newlines. Useful when
-	 * users use newlines to signal line and paragraph breaks. In all cases output
-	 * should be well-formed markup.
-	 *
-	 * In DIV, LI, TD, and TH elements, Ps are only added when their would be at
-	 * least two of them.
-	 *
-	 * @param string $html snippet
-	 * @return string|false output or false if parse error occurred
-	 */
-	public function process($html)
-	{
-		// normalize whitespace
-		$html = str_replace(array("\r\n", "\r"), "\n", $html);
-
-		// allows preserving entities untouched
-		$html = str_replace('&', $this->_unique . 'AMP', $html);
-
-		$this->_doc = new DOMDocument();
-	   
-		// parse to DOM, suppressing loadHTML warnings
-		// http://www.php.net/manual/en/domdocument.loadhtml.php#95463
-		libxml_use_internal_errors(true);
-		if (! @$this->_doc->loadHTML("<html><meta http-equiv='content-type' " 
-				. "content='text/html; charset={$this->encoding}'><body>{$html}</body>"
-				. "</html>")) {
-			return false;
-		}
-
-		$this->_xpath = new DOMXPath($this->_doc);
-		// start processing recursively at the BODY element
-		$nodeList = $this->_xpath->query('//body[1]');
-		$this->_addParagraphs($nodeList->item(0));
-
-		// serialize back to HTML
-		$html = $this->_doc->saveHTML();
-
-		// split AUTOPs into multiples at /\n\n+/
-		$html = preg_replace('/(' . $this->_unique . 'NL){2,}/', '</autop><autop>', $html);
-		$html = str_replace(array($this->_unique . 'BR', $this->_unique . 'NL', '<br>'), 
-				'<br />',
-				$html);
-		$html = str_replace('<br /></autop>', '</autop>', $html);
-
-		// re-parse so we can handle new AUTOP elements
-
-		if (! @$this->_doc->loadHTML($html)) {
-			return false;
-		}
-		// must re-create XPath object after DOM load
-		$this->_xpath = new DOMXPath($this->_doc);
-
-		// strip AUTOPs that only have comments/whitespace
-		foreach ($this->_xpath->query('//autop') as $autop) {
-			$hasContent = false;
-			if (trim($autop->textContent) !== '') {
-				$hasContent = true;
-			} else {
-				foreach ($autop->childNodes as $node) {
-					if ($node->nodeType === XML_ELEMENT_NODE) {
-						$hasContent = true;
-						break;
-					}
-				}
-			}
-			if (! $hasContent) {
-				// strip w/ preg_replace later (faster than moving nodes out)
-				$autop->setAttribute("r", "1");
-			}
-		}
-
-		// remove a single AUTOP inside certain elements
-		
-		foreach ($this->_xpath->query('//div') as $el) {
-			$autops = $this->_xpath->query('./autop', $el);
-			if ($autops->length === 1) {
-				// strip w/ preg_replace later (faster than moving nodes out)
-				$autops->item(0)->setAttribute("r", "1");
-			}
-		}
-		
-		$html = $this->_doc->saveHTML();
-		
-		// trim to the contents of BODY
-		$bodyStart = strpos($html, '<body>');
-		$bodyEnd = strpos($html, '</body>', $bodyStart + 6);
-		$html = substr($html, $bodyStart + 6, $bodyEnd - $bodyStart - 6);
-		
-		// strip AUTOPs that should be removed
-		$html = preg_replace('@<autop r="1">(.*?)</autop>@', '\\1', $html);
-
-		// commit to converting AUTOPs to Ps
-		$html = str_replace('<autop>', "\n<p>", $html);
-		$html = str_replace('</autop>', "</p>\n", $html);
-		
-		$html = str_replace('<br>', '<br />', $html);
-		$html = str_replace($this->_unique . 'AMP', '&', $html);
-		return $html;
-	}
-
-	/**
-	 * Add P and BR elements as necessary
-	 *
-	 * @param DOMElement $el
-	 */
-	protected function _addParagraphs(DOMElement $el)
-	{
-		// no need to recurse, just queue up
-		$elsToProcess = array($el);
-		$inlinesToProcess = array();
-		while ($el = array_shift($elsToProcess)) {
-			// if true, we can alter all child nodes, if not, we'll just call
-			// _addParagraphs on each element in the descendInto list
-			$alterInline = in_array($el->nodeName, $this->_alterList);
-
-			// inside affected elements, we want to trim leading whitespace from
-			// the first text node
-			$ltrimFirstTextNode = true;
-
-			// should we open a new AUTOP element to move inline elements into?
-			$openP = true;
-			$autop = null;
-
-			// after BR, ignore a newline
-			$isFollowingBr = false;
-
-			$node = $el->firstChild;
-			while (null !== $node) {
-				if ($alterInline) {
-					if ($openP) {
-						$openP = false;
-						// create a P to move inline content into (this may be removed later)
-						$autop = $el->insertBefore($this->_doc->createElement('autop'), $node);
-					}
-				}
-
-				$isElement = ($node->nodeType === XML_ELEMENT_NODE);
-				if ($isElement) {
-					$elName = $node->nodeName;
-				}
-				$isBlock = ($isElement && in_array($elName, $this->_blocks));
-
-				if ($alterInline) {
-					$isInline = $isElement && ! $isBlock;
-					$isText = ($node->nodeType === XML_TEXT_NODE);
-					$isLastInline = (! $node->nextSibling
-								   || ($node->nextSibling->nodeType === XML_ELEMENT_NODE
-									   && in_array($node->nextSibling->nodeName, $this->_blocks)));
-					if ($isElement) {
-						$isFollowingBr = ($node->nodeName === 'br');
-					}
-
-					if ($isText) {
-						$nodeText = $node->nodeValue;
-						if ($ltrimFirstTextNode) {
-							$nodeText = ltrim($nodeText);
-							$ltrimFirstTextNode = false;
-						}
-						if ($isFollowingBr && preg_match('@^[ \\t]*\\n[ \\t]*@', $nodeText, $m)) {
-							// if a user ends a line with <br>, don't add a second BR
-							$nodeText = substr($nodeText, strlen($m[0]));
-						}
-						if ($isLastInline) {
-							$nodeText = rtrim($nodeText);
-						}
-						$nodeText = str_replace("\n", $this->_unique . 'NL', $nodeText);
-						$tmpNode = $node;
-						$node = $node->nextSibling; // move loop to next node
-
-						// alter node in place, then move into AUTOP
-						$tmpNode->nodeValue = $nodeText;
-						$autop->appendChild($tmpNode);
-
-						continue;
-					}
-				}
-				if ($isBlock || ! $node->nextSibling) {
-					if ($isBlock) {
-						if (in_array($node->nodeName, $this->_descendList)) {
-							$elsToProcess[] = $node;
-							//$this->_addParagraphs($node);
-						}
-					}
-					$openP = true;
-					$ltrimFirstTextNode = true;
-				}
-				if ($alterInline) {
-					if (! $isBlock) {
-						$tmpNode = $node;
-						if ($isElement && false !== strpos($tmpNode->textContent, "\n")) {
-							$inlinesToProcess[] = $tmpNode;
-						}
-						$node = $node->nextSibling;
-						$autop->appendChild($tmpNode);
-						continue;
-					}
-				}
-
-				$node = $node->nextSibling;
-			}
-		}
-
-		// handle inline nodes
-		// no need to recurse, just queue up
-		while ($el = array_shift($inlinesToProcess)) {
-			$ignoreLeadingNewline = false;
-			foreach ($el->childNodes as $node) {
-				if ($node->nodeType === XML_ELEMENT_NODE) {
-					if ($node->nodeValue === 'BR') {
-						$ignoreLeadingNewline = true;
-					} else {
-						$ignoreLeadingNewline = false;
-						if (false !== strpos($node->textContent, "\n")) {
-							$inlinesToProcess[] = $node;
-						}
-					}
-					continue;
-				} elseif ($node->nodeType === XML_TEXT_NODE) {
-					$text = $node->nodeValue;
-					if ($text[0] === "\n" && $ignoreLeadingNewline) {
-						$text = substr($text, 1);
-						$ignoreLeadingNewline = false;
-					}
-					$node->nodeValue = str_replace("\n", $this->_unique . 'BR', $text);
-				}
-			}
-		}
-	}
-}
diff --git a/engine/lib/output.php b/engine/lib/output.php
index cce1c7cba..bff0bf6e9 100644
--- a/engine/lib/output.php
+++ b/engine/lib/output.php
@@ -16,7 +16,7 @@
  **/
 function parse_urls($text) {
 	// @todo this causes problems with <attr = "val">
-	// must be ing <attr="val"> format (no space).
+	// must be in <attr="val"> format (no space).
 	// By default htmlawed rewrites tags to this format.
 	// if PHP supported conditional negative lookbehinds we could use this:
 	// $r = preg_replace_callback('/(?<!=)(?<![ ])?(?<!["\'])((ht|f)tps?:\/\/[^\s\r\n\t<>"\'\!\(\),]+)/i',
@@ -46,6 +46,7 @@ function parse_urls($text) {
  *
  * @param string $pee The string
  * @deprecated Use elgg_autop instead
+ * @todo Add deprecation warning in 1.9
  *
  * @return string
  **/
@@ -56,12 +57,12 @@ function autop($pee) {
 /**
  * Create paragraphs from text with line spacing
  *
- * @param string $pee The string
+ * @param string $string The string
  *
  * @return string
  **/
-function elgg_autop($pee) {
-	return ElggAutop::getInstance()->process($pee);
+function elgg_autop($string) {
+	return ElggAutoP::getInstance()->process($string);
 }
 
 /**
@@ -358,7 +359,7 @@ function elgg_get_friendly_time($time) {
 /**
  * Strip tags and offer plugins the chance.
  * Plugins register for output:strip_tags plugin hook.
- * 	Original string included in $params['original_string']
+ * Original string included in $params['original_string']
  *
  * @param string $string Formatted string
  *
diff --git a/engine/tests/api/output.php b/engine/tests/api/output.php
index eb1a66b29..c3d5aa8c6 100644
--- a/engine/tests/api/output.php
+++ b/engine/tests/api/output.php
@@ -1,64 +1,74 @@
-<?php
-/**
- * Test case for ElggAutop functionality.
- * @author Steve Clay <steve@mrclay.org>
- */
-class ElggCoreOutputAutoPTest extends ElggCoreUnitTest {
-
-	/**
-	 * @var ElggAutop
-	 */
-	protected $_autop;
-
-	public function setUp() {
-		$this->_autop = new ElggAutop();
-	}
-	
-	public function testDomRoundtrip()
-	{
-		$d = dir(dirname(__DIR__) . '/test_files/output/autop');
-		$in = file_get_contents($d->path . "/domdoc_in.html");
-		$exp = file_get_contents($d->path . "/domdoc_exp.html");
-
-		$doc = new DOMDocument();
-		libxml_use_internal_errors(true);
-		$doc->loadHTML("<html><meta http-equiv='content-type' content='text/html; charset=utf-8'><body>"
-				. $in . '</body></html>');
-		$serialized = $doc->saveHTML();
-		list(,$out) = explode('<body>', $serialized, 2);
-		list($out) = explode('</body>', $out, 2);
-
-		$this->assertEqual($exp, $out, "DOMDocument's parsing/serialization roundtrip");
-	}
-
-	public function testProcess()
-	{
-		$data = $this->provider();
-		foreach ($data as $row) {
-			list($test, $in, $exp) = $row;
-			$out = $this->_autop->process($in);
-			$this->assertEqual($exp, $out, "Equality case {$test}");
-		}
-	}
-
-	public function provider()
-	{
-		$d = dir(dirname(__DIR__) . '/test_files/output/autop');
-		$tests = array();
-		while (false !== ($entry = $d->read())) {
-			if (preg_match('/^([a-z\\-]+)\.in\.html$/i', $entry, $m)) {
-				$tests[] = $m[1];
-			}
-		}
-
-		$data = array();
-		foreach ($tests as $test) {
-			$data[] = array(
-				$test,
-				file_get_contents($d->path . '/' . "{$test}.in.html"),
-				file_get_contents($d->path . '/' . "{$test}.exp.html"),
-			);
-		}
-		return $data;
-	}
-}
+<?php
+/**
+ * Test case for ElggAutoP functionality.
+ */
+class ElggCoreOutputAutoPTest extends ElggCoreUnitTest {
+
+	/**
+	 * @var ElggAutoP
+	 */
+	protected $_autop;
+
+	public function setUp() {
+		$this->_autop = new ElggAutoP();
+	}
+	
+	public function testDomRoundtrip() {
+		$d = dir(dirname(dirname(__FILE__)) . '/test_files/output/autop');
+		$in = file_get_contents($d->path . "/domdoc_in.html");
+		$exp = file_get_contents($d->path . "/domdoc_exp.html");
+		$exp = $this->flattenString($exp);
+
+		$doc = new DOMDocument();
+		libxml_use_internal_errors(true);
+		$doc->loadHTML("<html><meta http-equiv='content-type' content='text/html; charset=utf-8'><body>"
+				. $in . '</body></html>');
+		$serialized = $doc->saveHTML();
+		list(,$out) = explode('<body>', $serialized, 2);
+		list($out) = explode('</body>', $out, 2);
+		$out = $this->flattenString($out);
+
+		$this->assertEqual($exp, $out, "DOMDocument's parsing/serialization roundtrip");
+	}
+
+	public function testProcess() {
+		$data = $this->provider();
+		foreach ($data as $row) {
+			list($test, $in, $exp) = $row;
+			$exp = $this->flattenString($exp);
+			$out = $this->_autop->process($in);
+			$out = $this->flattenString($out);
+			
+			$this->assertEqual($exp, $out, "Equality case {$test}");
+		}
+	}
+
+	public function provider() {
+		$d = dir(dirname(dirname(__FILE__)) . '/test_files/output/autop');
+		$tests = array();
+		while (false !== ($entry = $d->read())) {
+			if (preg_match('/^([a-z\\-]+)\.in\.html$/i', $entry, $m)) {
+				$tests[] = $m[1];
+			}
+		}
+
+		$data = array();
+		foreach ($tests as $test) {
+			$data[] = array(
+				$test,
+				file_get_contents($d->path . '/' . "{$test}.in.html"),
+				file_get_contents($d->path . '/' . "{$test}.exp.html"),
+			);
+		}
+		return $data;
+	}
+
+	/**
+	 * Different versions of PHP return different whitespace between tags.
+	 * Removing all line breaks normalizes that.
+	 */
+	public function flattenString($string) {
+		$r = preg_replace('/[\n\r]+/', '', $string);
+		return $r;
+	}
+}
\ No newline at end of file
-- 
cgit v1.2.3


From c54fd6c6de4442f308f999caf36ae075de42a69c Mon Sep 17 00:00:00 2001
From: cash <cash.costello@gmail.com>
Date: Fri, 25 Jan 2013 18:16:19 -0500
Subject: Fixes #4972 decode special chars before encoding for friendly titles

---
 engine/lib/output.php | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'engine/lib/output.php')

diff --git a/engine/lib/output.php b/engine/lib/output.php
index bff0bf6e9..9295f2173 100644
--- a/engine/lib/output.php
+++ b/engine/lib/output.php
@@ -287,6 +287,8 @@ function elgg_get_friendly_title($title) {
 
 	// handle some special cases
 	$title = str_replace('&amp;', 'and', $title);
+	// quotes and angle brackets stored in the database as html encoded
+	$title = htmlspecialchars_decode($title);
 
 	$title = ElggTranslit::urlize($title);
 
-- 
cgit v1.2.3