Fix: Keep indentation in html and md code blocks.

Moves the logic for unwrapping broken lines in html (and Markdown) to
the node processing, instead of doing it over the full html content.
This allows us to skip if for code blocks (aka `<code>` elements within
`<pre>` elements).

1 files changed, 16 insertions, 17 deletions

diff --git a/include/html2bbcode.php b/include/html2bbcode.php
index f75a3e428..8822d6f1d 100644
--- a/include/html2bbcode.php
+++ b/include/html2bbcode.php
@@ -65,6 +65,22 @@ function node2bbcodesub(&$doc, $oldnode, $attributes, $startbb, $endbb)
 			if ($oldNode->hasChildNodes()) {
 				foreach ($oldNode->childNodes as $child) {
 					$newNode = $child->cloneNode(true);
+
+					// Newlines are insignificant in HTML, but not so in BBCode, so let's
+					// unwrap the child nodes of when converting them. Also we compress
+					// consecutive whitespace chars to one.
+					//
+					// The exception is `<pre>` and `<code>` elements which
+					// should keep both newlines and whitespace intact.
+					if ($oldNode->nodeName != 'pre' && $oldNode->nodeName != 'code') {
+						$newNode->nodeValue = str_replace(
+							array("\n<", ">\n", "\r", "\n", "\xC3\x82\xC2\xA0"),
+							array("<", ">", "<br />", " ", ""),
+							$newNode->nodeValue);
+
+						$newNode->nodeValue = preg_replace('=[\s]{2,}=i', " ", $newNode->nodeValue);
+					}
+
 					$oldNode->parentNode->insertBefore($newNode, $oldNode);
 				}
 			}
@@ -125,23 +141,6 @@ function html2bbcode($message)
 	deletenode($doc, 'xml');
 	deletenode($doc, 'removeme');
 
-	$xpath = new DomXPath($doc);
-	$list = $xpath->query("//pre");
-	foreach ($list as $node) {
-		if ($node->hasChildNodes()) {
-			foreach ($node->childNodes as $child) {
-				$child->nodeValue = str_replace("\n", "\r", $child->nodeValue);
-			}
-		} else {
-			$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);
-	$message = preg_replace('= [\s]*=i', " ", $message);
-	@$doc->loadHTML($message);
-
 	node2bbcode($doc, 'html', array(), "", "");
 	node2bbcode($doc, 'body', array(), "", "");