From be9cbc634a630f5e9d75a3e3d985152b17305b2f Mon Sep 17 00:00:00 2001
From: willnix <frieder.steinmetz@gmail.com>
Date: Sat, 19 Apr 2014 21:59:04 +0000
Subject: [PATCH] tagWhitelist allows alignment attribute now

This is the closest I could get to removing everything "unsave" without introducing an additional regex.
---
 html.go | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/html.go b/html.go
index 5d79ab6..54744c2 100644
--- a/html.go
+++ b/html.go
@@ -78,8 +78,15 @@ var (
 		"tbody",
 		
 	}
+	
+	alignments = []string{
+		"left",
+		"right",
+		"center",
+	}
+
 	urlRe        = `((https?|ftp):\/\/|\/)[-A-Za-z0-9+&@#\/%?=~_|!:,.;\(\)]+`
-	tagWhitelist = regexp.MustCompile(`^(<\/?(` + strings.Join(tags, "|") + `)>|<(br|hr)\s?\/?>)$`)
+	tagWhitelist = regexp.MustCompile(`^(<\/?(` + strings.Join(tags, "|") + `)(\salign="(` + strings.Join(alignments, "|") + `)")?>|<(br|hr)\s?\/?>)$`)
 	anchorClean  = regexp.MustCompile(`^(<a\shref="` + urlRe + `"(\stitle="[^"<>]+")?\s?>|<\/a>)$`)
 	imgClean     = regexp.MustCompile(`^(<img\ssrc="` + urlRe + `"(\swidth="\d{1,3}")?(\sheight="\d{1,3}")?(\salt="[^"<>]*")?(\stitle="[^"<>]*")?\s?\/?>)$`)
 	// TODO: improve this regexp to catch all possible entities: