From adf6e9c23ab9b665b598a9624ae9825b4fa45113 Mon Sep 17 00:00:00 2001
From: Ben Kurtovic <ben.kurtovic@verizon.net>
Date: Tue, 4 Sep 2012 22:41:17 -0400
Subject: [PATCH] Properly handle bad URI schemes.

---
 pages/copyvios.mako            | 4 ++++
 toolserver/copyvios/checker.py | 3 +++
 2 files changed, 7 insertions(+)

diff --git a/pages/copyvios.mako b/pages/copyvios.mako
index 0ec5c98..0a91c1b 100644
--- a/pages/copyvios.mako
+++ b/pages/copyvios.mako
@@ -10,6 +10,10 @@
                 <div class="red-box">
                     <p>The given page doesn't seem to exist: <a href="${page.url}">${page.title | h}</a>.</p>
                 </div>
+            % elif query.project and query.lang and query.title and query.url and page and result == "bad URI":
+                <div class="red-box">
+                    <p>Unsupported URI scheme: <a href="${query.url | h}">${query.url | h}</a>.</p>
+                </div>
             % endif
             <h1>Copyvio Detector</h1>
             <p>This tool attempts to detect <a href="//en.wikipedia.org/wiki/WP:COPYVIO">copyright violations</a> in articles. Simply give the title of the page you want to check and hit Submit. The tool will then search for its content elsewhere on the web and display a report if a similar webpage is found. If you also provide a URL, it will not query any search engines and instead display a report comparing the article to that particular webpage, like the <a href="//toolserver.org/~dcoetzee/duplicationdetector/">Duplication Detector</a>. Check out the <a href="//en.wikipedia.org/wiki/User:EarwigBot/Copyvios/FAQ">FAQ</a> for more information and technical details.</p>
diff --git a/toolserver/copyvios/checker.py b/toolserver/copyvios/checker.py
index b82ea4e..ca05651 100644
--- a/toolserver/copyvios/checker.py
+++ b/toolserver/copyvios/checker.py
@@ -2,6 +2,7 @@
 
 from datetime import datetime
 from hashlib import sha256
+from urlparse import urlparse
 
 from earwigbot import exceptions
 
@@ -15,6 +16,8 @@ def get_results(bot, site, query):
         return page, None
 
     if query.url:
+        if urlparse(query.url).scheme not in ["http", "https"]:
+            return page, "bad URI"
         result = page.copyvio_compare(query.url)
         result.cached = False
     else: