Add a new example for unconvertible-to-UTF-8 text part data

The example file that was used for checking for text
attachment data which could not be converted to UTF-8 is
one that we *can* actually deal with by guessing the
character set, since it's valid GB18030.  So, this commit
changes that test to check for the first few Chinese
characters in that email, and introduces a replacement
test with text from /dev/random, which should not be
interpretable in any sensible way.

2 files changed, 39 insertions, 2 deletions

diff --git a/spec/fixtures/files/no-part-charset-random-data.email b/spec/fixtures/files/no-part-charset-random-data.email
new file mode 100644
index 000000000..d51fd3f38
--- /dev/null
+++ b/spec/fixtures/files/no-part-charset-random-data.email
@@ -0,0 +1,30 @@
+From xxxx@yahoo.cn Mon Oct 08 14:01:34 2012
+Return-path: <xxxx@yahoo.cn>
+Envelope-to: foi@atlas.ukcod.org.uk
+Delivery-date: Mon, 08 Oct 2012 14:01:34 +0100
+Received: (qmail 63864 invoked from network); 8 Oct 2012 13:01:12 -0000
+DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=yahoo.cn; s=s1024; t=1349701272; bh=T/mtlIYvhB/L5RO+CvTazeAdGf1n1zsGXBoA8EKGT9M=; h=Message-ID:X-Yahoo-Newman-Property:X-YMail-OSG:X-Yahoo-SMTP:Received:X-mailer:From:Subject:To:Content-Transfer-Encoding:Content-Type:Date; b=LYI/PXvA7DA746bmyprChUg7N8YDvN9XE/bhfTt5MW7siOmxHHzn1w+s5X33PvLI0x0UfJLo+MCkTnGPKnG5BYY38US8PkocJYyphrvF/eaUl3ALf8UvxHBOJX1iIi89Xp2NnfbS8lz9kZAWifb9GOnOA5/kLDcL5/WJXliit2k=
+Message-ID: <xxxx@xxxx.yahoo.com>
+X-Yahoo-Newman-Property: ymail-5
+X-YMail-OSG: nPs5jgsVM1myUoKjeEPTxxalz4BM6BZMEUYu.E8NPMPQyo_
+ Yej8T2WCTurn767NOwhuDIqNxC2QGZINqfjmKcdyW7a1P_Zxqr9GsjgxODci
+ ihwr7qYAGDDbcsrB.PX4epnJZHl3yAwoGW.1ReEZnXQANFcNep7.zNEbZ_2k
+ RU1IhI9aHYvxPxt5RWugwOoFRh9P8Ym35A88IMazNtVaBiBEXF6Vk8Aqr9XP
+ 3Vh9xOT9Pn6X8qOUjNXkdb3xB4S5AAIRSE9mqhL1KzHBwdVQs25IoM_2FV2b
+ gPsQGgL4_mwBH0WcEMhdj7Kn6Nfb44L.50E_V3DH.8P7KzDK8zNVXSbAqohX
+ Qi6MzUK2frr8IyZyYzHb.ekff7kAcJgUoHvhnyPar8tRYxhQT3_xsUTzsx8N
+ oWckVPh_i3OT7U4ObgekqgtteMoYqPH2eF1SZXamGBAs-
+X-Yahoo-SMTP: YUQHwRWswBDjbw_M.D6EP4KpT9khlJErDRBQi4ySZQ--
+X-mailer: MIME::Lite 3.027 (F2.74; T1.31; A2.07; B3.13; Q3.13)
+From: =?GB2312?B?zsJKaWFu?= Bing <xxxx@yahoo.cn>
+Subject: =?GB2312?B?yM7A1svJ?=
+To: FOI Person <EMAIL_TO>
+Content-Transfer-Encoding: base64
+Content-Type: text/plain
+Date: Tue, 9 Oct 2012 20:53:06 +0800
+
+HPBSqsndNBX+ER4hyBoPhhnclcWKVFgbevdD5cJvfI/ARbxRYqA28hZ49Pf6A/ks
+NdVh4N5VPgRs/7SHYPfw5625pZJYTLj6nVdYk76sxnjiiAmwCJWGjPoWvO7nHUBv
+fuLXtNVq5HmD0bWWjAbSk2n74PW7v5izbNO2fjHyiyX2CIof0rriXDmOldJqoebO
+ejybrjG+Tahpu3FF1Mw98HfswzkdB46u/izLCzdUQVM=
+
diff --git a/spec/models/incoming_message_spec.rb b/spec/models/incoming_message_spec.rb
index e22235298..b97ee3ca8 100644
--- a/spec/models/incoming_message_spec.rb
+++ b/spec/models/incoming_message_spec.rb
@@ -59,12 +59,19 @@ describe IncomingMessage, " when dealing with incoming mail" do
         message.subject.should == "Câmara Responde:  Banco de ideias"
     end
 
-    it 'should not error on display of a message which has no charset set on the body part and
-        is not good utf-8' do
+    it 'should deal with GB18030 text even if the charset is missing' do
         ir = info_requests(:fancy_dog_request)
         receive_incoming_mail('no-part-charset-bad-utf8.email', ir.incoming_email)
         message = ir.incoming_messages[1]
         message.parse_raw_email!
+        message.get_main_body_text_internal.should include("贵公司负责人")
+    end
+
+    it 'should not error on display of a message which has no charset set on the body part and is not good UTF-8' do
+        ir = info_requests(:fancy_dog_request)
+        receive_incoming_mail('no-part-charset-random-data.email', ir.incoming_email)
+        message = ir.incoming_messages[1]
+        message.parse_raw_email!
         message.get_main_body_text_internal.should include("The above text was badly encoded")
     end