Sutty/trabajo-afectivo
5
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

Improved error handling of email parsing.

Browse source
This commit is contained in:
Martin Edenhofer 2012-10-24 20:23:04 +02:00
parent d83b08d7d0
commit a63752c134
3 changed files with 254 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
app/models/channel/email_parser.rb
View file

@ -146,14 +146,25 @@ class Channel::EmailParser
file.header.fields.each { |field|
headers_store[field.name.to_s] = field.value.to_s
}
# get filename from content-disposition
filename = nil
if file.header[:content_disposition].filename
if file.header[:content_disposition] && file.header[:content_disposition].filename
filename = file.header[:content_disposition].filename
end
if file.header[:content_type].string
# for some broken sm mail clients (X-MimeOLE: Produced By Microsoft Exchange V6.5)
if !filename
filename = file.header[:content_location].to_s
end
# get mime type
if file.header[:content_type] && file.header[:content_type].string
headers_store['Mime-Type'] = file.header[:content_type].string
end
if file.header.charset
# get charset
if file.header && file.header.charset
headers_store['Charset'] = file.header.charset
end
@ -166,6 +177,7 @@ class Channel::EmailParser
:filename => filename,
:preferences => headers_store,
}
data[:attachments].push attach
}
end
@ -205,7 +217,7 @@ class Channel::EmailParser
attachment = {
:data => mail.body.decoded,
:filename => mail.filename || filename,
:preferences => headers_store
:preferences => headers_store
}
data[:attachments].push attachment
end

216
test/fixtures/mail10.box vendored Normal file
View file

@ -0,0 +1,216 @@
From smith@example.com Tue Oct 23 14:55:00 2012
Return-Path: <smith@example.com>
X-Original-To: info@example.com
Delivered-To: example-sales@samba.edenhofer.de
X-Greylist: delayed 1679 seconds by postgrey-1.32 at samba; Tue, 23 Oct 2012 14:54:59 BST
Received: from mailout109.bayern.de (mailout109.bayern.de [195.200.70.109])
by samba.edenhofer.de (Postfix) with ESMTP id F2FCD500B14
for <info@example.com>; Tue, 23 Oct 2012 14:54:59 +0100 (BST)
Received: from avisout130.bybn.de (avisout130.bybn.de [10.197.20.130])
by mailout109.bayern.de (8.14.5/8.14.5) with ESMTP id q9NDR29S013763
for <info@example.com>; Tue, 23 Oct 2012 15:27:02 +0200
Received: from post23.bybn.de (post23.bybn.de [10.197.20.23])
by avisout130.bybn.de (8.14.4/8.14.4) with ESMTP id q9NDR1NJ003273
for <info@example.com>; Tue, 23 Oct 2012 15:27:02 +0200
(envelope-from smith@example.com)
Received: from lramail1.Landratsamt.de ([10.38.19.31])
by post23.bybn.de (8.14.5/8.14.4) with ESMTP id q9NDR1CF018327
for <info@example.com>; Tue, 23 Oct 2012 15:27:01 +0200
Content-class: urn:content-classes:message
MIME-Version: 1.0
Content-Type: multipart/related;
boundary="----_=_NextPart_001_01CDB122.15B956D2";
type="multipart/alternative"
X-MimeOLE: Produced By Microsoft Exchange V6.5
Subject: =?iso-8859-1?Q?Gru=DF_aus_Oberalteich?=
Date: Tue, 23 Oct 2012 15:27:00 +0200
Message-ID: <8FD7A79CBC14344E85C71183DF75D85A019B1699@lramail1.Landratsamt.de>
X-MS-Has-Attach:
X-MS-TNEF-Correlator:
Thread-Topic: =?iso-8859-1?Q?Gru=DF_aus_Oberalteich?=
Thread-Index: Ac2xIg1UWZ9khKyyT0yHHVxGjysbXQ==
From: "Smith Sepp" <smith@example.com>
To: <info@example.com>
X-Keywords:
X-UID: 108
Status: RO
Content-Length: 6878
Lines: 176
This is a multi-part message in MIME format.
------_=_NextPart_001_01CDB122.15B956D2
Content-Type: multipart/alternative;
boundary="----_=_NextPart_002_01CDB122.15B956D2"
------_=_NextPart_002_01CDB122.15B956D2
Content-Type: text/plain;
charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
Herzliche Gr=FC=DFe aus Oberalteich sendet Herrn Smith
=20
Sepp Smith - Dipl.Ing. agr. (FH)
Gesch=E4ftsf=FChrer der example Straubing-Bogen
Klosterhof 1 | 94327 Bogen-Oberalteich
Tel: 09422-505601 | Fax: 09422-505620
Internet: http://example-straubing-bogen.de <http://example-straubing-bogen.de/> =
Facebook: http://facebook.de/examplesrbog <http://facebook.de/examplesrbog>=20
- European Foundation f=FCr Quality Management
=20
------_=_NextPart_002_01CDB122.15B956D2
Content-Type: text/html;
charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
<html xmlns:v=3D"urn:schemas-microsoft-com:vml" =
xmlns:o=3D"urn:schemas-microsoft-com:office:office" =
xmlns:w=3D"urn:schemas-microsoft-com:office:word" =
xmlns:m=3D"http://schemas.microsoft.com/office/2004/12/omml" =
xmlns=3D"http://www.w3.org/TR/REC-html40"><head><meta =
http-equiv=3DContent-Type content=3D"text/html; =
charset=3Diso-8859-1"><meta name=3DGenerator content=3D"Microsoft Word =
14 (filtered medium)"><!--[if !mso]><style>v\:* =
{behavior:url(#default#VML);}
o\:* {behavior:url(#default#VML);}
w\:* {behavior:url(#default#VML);}
.shape {behavior:url(#default#VML);}
</style><![endif]--><style><!--
/* Font Definitions */
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
{font-family:Tahoma;
panose-1:2 11 6 4 3 5 4 4 2 4;}
@font-face
{font-family:Verdana;
panose-1:2 11 6 4 3 5 4 4 2 4;}
@font-face
{font-family:"Viner Hand ITC";
panose-1:3 7 5 2 3 5 2 2 2 3;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0cm;
margin-bottom:.0001pt;
font-size:11.0pt;
font-family:"Calibri","sans-serif";
mso-fareast-language:EN-US;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:blue;
text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
{mso-style-priority:99;
color:purple;
text-decoration:underline;}
p.MsoAcetate, li.MsoAcetate, div.MsoAcetate
{mso-style-priority:99;
mso-style-link:"Sprechblasentext Zchn";
margin:0cm;
margin-bottom:.0001pt;
font-size:8.0pt;
font-family:"Tahoma","sans-serif";
mso-fareast-language:EN-US;}
span.E-MailFormatvorlage17
{mso-style-type:personal-compose;
font-family:"Calibri","sans-serif";
color:windowtext;}
span.SprechblasentextZchn
{mso-style-name:"Sprechblasentext Zchn";
mso-style-priority:99;
mso-style-link:Sprechblasentext;
font-family:"Tahoma","sans-serif";}
.MsoChpDefault
{mso-style-type:export-only;
font-family:"Calibri","sans-serif";
mso-fareast-language:EN-US;}
@page WordSection1
{size:612.0pt 792.0pt;
margin:70.85pt 70.85pt 2.0cm 70.85pt;}
div.WordSection1
{page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext=3D"edit" spidmax=3D"1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext=3D"edit">
<o:idmap v:ext=3D"edit" data=3D"1" />
</o:shapelayout></xml><![endif]--></head><body lang=3DDE link=3Dblue =
vlink=3Dpurple><div class=3DWordSection1><p class=3DMsoNormal>Herzliche =
Gr=FC=DFe aus Oberalteich sendet Herrn Smith<o:p></o:p></p><p =
class=3DMsoNormal><o:p>&nbsp;</o:p></p><p class=3DMsoNormal><span =
style=3D'font-size:14.0pt;font-family:"Viner Hand =
ITC";mso-fareast-language:DE'>Sepp Smith=A0 - </span><span =
style=3D'font-size:8.0pt;font-family:"Verdana","sans-serif";mso-fareast-l=
anguage:DE'>Dipl.Ing. agr. (FH)</span><span =
style=3D'font-size:14.0pt;font-family:"Viner Hand =
ITC";mso-fareast-language:DE'><o:p></o:p></span></p><p =
class=3DMsoNormal><span =
style=3D'mso-fareast-language:DE'>Gesch=E4ftsf=FChrer der example =
Straubing-Bogen<o:p></o:p></span></p><p class=3DMsoNormal><span =
style=3D'mso-fareast-language:DE'>Klosterhof 1 | 94327 =
Bogen-Oberalteich<o:p></o:p></span></p><p class=3DMsoNormal><span =
style=3D'mso-fareast-language:DE'>Tel: 09422-505601 | Fax: =
09422-505620<o:p></o:p></span></p><p class=3DMsoNormal><span =
style=3D'mso-fareast-language:DE'>Internet: <a =
href=3D"http://example-straubing-bogen.de/"><span =
style=3D'color:blue'>http://example-straubing-bogen.de</span></a><o:p></o:p><=
/span></p><p class=3DMsoNormal><span lang=3DEN-US =
style=3D'mso-fareast-language:DE'>Facebook: </span><span =
style=3D'mso-fareast-language:DE'><a =
href=3D"http://facebook.de/examplesrbog"><span lang=3DEN-US =
style=3D'color:blue'>http://facebook.de/examplesrbog</span></a></span><span =
lang=3DEN-US style=3D'mso-fareast-language:DE'><o:p></o:p></span></p><p =
class=3DMsoNormal><b><span =
style=3D'font-size:7.5pt;color:navy;mso-fareast-language:DE'><img =
border=3D0 width=3D60 height=3D19 id=3D"Bild_x0020_1" =
src=3D"cid:image001.jpg@01CDB132.D8A510F0" alt=3D"Beschreibung: =
Beschreibung: efqmLogo"></span></b><b><span lang=3DEN-US =
style=3D'font-size:7.5pt;color:navy;mso-fareast-language:DE'>=A0 -=A0 =
European Foundation f=FCr Quality Management</span></b><span =
lang=3DEN-US style=3D'mso-fareast-language:DE'><o:p></o:p></span></p><p =
class=3DMsoNormal><span =
lang=3DEN-US><o:p>&nbsp;</o:p></span></p></div></body></html>
------_=_NextPart_002_01CDB122.15B956D2--
------_=_NextPart_001_01CDB122.15B956D2
Content-Type: image/jpeg;
name="image001.jpg"
Content-Transfer-Encoding: base64
Content-ID: <image001.jpg@01CDB132.D8A510F0>
Content-Description: image001.jpg
Content-Location: image001.jpg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=
------_=_NextPart_001_01CDB122.15B956D2--

24
test/unit/email_parser_test.rb
View file

@ -195,13 +195,33 @@ Hof",
:body => "Enjoy!\n\n-Martin\n\n--\nOld programmers never die. They just branch to a new address."
},
},
{
:data => IO.read('test/fixtures/mail10.box'),
:body_md5 => '8d6ea42f7f36a790e67f50e3a5f27063',
:attachments => [
{
:md5 => '08b0c83fd155db23f22bed845715225d',
:filename => 'message.html',
},
{
:md5 => 'a618d671348735744d4c9a4005b56799',
:filename => 'image001.jpg',
},
],
:params => {
:from => 'Smith Sepp <smith@example.com>',
:from_email => 'smith@example.com',
:from_display_name => 'Smith Sepp',
:subject => 'Gruß aus Oberalteich',
# :body => "Herzliche Grüße aus Oberalteich sendet Herrn Smith\n\n \n\nSepp Smith - Dipl.Ing. agr. (FH)\n\nGeschäftsführer der example Straubing-Bogen\n\nKlosterhof 1 | 94327 Bogen-Oberalteich\n\nTel: 09422-505601 | Fax: 09422-505620\n\nInternet: http://example-straubing-bogen.de <http://example-straubing-bogen.de/> \n\nFacebook: http://facebook.de/examplesrbog <http://facebook.de/examplesrbog> \n\n - European Foundation für Quality Management\n\n"
},
},
]
files.each { |file|
parser = Channel::EmailParser.new
data = parser.parse( file[:data] )
# check body
md5 = Digest::MD5.hexdigest( data[:body] )
assert_equal( file[:body_md5], md5 )