diff options
author | R David Murray <rdmurray@bitdance.com> | 2011-03-21 21:17:06 (GMT) |
---|---|---|
committer | R David Murray <rdmurray@bitdance.com> | 2011-03-21 21:17:06 (GMT) |
commit | 9aaba789b38834f40bb833735836a52237323be2 (patch) | |
tree | 0341ba51f5e09149e8f3bfa01b2cb9641c75243a /Lib/test/test_email | |
parent | 76a3d73cbd4fffb051f9fbb1a52c4e4815851254 (diff) | |
download | cpython-9aaba789b38834f40bb833735836a52237323be2.zip cpython-9aaba789b38834f40bb833735836a52237323be2.tar.gz cpython-9aaba789b38834f40bb833735836a52237323be2.tar.bz2 |
Correctly move email package tests to Lib/test.
Diffstat (limited to 'Lib/test/test_email')
53 files changed, 6274 insertions, 0 deletions
diff --git a/Lib/test/test_email/__init__.py b/Lib/test/test_email/__init__.py new file mode 100644 index 0000000..5aae093 --- /dev/null +++ b/Lib/test/test_email/__init__.py @@ -0,0 +1,13 @@ +import os +import sys +import unittest +import test.support + +# used by regrtest and __main__. +def test_main(): + here = os.path.dirname(__file__) + # Unittest mucks with the path, so we have to save and restore + # it to keep regrtest happy. + savepath = sys.path[:] + test.support._run_suite(unittest.defaultTestLoader.discover(here)) + sys.path[:] = savepath diff --git a/Lib/test/test_email/data/PyBanner048.gif b/Lib/test/test_email/data/PyBanner048.gif Binary files differnew file mode 100644 index 0000000..1a5c87f --- /dev/null +++ b/Lib/test/test_email/data/PyBanner048.gif diff --git a/Lib/test/test_email/data/audiotest.au b/Lib/test/test_email/data/audiotest.au Binary files differnew file mode 100644 index 0000000..f76b050 --- /dev/null +++ b/Lib/test/test_email/data/audiotest.au diff --git a/Lib/test/test_email/data/msg_01.txt b/Lib/test/test_email/data/msg_01.txt new file mode 100644 index 0000000..7e33bcf --- /dev/null +++ b/Lib/test/test_email/data/msg_01.txt @@ -0,0 +1,19 @@ +Return-Path: <bbb@zzz.org> +Delivered-To: bbb@zzz.org +Received: by mail.zzz.org (Postfix, from userid 889) + id 27CEAD38CC; Fri, 4 May 2001 14:05:44 -0400 (EDT) +MIME-Version: 1.0 +Content-Type: text/plain; charset=us-ascii +Content-Transfer-Encoding: 7bit +Message-ID: <15090.61304.110929.45684@aaa.zzz.org> +From: bbb@ddd.com (John X. Doe) +To: bbb@zzz.org +Subject: This is a test message +Date: Fri, 4 May 2001 14:05:44 -0400 + + +Hi, + +Do you like this message? + +-Me diff --git a/Lib/test/test_email/data/msg_02.txt b/Lib/test/test_email/data/msg_02.txt new file mode 100644 index 0000000..43f2480 --- /dev/null +++ b/Lib/test/test_email/data/msg_02.txt @@ -0,0 +1,135 @@ +MIME-version: 1.0 +From: ppp-request@zzz.org +Sender: ppp-admin@zzz.org +To: ppp@zzz.org +Subject: Ppp digest, Vol 1 #2 - 5 msgs +Date: Fri, 20 Apr 2001 20:18:00 -0400 (EDT) +X-Mailer: Mailman v2.0.4 +X-Mailman-Version: 2.0.4 +Content-Type: multipart/mixed; boundary="192.168.1.2.889.32614.987812255.500.21814" + +--192.168.1.2.889.32614.987812255.500.21814 +Content-type: text/plain; charset=us-ascii +Content-description: Masthead (Ppp digest, Vol 1 #2) + +Send Ppp mailing list submissions to + ppp@zzz.org + +To subscribe or unsubscribe via the World Wide Web, visit + http://www.zzz.org/mailman/listinfo/ppp +or, via email, send a message with subject or body 'help' to + ppp-request@zzz.org + +You can reach the person managing the list at + ppp-admin@zzz.org + +When replying, please edit your Subject line so it is more specific +than "Re: Contents of Ppp digest..." + + +--192.168.1.2.889.32614.987812255.500.21814 +Content-type: text/plain; charset=us-ascii +Content-description: Today's Topics (5 msgs) + +Today's Topics: + + 1. testing #1 (Barry A. Warsaw) + 2. testing #2 (Barry A. Warsaw) + 3. testing #3 (Barry A. Warsaw) + 4. testing #4 (Barry A. Warsaw) + 5. testing #5 (Barry A. Warsaw) + +--192.168.1.2.889.32614.987812255.500.21814 +Content-Type: multipart/digest; boundary="__--__--" + +--__--__-- + +Message: 1 +Content-Type: text/plain; charset=us-ascii +Content-Transfer-Encoding: 7bit +Date: Fri, 20 Apr 2001 20:16:13 -0400 +To: ppp@zzz.org +From: barry@digicool.com (Barry A. Warsaw) +Subject: [Ppp] testing #1 +Precedence: bulk + + +hello + + +--__--__-- + +Message: 2 +Date: Fri, 20 Apr 2001 20:16:21 -0400 +Content-Type: text/plain; charset=us-ascii +Content-Transfer-Encoding: 7bit +To: ppp@zzz.org +From: barry@digicool.com (Barry A. Warsaw) +Precedence: bulk + + +hello + + +--__--__-- + +Message: 3 +Date: Fri, 20 Apr 2001 20:16:25 -0400 +Content-Type: text/plain; charset=us-ascii +Content-Transfer-Encoding: 7bit +To: ppp@zzz.org +From: barry@digicool.com (Barry A. Warsaw) +Subject: [Ppp] testing #3 +Precedence: bulk + + +hello + + +--__--__-- + +Message: 4 +Date: Fri, 20 Apr 2001 20:16:28 -0400 +Content-Type: text/plain; charset=us-ascii +Content-Transfer-Encoding: 7bit +To: ppp@zzz.org +From: barry@digicool.com (Barry A. Warsaw) +Subject: [Ppp] testing #4 +Precedence: bulk + + +hello + + +--__--__-- + +Message: 5 +Date: Fri, 20 Apr 2001 20:16:32 -0400 +Content-Type: text/plain; charset=us-ascii +Content-Transfer-Encoding: 7bit +To: ppp@zzz.org +From: barry@digicool.com (Barry A. Warsaw) +Subject: [Ppp] testing #5 +Precedence: bulk + + +hello + + + + +--__--__---- +--192.168.1.2.889.32614.987812255.500.21814 +Content-type: text/plain; charset=us-ascii +Content-description: Digest Footer + +_______________________________________________ +Ppp mailing list +Ppp@zzz.org +http://www.zzz.org/mailman/listinfo/ppp + + +--192.168.1.2.889.32614.987812255.500.21814-- + +End of Ppp Digest + diff --git a/Lib/test/test_email/data/msg_03.txt b/Lib/test/test_email/data/msg_03.txt new file mode 100644 index 0000000..c748ebf --- /dev/null +++ b/Lib/test/test_email/data/msg_03.txt @@ -0,0 +1,16 @@ +Return-Path: <bbb@zzz.org> +Delivered-To: bbb@zzz.org +Received: by mail.zzz.org (Postfix, from userid 889) + id 27CEAD38CC; Fri, 4 May 2001 14:05:44 -0400 (EDT) +Message-ID: <15090.61304.110929.45684@aaa.zzz.org> +From: bbb@ddd.com (John X. Doe) +To: bbb@zzz.org +Subject: This is a test message +Date: Fri, 4 May 2001 14:05:44 -0400 + + +Hi, + +Do you like this message? + +-Me diff --git a/Lib/test/test_email/data/msg_04.txt b/Lib/test/test_email/data/msg_04.txt new file mode 100644 index 0000000..1f633c4 --- /dev/null +++ b/Lib/test/test_email/data/msg_04.txt @@ -0,0 +1,37 @@ +Return-Path: <barry@python.org> +Delivered-To: barry@python.org +Received: by mail.python.org (Postfix, from userid 889) + id C2BF0D37C6; Tue, 11 Sep 2001 00:05:05 -0400 (EDT) +MIME-Version: 1.0 +Content-Type: multipart/mixed; boundary="h90VIIIKmx" +Content-Transfer-Encoding: 7bit +Message-ID: <15261.36209.358846.118674@anthem.python.org> +From: barry@python.org (Barry A. Warsaw) +To: barry@python.org +Subject: a simple multipart +Date: Tue, 11 Sep 2001 00:05:05 -0400 +X-Mailer: VM 6.95 under 21.4 (patch 4) "Artificial Intelligence" XEmacs Lucid +X-Attribution: BAW +X-Oblique-Strategy: Make a door into a window + + +--h90VIIIKmx +Content-Type: text/plain +Content-Disposition: inline; + filename="msg.txt" +Content-Transfer-Encoding: 7bit + +a simple kind of mirror +to reflect upon our own + +--h90VIIIKmx +Content-Type: text/plain +Content-Disposition: inline; + filename="msg.txt" +Content-Transfer-Encoding: 7bit + +a simple kind of mirror +to reflect upon our own + +--h90VIIIKmx-- + diff --git a/Lib/test/test_email/data/msg_05.txt b/Lib/test/test_email/data/msg_05.txt new file mode 100644 index 0000000..87d5e9c --- /dev/null +++ b/Lib/test/test_email/data/msg_05.txt @@ -0,0 +1,28 @@ +From: foo +Subject: bar +To: baz +MIME-Version: 1.0 +Content-Type: multipart/report; report-type=delivery-status; + boundary="D1690A7AC1.996856090/mail.example.com" +Message-Id: <20010803162810.0CA8AA7ACC@mail.example.com> + +This is a MIME-encapsulated message. + +--D1690A7AC1.996856090/mail.example.com +Content-Type: text/plain + +Yadda yadda yadda + +--D1690A7AC1.996856090/mail.example.com + +Yadda yadda yadda + +--D1690A7AC1.996856090/mail.example.com +Content-Type: message/rfc822 + +From: nobody@python.org + +Yadda yadda yadda + +--D1690A7AC1.996856090/mail.example.com-- + diff --git a/Lib/test/test_email/data/msg_06.txt b/Lib/test/test_email/data/msg_06.txt new file mode 100644 index 0000000..69f3a47 --- /dev/null +++ b/Lib/test/test_email/data/msg_06.txt @@ -0,0 +1,33 @@ +Return-Path: <barry@python.org> +Delivered-To: barry@python.org +MIME-Version: 1.0 +Content-Type: message/rfc822 +Content-Description: forwarded message +Content-Transfer-Encoding: 7bit +Message-ID: <15265.9482.641338.555352@python.org> +From: barry@zope.com (Barry A. Warsaw) +Sender: barry@python.org +To: barry@python.org +Subject: forwarded message from Barry A. Warsaw +Date: Thu, 13 Sep 2001 17:28:42 -0400 +X-Mailer: VM 6.95 under 21.4 (patch 4) "Artificial Intelligence" XEmacs Lucid +X-Attribution: BAW +X-Oblique-Strategy: Be dirty +X-Url: http://barry.wooz.org + +MIME-Version: 1.0 +Content-Type: text/plain; charset=us-ascii +Return-Path: <barry@python.org> +Delivered-To: barry@python.org +Message-ID: <15265.9468.713530.98441@python.org> +From: barry@zope.com (Barry A. Warsaw) +Sender: barry@python.org +To: barry@python.org +Subject: testing +Date: Thu, 13 Sep 2001 17:28:28 -0400 +X-Mailer: VM 6.95 under 21.4 (patch 4) "Artificial Intelligence" XEmacs Lucid +X-Attribution: BAW +X-Oblique-Strategy: Spectrum analysis +X-Url: http://barry.wooz.org + + diff --git a/Lib/test/test_email/data/msg_07.txt b/Lib/test/test_email/data/msg_07.txt new file mode 100644 index 0000000..721f3a0 --- /dev/null +++ b/Lib/test/test_email/data/msg_07.txt @@ -0,0 +1,83 @@ +MIME-Version: 1.0 +From: Barry <barry@digicool.com> +To: Dingus Lovers <cravindogs@cravindogs.com> +Subject: Here is your dingus fish +Date: Fri, 20 Apr 2001 19:35:02 -0400 +Content-Type: multipart/mixed; boundary="BOUNDARY" + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" + +Hi there, + +This is the dingus fish. + +--BOUNDARY +Content-Type: image/gif; name="dingusfish.gif" +Content-Transfer-Encoding: base64 +content-disposition: attachment; filename="dingusfish.gif" + +R0lGODdhAAEAAfAAAP///wAAACwAAAAAAAEAAQAC/oSPqcvtD6OctNqLs968+w+G4kiW5omm6sq2 +7gvH8kzX9o3n+s73/g8MCofEovGITGICTKbyCV0FDNOo9SqpQqpOrJfXzTQj2vD3TGtqL+NtGQ2f +qTXmxzuOd7WXdcc9DyjU53ewFni4s0fGhdiYaEhGBelICTNoV1j5NUnFcrmUqemjNifJVWpaOqaI +oFq3SspZsSraE7sHq3jr1MZqWvi662vxV4tD+pvKW6aLDOCLyur8PDwbanyDeq0N3DctbQYeLDvR +RY6t95m6UB0d3mwIrV7e2VGNvjjffukeJp4w7F65KecGFsTHQGAygOrgrWs1jt28Rc88KESYcGLA +/obvTkH6p+CinWJiJmIMqXGQwH/y4qk0SYjgQTczT3ajKZGfuI0uJ4kkVI/DT5s3/ejkxI0aT4Y+ +YTYgWbImUaXk9nlLmnSh1qJiJFl0OpUqRK4oOy7NyRQtHWofhoYVxkwWXKUSn0YsS+fUV6lhqfYb +6ayd3Z5qQdG1B7bvQzaJjwUV2lixMUZ7JVsOlfjWVr/3NB/uFvnySBN6Dcb6rGwaRM3wsormw5cC +M9NxWy/bWdufudCvy8bOAjXjVVwta/uO21sE5RHBCzNFXtgq9ORtH4eYjVP4Yryo026nvkFmCeyA +B29efV6ravCMK5JwWd5897Qrx7ll38o6iHDZ/rXPR//feevhF4l7wjUGX3xq1eeRfM4RSJGBIV1D +z1gKPkfWag3mVBVvva1RlX5bAJTPR/2YqNtw/FkIYYEi/pIZiAdpcxpoHtmnYYoZtvhUftzdx5ZX +JSKDW405zkGcZzzGZ6KEv4FI224oDmijlEf+xp6MJK5ojY/ASeVUR+wsKRuJ+XFZ5o7ZeEime8t1 +ouUsU6YjF5ZtUihhkGfCdFQLWQFJ3UXxmElfhQnR+eCdcDbkFZp6vTRmj56ApCihn5QGpaToNZmR +n3NVSpZcQpZ2KEONusaiCsKAug0wkQbJSFO+PTSjneGxOuFjPlUk3ovWvdIerjUg9ZGIOtGq/qeX +eCYrrCX+1UPsgTKGGRSbzd5q156d/gpfbJxe66eD5iQKrXj7RGgruGxs62qebBHUKS32CKluCiqZ +qh+pmehmEb71noAUoe5e9Zm17S7773V10pjrtG4CmuurCV/n6zLK5turWNhqOvFXbjhZrMD0YhKe +wR0zOyuvsh6MWrGoIuzvyWu5y1WIFAqmJselypxXh6dKLNOKEB98L88bS2rkNqqlKzCNJp9c0G0j +Gzh0iRrCbHSXmPR643QS+4rWhgFmnSbSuXCjS0xAOWkU2UdLqyuUNfHSFdUouy3bm5i5GnDM3tG8 +doJ4r5tqu3pPbRSVfvs8uJzeNXhp3n4j/tZ42SwH7eaWUUOjc3qFV9453UHTXZfcLH+OeNs5g36x +lBnHvTm7EbMbLeuaLncao8vWCXimfo1o+843Ak6y4ChNeGntvAYvfLK4ezmoyNIbNCLTCXO9ZV3A +E8/s88RczPzDwI4Ob7XZyl7+9Miban29h+tJZPrE21wgvBphDfrrfPdCTPKJD/y98L1rZwHcV6Jq +Zab0metpuNIX/qAFPoz171WUaUb4HAhBSzHuHfjzHb3kha/2Cctis/ORArVHNYfFyYRH2pYIRzic +isVOfPWD1b6mRTqpCRBozzof6UZVvFXRxWIr3GGrEviGYgyPMfahheiSaLs/9QeFu7oZ/ndSY8DD +ya9x+uPed+7mxN2IzIISBOMLFYWVqC3Pew1T2nFuuCiwZS5/v6II10i4t1OJcUH2U9zxKodHsGGv +Oa+zkvNUYUOa/TCCRutF9MzDwdlUMJADTCGSbDQ5OV4PTamDoPEi6Ecc/RF5RWwkcdSXvSOaDWSn +I9LlvubFTQpuc6JKXLcKeb+xdbKRBnwREemXyjg6ME65aJiOuBgrktzykfPLJBKR9ClMavJ62/Ff +BlNIyod9yX9wcSXexnXFpvkrbXk64xsx5Db7wXKP5fSgsvwIMM/9631VLBfkmtbHRXpqmtei52hG +pUwSlo+BASQoeILDOBgREECxBBh5/iYmNsQ9dIv5+OI++QkqdsJPc3uykz5fkM+OraeekcQF7X4n +B5S67za5U967PmooGQhUXfF7afXyCD7ONdRe17QogYjVx38uLwtrS6nhTnm15LQUnu9E2uK6CNI/ +1HOABj0ESwOjut4FEpFQpdNAm4K2LHnDWHNcmKB2ioKBogysVZtMO2nSxUdZ8Yk2kJc7URioLVI0 +YgmtIwZj4LoeKemgnOnbUdGnzZ4Oa6scqiolBGqS6RgWNLu0RMhcaE6rhhU4hiuqFXPAG8fGwTPW +FKeLMtdVmXLSs5YJGF/YeVm7rREMlY3UYE+yCxbaMXX8y15m5zVHq6GOKDMynzII/jdUHdyVqIy0 +ifX2+r/EgtZcvRzSb72gU9ui87M2VecjKildW/aFqaYhKoryUjfB/g4qtyVuc60xFDGmCxwjW+qu +zjuwl2GkOWn66+3QiiEctvd04OVvcCVzjgT7lrkvjVGKKHmmlDUKowSeikb5kK/mJReuWOxONx+s +ULsl+Lqb0CVn0SrVyJ6wt4t6yTeSCafhPhAf0OXn6L60UMxiLolFAtmN35S2Ob1lZpQ1r/n0Qb5D +oQ1zJiRVDgF8N3Q8TYfbi3DyWCy3lT1nxyBs6FT3S2GOzWRlxwKvlRP0RPJA9SjxEy0UoEnkA+M4 +cnzLMJrBGWLFEaaUb5lvpqbq/loOaU5+DFuHPxo82/OZuM8FXG3oVNZhtWpMpb/0Xu5m/LfLhHZQ +7yuVI0MqZ7NE43imC8jH3IwGZlbPm0xkJYs7+2U48hXTsFSMqgGDvai0kLxyynKNT/waj+q1c1tz +GjOpPBgdCSq3UKZxCSsqFIY+O6JbAWGWcV1pwqLyj5sGqCF1xb1F3varUWqrJv6cN3PrUXzijtfZ +FshpBL3Xwr4GIPvU2N8EjrJgS1zl21rbXQMXeXc5jjFyrhpCzijSv/RQtyPSzHCFMhlME95fHglt +pRsX+dfSQjUeHAlpWzJ5iOo79Ldnaxai6bXTcGO3fp07ri7HLEmXXPlYi8bv/qVxvNcdra6m7Rlb +6JBTb5fd66VhFRjGArh2n7R1rDW4P5NOT9K0I183T2scYkeZ3q/VFyLb09U9ajzXBS8Kgkhc4mBS +kYY9cy3Vy9lUnuNJH8HGIclUilwnBtjUOH0gteGOZ4c/XNrhXLSYDyxfnD8z1pDy7rYRvDolhnbe +UMzxCZUs40s6s7UIvBnLgc0+vKuOkIXeOrDymlp+Zxra4MZLBbVrqD/jTJ597pDmnw5c4+DbyB88 +9Cg9DodYcSuMZT/114pptqc/EuTjRPvH/z5slzI3tluOEBBLqOXLOX+0I5929tO97wkvl/atCz+y +xJrdwteW2FNW/NSmBP+f/maYtVs/bYyBC7Ox3jsYZHL05CIrBa/nS+b3bHfiYm4Ueil1YZZSgAUI +fFZ1dxUmeA2oQRQ3RuGXNGLFV9/XbGFGPV6kfzk1TBBCd+izc7q1H+OHMJwmaBX2IQNYVAKHYepV +SSGCe6CnbYHHETKGNe43EDvFgZr0gB/nVHPHZ80VV1ojOiI3XDvYIkl4ayo4bxQIgrFXWTvBI0nH +VElWMuw2aLUWCRHHf8ymVCHjFlJnOSojfevCYyyyZDH0IcvHhrsnQ5O1OsWzONuVVKIxSxiFZ/tR +fKDAf6xFTnw4O9Qig2VCfW2hJQrmMOuHW0W3dLQmCMO2ccdUd/xyfflH/olTiHZVdGwb8nIwRzSE +J15jFlOJuBZBZ4CiyHyd2IFylFlB+HgHhYabhWOGwYO1ZH/Og1dtQlFMk352CGRSIFTapnWQEUtN +l4zv8S0aaCFDyGCBqDUxZYpxGHX01y/JuH1xhn7TOCnNCI4eKDs5WGX4R425F4vF1o3BJ4vO0otq +I3rimI7jJY1jISqnBxknCIvruF83mF5wN4X7qGLIhR8A2Vg0yFERSIXn9Vv3GHy3Vj/WIkKddlYi +yIMv2I/VMjTLpW7pt05SWIZR0RPyxpB4SIUM9lBPGBl0GC7oSEEwRYLe4pJpZY2P0zbI1n+Oc44w +qY3PUnmF0ixjVpDD/mJ9wpOBGTVgXlaCaZiPcIWK5NiKBIiPdGaQ0TWGvAiG7nMchdZb7Vgf8zNi +MuMyzRdy/lePe9iC4TRx7WhhOQI/QiSVNAmAa2lT/piFbuh7ofJoYSZzrSZ1bvmWw3eN2nKUPVky +uPN5/VRfohRd0VYZoqhKIlU6TXYhJxmPUIloAwc1bPmHEpaZYZORHNlXUJM07hATwHR8MJYqkwWR +WaIezFhxSFlc8/Fq82hEnpeRozg3ULhhr9lAGtVEkCg5ZNRuuVleBPaZadhG0ZgkyPmDOTOKzViM +YgOcpukKqQcbjAWS0IleQ2ROjdh6A+md1qWdBRSX7iSYgFRTtRmBpJioieXJiHfJiMGIR9fJOn8I +MSfXYhspn4ooSa2mSAj4n+8Bmg03fBJZoPOJgsVZRxu1oOMRPXYYjdqjihFaEoZpXBREanuJoRI6 +cibFinq4ngUKh/wQd/H5ofYCZ0HJXR62opZFaAT0iFIZo4DIiUojkjeqKiuoZirKo5Y1a7AWckGa +BkuYoD5lpDK6eUs6CkDqpETwl1EqpfhJpVeKpVl6EgUAADs= + +--BOUNDARY-- diff --git a/Lib/test/test_email/data/msg_08.txt b/Lib/test/test_email/data/msg_08.txt new file mode 100644 index 0000000..b563083 --- /dev/null +++ b/Lib/test/test_email/data/msg_08.txt @@ -0,0 +1,24 @@ +MIME-Version: 1.0 +From: Barry Warsaw <barry@zope.com> +To: Dingus Lovers <cravindogs@cravindogs.com> +Subject: Lyrics +Date: Fri, 20 Apr 2001 19:35:02 -0400 +Content-Type: multipart/mixed; boundary="BOUNDARY" + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" + + +--BOUNDARY +Content-Type: text/html; charset="iso-8859-1" + + +--BOUNDARY +Content-Type: text/plain; charset="iso-8859-2" + + +--BOUNDARY +Content-Type: text/plain; charset="koi8-r" + + +--BOUNDARY-- diff --git a/Lib/test/test_email/data/msg_09.txt b/Lib/test/test_email/data/msg_09.txt new file mode 100644 index 0000000..575c4c2 --- /dev/null +++ b/Lib/test/test_email/data/msg_09.txt @@ -0,0 +1,24 @@ +MIME-Version: 1.0 +From: Barry Warsaw <barry@zope.com> +To: Dingus Lovers <cravindogs@cravindogs.com> +Subject: Lyrics +Date: Fri, 20 Apr 2001 19:35:02 -0400 +Content-Type: multipart/mixed; boundary="BOUNDARY" + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" + + +--BOUNDARY +Content-Type: text/html; charset="iso-8859-1" + + +--BOUNDARY +Content-Type: text/plain + + +--BOUNDARY +Content-Type: text/plain; charset="koi8-r" + + +--BOUNDARY-- diff --git a/Lib/test/test_email/data/msg_10.txt b/Lib/test/test_email/data/msg_10.txt new file mode 100644 index 0000000..0790396 --- /dev/null +++ b/Lib/test/test_email/data/msg_10.txt @@ -0,0 +1,39 @@ +MIME-Version: 1.0 +From: Barry Warsaw <barry@zope.com> +To: Dingus Lovers <cravindogs@cravindogs.com> +Subject: Lyrics +Date: Fri, 20 Apr 2001 19:35:02 -0400 +Content-Type: multipart/mixed; boundary="BOUNDARY" + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" +Content-Transfer-Encoding: 7bit + +This is a 7bit encoded message. + +--BOUNDARY +Content-Type: text/html; charset="iso-8859-1" +Content-Transfer-Encoding: Quoted-Printable + +=A1This is a Quoted Printable encoded message! + +--BOUNDARY +Content-Type: text/plain; charset="iso-8859-1" +Content-Transfer-Encoding: Base64 + +VGhpcyBpcyBhIEJhc2U2NCBlbmNvZGVkIG1lc3NhZ2Uu + + +--BOUNDARY +Content-Type: text/plain; charset="iso-8859-1" +Content-Transfer-Encoding: Base64 + +VGhpcyBpcyBhIEJhc2U2NCBlbmNvZGVkIG1lc3NhZ2UuCg== + + +--BOUNDARY +Content-Type: text/plain; charset="iso-8859-1" + +This has no Content-Transfer-Encoding: header. + +--BOUNDARY-- diff --git a/Lib/test/test_email/data/msg_11.txt b/Lib/test/test_email/data/msg_11.txt new file mode 100644 index 0000000..8f7f199 --- /dev/null +++ b/Lib/test/test_email/data/msg_11.txt @@ -0,0 +1,7 @@ +Content-Type: message/rfc822 +MIME-Version: 1.0 +Subject: The enclosing message + +Subject: An enclosed message + +Here is the body of the message. diff --git a/Lib/test/test_email/data/msg_12.txt b/Lib/test/test_email/data/msg_12.txt new file mode 100644 index 0000000..4bec8d9 --- /dev/null +++ b/Lib/test/test_email/data/msg_12.txt @@ -0,0 +1,36 @@ +MIME-Version: 1.0 +From: Barry Warsaw <barry@zope.com> +To: Dingus Lovers <cravindogs@cravindogs.com> +Subject: Lyrics +Date: Fri, 20 Apr 2001 19:35:02 -0400 +Content-Type: multipart/mixed; boundary="BOUNDARY" + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" + + +--BOUNDARY +Content-Type: text/html; charset="iso-8859-1" + + +--BOUNDARY +Content-Type: multipart/mixed; boundary="ANOTHER" + +--ANOTHER +Content-Type: text/plain; charset="iso-8859-2" + + +--ANOTHER +Content-Type: text/plain; charset="iso-8859-3" + +--ANOTHER-- + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" + + +--BOUNDARY +Content-Type: text/plain; charset="koi8-r" + + +--BOUNDARY-- diff --git a/Lib/test/test_email/data/msg_12a.txt b/Lib/test/test_email/data/msg_12a.txt new file mode 100644 index 0000000..e94224e --- /dev/null +++ b/Lib/test/test_email/data/msg_12a.txt @@ -0,0 +1,38 @@ +MIME-Version: 1.0 +From: Barry Warsaw <barry@zope.com> +To: Dingus Lovers <cravindogs@cravindogs.com> +Subject: Lyrics +Date: Fri, 20 Apr 2001 19:35:02 -0400 +Content-Type: multipart/mixed; boundary="BOUNDARY" + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" + + +--BOUNDARY +Content-Type: text/html; charset="iso-8859-1" + + +--BOUNDARY +Content-Type: multipart/mixed; boundary="ANOTHER" + +--ANOTHER +Content-Type: text/plain; charset="iso-8859-2" + + +--ANOTHER +Content-Type: text/plain; charset="iso-8859-3" + + +--ANOTHER-- + + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" + + +--BOUNDARY +Content-Type: text/plain; charset="koi8-r" + + +--BOUNDARY-- diff --git a/Lib/test/test_email/data/msg_13.txt b/Lib/test/test_email/data/msg_13.txt new file mode 100644 index 0000000..8e6d52d --- /dev/null +++ b/Lib/test/test_email/data/msg_13.txt @@ -0,0 +1,94 @@ +MIME-Version: 1.0 +From: Barry <barry@digicool.com> +To: Dingus Lovers <cravindogs@cravindogs.com> +Subject: Here is your dingus fish +Date: Fri, 20 Apr 2001 19:35:02 -0400 +Content-Type: multipart/mixed; boundary="OUTER" + +--OUTER +Content-Type: text/plain; charset="us-ascii" + +A text/plain part + +--OUTER +Content-Type: multipart/mixed; boundary=BOUNDARY + + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" + +Hi there, + +This is the dingus fish. + +--BOUNDARY +Content-Type: image/gif; name="dingusfish.gif" +Content-Transfer-Encoding: base64 +content-disposition: attachment; filename="dingusfish.gif" + +R0lGODdhAAEAAfAAAP///wAAACwAAAAAAAEAAQAC/oSPqcvtD6OctNqLs968+w+G4kiW5omm6sq2 +7gvH8kzX9o3n+s73/g8MCofEovGITGICTKbyCV0FDNOo9SqpQqpOrJfXzTQj2vD3TGtqL+NtGQ2f +qTXmxzuOd7WXdcc9DyjU53ewFni4s0fGhdiYaEhGBelICTNoV1j5NUnFcrmUqemjNifJVWpaOqaI +oFq3SspZsSraE7sHq3jr1MZqWvi662vxV4tD+pvKW6aLDOCLyur8PDwbanyDeq0N3DctbQYeLDvR +RY6t95m6UB0d3mwIrV7e2VGNvjjffukeJp4w7F65KecGFsTHQGAygOrgrWs1jt28Rc88KESYcGLA +/obvTkH6p+CinWJiJmIMqXGQwH/y4qk0SYjgQTczT3ajKZGfuI0uJ4kkVI/DT5s3/ejkxI0aT4Y+ +YTYgWbImUaXk9nlLmnSh1qJiJFl0OpUqRK4oOy7NyRQtHWofhoYVxkwWXKUSn0YsS+fUV6lhqfYb +6ayd3Z5qQdG1B7bvQzaJjwUV2lixMUZ7JVsOlfjWVr/3NB/uFvnySBN6Dcb6rGwaRM3wsormw5cC +M9NxWy/bWdufudCvy8bOAjXjVVwta/uO21sE5RHBCzNFXtgq9ORtH4eYjVP4Yryo026nvkFmCeyA +B29efV6ravCMK5JwWd5897Qrx7ll38o6iHDZ/rXPR//feevhF4l7wjUGX3xq1eeRfM4RSJGBIV1D +z1gKPkfWag3mVBVvva1RlX5bAJTPR/2YqNtw/FkIYYEi/pIZiAdpcxpoHtmnYYoZtvhUftzdx5ZX +JSKDW405zkGcZzzGZ6KEv4FI224oDmijlEf+xp6MJK5ojY/ASeVUR+wsKRuJ+XFZ5o7ZeEime8t1 +ouUsU6YjF5ZtUihhkGfCdFQLWQFJ3UXxmElfhQnR+eCdcDbkFZp6vTRmj56ApCihn5QGpaToNZmR +n3NVSpZcQpZ2KEONusaiCsKAug0wkQbJSFO+PTSjneGxOuFjPlUk3ovWvdIerjUg9ZGIOtGq/qeX +eCYrrCX+1UPsgTKGGRSbzd5q156d/gpfbJxe66eD5iQKrXj7RGgruGxs62qebBHUKS32CKluCiqZ +qh+pmehmEb71noAUoe5e9Zm17S7773V10pjrtG4CmuurCV/n6zLK5turWNhqOvFXbjhZrMD0YhKe +wR0zOyuvsh6MWrGoIuzvyWu5y1WIFAqmJselypxXh6dKLNOKEB98L88bS2rkNqqlKzCNJp9c0G0j +Gzh0iRrCbHSXmPR643QS+4rWhgFmnSbSuXCjS0xAOWkU2UdLqyuUNfHSFdUouy3bm5i5GnDM3tG8 +doJ4r5tqu3pPbRSVfvs8uJzeNXhp3n4j/tZ42SwH7eaWUUOjc3qFV9453UHTXZfcLH+OeNs5g36x +lBnHvTm7EbMbLeuaLncao8vWCXimfo1o+843Ak6y4ChNeGntvAYvfLK4ezmoyNIbNCLTCXO9ZV3A +E8/s88RczPzDwI4Ob7XZyl7+9Miban29h+tJZPrE21wgvBphDfrrfPdCTPKJD/y98L1rZwHcV6Jq +Zab0metpuNIX/qAFPoz171WUaUb4HAhBSzHuHfjzHb3kha/2Cctis/ORArVHNYfFyYRH2pYIRzic +isVOfPWD1b6mRTqpCRBozzof6UZVvFXRxWIr3GGrEviGYgyPMfahheiSaLs/9QeFu7oZ/ndSY8DD +ya9x+uPed+7mxN2IzIISBOMLFYWVqC3Pew1T2nFuuCiwZS5/v6II10i4t1OJcUH2U9zxKodHsGGv +Oa+zkvNUYUOa/TCCRutF9MzDwdlUMJADTCGSbDQ5OV4PTamDoPEi6Ecc/RF5RWwkcdSXvSOaDWSn +I9LlvubFTQpuc6JKXLcKeb+xdbKRBnwREemXyjg6ME65aJiOuBgrktzykfPLJBKR9ClMavJ62/Ff +BlNIyod9yX9wcSXexnXFpvkrbXk64xsx5Db7wXKP5fSgsvwIMM/9631VLBfkmtbHRXpqmtei52hG +pUwSlo+BASQoeILDOBgREECxBBh5/iYmNsQ9dIv5+OI++QkqdsJPc3uykz5fkM+OraeekcQF7X4n +B5S67za5U967PmooGQhUXfF7afXyCD7ONdRe17QogYjVx38uLwtrS6nhTnm15LQUnu9E2uK6CNI/ +1HOABj0ESwOjut4FEpFQpdNAm4K2LHnDWHNcmKB2ioKBogysVZtMO2nSxUdZ8Yk2kJc7URioLVI0 +YgmtIwZj4LoeKemgnOnbUdGnzZ4Oa6scqiolBGqS6RgWNLu0RMhcaE6rhhU4hiuqFXPAG8fGwTPW +FKeLMtdVmXLSs5YJGF/YeVm7rREMlY3UYE+yCxbaMXX8y15m5zVHq6GOKDMynzII/jdUHdyVqIy0 +ifX2+r/EgtZcvRzSb72gU9ui87M2VecjKildW/aFqaYhKoryUjfB/g4qtyVuc60xFDGmCxwjW+qu +zjuwl2GkOWn66+3QiiEctvd04OVvcCVzjgT7lrkvjVGKKHmmlDUKowSeikb5kK/mJReuWOxONx+s +ULsl+Lqb0CVn0SrVyJ6wt4t6yTeSCafhPhAf0OXn6L60UMxiLolFAtmN35S2Ob1lZpQ1r/n0Qb5D +oQ1zJiRVDgF8N3Q8TYfbi3DyWCy3lT1nxyBs6FT3S2GOzWRlxwKvlRP0RPJA9SjxEy0UoEnkA+M4 +cnzLMJrBGWLFEaaUb5lvpqbq/loOaU5+DFuHPxo82/OZuM8FXG3oVNZhtWpMpb/0Xu5m/LfLhHZQ +7yuVI0MqZ7NE43imC8jH3IwGZlbPm0xkJYs7+2U48hXTsFSMqgGDvai0kLxyynKNT/waj+q1c1tz +GjOpPBgdCSq3UKZxCSsqFIY+O6JbAWGWcV1pwqLyj5sGqCF1xb1F3varUWqrJv6cN3PrUXzijtfZ +FshpBL3Xwr4GIPvU2N8EjrJgS1zl21rbXQMXeXc5jjFyrhpCzijSv/RQtyPSzHCFMhlME95fHglt +pRsX+dfSQjUeHAlpWzJ5iOo79Ldnaxai6bXTcGO3fp07ri7HLEmXXPlYi8bv/qVxvNcdra6m7Rlb +6JBTb5fd66VhFRjGArh2n7R1rDW4P5NOT9K0I183T2scYkeZ3q/VFyLb09U9ajzXBS8Kgkhc4mBS +kYY9cy3Vy9lUnuNJH8HGIclUilwnBtjUOH0gteGOZ4c/XNrhXLSYDyxfnD8z1pDy7rYRvDolhnbe +UMzxCZUs40s6s7UIvBnLgc0+vKuOkIXeOrDymlp+Zxra4MZLBbVrqD/jTJ597pDmnw5c4+DbyB88 +9Cg9DodYcSuMZT/114pptqc/EuTjRPvH/z5slzI3tluOEBBLqOXLOX+0I5929tO97wkvl/atCz+y +xJrdwteW2FNW/NSmBP+f/maYtVs/bYyBC7Ox3jsYZHL05CIrBa/nS+b3bHfiYm4Ueil1YZZSgAUI +fFZ1dxUmeA2oQRQ3RuGXNGLFV9/XbGFGPV6kfzk1TBBCd+izc7q1H+OHMJwmaBX2IQNYVAKHYepV +SSGCe6CnbYHHETKGNe43EDvFgZr0gB/nVHPHZ80VV1ojOiI3XDvYIkl4ayo4bxQIgrFXWTvBI0nH +VElWMuw2aLUWCRHHf8ymVCHjFlJnOSojfevCYyyyZDH0IcvHhrsnQ5O1OsWzONuVVKIxSxiFZ/tR +fKDAf6xFTnw4O9Qig2VCfW2hJQrmMOuHW0W3dLQmCMO2ccdUd/xyfflH/olTiHZVdGwb8nIwRzSE +J15jFlOJuBZBZ4CiyHyd2IFylFlB+HgHhYabhWOGwYO1ZH/Og1dtQlFMk352CGRSIFTapnWQEUtN +l4zv8S0aaCFDyGCBqDUxZYpxGHX01y/JuH1xhn7TOCnNCI4eKDs5WGX4R425F4vF1o3BJ4vO0otq +I3rimI7jJY1jISqnBxknCIvruF83mF5wN4X7qGLIhR8A2Vg0yFERSIXn9Vv3GHy3Vj/WIkKddlYi +yIMv2I/VMjTLpW7pt05SWIZR0RPyxpB4SIUM9lBPGBl0GC7oSEEwRYLe4pJpZY2P0zbI1n+Oc44w +qY3PUnmF0ixjVpDD/mJ9wpOBGTVgXlaCaZiPcIWK5NiKBIiPdGaQ0TWGvAiG7nMchdZb7Vgf8zNi +MuMyzRdy/lePe9iC4TRx7WhhOQI/QiSVNAmAa2lT/piFbuh7ofJoYSZzrSZ1bvmWw3eN2nKUPVky +uPN5/VRfohRd0VYZoqhKIlU6TXYhJxmPUIloAwc1bPmHEpaZYZORHNlXUJM07hATwHR8MJYqkwWR +WaIezFhxSFlc8/Fq82hEnpeRozg3ULhhr9lAGtVEkCg5ZNRuuVleBPaZadhG0ZgkyPmDOTOKzViM +YgOcpukKqQcbjAWS0IleQ2ROjdh6A+md1qWdBRSX7iSYgFRTtRmBpJioieXJiHfJiMGIR9fJOn8I +MSfXYhspn4ooSa2mSAj4n+8Bmg03fBJZoPOJgsVZRxu1oOMRPXYYjdqjihFaEoZpXBREanuJoRI6 +cibFinq4ngUKh/wQd/H5ofYCZ0HJXR62opZFaAT0iFIZo4DIiUojkjeqKiuoZirKo5Y1a7AWckGa +BkuYoD5lpDK6eUs6CkDqpETwl1EqpfhJpVeKpVl6EgUAADs= + +--BOUNDARY-- + +--OUTER-- diff --git a/Lib/test/test_email/data/msg_14.txt b/Lib/test/test_email/data/msg_14.txt new file mode 100644 index 0000000..5d98d2f --- /dev/null +++ b/Lib/test/test_email/data/msg_14.txt @@ -0,0 +1,23 @@ +Return-Path: <bbb@zzz.org> +Delivered-To: bbb@zzz.org +Received: by mail.zzz.org (Postfix, from userid 889) + id 27CEAD38CC; Fri, 4 May 2001 14:05:44 -0400 (EDT) +MIME-Version: 1.0 +Content-Type: text; charset=us-ascii +Content-Transfer-Encoding: 7bit +Message-ID: <15090.61304.110929.45684@aaa.zzz.org> +From: bbb@ddd.com (John X. Doe) +To: bbb@zzz.org +Subject: This is a test message +Date: Fri, 4 May 2001 14:05:44 -0400 + + +Hi, + +I'm sorry but I'm using a drainbread ISP, which although big and +wealthy can't seem to generate standard compliant email. :( + +This message has a Content-Type: header with no subtype. I hope you +can still read it. + +-Me diff --git a/Lib/test/test_email/data/msg_15.txt b/Lib/test/test_email/data/msg_15.txt new file mode 100644 index 0000000..0025624 --- /dev/null +++ b/Lib/test/test_email/data/msg_15.txt @@ -0,0 +1,52 @@ +Return-Path: <xx@xx.dk> +Received: from fepD.post.tele.dk (195.41.46.149) by mail.groupcare.dk (LSMTP for Windows NT v1.1b) with SMTP id <0.0014F8A2@mail.groupcare.dk>; Mon, 30 Apr 2001 12:17:50 +0200 +User-Agent: Microsoft-Outlook-Express-Macintosh-Edition/5.02.2106 +Subject: XX +From: xx@xx.dk +To: XX +Message-ID: <xxxx> +Mime-version: 1.0 +Content-type: multipart/mixed; + boundary="MS_Mac_OE_3071477847_720252_MIME_Part" + +> Denne meddelelse er i MIME-format. Da dit postl + +--MS_Mac_OE_3071477847_720252_MIME_Part +Content-type: multipart/alternative; + boundary="MS_Mac_OE_3071477847_720252_MIME_Part" + + +--MS_Mac_OE_3071477847_720252_MIME_Part +Content-type: text/plain; charset="ISO-8859-1" +Content-transfer-encoding: quoted-printable + +Some removed test. + +--MS_Mac_OE_3071477847_720252_MIME_Part +Content-type: text/html; charset="ISO-8859-1" +Content-transfer-encoding: quoted-printable + +<HTML> +<HEAD> +<TITLE>Some removed HTML</TITLE> +</HEAD> +<BODY> +Some removed text. +</BODY> +</HTML> + + +--MS_Mac_OE_3071477847_720252_MIME_Part-- + + +--MS_Mac_OE_3071477847_720252_MIME_Part +Content-type: image/gif; name="xx.gif"; + x-mac-creator="6F676C65"; + x-mac-type="47494666" +Content-disposition: attachment +Content-transfer-encoding: base64 + +Some removed base64 encoded chars. + +--MS_Mac_OE_3071477847_720252_MIME_Part-- + diff --git a/Lib/test/test_email/data/msg_16.txt b/Lib/test/test_email/data/msg_16.txt new file mode 100644 index 0000000..56167e9 --- /dev/null +++ b/Lib/test/test_email/data/msg_16.txt @@ -0,0 +1,123 @@ +Return-Path: <> +Delivered-To: scr-admin@socal-raves.org +Received: from cougar.noc.ucla.edu (cougar.noc.ucla.edu [169.232.10.18]) + by babylon.socal-raves.org (Postfix) with ESMTP id CCC2C51B84 + for <scr-admin@socal-raves.org>; Sun, 23 Sep 2001 20:13:54 -0700 (PDT) +Received: from sims-ms-daemon by cougar.noc.ucla.edu + (Sun Internet Mail Server sims.3.5.2000.03.23.18.03.p10) + id <0GK500B01D0B8Y@cougar.noc.ucla.edu> for scr-admin@socal-raves.org; Sun, + 23 Sep 2001 20:14:35 -0700 (PDT) +Received: from cougar.noc.ucla.edu + (Sun Internet Mail Server sims.3.5.2000.03.23.18.03.p10) + id <0GK500B01D0B8X@cougar.noc.ucla.edu>; Sun, 23 Sep 2001 20:14:35 -0700 (PDT) +Date: Sun, 23 Sep 2001 20:14:35 -0700 (PDT) +From: Internet Mail Delivery <postmaster@ucla.edu> +Subject: Delivery Notification: Delivery has failed +To: scr-admin@socal-raves.org +Message-id: <0GK500B04D0B8X@cougar.noc.ucla.edu> +MIME-version: 1.0 +Sender: scr-owner@socal-raves.org +Errors-To: scr-owner@socal-raves.org +X-BeenThere: scr@socal-raves.org +X-Mailman-Version: 2.1a3 +Precedence: bulk +List-Help: <mailto:scr-request@socal-raves.org?subject=help> +List-Post: <mailto:scr@socal-raves.org> +List-Subscribe: <http://socal-raves.org/mailman/listinfo/scr>, + <mailto:scr-request@socal-raves.org?subject=subscribe> +List-Id: SoCal-Raves <scr.socal-raves.org> +List-Unsubscribe: <http://socal-raves.org/mailman/listinfo/scr>, + <mailto:scr-request@socal-raves.org?subject=unsubscribe> +List-Archive: <http://socal-raves.org/mailman/private/scr/> +Content-Type: multipart/report; boundary="Boundary_(ID_PGS2F2a+z+/jL7hupKgRhA)" + + +--Boundary_(ID_PGS2F2a+z+/jL7hupKgRhA) +Content-type: text/plain; charset=ISO-8859-1 + +This report relates to a message you sent with the following header fields: + + Message-id: <002001c144a6$8752e060$56104586@oxy.edu> + Date: Sun, 23 Sep 2001 20:10:55 -0700 + From: "Ian T. Henry" <henryi@oxy.edu> + To: SoCal Raves <scr@socal-raves.org> + Subject: [scr] yeah for Ians!! + +Your message cannot be delivered to the following recipients: + + Recipient address: jangel1@cougar.noc.ucla.edu + Reason: recipient reached disk quota + + +--Boundary_(ID_PGS2F2a+z+/jL7hupKgRhA) +Content-type: message/DELIVERY-STATUS + +Original-envelope-id: 0GK500B4HD0888@cougar.noc.ucla.edu +Reporting-MTA: dns; cougar.noc.ucla.edu + +Action: failed +Status: 5.0.0 (recipient reached disk quota) +Original-recipient: rfc822;jangel1@cougar.noc.ucla.edu +Final-recipient: rfc822;jangel1@cougar.noc.ucla.edu + +--Boundary_(ID_PGS2F2a+z+/jL7hupKgRhA) +Content-type: MESSAGE/RFC822 + +Return-path: scr-admin@socal-raves.org +Received: from sims-ms-daemon by cougar.noc.ucla.edu + (Sun Internet Mail Server sims.3.5.2000.03.23.18.03.p10) + id <0GK500B01D0B8X@cougar.noc.ucla.edu>; Sun, 23 Sep 2001 20:14:35 -0700 (PDT) +Received: from panther.noc.ucla.edu by cougar.noc.ucla.edu + (Sun Internet Mail Server sims.3.5.2000.03.23.18.03.p10) + with ESMTP id <0GK500B4GD0888@cougar.noc.ucla.edu> for jangel1@sims-ms-daemon; + Sun, 23 Sep 2001 20:14:33 -0700 (PDT) +Received: from babylon.socal-raves.org + (ip-209-85-222-117.dreamhost.com [209.85.222.117]) + by panther.noc.ucla.edu (8.9.1a/8.9.1) with ESMTP id UAA09793 for + <jangel1@ucla.edu>; Sun, 23 Sep 2001 20:14:32 -0700 (PDT) +Received: from babylon (localhost [127.0.0.1]) by babylon.socal-raves.org + (Postfix) with ESMTP id D3B2951B70; Sun, 23 Sep 2001 20:13:47 -0700 (PDT) +Received: by babylon.socal-raves.org (Postfix, from userid 60001) + id A611F51B82; Sun, 23 Sep 2001 20:13:46 -0700 (PDT) +Received: from tiger.cc.oxy.edu (tiger.cc.oxy.edu [134.69.3.112]) + by babylon.socal-raves.org (Postfix) with ESMTP id ADA7351B70 for + <scr@socal-raves.org>; Sun, 23 Sep 2001 20:13:44 -0700 (PDT) +Received: from ent (n16h86.dhcp.oxy.edu [134.69.16.86]) + by tiger.cc.oxy.edu (8.8.8/8.8.8) with SMTP id UAA08100 for + <scr@socal-raves.org>; Sun, 23 Sep 2001 20:14:24 -0700 (PDT) +Date: Sun, 23 Sep 2001 20:10:55 -0700 +From: "Ian T. Henry" <henryi@oxy.edu> +Subject: [scr] yeah for Ians!! +Sender: scr-admin@socal-raves.org +To: SoCal Raves <scr@socal-raves.org> +Errors-to: scr-admin@socal-raves.org +Message-id: <002001c144a6$8752e060$56104586@oxy.edu> +MIME-version: 1.0 +X-Mailer: Microsoft Outlook Express 5.50.4522.1200 +Content-type: text/plain; charset=us-ascii +Precedence: bulk +Delivered-to: scr-post@babylon.socal-raves.org +Delivered-to: scr@socal-raves.org +X-Converted-To-Plain-Text: from multipart/alternative by demime 0.98e +X-Converted-To-Plain-Text: Alternative section used was text/plain +X-BeenThere: scr@socal-raves.org +X-Mailman-Version: 2.1a3 +List-Help: <mailto:scr-request@socal-raves.org?subject=help> +List-Post: <mailto:scr@socal-raves.org> +List-Subscribe: <http://socal-raves.org/mailman/listinfo/scr>, + <mailto:scr-request@socal-raves.org?subject=subscribe> +List-Id: SoCal-Raves <scr.socal-raves.org> +List-Unsubscribe: <http://socal-raves.org/mailman/listinfo/scr>, + <mailto:scr-request@socal-raves.org?subject=unsubscribe> +List-Archive: <http://socal-raves.org/mailman/private/scr/> + +I always love to find more Ian's that are over 3 years old!! + +Ian +_______________________________________________ +For event info, list questions, or to unsubscribe, see http://www.socal-raves.org/ + + + +--Boundary_(ID_PGS2F2a+z+/jL7hupKgRhA)-- + diff --git a/Lib/test/test_email/data/msg_17.txt b/Lib/test/test_email/data/msg_17.txt new file mode 100644 index 0000000..8d86e41 --- /dev/null +++ b/Lib/test/test_email/data/msg_17.txt @@ -0,0 +1,12 @@ +MIME-Version: 1.0 +From: Barry <barry@digicool.com> +To: Dingus Lovers <cravindogs@cravindogs.com> +Subject: Here is your dingus fish +Date: Fri, 20 Apr 2001 19:35:02 -0400 +Content-Type: multipart/mixed; boundary="BOUNDARY" + +Hi there, + +This is the dingus fish. + +[Non-text (image/gif) part of message omitted, filename dingusfish.gif] diff --git a/Lib/test/test_email/data/msg_18.txt b/Lib/test/test_email/data/msg_18.txt new file mode 100644 index 0000000..f9f4904 --- /dev/null +++ b/Lib/test/test_email/data/msg_18.txt @@ -0,0 +1,6 @@ +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit +X-Foobar-Spoink-Defrobnit: wasnipoop; giraffes="very-long-necked-animals"; + spooge="yummy"; hippos="gargantuan"; marshmallows="gooey" + diff --git a/Lib/test/test_email/data/msg_19.txt b/Lib/test/test_email/data/msg_19.txt new file mode 100644 index 0000000..49bf7fc --- /dev/null +++ b/Lib/test/test_email/data/msg_19.txt @@ -0,0 +1,43 @@ +Send Ppp mailing list submissions to + ppp@zzz.org + +To subscribe or unsubscribe via the World Wide Web, visit + http://www.zzz.org/mailman/listinfo/ppp +or, via email, send a message with subject or body 'help' to + ppp-request@zzz.org + +You can reach the person managing the list at + ppp-admin@zzz.org + +When replying, please edit your Subject line so it is more specific +than "Re: Contents of Ppp digest..." + +Today's Topics: + + 1. testing #1 (Barry A. Warsaw) + 2. testing #2 (Barry A. Warsaw) + 3. testing #3 (Barry A. Warsaw) + 4. testing #4 (Barry A. Warsaw) + 5. testing #5 (Barry A. Warsaw) + +hello + + +hello + + +hello + + +hello + + +hello + + + +_______________________________________________ +Ppp mailing list +Ppp@zzz.org +http://www.zzz.org/mailman/listinfo/ppp + diff --git a/Lib/test/test_email/data/msg_20.txt b/Lib/test/test_email/data/msg_20.txt new file mode 100644 index 0000000..1a6a887 --- /dev/null +++ b/Lib/test/test_email/data/msg_20.txt @@ -0,0 +1,22 @@ +Return-Path: <bbb@zzz.org> +Delivered-To: bbb@zzz.org +Received: by mail.zzz.org (Postfix, from userid 889) + id 27CEAD38CC; Fri, 4 May 2001 14:05:44 -0400 (EDT) +MIME-Version: 1.0 +Content-Type: text/plain; charset=us-ascii +Content-Transfer-Encoding: 7bit +Message-ID: <15090.61304.110929.45684@aaa.zzz.org> +From: bbb@ddd.com (John X. Doe) +To: bbb@zzz.org +Cc: ccc@zzz.org +CC: ddd@zzz.org +cc: eee@zzz.org +Subject: This is a test message +Date: Fri, 4 May 2001 14:05:44 -0400 + + +Hi, + +Do you like this message? + +-Me diff --git a/Lib/test/test_email/data/msg_21.txt b/Lib/test/test_email/data/msg_21.txt new file mode 100644 index 0000000..23590b2 --- /dev/null +++ b/Lib/test/test_email/data/msg_21.txt @@ -0,0 +1,20 @@ +From: aperson@dom.ain +To: bperson@dom.ain +Subject: Test +Content-Type: multipart/mixed; boundary="BOUNDARY" + +MIME message +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +One +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +Two +--BOUNDARY-- +End of MIME message diff --git a/Lib/test/test_email/data/msg_22.txt b/Lib/test/test_email/data/msg_22.txt new file mode 100644 index 0000000..af9de5f --- /dev/null +++ b/Lib/test/test_email/data/msg_22.txt @@ -0,0 +1,46 @@ +Mime-Version: 1.0 +Message-Id: <a05001902b7f1c33773e9@[134.84.183.138]> +Date: Tue, 16 Oct 2001 13:59:25 +0300 +To: a@example.com +From: b@example.com +Content-Type: multipart/mixed; boundary="============_-1208892523==_============" + +--============_-1208892523==_============ +Content-Type: text/plain; charset="us-ascii" ; format="flowed" + +Text text text. +--============_-1208892523==_============ +Content-Id: <a05001902b7f1c33773e9@[134.84.183.138].0.0> +Content-Type: image/jpeg; name="wibble.JPG" + ; x-mac-type="4A504547" + ; x-mac-creator="474B4F4E" +Content-Disposition: attachment; filename="wibble.JPG" +Content-Transfer-Encoding: base64 + +/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEB +AQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQH/wAALCAXABIEBAREA +g6bCjjw/pIZSjO6FWFpldjySOmCNrO7DBZibUXhTwtCixw+GtAijVdqxxaPp0aKvmGXa +qrbBQvms0mAMeYS/3iTV1dG0hHaRNK01XblnWxtVdjkHLMIgTyqnk9VB7CrP2KzIINpa +4O7I+zxYO9WV8jZg71Zlb+8rMDkEirAVQFAUAKAFAAAUAYAUDgADgY6DjpRtXj5RxjHA +4wQRj0wQCMdCAewpaKKK/9k= +--============_-1208892523==_============ +Content-Id: <a05001902b7f1c33773e9@[134.84.183.138].0.1> +Content-Type: image/jpeg; name="wibble2.JPG" + ; x-mac-type="4A504547" + ; x-mac-creator="474B4F4E" +Content-Disposition: attachment; filename="wibble2.JPG" +Content-Transfer-Encoding: base64 + +/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEB +AQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQH/wAALCAXABJ0BAREA +/8QAHwAAAQUBAQEBAQEAAAAAAAAAAAECAwQFBgcICQoL/8QAtRAAAgEDAwIEAwUFBAQA +W6NFJJBEkU10kKGTcWMDwxuU+0JHvk8qAtOpNwqSR0n8c3BlDyXHlqsUltHEiTvdXLxR +7vMiGDNJAJWkAMk8ZkCFp5G2oo5W++INrbQtNfTQxJAuXlupz9oS4d5Y1W+E2XlWZJJE +Y7LWYQxTLE1zuMbfBPxw8X2fibVdIbSbI6nLZxX635t9TjtYreWR7WGKJTLJFFKSlozO +0ShxIXM43uC3/9k= +--============_-1208892523==_============ +Content-Type: text/plain; charset="us-ascii" ; format="flowed" + +Text text text. +--============_-1208892523==_============-- + diff --git a/Lib/test/test_email/data/msg_23.txt b/Lib/test/test_email/data/msg_23.txt new file mode 100644 index 0000000..bb2e8ec --- /dev/null +++ b/Lib/test/test_email/data/msg_23.txt @@ -0,0 +1,8 @@ +From: aperson@dom.ain +Content-Type: multipart/mixed; boundary="BOUNDARY" + +--BOUNDARY +Content-Type: text/plain + +A message part +--BOUNDARY-- diff --git a/Lib/test/test_email/data/msg_24.txt b/Lib/test/test_email/data/msg_24.txt new file mode 100644 index 0000000..4e52339 --- /dev/null +++ b/Lib/test/test_email/data/msg_24.txt @@ -0,0 +1,10 @@ +Content-Type: multipart/mixed; boundary="BOUNDARY" +MIME-Version: 1.0 +Subject: A subject +To: aperson@dom.ain +From: bperson@dom.ain + +--BOUNDARY + + +--BOUNDARY-- diff --git a/Lib/test/test_email/data/msg_25.txt b/Lib/test/test_email/data/msg_25.txt new file mode 100644 index 0000000..9e35275 --- /dev/null +++ b/Lib/test/test_email/data/msg_25.txt @@ -0,0 +1,117 @@ +From MAILER-DAEMON Fri Apr 06 16:46:09 2001 +Received: from [204.245.199.98] (helo=zinfandel.lacita.com) + by www.linux.org.uk with esmtp (Exim 3.13 #1) + id 14lYR6-0008Iv-00 + for linuxuser-admin@www.linux.org.uk; Fri, 06 Apr 2001 16:46:09 +0100 +Received: from localhost (localhost) by zinfandel.lacita.com (8.7.3/8.6.10-MT4.00) with internal id JAB03225; Fri, 6 Apr 2001 09:23:06 -0800 (GMT-0800) +Date: Fri, 6 Apr 2001 09:23:06 -0800 (GMT-0800) +From: Mail Delivery Subsystem <MAILER-DAEMON@zinfandel.lacita.com> +Subject: Returned mail: Too many hops 19 (17 max): from <linuxuser-admin@www.linux.org.uk> via [199.164.235.226], to <scoffman@wellpartner.com> +Message-Id: <200104061723.JAB03225@zinfandel.lacita.com> +To: <linuxuser-admin@www.linux.org.uk> +To: postmaster@zinfandel.lacita.com +MIME-Version: 1.0 +Content-Type: multipart/report; report-type=delivery-status; + bo +Auto-Submitted: auto-generated (failure) + +This is a MIME-encapsulated message + +--JAB03225.986577786/zinfandel.lacita.com + +The original message was received at Fri, 6 Apr 2001 09:23:03 -0800 (GMT-0800) +from [199.164.235.226] + + ----- The following addresses have delivery notifications ----- +<scoffman@wellpartner.com> (unrecoverable error) + + ----- Transcript of session follows ----- +554 Too many hops 19 (17 max): from <linuxuser-admin@www.linux.org.uk> via [199.164.235.226], to <scoffman@wellpartner.com> + +--JAB03225.986577786/zinfandel.lacita.com +Content-Type: message/delivery-status + +Reporting-MTA: dns; zinfandel.lacita.com +Received-From-MTA: dns; [199.164.235.226] +Arrival-Date: Fri, 6 Apr 2001 09:23:03 -0800 (GMT-0800) + +Final-Recipient: rfc822; scoffman@wellpartner.com +Action: failed +Status: 5.4.6 +Last-Attempt-Date: Fri, 6 Apr 2001 09:23:06 -0800 (GMT-0800) + +--JAB03225.986577786/zinfandel.lacita.com +Content-Type: text/rfc822-headers + +Return-Path: linuxuser-admin@www.linux.org.uk +Received: from ns1.wellpartner.net ([199.164.235.226]) by zinfandel.lacita.com (8.7.3/8.6.10-MT4.00) with ESMTP id JAA03225 for <scoffman@wellpartner.com>; Fri, 6 Apr 2001 09:23:03 -0800 (GMT-0800) +Received: from zinfandel.lacita.com ([204.245.199.98]) + by + fo +Received: from ns1.wellpartner.net ([199.164.235.226]) by zinfandel.lacita.com (8.7.3/8.6.10-MT4.00) with ESMTP id JAA03221 for <scoffman@wellpartner.com>; Fri, 6 Apr 2001 09:22:18 -0800 (GMT-0800) +Received: from zinfandel.lacita.com ([204.245.199.98]) + by + fo +Received: from ns1.wellpartner.net ([199.164.235.226]) by zinfandel.lacita.com (8.7.3/8.6.10-MT4.00) with ESMTP id JAA03217 for <scoffman@wellpartner.com>; Fri, 6 Apr 2001 09:21:37 -0800 (GMT-0800) +Received: from zinfandel.lacita.com ([204.245.199.98]) + by + fo +Received: from ns1.wellpartner.net ([199.164.235.226]) by zinfandel.lacita.com (8.7.3/8.6.10-MT4.00) with ESMTP id JAA03213 for <scoffman@wellpartner.com>; Fri, 6 Apr 2001 09:20:56 -0800 (GMT-0800) +Received: from zinfandel.lacita.com ([204.245.199.98]) + by + fo +Received: from ns1.wellpartner.net ([199.164.235.226]) by zinfandel.lacita.com (8.7.3/8.6.10-MT4.00) with ESMTP id JAA03209 for <scoffman@wellpartner.com>; Fri, 6 Apr 2001 09:20:15 -0800 (GMT-0800) +Received: from zinfandel.lacita.com ([204.245.199.98]) + by + fo +Received: from ns1.wellpartner.net ([199.164.235.226]) by zinfandel.lacita.com (8.7.3/8.6.10-MT4.00) with ESMTP id JAA03205 for <scoffman@wellpartner.com>; Fri, 6 Apr 2001 09:19:33 -0800 (GMT-0800) +Received: from zinfandel.lacita.com ([204.245.199.98]) + by + fo +Received: from ns1.wellpartner.net ([199.164.235.226]) by zinfandel.lacita.com (8.7.3/8.6.10-MT4.00) with ESMTP id JAA03201 for <scoffman@wellpartner.com>; Fri, 6 Apr 2001 09:18:52 -0800 (GMT-0800) +Received: from zinfandel.lacita.com ([204.245.199.98]) + by + fo +Received: from ns1.wellpartner.net ([199.164.235.226]) by zinfandel.lacita.com (8.7.3/8.6.10-MT4.00) with ESMTP id JAA03197 for <scoffman@wellpartner.com>; Fri, 6 Apr 2001 09:17:54 -0800 (GMT-0800) +Received: from www.linux.org.uk (parcelfarce.linux.theplanet.co.uk [195.92.249.252]) + by + fo +Received: from localhost.localdomain + ([ + by + id +Received: from [212.1.130.11] (helo=s1.uklinux.net ident=root) + by + id + fo +Received: from server (ppp-2-22.cvx4.telinco.net [212.1.149.22]) + by + fo +From: Daniel James <daniel@linuxuser.co.uk> +Organization: LinuxUser +To: linuxuser@www.linux.org.uk +X-Mailer: KMail [version 1.1.99] +Content-Type: text/plain; + c +MIME-Version: 1.0 +Message-Id: <01040616033903.00962@server> +Content-Transfer-Encoding: 8bit +Subject: [LinuxUser] bulletin no. 45 +Sender: linuxuser-admin@www.linux.org.uk +Errors-To: linuxuser-admin@www.linux.org.uk +X-BeenThere: linuxuser@www.linux.org.uk +X-Mailman-Version: 2.0.3 +Precedence: bulk +List-Help: <mailto:linuxuser-request@www.linux.org.uk?subject=help> +List-Post: <mailto:linuxuser@www.linux.org.uk> +List-Subscribe: <http://www.linux.org.uk/mailman/listinfo/linuxuser>, + <m +List-Id: bulletins from LinuxUser magazine <linuxuser.www.linux.org.uk> +List-Unsubscribe: <http://www.linux.org.uk/mailman/listinfo/linuxuser>, + <m +List-Archive: <http://www.linux.org.uk/pipermail/linuxuser/> +Date: Fri, 6 Apr 2001 16:03:39 +0100 + +--JAB03225.986577786/zinfandel.lacita.com-- + + diff --git a/Lib/test/test_email/data/msg_26.txt b/Lib/test/test_email/data/msg_26.txt new file mode 100644 index 0000000..58efaa9 --- /dev/null +++ b/Lib/test/test_email/data/msg_26.txt @@ -0,0 +1,46 @@ +Received: from xcar [192.168.0.2] by jeeves.wooster.local
+ (SMTPD32-7.07 EVAL) id AFF92F0214; Sun, 12 May 2002 08:55:37 +0100
+Date: Sun, 12 May 2002 08:56:15 +0100
+From: Father Time <father.time@xcar.wooster.local>
+To: timbo@jeeves.wooster.local
+Subject: IMAP file test
+Message-ID: <6df65d354b.father.time@rpc.wooster.local>
+X-Organization: Home
+User-Agent: Messenger-Pro/2.50a (MsgServe/1.50) (RISC-OS/4.02) POPstar/2.03
+MIME-Version: 1.0
+Content-Type: multipart/mixed; boundary="1618492860--2051301190--113853680"
+Status: R
+X-UIDL: 319998302
+
+This message is in MIME format which your mailer apparently does not support.
+You either require a newer version of your software which supports MIME, or
+a separate MIME decoding utility. Alternatively, ask the sender of this
+message to resend it in a different format.
+
+--1618492860--2051301190--113853680
+Content-Type: text/plain; charset=us-ascii
+
+Simple email with attachment.
+
+
+--1618492860--2051301190--113853680
+Content-Type: application/riscos; name="clock.bmp,69c"; type=BMP;
+ load=&fff69c4b; exec=&355dd4d1; access=&03
+Content-Disposition: attachment; filename="clock.bmp"
+Content-Transfer-Encoding: base64
+
+Qk12AgAAAAAAAHYAAAAoAAAAIAAAACAAAAABAAQAAAAAAAAAAADXDQAA1w0AAAAAAAAA
+AAAAAAAAAAAAiAAAiAAAAIiIAIgAAACIAIgAiIgAALu7uwCIiIgAERHdACLuIgAz//8A
+zAAAAN0R3QDu7iIA////AAAAAAAAAAAAAAAAAAAAAAAAAAi3AAAAAAAAADeAAAAAAAAA
+C3ADMzMzMANwAAAAAAAAAAAHMAAAAANwAAAAAAAAAACAMAd3zPfwAwgAAAAAAAAIAwd/
+f8x/f3AwgAAAAAAAgDB0x/f3//zPAwgAAAAAAAcHfM9////8z/AwAAAAAAiwd/f3////
+////A4AAAAAAcEx/f///////zAMAAAAAiwfM9////3///8zwOAAAAAcHf3////B/////
+8DAAAAALB/f3///wd3d3//AwAAAABwTPf//wCQAAD/zAMAAAAAsEx/f///B////8wDAA
+AAAHB39////wf/////AwAAAACwf39///8H/////wMAAAAIcHfM9///B////M8DgAAAAA
+sHTH///wf///xAMAAAAACHB3f3//8H////cDgAAAAAALB3zH//D//M9wMAAAAAAAgLB0
+z39///xHAwgAAAAAAAgLB3d3RHd3cDCAAAAAAAAAgLAHd0R3cAMIAAAAAAAAgAgLcAAA
+AAMwgAgAAAAACDAAAAu7t7cwAAgDgAAAAABzcIAAAAAAAAgDMwAAAAAAN7uwgAAAAAgH
+MzMAAAAACH97tzAAAAALu3c3gAAAAAAL+7tzDABAu7f7cAAAAAAACA+3MA7EQAv/sIAA
+AAAAAAAIAAAAAAAAAIAAAAAA
+
+--1618492860--2051301190--113853680--
diff --git a/Lib/test/test_email/data/msg_27.txt b/Lib/test/test_email/data/msg_27.txt new file mode 100644 index 0000000..d019176 --- /dev/null +++ b/Lib/test/test_email/data/msg_27.txt @@ -0,0 +1,15 @@ +Return-Path: <aperson@dom.ain> +Received: by mail.dom.ain (Postfix, from userid 889) + id B9D0AD35DB; Tue, 4 Jun 2002 21:46:59 -0400 (EDT) +Message-ID: <15613.28051.707126.569693@dom.ain> +Date: Tue, 4 Jun 2002 21:46:59 -0400 +MIME-Version: 1.0 +Content-Type: text/plain; charset=us-ascii +Content-Transfer-Encoding: 7bit +Subject: bug demonstration + 12345678911234567892123456789312345678941234567895123456789612345678971234567898112345678911234567892123456789112345678911234567892123456789 + more text +From: aperson@dom.ain (Anne P. Erson) +To: bperson@dom.ain (Barney P. Erson) + +test diff --git a/Lib/test/test_email/data/msg_28.txt b/Lib/test/test_email/data/msg_28.txt new file mode 100644 index 0000000..1e4824c --- /dev/null +++ b/Lib/test/test_email/data/msg_28.txt @@ -0,0 +1,25 @@ +From: aperson@dom.ain +MIME-Version: 1.0 +Content-Type: multipart/digest; boundary=BOUNDARY + +--BOUNDARY +Content-Type: message/rfc822 + +Content-Type: text/plain; charset=us-ascii +To: aa@bb.org +From: cc@dd.org +Subject: ee + +message 1 + +--BOUNDARY +Content-Type: message/rfc822 + +Content-Type: text/plain; charset=us-ascii +To: aa@bb.org +From: cc@dd.org +Subject: ee + +message 2 + +--BOUNDARY-- diff --git a/Lib/test/test_email/data/msg_29.txt b/Lib/test/test_email/data/msg_29.txt new file mode 100644 index 0000000..1fab561 --- /dev/null +++ b/Lib/test/test_email/data/msg_29.txt @@ -0,0 +1,22 @@ +Return-Path: <bbb@zzz.org> +Delivered-To: bbb@zzz.org +Received: by mail.zzz.org (Postfix, from userid 889) + id 27CEAD38CC; Fri, 4 May 2001 14:05:44 -0400 (EDT) +MIME-Version: 1.0 +Content-Type: text/plain; charset=us-ascii; + title*0*="us-ascii'en'This%20is%20even%20more%20"; + title*1*="%2A%2A%2Afun%2A%2A%2A%20"; + title*2="isn't it!" +Content-Transfer-Encoding: 7bit +Message-ID: <15090.61304.110929.45684@aaa.zzz.org> +From: bbb@ddd.com (John X. Doe) +To: bbb@zzz.org +Subject: This is a test message +Date: Fri, 4 May 2001 14:05:44 -0400 + + +Hi, + +Do you like this message? + +-Me diff --git a/Lib/test/test_email/data/msg_30.txt b/Lib/test/test_email/data/msg_30.txt new file mode 100644 index 0000000..4334bb6 --- /dev/null +++ b/Lib/test/test_email/data/msg_30.txt @@ -0,0 +1,23 @@ +From: aperson@dom.ain +MIME-Version: 1.0 +Content-Type: multipart/digest; boundary=BOUNDARY + +--BOUNDARY + +Content-Type: text/plain; charset=us-ascii +To: aa@bb.org +From: cc@dd.org +Subject: ee + +message 1 + +--BOUNDARY + +Content-Type: text/plain; charset=us-ascii +To: aa@bb.org +From: cc@dd.org +Subject: ee + +message 2 + +--BOUNDARY-- diff --git a/Lib/test/test_email/data/msg_31.txt b/Lib/test/test_email/data/msg_31.txt new file mode 100644 index 0000000..1e58e56 --- /dev/null +++ b/Lib/test/test_email/data/msg_31.txt @@ -0,0 +1,15 @@ +From: aperson@dom.ain +MIME-Version: 1.0 +Content-Type: multipart/mixed; boundary=BOUNDARY_ + +--BOUNDARY +Content-Type: text/plain + +message 1 + +--BOUNDARY +Content-Type: text/plain + +message 2 + +--BOUNDARY-- diff --git a/Lib/test/test_email/data/msg_32.txt b/Lib/test/test_email/data/msg_32.txt new file mode 100644 index 0000000..07ec5af --- /dev/null +++ b/Lib/test/test_email/data/msg_32.txt @@ -0,0 +1,14 @@ +Delivered-To: freebsd-isp@freebsd.org +Date: Tue, 26 Sep 2000 12:23:03 -0500 +From: Anne Person <aperson@example.com> +To: Barney Dude <bdude@example.com> +Subject: Re: Limiting Perl CPU Utilization... +Mime-Version: 1.0 +Content-Type: text/plain; charset*=ansi-x3.4-1968''us-ascii +Content-Disposition: inline +User-Agent: Mutt/1.3.8i +Sender: owner-freebsd-isp@FreeBSD.ORG +Precedence: bulk +X-Loop: FreeBSD.org + +Some message. diff --git a/Lib/test/test_email/data/msg_33.txt b/Lib/test/test_email/data/msg_33.txt new file mode 100644 index 0000000..042787a --- /dev/null +++ b/Lib/test/test_email/data/msg_33.txt @@ -0,0 +1,29 @@ +Delivered-To: freebsd-isp@freebsd.org +Date: Wed, 27 Sep 2000 11:11:09 -0500 +From: Anne Person <aperson@example.com> +To: Barney Dude <bdude@example.com> +Subject: Re: Limiting Perl CPU Utilization... +Mime-Version: 1.0 +Content-Type: multipart/signed; micalg*=ansi-x3.4-1968''pgp-md5; + protocol*=ansi-x3.4-1968''application%2Fpgp-signature; + boundary*="ansi-x3.4-1968''EeQfGwPcQSOJBaQU" +Content-Disposition: inline +Sender: owner-freebsd-isp@FreeBSD.ORG +Precedence: bulk +X-Loop: FreeBSD.org + + +--EeQfGwPcQSOJBaQU +Content-Type: text/plain; charset*=ansi-x3.4-1968''us-ascii +Content-Disposition: inline +Content-Transfer-Encoding: quoted-printable + +part 1 + +--EeQfGwPcQSOJBaQU +Content-Type: text/plain +Content-Disposition: inline + +part 2 + +--EeQfGwPcQSOJBaQU-- diff --git a/Lib/test/test_email/data/msg_34.txt b/Lib/test/test_email/data/msg_34.txt new file mode 100644 index 0000000..055dfea --- /dev/null +++ b/Lib/test/test_email/data/msg_34.txt @@ -0,0 +1,19 @@ +From: aperson@dom.ain +To: bperson@dom.ain +Content-Type: multipart/digest; boundary=XYZ + +--XYZ +Content-Type: text/plain + + +This is a text plain part that is counter to recommended practice in +RFC 2046, $5.1.5, but is not illegal + +--XYZ + +From: cperson@dom.ain +To: dperson@dom.ain + +A submessage + +--XYZ-- diff --git a/Lib/test/test_email/data/msg_35.txt b/Lib/test/test_email/data/msg_35.txt new file mode 100644 index 0000000..be7d5a2 --- /dev/null +++ b/Lib/test/test_email/data/msg_35.txt @@ -0,0 +1,4 @@ +From: aperson@dom.ain +To: bperson@dom.ain +Subject: here's something interesting +counter to RFC 2822, there's no separating newline here diff --git a/Lib/test/test_email/data/msg_36.txt b/Lib/test/test_email/data/msg_36.txt new file mode 100644 index 0000000..5632c30 --- /dev/null +++ b/Lib/test/test_email/data/msg_36.txt @@ -0,0 +1,40 @@ +Mime-Version: 1.0 +Content-Type: Multipart/Mixed; Boundary="NextPart" +To: IETF-Announce:; +From: Internet-Drafts@ietf.org +Subject: I-D ACTION:draft-ietf-mboned-mix-00.txt +Date: Tue, 22 Dec 1998 16:55:06 -0500 + +--NextPart + +Blah blah blah + +--NextPart +Content-Type: Multipart/Alternative; Boundary="OtherAccess" + +--OtherAccess +Content-Type: Message/External-body; + access-type="mail-server"; + server="mailserv@ietf.org" + +Content-Type: text/plain +Content-ID: <19981222151406.I-D@ietf.org> + +ENCODING mime +FILE /internet-drafts/draft-ietf-mboned-mix-00.txt + +--OtherAccess +Content-Type: Message/External-body; + name="draft-ietf-mboned-mix-00.txt"; + site="ftp.ietf.org"; + access-type="anon-ftp"; + directory="internet-drafts" + +Content-Type: text/plain +Content-ID: <19981222151406.I-D@ietf.org> + + +--OtherAccess-- + +--NextPart-- + diff --git a/Lib/test/test_email/data/msg_37.txt b/Lib/test/test_email/data/msg_37.txt new file mode 100644 index 0000000..038d34a --- /dev/null +++ b/Lib/test/test_email/data/msg_37.txt @@ -0,0 +1,22 @@ +Content-Type: multipart/mixed; boundary=ABCDE + +--ABCDE +Content-Type: text/x-one + +Blah + +--ABCDE +--ABCDE +Content-Type: text/x-two + +Blah + +--ABCDE +--ABCDE +--ABCDE +--ABCDE +Content-Type: text/x-two + +Blah + +--ABCDE-- diff --git a/Lib/test/test_email/data/msg_38.txt b/Lib/test/test_email/data/msg_38.txt new file mode 100644 index 0000000..006df81 --- /dev/null +++ b/Lib/test/test_email/data/msg_38.txt @@ -0,0 +1,101 @@ +MIME-Version: 1.0 +Content-Type: multipart/mixed; boundary="----- =_aaaaaaaaaa0" + +------- =_aaaaaaaaaa0 +Content-Type: multipart/mixed; boundary="----- =_aaaaaaaaaa1" +Content-ID: <20592.1022586929.1@example.com> + +------- =_aaaaaaaaaa1 +Content-Type: multipart/alternative; boundary="----- =_aaaaaaaaaa2" +Content-ID: <20592.1022586929.2@example.com> + +------- =_aaaaaaaaaa2 +Content-Type: text/plain +Content-ID: <20592.1022586929.3@example.com> +Content-Description: very tricky +Content-Transfer-Encoding: 7bit + + +Unlike the test test_nested-multiples-with-internal-boundary, this +piece of text not only contains the outer boundary tags +------- =_aaaaaaaaaa1 +and +------- =_aaaaaaaaaa0 +but puts them at the start of a line! And, to be even nastier, it +even includes a couple of end tags, such as this one: + +------- =_aaaaaaaaaa1-- + +and this one, which is from a multipart we haven't even seen yet! + +------- =_aaaaaaaaaa4-- + +This will, I'm sure, cause much breakage of MIME parsers. But, as +far as I can tell, it's perfectly legal. I have not yet ever seen +a case of this in the wild, but I've seen *similar* things. + + +------- =_aaaaaaaaaa2 +Content-Type: application/octet-stream +Content-ID: <20592.1022586929.4@example.com> +Content-Description: patch2 +Content-Transfer-Encoding: base64 + +XXX + +------- =_aaaaaaaaaa2-- + +------- =_aaaaaaaaaa1 +Content-Type: multipart/alternative; boundary="----- =_aaaaaaaaaa3" +Content-ID: <20592.1022586929.6@example.com> + +------- =_aaaaaaaaaa3 +Content-Type: application/octet-stream +Content-ID: <20592.1022586929.7@example.com> +Content-Description: patch3 +Content-Transfer-Encoding: base64 + +XXX + +------- =_aaaaaaaaaa3 +Content-Type: application/octet-stream +Content-ID: <20592.1022586929.8@example.com> +Content-Description: patch4 +Content-Transfer-Encoding: base64 + +XXX + +------- =_aaaaaaaaaa3-- + +------- =_aaaaaaaaaa1 +Content-Type: multipart/alternative; boundary="----- =_aaaaaaaaaa4" +Content-ID: <20592.1022586929.10@example.com> + +------- =_aaaaaaaaaa4 +Content-Type: application/octet-stream +Content-ID: <20592.1022586929.11@example.com> +Content-Description: patch5 +Content-Transfer-Encoding: base64 + +XXX + +------- =_aaaaaaaaaa4 +Content-Type: application/octet-stream +Content-ID: <20592.1022586929.12@example.com> +Content-Description: patch6 +Content-Transfer-Encoding: base64 + +XXX + +------- =_aaaaaaaaaa4-- + +------- =_aaaaaaaaaa1-- + +------- =_aaaaaaaaaa0 +Content-Type: text/plain; charset="us-ascii" +Content-ID: <20592.1022586929.15@example.com> + +-- +It's never too late to have a happy childhood. + +------- =_aaaaaaaaaa0-- diff --git a/Lib/test/test_email/data/msg_39.txt b/Lib/test/test_email/data/msg_39.txt new file mode 100644 index 0000000..124b269 --- /dev/null +++ b/Lib/test/test_email/data/msg_39.txt @@ -0,0 +1,83 @@ +MIME-Version: 1.0 +Content-Type: multipart/mixed; boundary="----- =_aaaaaaaaaa0" + +------- =_aaaaaaaaaa0 +Content-Type: multipart/mixed; boundary="----- =_aaaaaaaaaa1" +Content-ID: <20592.1022586929.1@example.com> + +------- =_aaaaaaaaaa1 +Content-Type: multipart/alternative; boundary="----- =_aaaaaaaaaa1" +Content-ID: <20592.1022586929.2@example.com> + +------- =_aaaaaaaaaa1 +Content-Type: application/octet-stream +Content-ID: <20592.1022586929.3@example.com> +Content-Description: patch1 +Content-Transfer-Encoding: base64 + +XXX + +------- =_aaaaaaaaaa1 +Content-Type: application/octet-stream +Content-ID: <20592.1022586929.4@example.com> +Content-Description: patch2 +Content-Transfer-Encoding: base64 + +XXX + +------- =_aaaaaaaaaa1-- + +------- =_aaaaaaaaaa1 +Content-Type: multipart/alternative; boundary="----- =_aaaaaaaaaa1" +Content-ID: <20592.1022586929.6@example.com> + +------- =_aaaaaaaaaa1 +Content-Type: application/octet-stream +Content-ID: <20592.1022586929.7@example.com> +Content-Description: patch3 +Content-Transfer-Encoding: base64 + +XXX + +------- =_aaaaaaaaaa1 +Content-Type: application/octet-stream +Content-ID: <20592.1022586929.8@example.com> +Content-Description: patch4 +Content-Transfer-Encoding: base64 + +XXX + +------- =_aaaaaaaaaa1-- + +------- =_aaaaaaaaaa1 +Content-Type: multipart/alternative; boundary="----- =_aaaaaaaaaa1" +Content-ID: <20592.1022586929.10@example.com> + +------- =_aaaaaaaaaa1 +Content-Type: application/octet-stream +Content-ID: <20592.1022586929.11@example.com> +Content-Description: patch5 +Content-Transfer-Encoding: base64 + +XXX + +------- =_aaaaaaaaaa1 +Content-Type: application/octet-stream +Content-ID: <20592.1022586929.12@example.com> +Content-Description: patch6 +Content-Transfer-Encoding: base64 + +XXX + +------- =_aaaaaaaaaa1-- + +------- =_aaaaaaaaaa1-- + +------- =_aaaaaaaaaa0 +Content-Type: text/plain; charset="us-ascii" +Content-ID: <20592.1022586929.15@example.com> + +-- +It's never too late to have a happy childhood. + +------- =_aaaaaaaaaa0-- diff --git a/Lib/test/test_email/data/msg_40.txt b/Lib/test/test_email/data/msg_40.txt new file mode 100644 index 0000000..1435fa1 --- /dev/null +++ b/Lib/test/test_email/data/msg_40.txt @@ -0,0 +1,10 @@ +MIME-Version: 1.0 +Content-Type: text/html; boundary="--961284236552522269" + +----961284236552522269 +Content-Type: text/html; +Content-Transfer-Encoding: 7Bit + +<html></html> + +----961284236552522269-- diff --git a/Lib/test/test_email/data/msg_41.txt b/Lib/test/test_email/data/msg_41.txt new file mode 100644 index 0000000..76cdd1c --- /dev/null +++ b/Lib/test/test_email/data/msg_41.txt @@ -0,0 +1,8 @@ +From: "Allison Dunlap" <xxx@example.com> +To: yyy@example.com +Subject: 64423 +Date: Sun, 11 Jul 2004 16:09:27 -0300 +MIME-Version: 1.0 +Content-Type: multipart/alternative; + +Blah blah blah diff --git a/Lib/test/test_email/data/msg_42.txt b/Lib/test/test_email/data/msg_42.txt new file mode 100644 index 0000000..a75f8f4 --- /dev/null +++ b/Lib/test/test_email/data/msg_42.txt @@ -0,0 +1,20 @@ +Content-Type: multipart/mixed; boundary="AAA" +From: Mail Delivery Subsystem <xxx@example.com> +To: yyy@example.com + +This is a MIME-encapsulated message + +--AAA + +Stuff + +--AAA +Content-Type: message/rfc822 + +From: webmaster@python.org +To: zzz@example.com +Content-Type: multipart/mixed; boundary="BBB" + +--BBB-- + +--AAA-- diff --git a/Lib/test/test_email/data/msg_43.txt b/Lib/test/test_email/data/msg_43.txt new file mode 100644 index 0000000..797d12c --- /dev/null +++ b/Lib/test/test_email/data/msg_43.txt @@ -0,0 +1,217 @@ +From SRS0=aO/p=ON=bag.python.org=None@bounce2.pobox.com Fri Nov 26 21:40:36 2004 +X-VM-v5-Data: ([nil nil nil nil nil nil nil nil nil] + [nil nil nil nil nil nil nil "MAILER DAEMON <>" "MAILER DAEMON <>" nil nil "Banned file: auto__mail.python.bat in mail from you" "^From:" nil nil nil nil "Banned file: auto__mail.python.bat in mail from you" nil nil nil nil nil nil nil] + nil) +MIME-Version: 1.0 +Message-Id: <edab.7804f5cb8070@python.org> +Content-Type: multipart/report; report-type=delivery-status; + charset=utf-8; + boundary="----------=_1101526904-1956-5" +X-Virus-Scanned: by XS4ALL Virus Scanner +X-UIDL: 4\G!!!<c"!UV["!M7C!! +From: MAILER DAEMON <> +To: <webmaster@python.org> +Subject: Banned file: auto__mail.python.bat in mail from you +Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +This is a multi-part message in MIME format... + +------------=_1101526904-1956-5 +Content-Type: text/plain; charset="utf-8" +Content-Disposition: inline +Content-Transfer-Encoding: 7bit + +BANNED FILENAME ALERT + +Your message to: xxxxxxx@dot.ca.gov, xxxxxxxxxxxxx@dot.ca.gov, xxxxxxxxxx@dot.ca.gov, xxxxxxxx@dot.ca.gov, xxxxxxxxxx@dot.ca.gov, xxxxxx@dot.ca.gov, xxxxxxxxxx@dot.ca.gov, xxxxxx@dot.ca.gov, xxxxxx@dot.ca.gov, xxxxxxxxxxxxxxxx@dot.ca.gov, xxxxxxxxxxx@dot.ca.gov, xxxxxxxxxx@dot.ca.gov, xxxxxxxxxx@dot.ca.gov, xxxxxxxxxxxx@dot.ca.gov, xxxxxxxxxxxx@dot.ca.gov, xxxxxxx@dot.ca.gov, xxxxxxxxx@dot.ca.gov, xxxxxxxxxx@dot.ca.gov, xxxxxx@dot.ca.gov, xxx@dot.ca.gov, xxxxxxx@dot.ca.gov, xxxxxxx@dot.ca.gov, xxxxxxxxxxxxxxx@dot.ca.gov, xxxxxxxxxx@dot.ca.gov, xxxxxxx@dot.ca.gov, xxx@dot.ca.gov, xxxxxxxx@dot.ca.gov, xxxxxxxxxxxxx@dot.ca.gov, xxxxxxxxxxxxx@dot.ca.gov, xxxxxxxxxxx@dot.ca.gov, xxxxxxxxx@dot.ca.gov, xxxxxxxxxx@dot.ca.gov, xxxxxxxxxxxx@dot.ca.gov, xxxxxxx@dot.ca.gov, xxxxxxxxxxxxxxx@dot.ca.gov, xxxxxxxxxxxxx@dot.ca.gov, xxxx@dot.ca.gov, xxxxxxxx@dot.ca.gov, xxxxxxxxxx@dot.ca.gov, xxxxxxxxxxxxxxxxxx@dot.ca.gov +was blocked by our Spam Firewall. The email you sent with the following subject has NOT BEEN DELIVERED: + +Subject: Delivery_failure_notice + +An attachment in that mail was of a file type that the Spam Firewall is set to block. + + + +------------=_1101526904-1956-5 +Content-Type: message/delivery-status +Content-Disposition: inline +Content-Transfer-Encoding: 7bit +Content-Description: Delivery error report + +Reporting-MTA: dns; sacspam01.dot.ca.gov +Received-From-MTA: smtp; sacspam01.dot.ca.gov ([127.0.0.1]) +Arrival-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +Final-Recipient: rfc822; xxxxxxx@dot.ca.gov +Action: failed +Status: 5.7.1 +Diagnostic-Code: smtp; 550 5.7.1 Message content rejected, id=01956-02-2 - BANNED: auto__mail.python.bat +Last-Attempt-Date: Fri, 26 Nov 2004 19:41:44 -0800 (PST) + +------------=_1101526904-1956-5 +Content-Type: text/rfc822-headers +Content-Disposition: inline +Content-Transfer-Encoding: 7bit +Content-Description: Undelivered-message headers + +Received: from kgsav.org (ppp-70-242-162-63.dsl.spfdmo.swbell.net [70.242.162.63]) + by sacspam01.dot.ca.gov (Spam Firewall) with SMTP + id A232AD03DE3A; Fri, 26 Nov 2004 19:41:35 -0800 (PST) +From: webmaster@python.org +To: xxxxx@dot.ca.gov +Date: Sat, 27 Nov 2004 03:35:30 UTC +Subject: Delivery_failure_notice +Importance: Normal +X-Priority: 3 (Normal) +X-MSMail-Priority: Normal +Message-ID: <edab.7804f5cb8070@python.org> +MIME-Version: 1.0 +Content-Type: multipart/mixed; boundary="====67bd2b7a5.f99f7" +Content-Transfer-Encoding: 7bit + +------------=_1101526904-1956-5-- + diff --git a/Lib/test/test_email/data/msg_44.txt b/Lib/test/test_email/data/msg_44.txt new file mode 100644 index 0000000..15a2252 --- /dev/null +++ b/Lib/test/test_email/data/msg_44.txt @@ -0,0 +1,33 @@ +Return-Path: <barry@python.org> +Delivered-To: barry@python.org +Received: by mail.python.org (Postfix, from userid 889) + id C2BF0D37C6; Tue, 11 Sep 2001 00:05:05 -0400 (EDT) +MIME-Version: 1.0 +Content-Type: multipart/mixed; boundary="h90VIIIKmx" +Content-Transfer-Encoding: 7bit +Message-ID: <15261.36209.358846.118674@anthem.python.org> +From: barry@python.org (Barry A. Warsaw) +To: barry@python.org +Subject: a simple multipart +Date: Tue, 11 Sep 2001 00:05:05 -0400 +X-Mailer: VM 6.95 under 21.4 (patch 4) "Artificial Intelligence" XEmacs Lucid +X-Attribution: BAW +X-Oblique-Strategy: Make a door into a window + + +--h90VIIIKmx +Content-Type: text/plain; name="msg.txt" +Content-Transfer-Encoding: 7bit + +a simple kind of mirror +to reflect upon our own + +--h90VIIIKmx +Content-Type: text/plain; name="msg.txt" +Content-Transfer-Encoding: 7bit + +a simple kind of mirror +to reflect upon our own + +--h90VIIIKmx-- + diff --git a/Lib/test/test_email/data/msg_45.txt b/Lib/test/test_email/data/msg_45.txt new file mode 100644 index 0000000..58fde95 --- /dev/null +++ b/Lib/test/test_email/data/msg_45.txt @@ -0,0 +1,33 @@ +From: <foo@bar.baz> +To: <baz@bar.foo> +Subject: test +X-Long-Line: Some really long line contains a lot of text and thus has to be rewrapped because it is some + really long + line +MIME-Version: 1.0 +Content-Type: multipart/signed; boundary="borderline"; + protocol="application/pgp-signature"; micalg=pgp-sha1 + +This is an OpenPGP/MIME signed message (RFC 2440 and 3156) +--borderline +Content-Type: text/plain +X-Long-Line: Another really long line contains a lot of text and thus has to be rewrapped because it is another + really long + line + +This is the signed contents. + +--borderline +Content-Type: application/pgp-signature; name="signature.asc" +Content-Description: OpenPGP digital signature +Content-Disposition: attachment; filename="signature.asc" + +-----BEGIN PGP SIGNATURE----- +Version: GnuPG v2.0.6 (GNU/Linux) + +iD8DBQFG03voRhp6o4m9dFsRApSZAKCCAN3IkJlVRg6NvAiMHlvvIuMGPQCeLZtj +FGwfnRHFBFO/S4/DKysm0lI= +=t7+s +-----END PGP SIGNATURE----- + +--borderline-- diff --git a/Lib/test/test_email/data/msg_46.txt b/Lib/test/test_email/data/msg_46.txt new file mode 100644 index 0000000..1e22c4f --- /dev/null +++ b/Lib/test/test_email/data/msg_46.txt @@ -0,0 +1,23 @@ +Return-Path: <sender@example.net> +Delivery-Date: Mon, 08 Feb 2010 14:05:16 +0100 +Received: from example.org (example.org [64.5.53.58]) + by example.net (node=mxbap2) with ESMTP (Nemesis) + id UNIQUE for someone@example.com; Mon, 08 Feb 2010 14:05:16 +0100 +Date: Mon, 01 Feb 2010 12:21:16 +0100 +From: "Sender" <sender@example.net> +To: <someone@example.com> +Subject: GroupwiseForwardingTest +Mime-Version: 1.0 +Content-Type: message/rfc822 + +Return-path: <sender@example.net> +Message-ID: <4B66B890.4070408@teconcept.de> +Date: Mon, 01 Feb 2010 12:18:40 +0100 +From: "Dr. Sender" <sender@example.net> +MIME-Version: 1.0 +To: "Recipient" <recipient@example.com> +Subject: GroupwiseForwardingTest +Content-Type: text/plain; charset=ISO-8859-15 +Content-Transfer-Encoding: 7bit + +Testing email forwarding with Groupwise 1.2.2010 diff --git a/Lib/test/test_email/test_asian_codecs.py b/Lib/test/test_email/test_asian_codecs.py new file mode 100644 index 0000000..a4dd9a9 --- /dev/null +++ b/Lib/test/test_email/test_asian_codecs.py @@ -0,0 +1,82 @@ +# Copyright (C) 2002-2006 Python Software Foundation +# Contact: email-sig@python.org +# email package unit tests for (optional) Asian codecs + +import unittest +from test.support import run_unittest + +from test.test_email.test_email import TestEmailBase +from email.charset import Charset +from email.header import Header, decode_header +from email.message import Message + +# We're compatible with Python 2.3, but it doesn't have the built-in Asian +# codecs, so we have to skip all these tests. +try: + str(b'foo', 'euc-jp') +except LookupError: + raise unittest.SkipTest + + + +class TestEmailAsianCodecs(TestEmailBase): + def test_japanese_codecs(self): + eq = self.ndiffAssertEqual + jcode = "euc-jp" + gcode = "iso-8859-1" + j = Charset(jcode) + g = Charset(gcode) + h = Header("Hello World!") + jhello = str(b'\xa5\xcf\xa5\xed\xa1\xbc\xa5\xef\xa1\xbc' + b'\xa5\xeb\xa5\xc9\xa1\xaa', jcode) + ghello = str(b'Gr\xfc\xdf Gott!', gcode) + h.append(jhello, j) + h.append(ghello, g) + # BAW: This used to -- and maybe should -- fold the two iso-8859-1 + # chunks into a single encoded word. However it doesn't violate the + # standard to have them as two encoded chunks and maybe it's + # reasonable <wink> for each .append() call to result in a separate + # encoded word. + eq(h.encode(), """\ +Hello World! =?iso-2022-jp?b?GyRCJU8lbSE8JW8hPCVrJUkhKhsoQg==?= + =?iso-8859-1?q?Gr=FC=DF_Gott!?=""") + eq(decode_header(h.encode()), + [(b'Hello World!', None), + (b'\x1b$B%O%m!<%o!<%k%I!*\x1b(B', 'iso-2022-jp'), + (b'Gr\xfc\xdf Gott!', gcode)]) + subject_bytes = (b'test-ja \xa4\xd8\xc5\xea\xb9\xc6\xa4\xb5' + b'\xa4\xec\xa4\xbf\xa5\xe1\xa1\xbc\xa5\xeb\xa4\xcf\xbb\xca\xb2' + b'\xf1\xbc\xd4\xa4\xce\xbe\xb5\xc7\xa7\xa4\xf2\xc2\xd4\xa4\xc3' + b'\xa4\xc6\xa4\xa4\xa4\xde\xa4\xb9') + subject = str(subject_bytes, jcode) + h = Header(subject, j, header_name="Subject") + # test a very long header + enc = h.encode() + # TK: splitting point may differ by codec design and/or Header encoding + eq(enc , """\ +=?iso-2022-jp?b?dGVzdC1qYSAbJEIkWEVqOUYkNSRsJD8lYSE8JWskTztKGyhC?= + =?iso-2022-jp?b?GyRCMnE8VCROPjVHJyRyQlQkQyRGJCQkXiQ5GyhC?=""") + # TK: full decode comparison + eq(str(h).encode(jcode), subject_bytes) + + def test_payload_encoding_utf8(self): + jhello = str(b'\xa5\xcf\xa5\xed\xa1\xbc\xa5\xef\xa1\xbc' + b'\xa5\xeb\xa5\xc9\xa1\xaa', 'euc-jp') + msg = Message() + msg.set_payload(jhello, 'utf-8') + ustr = msg.get_payload(decode=True).decode(msg.get_content_charset()) + self.assertEqual(jhello, ustr) + + def test_payload_encoding(self): + jcode = 'euc-jp' + jhello = str(b'\xa5\xcf\xa5\xed\xa1\xbc\xa5\xef\xa1\xbc' + b'\xa5\xeb\xa5\xc9\xa1\xaa', jcode) + msg = Message() + msg.set_payload(jhello, jcode) + ustr = msg.get_payload(decode=True).decode(msg.get_content_charset()) + self.assertEqual(jhello, ustr) + + + +if __name__ == '__main__': + unittest.main() diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py new file mode 100644 index 0000000..29dd0fc --- /dev/null +++ b/Lib/test/test_email/test_email.py @@ -0,0 +1,4146 @@ +# Copyright (C) 2001-2010 Python Software Foundation +# Contact: email-sig@python.org +# email package unit tests + +import os +import re +import sys +import time +import base64 +import difflib +import unittest +import warnings +import textwrap + +from io import StringIO, BytesIO +from itertools import chain + +import email + +from email.charset import Charset +from email.header import Header, decode_header, make_header +from email.parser import Parser, HeaderParser +from email.generator import Generator, DecodedGenerator +from email.message import Message +from email.mime.application import MIMEApplication +from email.mime.audio import MIMEAudio +from email.mime.text import MIMEText +from email.mime.image import MIMEImage +from email.mime.base import MIMEBase +from email.mime.message import MIMEMessage +from email.mime.multipart import MIMEMultipart +from email import utils +from email import errors +from email import encoders +from email import iterators +from email import base64mime +from email import quoprimime + +from test.support import findfile, run_unittest, unlink +from test.test_email import __file__ as landmark + + +NL = '\n' +EMPTYSTRING = '' +SPACE = ' ' + + + +def openfile(filename, *args, **kws): + path = os.path.join(os.path.dirname(landmark), 'data', filename) + return open(path, *args, **kws) + + + +# Base test class +class TestEmailBase(unittest.TestCase): + def ndiffAssertEqual(self, first, second): + """Like assertEqual except use ndiff for readable output.""" + if first != second: + sfirst = str(first) + ssecond = str(second) + rfirst = [repr(line) for line in sfirst.splitlines()] + rsecond = [repr(line) for line in ssecond.splitlines()] + diff = difflib.ndiff(rfirst, rsecond) + raise self.failureException(NL + NL.join(diff)) + + def _msgobj(self, filename): + with openfile(findfile(filename)) as fp: + return email.message_from_file(fp) + + + +# Test various aspects of the Message class's API +class TestMessageAPI(TestEmailBase): + def test_get_all(self): + eq = self.assertEqual + msg = self._msgobj('msg_20.txt') + eq(msg.get_all('cc'), ['ccc@zzz.org', 'ddd@zzz.org', 'eee@zzz.org']) + eq(msg.get_all('xx', 'n/a'), 'n/a') + + def test_getset_charset(self): + eq = self.assertEqual + msg = Message() + eq(msg.get_charset(), None) + charset = Charset('iso-8859-1') + msg.set_charset(charset) + eq(msg['mime-version'], '1.0') + eq(msg.get_content_type(), 'text/plain') + eq(msg['content-type'], 'text/plain; charset="iso-8859-1"') + eq(msg.get_param('charset'), 'iso-8859-1') + eq(msg['content-transfer-encoding'], 'quoted-printable') + eq(msg.get_charset().input_charset, 'iso-8859-1') + # Remove the charset + msg.set_charset(None) + eq(msg.get_charset(), None) + eq(msg['content-type'], 'text/plain') + # Try adding a charset when there's already MIME headers present + msg = Message() + msg['MIME-Version'] = '2.0' + msg['Content-Type'] = 'text/x-weird' + msg['Content-Transfer-Encoding'] = 'quinted-puntable' + msg.set_charset(charset) + eq(msg['mime-version'], '2.0') + eq(msg['content-type'], 'text/x-weird; charset="iso-8859-1"') + eq(msg['content-transfer-encoding'], 'quinted-puntable') + + def test_set_charset_from_string(self): + eq = self.assertEqual + msg = Message() + msg.set_charset('us-ascii') + eq(msg.get_charset().input_charset, 'us-ascii') + eq(msg['content-type'], 'text/plain; charset="us-ascii"') + + def test_set_payload_with_charset(self): + msg = Message() + charset = Charset('iso-8859-1') + msg.set_payload('This is a string payload', charset) + self.assertEqual(msg.get_charset().input_charset, 'iso-8859-1') + + def test_get_charsets(self): + eq = self.assertEqual + + msg = self._msgobj('msg_08.txt') + charsets = msg.get_charsets() + eq(charsets, [None, 'us-ascii', 'iso-8859-1', 'iso-8859-2', 'koi8-r']) + + msg = self._msgobj('msg_09.txt') + charsets = msg.get_charsets('dingbat') + eq(charsets, ['dingbat', 'us-ascii', 'iso-8859-1', 'dingbat', + 'koi8-r']) + + msg = self._msgobj('msg_12.txt') + charsets = msg.get_charsets() + eq(charsets, [None, 'us-ascii', 'iso-8859-1', None, 'iso-8859-2', + 'iso-8859-3', 'us-ascii', 'koi8-r']) + + def test_get_filename(self): + eq = self.assertEqual + + msg = self._msgobj('msg_04.txt') + filenames = [p.get_filename() for p in msg.get_payload()] + eq(filenames, ['msg.txt', 'msg.txt']) + + msg = self._msgobj('msg_07.txt') + subpart = msg.get_payload(1) + eq(subpart.get_filename(), 'dingusfish.gif') + + def test_get_filename_with_name_parameter(self): + eq = self.assertEqual + + msg = self._msgobj('msg_44.txt') + filenames = [p.get_filename() for p in msg.get_payload()] + eq(filenames, ['msg.txt', 'msg.txt']) + + def test_get_boundary(self): + eq = self.assertEqual + msg = self._msgobj('msg_07.txt') + # No quotes! + eq(msg.get_boundary(), 'BOUNDARY') + + def test_set_boundary(self): + eq = self.assertEqual + # This one has no existing boundary parameter, but the Content-Type: + # header appears fifth. + msg = self._msgobj('msg_01.txt') + msg.set_boundary('BOUNDARY') + header, value = msg.items()[4] + eq(header.lower(), 'content-type') + eq(value, 'text/plain; charset="us-ascii"; boundary="BOUNDARY"') + # This one has a Content-Type: header, with a boundary, stuck in the + # middle of its headers. Make sure the order is preserved; it should + # be fifth. + msg = self._msgobj('msg_04.txt') + msg.set_boundary('BOUNDARY') + header, value = msg.items()[4] + eq(header.lower(), 'content-type') + eq(value, 'multipart/mixed; boundary="BOUNDARY"') + # And this one has no Content-Type: header at all. + msg = self._msgobj('msg_03.txt') + self.assertRaises(errors.HeaderParseError, + msg.set_boundary, 'BOUNDARY') + + def test_make_boundary(self): + msg = MIMEMultipart('form-data') + # Note that when the boundary gets created is an implementation + # detail and might change. + self.assertEqual(msg.items()[0][1], 'multipart/form-data') + # Trigger creation of boundary + msg.as_string() + self.assertEqual(msg.items()[0][1][:33], + 'multipart/form-data; boundary="==') + # XXX: there ought to be tests of the uniqueness of the boundary, too. + + def test_message_rfc822_only(self): + # Issue 7970: message/rfc822 not in multipart parsed by + # HeaderParser caused an exception when flattened. + with openfile(findfile('msg_46.txt')) as fp: + msgdata = fp.read() + parser = HeaderParser() + msg = parser.parsestr(msgdata) + out = StringIO() + gen = Generator(out, True, 0) + gen.flatten(msg, False) + self.assertEqual(out.getvalue(), msgdata) + + def test_get_decoded_payload(self): + eq = self.assertEqual + msg = self._msgobj('msg_10.txt') + # The outer message is a multipart + eq(msg.get_payload(decode=True), None) + # Subpart 1 is 7bit encoded + eq(msg.get_payload(0).get_payload(decode=True), + b'This is a 7bit encoded message.\n') + # Subpart 2 is quopri + eq(msg.get_payload(1).get_payload(decode=True), + b'\xa1This is a Quoted Printable encoded message!\n') + # Subpart 3 is base64 + eq(msg.get_payload(2).get_payload(decode=True), + b'This is a Base64 encoded message.') + # Subpart 4 is base64 with a trailing newline, which + # used to be stripped (issue 7143). + eq(msg.get_payload(3).get_payload(decode=True), + b'This is a Base64 encoded message.\n') + # Subpart 5 has no Content-Transfer-Encoding: header. + eq(msg.get_payload(4).get_payload(decode=True), + b'This has no Content-Transfer-Encoding: header.\n') + + def test_get_decoded_uu_payload(self): + eq = self.assertEqual + msg = Message() + msg.set_payload('begin 666 -\n+:&5L;&\\@=V]R;&0 \n \nend\n') + for cte in ('x-uuencode', 'uuencode', 'uue', 'x-uue'): + msg['content-transfer-encoding'] = cte + eq(msg.get_payload(decode=True), b'hello world') + # Now try some bogus data + msg.set_payload('foo') + eq(msg.get_payload(decode=True), b'foo') + + def test_decoded_generator(self): + eq = self.assertEqual + msg = self._msgobj('msg_07.txt') + with openfile('msg_17.txt') as fp: + text = fp.read() + s = StringIO() + g = DecodedGenerator(s) + g.flatten(msg) + eq(s.getvalue(), text) + + def test__contains__(self): + msg = Message() + msg['From'] = 'Me' + msg['to'] = 'You' + # Check for case insensitivity + self.assertTrue('from' in msg) + self.assertTrue('From' in msg) + self.assertTrue('FROM' in msg) + self.assertTrue('to' in msg) + self.assertTrue('To' in msg) + self.assertTrue('TO' in msg) + + def test_as_string(self): + eq = self.ndiffAssertEqual + msg = self._msgobj('msg_01.txt') + with openfile('msg_01.txt') as fp: + text = fp.read() + eq(text, str(msg)) + fullrepr = msg.as_string(unixfrom=True) + lines = fullrepr.split('\n') + self.assertTrue(lines[0].startswith('From ')) + eq(text, NL.join(lines[1:])) + + def test_bad_param(self): + msg = email.message_from_string("Content-Type: blarg; baz; boo\n") + self.assertEqual(msg.get_param('baz'), '') + + def test_missing_filename(self): + msg = email.message_from_string("From: foo\n") + self.assertEqual(msg.get_filename(), None) + + def test_bogus_filename(self): + msg = email.message_from_string( + "Content-Disposition: blarg; filename\n") + self.assertEqual(msg.get_filename(), '') + + def test_missing_boundary(self): + msg = email.message_from_string("From: foo\n") + self.assertEqual(msg.get_boundary(), None) + + def test_get_params(self): + eq = self.assertEqual + msg = email.message_from_string( + 'X-Header: foo=one; bar=two; baz=three\n') + eq(msg.get_params(header='x-header'), + [('foo', 'one'), ('bar', 'two'), ('baz', 'three')]) + msg = email.message_from_string( + 'X-Header: foo; bar=one; baz=two\n') + eq(msg.get_params(header='x-header'), + [('foo', ''), ('bar', 'one'), ('baz', 'two')]) + eq(msg.get_params(), None) + msg = email.message_from_string( + 'X-Header: foo; bar="one"; baz=two\n') + eq(msg.get_params(header='x-header'), + [('foo', ''), ('bar', 'one'), ('baz', 'two')]) + + def test_get_param_liberal(self): + msg = Message() + msg['Content-Type'] = 'Content-Type: Multipart/mixed; boundary = "CPIMSSMTPC06p5f3tG"' + self.assertEqual(msg.get_param('boundary'), 'CPIMSSMTPC06p5f3tG') + + def test_get_param(self): + eq = self.assertEqual + msg = email.message_from_string( + "X-Header: foo=one; bar=two; baz=three\n") + eq(msg.get_param('bar', header='x-header'), 'two') + eq(msg.get_param('quuz', header='x-header'), None) + eq(msg.get_param('quuz'), None) + msg = email.message_from_string( + 'X-Header: foo; bar="one"; baz=two\n') + eq(msg.get_param('foo', header='x-header'), '') + eq(msg.get_param('bar', header='x-header'), 'one') + eq(msg.get_param('baz', header='x-header'), 'two') + # XXX: We are not RFC-2045 compliant! We cannot parse: + # msg["Content-Type"] = 'text/plain; weird="hey; dolly? [you] @ <\\"home\\">?"' + # msg.get_param("weird") + # yet. + + def test_get_param_funky_continuation_lines(self): + msg = self._msgobj('msg_22.txt') + self.assertEqual(msg.get_payload(1).get_param('name'), 'wibble.JPG') + + def test_get_param_with_semis_in_quotes(self): + msg = email.message_from_string( + 'Content-Type: image/pjpeg; name="Jim&&Jill"\n') + self.assertEqual(msg.get_param('name'), 'Jim&&Jill') + self.assertEqual(msg.get_param('name', unquote=False), + '"Jim&&Jill"') + + def test_get_param_with_quotes(self): + msg = email.message_from_string( + 'Content-Type: foo; bar*0="baz\\"foobar"; bar*1="\\"baz"') + self.assertEqual(msg.get_param('bar'), 'baz"foobar"baz') + msg = email.message_from_string( + "Content-Type: foo; bar*0=\"baz\\\"foobar\"; bar*1=\"\\\"baz\"") + self.assertEqual(msg.get_param('bar'), 'baz"foobar"baz') + + def test_field_containment(self): + unless = self.assertTrue + msg = email.message_from_string('Header: exists') + unless('header' in msg) + unless('Header' in msg) + unless('HEADER' in msg) + self.assertFalse('headerx' in msg) + + def test_set_param(self): + eq = self.assertEqual + msg = Message() + msg.set_param('charset', 'iso-2022-jp') + eq(msg.get_param('charset'), 'iso-2022-jp') + msg.set_param('importance', 'high value') + eq(msg.get_param('importance'), 'high value') + eq(msg.get_param('importance', unquote=False), '"high value"') + eq(msg.get_params(), [('text/plain', ''), + ('charset', 'iso-2022-jp'), + ('importance', 'high value')]) + eq(msg.get_params(unquote=False), [('text/plain', ''), + ('charset', '"iso-2022-jp"'), + ('importance', '"high value"')]) + msg.set_param('charset', 'iso-9999-xx', header='X-Jimmy') + eq(msg.get_param('charset', header='X-Jimmy'), 'iso-9999-xx') + + def test_del_param(self): + eq = self.assertEqual + msg = self._msgobj('msg_05.txt') + eq(msg.get_params(), + [('multipart/report', ''), ('report-type', 'delivery-status'), + ('boundary', 'D1690A7AC1.996856090/mail.example.com')]) + old_val = msg.get_param("report-type") + msg.del_param("report-type") + eq(msg.get_params(), + [('multipart/report', ''), + ('boundary', 'D1690A7AC1.996856090/mail.example.com')]) + msg.set_param("report-type", old_val) + eq(msg.get_params(), + [('multipart/report', ''), + ('boundary', 'D1690A7AC1.996856090/mail.example.com'), + ('report-type', old_val)]) + + def test_del_param_on_other_header(self): + msg = Message() + msg.add_header('Content-Disposition', 'attachment', filename='bud.gif') + msg.del_param('filename', 'content-disposition') + self.assertEqual(msg['content-disposition'], 'attachment') + + def test_set_type(self): + eq = self.assertEqual + msg = Message() + self.assertRaises(ValueError, msg.set_type, 'text') + msg.set_type('text/plain') + eq(msg['content-type'], 'text/plain') + msg.set_param('charset', 'us-ascii') + eq(msg['content-type'], 'text/plain; charset="us-ascii"') + msg.set_type('text/html') + eq(msg['content-type'], 'text/html; charset="us-ascii"') + + def test_set_type_on_other_header(self): + msg = Message() + msg['X-Content-Type'] = 'text/plain' + msg.set_type('application/octet-stream', 'X-Content-Type') + self.assertEqual(msg['x-content-type'], 'application/octet-stream') + + def test_get_content_type_missing(self): + msg = Message() + self.assertEqual(msg.get_content_type(), 'text/plain') + + def test_get_content_type_missing_with_default_type(self): + msg = Message() + msg.set_default_type('message/rfc822') + self.assertEqual(msg.get_content_type(), 'message/rfc822') + + def test_get_content_type_from_message_implicit(self): + msg = self._msgobj('msg_30.txt') + self.assertEqual(msg.get_payload(0).get_content_type(), + 'message/rfc822') + + def test_get_content_type_from_message_explicit(self): + msg = self._msgobj('msg_28.txt') + self.assertEqual(msg.get_payload(0).get_content_type(), + 'message/rfc822') + + def test_get_content_type_from_message_text_plain_implicit(self): + msg = self._msgobj('msg_03.txt') + self.assertEqual(msg.get_content_type(), 'text/plain') + + def test_get_content_type_from_message_text_plain_explicit(self): + msg = self._msgobj('msg_01.txt') + self.assertEqual(msg.get_content_type(), 'text/plain') + + def test_get_content_maintype_missing(self): + msg = Message() + self.assertEqual(msg.get_content_maintype(), 'text') + + def test_get_content_maintype_missing_with_default_type(self): + msg = Message() + msg.set_default_type('message/rfc822') + self.assertEqual(msg.get_content_maintype(), 'message') + + def test_get_content_maintype_from_message_implicit(self): + msg = self._msgobj('msg_30.txt') + self.assertEqual(msg.get_payload(0).get_content_maintype(), 'message') + + def test_get_content_maintype_from_message_explicit(self): + msg = self._msgobj('msg_28.txt') + self.assertEqual(msg.get_payload(0).get_content_maintype(), 'message') + + def test_get_content_maintype_from_message_text_plain_implicit(self): + msg = self._msgobj('msg_03.txt') + self.assertEqual(msg.get_content_maintype(), 'text') + + def test_get_content_maintype_from_message_text_plain_explicit(self): + msg = self._msgobj('msg_01.txt') + self.assertEqual(msg.get_content_maintype(), 'text') + + def test_get_content_subtype_missing(self): + msg = Message() + self.assertEqual(msg.get_content_subtype(), 'plain') + + def test_get_content_subtype_missing_with_default_type(self): + msg = Message() + msg.set_default_type('message/rfc822') + self.assertEqual(msg.get_content_subtype(), 'rfc822') + + def test_get_content_subtype_from_message_implicit(self): + msg = self._msgobj('msg_30.txt') + self.assertEqual(msg.get_payload(0).get_content_subtype(), 'rfc822') + + def test_get_content_subtype_from_message_explicit(self): + msg = self._msgobj('msg_28.txt') + self.assertEqual(msg.get_payload(0).get_content_subtype(), 'rfc822') + + def test_get_content_subtype_from_message_text_plain_implicit(self): + msg = self._msgobj('msg_03.txt') + self.assertEqual(msg.get_content_subtype(), 'plain') + + def test_get_content_subtype_from_message_text_plain_explicit(self): + msg = self._msgobj('msg_01.txt') + self.assertEqual(msg.get_content_subtype(), 'plain') + + def test_get_content_maintype_error(self): + msg = Message() + msg['Content-Type'] = 'no-slash-in-this-string' + self.assertEqual(msg.get_content_maintype(), 'text') + + def test_get_content_subtype_error(self): + msg = Message() + msg['Content-Type'] = 'no-slash-in-this-string' + self.assertEqual(msg.get_content_subtype(), 'plain') + + def test_replace_header(self): + eq = self.assertEqual + msg = Message() + msg.add_header('First', 'One') + msg.add_header('Second', 'Two') + msg.add_header('Third', 'Three') + eq(msg.keys(), ['First', 'Second', 'Third']) + eq(msg.values(), ['One', 'Two', 'Three']) + msg.replace_header('Second', 'Twenty') + eq(msg.keys(), ['First', 'Second', 'Third']) + eq(msg.values(), ['One', 'Twenty', 'Three']) + msg.add_header('First', 'Eleven') + msg.replace_header('First', 'One Hundred') + eq(msg.keys(), ['First', 'Second', 'Third', 'First']) + eq(msg.values(), ['One Hundred', 'Twenty', 'Three', 'Eleven']) + self.assertRaises(KeyError, msg.replace_header, 'Fourth', 'Missing') + + def test_broken_base64_payload(self): + x = 'AwDp0P7//y6LwKEAcPa/6Q=9' + msg = Message() + msg['content-type'] = 'audio/x-midi' + msg['content-transfer-encoding'] = 'base64' + msg.set_payload(x) + self.assertEqual(msg.get_payload(decode=True), + bytes(x, 'raw-unicode-escape')) + + # Issue 1078919 + def test_ascii_add_header(self): + msg = Message() + msg.add_header('Content-Disposition', 'attachment', + filename='bud.gif') + self.assertEqual('attachment; filename="bud.gif"', + msg['Content-Disposition']) + + def test_noascii_add_header(self): + msg = Message() + msg.add_header('Content-Disposition', 'attachment', + filename="Fußballer.ppt") + self.assertEqual( + 'attachment; filename*=utf-8\'\'Fu%C3%9Fballer.ppt', + msg['Content-Disposition']) + + def test_nonascii_add_header_via_triple(self): + msg = Message() + msg.add_header('Content-Disposition', 'attachment', + filename=('iso-8859-1', '', 'Fußballer.ppt')) + self.assertEqual( + 'attachment; filename*=iso-8859-1\'\'Fu%DFballer.ppt', + msg['Content-Disposition']) + + def test_ascii_add_header_with_tspecial(self): + msg = Message() + msg.add_header('Content-Disposition', 'attachment', + filename="windows [filename].ppt") + self.assertEqual( + 'attachment; filename="windows [filename].ppt"', + msg['Content-Disposition']) + + def test_nonascii_add_header_with_tspecial(self): + msg = Message() + msg.add_header('Content-Disposition', 'attachment', + filename="Fußballer [filename].ppt") + self.assertEqual( + "attachment; filename*=utf-8''Fu%C3%9Fballer%20%5Bfilename%5D.ppt", + msg['Content-Disposition']) + + # Issue 5871: reject an attempt to embed a header inside a header value + # (header injection attack). + def test_embeded_header_via_Header_rejected(self): + msg = Message() + msg['Dummy'] = Header('dummy\nX-Injected-Header: test') + self.assertRaises(errors.HeaderParseError, msg.as_string) + + def test_embeded_header_via_string_rejected(self): + msg = Message() + msg['Dummy'] = 'dummy\nX-Injected-Header: test' + self.assertRaises(errors.HeaderParseError, msg.as_string) + +# Test the email.encoders module +class TestEncoders(unittest.TestCase): + + def test_EncodersEncode_base64(self): + with openfile('PyBanner048.gif', 'rb') as fp: + bindata = fp.read() + mimed = email.mime.image.MIMEImage(bindata) + base64ed = mimed.get_payload() + # the transfer-encoded body lines should all be <=76 characters + lines = base64ed.split('\n') + self.assertLessEqual(max([ len(x) for x in lines ]), 76) + + def test_encode_empty_payload(self): + eq = self.assertEqual + msg = Message() + msg.set_charset('us-ascii') + eq(msg['content-transfer-encoding'], '7bit') + + def test_default_cte(self): + eq = self.assertEqual + # 7bit data and the default us-ascii _charset + msg = MIMEText('hello world') + eq(msg['content-transfer-encoding'], '7bit') + # Similar, but with 8bit data + msg = MIMEText('hello \xf8 world') + eq(msg['content-transfer-encoding'], '8bit') + # And now with a different charset + msg = MIMEText('hello \xf8 world', _charset='iso-8859-1') + eq(msg['content-transfer-encoding'], 'quoted-printable') + + def test_encode7or8bit(self): + # Make sure a charset whose input character set is 8bit but + # whose output character set is 7bit gets a transfer-encoding + # of 7bit. + eq = self.assertEqual + msg = MIMEText('文', _charset='euc-jp') + eq(msg['content-transfer-encoding'], '7bit') + + +# Test long header wrapping +class TestLongHeaders(TestEmailBase): + def test_split_long_continuation(self): + eq = self.ndiffAssertEqual + msg = email.message_from_string("""\ +Subject: bug demonstration +\t12345678911234567892123456789312345678941234567895123456789612345678971234567898112345678911234567892123456789112345678911234567892123456789 +\tmore text + +test +""") + sfp = StringIO() + g = Generator(sfp) + g.flatten(msg) + eq(sfp.getvalue(), """\ +Subject: bug demonstration +\t12345678911234567892123456789312345678941234567895123456789612345678971234567898112345678911234567892123456789112345678911234567892123456789 +\tmore text + +test +""") + + def test_another_long_almost_unsplittable_header(self): + eq = self.ndiffAssertEqual + hstr = """\ +bug demonstration +\t12345678911234567892123456789312345678941234567895123456789612345678971234567898112345678911234567892123456789112345678911234567892123456789 +\tmore text""" + h = Header(hstr, continuation_ws='\t') + eq(h.encode(), """\ +bug demonstration +\t12345678911234567892123456789312345678941234567895123456789612345678971234567898112345678911234567892123456789112345678911234567892123456789 +\tmore text""") + h = Header(hstr.replace('\t', ' ')) + eq(h.encode(), """\ +bug demonstration + 12345678911234567892123456789312345678941234567895123456789612345678971234567898112345678911234567892123456789112345678911234567892123456789 + more text""") + + def test_long_nonstring(self): + eq = self.ndiffAssertEqual + g = Charset("iso-8859-1") + cz = Charset("iso-8859-2") + utf8 = Charset("utf-8") + g_head = (b'Die Mieter treten hier ein werden mit einem Foerderband ' + b'komfortabel den Korridor entlang, an s\xfcdl\xfcndischen ' + b'Wandgem\xe4lden vorbei, gegen die rotierenden Klingen ' + b'bef\xf6rdert. ') + cz_head = (b'Finan\xe8ni metropole se hroutily pod tlakem jejich ' + b'd\xf9vtipu.. ') + utf8_head = ('\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f' + '\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00' + '\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c' + '\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067' + '\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das ' + 'Nunstuck git und Slotermeyer? Ja! Beiherhund das Oder ' + 'die Flipperwaldt gersput.\u300d\u3068\u8a00\u3063\u3066' + '\u3044\u307e\u3059\u3002') + h = Header(g_head, g, header_name='Subject') + h.append(cz_head, cz) + h.append(utf8_head, utf8) + msg = Message() + msg['Subject'] = h + sfp = StringIO() + g = Generator(sfp) + g.flatten(msg) + eq(sfp.getvalue(), """\ +Subject: =?iso-8859-1?q?Die_Mieter_treten_hier_ein_werden_mit_einem_Foerderb?= + =?iso-8859-1?q?and_komfortabel_den_Korridor_entlang=2C_an_s=FCdl=FCndischen?= + =?iso-8859-1?q?_Wandgem=E4lden_vorbei=2C_gegen_die_rotierenden_Klingen_bef?= + =?iso-8859-1?q?=F6rdert=2E_?= =?iso-8859-2?q?Finan=E8ni_metropole_se_hrouti?= + =?iso-8859-2?q?ly_pod_tlakem_jejich_d=F9vtipu=2E=2E_?= =?utf-8?b?5q2j56K6?= + =?utf-8?b?44Gr6KiA44GG44Go57+76Kiz44Gv44GV44KM44Gm44GE44G+44Gb44KT44CC5LiA?= + =?utf-8?b?6YOo44Gv44OJ44Kk44OE6Kqe44Gn44GZ44GM44CB44GC44Go44Gv44Gn44Gf44KJ?= + =?utf-8?b?44KB44Gn44GZ44CC5a6f6Zqb44Gr44Gv44CMV2VubiBpc3QgZGFzIE51bnN0dWNr?= + =?utf-8?b?IGdpdCB1bmQgU2xvdGVybWV5ZXI/IEphISBCZWloZXJodW5kIGRhcyBPZGVyIGRp?= + =?utf-8?b?ZSBGbGlwcGVyd2FsZHQgZ2Vyc3B1dC7jgI3jgajoqIDjgaPjgabjgYTjgb7jgZk=?= + =?utf-8?b?44CC?= + +""") + eq(h.encode(maxlinelen=76), """\ +=?iso-8859-1?q?Die_Mieter_treten_hier_ein_werden_mit_einem_Foerde?= + =?iso-8859-1?q?rband_komfortabel_den_Korridor_entlang=2C_an_s=FCdl=FCndis?= + =?iso-8859-1?q?chen_Wandgem=E4lden_vorbei=2C_gegen_die_rotierenden_Klinge?= + =?iso-8859-1?q?n_bef=F6rdert=2E_?= =?iso-8859-2?q?Finan=E8ni_metropole_se?= + =?iso-8859-2?q?_hroutily_pod_tlakem_jejich_d=F9vtipu=2E=2E_?= + =?utf-8?b?5q2j56K644Gr6KiA44GG44Go57+76Kiz44Gv44GV44KM44Gm44GE44G+44Gb?= + =?utf-8?b?44KT44CC5LiA6YOo44Gv44OJ44Kk44OE6Kqe44Gn44GZ44GM44CB44GC44Go?= + =?utf-8?b?44Gv44Gn44Gf44KJ44KB44Gn44GZ44CC5a6f6Zqb44Gr44Gv44CMV2VubiBp?= + =?utf-8?b?c3QgZGFzIE51bnN0dWNrIGdpdCB1bmQgU2xvdGVybWV5ZXI/IEphISBCZWlo?= + =?utf-8?b?ZXJodW5kIGRhcyBPZGVyIGRpZSBGbGlwcGVyd2FsZHQgZ2Vyc3B1dC7jgI0=?= + =?utf-8?b?44Go6KiA44Gj44Gm44GE44G+44GZ44CC?=""") + + def test_long_header_encode(self): + eq = self.ndiffAssertEqual + h = Header('wasnipoop; giraffes="very-long-necked-animals"; ' + 'spooge="yummy"; hippos="gargantuan"; marshmallows="gooey"', + header_name='X-Foobar-Spoink-Defrobnit') + eq(h.encode(), '''\ +wasnipoop; giraffes="very-long-necked-animals"; + spooge="yummy"; hippos="gargantuan"; marshmallows="gooey"''') + + def test_long_header_encode_with_tab_continuation_is_just_a_hint(self): + eq = self.ndiffAssertEqual + h = Header('wasnipoop; giraffes="very-long-necked-animals"; ' + 'spooge="yummy"; hippos="gargantuan"; marshmallows="gooey"', + header_name='X-Foobar-Spoink-Defrobnit', + continuation_ws='\t') + eq(h.encode(), '''\ +wasnipoop; giraffes="very-long-necked-animals"; + spooge="yummy"; hippos="gargantuan"; marshmallows="gooey"''') + + def test_long_header_encode_with_tab_continuation(self): + eq = self.ndiffAssertEqual + h = Header('wasnipoop; giraffes="very-long-necked-animals";\t' + 'spooge="yummy"; hippos="gargantuan"; marshmallows="gooey"', + header_name='X-Foobar-Spoink-Defrobnit', + continuation_ws='\t') + eq(h.encode(), '''\ +wasnipoop; giraffes="very-long-necked-animals"; +\tspooge="yummy"; hippos="gargantuan"; marshmallows="gooey"''') + + def test_header_encode_with_different_output_charset(self): + h = Header('文', 'euc-jp') + self.assertEqual(h.encode(), "=?iso-2022-jp?b?GyRCSjgbKEI=?=") + + def test_long_header_encode_with_different_output_charset(self): + h = Header(b'test-ja \xa4\xd8\xc5\xea\xb9\xc6\xa4\xb5\xa4\xec\xa4' + b'\xbf\xa5\xe1\xa1\xbc\xa5\xeb\xa4\xcf\xbb\xca\xb2\xf1\xbc\xd4' + b'\xa4\xce\xbe\xb5\xc7\xa7\xa4\xf2\xc2\xd4\xa4\xc3\xa4\xc6\xa4' + b'\xa4\xa4\xde\xa4\xb9'.decode('euc-jp'), 'euc-jp') + res = """\ +=?iso-2022-jp?b?dGVzdC1qYSAbJEIkWEVqOUYkNSRsJD8lYSE8JWskTztKMnE8VCROPjUbKEI=?= + =?iso-2022-jp?b?GyRCRyckckJUJEMkRiQkJF4kORsoQg==?=""" + self.assertEqual(h.encode(), res) + + def test_header_splitter(self): + eq = self.ndiffAssertEqual + msg = MIMEText('') + # It'd be great if we could use add_header() here, but that doesn't + # guarantee an order of the parameters. + msg['X-Foobar-Spoink-Defrobnit'] = ( + 'wasnipoop; giraffes="very-long-necked-animals"; ' + 'spooge="yummy"; hippos="gargantuan"; marshmallows="gooey"') + sfp = StringIO() + g = Generator(sfp) + g.flatten(msg) + eq(sfp.getvalue(), '''\ +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit +X-Foobar-Spoink-Defrobnit: wasnipoop; giraffes="very-long-necked-animals"; + spooge="yummy"; hippos="gargantuan"; marshmallows="gooey" + +''') + + def test_no_semis_header_splitter(self): + eq = self.ndiffAssertEqual + msg = Message() + msg['From'] = 'test@dom.ain' + msg['References'] = SPACE.join('<%d@dom.ain>' % i for i in range(10)) + msg.set_payload('Test') + sfp = StringIO() + g = Generator(sfp) + g.flatten(msg) + eq(sfp.getvalue(), """\ +From: test@dom.ain +References: <0@dom.ain> <1@dom.ain> <2@dom.ain> <3@dom.ain> <4@dom.ain> + <5@dom.ain> <6@dom.ain> <7@dom.ain> <8@dom.ain> <9@dom.ain> + +Test""") + + def test_no_split_long_header(self): + eq = self.ndiffAssertEqual + hstr = 'References: ' + 'x' * 80 + h = Header(hstr) + # These come on two lines because Headers are really field value + # classes and don't really know about their field names. + eq(h.encode(), """\ +References: + xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx""") + h = Header('x' * 80) + eq(h.encode(), 'xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx') + + def test_splitting_multiple_long_lines(self): + eq = self.ndiffAssertEqual + hstr = """\ +from babylon.socal-raves.org (localhost [127.0.0.1]); by babylon.socal-raves.org (Postfix) with ESMTP id B570E51B81; for <mailman-admin@babylon.socal-raves.org>; Sat, 2 Feb 2002 17:00:06 -0800 (PST) +\tfrom babylon.socal-raves.org (localhost [127.0.0.1]); by babylon.socal-raves.org (Postfix) with ESMTP id B570E51B81; for <mailman-admin@babylon.socal-raves.org>; Sat, 2 Feb 2002 17:00:06 -0800 (PST) +\tfrom babylon.socal-raves.org (localhost [127.0.0.1]); by babylon.socal-raves.org (Postfix) with ESMTP id B570E51B81; for <mailman-admin@babylon.socal-raves.org>; Sat, 2 Feb 2002 17:00:06 -0800 (PST) +""" + h = Header(hstr, continuation_ws='\t') + eq(h.encode(), """\ +from babylon.socal-raves.org (localhost [127.0.0.1]); + by babylon.socal-raves.org (Postfix) with ESMTP id B570E51B81; + for <mailman-admin@babylon.socal-raves.org>; + Sat, 2 Feb 2002 17:00:06 -0800 (PST) +\tfrom babylon.socal-raves.org (localhost [127.0.0.1]); + by babylon.socal-raves.org (Postfix) with ESMTP id B570E51B81; + for <mailman-admin@babylon.socal-raves.org>; + Sat, 2 Feb 2002 17:00:06 -0800 (PST) +\tfrom babylon.socal-raves.org (localhost [127.0.0.1]); + by babylon.socal-raves.org (Postfix) with ESMTP id B570E51B81; + for <mailman-admin@babylon.socal-raves.org>; + Sat, 2 Feb 2002 17:00:06 -0800 (PST)""") + + def test_splitting_first_line_only_is_long(self): + eq = self.ndiffAssertEqual + hstr = """\ +from modemcable093.139-201-24.que.mc.videotron.ca ([24.201.139.93] helo=cthulhu.gerg.ca) +\tby kronos.mems-exchange.org with esmtp (Exim 4.05) +\tid 17k4h5-00034i-00 +\tfor test@mems-exchange.org; Wed, 28 Aug 2002 11:25:20 -0400""" + h = Header(hstr, maxlinelen=78, header_name='Received', + continuation_ws='\t') + eq(h.encode(), """\ +from modemcable093.139-201-24.que.mc.videotron.ca ([24.201.139.93] + helo=cthulhu.gerg.ca) +\tby kronos.mems-exchange.org with esmtp (Exim 4.05) +\tid 17k4h5-00034i-00 +\tfor test@mems-exchange.org; Wed, 28 Aug 2002 11:25:20 -0400""") + + def test_long_8bit_header(self): + eq = self.ndiffAssertEqual + msg = Message() + h = Header('Britische Regierung gibt', 'iso-8859-1', + header_name='Subject') + h.append('gr\xfcnes Licht f\xfcr Offshore-Windkraftprojekte') + eq(h.encode(maxlinelen=76), """\ +=?iso-8859-1?q?Britische_Regierung_gibt_gr=FCnes_Licht_f=FCr_Offs?= + =?iso-8859-1?q?hore-Windkraftprojekte?=""") + msg['Subject'] = h + eq(msg.as_string(maxheaderlen=76), """\ +Subject: =?iso-8859-1?q?Britische_Regierung_gibt_gr=FCnes_Licht_f=FCr_Offs?= + =?iso-8859-1?q?hore-Windkraftprojekte?= + +""") + eq(msg.as_string(maxheaderlen=0), """\ +Subject: =?iso-8859-1?q?Britische_Regierung_gibt_gr=FCnes_Licht_f=FCr_Offshore-Windkraftprojekte?= + +""") + + def test_long_8bit_header_no_charset(self): + eq = self.ndiffAssertEqual + msg = Message() + header_string = ('Britische Regierung gibt gr\xfcnes Licht ' + 'f\xfcr Offshore-Windkraftprojekte ' + '<a-very-long-address@example.com>') + msg['Reply-To'] = header_string + self.assertRaises(UnicodeEncodeError, msg.as_string) + msg = Message() + msg['Reply-To'] = Header(header_string, 'utf-8', + header_name='Reply-To') + eq(msg.as_string(maxheaderlen=78), """\ +Reply-To: =?utf-8?q?Britische_Regierung_gibt_gr=C3=BCnes_Licht_f=C3=BCr_Offs?= + =?utf-8?q?hore-Windkraftprojekte_=3Ca-very-long-address=40example=2Ecom=3E?= + +""") + + def test_long_to_header(self): + eq = self.ndiffAssertEqual + to = ('"Someone Test #A" <someone@eecs.umich.edu>,' + '<someone@eecs.umich.edu>,' + '"Someone Test #B" <someone@umich.edu>, ' + '"Someone Test #C" <someone@eecs.umich.edu>, ' + '"Someone Test #D" <someone@eecs.umich.edu>') + msg = Message() + msg['To'] = to + eq(msg.as_string(maxheaderlen=78), '''\ +To: "Someone Test #A" <someone@eecs.umich.edu>,<someone@eecs.umich.edu>, + "Someone Test #B" <someone@umich.edu>, + "Someone Test #C" <someone@eecs.umich.edu>, + "Someone Test #D" <someone@eecs.umich.edu> + +''') + + def test_long_line_after_append(self): + eq = self.ndiffAssertEqual + s = 'This is an example of string which has almost the limit of header length.' + h = Header(s) + h.append('Add another line.') + eq(h.encode(maxlinelen=76), """\ +This is an example of string which has almost the limit of header length. + Add another line.""") + + def test_shorter_line_with_append(self): + eq = self.ndiffAssertEqual + s = 'This is a shorter line.' + h = Header(s) + h.append('Add another sentence. (Surprise?)') + eq(h.encode(), + 'This is a shorter line. Add another sentence. (Surprise?)') + + def test_long_field_name(self): + eq = self.ndiffAssertEqual + fn = 'X-Very-Very-Very-Long-Header-Name' + gs = ('Die Mieter treten hier ein werden mit einem Foerderband ' + 'komfortabel den Korridor entlang, an s\xfcdl\xfcndischen ' + 'Wandgem\xe4lden vorbei, gegen die rotierenden Klingen ' + 'bef\xf6rdert. ') + h = Header(gs, 'iso-8859-1', header_name=fn) + # BAW: this seems broken because the first line is too long + eq(h.encode(maxlinelen=76), """\ +=?iso-8859-1?q?Die_Mieter_treten_hier_e?= + =?iso-8859-1?q?in_werden_mit_einem_Foerderband_komfortabel_den_Korridor_e?= + =?iso-8859-1?q?ntlang=2C_an_s=FCdl=FCndischen_Wandgem=E4lden_vorbei=2C_ge?= + =?iso-8859-1?q?gen_die_rotierenden_Klingen_bef=F6rdert=2E_?=""") + + def test_long_received_header(self): + h = ('from FOO.TLD (vizworld.acl.foo.tld [123.452.678.9]) ' + 'by hrothgar.la.mastaler.com (tmda-ofmipd) with ESMTP; ' + 'Wed, 05 Mar 2003 18:10:18 -0700') + msg = Message() + msg['Received-1'] = Header(h, continuation_ws='\t') + msg['Received-2'] = h + # This should be splitting on spaces not semicolons. + self.ndiffAssertEqual(msg.as_string(maxheaderlen=78), """\ +Received-1: from FOO.TLD (vizworld.acl.foo.tld [123.452.678.9]) by hrothgar.la.mastaler.com (tmda-ofmipd) with ESMTP; + Wed, 05 Mar 2003 18:10:18 -0700 +Received-2: from FOO.TLD (vizworld.acl.foo.tld [123.452.678.9]) by hrothgar.la.mastaler.com (tmda-ofmipd) with ESMTP; + Wed, 05 Mar 2003 18:10:18 -0700 + +""") + + def test_string_headerinst_eq(self): + h = ('<15975.17901.207240.414604@sgigritzmann1.mathematik.' + 'tu-muenchen.de> (David Bremner\'s message of ' + '"Thu, 6 Mar 2003 13:58:21 +0100")') + msg = Message() + msg['Received-1'] = Header(h, header_name='Received-1', + continuation_ws='\t') + msg['Received-2'] = h + # XXX This should be splitting on spaces not commas. + self.ndiffAssertEqual(msg.as_string(maxheaderlen=78), """\ +Received-1: <15975.17901.207240.414604@sgigritzmann1.mathematik.tu-muenchen.de> (David Bremner's message of \"Thu, + 6 Mar 2003 13:58:21 +0100\") +Received-2: <15975.17901.207240.414604@sgigritzmann1.mathematik.tu-muenchen.de> (David Bremner's message of \"Thu, + 6 Mar 2003 13:58:21 +0100\") + +""") + + def test_long_unbreakable_lines_with_continuation(self): + eq = self.ndiffAssertEqual + msg = Message() + t = """\ +iVBORw0KGgoAAAANSUhEUgAAADAAAAAwBAMAAAClLOS0AAAAGFBMVEUAAAAkHiJeRUIcGBi9 + locQDQ4zJykFBAXJfWDjAAACYUlEQVR4nF2TQY/jIAyFc6lydlG5x8Nyp1Y69wj1PN2I5gzp""" + msg['Face-1'] = t + msg['Face-2'] = Header(t, header_name='Face-2') + # XXX This splitting is all wrong. It the first value line should be + # snug against the field name. + eq(msg.as_string(maxheaderlen=78), """\ +Face-1:\x20 + iVBORw0KGgoAAAANSUhEUgAAADAAAAAwBAMAAAClLOS0AAAAGFBMVEUAAAAkHiJeRUIcGBi9 + locQDQ4zJykFBAXJfWDjAAACYUlEQVR4nF2TQY/jIAyFc6lydlG5x8Nyp1Y69wj1PN2I5gzp +Face-2:\x20 + iVBORw0KGgoAAAANSUhEUgAAADAAAAAwBAMAAAClLOS0AAAAGFBMVEUAAAAkHiJeRUIcGBi9 + locQDQ4zJykFBAXJfWDjAAACYUlEQVR4nF2TQY/jIAyFc6lydlG5x8Nyp1Y69wj1PN2I5gzp + +""") + + def test_another_long_multiline_header(self): + eq = self.ndiffAssertEqual + m = ('Received: from siimage.com ' + '([172.25.1.3]) by zima.siliconimage.com with ' + 'Microsoft SMTPSVC(5.0.2195.4905); ' + 'Wed, 16 Oct 2002 07:41:11 -0700') + msg = email.message_from_string(m) + eq(msg.as_string(maxheaderlen=78), '''\ +Received: from siimage.com ([172.25.1.3]) by zima.siliconimage.com with Microsoft SMTPSVC(5.0.2195.4905); + Wed, 16 Oct 2002 07:41:11 -0700 + +''') + + def test_long_lines_with_different_header(self): + eq = self.ndiffAssertEqual + h = ('List-Unsubscribe: ' + '<http://lists.sourceforge.net/lists/listinfo/spamassassin-talk>,' + ' <mailto:spamassassin-talk-request@lists.sourceforge.net' + '?subject=unsubscribe>') + msg = Message() + msg['List'] = h + msg['List'] = Header(h, header_name='List') + eq(msg.as_string(maxheaderlen=78), """\ +List: List-Unsubscribe: <http://lists.sourceforge.net/lists/listinfo/spamassassin-talk>, + <mailto:spamassassin-talk-request@lists.sourceforge.net?subject=unsubscribe> +List: List-Unsubscribe: <http://lists.sourceforge.net/lists/listinfo/spamassassin-talk>, + <mailto:spamassassin-talk-request@lists.sourceforge.net?subject=unsubscribe> + +""") + + def test_long_rfc2047_header_with_embedded_fws(self): + h = Header(textwrap.dedent("""\ + We're going to pretend this header is in a non-ascii character set + \tto see if line wrapping with encoded words and embedded + folding white space works"""), + charset='utf-8', + header_name='Test') + self.assertEqual(h.encode()+'\n', textwrap.dedent("""\ + =?utf-8?q?We=27re_going_to_pretend_this_header_is_in_a_non-ascii_chara?= + =?utf-8?q?cter_set?= + =?utf-8?q?_to_see_if_line_wrapping_with_encoded_words_and_embedded?= + =?utf-8?q?_folding_white_space_works?=""")+'\n') + + + +# Test mangling of "From " lines in the body of a message +class TestFromMangling(unittest.TestCase): + def setUp(self): + self.msg = Message() + self.msg['From'] = 'aaa@bbb.org' + self.msg.set_payload("""\ +From the desk of A.A.A.: +Blah blah blah +""") + + def test_mangled_from(self): + s = StringIO() + g = Generator(s, mangle_from_=True) + g.flatten(self.msg) + self.assertEqual(s.getvalue(), """\ +From: aaa@bbb.org + +>From the desk of A.A.A.: +Blah blah blah +""") + + def test_dont_mangle_from(self): + s = StringIO() + g = Generator(s, mangle_from_=False) + g.flatten(self.msg) + self.assertEqual(s.getvalue(), """\ +From: aaa@bbb.org + +From the desk of A.A.A.: +Blah blah blah +""") + + + +# Test the basic MIMEAudio class +class TestMIMEAudio(unittest.TestCase): + def setUp(self): + # Make sure we pick up the audiotest.au that lives in email/test/data. + # In Python, there's an audiotest.au living in Lib/test but that isn't + # included in some binary distros that don't include the test + # package. The trailing empty string on the .join() is significant + # since findfile() will do a dirname(). + datadir = os.path.join(os.path.dirname(landmark), 'data', '') + with open(findfile('audiotest.au', datadir), 'rb') as fp: + self._audiodata = fp.read() + self._au = MIMEAudio(self._audiodata) + + def test_guess_minor_type(self): + self.assertEqual(self._au.get_content_type(), 'audio/basic') + + def test_encoding(self): + payload = self._au.get_payload() + self.assertEqual(base64.decodebytes(bytes(payload, 'ascii')), + self._audiodata) + + def test_checkSetMinor(self): + au = MIMEAudio(self._audiodata, 'fish') + self.assertEqual(au.get_content_type(), 'audio/fish') + + def test_add_header(self): + eq = self.assertEqual + unless = self.assertTrue + self._au.add_header('Content-Disposition', 'attachment', + filename='audiotest.au') + eq(self._au['content-disposition'], + 'attachment; filename="audiotest.au"') + eq(self._au.get_params(header='content-disposition'), + [('attachment', ''), ('filename', 'audiotest.au')]) + eq(self._au.get_param('filename', header='content-disposition'), + 'audiotest.au') + missing = [] + eq(self._au.get_param('attachment', header='content-disposition'), '') + unless(self._au.get_param('foo', failobj=missing, + header='content-disposition') is missing) + # Try some missing stuff + unless(self._au.get_param('foobar', missing) is missing) + unless(self._au.get_param('attachment', missing, + header='foobar') is missing) + + + +# Test the basic MIMEImage class +class TestMIMEImage(unittest.TestCase): + def setUp(self): + with openfile('PyBanner048.gif', 'rb') as fp: + self._imgdata = fp.read() + self._im = MIMEImage(self._imgdata) + + def test_guess_minor_type(self): + self.assertEqual(self._im.get_content_type(), 'image/gif') + + def test_encoding(self): + payload = self._im.get_payload() + self.assertEqual(base64.decodebytes(bytes(payload, 'ascii')), + self._imgdata) + + def test_checkSetMinor(self): + im = MIMEImage(self._imgdata, 'fish') + self.assertEqual(im.get_content_type(), 'image/fish') + + def test_add_header(self): + eq = self.assertEqual + unless = self.assertTrue + self._im.add_header('Content-Disposition', 'attachment', + filename='dingusfish.gif') + eq(self._im['content-disposition'], + 'attachment; filename="dingusfish.gif"') + eq(self._im.get_params(header='content-disposition'), + [('attachment', ''), ('filename', 'dingusfish.gif')]) + eq(self._im.get_param('filename', header='content-disposition'), + 'dingusfish.gif') + missing = [] + eq(self._im.get_param('attachment', header='content-disposition'), '') + unless(self._im.get_param('foo', failobj=missing, + header='content-disposition') is missing) + # Try some missing stuff + unless(self._im.get_param('foobar', missing) is missing) + unless(self._im.get_param('attachment', missing, + header='foobar') is missing) + + + +# Test the basic MIMEApplication class +class TestMIMEApplication(unittest.TestCase): + def test_headers(self): + eq = self.assertEqual + msg = MIMEApplication(b'\xfa\xfb\xfc\xfd\xfe\xff') + eq(msg.get_content_type(), 'application/octet-stream') + eq(msg['content-transfer-encoding'], 'base64') + + def test_body(self): + eq = self.assertEqual + bytesdata = b'\xfa\xfb\xfc\xfd\xfe\xff' + msg = MIMEApplication(bytesdata) + # whitespace in the cte encoded block is RFC-irrelevant. + eq(msg.get_payload().strip(), '+vv8/f7/') + eq(msg.get_payload(decode=True), bytesdata) + + + +# Test the basic MIMEText class +class TestMIMEText(unittest.TestCase): + def setUp(self): + self._msg = MIMEText('hello there') + + def test_types(self): + eq = self.assertEqual + unless = self.assertTrue + eq(self._msg.get_content_type(), 'text/plain') + eq(self._msg.get_param('charset'), 'us-ascii') + missing = [] + unless(self._msg.get_param('foobar', missing) is missing) + unless(self._msg.get_param('charset', missing, header='foobar') + is missing) + + def test_payload(self): + self.assertEqual(self._msg.get_payload(), 'hello there') + self.assertTrue(not self._msg.is_multipart()) + + def test_charset(self): + eq = self.assertEqual + msg = MIMEText('hello there', _charset='us-ascii') + eq(msg.get_charset().input_charset, 'us-ascii') + eq(msg['content-type'], 'text/plain; charset="us-ascii"') + + def test_7bit_input(self): + eq = self.assertEqual + msg = MIMEText('hello there', _charset='us-ascii') + eq(msg.get_charset().input_charset, 'us-ascii') + eq(msg['content-type'], 'text/plain; charset="us-ascii"') + + def test_7bit_input_no_charset(self): + eq = self.assertEqual + msg = MIMEText('hello there') + eq(msg.get_charset(), 'us-ascii') + eq(msg['content-type'], 'text/plain; charset="us-ascii"') + self.assertTrue('hello there' in msg.as_string()) + + def test_utf8_input(self): + teststr = '\u043a\u0438\u0440\u0438\u043b\u0438\u0446\u0430' + eq = self.assertEqual + msg = MIMEText(teststr, _charset='utf-8') + eq(msg.get_charset().output_charset, 'utf-8') + eq(msg['content-type'], 'text/plain; charset="utf-8"') + eq(msg.get_payload(decode=True), teststr.encode('utf-8')) + + @unittest.skip("can't fix because of backward compat in email5, " + "will fix in email6") + def test_utf8_input_no_charset(self): + teststr = '\u043a\u0438\u0440\u0438\u043b\u0438\u0446\u0430' + self.assertRaises(UnicodeEncodeError, MIMEText, teststr) + + + +# Test complicated multipart/* messages +class TestMultipart(TestEmailBase): + def setUp(self): + with openfile('PyBanner048.gif', 'rb') as fp: + data = fp.read() + container = MIMEBase('multipart', 'mixed', boundary='BOUNDARY') + image = MIMEImage(data, name='dingusfish.gif') + image.add_header('content-disposition', 'attachment', + filename='dingusfish.gif') + intro = MIMEText('''\ +Hi there, + +This is the dingus fish. +''') + container.attach(intro) + container.attach(image) + container['From'] = 'Barry <barry@digicool.com>' + container['To'] = 'Dingus Lovers <cravindogs@cravindogs.com>' + container['Subject'] = 'Here is your dingus fish' + + now = 987809702.54848599 + timetuple = time.localtime(now) + if timetuple[-1] == 0: + tzsecs = time.timezone + else: + tzsecs = time.altzone + if tzsecs > 0: + sign = '-' + else: + sign = '+' + tzoffset = ' %s%04d' % (sign, tzsecs / 36) + container['Date'] = time.strftime( + '%a, %d %b %Y %H:%M:%S', + time.localtime(now)) + tzoffset + self._msg = container + self._im = image + self._txt = intro + + def test_hierarchy(self): + # convenience + eq = self.assertEqual + unless = self.assertTrue + raises = self.assertRaises + # tests + m = self._msg + unless(m.is_multipart()) + eq(m.get_content_type(), 'multipart/mixed') + eq(len(m.get_payload()), 2) + raises(IndexError, m.get_payload, 2) + m0 = m.get_payload(0) + m1 = m.get_payload(1) + unless(m0 is self._txt) + unless(m1 is self._im) + eq(m.get_payload(), [m0, m1]) + unless(not m0.is_multipart()) + unless(not m1.is_multipart()) + + def test_empty_multipart_idempotent(self): + text = """\ +Content-Type: multipart/mixed; boundary="BOUNDARY" +MIME-Version: 1.0 +Subject: A subject +To: aperson@dom.ain +From: bperson@dom.ain + + +--BOUNDARY + + +--BOUNDARY-- +""" + msg = Parser().parsestr(text) + self.ndiffAssertEqual(text, msg.as_string()) + + def test_no_parts_in_a_multipart_with_none_epilogue(self): + outer = MIMEBase('multipart', 'mixed') + outer['Subject'] = 'A subject' + outer['To'] = 'aperson@dom.ain' + outer['From'] = 'bperson@dom.ain' + outer.set_boundary('BOUNDARY') + self.ndiffAssertEqual(outer.as_string(), '''\ +Content-Type: multipart/mixed; boundary="BOUNDARY" +MIME-Version: 1.0 +Subject: A subject +To: aperson@dom.ain +From: bperson@dom.ain + +--BOUNDARY + +--BOUNDARY--''') + + def test_no_parts_in_a_multipart_with_empty_epilogue(self): + outer = MIMEBase('multipart', 'mixed') + outer['Subject'] = 'A subject' + outer['To'] = 'aperson@dom.ain' + outer['From'] = 'bperson@dom.ain' + outer.preamble = '' + outer.epilogue = '' + outer.set_boundary('BOUNDARY') + self.ndiffAssertEqual(outer.as_string(), '''\ +Content-Type: multipart/mixed; boundary="BOUNDARY" +MIME-Version: 1.0 +Subject: A subject +To: aperson@dom.ain +From: bperson@dom.ain + + +--BOUNDARY + +--BOUNDARY-- +''') + + def test_one_part_in_a_multipart(self): + eq = self.ndiffAssertEqual + outer = MIMEBase('multipart', 'mixed') + outer['Subject'] = 'A subject' + outer['To'] = 'aperson@dom.ain' + outer['From'] = 'bperson@dom.ain' + outer.set_boundary('BOUNDARY') + msg = MIMEText('hello world') + outer.attach(msg) + eq(outer.as_string(), '''\ +Content-Type: multipart/mixed; boundary="BOUNDARY" +MIME-Version: 1.0 +Subject: A subject +To: aperson@dom.ain +From: bperson@dom.ain + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +hello world +--BOUNDARY--''') + + def test_seq_parts_in_a_multipart_with_empty_preamble(self): + eq = self.ndiffAssertEqual + outer = MIMEBase('multipart', 'mixed') + outer['Subject'] = 'A subject' + outer['To'] = 'aperson@dom.ain' + outer['From'] = 'bperson@dom.ain' + outer.preamble = '' + msg = MIMEText('hello world') + outer.attach(msg) + outer.set_boundary('BOUNDARY') + eq(outer.as_string(), '''\ +Content-Type: multipart/mixed; boundary="BOUNDARY" +MIME-Version: 1.0 +Subject: A subject +To: aperson@dom.ain +From: bperson@dom.ain + + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +hello world +--BOUNDARY--''') + + + def test_seq_parts_in_a_multipart_with_none_preamble(self): + eq = self.ndiffAssertEqual + outer = MIMEBase('multipart', 'mixed') + outer['Subject'] = 'A subject' + outer['To'] = 'aperson@dom.ain' + outer['From'] = 'bperson@dom.ain' + outer.preamble = None + msg = MIMEText('hello world') + outer.attach(msg) + outer.set_boundary('BOUNDARY') + eq(outer.as_string(), '''\ +Content-Type: multipart/mixed; boundary="BOUNDARY" +MIME-Version: 1.0 +Subject: A subject +To: aperson@dom.ain +From: bperson@dom.ain + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +hello world +--BOUNDARY--''') + + + def test_seq_parts_in_a_multipart_with_none_epilogue(self): + eq = self.ndiffAssertEqual + outer = MIMEBase('multipart', 'mixed') + outer['Subject'] = 'A subject' + outer['To'] = 'aperson@dom.ain' + outer['From'] = 'bperson@dom.ain' + outer.epilogue = None + msg = MIMEText('hello world') + outer.attach(msg) + outer.set_boundary('BOUNDARY') + eq(outer.as_string(), '''\ +Content-Type: multipart/mixed; boundary="BOUNDARY" +MIME-Version: 1.0 +Subject: A subject +To: aperson@dom.ain +From: bperson@dom.ain + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +hello world +--BOUNDARY--''') + + + def test_seq_parts_in_a_multipart_with_empty_epilogue(self): + eq = self.ndiffAssertEqual + outer = MIMEBase('multipart', 'mixed') + outer['Subject'] = 'A subject' + outer['To'] = 'aperson@dom.ain' + outer['From'] = 'bperson@dom.ain' + outer.epilogue = '' + msg = MIMEText('hello world') + outer.attach(msg) + outer.set_boundary('BOUNDARY') + eq(outer.as_string(), '''\ +Content-Type: multipart/mixed; boundary="BOUNDARY" +MIME-Version: 1.0 +Subject: A subject +To: aperson@dom.ain +From: bperson@dom.ain + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +hello world +--BOUNDARY-- +''') + + + def test_seq_parts_in_a_multipart_with_nl_epilogue(self): + eq = self.ndiffAssertEqual + outer = MIMEBase('multipart', 'mixed') + outer['Subject'] = 'A subject' + outer['To'] = 'aperson@dom.ain' + outer['From'] = 'bperson@dom.ain' + outer.epilogue = '\n' + msg = MIMEText('hello world') + outer.attach(msg) + outer.set_boundary('BOUNDARY') + eq(outer.as_string(), '''\ +Content-Type: multipart/mixed; boundary="BOUNDARY" +MIME-Version: 1.0 +Subject: A subject +To: aperson@dom.ain +From: bperson@dom.ain + +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +hello world +--BOUNDARY-- + +''') + + def test_message_external_body(self): + eq = self.assertEqual + msg = self._msgobj('msg_36.txt') + eq(len(msg.get_payload()), 2) + msg1 = msg.get_payload(1) + eq(msg1.get_content_type(), 'multipart/alternative') + eq(len(msg1.get_payload()), 2) + for subpart in msg1.get_payload(): + eq(subpart.get_content_type(), 'message/external-body') + eq(len(subpart.get_payload()), 1) + subsubpart = subpart.get_payload(0) + eq(subsubpart.get_content_type(), 'text/plain') + + def test_double_boundary(self): + # msg_37.txt is a multipart that contains two dash-boundary's in a + # row. Our interpretation of RFC 2046 calls for ignoring the second + # and subsequent boundaries. + msg = self._msgobj('msg_37.txt') + self.assertEqual(len(msg.get_payload()), 3) + + def test_nested_inner_contains_outer_boundary(self): + eq = self.ndiffAssertEqual + # msg_38.txt has an inner part that contains outer boundaries. My + # interpretation of RFC 2046 (based on sections 5.1 and 5.1.2) say + # these are illegal and should be interpreted as unterminated inner + # parts. + msg = self._msgobj('msg_38.txt') + sfp = StringIO() + iterators._structure(msg, sfp) + eq(sfp.getvalue(), """\ +multipart/mixed + multipart/mixed + multipart/alternative + text/plain + text/plain + text/plain + text/plain +""") + + def test_nested_with_same_boundary(self): + eq = self.ndiffAssertEqual + # msg 39.txt is similarly evil in that it's got inner parts that use + # the same boundary as outer parts. Again, I believe the way this is + # parsed is closest to the spirit of RFC 2046 + msg = self._msgobj('msg_39.txt') + sfp = StringIO() + iterators._structure(msg, sfp) + eq(sfp.getvalue(), """\ +multipart/mixed + multipart/mixed + multipart/alternative + application/octet-stream + application/octet-stream + text/plain +""") + + def test_boundary_in_non_multipart(self): + msg = self._msgobj('msg_40.txt') + self.assertEqual(msg.as_string(), '''\ +MIME-Version: 1.0 +Content-Type: text/html; boundary="--961284236552522269" + +----961284236552522269 +Content-Type: text/html; +Content-Transfer-Encoding: 7Bit + +<html></html> + +----961284236552522269-- +''') + + def test_boundary_with_leading_space(self): + eq = self.assertEqual + msg = email.message_from_string('''\ +MIME-Version: 1.0 +Content-Type: multipart/mixed; boundary=" XXXX" + +-- XXXX +Content-Type: text/plain + + +-- XXXX +Content-Type: text/plain + +-- XXXX-- +''') + self.assertTrue(msg.is_multipart()) + eq(msg.get_boundary(), ' XXXX') + eq(len(msg.get_payload()), 2) + + def test_boundary_without_trailing_newline(self): + m = Parser().parsestr("""\ +Content-Type: multipart/mixed; boundary="===============0012394164==" +MIME-Version: 1.0 + +--===============0012394164== +Content-Type: image/file1.jpg +MIME-Version: 1.0 +Content-Transfer-Encoding: base64 + +YXNkZg== +--===============0012394164==--""") + self.assertEqual(m.get_payload(0).get_payload(), 'YXNkZg==') + + + +# Test some badly formatted messages +class TestNonConformant(TestEmailBase): + def test_parse_missing_minor_type(self): + eq = self.assertEqual + msg = self._msgobj('msg_14.txt') + eq(msg.get_content_type(), 'text/plain') + eq(msg.get_content_maintype(), 'text') + eq(msg.get_content_subtype(), 'plain') + + def test_same_boundary_inner_outer(self): + unless = self.assertTrue + msg = self._msgobj('msg_15.txt') + # XXX We can probably eventually do better + inner = msg.get_payload(0) + unless(hasattr(inner, 'defects')) + self.assertEqual(len(inner.defects), 1) + unless(isinstance(inner.defects[0], + errors.StartBoundaryNotFoundDefect)) + + def test_multipart_no_boundary(self): + unless = self.assertTrue + msg = self._msgobj('msg_25.txt') + unless(isinstance(msg.get_payload(), str)) + self.assertEqual(len(msg.defects), 2) + unless(isinstance(msg.defects[0], errors.NoBoundaryInMultipartDefect)) + unless(isinstance(msg.defects[1], + errors.MultipartInvariantViolationDefect)) + + def test_invalid_content_type(self): + eq = self.assertEqual + neq = self.ndiffAssertEqual + msg = Message() + # RFC 2045, $5.2 says invalid yields text/plain + msg['Content-Type'] = 'text' + eq(msg.get_content_maintype(), 'text') + eq(msg.get_content_subtype(), 'plain') + eq(msg.get_content_type(), 'text/plain') + # Clear the old value and try something /really/ invalid + del msg['content-type'] + msg['Content-Type'] = 'foo' + eq(msg.get_content_maintype(), 'text') + eq(msg.get_content_subtype(), 'plain') + eq(msg.get_content_type(), 'text/plain') + # Still, make sure that the message is idempotently generated + s = StringIO() + g = Generator(s) + g.flatten(msg) + neq(s.getvalue(), 'Content-Type: foo\n\n') + + def test_no_start_boundary(self): + eq = self.ndiffAssertEqual + msg = self._msgobj('msg_31.txt') + eq(msg.get_payload(), """\ +--BOUNDARY +Content-Type: text/plain + +message 1 + +--BOUNDARY +Content-Type: text/plain + +message 2 + +--BOUNDARY-- +""") + + def test_no_separating_blank_line(self): + eq = self.ndiffAssertEqual + msg = self._msgobj('msg_35.txt') + eq(msg.as_string(), """\ +From: aperson@dom.ain +To: bperson@dom.ain +Subject: here's something interesting + +counter to RFC 2822, there's no separating newline here +""") + + def test_lying_multipart(self): + unless = self.assertTrue + msg = self._msgobj('msg_41.txt') + unless(hasattr(msg, 'defects')) + self.assertEqual(len(msg.defects), 2) + unless(isinstance(msg.defects[0], errors.NoBoundaryInMultipartDefect)) + unless(isinstance(msg.defects[1], + errors.MultipartInvariantViolationDefect)) + + def test_missing_start_boundary(self): + outer = self._msgobj('msg_42.txt') + # The message structure is: + # + # multipart/mixed + # text/plain + # message/rfc822 + # multipart/mixed [*] + # + # [*] This message is missing its start boundary + bad = outer.get_payload(1).get_payload(0) + self.assertEqual(len(bad.defects), 1) + self.assertTrue(isinstance(bad.defects[0], + errors.StartBoundaryNotFoundDefect)) + + def test_first_line_is_continuation_header(self): + eq = self.assertEqual + m = ' Line 1\nLine 2\nLine 3' + msg = email.message_from_string(m) + eq(msg.keys(), []) + eq(msg.get_payload(), 'Line 2\nLine 3') + eq(len(msg.defects), 1) + self.assertTrue(isinstance(msg.defects[0], + errors.FirstHeaderLineIsContinuationDefect)) + eq(msg.defects[0].line, ' Line 1\n') + + + +# Test RFC 2047 header encoding and decoding +class TestRFC2047(TestEmailBase): + def test_rfc2047_multiline(self): + eq = self.assertEqual + s = """Re: =?mac-iceland?q?r=8Aksm=9Arg=8Cs?= baz + foo bar =?mac-iceland?q?r=8Aksm=9Arg=8Cs?=""" + dh = decode_header(s) + eq(dh, [ + (b'Re:', None), + (b'r\x8aksm\x9arg\x8cs', 'mac-iceland'), + (b'baz foo bar', None), + (b'r\x8aksm\x9arg\x8cs', 'mac-iceland')]) + header = make_header(dh) + eq(str(header), + 'Re: r\xe4ksm\xf6rg\xe5s baz foo bar r\xe4ksm\xf6rg\xe5s') + self.ndiffAssertEqual(header.encode(maxlinelen=76), """\ +Re: =?mac-iceland?q?r=8Aksm=9Arg=8Cs?= baz foo bar =?mac-iceland?q?r=8Aksm?= + =?mac-iceland?q?=9Arg=8Cs?=""") + + def test_whitespace_eater_unicode(self): + eq = self.assertEqual + s = '=?ISO-8859-1?Q?Andr=E9?= Pirard <pirard@dom.ain>' + dh = decode_header(s) + eq(dh, [(b'Andr\xe9', 'iso-8859-1'), + (b'Pirard <pirard@dom.ain>', None)]) + header = str(make_header(dh)) + eq(header, 'Andr\xe9 Pirard <pirard@dom.ain>') + + def test_whitespace_eater_unicode_2(self): + eq = self.assertEqual + s = 'The =?iso-8859-1?b?cXVpY2sgYnJvd24gZm94?= jumped over the =?iso-8859-1?b?bGF6eSBkb2c=?=' + dh = decode_header(s) + eq(dh, [(b'The', None), (b'quick brown fox', 'iso-8859-1'), + (b'jumped over the', None), (b'lazy dog', 'iso-8859-1')]) + hu = str(make_header(dh)) + eq(hu, 'The quick brown fox jumped over the lazy dog') + + def test_rfc2047_missing_whitespace(self): + s = 'Sm=?ISO-8859-1?B?9g==?=rg=?ISO-8859-1?B?5Q==?=sbord' + dh = decode_header(s) + self.assertEqual(dh, [(s, None)]) + + def test_rfc2047_with_whitespace(self): + s = 'Sm =?ISO-8859-1?B?9g==?= rg =?ISO-8859-1?B?5Q==?= sbord' + dh = decode_header(s) + self.assertEqual(dh, [(b'Sm', None), (b'\xf6', 'iso-8859-1'), + (b'rg', None), (b'\xe5', 'iso-8859-1'), + (b'sbord', None)]) + + def test_rfc2047_B_bad_padding(self): + s = '=?iso-8859-1?B?%s?=' + data = [ # only test complete bytes + ('dm==', b'v'), ('dm=', b'v'), ('dm', b'v'), + ('dmk=', b'vi'), ('dmk', b'vi') + ] + for q, a in data: + dh = decode_header(s % q) + self.assertEqual(dh, [(a, 'iso-8859-1')]) + + def test_rfc2047_Q_invalid_digits(self): + # issue 10004. + s = '=?iso-8659-1?Q?andr=e9=zz?=' + self.assertEqual(decode_header(s), + [(b'andr\xe9=zz', 'iso-8659-1')]) + + +# Test the MIMEMessage class +class TestMIMEMessage(TestEmailBase): + def setUp(self): + with openfile('msg_11.txt') as fp: + self._text = fp.read() + + def test_type_error(self): + self.assertRaises(TypeError, MIMEMessage, 'a plain string') + + def test_valid_argument(self): + eq = self.assertEqual + unless = self.assertTrue + subject = 'A sub-message' + m = Message() + m['Subject'] = subject + r = MIMEMessage(m) + eq(r.get_content_type(), 'message/rfc822') + payload = r.get_payload() + unless(isinstance(payload, list)) + eq(len(payload), 1) + subpart = payload[0] + unless(subpart is m) + eq(subpart['subject'], subject) + + def test_bad_multipart(self): + eq = self.assertEqual + msg1 = Message() + msg1['Subject'] = 'subpart 1' + msg2 = Message() + msg2['Subject'] = 'subpart 2' + r = MIMEMessage(msg1) + self.assertRaises(errors.MultipartConversionError, r.attach, msg2) + + def test_generate(self): + # First craft the message to be encapsulated + m = Message() + m['Subject'] = 'An enclosed message' + m.set_payload('Here is the body of the message.\n') + r = MIMEMessage(m) + r['Subject'] = 'The enclosing message' + s = StringIO() + g = Generator(s) + g.flatten(r) + self.assertEqual(s.getvalue(), """\ +Content-Type: message/rfc822 +MIME-Version: 1.0 +Subject: The enclosing message + +Subject: An enclosed message + +Here is the body of the message. +""") + + def test_parse_message_rfc822(self): + eq = self.assertEqual + unless = self.assertTrue + msg = self._msgobj('msg_11.txt') + eq(msg.get_content_type(), 'message/rfc822') + payload = msg.get_payload() + unless(isinstance(payload, list)) + eq(len(payload), 1) + submsg = payload[0] + self.assertTrue(isinstance(submsg, Message)) + eq(submsg['subject'], 'An enclosed message') + eq(submsg.get_payload(), 'Here is the body of the message.\n') + + def test_dsn(self): + eq = self.assertEqual + unless = self.assertTrue + # msg 16 is a Delivery Status Notification, see RFC 1894 + msg = self._msgobj('msg_16.txt') + eq(msg.get_content_type(), 'multipart/report') + unless(msg.is_multipart()) + eq(len(msg.get_payload()), 3) + # Subpart 1 is a text/plain, human readable section + subpart = msg.get_payload(0) + eq(subpart.get_content_type(), 'text/plain') + eq(subpart.get_payload(), """\ +This report relates to a message you sent with the following header fields: + + Message-id: <002001c144a6$8752e060$56104586@oxy.edu> + Date: Sun, 23 Sep 2001 20:10:55 -0700 + From: "Ian T. Henry" <henryi@oxy.edu> + To: SoCal Raves <scr@socal-raves.org> + Subject: [scr] yeah for Ians!! + +Your message cannot be delivered to the following recipients: + + Recipient address: jangel1@cougar.noc.ucla.edu + Reason: recipient reached disk quota + +""") + # Subpart 2 contains the machine parsable DSN information. It + # consists of two blocks of headers, represented by two nested Message + # objects. + subpart = msg.get_payload(1) + eq(subpart.get_content_type(), 'message/delivery-status') + eq(len(subpart.get_payload()), 2) + # message/delivery-status should treat each block as a bunch of + # headers, i.e. a bunch of Message objects. + dsn1 = subpart.get_payload(0) + unless(isinstance(dsn1, Message)) + eq(dsn1['original-envelope-id'], '0GK500B4HD0888@cougar.noc.ucla.edu') + eq(dsn1.get_param('dns', header='reporting-mta'), '') + # Try a missing one <wink> + eq(dsn1.get_param('nsd', header='reporting-mta'), None) + dsn2 = subpart.get_payload(1) + unless(isinstance(dsn2, Message)) + eq(dsn2['action'], 'failed') + eq(dsn2.get_params(header='original-recipient'), + [('rfc822', ''), ('jangel1@cougar.noc.ucla.edu', '')]) + eq(dsn2.get_param('rfc822', header='final-recipient'), '') + # Subpart 3 is the original message + subpart = msg.get_payload(2) + eq(subpart.get_content_type(), 'message/rfc822') + payload = subpart.get_payload() + unless(isinstance(payload, list)) + eq(len(payload), 1) + subsubpart = payload[0] + unless(isinstance(subsubpart, Message)) + eq(subsubpart.get_content_type(), 'text/plain') + eq(subsubpart['message-id'], + '<002001c144a6$8752e060$56104586@oxy.edu>') + + def test_epilogue(self): + eq = self.ndiffAssertEqual + with openfile('msg_21.txt') as fp: + text = fp.read() + msg = Message() + msg['From'] = 'aperson@dom.ain' + msg['To'] = 'bperson@dom.ain' + msg['Subject'] = 'Test' + msg.preamble = 'MIME message' + msg.epilogue = 'End of MIME message\n' + msg1 = MIMEText('One') + msg2 = MIMEText('Two') + msg.add_header('Content-Type', 'multipart/mixed', boundary='BOUNDARY') + msg.attach(msg1) + msg.attach(msg2) + sfp = StringIO() + g = Generator(sfp) + g.flatten(msg) + eq(sfp.getvalue(), text) + + def test_no_nl_preamble(self): + eq = self.ndiffAssertEqual + msg = Message() + msg['From'] = 'aperson@dom.ain' + msg['To'] = 'bperson@dom.ain' + msg['Subject'] = 'Test' + msg.preamble = 'MIME message' + msg.epilogue = '' + msg1 = MIMEText('One') + msg2 = MIMEText('Two') + msg.add_header('Content-Type', 'multipart/mixed', boundary='BOUNDARY') + msg.attach(msg1) + msg.attach(msg2) + eq(msg.as_string(), """\ +From: aperson@dom.ain +To: bperson@dom.ain +Subject: Test +Content-Type: multipart/mixed; boundary="BOUNDARY" + +MIME message +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +One +--BOUNDARY +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +Two +--BOUNDARY-- +""") + + def test_default_type(self): + eq = self.assertEqual + with openfile('msg_30.txt') as fp: + msg = email.message_from_file(fp) + container1 = msg.get_payload(0) + eq(container1.get_default_type(), 'message/rfc822') + eq(container1.get_content_type(), 'message/rfc822') + container2 = msg.get_payload(1) + eq(container2.get_default_type(), 'message/rfc822') + eq(container2.get_content_type(), 'message/rfc822') + container1a = container1.get_payload(0) + eq(container1a.get_default_type(), 'text/plain') + eq(container1a.get_content_type(), 'text/plain') + container2a = container2.get_payload(0) + eq(container2a.get_default_type(), 'text/plain') + eq(container2a.get_content_type(), 'text/plain') + + def test_default_type_with_explicit_container_type(self): + eq = self.assertEqual + with openfile('msg_28.txt') as fp: + msg = email.message_from_file(fp) + container1 = msg.get_payload(0) + eq(container1.get_default_type(), 'message/rfc822') + eq(container1.get_content_type(), 'message/rfc822') + container2 = msg.get_payload(1) + eq(container2.get_default_type(), 'message/rfc822') + eq(container2.get_content_type(), 'message/rfc822') + container1a = container1.get_payload(0) + eq(container1a.get_default_type(), 'text/plain') + eq(container1a.get_content_type(), 'text/plain') + container2a = container2.get_payload(0) + eq(container2a.get_default_type(), 'text/plain') + eq(container2a.get_content_type(), 'text/plain') + + def test_default_type_non_parsed(self): + eq = self.assertEqual + neq = self.ndiffAssertEqual + # Set up container + container = MIMEMultipart('digest', 'BOUNDARY') + container.epilogue = '' + # Set up subparts + subpart1a = MIMEText('message 1\n') + subpart2a = MIMEText('message 2\n') + subpart1 = MIMEMessage(subpart1a) + subpart2 = MIMEMessage(subpart2a) + container.attach(subpart1) + container.attach(subpart2) + eq(subpart1.get_content_type(), 'message/rfc822') + eq(subpart1.get_default_type(), 'message/rfc822') + eq(subpart2.get_content_type(), 'message/rfc822') + eq(subpart2.get_default_type(), 'message/rfc822') + neq(container.as_string(0), '''\ +Content-Type: multipart/digest; boundary="BOUNDARY" +MIME-Version: 1.0 + +--BOUNDARY +Content-Type: message/rfc822 +MIME-Version: 1.0 + +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +message 1 + +--BOUNDARY +Content-Type: message/rfc822 +MIME-Version: 1.0 + +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +message 2 + +--BOUNDARY-- +''') + del subpart1['content-type'] + del subpart1['mime-version'] + del subpart2['content-type'] + del subpart2['mime-version'] + eq(subpart1.get_content_type(), 'message/rfc822') + eq(subpart1.get_default_type(), 'message/rfc822') + eq(subpart2.get_content_type(), 'message/rfc822') + eq(subpart2.get_default_type(), 'message/rfc822') + neq(container.as_string(0), '''\ +Content-Type: multipart/digest; boundary="BOUNDARY" +MIME-Version: 1.0 + +--BOUNDARY + +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +message 1 + +--BOUNDARY + +Content-Type: text/plain; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit + +message 2 + +--BOUNDARY-- +''') + + def test_mime_attachments_in_constructor(self): + eq = self.assertEqual + text1 = MIMEText('') + text2 = MIMEText('') + msg = MIMEMultipart(_subparts=(text1, text2)) + eq(len(msg.get_payload()), 2) + eq(msg.get_payload(0), text1) + eq(msg.get_payload(1), text2) + + def test_default_multipart_constructor(self): + msg = MIMEMultipart() + self.assertTrue(msg.is_multipart()) + + +# A general test of parser->model->generator idempotency. IOW, read a message +# in, parse it into a message object tree, then without touching the tree, +# regenerate the plain text. The original text and the transformed text +# should be identical. Note: that we ignore the Unix-From since that may +# contain a changed date. +class TestIdempotent(TestEmailBase): + + linesep = '\n' + + def _msgobj(self, filename): + with openfile(filename) as fp: + data = fp.read() + msg = email.message_from_string(data) + return msg, data + + def _idempotent(self, msg, text, unixfrom=False): + eq = self.ndiffAssertEqual + s = StringIO() + g = Generator(s, maxheaderlen=0) + g.flatten(msg, unixfrom=unixfrom) + eq(text, s.getvalue()) + + def test_parse_text_message(self): + eq = self.assertEqual + msg, text = self._msgobj('msg_01.txt') + eq(msg.get_content_type(), 'text/plain') + eq(msg.get_content_maintype(), 'text') + eq(msg.get_content_subtype(), 'plain') + eq(msg.get_params()[1], ('charset', 'us-ascii')) + eq(msg.get_param('charset'), 'us-ascii') + eq(msg.preamble, None) + eq(msg.epilogue, None) + self._idempotent(msg, text) + + def test_parse_untyped_message(self): + eq = self.assertEqual + msg, text = self._msgobj('msg_03.txt') + eq(msg.get_content_type(), 'text/plain') + eq(msg.get_params(), None) + eq(msg.get_param('charset'), None) + self._idempotent(msg, text) + + def test_simple_multipart(self): + msg, text = self._msgobj('msg_04.txt') + self._idempotent(msg, text) + + def test_MIME_digest(self): + msg, text = self._msgobj('msg_02.txt') + self._idempotent(msg, text) + + def test_long_header(self): + msg, text = self._msgobj('msg_27.txt') + self._idempotent(msg, text) + + def test_MIME_digest_with_part_headers(self): + msg, text = self._msgobj('msg_28.txt') + self._idempotent(msg, text) + + def test_mixed_with_image(self): + msg, text = self._msgobj('msg_06.txt') + self._idempotent(msg, text) + + def test_multipart_report(self): + msg, text = self._msgobj('msg_05.txt') + self._idempotent(msg, text) + + def test_dsn(self): + msg, text = self._msgobj('msg_16.txt') + self._idempotent(msg, text) + + def test_preamble_epilogue(self): + msg, text = self._msgobj('msg_21.txt') + self._idempotent(msg, text) + + def test_multipart_one_part(self): + msg, text = self._msgobj('msg_23.txt') + self._idempotent(msg, text) + + def test_multipart_no_parts(self): + msg, text = self._msgobj('msg_24.txt') + self._idempotent(msg, text) + + def test_no_start_boundary(self): + msg, text = self._msgobj('msg_31.txt') + self._idempotent(msg, text) + + def test_rfc2231_charset(self): + msg, text = self._msgobj('msg_32.txt') + self._idempotent(msg, text) + + def test_more_rfc2231_parameters(self): + msg, text = self._msgobj('msg_33.txt') + self._idempotent(msg, text) + + def test_text_plain_in_a_multipart_digest(self): + msg, text = self._msgobj('msg_34.txt') + self._idempotent(msg, text) + + def test_nested_multipart_mixeds(self): + msg, text = self._msgobj('msg_12a.txt') + self._idempotent(msg, text) + + def test_message_external_body_idempotent(self): + msg, text = self._msgobj('msg_36.txt') + self._idempotent(msg, text) + + def test_message_delivery_status(self): + msg, text = self._msgobj('msg_43.txt') + self._idempotent(msg, text, unixfrom=True) + + def test_message_signed_idempotent(self): + msg, text = self._msgobj('msg_45.txt') + self._idempotent(msg, text) + + def test_content_type(self): + eq = self.assertEqual + unless = self.assertTrue + # Get a message object and reset the seek pointer for other tests + msg, text = self._msgobj('msg_05.txt') + eq(msg.get_content_type(), 'multipart/report') + # Test the Content-Type: parameters + params = {} + for pk, pv in msg.get_params(): + params[pk] = pv + eq(params['report-type'], 'delivery-status') + eq(params['boundary'], 'D1690A7AC1.996856090/mail.example.com') + eq(msg.preamble, 'This is a MIME-encapsulated message.' + self.linesep) + eq(msg.epilogue, self.linesep) + eq(len(msg.get_payload()), 3) + # Make sure the subparts are what we expect + msg1 = msg.get_payload(0) + eq(msg1.get_content_type(), 'text/plain') + eq(msg1.get_payload(), 'Yadda yadda yadda' + self.linesep) + msg2 = msg.get_payload(1) + eq(msg2.get_content_type(), 'text/plain') + eq(msg2.get_payload(), 'Yadda yadda yadda' + self.linesep) + msg3 = msg.get_payload(2) + eq(msg3.get_content_type(), 'message/rfc822') + self.assertTrue(isinstance(msg3, Message)) + payload = msg3.get_payload() + unless(isinstance(payload, list)) + eq(len(payload), 1) + msg4 = payload[0] + unless(isinstance(msg4, Message)) + eq(msg4.get_payload(), 'Yadda yadda yadda' + self.linesep) + + def test_parser(self): + eq = self.assertEqual + unless = self.assertTrue + msg, text = self._msgobj('msg_06.txt') + # Check some of the outer headers + eq(msg.get_content_type(), 'message/rfc822') + # Make sure the payload is a list of exactly one sub-Message, and that + # that submessage has a type of text/plain + payload = msg.get_payload() + unless(isinstance(payload, list)) + eq(len(payload), 1) + msg1 = payload[0] + self.assertTrue(isinstance(msg1, Message)) + eq(msg1.get_content_type(), 'text/plain') + self.assertTrue(isinstance(msg1.get_payload(), str)) + eq(msg1.get_payload(), self.linesep) + + + +# Test various other bits of the package's functionality +class TestMiscellaneous(TestEmailBase): + def test_message_from_string(self): + with openfile('msg_01.txt') as fp: + text = fp.read() + msg = email.message_from_string(text) + s = StringIO() + # Don't wrap/continue long headers since we're trying to test + # idempotency. + g = Generator(s, maxheaderlen=0) + g.flatten(msg) + self.assertEqual(text, s.getvalue()) + + def test_message_from_file(self): + with openfile('msg_01.txt') as fp: + text = fp.read() + fp.seek(0) + msg = email.message_from_file(fp) + s = StringIO() + # Don't wrap/continue long headers since we're trying to test + # idempotency. + g = Generator(s, maxheaderlen=0) + g.flatten(msg) + self.assertEqual(text, s.getvalue()) + + def test_message_from_string_with_class(self): + unless = self.assertTrue + with openfile('msg_01.txt') as fp: + text = fp.read() + + # Create a subclass + class MyMessage(Message): + pass + + msg = email.message_from_string(text, MyMessage) + unless(isinstance(msg, MyMessage)) + # Try something more complicated + with openfile('msg_02.txt') as fp: + text = fp.read() + msg = email.message_from_string(text, MyMessage) + for subpart in msg.walk(): + unless(isinstance(subpart, MyMessage)) + + def test_message_from_file_with_class(self): + unless = self.assertTrue + # Create a subclass + class MyMessage(Message): + pass + + with openfile('msg_01.txt') as fp: + msg = email.message_from_file(fp, MyMessage) + unless(isinstance(msg, MyMessage)) + # Try something more complicated + with openfile('msg_02.txt') as fp: + msg = email.message_from_file(fp, MyMessage) + for subpart in msg.walk(): + unless(isinstance(subpart, MyMessage)) + + def test__all__(self): + module = __import__('email') + # Can't use sorted() here due to Python 2.3 compatibility + all = module.__all__[:] + all.sort() + self.assertEqual(all, [ + 'base64mime', 'charset', 'encoders', 'errors', 'generator', + 'header', 'iterators', 'message', 'message_from_binary_file', + 'message_from_bytes', 'message_from_file', + 'message_from_string', 'mime', 'parser', + 'quoprimime', 'utils', + ]) + + def test_formatdate(self): + now = time.time() + self.assertEqual(utils.parsedate(utils.formatdate(now))[:6], + time.gmtime(now)[:6]) + + def test_formatdate_localtime(self): + now = time.time() + self.assertEqual( + utils.parsedate(utils.formatdate(now, localtime=True))[:6], + time.localtime(now)[:6]) + + def test_formatdate_usegmt(self): + now = time.time() + self.assertEqual( + utils.formatdate(now, localtime=False), + time.strftime('%a, %d %b %Y %H:%M:%S -0000', time.gmtime(now))) + self.assertEqual( + utils.formatdate(now, localtime=False, usegmt=True), + time.strftime('%a, %d %b %Y %H:%M:%S GMT', time.gmtime(now))) + + def test_parsedate_none(self): + self.assertEqual(utils.parsedate(''), None) + + def test_parsedate_compact(self): + # The FWS after the comma is optional + self.assertEqual(utils.parsedate('Wed,3 Apr 2002 14:58:26 +0800'), + utils.parsedate('Wed, 3 Apr 2002 14:58:26 +0800')) + + def test_parsedate_no_dayofweek(self): + eq = self.assertEqual + eq(utils.parsedate_tz('25 Feb 2003 13:47:26 -0800'), + (2003, 2, 25, 13, 47, 26, 0, 1, -1, -28800)) + + def test_parsedate_compact_no_dayofweek(self): + eq = self.assertEqual + eq(utils.parsedate_tz('5 Feb 2003 13:47:26 -0800'), + (2003, 2, 5, 13, 47, 26, 0, 1, -1, -28800)) + + def test_parsedate_no_space_before_positive_offset(self): + self.assertEqual(utils.parsedate_tz('Wed, 3 Apr 2002 14:58:26+0800'), + (2002, 4, 3, 14, 58, 26, 0, 1, -1, 28800)) + + def test_parsedate_no_space_before_negative_offset(self): + # Issue 1155362: we already handled '+' for this case. + self.assertEqual(utils.parsedate_tz('Wed, 3 Apr 2002 14:58:26-0800'), + (2002, 4, 3, 14, 58, 26, 0, 1, -1, -28800)) + + + def test_parsedate_accepts_time_with_dots(self): + eq = self.assertEqual + eq(utils.parsedate_tz('5 Feb 2003 13.47.26 -0800'), + (2003, 2, 5, 13, 47, 26, 0, 1, -1, -28800)) + eq(utils.parsedate_tz('5 Feb 2003 13.47 -0800'), + (2003, 2, 5, 13, 47, 0, 0, 1, -1, -28800)) + + def test_parsedate_acceptable_to_time_functions(self): + eq = self.assertEqual + timetup = utils.parsedate('5 Feb 2003 13:47:26 -0800') + t = int(time.mktime(timetup)) + eq(time.localtime(t)[:6], timetup[:6]) + eq(int(time.strftime('%Y', timetup)), 2003) + timetup = utils.parsedate_tz('5 Feb 2003 13:47:26 -0800') + t = int(time.mktime(timetup[:9])) + eq(time.localtime(t)[:6], timetup[:6]) + eq(int(time.strftime('%Y', timetup[:9])), 2003) + + def test_parsedate_y2k(self): + """Test for parsing a date with a two-digit year. + + Parsing a date with a two-digit year should return the correct + four-digit year. RFC822 allows two-digit years, but RFC2822 (which + obsoletes RFC822) requires four-digit years. + + """ + self.assertEqual(utils.parsedate_tz('25 Feb 03 13:47:26 -0800'), + utils.parsedate_tz('25 Feb 2003 13:47:26 -0800')) + self.assertEqual(utils.parsedate_tz('25 Feb 71 13:47:26 -0800'), + utils.parsedate_tz('25 Feb 1971 13:47:26 -0800')) + + def test_parseaddr_empty(self): + self.assertEqual(utils.parseaddr('<>'), ('', '')) + self.assertEqual(utils.formataddr(utils.parseaddr('<>')), '') + + def test_noquote_dump(self): + self.assertEqual( + utils.formataddr(('A Silly Person', 'person@dom.ain')), + 'A Silly Person <person@dom.ain>') + + def test_escape_dump(self): + self.assertEqual( + utils.formataddr(('A (Very) Silly Person', 'person@dom.ain')), + r'"A \(Very\) Silly Person" <person@dom.ain>') + a = r'A \(Special\) Person' + b = 'person@dom.ain' + self.assertEqual(utils.parseaddr(utils.formataddr((a, b))), (a, b)) + + def test_escape_backslashes(self): + self.assertEqual( + utils.formataddr(('Arthur \Backslash\ Foobar', 'person@dom.ain')), + r'"Arthur \\Backslash\\ Foobar" <person@dom.ain>') + a = r'Arthur \Backslash\ Foobar' + b = 'person@dom.ain' + self.assertEqual(utils.parseaddr(utils.formataddr((a, b))), (a, b)) + + def test_name_with_dot(self): + x = 'John X. Doe <jxd@example.com>' + y = '"John X. Doe" <jxd@example.com>' + a, b = ('John X. Doe', 'jxd@example.com') + self.assertEqual(utils.parseaddr(x), (a, b)) + self.assertEqual(utils.parseaddr(y), (a, b)) + # formataddr() quotes the name if there's a dot in it + self.assertEqual(utils.formataddr((a, b)), y) + + def test_parseaddr_preserves_quoted_pairs_in_addresses(self): + # issue 10005. Note that in the third test the second pair of + # backslashes is not actually a quoted pair because it is not inside a + # comment or quoted string: the address being parsed has a quoted + # string containing a quoted backslash, followed by 'example' and two + # backslashes, followed by another quoted string containing a space and + # the word 'example'. parseaddr copies those two backslashes + # literally. Per rfc5322 this is not technically correct since a \ may + # not appear in an address outside of a quoted string. It is probably + # a sensible Postel interpretation, though. + eq = self.assertEqual + eq(utils.parseaddr('""example" example"@example.com'), + ('', '""example" example"@example.com')) + eq(utils.parseaddr('"\\"example\\" example"@example.com'), + ('', '"\\"example\\" example"@example.com')) + eq(utils.parseaddr('"\\\\"example\\\\" example"@example.com'), + ('', '"\\\\"example\\\\" example"@example.com')) + + def test_parseaddr_preserves_spaces_in_local_part(self): + # issue 9286. A normal RFC5322 local part should not contain any + # folding white space, but legacy local parts can (they are a sequence + # of atoms, not dotatoms). On the other hand we strip whitespace from + # before the @ and around dots, on the assumption that the whitespace + # around the punctuation is a mistake in what would otherwise be + # an RFC5322 local part. Leading whitespace is, usual, stripped as well. + self.assertEqual(('', "merwok wok@xample.com"), + utils.parseaddr("merwok wok@xample.com")) + self.assertEqual(('', "merwok wok@xample.com"), + utils.parseaddr("merwok wok@xample.com")) + self.assertEqual(('', "merwok wok@xample.com"), + utils.parseaddr(" merwok wok @xample.com")) + self.assertEqual(('', 'merwok"wok" wok@xample.com'), + utils.parseaddr('merwok"wok" wok@xample.com')) + self.assertEqual(('', 'merwok.wok.wok@xample.com'), + utils.parseaddr('merwok. wok . wok@xample.com')) + + def test_multiline_from_comment(self): + x = """\ +Foo +\tBar <foo@example.com>""" + self.assertEqual(utils.parseaddr(x), ('Foo Bar', 'foo@example.com')) + + def test_quote_dump(self): + self.assertEqual( + utils.formataddr(('A Silly; Person', 'person@dom.ain')), + r'"A Silly; Person" <person@dom.ain>') + + def test_charset_richcomparisons(self): + eq = self.assertEqual + ne = self.assertNotEqual + cset1 = Charset() + cset2 = Charset() + eq(cset1, 'us-ascii') + eq(cset1, 'US-ASCII') + eq(cset1, 'Us-AsCiI') + eq('us-ascii', cset1) + eq('US-ASCII', cset1) + eq('Us-AsCiI', cset1) + ne(cset1, 'usascii') + ne(cset1, 'USASCII') + ne(cset1, 'UsAsCiI') + ne('usascii', cset1) + ne('USASCII', cset1) + ne('UsAsCiI', cset1) + eq(cset1, cset2) + eq(cset2, cset1) + + def test_getaddresses(self): + eq = self.assertEqual + eq(utils.getaddresses(['aperson@dom.ain (Al Person)', + 'Bud Person <bperson@dom.ain>']), + [('Al Person', 'aperson@dom.ain'), + ('Bud Person', 'bperson@dom.ain')]) + + def test_getaddresses_nasty(self): + eq = self.assertEqual + eq(utils.getaddresses(['foo: ;']), [('', '')]) + eq(utils.getaddresses( + ['[]*-- =~$']), + [('', ''), ('', ''), ('', '*--')]) + eq(utils.getaddresses( + ['foo: ;', '"Jason R. Mastaler" <jason@dom.ain>']), + [('', ''), ('Jason R. Mastaler', 'jason@dom.ain')]) + + def test_getaddresses_embedded_comment(self): + """Test proper handling of a nested comment""" + eq = self.assertEqual + addrs = utils.getaddresses(['User ((nested comment)) <foo@bar.com>']) + eq(addrs[0][1], 'foo@bar.com') + + def test_utils_quote_unquote(self): + eq = self.assertEqual + msg = Message() + msg.add_header('content-disposition', 'attachment', + filename='foo\\wacky"name') + eq(msg.get_filename(), 'foo\\wacky"name') + + def test_get_body_encoding_with_bogus_charset(self): + charset = Charset('not a charset') + self.assertEqual(charset.get_body_encoding(), 'base64') + + def test_get_body_encoding_with_uppercase_charset(self): + eq = self.assertEqual + msg = Message() + msg['Content-Type'] = 'text/plain; charset=UTF-8' + eq(msg['content-type'], 'text/plain; charset=UTF-8') + charsets = msg.get_charsets() + eq(len(charsets), 1) + eq(charsets[0], 'utf-8') + charset = Charset(charsets[0]) + eq(charset.get_body_encoding(), 'base64') + msg.set_payload(b'hello world', charset=charset) + eq(msg.get_payload(), 'aGVsbG8gd29ybGQ=\n') + eq(msg.get_payload(decode=True), b'hello world') + eq(msg['content-transfer-encoding'], 'base64') + # Try another one + msg = Message() + msg['Content-Type'] = 'text/plain; charset="US-ASCII"' + charsets = msg.get_charsets() + eq(len(charsets), 1) + eq(charsets[0], 'us-ascii') + charset = Charset(charsets[0]) + eq(charset.get_body_encoding(), encoders.encode_7or8bit) + msg.set_payload('hello world', charset=charset) + eq(msg.get_payload(), 'hello world') + eq(msg['content-transfer-encoding'], '7bit') + + def test_charsets_case_insensitive(self): + lc = Charset('us-ascii') + uc = Charset('US-ASCII') + self.assertEqual(lc.get_body_encoding(), uc.get_body_encoding()) + + def test_partial_falls_inside_message_delivery_status(self): + eq = self.ndiffAssertEqual + # The Parser interface provides chunks of data to FeedParser in 8192 + # byte gulps. SF bug #1076485 found one of those chunks inside + # message/delivery-status header block, which triggered an + # unreadline() of NeedMoreData. + msg = self._msgobj('msg_43.txt') + sfp = StringIO() + iterators._structure(msg, sfp) + eq(sfp.getvalue(), """\ +multipart/report + text/plain + message/delivery-status + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/plain + text/rfc822-headers +""") + + def test_make_msgid_domain(self): + self.assertEqual( + email.utils.make_msgid(domain='testdomain-string')[-19:], + '@testdomain-string>') + + +# Test the iterator/generators +class TestIterators(TestEmailBase): + def test_body_line_iterator(self): + eq = self.assertEqual + neq = self.ndiffAssertEqual + # First a simple non-multipart message + msg = self._msgobj('msg_01.txt') + it = iterators.body_line_iterator(msg) + lines = list(it) + eq(len(lines), 6) + neq(EMPTYSTRING.join(lines), msg.get_payload()) + # Now a more complicated multipart + msg = self._msgobj('msg_02.txt') + it = iterators.body_line_iterator(msg) + lines = list(it) + eq(len(lines), 43) + with openfile('msg_19.txt') as fp: + neq(EMPTYSTRING.join(lines), fp.read()) + + def test_typed_subpart_iterator(self): + eq = self.assertEqual + msg = self._msgobj('msg_04.txt') + it = iterators.typed_subpart_iterator(msg, 'text') + lines = [] + subparts = 0 + for subpart in it: + subparts += 1 + lines.append(subpart.get_payload()) + eq(subparts, 2) + eq(EMPTYSTRING.join(lines), """\ +a simple kind of mirror +to reflect upon our own +a simple kind of mirror +to reflect upon our own +""") + + def test_typed_subpart_iterator_default_type(self): + eq = self.assertEqual + msg = self._msgobj('msg_03.txt') + it = iterators.typed_subpart_iterator(msg, 'text', 'plain') + lines = [] + subparts = 0 + for subpart in it: + subparts += 1 + lines.append(subpart.get_payload()) + eq(subparts, 1) + eq(EMPTYSTRING.join(lines), """\ + +Hi, + +Do you like this message? + +-Me +""") + + def test_pushCR_LF(self): + '''FeedParser BufferedSubFile.push() assumed it received complete + line endings. A CR ending one push() followed by a LF starting + the next push() added an empty line. + ''' + imt = [ + ("a\r \n", 2), + ("b", 0), + ("c\n", 1), + ("", 0), + ("d\r\n", 1), + ("e\r", 0), + ("\nf", 1), + ("\r\n", 1), + ] + from email.feedparser import BufferedSubFile, NeedMoreData + bsf = BufferedSubFile() + om = [] + nt = 0 + for il, n in imt: + bsf.push(il) + nt += n + n1 = 0 + while True: + ol = bsf.readline() + if ol == NeedMoreData: + break + om.append(ol) + n1 += 1 + self.assertTrue(n == n1) + self.assertTrue(len(om) == nt) + self.assertTrue(''.join([il for il, n in imt]) == ''.join(om)) + + + +class TestParsers(TestEmailBase): + def test_header_parser(self): + eq = self.assertEqual + # Parse only the headers of a complex multipart MIME document + with openfile('msg_02.txt') as fp: + msg = HeaderParser().parse(fp) + eq(msg['from'], 'ppp-request@zzz.org') + eq(msg['to'], 'ppp@zzz.org') + eq(msg.get_content_type(), 'multipart/mixed') + self.assertFalse(msg.is_multipart()) + self.assertTrue(isinstance(msg.get_payload(), str)) + + def test_whitespace_continuation(self): + eq = self.assertEqual + # This message contains a line after the Subject: header that has only + # whitespace, but it is not empty! + msg = email.message_from_string("""\ +From: aperson@dom.ain +To: bperson@dom.ain +Subject: the next line has a space on it +\x20 +Date: Mon, 8 Apr 2002 15:09:19 -0400 +Message-ID: spam + +Here's the message body +""") + eq(msg['subject'], 'the next line has a space on it\n ') + eq(msg['message-id'], 'spam') + eq(msg.get_payload(), "Here's the message body\n") + + def test_whitespace_continuation_last_header(self): + eq = self.assertEqual + # Like the previous test, but the subject line is the last + # header. + msg = email.message_from_string("""\ +From: aperson@dom.ain +To: bperson@dom.ain +Date: Mon, 8 Apr 2002 15:09:19 -0400 +Message-ID: spam +Subject: the next line has a space on it +\x20 + +Here's the message body +""") + eq(msg['subject'], 'the next line has a space on it\n ') + eq(msg['message-id'], 'spam') + eq(msg.get_payload(), "Here's the message body\n") + + def test_crlf_separation(self): + eq = self.assertEqual + with openfile('msg_26.txt', newline='\n') as fp: + msg = Parser().parse(fp) + eq(len(msg.get_payload()), 2) + part1 = msg.get_payload(0) + eq(part1.get_content_type(), 'text/plain') + eq(part1.get_payload(), 'Simple email with attachment.\r\n\r\n') + part2 = msg.get_payload(1) + eq(part2.get_content_type(), 'application/riscos') + + def test_crlf_flatten(self): + # Using newline='\n' preserves the crlfs in this input file. + with openfile('msg_26.txt', newline='\n') as fp: + text = fp.read() + msg = email.message_from_string(text) + s = StringIO() + g = Generator(s) + g.flatten(msg, linesep='\r\n') + self.assertEqual(s.getvalue(), text) + + maxDiff = None + + def test_multipart_digest_with_extra_mime_headers(self): + eq = self.assertEqual + neq = self.ndiffAssertEqual + with openfile('msg_28.txt') as fp: + msg = email.message_from_file(fp) + # Structure is: + # multipart/digest + # message/rfc822 + # text/plain + # message/rfc822 + # text/plain + eq(msg.is_multipart(), 1) + eq(len(msg.get_payload()), 2) + part1 = msg.get_payload(0) + eq(part1.get_content_type(), 'message/rfc822') + eq(part1.is_multipart(), 1) + eq(len(part1.get_payload()), 1) + part1a = part1.get_payload(0) + eq(part1a.is_multipart(), 0) + eq(part1a.get_content_type(), 'text/plain') + neq(part1a.get_payload(), 'message 1\n') + # next message/rfc822 + part2 = msg.get_payload(1) + eq(part2.get_content_type(), 'message/rfc822') + eq(part2.is_multipart(), 1) + eq(len(part2.get_payload()), 1) + part2a = part2.get_payload(0) + eq(part2a.is_multipart(), 0) + eq(part2a.get_content_type(), 'text/plain') + neq(part2a.get_payload(), 'message 2\n') + + def test_three_lines(self): + # A bug report by Andrew McNamara + lines = ['From: Andrew Person <aperson@dom.ain', + 'Subject: Test', + 'Date: Tue, 20 Aug 2002 16:43:45 +1000'] + msg = email.message_from_string(NL.join(lines)) + self.assertEqual(msg['date'], 'Tue, 20 Aug 2002 16:43:45 +1000') + + def test_strip_line_feed_and_carriage_return_in_headers(self): + eq = self.assertEqual + # For [ 1002475 ] email message parser doesn't handle \r\n correctly + value1 = 'text' + value2 = 'more text' + m = 'Header: %s\r\nNext-Header: %s\r\n\r\nBody\r\n\r\n' % ( + value1, value2) + msg = email.message_from_string(m) + eq(msg.get('Header'), value1) + eq(msg.get('Next-Header'), value2) + + def test_rfc2822_header_syntax(self): + eq = self.assertEqual + m = '>From: foo\nFrom: bar\n!"#QUX;~: zoo\n\nbody' + msg = email.message_from_string(m) + eq(len(msg), 3) + eq(sorted(field for field in msg), ['!"#QUX;~', '>From', 'From']) + eq(msg.get_payload(), 'body') + + def test_rfc2822_space_not_allowed_in_header(self): + eq = self.assertEqual + m = '>From foo@example.com 11:25:53\nFrom: bar\n!"#QUX;~: zoo\n\nbody' + msg = email.message_from_string(m) + eq(len(msg.keys()), 0) + + def test_rfc2822_one_character_header(self): + eq = self.assertEqual + m = 'A: first header\nB: second header\nCC: third header\n\nbody' + msg = email.message_from_string(m) + headers = msg.keys() + headers.sort() + eq(headers, ['A', 'B', 'CC']) + eq(msg.get_payload(), 'body') + + def test_CRLFLF_at_end_of_part(self): + # issue 5610: feedparser should not eat two chars from body part ending + # with "\r\n\n". + m = ( + "From: foo@bar.com\n" + "To: baz\n" + "Mime-Version: 1.0\n" + "Content-Type: multipart/mixed; boundary=BOUNDARY\n" + "\n" + "--BOUNDARY\n" + "Content-Type: text/plain\n" + "\n" + "body ending with CRLF newline\r\n" + "\n" + "--BOUNDARY--\n" + ) + msg = email.message_from_string(m) + self.assertTrue(msg.get_payload(0).get_payload().endswith('\r\n')) + + +class Test8BitBytesHandling(unittest.TestCase): + # In Python3 all input is string, but that doesn't work if the actual input + # uses an 8bit transfer encoding. To hack around that, in email 5.1 we + # decode byte streams using the surrogateescape error handler, and + # reconvert to binary at appropriate places if we detect surrogates. This + # doesn't allow us to transform headers with 8bit bytes (they get munged), + # but it does allow us to parse and preserve them, and to decode body + # parts that use an 8bit CTE. + + bodytest_msg = textwrap.dedent("""\ + From: foo@bar.com + To: baz + Mime-Version: 1.0 + Content-Type: text/plain; charset={charset} + Content-Transfer-Encoding: {cte} + + {bodyline} + """) + + def test_known_8bit_CTE(self): + m = self.bodytest_msg.format(charset='utf-8', + cte='8bit', + bodyline='pöstal').encode('utf-8') + msg = email.message_from_bytes(m) + self.assertEqual(msg.get_payload(), "pöstal\n") + self.assertEqual(msg.get_payload(decode=True), + "pöstal\n".encode('utf-8')) + + def test_unknown_8bit_CTE(self): + m = self.bodytest_msg.format(charset='notavalidcharset', + cte='8bit', + bodyline='pöstal').encode('utf-8') + msg = email.message_from_bytes(m) + self.assertEqual(msg.get_payload(), "p\uFFFD\uFFFDstal\n") + self.assertEqual(msg.get_payload(decode=True), + "pöstal\n".encode('utf-8')) + + def test_8bit_in_quopri_body(self): + # This is non-RFC compliant data...without 'decode' the library code + # decodes the body using the charset from the headers, and because the + # source byte really is utf-8 this works. This is likely to fail + # against real dirty data (ie: produce mojibake), but the data is + # invalid anyway so it is as good a guess as any. But this means that + # this test just confirms the current behavior; that behavior is not + # necessarily the best possible behavior. With 'decode' it is + # returning the raw bytes, so that test should be of correct behavior, + # or at least produce the same result that email4 did. + m = self.bodytest_msg.format(charset='utf-8', + cte='quoted-printable', + bodyline='p=C3=B6stál').encode('utf-8') + msg = email.message_from_bytes(m) + self.assertEqual(msg.get_payload(), 'p=C3=B6stál\n') + self.assertEqual(msg.get_payload(decode=True), + 'pöstál\n'.encode('utf-8')) + + def test_invalid_8bit_in_non_8bit_cte_uses_replace(self): + # This is similar to the previous test, but proves that if the 8bit + # byte is undecodeable in the specified charset, it gets replaced + # by the unicode 'unknown' character. Again, this may or may not + # be the ideal behavior. Note that if decode=False none of the + # decoders will get involved, so this is the only test we need + # for this behavior. + m = self.bodytest_msg.format(charset='ascii', + cte='quoted-printable', + bodyline='p=C3=B6stál').encode('utf-8') + msg = email.message_from_bytes(m) + self.assertEqual(msg.get_payload(), 'p=C3=B6st\uFFFD\uFFFDl\n') + self.assertEqual(msg.get_payload(decode=True), + 'pöstál\n'.encode('utf-8')) + + def test_8bit_in_base64_body(self): + # Sticking an 8bit byte in a base64 block makes it undecodable by + # normal means, so the block is returned undecoded, but as bytes. + m = self.bodytest_msg.format(charset='utf-8', + cte='base64', + bodyline='cMO2c3RhbAá=').encode('utf-8') + msg = email.message_from_bytes(m) + self.assertEqual(msg.get_payload(decode=True), + 'cMO2c3RhbAá=\n'.encode('utf-8')) + + def test_8bit_in_uuencode_body(self): + # Sticking an 8bit byte in a uuencode block makes it undecodable by + # normal means, so the block is returned undecoded, but as bytes. + m = self.bodytest_msg.format(charset='utf-8', + cte='uuencode', + bodyline='<,.V<W1A; á ').encode('utf-8') + msg = email.message_from_bytes(m) + self.assertEqual(msg.get_payload(decode=True), + '<,.V<W1A; á \n'.encode('utf-8')) + + + headertest_headers = ( + ('From: foo@bar.com', ('From', 'foo@bar.com')), + ('To: báz', ('To', '=?unknown-8bit?q?b=C3=A1z?=')), + ('Subject: Maintenant je vous présente mon collègue, le pouf célèbre\n' + '\tJean de Baddie', + ('Subject', '=?unknown-8bit?q?Maintenant_je_vous_pr=C3=A9sente_mon_' + 'coll=C3=A8gue=2C_le_pouf_c=C3=A9l=C3=A8bre?=\n' + ' =?unknown-8bit?q?_Jean_de_Baddie?=')), + ('From: göst', ('From', '=?unknown-8bit?b?Z8O2c3Q=?=')), + ) + headertest_msg = ('\n'.join([src for (src, _) in headertest_headers]) + + '\nYes, they are flying.\n').encode('utf-8') + + def test_get_8bit_header(self): + msg = email.message_from_bytes(self.headertest_msg) + self.assertEqual(str(msg.get('to')), 'b\uFFFD\uFFFDz') + self.assertEqual(str(msg['to']), 'b\uFFFD\uFFFDz') + + def test_print_8bit_headers(self): + msg = email.message_from_bytes(self.headertest_msg) + self.assertEqual(str(msg), + textwrap.dedent("""\ + From: {} + To: {} + Subject: {} + From: {} + + Yes, they are flying. + """).format(*[expected[1] for (_, expected) in + self.headertest_headers])) + + def test_values_with_8bit_headers(self): + msg = email.message_from_bytes(self.headertest_msg) + self.assertListEqual([str(x) for x in msg.values()], + ['foo@bar.com', + 'b\uFFFD\uFFFDz', + 'Maintenant je vous pr\uFFFD\uFFFDsente mon ' + 'coll\uFFFD\uFFFDgue, le pouf ' + 'c\uFFFD\uFFFDl\uFFFD\uFFFDbre\n' + '\tJean de Baddie', + "g\uFFFD\uFFFDst"]) + + def test_items_with_8bit_headers(self): + msg = email.message_from_bytes(self.headertest_msg) + self.assertListEqual([(str(x), str(y)) for (x, y) in msg.items()], + [('From', 'foo@bar.com'), + ('To', 'b\uFFFD\uFFFDz'), + ('Subject', 'Maintenant je vous ' + 'pr\uFFFD\uFFFDsente ' + 'mon coll\uFFFD\uFFFDgue, le pouf ' + 'c\uFFFD\uFFFDl\uFFFD\uFFFDbre\n' + '\tJean de Baddie'), + ('From', 'g\uFFFD\uFFFDst')]) + + def test_get_all_with_8bit_headers(self): + msg = email.message_from_bytes(self.headertest_msg) + self.assertListEqual([str(x) for x in msg.get_all('from')], + ['foo@bar.com', + 'g\uFFFD\uFFFDst']) + + def test_get_content_type_with_8bit(self): + msg = email.message_from_bytes(textwrap.dedent("""\ + Content-Type: text/pl\xA7in; charset=utf-8 + """).encode('latin-1')) + self.assertEqual(msg.get_content_type(), "text/pl\uFFFDin") + self.assertEqual(msg.get_content_maintype(), "text") + self.assertEqual(msg.get_content_subtype(), "pl\uFFFDin") + + def test_get_params_with_8bit(self): + msg = email.message_from_bytes( + 'X-Header: foo=\xa7ne; b\xa7r=two; baz=three\n'.encode('latin-1')) + self.assertEqual(msg.get_params(header='x-header'), + [('foo', '\uFFFDne'), ('b\uFFFDr', 'two'), ('baz', 'three')]) + self.assertEqual(msg.get_param('Foo', header='x-header'), '\uFFFdne') + # XXX: someday you might be able to get 'b\xa7r', for now you can't. + self.assertEqual(msg.get_param('b\xa7r', header='x-header'), None) + + def test_get_rfc2231_params_with_8bit(self): + msg = email.message_from_bytes(textwrap.dedent("""\ + Content-Type: text/plain; charset=us-ascii; + title*=us-ascii'en'This%20is%20not%20f\xa7n""" + ).encode('latin-1')) + self.assertEqual(msg.get_param('title'), + ('us-ascii', 'en', 'This is not f\uFFFDn')) + + def test_set_rfc2231_params_with_8bit(self): + msg = email.message_from_bytes(textwrap.dedent("""\ + Content-Type: text/plain; charset=us-ascii; + title*=us-ascii'en'This%20is%20not%20f\xa7n""" + ).encode('latin-1')) + msg.set_param('title', 'test') + self.assertEqual(msg.get_param('title'), 'test') + + def test_del_rfc2231_params_with_8bit(self): + msg = email.message_from_bytes(textwrap.dedent("""\ + Content-Type: text/plain; charset=us-ascii; + title*=us-ascii'en'This%20is%20not%20f\xa7n""" + ).encode('latin-1')) + msg.del_param('title') + self.assertEqual(msg.get_param('title'), None) + self.assertEqual(msg.get_content_maintype(), 'text') + + def test_get_payload_with_8bit_cte_header(self): + msg = email.message_from_bytes(textwrap.dedent("""\ + Content-Transfer-Encoding: b\xa7se64 + Content-Type: text/plain; charset=latin-1 + + payload + """).encode('latin-1')) + self.assertEqual(msg.get_payload(), 'payload\n') + self.assertEqual(msg.get_payload(decode=True), b'payload\n') + + non_latin_bin_msg = textwrap.dedent("""\ + From: foo@bar.com + To: báz + Subject: Maintenant je vous présente mon collègue, le pouf célèbre + \tJean de Baddie + Mime-Version: 1.0 + Content-Type: text/plain; charset="utf-8" + Content-Transfer-Encoding: 8bit + + Да, они летят. + """).encode('utf-8') + + def test_bytes_generator(self): + msg = email.message_from_bytes(self.non_latin_bin_msg) + out = BytesIO() + email.generator.BytesGenerator(out).flatten(msg) + self.assertEqual(out.getvalue(), self.non_latin_bin_msg) + + def test_bytes_generator_handles_None_body(self): + #Issue 11019 + msg = email.message.Message() + out = BytesIO() + email.generator.BytesGenerator(out).flatten(msg) + self.assertEqual(out.getvalue(), b"\n") + + non_latin_bin_msg_as7bit_wrapped = textwrap.dedent("""\ + From: foo@bar.com + To: =?unknown-8bit?q?b=C3=A1z?= + Subject: =?unknown-8bit?q?Maintenant_je_vous_pr=C3=A9sente_mon_coll=C3=A8gue?= + =?unknown-8bit?q?=2C_le_pouf_c=C3=A9l=C3=A8bre?= + =?unknown-8bit?q?_Jean_de_Baddie?= + Mime-Version: 1.0 + Content-Type: text/plain; charset="utf-8" + Content-Transfer-Encoding: base64 + + 0JTQsCwg0L7QvdC4INC70LXRgtGP0YIuCg== + """) + + def test_generator_handles_8bit(self): + msg = email.message_from_bytes(self.non_latin_bin_msg) + out = StringIO() + email.generator.Generator(out).flatten(msg) + self.assertEqual(out.getvalue(), self.non_latin_bin_msg_as7bit_wrapped) + + def test_bytes_generator_with_unix_from(self): + # The unixfrom contains a current date, so we can't check it + # literally. Just make sure the first word is 'From' and the + # rest of the message matches the input. + msg = email.message_from_bytes(self.non_latin_bin_msg) + out = BytesIO() + email.generator.BytesGenerator(out).flatten(msg, unixfrom=True) + lines = out.getvalue().split(b'\n') + self.assertEqual(lines[0].split()[0], b'From') + self.assertEqual(b'\n'.join(lines[1:]), self.non_latin_bin_msg) + + non_latin_bin_msg_as7bit = non_latin_bin_msg_as7bit_wrapped.split('\n') + non_latin_bin_msg_as7bit[2:4] = [ + 'Subject: =?unknown-8bit?q?Maintenant_je_vous_pr=C3=A9sente_mon_' + 'coll=C3=A8gue=2C_le_pouf_c=C3=A9l=C3=A8bre?='] + non_latin_bin_msg_as7bit = '\n'.join(non_latin_bin_msg_as7bit) + + def test_message_from_binary_file(self): + fn = 'test.msg' + self.addCleanup(unlink, fn) + with open(fn, 'wb') as testfile: + testfile.write(self.non_latin_bin_msg) + with open(fn, 'rb') as testfile: + m = email.parser.BytesParser().parse(testfile) + self.assertEqual(str(m), self.non_latin_bin_msg_as7bit) + + latin_bin_msg = textwrap.dedent("""\ + From: foo@bar.com + To: Dinsdale + Subject: Nudge nudge, wink, wink + Mime-Version: 1.0 + Content-Type: text/plain; charset="latin-1" + Content-Transfer-Encoding: 8bit + + oh là là, know what I mean, know what I mean? + """).encode('latin-1') + + latin_bin_msg_as7bit = textwrap.dedent("""\ + From: foo@bar.com + To: Dinsdale + Subject: Nudge nudge, wink, wink + Mime-Version: 1.0 + Content-Type: text/plain; charset="iso-8859-1" + Content-Transfer-Encoding: quoted-printable + + oh l=E0 l=E0, know what I mean, know what I mean? + """) + + def test_string_generator_reencodes_to_quopri_when_appropriate(self): + m = email.message_from_bytes(self.latin_bin_msg) + self.assertEqual(str(m), self.latin_bin_msg_as7bit) + + def test_decoded_generator_emits_unicode_body(self): + m = email.message_from_bytes(self.latin_bin_msg) + out = StringIO() + email.generator.DecodedGenerator(out).flatten(m) + #DecodedHeader output contains an extra blank line compared + #to the input message. RDM: not sure if this is a bug or not, + #but it is not specific to the 8bit->7bit conversion. + self.assertEqual(out.getvalue(), + self.latin_bin_msg.decode('latin-1')+'\n') + + def test_bytes_feedparser(self): + bfp = email.feedparser.BytesFeedParser() + for i in range(0, len(self.latin_bin_msg), 10): + bfp.feed(self.latin_bin_msg[i:i+10]) + m = bfp.close() + self.assertEqual(str(m), self.latin_bin_msg_as7bit) + + def test_crlf_flatten(self): + with openfile('msg_26.txt', 'rb') as fp: + text = fp.read() + msg = email.message_from_bytes(text) + s = BytesIO() + g = email.generator.BytesGenerator(s) + g.flatten(msg, linesep='\r\n') + self.assertEqual(s.getvalue(), text) + maxDiff = None + + +class BaseTestBytesGeneratorIdempotent: + + maxDiff = None + + def _msgobj(self, filename): + with openfile(filename, 'rb') as fp: + data = fp.read() + data = self.normalize_linesep_regex.sub(self.blinesep, data) + msg = email.message_from_bytes(data) + return msg, data + + def _idempotent(self, msg, data, unixfrom=False): + b = BytesIO() + g = email.generator.BytesGenerator(b, maxheaderlen=0) + g.flatten(msg, unixfrom=unixfrom, linesep=self.linesep) + self.assertByteStringsEqual(data, b.getvalue()) + + def assertByteStringsEqual(self, str1, str2): + # Not using self.blinesep here is intentional. This way the output + # is more useful when the failure results in mixed line endings. + self.assertListEqual(str1.split(b'\n'), str2.split(b'\n')) + + +class TestBytesGeneratorIdempotentNL(BaseTestBytesGeneratorIdempotent, + TestIdempotent): + linesep = '\n' + blinesep = b'\n' + normalize_linesep_regex = re.compile(br'\r\n') + + +class TestBytesGeneratorIdempotentCRLF(BaseTestBytesGeneratorIdempotent, + TestIdempotent): + linesep = '\r\n' + blinesep = b'\r\n' + normalize_linesep_regex = re.compile(br'(?<!\r)\n') + + +class TestBase64(unittest.TestCase): + def test_len(self): + eq = self.assertEqual + eq(base64mime.header_length('hello'), + len(base64mime.body_encode(b'hello', eol=''))) + for size in range(15): + if size == 0 : bsize = 0 + elif size <= 3 : bsize = 4 + elif size <= 6 : bsize = 8 + elif size <= 9 : bsize = 12 + elif size <= 12: bsize = 16 + else : bsize = 20 + eq(base64mime.header_length('x' * size), bsize) + + def test_decode(self): + eq = self.assertEqual + eq(base64mime.decode(''), b'') + eq(base64mime.decode('aGVsbG8='), b'hello') + + def test_encode(self): + eq = self.assertEqual + eq(base64mime.body_encode(b''), b'') + eq(base64mime.body_encode(b'hello'), 'aGVsbG8=\n') + # Test the binary flag + eq(base64mime.body_encode(b'hello\n'), 'aGVsbG8K\n') + # Test the maxlinelen arg + eq(base64mime.body_encode(b'xxxx ' * 20, maxlinelen=40), """\ +eHh4eCB4eHh4IHh4eHggeHh4eCB4eHh4IHh4eHgg +eHh4eCB4eHh4IHh4eHggeHh4eCB4eHh4IHh4eHgg +eHh4eCB4eHh4IHh4eHggeHh4eCB4eHh4IHh4eHgg +eHh4eCB4eHh4IA== +""") + # Test the eol argument + eq(base64mime.body_encode(b'xxxx ' * 20, maxlinelen=40, eol='\r\n'), + """\ +eHh4eCB4eHh4IHh4eHggeHh4eCB4eHh4IHh4eHgg\r +eHh4eCB4eHh4IHh4eHggeHh4eCB4eHh4IHh4eHgg\r +eHh4eCB4eHh4IHh4eHggeHh4eCB4eHh4IHh4eHgg\r +eHh4eCB4eHh4IA==\r +""") + + def test_header_encode(self): + eq = self.assertEqual + he = base64mime.header_encode + eq(he('hello'), '=?iso-8859-1?b?aGVsbG8=?=') + eq(he('hello\r\nworld'), '=?iso-8859-1?b?aGVsbG8NCndvcmxk?=') + eq(he('hello\nworld'), '=?iso-8859-1?b?aGVsbG8Kd29ybGQ=?=') + # Test the charset option + eq(he('hello', charset='iso-8859-2'), '=?iso-8859-2?b?aGVsbG8=?=') + eq(he('hello\nworld'), '=?iso-8859-1?b?aGVsbG8Kd29ybGQ=?=') + + + +class TestQuopri(unittest.TestCase): + def setUp(self): + # Set of characters (as byte integers) that don't need to be encoded + # in headers. + self.hlit = list(chain( + range(ord('a'), ord('z') + 1), + range(ord('A'), ord('Z') + 1), + range(ord('0'), ord('9') + 1), + (c for c in b'!*+-/'))) + # Set of characters (as byte integers) that do need to be encoded in + # headers. + self.hnon = [c for c in range(256) if c not in self.hlit] + assert len(self.hlit) + len(self.hnon) == 256 + # Set of characters (as byte integers) that don't need to be encoded + # in bodies. + self.blit = list(range(ord(' '), ord('~') + 1)) + self.blit.append(ord('\t')) + self.blit.remove(ord('=')) + # Set of characters (as byte integers) that do need to be encoded in + # bodies. + self.bnon = [c for c in range(256) if c not in self.blit] + assert len(self.blit) + len(self.bnon) == 256 + + def test_quopri_header_check(self): + for c in self.hlit: + self.assertFalse(quoprimime.header_check(c), + 'Should not be header quopri encoded: %s' % chr(c)) + for c in self.hnon: + self.assertTrue(quoprimime.header_check(c), + 'Should be header quopri encoded: %s' % chr(c)) + + def test_quopri_body_check(self): + for c in self.blit: + self.assertFalse(quoprimime.body_check(c), + 'Should not be body quopri encoded: %s' % chr(c)) + for c in self.bnon: + self.assertTrue(quoprimime.body_check(c), + 'Should be body quopri encoded: %s' % chr(c)) + + def test_header_quopri_len(self): + eq = self.assertEqual + eq(quoprimime.header_length(b'hello'), 5) + # RFC 2047 chrome is not included in header_length(). + eq(len(quoprimime.header_encode(b'hello', charset='xxx')), + quoprimime.header_length(b'hello') + + # =?xxx?q?...?= means 10 extra characters + 10) + eq(quoprimime.header_length(b'h@e@l@l@o@'), 20) + # RFC 2047 chrome is not included in header_length(). + eq(len(quoprimime.header_encode(b'h@e@l@l@o@', charset='xxx')), + quoprimime.header_length(b'h@e@l@l@o@') + + # =?xxx?q?...?= means 10 extra characters + 10) + for c in self.hlit: + eq(quoprimime.header_length(bytes([c])), 1, + 'expected length 1 for %r' % chr(c)) + for c in self.hnon: + # Space is special; it's encoded to _ + if c == ord(' '): + continue + eq(quoprimime.header_length(bytes([c])), 3, + 'expected length 3 for %r' % chr(c)) + eq(quoprimime.header_length(b' '), 1) + + def test_body_quopri_len(self): + eq = self.assertEqual + for c in self.blit: + eq(quoprimime.body_length(bytes([c])), 1) + for c in self.bnon: + eq(quoprimime.body_length(bytes([c])), 3) + + def test_quote_unquote_idempotent(self): + for x in range(256): + c = chr(x) + self.assertEqual(quoprimime.unquote(quoprimime.quote(c)), c) + + def test_header_encode(self): + eq = self.assertEqual + he = quoprimime.header_encode + eq(he(b'hello'), '=?iso-8859-1?q?hello?=') + eq(he(b'hello', charset='iso-8859-2'), '=?iso-8859-2?q?hello?=') + eq(he(b'hello\nworld'), '=?iso-8859-1?q?hello=0Aworld?=') + # Test a non-ASCII character + eq(he(b'hello\xc7there'), '=?iso-8859-1?q?hello=C7there?=') + + def test_decode(self): + eq = self.assertEqual + eq(quoprimime.decode(''), '') + eq(quoprimime.decode('hello'), 'hello') + eq(quoprimime.decode('hello', 'X'), 'hello') + eq(quoprimime.decode('hello\nworld', 'X'), 'helloXworld') + + def test_encode(self): + eq = self.assertEqual + eq(quoprimime.body_encode(''), '') + eq(quoprimime.body_encode('hello'), 'hello') + # Test the binary flag + eq(quoprimime.body_encode('hello\r\nworld'), 'hello\nworld') + # Test the maxlinelen arg + eq(quoprimime.body_encode('xxxx ' * 20, maxlinelen=40), """\ +xxxx xxxx xxxx xxxx xxxx xxxx xxxx xxxx= + xxxx xxxx xxxx xxxx xxxx xxxx xxxx xxx= +x xxxx xxxx xxxx xxxx=20""") + # Test the eol argument + eq(quoprimime.body_encode('xxxx ' * 20, maxlinelen=40, eol='\r\n'), + """\ +xxxx xxxx xxxx xxxx xxxx xxxx xxxx xxxx=\r + xxxx xxxx xxxx xxxx xxxx xxxx xxxx xxx=\r +x xxxx xxxx xxxx xxxx=20""") + eq(quoprimime.body_encode("""\ +one line + +two line"""), """\ +one line + +two line""") + + + +# Test the Charset class +class TestCharset(unittest.TestCase): + def tearDown(self): + from email import charset as CharsetModule + try: + del CharsetModule.CHARSETS['fake'] + except KeyError: + pass + + def test_codec_encodeable(self): + eq = self.assertEqual + # Make sure us-ascii = no Unicode conversion + c = Charset('us-ascii') + eq(c.header_encode('Hello World!'), 'Hello World!') + # Test 8-bit idempotency with us-ascii + s = '\xa4\xa2\xa4\xa4\xa4\xa6\xa4\xa8\xa4\xaa' + self.assertRaises(UnicodeError, c.header_encode, s) + c = Charset('utf-8') + eq(c.header_encode(s), '=?utf-8?b?wqTCosKkwqTCpMKmwqTCqMKkwqo=?=') + + def test_body_encode(self): + eq = self.assertEqual + # Try a charset with QP body encoding + c = Charset('iso-8859-1') + eq('hello w=F6rld', c.body_encode('hello w\xf6rld')) + # Try a charset with Base64 body encoding + c = Charset('utf-8') + eq('aGVsbG8gd29ybGQ=\n', c.body_encode(b'hello world')) + # Try a charset with None body encoding + c = Charset('us-ascii') + eq('hello world', c.body_encode('hello world')) + # Try the convert argument, where input codec != output codec + c = Charset('euc-jp') + # With apologies to Tokio Kikuchi ;) + # XXX FIXME +## try: +## eq('\x1b$B5FCO;~IW\x1b(B', +## c.body_encode('\xb5\xc6\xc3\xcf\xbb\xfe\xc9\xd7')) +## eq('\xb5\xc6\xc3\xcf\xbb\xfe\xc9\xd7', +## c.body_encode('\xb5\xc6\xc3\xcf\xbb\xfe\xc9\xd7', False)) +## except LookupError: +## # We probably don't have the Japanese codecs installed +## pass + # Testing SF bug #625509, which we have to fake, since there are no + # built-in encodings where the header encoding is QP but the body + # encoding is not. + from email import charset as CharsetModule + CharsetModule.add_charset('fake', CharsetModule.QP, None, 'utf-8') + c = Charset('fake') + eq('hello world', c.body_encode('hello world')) + + def test_unicode_charset_name(self): + charset = Charset('us-ascii') + self.assertEqual(str(charset), 'us-ascii') + self.assertRaises(errors.CharsetError, Charset, 'asc\xffii') + + + +# Test multilingual MIME headers. +class TestHeader(TestEmailBase): + def test_simple(self): + eq = self.ndiffAssertEqual + h = Header('Hello World!') + eq(h.encode(), 'Hello World!') + h.append(' Goodbye World!') + eq(h.encode(), 'Hello World! Goodbye World!') + + def test_simple_surprise(self): + eq = self.ndiffAssertEqual + h = Header('Hello World!') + eq(h.encode(), 'Hello World!') + h.append('Goodbye World!') + eq(h.encode(), 'Hello World! Goodbye World!') + + def test_header_needs_no_decoding(self): + h = 'no decoding needed' + self.assertEqual(decode_header(h), [(h, None)]) + + def test_long(self): + h = Header("I am the very model of a modern Major-General; I've information vegetable, animal, and mineral; I know the kings of England, and I quote the fights historical from Marathon to Waterloo, in order categorical; I'm very well acquainted, too, with matters mathematical; I understand equations, both the simple and quadratical; about binomial theorem I'm teeming with a lot o' news, with many cheerful facts about the square of the hypotenuse.", + maxlinelen=76) + for l in h.encode(splitchars=' ').split('\n '): + self.assertTrue(len(l) <= 76) + + def test_multilingual(self): + eq = self.ndiffAssertEqual + g = Charset("iso-8859-1") + cz = Charset("iso-8859-2") + utf8 = Charset("utf-8") + g_head = (b'Die Mieter treten hier ein werden mit einem ' + b'Foerderband komfortabel den Korridor entlang, ' + b'an s\xfcdl\xfcndischen Wandgem\xe4lden vorbei, ' + b'gegen die rotierenden Klingen bef\xf6rdert. ') + cz_head = (b'Finan\xe8ni metropole se hroutily pod tlakem jejich ' + b'd\xf9vtipu.. ') + utf8_head = ('\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f' + '\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00' + '\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c' + '\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067' + '\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das ' + 'Nunstuck git und Slotermeyer? Ja! Beiherhund das Oder ' + 'die Flipperwaldt gersput.\u300d\u3068\u8a00\u3063\u3066' + '\u3044\u307e\u3059\u3002') + h = Header(g_head, g) + h.append(cz_head, cz) + h.append(utf8_head, utf8) + enc = h.encode(maxlinelen=76) + eq(enc, """\ +=?iso-8859-1?q?Die_Mieter_treten_hier_ein_werden_mit_einem_Foerderband_kom?= + =?iso-8859-1?q?fortabel_den_Korridor_entlang=2C_an_s=FCdl=FCndischen_Wand?= + =?iso-8859-1?q?gem=E4lden_vorbei=2C_gegen_die_rotierenden_Klingen_bef=F6r?= + =?iso-8859-1?q?dert=2E_?= =?iso-8859-2?q?Finan=E8ni_metropole_se_hroutily?= + =?iso-8859-2?q?_pod_tlakem_jejich_d=F9vtipu=2E=2E_?= =?utf-8?b?5q2j56K6?= + =?utf-8?b?44Gr6KiA44GG44Go57+76Kiz44Gv44GV44KM44Gm44GE44G+44Gb44KT44CC?= + =?utf-8?b?5LiA6YOo44Gv44OJ44Kk44OE6Kqe44Gn44GZ44GM44CB44GC44Go44Gv44Gn?= + =?utf-8?b?44Gf44KJ44KB44Gn44GZ44CC5a6f6Zqb44Gr44Gv44CMV2VubiBpc3QgZGFz?= + =?utf-8?b?IE51bnN0dWNrIGdpdCB1bmQgU2xvdGVybWV5ZXI/IEphISBCZWloZXJodW5k?= + =?utf-8?b?IGRhcyBPZGVyIGRpZSBGbGlwcGVyd2FsZHQgZ2Vyc3B1dC7jgI3jgajoqIA=?= + =?utf-8?b?44Gj44Gm44GE44G+44GZ44CC?=""") + decoded = decode_header(enc) + eq(len(decoded), 3) + eq(decoded[0], (g_head, 'iso-8859-1')) + eq(decoded[1], (cz_head, 'iso-8859-2')) + eq(decoded[2], (utf8_head.encode('utf-8'), 'utf-8')) + ustr = str(h) + eq(ustr, + (b'Die Mieter treten hier ein werden mit einem Foerderband ' + b'komfortabel den Korridor entlang, an s\xc3\xbcdl\xc3\xbcndischen ' + b'Wandgem\xc3\xa4lden vorbei, gegen die rotierenden Klingen ' + b'bef\xc3\xb6rdert. Finan\xc4\x8dni metropole se hroutily pod ' + b'tlakem jejich d\xc5\xafvtipu.. \xe6\xad\xa3\xe7\xa2\xba\xe3\x81' + b'\xab\xe8\xa8\x80\xe3\x81\x86\xe3\x81\xa8\xe7\xbf\xbb\xe8\xa8\xb3' + b'\xe3\x81\xaf\xe3\x81\x95\xe3\x82\x8c\xe3\x81\xa6\xe3\x81\x84\xe3' + b'\x81\xbe\xe3\x81\x9b\xe3\x82\x93\xe3\x80\x82\xe4\xb8\x80\xe9\x83' + b'\xa8\xe3\x81\xaf\xe3\x83\x89\xe3\x82\xa4\xe3\x83\x84\xe8\xaa\x9e' + b'\xe3\x81\xa7\xe3\x81\x99\xe3\x81\x8c\xe3\x80\x81\xe3\x81\x82\xe3' + b'\x81\xa8\xe3\x81\xaf\xe3\x81\xa7\xe3\x81\x9f\xe3\x82\x89\xe3\x82' + b'\x81\xe3\x81\xa7\xe3\x81\x99\xe3\x80\x82\xe5\xae\x9f\xe9\x9a\x9b' + b'\xe3\x81\xab\xe3\x81\xaf\xe3\x80\x8cWenn ist das Nunstuck git ' + b'und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt ' + b'gersput.\xe3\x80\x8d\xe3\x81\xa8\xe8\xa8\x80\xe3\x81\xa3\xe3\x81' + b'\xa6\xe3\x81\x84\xe3\x81\xbe\xe3\x81\x99\xe3\x80\x82' + ).decode('utf-8')) + # Test make_header() + newh = make_header(decode_header(enc)) + eq(newh, h) + + def test_empty_header_encode(self): + h = Header() + self.assertEqual(h.encode(), '') + + def test_header_ctor_default_args(self): + eq = self.ndiffAssertEqual + h = Header() + eq(h, '') + h.append('foo', Charset('iso-8859-1')) + eq(h, 'foo') + + def test_explicit_maxlinelen(self): + eq = self.ndiffAssertEqual + hstr = ('A very long line that must get split to something other ' + 'than at the 76th character boundary to test the non-default ' + 'behavior') + h = Header(hstr) + eq(h.encode(), '''\ +A very long line that must get split to something other than at the 76th + character boundary to test the non-default behavior''') + eq(str(h), hstr) + h = Header(hstr, header_name='Subject') + eq(h.encode(), '''\ +A very long line that must get split to something other than at the + 76th character boundary to test the non-default behavior''') + eq(str(h), hstr) + h = Header(hstr, maxlinelen=1024, header_name='Subject') + eq(h.encode(), hstr) + eq(str(h), hstr) + + def test_quopri_splittable(self): + eq = self.ndiffAssertEqual + h = Header(charset='iso-8859-1', maxlinelen=20) + x = 'xxxx ' * 20 + h.append(x) + s = h.encode() + eq(s, """\ +=?iso-8859-1?q?xxx?= + =?iso-8859-1?q?x_?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?_x?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?x_?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?_x?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?x_?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?_x?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?x_?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?_x?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?x_?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?_x?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?x_?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?_x?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?x_?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?_x?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?x_?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?_x?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?x_?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?_x?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?x_?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?xx?= + =?iso-8859-1?q?_?=""") + eq(x, str(make_header(decode_header(s)))) + h = Header(charset='iso-8859-1', maxlinelen=40) + h.append('xxxx ' * 20) + s = h.encode() + eq(s, """\ +=?iso-8859-1?q?xxxx_xxxx_xxxx_xxxx_xxx?= + =?iso-8859-1?q?x_xxxx_xxxx_xxxx_xxxx_?= + =?iso-8859-1?q?xxxx_xxxx_xxxx_xxxx_xx?= + =?iso-8859-1?q?xx_xxxx_xxxx_xxxx_xxxx?= + =?iso-8859-1?q?_xxxx_xxxx_?=""") + eq(x, str(make_header(decode_header(s)))) + + def test_base64_splittable(self): + eq = self.ndiffAssertEqual + h = Header(charset='koi8-r', maxlinelen=20) + x = 'xxxx ' * 20 + h.append(x) + s = h.encode() + eq(s, """\ +=?koi8-r?b?eHh4?= + =?koi8-r?b?eCB4?= + =?koi8-r?b?eHh4?= + =?koi8-r?b?IHh4?= + =?koi8-r?b?eHgg?= + =?koi8-r?b?eHh4?= + =?koi8-r?b?eCB4?= + =?koi8-r?b?eHh4?= + =?koi8-r?b?IHh4?= + =?koi8-r?b?eHgg?= + =?koi8-r?b?eHh4?= + =?koi8-r?b?eCB4?= + =?koi8-r?b?eHh4?= + =?koi8-r?b?IHh4?= + =?koi8-r?b?eHgg?= + =?koi8-r?b?eHh4?= + =?koi8-r?b?eCB4?= + =?koi8-r?b?eHh4?= + =?koi8-r?b?IHh4?= + =?koi8-r?b?eHgg?= + =?koi8-r?b?eHh4?= + =?koi8-r?b?eCB4?= + =?koi8-r?b?eHh4?= + =?koi8-r?b?IHh4?= + =?koi8-r?b?eHgg?= + =?koi8-r?b?eHh4?= + =?koi8-r?b?eCB4?= + =?koi8-r?b?eHh4?= + =?koi8-r?b?IHh4?= + =?koi8-r?b?eHgg?= + =?koi8-r?b?eHh4?= + =?koi8-r?b?eCB4?= + =?koi8-r?b?eHh4?= + =?koi8-r?b?IA==?=""") + eq(x, str(make_header(decode_header(s)))) + h = Header(charset='koi8-r', maxlinelen=40) + h.append(x) + s = h.encode() + eq(s, """\ +=?koi8-r?b?eHh4eCB4eHh4IHh4eHggeHh4?= + =?koi8-r?b?eCB4eHh4IHh4eHggeHh4eCB4?= + =?koi8-r?b?eHh4IHh4eHggeHh4eCB4eHh4?= + =?koi8-r?b?IHh4eHggeHh4eCB4eHh4IHh4?= + =?koi8-r?b?eHggeHh4eCB4eHh4IHh4eHgg?= + =?koi8-r?b?eHh4eCB4eHh4IA==?=""") + eq(x, str(make_header(decode_header(s)))) + + def test_us_ascii_header(self): + eq = self.assertEqual + s = 'hello' + x = decode_header(s) + eq(x, [('hello', None)]) + h = make_header(x) + eq(s, h.encode()) + + def test_string_charset(self): + eq = self.assertEqual + h = Header() + h.append('hello', 'iso-8859-1') + eq(h, 'hello') + +## def test_unicode_error(self): +## raises = self.assertRaises +## raises(UnicodeError, Header, u'[P\xf6stal]', 'us-ascii') +## raises(UnicodeError, Header, '[P\xf6stal]', 'us-ascii') +## h = Header() +## raises(UnicodeError, h.append, u'[P\xf6stal]', 'us-ascii') +## raises(UnicodeError, h.append, '[P\xf6stal]', 'us-ascii') +## raises(UnicodeError, Header, u'\u83ca\u5730\u6642\u592b', 'iso-8859-1') + + def test_utf8_shortest(self): + eq = self.assertEqual + h = Header('p\xf6stal', 'utf-8') + eq(h.encode(), '=?utf-8?q?p=C3=B6stal?=') + h = Header('\u83ca\u5730\u6642\u592b', 'utf-8') + eq(h.encode(), '=?utf-8?b?6I+K5Zyw5pmC5aSr?=') + + def test_bad_8bit_header(self): + raises = self.assertRaises + eq = self.assertEqual + x = b'Ynwp4dUEbay Auction Semiar- No Charge \x96 Earn Big' + raises(UnicodeError, Header, x) + h = Header() + raises(UnicodeError, h.append, x) + e = x.decode('utf-8', 'replace') + eq(str(Header(x, errors='replace')), e) + h.append(x, errors='replace') + eq(str(h), e) + + def test_encoded_adjacent_nonencoded(self): + eq = self.assertEqual + h = Header() + h.append('hello', 'iso-8859-1') + h.append('world') + s = h.encode() + eq(s, '=?iso-8859-1?q?hello?= world') + h = make_header(decode_header(s)) + eq(h.encode(), s) + + def test_whitespace_eater(self): + eq = self.assertEqual + s = 'Subject: =?koi8-r?b?8NLP18XSy8EgzsEgxsnOwczYztk=?= =?koi8-r?q?=CA?= zz.' + parts = decode_header(s) + eq(parts, [(b'Subject:', None), (b'\xf0\xd2\xcf\xd7\xc5\xd2\xcb\xc1 \xce\xc1 \xc6\xc9\xce\xc1\xcc\xd8\xce\xd9\xca', 'koi8-r'), (b'zz.', None)]) + hdr = make_header(parts) + eq(hdr.encode(), + 'Subject: =?koi8-r?b?8NLP18XSy8EgzsEgxsnOwczYztnK?= zz.') + + def test_broken_base64_header(self): + raises = self.assertRaises + s = 'Subject: =?EUC-KR?B?CSixpLDtKSC/7Liuvsax4iC6uLmwMcijIKHaILzSwd/H0SC8+LCjwLsgv7W/+Mj3I ?=' + raises(errors.HeaderParseError, decode_header, s) + + def test_shift_jis_charset(self): + h = Header('文', charset='shift_jis') + self.assertEqual(h.encode(), '=?iso-2022-jp?b?GyRCSjgbKEI=?=') + + def test_flatten_header_with_no_value(self): + # Issue 11401 (regression from email 4.x) Note that the space after + # the header doesn't reflect the input, but this is also the way + # email 4.x behaved. At some point it would be nice to fix that. + msg = email.message_from_string("EmptyHeader:") + self.assertEqual(str(msg), "EmptyHeader: \n\n") + + + +# Test RFC 2231 header parameters (en/de)coding +class TestRFC2231(TestEmailBase): + def test_get_param(self): + eq = self.assertEqual + msg = self._msgobj('msg_29.txt') + eq(msg.get_param('title'), + ('us-ascii', 'en', 'This is even more ***fun*** isn\'t it!')) + eq(msg.get_param('title', unquote=False), + ('us-ascii', 'en', '"This is even more ***fun*** isn\'t it!"')) + + def test_set_param(self): + eq = self.ndiffAssertEqual + msg = Message() + msg.set_param('title', 'This is even more ***fun*** isn\'t it!', + charset='us-ascii') + eq(msg.get_param('title'), + ('us-ascii', '', 'This is even more ***fun*** isn\'t it!')) + msg.set_param('title', 'This is even more ***fun*** isn\'t it!', + charset='us-ascii', language='en') + eq(msg.get_param('title'), + ('us-ascii', 'en', 'This is even more ***fun*** isn\'t it!')) + msg = self._msgobj('msg_01.txt') + msg.set_param('title', 'This is even more ***fun*** isn\'t it!', + charset='us-ascii', language='en') + eq(msg.as_string(maxheaderlen=78), """\ +Return-Path: <bbb@zzz.org> +Delivered-To: bbb@zzz.org +Received: by mail.zzz.org (Postfix, from userid 889) +\tid 27CEAD38CC; Fri, 4 May 2001 14:05:44 -0400 (EDT) +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit +Message-ID: <15090.61304.110929.45684@aaa.zzz.org> +From: bbb@ddd.com (John X. Doe) +To: bbb@zzz.org +Subject: This is a test message +Date: Fri, 4 May 2001 14:05:44 -0400 +Content-Type: text/plain; charset=us-ascii; + title*=us-ascii'en'This%20is%20even%20more%20%2A%2A%2Afun%2A%2A%2A%20isn%27t%20it%21 + + +Hi, + +Do you like this message? + +-Me +""") + + def test_del_param(self): + eq = self.ndiffAssertEqual + msg = self._msgobj('msg_01.txt') + msg.set_param('foo', 'bar', charset='us-ascii', language='en') + msg.set_param('title', 'This is even more ***fun*** isn\'t it!', + charset='us-ascii', language='en') + msg.del_param('foo', header='Content-Type') + eq(msg.as_string(maxheaderlen=78), """\ +Return-Path: <bbb@zzz.org> +Delivered-To: bbb@zzz.org +Received: by mail.zzz.org (Postfix, from userid 889) +\tid 27CEAD38CC; Fri, 4 May 2001 14:05:44 -0400 (EDT) +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit +Message-ID: <15090.61304.110929.45684@aaa.zzz.org> +From: bbb@ddd.com (John X. Doe) +To: bbb@zzz.org +Subject: This is a test message +Date: Fri, 4 May 2001 14:05:44 -0400 +Content-Type: text/plain; charset="us-ascii"; + title*=us-ascii'en'This%20is%20even%20more%20%2A%2A%2Afun%2A%2A%2A%20isn%27t%20it%21 + + +Hi, + +Do you like this message? + +-Me +""") + + def test_rfc2231_get_content_charset(self): + eq = self.assertEqual + msg = self._msgobj('msg_32.txt') + eq(msg.get_content_charset(), 'us-ascii') + + def test_rfc2231_parse_rfc_quoting(self): + m = textwrap.dedent('''\ + Content-Disposition: inline; + \tfilename*0*=''This%20is%20even%20more%20; + \tfilename*1*=%2A%2A%2Afun%2A%2A%2A%20; + \tfilename*2="is it not.pdf" + + ''') + msg = email.message_from_string(m) + self.assertEqual(msg.get_filename(), + 'This is even more ***fun*** is it not.pdf') + self.assertEqual(m, msg.as_string()) + + def test_rfc2231_parse_extra_quoting(self): + m = textwrap.dedent('''\ + Content-Disposition: inline; + \tfilename*0*="''This%20is%20even%20more%20"; + \tfilename*1*="%2A%2A%2Afun%2A%2A%2A%20"; + \tfilename*2="is it not.pdf" + + ''') + msg = email.message_from_string(m) + self.assertEqual(msg.get_filename(), + 'This is even more ***fun*** is it not.pdf') + self.assertEqual(m, msg.as_string()) + + def test_rfc2231_no_language_or_charset(self): + m = '''\ +Content-Transfer-Encoding: 8bit +Content-Disposition: inline; filename="file____C__DOCUMENTS_20AND_20SETTINGS_FABIEN_LOCAL_20SETTINGS_TEMP_nsmail.htm" +Content-Type: text/html; NAME*0=file____C__DOCUMENTS_20AND_20SETTINGS_FABIEN_LOCAL_20SETTINGS_TEM; NAME*1=P_nsmail.htm + +''' + msg = email.message_from_string(m) + param = msg.get_param('NAME') + self.assertFalse(isinstance(param, tuple)) + self.assertEqual( + param, + 'file____C__DOCUMENTS_20AND_20SETTINGS_FABIEN_LOCAL_20SETTINGS_TEMP_nsmail.htm') + + def test_rfc2231_no_language_or_charset_in_filename(self): + m = '''\ +Content-Disposition: inline; +\tfilename*0*="''This%20is%20even%20more%20"; +\tfilename*1*="%2A%2A%2Afun%2A%2A%2A%20"; +\tfilename*2="is it not.pdf" + +''' + msg = email.message_from_string(m) + self.assertEqual(msg.get_filename(), + 'This is even more ***fun*** is it not.pdf') + + def test_rfc2231_no_language_or_charset_in_filename_encoded(self): + m = '''\ +Content-Disposition: inline; +\tfilename*0*="''This%20is%20even%20more%20"; +\tfilename*1*="%2A%2A%2Afun%2A%2A%2A%20"; +\tfilename*2="is it not.pdf" + +''' + msg = email.message_from_string(m) + self.assertEqual(msg.get_filename(), + 'This is even more ***fun*** is it not.pdf') + + def test_rfc2231_partly_encoded(self): + m = '''\ +Content-Disposition: inline; +\tfilename*0="''This%20is%20even%20more%20"; +\tfilename*1*="%2A%2A%2Afun%2A%2A%2A%20"; +\tfilename*2="is it not.pdf" + +''' + msg = email.message_from_string(m) + self.assertEqual( + msg.get_filename(), + 'This%20is%20even%20more%20***fun*** is it not.pdf') + + def test_rfc2231_partly_nonencoded(self): + m = '''\ +Content-Disposition: inline; +\tfilename*0="This%20is%20even%20more%20"; +\tfilename*1="%2A%2A%2Afun%2A%2A%2A%20"; +\tfilename*2="is it not.pdf" + +''' + msg = email.message_from_string(m) + self.assertEqual( + msg.get_filename(), + 'This%20is%20even%20more%20%2A%2A%2Afun%2A%2A%2A%20is it not.pdf') + + def test_rfc2231_no_language_or_charset_in_boundary(self): + m = '''\ +Content-Type: multipart/alternative; +\tboundary*0*="''This%20is%20even%20more%20"; +\tboundary*1*="%2A%2A%2Afun%2A%2A%2A%20"; +\tboundary*2="is it not.pdf" + +''' + msg = email.message_from_string(m) + self.assertEqual(msg.get_boundary(), + 'This is even more ***fun*** is it not.pdf') + + def test_rfc2231_no_language_or_charset_in_charset(self): + # This is a nonsensical charset value, but tests the code anyway + m = '''\ +Content-Type: text/plain; +\tcharset*0*="This%20is%20even%20more%20"; +\tcharset*1*="%2A%2A%2Afun%2A%2A%2A%20"; +\tcharset*2="is it not.pdf" + +''' + msg = email.message_from_string(m) + self.assertEqual(msg.get_content_charset(), + 'this is even more ***fun*** is it not.pdf') + + def test_rfc2231_bad_encoding_in_filename(self): + m = '''\ +Content-Disposition: inline; +\tfilename*0*="bogus'xx'This%20is%20even%20more%20"; +\tfilename*1*="%2A%2A%2Afun%2A%2A%2A%20"; +\tfilename*2="is it not.pdf" + +''' + msg = email.message_from_string(m) + self.assertEqual(msg.get_filename(), + 'This is even more ***fun*** is it not.pdf') + + def test_rfc2231_bad_encoding_in_charset(self): + m = """\ +Content-Type: text/plain; charset*=bogus''utf-8%E2%80%9D + +""" + msg = email.message_from_string(m) + # This should return None because non-ascii characters in the charset + # are not allowed. + self.assertEqual(msg.get_content_charset(), None) + + def test_rfc2231_bad_character_in_charset(self): + m = """\ +Content-Type: text/plain; charset*=ascii''utf-8%E2%80%9D + +""" + msg = email.message_from_string(m) + # This should return None because non-ascii characters in the charset + # are not allowed. + self.assertEqual(msg.get_content_charset(), None) + + def test_rfc2231_bad_character_in_filename(self): + m = '''\ +Content-Disposition: inline; +\tfilename*0*="ascii'xx'This%20is%20even%20more%20"; +\tfilename*1*="%2A%2A%2Afun%2A%2A%2A%20"; +\tfilename*2*="is it not.pdf%E2" + +''' + msg = email.message_from_string(m) + self.assertEqual(msg.get_filename(), + 'This is even more ***fun*** is it not.pdf\ufffd') + + def test_rfc2231_unknown_encoding(self): + m = """\ +Content-Transfer-Encoding: 8bit +Content-Disposition: inline; filename*=X-UNKNOWN''myfile.txt + +""" + msg = email.message_from_string(m) + self.assertEqual(msg.get_filename(), 'myfile.txt') + + def test_rfc2231_single_tick_in_filename_extended(self): + eq = self.assertEqual + m = """\ +Content-Type: application/x-foo; +\tname*0*=\"Frank's\"; name*1*=\" Document\" + +""" + msg = email.message_from_string(m) + charset, language, s = msg.get_param('name') + eq(charset, None) + eq(language, None) + eq(s, "Frank's Document") + + def test_rfc2231_single_tick_in_filename(self): + m = """\ +Content-Type: application/x-foo; name*0=\"Frank's\"; name*1=\" Document\" + +""" + msg = email.message_from_string(m) + param = msg.get_param('name') + self.assertFalse(isinstance(param, tuple)) + self.assertEqual(param, "Frank's Document") + + def test_rfc2231_tick_attack_extended(self): + eq = self.assertEqual + m = """\ +Content-Type: application/x-foo; +\tname*0*=\"us-ascii'en-us'Frank's\"; name*1*=\" Document\" + +""" + msg = email.message_from_string(m) + charset, language, s = msg.get_param('name') + eq(charset, 'us-ascii') + eq(language, 'en-us') + eq(s, "Frank's Document") + + def test_rfc2231_tick_attack(self): + m = """\ +Content-Type: application/x-foo; +\tname*0=\"us-ascii'en-us'Frank's\"; name*1=\" Document\" + +""" + msg = email.message_from_string(m) + param = msg.get_param('name') + self.assertFalse(isinstance(param, tuple)) + self.assertEqual(param, "us-ascii'en-us'Frank's Document") + + def test_rfc2231_no_extended_values(self): + eq = self.assertEqual + m = """\ +Content-Type: application/x-foo; name=\"Frank's Document\" + +""" + msg = email.message_from_string(m) + eq(msg.get_param('name'), "Frank's Document") + + def test_rfc2231_encoded_then_unencoded_segments(self): + eq = self.assertEqual + m = """\ +Content-Type: application/x-foo; +\tname*0*=\"us-ascii'en-us'My\"; +\tname*1=\" Document\"; +\tname*2*=\" For You\" + +""" + msg = email.message_from_string(m) + charset, language, s = msg.get_param('name') + eq(charset, 'us-ascii') + eq(language, 'en-us') + eq(s, 'My Document For You') + + def test_rfc2231_unencoded_then_encoded_segments(self): + eq = self.assertEqual + m = """\ +Content-Type: application/x-foo; +\tname*0=\"us-ascii'en-us'My\"; +\tname*1*=\" Document\"; +\tname*2*=\" For You\" + +""" + msg = email.message_from_string(m) + charset, language, s = msg.get_param('name') + eq(charset, 'us-ascii') + eq(language, 'en-us') + eq(s, 'My Document For You') + + + +# Tests to ensure that signed parts of an email are completely preserved, as +# required by RFC1847 section 2.1. Note that these are incomplete, because the +# email package does not currently always preserve the body. See issue 1670765. +class TestSigned(TestEmailBase): + + def _msg_and_obj(self, filename): + with openfile(findfile(filename)) as fp: + original = fp.read() + msg = email.message_from_string(original) + return original, msg + + def _signed_parts_eq(self, original, result): + # Extract the first mime part of each message + import re + repart = re.compile(r'^--([^\n]+)\n(.*?)\n--\1$', re.S | re.M) + inpart = repart.search(original).group(2) + outpart = repart.search(result).group(2) + self.assertEqual(outpart, inpart) + + def test_long_headers_as_string(self): + original, msg = self._msg_and_obj('msg_45.txt') + result = msg.as_string() + self._signed_parts_eq(original, result) + + def test_long_headers_as_string_maxheaderlen(self): + original, msg = self._msg_and_obj('msg_45.txt') + result = msg.as_string(maxheaderlen=60) + self._signed_parts_eq(original, result) + + def test_long_headers_flatten(self): + original, msg = self._msg_and_obj('msg_45.txt') + fp = StringIO() + Generator(fp).flatten(msg) + result = fp.getvalue() + self._signed_parts_eq(original, result) + + + +if __name__ == '__main__': + unittest.main() diff --git a/Lib/test/test_email/tourture_test.py b/Lib/test/test_email/tourture_test.py new file mode 100644 index 0000000..544b1bb --- /dev/null +++ b/Lib/test/test_email/tourture_test.py @@ -0,0 +1,136 @@ +# Copyright (C) 2002-2004 Python Software Foundation +# +# A torture test of the email package. This should not be run as part of the +# standard Python test suite since it requires several meg of email messages +# collected in the wild. These source messages are not checked into the +# Python distro, but are available as part of the standalone email package at +# http://sf.net/projects/mimelib + +import sys +import os +import unittest +from io import StringIO +from types import ListType + +from email.test.test_email import TestEmailBase +from test.support import TestSkipped, run_unittest + +import email +from email import __file__ as testfile +from email.iterators import _structure + +def openfile(filename): + from os.path import join, dirname, abspath + path = abspath(join(dirname(testfile), os.pardir, 'moredata', filename)) + return open(path, 'r') + +# Prevent this test from running in the Python distro +try: + openfile('crispin-torture.txt') +except IOError: + raise TestSkipped + + + +class TortureBase(TestEmailBase): + def _msgobj(self, filename): + fp = openfile(filename) + try: + msg = email.message_from_file(fp) + finally: + fp.close() + return msg + + + +class TestCrispinTorture(TortureBase): + # Mark Crispin's torture test from the SquirrelMail project + def test_mondo_message(self): + eq = self.assertEqual + neq = self.ndiffAssertEqual + msg = self._msgobj('crispin-torture.txt') + payload = msg.get_payload() + eq(type(payload), ListType) + eq(len(payload), 12) + eq(msg.preamble, None) + eq(msg.epilogue, '\n') + # Probably the best way to verify the message is parsed correctly is to + # dump its structure and compare it against the known structure. + fp = StringIO() + _structure(msg, fp=fp) + neq(fp.getvalue(), """\ +multipart/mixed + text/plain + message/rfc822 + multipart/alternative + text/plain + multipart/mixed + text/richtext + application/andrew-inset + message/rfc822 + audio/basic + audio/basic + image/pbm + message/rfc822 + multipart/mixed + multipart/mixed + text/plain + audio/x-sun + multipart/mixed + image/gif + image/gif + application/x-be2 + application/atomicmail + audio/x-sun + message/rfc822 + multipart/mixed + text/plain + image/pgm + text/plain + message/rfc822 + multipart/mixed + text/plain + image/pbm + message/rfc822 + application/postscript + image/gif + message/rfc822 + multipart/mixed + audio/basic + audio/basic + message/rfc822 + multipart/mixed + application/postscript + text/plain + message/rfc822 + multipart/mixed + text/plain + multipart/parallel + image/gif + audio/basic + application/atomicmail + message/rfc822 + audio/x-sun +""") + + +def _testclasses(): + mod = sys.modules[__name__] + return [getattr(mod, name) for name in dir(mod) if name.startswith('Test')] + + +def suite(): + suite = unittest.TestSuite() + for testclass in _testclasses(): + suite.addTest(unittest.makeSuite(testclass)) + return suite + + +def test_main(): + for testclass in _testclasses(): + run_unittest(testclass) + + + +if __name__ == '__main__': + unittest.main(defaultTest='suite') |