mms2r 1.0.0 → 1.0.2

data/History.txt

@@ -1,4 +1,22 @@
+== 1.0.2 / 2007-03-07
+
+* Reorganized tests and fixtures
+* Added carriers:
+* Cingular => cingularme.com
+* Nextel => messaging.nextel.com
+* Verizon => vtext.com
+
+== 1.0.2 / 2007-03-07
+
+* Flubbed RubyForge release ... do not use this.
+
 == 1.0.0 / 2007-03-06
 
 * Birthday!
+* AT&T/Cingular => mmode.com
+* Cingular => mms.mycingular.com
+* Sprint => pm.sprint.com
+* Sprint => messaging.sprintpcs.com
+* T-Mobile => tmomail.net
+* Verizon => vzwpix.com
 

data/Manifest.txt

@@ -3,6 +3,7 @@ Manifest.txt
 README.txt
 Rakefile
 conf/mms2r_cingularmedia_transform.yml
+conf/mms2r_nextelmedia_ignore.yml
 conf/mms2r_sprintmedia_ignore.yml
 conf/mms2r_tmobilemedia_ignore.yml
 conf/mms2r_verizonmedia_ignore.yml
@@ -10,6 +11,7 @@ lib/mms2r.rb
 lib/mms2r/cingular_media.rb
 lib/mms2r/media.rb
 lib/mms2r/mmode_media.rb
+lib/mms2r/nextel_media.rb
 lib/mms2r/sprint_media.rb
 lib/mms2r/tmobile_media.rb
 lib/mms2r/verizon_media.rb
@@ -38,17 +40,28 @@ lib/vendor/tmail/scanner_r.rb
 lib/vendor/tmail/stringio.rb
 lib/vendor/tmail/tmail.rb
 lib/vendor/tmail/utils.rb
+test/files/cingularme-text-01.mail
 test/files/dot.jpg
+test/files/hello_world_mail_multipart.mail
+test/files/hello_world_mail_plain_no_content_type.mail
+test/files/hello_world_mail_plain_with_content_type.mail
+test/files/mmode-image-01.mail
+test/files/nextel-image-01.mail
+test/files/simple_image.mail
+test/files/simple_multipart_alternative.mail
 test/files/sprint-image-01.mail
 test/files/sprint-text-01.mail
 test/files/sprint-video-01.mail
 test/files/sprint.mov
+test/files/tmobile-image-01.mail
 test/files/verizon-image-01.mail
 test/files/verizon-text-01.mail
 test/files/verizon-video-01.mail
+test/files/vtext-text-01.mail
 test/test_mms2r_cingular.rb
 test/test_mms2r_media.rb
 test/test_mms2r_mmode.rb
+test/test_mms2r_nextel.rb
 test/test_mms2r_sprint.rb
 test/test_mms2r_tmobile.rb
 test/test_mms2r_verizon.rb

data/README.txt

@@ -8,47 +8,67 @@ http://mms2r.rubyforge.org/
   
 MMS2R is a library that decodes the parts of an MMS message to disk while 
 stripping out advertising injected by the cellphone carriers.  MMS messages are 
-multipart email and the carriers often inject branding into these messages. 
+multipart email and the carriers often inject branding into these messages.  Use
+MMS2R if you want to get at the real user generated content from a MMS without
+having to deal with the garbage from the carriers.
 
 If MMS2R is not aware of a particular carrier no extra processing is done 
 to the MMS other than decoding and consolidating its media.
 
 Contact the author to add additional carriers to be processed by the library.
 
-== FEATURES/PROBLEMS:
-
 Corpus of carriers currently processed by MMS2R:
 
 * AT&T/Cingular => mmode.com
 * Cingular => mms.mycingular.com
+* Cingular => cingularme.com
+* Nextel => messaging.nextel.com
 * Sprint => pm.sprint.com
 * Sprint => messaging.sprintpcs.com
 * T-Mobile => tmomail.net
 * Verizon => vzwpix.com
-  
+* Verizon => vtext.com
+
+== FEATURES/PROBLEMS:
+
+TMail from 1.3.1 of ActionMailer is shipped as a vendor library with MMS2R
+ 
 == SYNOPSIS:
 
   require 'rubygems'
   require 'mms2r'
+  require 'mms2r/media'
   require 'tmail'
-  media = TMail::Media.parse(IO.readlines("mymail.file").join)
-  mms = MMS2R::Media.create(mail,Logger.new(STDOUT))
+  require 'fileutils'
+
+  media = TMail::Media.parse(IO.readlines("sample-MMS.file").join)
+  mms = MMS2R::Media.create(media,Logger.new(STDOUT))
+
+  # process finds all the media in a MMS, strips advertsing, then
+  # writes the user generated media to disk
   mms.process
-  # mms.media is a hash that is indexed by mime-type
-  # the mime-type key returns an array of filepaths
-  # to media in the MMS that was of that type
-  mms.media['image/jpeg'].each {|f| puts "${f}"}
-  mms.media['text/plain'].each {|f| puts "${f}"}
-  text = File.open(mms.media['text/plain'][0], 'rb') { |file|
-       file.read
-  }
+
+  # mms.media is a hash that is indexed by mime-type.
+  # The mime-type key returns an array of filepaths
+  # to media in the MMS that is of that type
+  mms.media['image/jpeg'].each {|f| puts "#{f}"}
+  mms.media['text/plain'].each {|f| puts "#{f}"}
+
+  # print the text (assumes MMS had text)
+  text = IO.readlines(mms.media['text/plain'][0]).join
   puts text
+
+  # save the image (assumes MMS had a jpeg)
+  FileUtils.cp mms.media['image/jpeg'][0], '/some/where/use/ful', :verbose => true
+
+  puts "does the MMS have video? #{!mms.media['video/quicktime'].nil?}"
+
   #remove the media that was put to temporary disk
-  #mms.purge
+  mms.purge
 
 == REQUIREMENTS:
 
-* TMail
+* RCov
 * Hpricot
 
 == INSTALL:

data/Rakefile

@@ -13,7 +13,7 @@ Hoe.new('mms2r', MMS2R::Media::VERSION) do |p|
   p.author = 'Mike Mondragon'
   p.email = 'mike@mondragon.cc'
   p.summary = 'Extract media from MMS '
-  p.description = p.paragraphs_of('README.txt', 2..5).join("\n\n")
+  p.description = p.paragraphs_of('README.txt', 2..8).join("\n\n")
   p.url = p.paragraphs_of('README.txt', 0).first.split(/\n/)[1..-1]
   p.changes = p.paragraphs_of('History.txt', 0..1).join("\n\n")
   p.extra_deps << ['hpricot']

data/conf/mms2r_cingularmedia_transform.yml

@@ -1,6 +1,6 @@
 --- 
 text/plain: 
-  "--\n\
+  "\n--\n\
     ===============================================\n\
     Brought to you by, Cingular Wireless Messaging\n\
-    http://www.CingularMe.COM/\n ": ""
+    http://www.CingularMe.COM/": ""

data/conf/mms2r_nextelmedia_ignore.yml

@@ -0,0 +1,5 @@
+--- 
+text/plain: 
+- This is an MMS message.  2006 Sprint Nextel. All rights reserved.
+text/html: 
+- <center>This is an MMS message. <br><center> 2006 Sprint Nextel. All rights reserved</center>

data/lib/mms2r/media.rb

@@ -10,6 +10,7 @@ require 'mms2r'
 require 'mms2r/version'
 require 'mms2r/cingular_media'
 require 'mms2r/mmode_media'
+require 'mms2r/nextel_media'
 require 'mms2r/sprint_media'
 require 'mms2r/tmobile_media'
 require 'mms2r/verizon_media'
@@ -56,10 +57,13 @@ module MMS2R
 
   CARRIER_CLASSES = {
     'mms.mycingular.com' => MMS2R::CingularMedia,
+    'cingularme.com' => MMS2R::CingularMedia,
     'mmode.com' => MMS2R::MModeMedia,
+    'messaging.nextel.com' => MMS2R::NextelMedia,
     'pm.sprint.com' => MMS2R::SprintMedia,
     'messaging.sprintpcs.com' => MMS2R::SprintMedia,
     'tmomail.net' => MMS2R::TMobileMedia,
+    'vtext.com' => MMS2R::VerizonMedia,
     'vzwpix.com' => MMS2R::VerizonMedia
   }
 
@@ -111,30 +115,35 @@ module MMS2R
       # if the part is not base64 encoded.
       part.base64_decode
       file = temp_file(part)
-      content = part.body
-      content = transform_text(self.class.part_type?(part),content) if self.class.main_type?(part).eql?('text')
+      if self.class.main_type?(part).eql?('text')
+        type, content = transform_text(part)
+      else
+        type = self.class.part_type?(part)
+        content = part.body
+      end
       @logger.info("#{self.class} writing file #{file}") unless @logger.nil?
       File.open(file,'w'){ |f|
         f.write(content)
       }
-      type = self.class.part_type?(part)
       return type, file
     end
 
     ##
     # Helper for process_media template method to transform text.
 
-    def transform_text(type,text)
+    def transform_text(part)
+      type = self.class.part_type?(part)
+      text = part.body
       f = "#{self.class.name.downcase.gsub(/::/,'_')}_transform.yml"
       yf = File.join(self.class.conf_dir(), "#{f}")
-      return text unless File::exist?(yf)
+      return type, text unless File::exist?(yf)
       h = YAML::load_file(yf)
       a = h[type]
-      return text if a.nil?
+      return type, text if a.nil?
       a.each do |from,to|
         text.gsub!(/#{from}/m,to)
       end
-      text
+      return type, text
     end
 
     ##
@@ -210,6 +219,14 @@ module MMS2R
         parts = Array.new()
         parts << @mail
       end
+      parts.each do |p|
+        if self.class.part_type?(p).eql?('multipart/alternative')
+          part = parts.delete(p)
+          part.parts.each do |mp|
+             parts << mp
+          end
+        end
+      end
       parts.each do |p|
         t = self.class.part_type?(p)
         unless ignore_media?(t,p)

data/lib/mms2r/nextel_media.rb

@@ -0,0 +1,11 @@
+require 'mms2r'
+require 'mms2r/media'
+
+module MMS2R
+
+  ##
+  # Nextel version of MMS2R::Media
+
+  class MMS2R::NextelMedia < MMS2R::Media
+  end
+end

data/lib/mms2r/sprint_media.rb

@@ -22,8 +22,7 @@ module MMS2R
       part.base64_decode
       if self.class.part_type?(part).eql?('text/plain')
         file_name = filename?(part)
-        type = 'text/plain'
-        content = transform_text(type,part.body)
+        type, content = transform_text(part)
       elsif self.class.part_type?(part).eql?('text/html')
         doc = Hpricot(part.body)
         trs = doc.search("/html/body//tr")

data/lib/mms2r/version.rb

@@ -6,7 +6,7 @@ module MMS2R
     ##
     # MMS2R Library version
 
-    VERSION = '1.0.0'
+    VERSION = '1.0.2'
 
   end
 end

data/test/files/cingularme-text-01.mail

@@ -0,0 +1,13 @@
+From: 2068675309@cingularme.com
+To: tommytutone@example.com
+Subject: 
+X-OPWV-Extra-Message-Type: MO
+Message-Id: <01234567890123.ABCD4567.foobar01.cingularme.com@cingularme.com>
+Date: Wed, 7 Feb 2007 00:39:36 -0500
+
+hello world
+
+--
+===============================================
+Brought to you by, Cingular Wireless Messaging
+http://www.CingularMe.COM/

data/test/files/hello_world_mail_multipart.mail

@@ -0,0 +1,17 @@
+Message-Id: <00000000000002.0123456789@mx.mms.example.com>
+Mime-Version: 1.0
+From: 2068675309@mms.example.com
+To: tommytutone@example.com
+Subject: text only
+Date: Thu, 11 Jan 2007 02:28:22 -0500
+Content-Type: multipart/mixed;  boundary="----=_Part_1061064_5544954.1168500502466"
+
+------=_Part_1061064_5544954.1168500502466
+Content-Type: text/plain; charset=utf-8
+Content-Transfer-Encoding: base64
+Content-Location: hello_world.txt
+Content-Disposition: inline
+
+aGVsbG8gd29ybGQ=
+------=_Part_1061064_5544954.1168500502466--
+

data/test/files/hello_world_mail_plain_no_content_type.mail

@@ -0,0 +1,7 @@
+From:2068675309@mms.example.com
+To:tommytutone@example.com
+Subject: text only
+Message-Id: <00000000000001.0123456789@mx.mms.example.com>
+Date: Wed, 10 Jan 2007 08:18:30 -0600 (CST)
+
+hello world

data/test/files/hello_world_mail_plain_with_content_type.mail

@@ -0,0 +1,8 @@
+From:2068675309@mms.example.com
+To:tommytutone@example.com
+Subject: text only
+Message-Id: <00000000000001.0123456789@mx.mms.example.com>
+Content-Type: text/plain; charset=utf-8
+Date: Wed, 10 Jan 2007 08:18:30 -0600 (CST)
+
+hello world

data/test/files/mmode-image-01.mail

@@ -0,0 +1,36 @@
+Message-Id: <0123456.7890123456789.JavaMail.foot@st-09>
+Date: Sat, 16 Sep 2006 08:05:47 -0600 (GMT-06:00)
+From: 12068675309@mmode.com
+To: tommytutone@example.com
+Subject: Picture(3).jpg
+Mime-Version: 1.0
+Content-Type: multipart/mixed; 
+	boundary="----=_Part_012345_678901.1231231231239"
+X-Mms-Delivery-Report: no
+X-Mms-Delivery-Time: Sat, 16 Sep 2006 08:05:47 -0600 (GMT-06:00)
+X-Mms-MMS-Version: 1.0
+X-Mms-Message-Class: Personal
+X-Mms-Message-Type: m-send-req
+X-Mms-Message-Size: 33774
+X-Mms-Read-Reply: no
+X-Mms-Sender-Visibility: Show
+X-Mms-Transaction-ID: 3-1fac@mms.mmode.com
+X-Mms-Message-ID: 12345678@mms.mmode.com
+X-Priority: 3
+
+------=_Part_012345_678901.1231231231239
+Content-Type: image/jpeg; name="picture(3).jpg"
+Content-Transfer-Encoding: base64
+Content-ID: <picture(3).jpg>
+Content-Location: picture(3).jpg
+Content-Disposition: attachment
+
+/9j/4AAQSkZJRgABAQEASABIAAD/4QAWRXhpZgAATU0AKgAAAAgAAAAAAAD//gAXQ3JlYXRl
+ZCB3aXRoIFRoZSBHSU1Q/9sAQwAFAwQEBAMFBAQEBQUFBgcMCAcHBwcPCwsJDBEPEhIRDxER
+ExYcFxMUGhURERghGBodHR8fHxMXIiQiHiQcHh8e/9sAQwEFBQUHBgcOCAgOHhQRFB4eHh4e
+Hh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4e/8AAEQgAAQAB
+AwEiAAIRAQMRAf/EABUAAQEAAAAAAAAAAAAAAAAAAAAH/8QAFBABAAAAAAAAAAAAAAAAAAAA
+AP/EABUBAQEAAAAAAAAAAAAAAAAAAAcI/8QAFBEBAAAAAAAAAAAAAAAAAAAAAP/aAAwDAQAC
+EQMRAD8AlgA6WW//2Q==
+------=_Part_012345_678901.1231231231239--
+

data/test/files/nextel-image-01.mail

@@ -0,0 +1,46 @@
+Content-Type: multipart/related; boundary="01ab23456c78qwerty_0000"; type="multipart/alternative"
+To: <tommytutone@example.com>
+Date: Sun, 04 Feb 2007 05:38:37 GMT
+From: 2068675309@messaging.nextel.com
+Sender: "2068675309" <2068675309@messaging.nextel.com>
+X-Priority: 3
+MIME-Version: 1.0
+Message-Id: <01234567890123.ABCD4567.fofofo03.messaging.nextel.com@fofozzzz>
+
+This is a multi-part message in MIME format.
+
+--01ab23456c78qwerty_0000
+Content-Type: multipart/alternative; boundary="abcd_0123456789_abcdefg"
+
+
+--abcd_0123456789_abcdefg
+Content-Type: text/plain; charset="utf-8"
+
+This is an MMS message.  2006 Sprint Nextel. All rights reserved.
+
+--abcd_0123456789_abcdefg
+Content-Type: text/html; charset="utf-8"
+
+<html><body>
+
+<center>This is an MMS message. <br><center> 2006 Sprint Nextel. All rights reserved</center><br><img src="cid:Jan15_0001.jpg.jpg" border="0" alt="Jan15_0001.jpg"><p>
+<p><br><p>
+</center>
+</body></html>
+
+--abcd_0123456789_abcdefg--
+
+--01ab23456c78qwerty_0000
+Content-ID: <Jan15_0001.jpg.jpg>
+Content-Type: image/jpeg; name="Jan15_0001.jpg"
+Content-Disposition: inline; filename="Jan15_0001.jpg"
+Content-Transfer-Encoding: base64
+
+/9j/4AAQSkZJRgABAQEASABIAAD/4QAWRXhpZgAATU0AKgAAAAgAAAAAAAD//gAXQ3JlYXRl
+ZCB3aXRoIFRoZSBHSU1Q/9sAQwAFAwQEBAMFBAQEBQUFBgcMCAcHBwcPCwsJDBEPEhIRDxER
+ExYcFxMUGhURERghGBodHR8fHxMXIiQiHiQcHh8e/9sAQwEFBQUHBgcOCAgOHhQRFB4eHh4e
+Hh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4e/8AAEQgAAQAB
+AwEiAAIRAQMRAf/EABUAAQEAAAAAAAAAAAAAAAAAAAAH/8QAFBABAAAAAAAAAAAAAAAAAAAA
+AP/EABUBAQEAAAAAAAAAAAAAAAAAAAcI/8QAFBEBAAAAAAAAAAAAAAAAAAAAAP/aAAwDAQAC
+EQMRAD8AlgA6WW//2Q==
+--01ab23456c78qwerty_0000--

data/test/files/simple_image.mail

@@ -0,0 +1,19 @@
+Mime-Version: 1.0
+Message-Id: <00000000000001.0123456789@mx.mms.example.com>
+Date: Sun, 29 Oct 2006 20:40:30 -0800 (PST)
+To: tommytutone@example.com
+From: 2068675309@mms.example.com
+Subject: image test
+Content-Type: multipart/related; type="multipart/alternative";
+	boundary="----=_Part_1224755_98719.1162204830872"; start="<SMIL.TXT>"
+X-Mms-Delivery-Report: no
+
+------=_Part_1224755_98719.1162204830872
+Content-Type: image/gif; name=spacer.gif
+Content-Transfer-Encoding: base64
+Content-Disposition: attachment; filename=spacer.gif
+Content-ID: <spacer.gif>
+
+R0lGODlhAQABAIAAAP///wAAACH5BAAAAAAALAAAAAABAAEAAAICRAEAOw==
+------=_Part_1224755_98719.1162204830872--
+