Merge remote-tracking branch 'github/split-to-spec' into HEAD

Conflicts:
	lib/mail/message.rb

CHANGELOG.rdoc

@@ -9,6 +9,7 @@ Features:
 * Setting the html_ or text_part sets a default text/html or text/plain content type (jeremy)
 * Setting the html_ or text_part to nil removes it (jeremy)
 * Addresses without a parsable email or display name still format as their raw text (jeremy)
+* Close pull request 504 - Alias GB2312 charset to GB18030 Ruby encoding (bpot)
 * Close pull request 399 - Accept :ca_path and :ca_file options for SMTP delivery (ndbroadbent)
 * Close pull request 389 - Don't add superfluous message headers to MIME parts (djmaze, jeremy)
 
@@ -29,6 +30,8 @@ Bugs:
 * The Received header may contain zero name/value pairs, qmail-style (jeremy)
 * Fix that setting an attachment with a :mime_type and :encoding would override the :encoding (jeremy)
 * Fix that declaring an html_part but no text_part would use multipart/alternative anyway (jeremy)
+* Close pull request 508 - Don't add an extra CRLF to MIME parts; split MIME parts on correct CRLF boundaries (Aalanar)
+* Close pull request 506 - Escape backslashes in quoted strings (ConradIrwin)
 * Close pull request 496 - Correctly handle quoted-printable line breaks (jeremy)
 * Close pull request 493 - Repair misencoded quoted-printable line breaks (jeremy)
 * Close pull request 487 - Extract comments from group email addresses (bpot)
@@ -46,6 +49,7 @@ Housekeeping:
 * Remove i18n dependency and last vestiges of activesupport dependency in specs (jeremy)
 * Clarify that Sender is a single address, not an address list (jeremy)
 * Add an MIT-LICENSE file to make licensing clear & obvious; update to 2013 (jeremy)
+* Close pull request 501 - Tighten up header/body whitespace splitting (ConradIrwin)
 * Close pull request 499 - Clean up some dead code (ConradIrwin)
 * Close pull request 489, 495 - Docs typos (JackDanger, francois)
 * Close pull request 485 - Be explicit about unsupported address parsing (bpot)

README.md

@@ -339,8 +339,8 @@ mail = Mail.read('multipart_email')
 
 mail.multipart?          #=> true
 mail.parts.length        #=> 2
-mail.preamble            #=> "Text before the first part"
-mail.epilogue            #=> "Text after the last part"
+mail.body.preamble       #=> "Text before the first part"
+mail.body.epilogue       #=> "Text after the last part"
 mail.parts.map { |p| p.content_type }  #=> ['text/plain', 'application/pdf']
 mail.parts.map { |p| p.class }         #=> [Mail::Message, Mail::Message]
 mail.parts[0].content_type_parameters  #=> {'charset' => 'ISO-8859-1'}

lib/mail/body.rb

@@ -264,7 +264,7 @@ def <<( val )
 
     def split!(boundary)
       self.boundary = boundary
-      parts = raw_source.split(/--#{Regexp.escape(boundary)}(?=(?:--)?\s*$)/)
+      parts = raw_source.split(/(?:\A|\r\n)--#{Regexp.escape(boundary)}(?=(?:--)?\s*$)/)
       # Make the preamble equal to the preamble (if any)
       self.preamble = parts[0].to_s.strip
       # Make the epilogue equal to the epilogue (if any)
@@ -288,11 +288,11 @@ def need_to_sort?
     private
 
     def crlf_boundary
-      "\r\n\r\n--#{boundary}\r\n"
+      "\r\n--#{boundary}\r\n"
     end
 
     def end_boundary
-      "\r\n\r\n--#{boundary}--\r\n"
+      "\r\n--#{boundary}--\r\n"
     end
 
     def set_charset

lib/mail/encodings.rb

@@ -114,19 +114,19 @@ def Encodings.decode_encode(str, output_type)
     # String has to be of the format =?<encoding>?[QB]?<string>?=
     def Encodings.value_decode(str)
       # Optimization: If there's no encoded-words in the string, just return it
-      return str unless str.index("=?")
+      return str unless str =~ /\=\?[^?]+\?[QB]\?[^?]+?\?\=/xmi
 
       lines = collapse_adjacent_encodings(str)
 
       # Split on white-space boundaries with capture, so we capture the white-space as well
       lines.map do |line|
         line.split(/([ \t])/).map do |text|
-          if text.index('=?') .nil?
+          if text.index('=?').nil?
             text
           else
             # Search for occurences of quoted strings or plain strings
-            text.scan(/(                                  # Group around entire regex to include it in matches
-                        \=\?[^?]+\?([QB])\?[^?]+?\?\=  # Quoted String with subgroup for encoding method
+            text.scan(/(                                 # Group around entire regex to include it in matches
+                        \=\?[^?]+\?([QB])\?[^?]+?\?\=    # Quoted String with subgroup for encoding method
                         |                                # or
                         .+?(?=\=\?|$)                    # Plain String
                       )/xmi).map do |matches|

lib/mail/fields/bcc_field.rb

@@ -16,7 +16,7 @@
 # 
 #  mail = Mail.new
 #  mail.bcc = 'Mikel Lindsaar <mikel@test.lindsaar.net>, ada@test.lindsaar.net'
-#  mail.bcc    #=> ['Mikel Lindsaar <mikel@test.lindsaar.net>', 'ada@test.lindsaar.net']
+#  mail.bcc    #=> ['mikel@test.lindsaar.net', 'ada@test.lindsaar.net']
 #  mail[:bcc]  #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::BccField:0x180e1c4
 #  mail['bcc'] #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::BccField:0x180e1c4
 #  mail['Bcc'] #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::BccField:0x180e1c4

lib/mail/fields/cc_field.rb

@@ -16,7 +16,7 @@
 # 
 #  mail = Mail.new
 #  mail.cc = 'Mikel Lindsaar <mikel@test.lindsaar.net>, ada@test.lindsaar.net'
-#  mail.cc    #=> ['Mikel Lindsaar <mikel@test.lindsaar.net>', 'ada@test.lindsaar.net']
+#  mail.cc    #=> ['mikel@test.lindsaar.net', 'ada@test.lindsaar.net']
 #  mail[:cc]  #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::CcField:0x180e1c4
 #  mail['cc'] #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::CcField:0x180e1c4
 #  mail['Cc'] #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::CcField:0x180e1c4

lib/mail/fields/from_field.rb

@@ -16,7 +16,7 @@
 # 
 #  mail = Mail.new
 #  mail.from = 'Mikel Lindsaar <mikel@test.lindsaar.net>, ada@test.lindsaar.net'
-#  mail.from    #=> ['Mikel Lindsaar <mikel@test.lindsaar.net>', 'ada@test.lindsaar.net']
+#  mail.from    #=> ['mikel@test.lindsaar.net', 'ada@test.lindsaar.net']
 #  mail[:from]  #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::FromField:0x180e1c4
 #  mail['from'] #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::FromField:0x180e1c4
 #  mail['From'] #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::FromField:0x180e1c4

lib/mail/fields/reply_to_field.rb

@@ -16,7 +16,7 @@
 # 
 #  mail = Mail.new
 #  mail.reply_to = 'Mikel Lindsaar <mikel@test.lindsaar.net>, ada@test.lindsaar.net'
-#  mail.reply_to    #=> ['Mikel Lindsaar <mikel@test.lindsaar.net>', 'ada@test.lindsaar.net']
+#  mail.reply_to    #=> ['mikel@test.lindsaar.net', 'ada@test.lindsaar.net']
 #  mail[:reply_to]  #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::ReplyToField:0x180e1c4
 #  mail['reply-to'] #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::ReplyToField:0x180e1c4
 #  mail['Reply-To'] #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::ReplyToField:0x180e1c4

lib/mail/fields/resent_bcc_field.rb

@@ -16,7 +16,7 @@
 # 
 #  mail = Mail.new
 #  mail.resent_bcc = 'Mikel Lindsaar <mikel@test.lindsaar.net>, ada@test.lindsaar.net'
-#  mail.resent_bcc    #=> ['Mikel Lindsaar <mikel@test.lindsaar.net>', 'ada@test.lindsaar.net']
+#  mail.resent_bcc    #=> ['mikel@test.lindsaar.net', 'ada@test.lindsaar.net']
 #  mail[:resent_bcc]  #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::ResentBccField:0x180e1c4
 #  mail['resent-bcc'] #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::ResentBccField:0x180e1c4
 #  mail['Resent-Bcc'] #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::ResentBccField:0x180e1c4

lib/mail/fields/resent_cc_field.rb

@@ -16,7 +16,7 @@
 # 
 #  mail = Mail.new
 #  mail.resent_cc = 'Mikel Lindsaar <mikel@test.lindsaar.net>, ada@test.lindsaar.net'
-#  mail.resent_cc    #=> ['Mikel Lindsaar <mikel@test.lindsaar.net>', 'ada@test.lindsaar.net']
+#  mail.resent_cc    #=> ['mikel@test.lindsaar.net', 'ada@test.lindsaar.net']
 #  mail[:resent_cc]  #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::ResentCcField:0x180e1c4
 #  mail['resent-cc'] #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::ResentCcField:0x180e1c4
 #  mail['Resent-Cc'] #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::ResentCcField:0x180e1c4

lib/mail/fields/resent_from_field.rb

@@ -16,7 +16,7 @@
 #
 #  mail = Mail.new
 #  mail.resent_from = 'Mikel Lindsaar <mikel@test.lindsaar.net>, ada@test.lindsaar.net'
-#  mail.resent_from    #=> ['Mikel Lindsaar <mikel@test.lindsaar.net>', 'ada@test.lindsaar.net']
+#  mail.resent_from    #=> ['mikel@test.lindsaar.net', 'ada@test.lindsaar.net']
 #  mail[:resent_from]  #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::ResentFromField:0x180e1c4
 #  mail['resent-from'] #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::ResentFromField:0x180e1c4
 #  mail['Resent-From'] #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::ResentFromField:0x180e1c4

lib/mail/fields/resent_sender_field.rb

@@ -16,7 +16,7 @@
 # 
 #  mail = Mail.new
 #  mail.resent_sender = 'Mikel Lindsaar <mikel@test.lindsaar.net>, ada@test.lindsaar.net'
-#  mail.resent_sender    #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::ResentSenderField:0x180e1c4
+#  mail.resent_sender    #=> ['mikel@test.lindsaar.net']
 #  mail[:resent_sender]  #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::ResentSenderField:0x180e1c4
 #  mail['resent-sender'] #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::ResentSenderField:0x180e1c4
 #  mail['Resent-Sender'] #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::ResentSenderField:0x180e1c4

lib/mail/fields/resent_to_field.rb

@@ -16,7 +16,7 @@
 # 
 #  mail = Mail.new
 #  mail.resent_to = 'Mikel Lindsaar <mikel@test.lindsaar.net>, ada@test.lindsaar.net'
-#  mail.resent_to    #=> ['Mikel Lindsaar <mikel@test.lindsaar.net>', 'ada@test.lindsaar.net']
+#  mail.resent_to    #=> ['mikel@test.lindsaar.net', 'ada@test.lindsaar.net']
 #  mail[:resent_to]  #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::ResentToField:0x180e1c4
 #  mail['resent-to'] #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::ResentToField:0x180e1c4
 #  mail['Resent-To'] #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::ResentToField:0x180e1c4

lib/mail/fields/sender_field.rb

@@ -16,7 +16,7 @@
 # 
 #  mail = Mail.new
 #  mail.sender = 'Mikel Lindsaar <mikel@test.lindsaar.net>'
-#  mail.sender    #=> 'Mikel Lindsaar <mikel@test.lindsaar.net>'
+#  mail.sender    #=> 'mikel@test.lindsaar.net'
 #  mail[:sender]  #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::SenderField:0x180e1c4
 #  mail['sender'] #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::SenderField:0x180e1c4
 #  mail['Sender'] #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::SenderField:0x180e1c4

lib/mail/fields/to_field.rb

@@ -16,7 +16,7 @@
 # 
 #  mail = Mail.new
 #  mail.to = 'Mikel Lindsaar <mikel@test.lindsaar.net>, ada@test.lindsaar.net'
-#  mail.to    #=> ['Mikel Lindsaar <mikel@test.lindsaar.net>', 'ada@test.lindsaar.net']
+#  mail.to    #=> ['mikel@test.lindsaar.net', 'ada@test.lindsaar.net']
 #  mail[:to]  #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::ToField:0x180e1c4
 #  mail['to'] #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::ToField:0x180e1c4
 #  mail['To'] #=> '#<Mail::Field:0x180e5e8 @field=#<Mail::ToField:0x180e1c4

lib/mail/message.rb

@@ -938,8 +938,8 @@ def resent_sender( val = nil )
     #
     # Example:
     #
-    #  mail.sender = 'Mikel <mikel@test.lindsaar.net>'
-    #  mail.sender #=> 'mikel@test.lindsaar.net'
+    #  mail.resent_sender = 'Mikel <mikel@test.lindsaar.net>'
+    #  mail.resent_sender #=> 'mikel@test.lindsaar.net'
     def resent_sender=( val )
       header[:resent_sender] = val
     end
@@ -1889,11 +1889,8 @@ def text?
     #   this standard. The body is simply a sequence of characters that
     #   follows the header and is separated from the header by an empty line
     #   (i.e., a line with nothing preceding the CRLF).
-    #
-    # Additionally, I allow for the case where someone might have put whitespace
-    # on the "gap line"
     def parse_message
-      header_part, body_part = raw_source.lstrip.split(/#{CRLF}#{CRLF}|#{CRLF}#{WSP}*#{CRLF}(?!#{WSP})/m, 2)
+      header_part, body_part = raw_source.lstrip.split(/#{CRLF}#{CRLF}/, 2)
       self.header = header_part
       self.body   = body_part
     end

lib/mail/utilities.rb

@@ -41,28 +41,36 @@ def quote_token( str )
       token_safe?( str ) ? str : dquote(str)
     end
 
-    # Wraps supplied string in double quotes unless it is already wrapped.
-    # 
-    # Additionally will escape any double quotation marks in the string with a single
-    # backslash in front of the '"' character.
+    # Wraps supplied string in double quotes and applies \-escaping as necessary,
+    # unless it is already wrapped.
+    #
+    # Example:
+    #
+    #  string = 'This is a string'
+    #  dquote(string) #=> '"This is a string"'
+    #
+    #  string = 'This is "a string"'
+    #  dquote(string #=> '"This is \"a string\"'
     def dquote( str )
-      match = str.match(/^"(.*)?"$/)
-      str = match[1] if match
-      # First remove all escaped double quotes:
-      str = str.gsub(/\\"/, '"')
-      # Then wrap and re-escape all double quotes
-      '"' + str.gsub(/["]/n) {|s| '\\' + s } + '"'
+      '"' + unquote(str).gsub(/[\\"]/n) {|s| '\\' + s } + '"'
     end
-
-    # Unwraps supplied string from inside double quotes.
-    # 
+
+    # Unwraps supplied string from inside double quotes and
+    # removes any \-escaping.
+    #
     # Example:
-    # 
+    #
     #  string = '"This is a string"'
     #  unquote(string) #=> 'This is a string'
+    #
+    #  string = '"This is \"a string\""'
+    #  unqoute(string) #=> 'This is "a string"'
     def unquote( str )
-      match = str.match(/^"(.*?)"$/)
-      match ? match[1] : str
+      if str =~ /^"(.*?)"$/
+        $1.gsub(/\\(.)/, '\1')
+      else
+        str
+      end
     end
 
     # Wraps a string in parenthesis and escapes any that are in the string itself.

lib/mail/version_specific/ruby_1_9.rb

@@ -132,6 +132,10 @@ def Ruby19.pick_encoding(charset)
       when 'shift-jis'
         Encoding::Shift_JIS
 
+      # GB2312 (Chinese charset) is a subset of GB18030 (its replacement)
+      when /gb2312/i
+        Encoding::GB18030
+
       else
         charset
       end

mail.gemspec

@@ -10,6 +10,7 @@ Gem::Specification.new do |s|
   s.homepage    = "http://github.com/mikel/mail"
   s.description = "A really Ruby Mail handler."
   s.summary     = "Mail provides a nice Ruby DSL for making, sending and reading emails."
+  s.license     = "MIT"
 
   s.platform = Gem::Platform::RUBY
   s.has_rdoc = true

spec/fixtures/emails/mime_emails/sig_only_email.eml

@@ -6,24 +6,24 @@ Message-ID: <20070604150131.40d4fa1e@reforged>
 Mime-Version: 1.0
 Content-Type: multipart/signed; boundary=Sig_2GIY2xfzqSADMmu9sKGJqWm;
  protocol="application/pgp-signature"; micalg=PGP-SHA1
- 
+
 --Sig_2GIY2xfzqSADMmu9sKGJqWm
 Content-Type: text/plain; charset=US-ASCII
 Content-Transfer-Encoding: quoted-printable
- 
+
 This is random text, not what has been signed below, ie, this sig
 email is not signed correctly.
- 
+
 --Sig_2GIY2xfzqSADMmu9sKGJqWm
 Content-Type: application/pgp-signature; name=signature.asc
 Content-Disposition: attachment; filename=signature.asc
- 
+
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1.4.6 (GNU/Linux)
- 
+
 iD8DB1111Iu7dfRchrkBInkRArniAKCue17JOxXBiAZHwLy3uFacU+pmhwCgwzhf
 V5YSPv2xmYOA6mJ6oVaasseQ=
 =T7p9
 -----END PGP SIGNATURE-----
- 
+
 --Sig_2GIY2xfzqSADMmu9sKGJqWm--

spec/mail/attachments_list_spec.rb

@@ -117,6 +117,14 @@ def check_decoded(actual, expected)
       expected.should eq @test_png
     end
 
+    it "should only add one newline between attachment body and boundary" do
+      contents = "I have\ntwo lines with trailing newlines\n\n"
+      @mail.attachments['text.txt'] = { :content => contents}
+      encoded = @mail.encoded
+      regex = /\r\n#{Regexp.escape(contents.gsub(/\n/, "\r\n"))}\r\n--#{@mail.boundary}--\r\n\Z/
+      encoded.should match regex
+    end
+
   end
 
   describe "multiple attachments" do