mail 2.2.15 → 2.3.0

data/lib/mail/multibyte/unicode.rb

@@ -0,0 +1,392 @@
+module Mail
+  module Multibyte
+    module Unicode
+
+      extend self
+
+      # A list of all available normalization forms. See http://www.unicode.org/reports/tr15/tr15-29.html for more
+      # information about normalization.
+      NORMALIZATION_FORMS = [:c, :kc, :d, :kd]
+
+      # The Unicode version that is supported by the implementation
+      UNICODE_VERSION = '5.2.0'
+
+      # The default normalization used for operations that require normalization. It can be set to any of the
+      # normalizations in NORMALIZATION_FORMS.
+      #
+      # Example:
+      #   Mail::Multibyte::Unicode.default_normalization_form = :c
+      attr_accessor :default_normalization_form
+      @default_normalization_form = :kc
+
+      # Hangul character boundaries and properties
+      HANGUL_SBASE = 0xAC00
+      HANGUL_LBASE = 0x1100
+      HANGUL_VBASE = 0x1161
+      HANGUL_TBASE = 0x11A7
+      HANGUL_LCOUNT = 19
+      HANGUL_VCOUNT = 21
+      HANGUL_TCOUNT = 28
+      HANGUL_NCOUNT = HANGUL_VCOUNT * HANGUL_TCOUNT
+      HANGUL_SCOUNT = 11172
+      HANGUL_SLAST = HANGUL_SBASE + HANGUL_SCOUNT
+      HANGUL_JAMO_FIRST = 0x1100
+      HANGUL_JAMO_LAST = 0x11FF
+
+      # All the unicode whitespace
+      WHITESPACE = [
+        (0x0009..0x000D).to_a, # White_Space # Cc   [5] <control-0009>..<control-000D>
+        0x0020,                # White_Space # Zs       SPACE
+        0x0085,                # White_Space # Cc       <control-0085>
+        0x00A0,                # White_Space # Zs       NO-BREAK SPACE
+        0x1680,                # White_Space # Zs       OGHAM SPACE MARK
+        0x180E,                # White_Space # Zs       MONGOLIAN VOWEL SEPARATOR
+        (0x2000..0x200A).to_a, # White_Space # Zs  [11] EN QUAD..HAIR SPACE
+        0x2028,                # White_Space # Zl       LINE SEPARATOR
+        0x2029,                # White_Space # Zp       PARAGRAPH SEPARATOR
+        0x202F,                # White_Space # Zs       NARROW NO-BREAK SPACE
+        0x205F,                # White_Space # Zs       MEDIUM MATHEMATICAL SPACE
+        0x3000,                # White_Space # Zs       IDEOGRAPHIC SPACE
+      ].flatten.freeze
+
+      # BOM (byte order mark) can also be seen as whitespace, it's a non-rendering character used to distinguish
+      # between little and big endian. This is not an issue in utf-8, so it must be ignored.
+      LEADERS_AND_TRAILERS = WHITESPACE + [65279] # ZERO-WIDTH NO-BREAK SPACE aka BOM
+
+      # Returns a regular expression pattern that matches the passed Unicode codepoints
+      def self.codepoints_to_pattern(array_of_codepoints) #:nodoc:
+        array_of_codepoints.collect{ |e| [e].pack 'U*' }.join('|')
+      end
+      TRAILERS_PAT = /(#{codepoints_to_pattern(LEADERS_AND_TRAILERS)})+\Z/u
+      LEADERS_PAT = /\A(#{codepoints_to_pattern(LEADERS_AND_TRAILERS)})+/u
+
+      # Unpack the string at codepoints boundaries. Raises an EncodingError when the encoding of the string isn't
+      # valid UTF-8.
+      #
+      # Example:
+      #   Unicode.u_unpack('Café') # => [67, 97, 102, 233]
+      def u_unpack(string)
+        begin
+          string.unpack 'U*'
+        rescue ArgumentError
+          raise EncodingError, 'malformed UTF-8 character'
+        end
+      end
+
+      # Detect whether the codepoint is in a certain character class. Returns +true+ when it's in the specified
+      # character class and +false+ otherwise. Valid character classes are: <tt>:cr</tt>, <tt>:lf</tt>, <tt>:l</tt>,
+      # <tt>:v</tt>, <tt>:lv</tt>, <tt>:lvt</tt> and <tt>:t</tt>.
+      #
+      # Primarily used by the grapheme cluster support.
+      def in_char_class?(codepoint, classes)
+        classes.detect { |c| database.boundary[c] === codepoint } ? true : false
+      end
+
+      # Unpack the string at grapheme boundaries. Returns a list of character lists.
+      #
+      # Example:
+      #   Unicode.g_unpack('क्षि') # => [[2325, 2381], [2359], [2367]]
+      #   Unicode.g_unpack('Café') # => [[67], [97], [102], [233]]
+      def g_unpack(string)
+        codepoints = u_unpack(string)
+        unpacked = []
+        pos = 0
+        marker = 0
+        eoc = codepoints.length
+        while(pos < eoc)
+          pos += 1
+          previous = codepoints[pos-1]
+          current = codepoints[pos]
+          if (
+              # CR X LF
+              ( previous == database.boundary[:cr] and current == database.boundary[:lf] ) or
+              # L X (L|V|LV|LVT)
+              ( database.boundary[:l] === previous and in_char_class?(current, [:l,:v,:lv,:lvt]) ) or
+              # (LV|V) X (V|T)
+              ( in_char_class?(previous, [:lv,:v]) and in_char_class?(current, [:v,:t]) ) or
+              # (LVT|T) X (T)
+              ( in_char_class?(previous, [:lvt,:t]) and database.boundary[:t] === current ) or
+              # X Extend
+              (database.boundary[:extend] === current)
+            )
+          else
+            unpacked << codepoints[marker..pos-1]
+            marker = pos
+          end
+        end
+        unpacked
+      end
+
+      # Reverse operation of g_unpack.
+      #
+      # Example:
+      #   Unicode.g_pack(Unicode.g_unpack('क्षि')) # => 'क्षि'
+      def g_pack(unpacked)
+        (unpacked.flatten).pack('U*')
+      end
+
+      # Re-order codepoints so the string becomes canonical.
+      def reorder_characters(codepoints)
+        length = codepoints.length- 1
+        pos = 0
+        while pos < length do
+          cp1, cp2 = database.codepoints[codepoints[pos]], database.codepoints[codepoints[pos+1]]
+          if (cp1.combining_class > cp2.combining_class) && (cp2.combining_class > 0)
+            codepoints[pos..pos+1] = cp2.code, cp1.code
+            pos += (pos > 0 ? -1 : 1)
+          else
+            pos += 1
+          end
+        end
+        codepoints
+      end
+
+      # Decompose composed characters to the decomposed form.
+      def decompose_codepoints(type, codepoints)
+        codepoints.inject([]) do |decomposed, cp|
+          # if it's a hangul syllable starter character
+          if HANGUL_SBASE <= cp and cp < HANGUL_SLAST
+            sindex = cp - HANGUL_SBASE
+            ncp = [] # new codepoints
+            ncp << HANGUL_LBASE + sindex / HANGUL_NCOUNT
+            ncp << HANGUL_VBASE + (sindex % HANGUL_NCOUNT) / HANGUL_TCOUNT
+            tindex = sindex % HANGUL_TCOUNT
+            ncp << (HANGUL_TBASE + tindex) unless tindex == 0
+            decomposed.concat ncp
+          # if the codepoint is decomposable in with the current decomposition type
+          elsif (ncp = database.codepoints[cp].decomp_mapping) and (!database.codepoints[cp].decomp_type || type == :compatability)
+            decomposed.concat decompose_codepoints(type, ncp.dup)
+          else
+            decomposed << cp
+          end
+        end
+      end
+
+      # Compose decomposed characters to the composed form.
+      def compose_codepoints(codepoints)
+        pos = 0
+        eoa = codepoints.length - 1
+        starter_pos = 0
+        starter_char = codepoints[0]
+        previous_combining_class = -1
+        while pos < eoa
+          pos += 1
+          lindex = starter_char - HANGUL_LBASE
+          # -- Hangul
+          if 0 <= lindex and lindex < HANGUL_LCOUNT
+            vindex = codepoints[starter_pos+1] - HANGUL_VBASE rescue vindex = -1
+            if 0 <= vindex and vindex < HANGUL_VCOUNT
+              tindex = codepoints[starter_pos+2] - HANGUL_TBASE rescue tindex = -1
+              if 0 <= tindex and tindex < HANGUL_TCOUNT
+                j = starter_pos + 2
+                eoa -= 2
+              else
+                tindex = 0
+                j = starter_pos + 1
+                eoa -= 1
+              end
+              codepoints[starter_pos..j] = (lindex * HANGUL_VCOUNT + vindex) * HANGUL_TCOUNT + tindex + HANGUL_SBASE
+            end
+            starter_pos += 1
+            starter_char = codepoints[starter_pos]
+          # -- Other characters
+          else
+            current_char = codepoints[pos]
+            current = database.codepoints[current_char]
+            if current.combining_class > previous_combining_class
+              if ref = database.composition_map[starter_char]
+                composition = ref[current_char]
+              else
+                composition = nil
+              end
+              unless composition.nil?
+                codepoints[starter_pos] = composition
+                starter_char = composition
+                codepoints.delete_at pos
+                eoa -= 1
+                pos -= 1
+                previous_combining_class = -1
+              else
+                previous_combining_class = current.combining_class
+              end
+            else
+              previous_combining_class = current.combining_class
+            end
+            if current.combining_class == 0
+              starter_pos = pos
+              starter_char = codepoints[pos]
+            end
+          end
+        end
+        codepoints
+      end
+
+      # Replaces all ISO-8859-1 or CP1252 characters by their UTF-8 equivalent resulting in a valid UTF-8 string.
+      #
+      # Passing +true+ will forcibly tidy all bytes, assuming that the string's encoding is entirely CP1252 or ISO-8859-1.
+      def tidy_bytes(string, force = false)
+        if force
+          return string.unpack("C*").map do |b|
+            tidy_byte(b)
+          end.flatten.compact.pack("C*").unpack("U*").pack("U*")
+        end
+
+        bytes = string.unpack("C*")
+        conts_expected = 0
+        last_lead = 0
+
+        bytes.each_index do |i|
+
+          byte          = bytes[i]
+          is_cont       = byte > 127 && byte < 192
+          is_lead       = byte > 191 && byte < 245
+          is_unused     = byte > 240
+          is_restricted = byte > 244
+
+          # Impossible or highly unlikely byte? Clean it.
+          if is_unused || is_restricted
+            bytes[i] = tidy_byte(byte)
+          elsif is_cont
+            # Not expecting contination byte? Clean up. Otherwise, now expect one less.
+            conts_expected == 0 ? bytes[i] = tidy_byte(byte) : conts_expected -= 1
+          else
+            if conts_expected > 0
+              # Expected continuation, but got ASCII or leading? Clean backwards up to
+              # the leading byte.
+              (1..(i - last_lead)).each {|j| bytes[i - j] = tidy_byte(bytes[i - j])}
+              conts_expected = 0
+            end
+            if is_lead
+              # Final byte is leading? Clean it.
+              if i == bytes.length - 1
+                bytes[i] = tidy_byte(bytes.last)
+              else
+                # Valid leading byte? Expect continuations determined by position of
+                # first zero bit, with max of 3.
+                conts_expected = byte < 224 ? 1 : byte < 240 ? 2 : 3
+                last_lead = i
+              end
+            end
+          end
+        end
+        bytes.empty? ? "" : bytes.flatten.compact.pack("C*").unpack("U*").pack("U*")
+      end
+
+      # Returns the KC normalization of the string by default. NFKC is considered the best normalization form for
+      # passing strings to databases and validations.
+      #
+      # * <tt>string</tt> - The string to perform normalization on.
+      # * <tt>form</tt> - The form you want to normalize in. Should be one of the following:
+      #   <tt>:c</tt>, <tt>:kc</tt>, <tt>:d</tt>, or <tt>:kd</tt>. Default is
+      #   Mail::Multibyte.default_normalization_form
+      def normalize(string, form=nil)
+        form ||= @default_normalization_form
+        # See http://www.unicode.org/reports/tr15, Table 1
+        codepoints = u_unpack(string)
+        case form
+          when :d
+            reorder_characters(decompose_codepoints(:canonical, codepoints))
+          when :c
+            compose_codepoints(reorder_characters(decompose_codepoints(:canonical, codepoints)))
+          when :kd
+            reorder_characters(decompose_codepoints(:compatability, codepoints))
+          when :kc
+            compose_codepoints(reorder_characters(decompose_codepoints(:compatability, codepoints)))
+          else
+            raise ArgumentError, "#{form} is not a valid normalization variant", caller
+        end.pack('U*')
+      end
+
+      def apply_mapping(string, mapping) #:nodoc:
+        u_unpack(string).map do |codepoint|
+          cp = database.codepoints[codepoint]
+          if cp and (ncp = cp.send(mapping)) and ncp > 0
+            ncp
+          else
+            codepoint
+          end
+        end.pack('U*')
+      end
+
+      # Holds data about a codepoint in the Unicode database
+      class Codepoint
+        attr_accessor :code, :combining_class, :decomp_type, :decomp_mapping, :uppercase_mapping, :lowercase_mapping
+      end
+
+      # Holds static data from the Unicode database
+      class UnicodeDatabase
+        ATTRIBUTES = :codepoints, :composition_exclusion, :composition_map, :boundary, :cp1252
+
+        attr_writer(*ATTRIBUTES)
+
+        def initialize
+          @codepoints = Hash.new(Codepoint.new)
+          @composition_exclusion = []
+          @composition_map = {}
+          @boundary = {}
+          @cp1252 = {}
+        end
+
+        # Lazy load the Unicode database so it's only loaded when it's actually used
+        ATTRIBUTES.each do |attr_name|
+          class_eval(<<-EOS, __FILE__, __LINE__ + 1)
+            def #{attr_name}     # def codepoints
+              load               #   load
+              @#{attr_name}      #   @codepoints
+            end                  # end
+          EOS
+        end
+
+        # Loads the Unicode database and returns all the internal objects of UnicodeDatabase.
+        def load
+          begin
+            @codepoints, @composition_exclusion, @composition_map, @boundary, @cp1252 = File.open(self.class.filename, 'rb') { |f| Marshal.load f.read }
+          rescue Exception => e
+              raise IOError.new("Couldn't load the Unicode tables for UTF8Handler (#{e.message}), Mail::Multibyte is unusable")
+          end
+
+          # Redefine the === method so we can write shorter rules for grapheme cluster breaks
+          @boundary.each do |k,_|
+            @boundary[k].instance_eval do
+              def ===(other)
+                detect { |i| i === other } ? true : false
+              end
+            end if @boundary[k].kind_of?(Array)
+          end
+
+          # define attr_reader methods for the instance variables
+          class << self
+            attr_reader(*ATTRIBUTES)
+          end
+        end
+
+        # Returns the directory in which the data files are stored
+        def self.dirname
+          File.dirname(__FILE__) + '/../values/'
+        end
+
+        # Returns the filename for the data file for this version
+        def self.filename
+          File.expand_path File.join(dirname, "unicode_tables.dat")
+        end
+      end
+
+      private
+
+      def tidy_byte(byte)
+        if byte < 160
+          [database.cp1252[byte] || byte].pack("U").unpack("C*")
+        elsif byte < 192
+          [194, byte]
+        else
+          [195, byte - 64]
+        end
+      end
+
+      def database
+        @database ||= UnicodeDatabase.new
+      end
+
+    end
+  end
+end

data/lib/mail/multibyte/utils.rb

@@ -0,0 +1,60 @@
+# encoding: utf-8
+
+module Mail #:nodoc:
+  module Multibyte #:nodoc:
+    if Kernel.const_defined?(:Encoding)
+      # Returns a regular expression that matches valid characters in the current encoding
+      def self.valid_character
+        VALID_CHARACTER[Encoding.default_external.to_s]
+      end
+    else
+      def self.valid_character
+        case $KCODE
+        when 'UTF8'
+          VALID_CHARACTER['UTF-8']
+        when 'SJIS'
+          VALID_CHARACTER['Shift_JIS']
+        end
+      end
+    end
+
+    if 'string'.respond_to?(:valid_encoding?)
+      # Verifies the encoding of a string
+      def self.verify(string)
+        string.valid_encoding?
+      end
+    else
+      def self.verify(string)
+        if expression = valid_character
+          # Splits the string on character boundaries, which are determined based on $KCODE.
+          string.split(//).all? { |c| expression =~ c }
+        else
+          true
+        end
+      end
+    end
+
+    # Verifies the encoding of the string and raises an exception when it's not valid
+    def self.verify!(string)
+      raise EncodingError.new("Found characters with invalid encoding") unless verify(string)
+    end
+
+    if 'string'.respond_to?(:force_encoding)
+      # Removes all invalid characters from the string.
+      #
+      # Note: this method is a no-op in Ruby 1.9
+      def self.clean(string)
+        string
+      end
+    else
+      def self.clean(string)
+        if expression = valid_character
+          # Splits the string on character boundaries, which are determined based on $KCODE.
+          string.split(//).grep(expression).join
+        else
+          string
+        end
+      end
+    end
+  end
+end

data/lib/mail/multibyte.rb

@@ -0,0 +1,42 @@
+# encoding: utf-8
+module Mail #:nodoc:
+  module Multibyte
+    require 'mail/multibyte/exceptions'
+    require 'mail/multibyte/chars'
+    require 'mail/multibyte/unicode'
+
+    # The proxy class returned when calling mb_chars. You can use this accessor to configure your own proxy
+    # class so you can support other encodings. See the Mail::Multibyte::Chars implementation for
+    # an example how to do this.
+    #
+    # Example:
+    #   Mail::Multibyte.proxy_class = CharsForUTF32
+    def self.proxy_class=(klass)
+      @proxy_class = klass
+    end
+
+    # Returns the current proxy class
+    def self.proxy_class
+      @proxy_class ||= Mail::Multibyte::Chars
+    end
+
+    # Regular expressions that describe valid byte sequences for a character
+    VALID_CHARACTER = {
+      # Borrowed from the Kconv library by Shinji KONO - (also as seen on the W3C site)
+      'UTF-8' => /\A(?:
+                  [\x00-\x7f]                                         |
+                  [\xc2-\xdf] [\x80-\xbf]                             |
+                  \xe0        [\xa0-\xbf] [\x80-\xbf]                 |
+                  [\xe1-\xef] [\x80-\xbf] [\x80-\xbf]                 |
+                  \xf0        [\x90-\xbf] [\x80-\xbf] [\x80-\xbf]     |
+                  [\xf1-\xf3] [\x80-\xbf] [\x80-\xbf] [\x80-\xbf]     |
+                  \xf4        [\x80-\x8f] [\x80-\xbf] [\x80-\xbf])\z /xn,
+      # Quick check for valid Shift-JIS characters, disregards the odd-even pairing
+      'Shift_JIS' => /\A(?:
+                  [\x00-\x7e\xa1-\xdf]                                     |
+                  [\x81-\x9f\xe0-\xef] [\x40-\x7e\x80-\x9e\x9f-\xfc])\z /xn
+    }
+  end
+end
+
+require 'mail/multibyte/utils'

data/lib/mail/network/delivery_methods/smtp.rb

@@ -124,11 +124,12 @@ module Mail
         end
       end
       
+      response = nil
       smtp.start(settings[:domain], settings[:user_name], settings[:password], settings[:authentication]) do |smtp|
-        smtp.sendmail(message, envelope_from, destinations)
+        response = smtp.sendmail(message, envelope_from, destinations)
       end
-      
-      self
+
+      return settings[:return_response] ? response : self
     end
     
     

data/lib/mail/network/delivery_methods/smtp_connection.rb

@@ -0,0 +1,74 @@
+module Mail
+  # == Sending Email with SMTP
+  # 
+  # Mail allows you to send emails using an open SMTP connection.  This is done by
+  # passing a created Net::SMTP object.  This way we can get better performance to
+  # our local mail server by reducing the number of connections at any one time.
+  #
+  # === Sending via SMTP server on Localhost
+  # 
+  # To send mail open a connection with Net::Smtp using any options you like
+  # === Delivering the email
+  # 
+  # Once you have the settings right, sending the email is done by:
+  #
+  #   smtp_conn = Net::SMTP.start(settings[:address], settings[:port])
+  #   Mail.defaults do
+  #     delivery_method :smtp_connection, { :connection => smtp_conn }
+  #   end
+  # 
+  #   Mail.deliver do
+  #     to 'mikel@test.lindsaar.net'
+  #     from 'ada@test.lindsaar.net'
+  #     subject 'testing sendmail'
+  #     body 'testing sendmail'
+  #   end
+  # 
+  # Or by calling deliver on a Mail message
+  # 
+  #   mail = Mail.new do
+  #     to 'mikel@test.lindsaar.net'
+  #     from 'ada@test.lindsaar.net'
+  #     subject 'testing sendmail'
+  #     body 'testing sendmail'
+  #   end
+  # 
+  #   mail.deliver!
+  class SMTPConnection
+
+    def initialize(values)
+      raise ArgumentError.new('A Net::SMTP object is required for this delivery method') if values[:connection].nil?
+      self.smtp = values[:connection]
+      self.settings = values
+    end
+    
+    attr_accessor :smtp
+    attr_accessor :settings
+    
+    # Send the message via SMTP.
+    # The from and to attributes are optional. If not set, they are retrieve from the Message.
+    def deliver!(mail)
+
+      # Set the envelope from to be either the return-path, the sender or the first from address
+      envelope_from = mail.return_path || mail.sender || mail.from_addrs.first
+      if envelope_from.blank?
+        raise ArgumentError.new('A sender (Return-Path, Sender or From) required to send a message') 
+      end
+      
+      destinations ||= mail.destinations if mail.respond_to?(:destinations) && mail.destinations
+      if destinations.blank?
+        raise ArgumentError.new('At least one recipient (To, Cc or Bcc) is required to send a message') 
+      end
+      
+      message ||= mail.encoded if mail.respond_to?(:encoded)
+      if message.blank?
+        raise ArgumentError.new('A encoded content is required to send a message')
+      end
+            
+      response = smtp.sendmail(message, envelope_from, destinations)
+      
+      settings[:return_response] ? response : self 
+    end
+        
+  end
+end

data/lib/mail/network/retriever_methods/test_retriever.rb

@@ -3,7 +3,14 @@
 module Mail
 
   class TestRetriever < Retriever
-    cattr_accessor :emails
+
+    def self.emails
+      @@emails
+    end
+
+    def self.emails=(val)
+      @@emails = val
+    end
 
     def initialize(values)
       @@emails = []

data/lib/mail/network.rb

@@ -4,6 +4,7 @@ module Mail
   autoload :SMTP, 'mail/network/delivery_methods/smtp'
   autoload :FileDelivery, 'mail/network/delivery_methods/file_delivery'
   autoload :Sendmail, 'mail/network/delivery_methods/sendmail'
+  autoload :SMTPConnection, 'mail/network/delivery_methods/smtp_connection'
   autoload :TestMailer, 'mail/network/delivery_methods/test_mailer'
 
   autoload :POP3, 'mail/network/retriever_methods/pop3'

data/lib/mail/part.rb

@@ -103,7 +103,7 @@ module Mail
         self.body   = body_part
       else
         self.header = "Content-Type: text/plain\r\n"
-        self.body   = header_part
+        self.body   = raw_source
       end
     end
     

data/lib/mail/parts_list.rb

@@ -1,6 +1,6 @@
 module Mail
   class PartsList < Array
-    
+
     def attachments
       Mail::AttachmentsList.new(self)
     end
@@ -14,30 +14,38 @@ module Mail
         to_a
       end
     end
-    
+
     undef :map
     alias_method :map, :collect
 
     def map!
       raise NoMethodError, "#map! is not defined, please call #collect and create a new PartsList"
     end
-    
+
     def collect!
       raise NoMethodError, "#collect! is not defined, please call #collect and create a new PartsList"
     end
-    
+
     def sort!(order)
       sorted = self.sort do |a, b|
         # OK, 10000 is arbitrary... if anyone actually wants to explicitly sort 10000 parts of a
         # single email message... please show me a use case and I'll put more work into this method,
         # in the meantime, it works :)
-        a_order = order.index(a[:content_type].string.downcase) || 10000
-        b_order = order.index(b[:content_type].string.downcase) || 10000
-        a_order <=> b_order
+        get_order_value(a, order) <=> get_order_value(b, order)
       end
       self.clear
       sorted.each { |p| self << p }
     end
-    
+
+  private
+
+    def get_order_value(part, order)
+      if part.respond_to?(:content_type)
+        order.index(part[:content_type].string.downcase) || 10000
+      else
+        10000
+      end
+    end
+
   end
-end
+end