lib/sup/message.rb in sup-0.5 vs lib/sup/message.rb in sup-0.6

@@ -35,11 +35,11 @@
   MAX_SIG_DISTANCE = 15 # lines from the end
   DEFAULT_SUBJECT = ""
   DEFAULT_SENDER = "(missing sender)"
 
   attr_reader :id, :date, :from, :subj, :refs, :replytos, :to, :source,
-              :cc, :bcc, :labels, :list_address, :recipient_email, :replyto,
+              :cc, :bcc, :labels, :attachments, :list_address, :recipient_email, :replyto,
               :source_info, :list_subscribe, :list_unsubscribe
 
   bool_reader :dirty, :source_marked_read, :snippet_contains_encrypted_content
 
   ## if you specify a :header, will use values from that. otherwise,
@@ -52,10 +52,11 @@
     @have_snippet = !(opts[:snippet].nil? || opts[:snippet].empty?)
     @labels = [] + (opts[:labels] || [])
     @dirty = false
     @encrypted = false
     @chunks = nil
+    @attachments = []
 
     ## we need to initialize this. see comments in parse_header as to
     ## why.
     @refs = []
 
@@ -146,11 +147,22 @@
   def draft_filename
     raise "not a draft" unless is_draft?
     @source.fn_for_offset @source_info
   end
 
-  def sanitize_message_id mid; mid.gsub(/\s+/, "")[0..254] end
+  ## sanitize message ids by removing spaces and non-ascii characters.
+  ## also, truncate to 255 characters. all these steps are necessary
+  ## to make ferret happy. of course, we probably fuck up a couple
+  ## valid message ids as well. as long as we're consistent, this
+  ## should be fine, though.
+  ##
+  ## also, mostly the message ids that are changed by this belong to
+  ## spam email.
+  ##
+  ## an alternative would be to SHA1 or MD5 all message ids on a regular basis.
+  ## don't tempt me.
+  def sanitize_message_id mid; mid.gsub(/(\s|[^\000-\177])+/, "")[0..254] end
 
   def save index
     return unless @dirty
     index.sync_message self
     @dirty = false
@@ -403,10 +415,15 @@
           ["sup-attachment-#{Time.now.to_i}-#{rand 10000}", extension].join(".")
         end
 
       ## if there's a filename, we'll treat it as an attachment.
       if filename
+        # add this to the attachments list if its not a generated html
+        # attachment (should we allow images with generated names?).
+        # Lowercase the filename because searches are easier that way 
+        @attachments.push filename.downcase unless filename =~ /^sup-attachment-/
+        add_label :attachment unless filename =~ /^sup-attachment-/
         [Chunk::Attachment.new(m.header.content_type, filename, m, sibling_types)]
 
       ## otherwise, it's body text
       else
         body = Message.convert_from m.decode, m.charset if m.body
@@ -421,10 +438,10 @@
       raise MessageFormatError, "RubyMail decode returned a null body" unless body
       return body unless charset
       Iconv.iconv($encoding + "//IGNORE", charset, body + " ").join[0 .. -2]
     rescue Errno::EINVAL, Iconv::InvalidEncoding, Iconv::IllegalSequence, MessageFormatError => e
       Redwood::log "warning: error (#{e.class.name}) decoding message body from #{charset}: #{e.message}"
-      File.open("sup-unable-to-decode.txt", "w") { |f| f.write body }
+      File.open(File.join(BASE_DIR,"unable-to-decode.txt"), "w") { |f| f.write body }
       body
     end
   end
 
   ## parse the lines of text into chunk objects.  the heuristics here