imap.rb in sup-0.1

- old
+ new

@@ -4,11 +4,11 @@
 require 'time'
 require 'rmail'
 
 ## fucking imap fucking sucks. what the FUCK kind of committee of
 ## dunces designed this shit.
-
+##
 ## imap talks about 'unique ids' for messages, to be used for
 ## cross-session identification. great---just what sup needs! except
 ## it turns out the uids can be invalidated every time the
 ## 'uidvalidity' value changes on the server, and 'uidvalidity' can
 ## change without restriction. it can change any time you log in. it
@@ -17,30 +17,44 @@
 ## people from just setting it to the current timestamp, and in fact
 ## that's exactly what the one imap server i have at my disposal
 ## does. thus the so-called uids are absolutely useless and imap
 ## provides no cross-session way of uniquely identifying a
 ## message. but thanks for the "strong recommendation", guys!
-
+##
 ## so right now i'm using the 'internal date' and the size of each
 ## message to uniquely identify it, and i scan over the entire mailbox
 ## each time i open it to map those things to message ids. that can be
 ## slow for large mailboxes, and we'll just have to hope that there
 ## are no collisions. ho ho! a perfectly reasonable solution!
-
+##
+## and here's another thing. check out RFC2060 2.2.2 paragraph 5:
+##
+##   A client MUST be prepared to accept any server response at all times.
+##   This includes server data that was not requested.
+##
+## yeah. that totally makes a lot of sense. and once again, the idiocy
+## of the spec actually happens in practice. you'll request flags for
+## one message, and get it interspersed with a random bunch of flags
+## for some other messages, including a different set of flags for the
+## same message! totally ok by the imap spec. totally retarded by any
+## other metric.
+##
 ## fuck you, imap committee. you managed to design something nearly as
 ## shitty as mbox but goddamn THIRTY YEARS LATER.
 module Redwood
 
 class IMAP < Source
   SCAN_INTERVAL = 60 # seconds
 
   ## upon these errors we'll try to rereconnect a few times
-  RECOVERABLE_ERRORS = [ Errno::EPIPE, Errno::ETIMEDOUT ]
+  RECOVERABLE_ERRORS = [ Errno::EPIPE, Errno::ETIMEDOUT, OpenSSL::SSL::SSLError ]
 
   attr_accessor :username, :password
+  yaml_properties :uri, :username, :password, :cur_offset, :usual,
+                  :archived, :id, :labels
 
-  def initialize uri, username, password, last_idate=nil, usual=true, archived=false, id=nil
+  def initialize uri, username, password, last_idate=nil, usual=true, archived=false, id=nil, labels=[]
     raise ArgumentError, "username and password must be specified" unless username && password
     raise ArgumentError, "not an imap uri" unless uri =~ %r!imaps?://!
 
     super uri, last_idate, usual, archived, id
 
@@ -49,15 +63,23 @@
     @password = password
     @imap = nil
     @imap_ids = {}
     @ids = []
     @last_scan = nil
-    @labels = [:unread]
-    @labels << mailbox.intern unless mailbox =~ /inbox/i
+    @labels = (labels || []).freeze
+    @say_id = nil
     @mutex = Mutex.new
   end
 
+  def self.suggest_labels_for path
+    if path =~ /inbox/i
+      [path.intern]
+    else
+      []
+    end
+  end
+
   def host; @parsed_uri.host; end
   def port; @parsed_uri.port || (ssl? ? 993 : 143); end
   def mailbox
     x = @parsed_uri.path[1..-1]
     x.nil? || x.empty? ? 'INBOX' : x
@@ -86,10 +108,11 @@
   end
 
   def raw_header id
     unsynchronized_scan_mailbox
     header, flags = get_imap_fields id, 'RFC822.HEADER', 'FLAGS'
+    ## very bad. this is very very bad. very bad bad bad.
     header = header + "Status: RO\n" if flags.include? :Seen # fake an mbox-style read header # TODO: improve source-marked-as-read reporting system
     header.gsub(/\r\n/, "\n")
   end
   synchronized :raw_header
 
@@ -113,13 +136,13 @@
     end
     @last_scan = Time.now
 
     return if last_id == @ids.length
 
-    Redwood::log "fetching IMAP headers #{(@ids.length + 1) .. last_id}"
-    values = safely { @imap.fetch((@ids.length + 1) .. last_id, ['RFC822.SIZE', 'INTERNALDATE']) }
-    values.each do |v|
+    range = (@ids.length + 1) .. last_id
+    Redwood::log "fetching IMAP headers #{range}"
+    fetch(range, ['RFC822.SIZE', 'INTERNALDATE']).each do |v|
       id = make_id v
       @ids << id
       @imap_ids[id] = v.seqno
     end
   end
@@ -135,11 +158,11 @@
     start = ids.index(cur_offset || start_offset) or raise OutOfSyncSourceError, "Unknown message id #{cur_offset || start_offset}."
 
     start.upto(ids.length - 1) do |i|         
       id = ids[i]
       self.cur_offset = id
-      yield id, @labels.clone
+      yield id, @labels
     end
   end
 
   def start_offset
     unsynchronized_scan_mailbox
@@ -155,10 +178,28 @@
 
   def pct_done; 100.0 * (@ids.index(cur_offset) || 0).to_f / (@ids.length - 1).to_f; end
 
 private
 
+  def fetch ids, fields
+    results = safely { @imap.fetch ids, fields }
+    good_results = 
+      if ids.respond_to? :member?
+        results.find_all { |r| ids.member?(r.seqno) && fields.all? { |f| r.attr.member?(f) } }
+      else
+        results.find_all { |r| ids == r.seqno && fields.all? { |f| r.attr.member?(f) } }
+      end
+
+    if good_results.empty?
+      raise FatalSourceError, "no IMAP response for #{ids} containing all fields #{fields.join(', ')} (got #{results.size} results)"
+    elsif good_results.size < results.size
+      Redwood::log "Your IMAP server sucks. It sent #{results.size} results for a request for #{good_results.size} messages. What are you using, Binc?"
+    end
+
+    good_results
+  end
+
   def unsafe_connect
     say "Connecting to IMAP server #{host}:#{port}..."
 
     ## apparently imap.rb does a lot of threaded stuff internally and
     ## if an exception occurs, it will catch it and re-raise it on the
@@ -207,23 +248,27 @@
     @say_id = nil
   end
 
   def make_id imap_stuff
     # use 7 digits for the size. why 7? seems nice.
+    %w(RFC822.SIZE INTERNALDATE).each do |w|
+      raise FatalSourceError, "requested data not in IMAP response: #{w}" unless imap_stuff.attr[w]
+    end
+    
     msize, mdate = imap_stuff.attr['RFC822.SIZE'] % 10000000, Time.parse(imap_stuff.attr["INTERNALDATE"])
     sprintf("%d%07d", mdate.to_i, msize).to_i
   end
 
   def get_imap_fields id, *fields
     imap_id = @imap_ids[id] or raise OutOfSyncSourceError, "Unknown message id #{id}"
 
     retried = false
-    results = safely { @imap.fetch imap_id, (fields + ['RFC822.SIZE', 'INTERNALDATE']).uniq }.first
-    got_id = make_id results
+    result = fetch(imap_id, (fields + ['RFC822.SIZE', 'INTERNALDATE']).uniq).first
+    got_id = make_id result
     raise OutOfSyncSourceError, "IMAP message mismatch: requested #{id}, got #{got_id}." unless got_id == id
 
-    fields.map { |f| results.attr[f] }
+    fields.map { |f| result.attr[f] or raise FatalSourceError, "empty response from IMAP server: #{f}" }
   end
 
   ## execute a block, connected if unconnected, re-connected up to 3
   ## times if a recoverable error occurs, and properly dying if an
   ## unrecoverable error occurs.
@@ -231,22 +276,22 @@
     retries = 0
     begin
       begin
         unsafe_connect unless @imap
         yield
-      rescue *RECOVERABLE_ERRORS
+      rescue *RECOVERABLE_ERRORS => e
         if (retries += 1) <= 3
           @imap = nil
+          Redwood::log "got #{e.class.name}: #{e.message.inspect}"
+          sleep 2
           retry
         end
         raise
       end
-    rescue SocketError, Net::IMAP::Error, SystemCallError, IOError => e
-      raise FatalSourceError, "While communicating with IMAP server: #{e.message}"
+    rescue SocketError, Net::IMAP::Error, SystemCallError, IOError, OpenSSL::SSL::SSLError => e
+      raise FatalSourceError, "While communicating with IMAP server (type #{e.class.name}): #{e.message.inspect}"
     end
   end
 
 end
-
-Redwood::register_yaml(IMAP, %w(uri username password cur_offset usual archived id))
 
 end