Implement a named properties map, capturing names of outlook's model, needed for vcard converter.

git-svn-id: https://ruby-msg.googlecode.com/svn/trunk@28 c30d66de-b626-0410-988f-81f6512a6d81

Author: aquasync

TODO

@@ -4,6 +4,12 @@ Draws on msgconvert.pl, and tries to be a cleaner and more complete approach.
 
 Highest priority
 ------------------------
+* certain parsing still not correct, especially small properties directory, 
+  things like bools, multiavlue shorts etc.
+* still a lot of cleaning up to do. removal of dead debug code, moving stuff
+  into the right classes.
+* unit tests, to lock down the functionality i have so far
+
 * get some sort of working From: header
   there doesn't appear to be a way to get an smtp address for the sender in an
   internal mail. you need to query the exchanger server, using the sender_entryid

data/named_map.yaml

@@ -0,0 +1,114 @@
+# this file provides for the mapping of the keys of named properties
+# to symbolic names (as opposed to mapitags.yaml, which is currently
+# in a different format, has a different source, and is only fixed
+# code properties)
+#
+# essentially the symbols are slightly munged versions of the names
+# given to these properties by CDO, or Outlook's object model.
+# it was parsed out of cdo10.htm, and neatened up a bit.
+#
+# interestingly, despite having separate guids, the codes are picked not to
+# clash. further the names themselves have only 3 clashes in all the below.
+{
+[0x8005, PSETID_Address]: file_under,
+[0x8017, PSETID_Address]: last_name_and_first_name,
+[0x8018, PSETID_Address]: company_and_full_name,
+[0x8019, PSETID_Address]: full_name_and_company,
+[0x801a, PSETID_Address]: home_address,
+[0x801b, PSETID_Address]: business_address,
+[0x801c, PSETID_Address]: other_address,
+[0x8022, PSETID_Address]: selected_address,
+[0x802b, PSETID_Address]: web_page,
+[0x802c, PSETID_Address]: yomi_first_name,
+[0x802d, PSETID_Address]: yomi_last_name,
+[0x802e, PSETID_Address]: yomi_company_name,
+[0x8030, PSETID_Address]: last_first_no_space,
+[0x8031, PSETID_Address]: last_first_space_only,
+[0x8032, PSETID_Address]: company_last_first_no_space,
+[0x8033, PSETID_Address]: company_last_first_space_only,
+[0x8034, PSETID_Address]: last_first_no_space_company,
+[0x8035, PSETID_Address]: last_first_space_only_company,
+[0x8036, PSETID_Address]: last_first_and_suffix,
+[0x8045, PSETID_Address]: business_address_street,
+[0x8046, PSETID_Address]: business_address_city,
+[0x8047, PSETID_Address]: business_address_state,
+[0x8048, PSETID_Address]: business_address_postal_code,
+[0x8049, PSETID_Address]: business_address_country,
+[0x804a, PSETID_Address]: business_address_post_office_box,
+[0x804f, PSETID_Address]: user_field1,
+[0x8050, PSETID_Address]: user_field2,
+[0x8051, PSETID_Address]: user_field3,
+[0x8052, PSETID_Address]: user_field4,
+[0x8062, PSETID_Address]: imaddress,
+[0x8082, PSETID_Address]: email_addr_type,
+[0x8083, PSETID_Address]: email_email_address,
+[0x8084, PSETID_Address]: email_original_display_name,
+[0x8085, PSETID_Address]: email_original_entry_id,
+[0x8092, PSETID_Address]: email2_addr_type,
+[0x8093, PSETID_Address]: email2_email_address,
+[0x8094, PSETID_Address]: email2_original_display_name,
+[0x8095, PSETID_Address]: email2_original_entry_id,
+[0x80a2, PSETID_Address]: email3_addr_type,
+[0x80a3, PSETID_Address]: email3_email_address,
+[0x80a4, PSETID_Address]: email3_original_display_name,
+[0x80a5, PSETID_Address]: email3_original_entry_id,
+[0x80d8, PSETID_Address]: internet_free_busy_address,
+[0x8101, PSETID_Task]: status,
+[0x8102, PSETID_Task]: percent_complete,
+[0x8103, PSETID_Task]: team_task,
+[0x8104, PSETID_Task]: start_date,
+[0x8105, PSETID_Task]: due_date,
+[0x8106, PSETID_Task]: duration,
+[0x810f, PSETID_Task]: date_completed,
+[0x8110, PSETID_Task]: actual_work,
+[0x8111, PSETID_Task]: total_work,
+[0x811c, PSETID_Task]: complete,
+[0x811f, PSETID_Task]: owner,
+[0x8126, PSETID_Task]: is_recurring,
+[0x8205, PSETID_Appointment]: busy_status,
+[0x8208, PSETID_Appointment]: location,
+[0x820d, PSETID_Appointment]: start_date,
+[0x820e, PSETID_Appointment]: end_date,
+[0x8213, PSETID_Appointment]: duration,
+[0x8214, PSETID_Appointment]: colors,
+[0x8216, PSETID_Appointment]: recurrence_state,
+[0x8218, PSETID_Appointment]: response_status,
+[0x8222, PSETID_Appointment]: reply_time,
+[0x8223, PSETID_Appointment]: is_recurring,
+[0x822e, PSETID_Appointment]: organizer,
+[0x8231, PSETID_Appointment]: recurrence_type,
+[0x8232, PSETID_Appointment]: recurrence_pattern,
+# also had CdoPR_FLAG_DUE_BY, when applied to messages. i don't currently
+# use message class specific names
+[0x8502, PSETID_Common]: reminder_time,
+[0x8503, PSETID_Common]: reminder_set,
+[0x8516, PSETID_Common]: common_start,
+[0x8517, PSETID_Common]: common_end,
+[0x851c, PSETID_Common]: reminder_override,
+[0x851e, PSETID_Common]: reminder_sound,
+[0x851f, PSETID_Common]: reminder_file,
+# this one only listed as CdoPR_FLAG_TEXT. maybe should be
+# reminder_text
+[0x8530, PSETID_Common]: flag_text,
+[0x8534, PSETID_Common]: mileage,
+[0x8535, PSETID_Common]: billing_information,
+[0x8539, PSETID_Common]: companies,
+[0x853a, PSETID_Common]: contact_names,
+# had CdoPR_FLAG_DUE_BY_NEXT for this one also
+[0x8560, PSETID_Common]: reminder_next_time,
+[0x8700, PSETID_Log]: entry,
+[0x8704, PSETID_Log]: start_date,
+[0x8705, PSETID_Log]: start_time,
+[0x8706, PSETID_Log]: start,
+[0x8707, PSETID_Log]: duration,
+[0x8708, PSETID_Log]: end,
+[0x870e, PSETID_Log]: doc_printed,
+[0x870f, PSETID_Log]: doc_saved,
+[0x8710, PSETID_Log]: doc_routed,
+[0x8711, PSETID_Log]: doc_posted,
+[0x8712, PSETID_Log]: entry_type,
+[0x8b00, PSETID_Note]: color,
+[0x8b02, PSETID_Note]: width,
+[0x8b03, PSETID_Note]: height,
+["Keywords", PS_PUBLIC_STRINGS]: categories
+}

lib/msg.rb

@@ -207,7 +207,18 @@ def inspect
 
 	# --------
 	# beginnings of conversion stuff
-	
+
+	def convert
+		# 
+		# for now, multiplex between returning a Mime object,
+		# a Vpim::Vcard object,
+		# a Vpim::Vcalendar object
+		#
+		# all of which should support a common serialization,
+		# to save the result to a file.
+		#
+	end
+
 	def body_to_mime
 		# to create the body
 		# should have some options about serializing rtf. and possibly options to check the rtf
@@ -242,6 +253,9 @@ def body_to_mime
 	end
 
 	def to_mime
+		# intended to be used for IPM.note, which is the email type. can use it for others if desired,
+		# YMMV
+		Log.warn "to_mime used on a #{props.message_class}" unless props.message_class == 'IPM.Note'
 		# we always have a body
 		mime = body = body_to_mime
 
@@ -272,6 +286,9 @@ def to_mime
 		mime
 	end
 
+	def to_vcard
+	end
+
 	# after looking at other MAPI property stores, such as tnef / pst, i might want to separate
 	# the parsing from other stuff here, but for now its ok.
 	class Properties
@@ -283,23 +300,28 @@ class Properties
 			0x0102 => IDENTITY_PROC, # binary?
 		}
 
-		MAPITAGS = open('data/mapitags.yaml') { |file| YAML.load file }
-
 		# these won't be strings for much longer.
+		# maybe later, the Key#inspect could automatically show symbolic guid names if they
+		# are part of this builtin list.
 		# FIXME
 		PS_MAPI =             '{not-really-sure-what-this-should-say}'
 		PS_PUBLIC_STRINGS =   '{00020329-0000-0000-c000-000000000046}'
 		# string properties in this namespace automatically get added to the internet headers
 		PS_INTERNET_HEADERS = '{00020386-0000-0000-c000-000000000046}'
-		# const GUID PS_PUBLIC_STRINGS    = {0x00020329, 0x0000, 0x0000, {0xC0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x46}};
-		# const GUID PS_INTERNET_HEADERS  = {0x00020386, 0x0000, 0x0000, {0xC0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x46}};
-		# theres are bunch of outlook onoes i think
-		# const GUID PSETID_Appointment   = {0x00062002, 0x0000, 0x0000, {0xC0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x46}};
-		# const GUID PSETID_Task          = {0x00062003, 0x0000, 0x0000, {0xC0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x46}};
-		# const GUID PSETID_Address       = {0x00062004, 0x0000, 0x0000, {0xC0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x46}};
-		# const GUID PSETID_Common        = {0x00062008, 0x0000, 0x0000, {0xC0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x46}};
-		# const GUID PSETID_Log           = {0x0006200A, 0x0000, 0x0000, {0xC0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x46}};
+		# theres are bunch of outlook ones i think
 		# http://blogs.msdn.com/stephen_griffin/archive/2006/05/10/outlook-2007-beta-documentation-notification-based-indexing-support.aspx
+		# IPM.Appointment
+		PSETID_Appointment =  '{00062002-0000-0000-c000-000000000046}'
+		# IPM.Task
+		PSETID_Task =         '{00062003-0000-0000-c000-000000000046}'
+		# used for IPM.Contact
+		PSETID_Address =      '{00062004-0000-0000-c000-000000000046}'
+		PSETID_Common =       '{00062008-0000-0000-c000-000000000046}'
+		# didn't find a source for this name. it is for IPM.StickyNote
+		PSETID_Note =         '{0006200e-0000-0000-c000-000000000046}'
+		# for IPM.Activity. also called the journal?
+		PSETID_Log =          '{0006200a-0000-0000-c000-000000000046}'
+
 		# Enumerable removed. not really needed
 
 		# access the underlying raw properties by code. no implicit type conversion
@@ -462,7 +484,7 @@ def parse_properties obj
 					add_property key, Ole::Storage::OleDir.parse_time(*data[8..-1].unpack('L*'))
 				else
 					Log.warn "ignoring data in __properties section, encoding: #{encoding}"
-					Log << data.unpack('H*').inspect
+					Log << data.unpack('H*').inspect + "\n"
 				end
 			end
 		end
@@ -601,10 +623,12 @@ def to_sym
 					else
 						# handle other guids here, like mapping names to outlook properties, based on the
 						# outlook object model.
-						code
+						NAMED_MAP[self].to_sym rescue code
 					end
 				when String
 					# return something like
+					# note that named properties don't go through the map at the moment. so #categories
+					# doesn't work yet
 					code.downcase.to_sym
 				end
 			end
@@ -644,6 +668,14 @@ def inspect
 				end
 			end
 		end
+
+		# YUCK moved here because we need Key
+		# data files that provide for the code to symbolic name mapping
+		# guids in named_map are really constant references to the above
+		MAPITAGS = open('data/mapitags.yaml') { |file| YAML.load file }
+		NAMED_MAP = Hash[*open('data/named_map.yaml') { |file| YAML.load file }.map do |key, value|
+			[Key.new(key[0], const_get(key[1])), value]
+		end.flatten]
 	end
 
 	class Attachment