new Mark Remaining Read option

trunk/ripnews/CHANGELOG

@@ -1,6 +1,10 @@
-# $Dwarf: CHANGELOG,v 1.37 2005/02/05 08:29:36 ward Exp $
+# $Dwarf: CHANGELOG,v 1.38 2005/02/09 09:14:35 ward Exp $
 # $Source$
 
+from 0.5.2 to ...
+	- fix the occasional deadlock
+	- implement Mark Remaining Read option
+
 from 0.5.1 to 0.5.2
 	- major improvement in memory usage
 	- speed ups

trunk/ripnews/README

@@ -1,4 +1,4 @@
-# $Dwarf: README,v 1.19 2005/02/24 09:02:24 ward Exp $
+# $Dwarf: README,v 1.20 2005/03/01 09:18:25 ward Exp $
 # $Source$
 
 Ripnews is a bulk downloader for usenet. It's quite flexible in terms of
@@ -118,13 +118,21 @@ Supported config options:
 OPT_I=<pattern>			Set include pattern.
 OPT_L=<bool>			Set long filenames.
 OPT_C=<bool>			Sets combined filenames.
-OPT_X=<pattern>			Set exclude pattern. Ripnews will read articles                                 matching this pattern but it will not attempt
+OPT_X=<pattern>			Set exclude pattern. Ripnews will read articles
+				matching this pattern but it will not attempt
 				to download them.
 OPT_MR=<pattern>		Set "mark read" pattern. Ripnews will place
 				articles matching this pattern in your newsrc,
 				afterwards they will never be present in memory
 				again. Great for reducing memory usage when
 				checking a group for the first time.
+OPT_MRR=<bool>			Mark Remaining Read. If this is set to
+				true and the article doesn't match an exclude or
+				include pattern, the article will be
+				marked as read. The purpose of this is
+				to keep the caches of extremely large
+				groups small as to make processing
+				quicker.
 OPT_T=<bool>			Set test mode. Newsrc files will not be written
 				to.
 TEMPDIR=<dir>			Set tempdir location.

trunk/ripnews/ripnews.rb

@@ -1,6 +1,6 @@
 #!/usr/local/bin/ruby -w
 
-# $Dwarf: ripnews.rb,v 1.102 2005/03/01 09:18:50 ward Exp $
+# $Dwarf: ripnews.rb,v 1.103 2005/03/01 19:56:56 ward Exp $
 # $Source$
 
 #
@@ -428,9 +428,9 @@ def get_multi(subj, group)
 		end
 
 		@decode_threads << Thread.new(body, file, fileout, subj) do |tbody, tfile, tfileout, tsubj|
-			puts "inside thread pre pass\n"
+#			puts "inside thread pre pass\n"
 			Thread.pass
-			puts "inside thread post pass\n"
+#			puts "inside thread post pass\n"
 			if UUEncode.is_uuencoded(tbody)
 				print "	UUDecoding...\n"
 				if tfile
@@ -478,7 +478,7 @@ def get_multi(subj, group)
 			output_data(tsubj, tmode, tfilename, tbody)
 		end # thread end
 
-		puts "ouside thread\n"
+#		puts "ouside thread\n"
 
 		return true
 	else
@@ -488,7 +488,7 @@ def get_multi(subj, group)
 end
 
 def fill_preselector(group)
-	if @config[group].has_key?("-I")
+	if @config[group].has_key?("-I") and !(@config[group].has_key?("-MRR") and @config[group]["-MRR"])
 		@articles.set_preselect_pattern(Regexp.new(@config[group]["-I"]))
 	end
 end
@@ -652,12 +652,12 @@ def main
 		end
 		for i in @articles.get_group_subjects.sort{|a, b| ward_sort(a, b)}
 			print "#{i}\n" if Debuglevel > 2
+			# explicitly mark as read
 			if @config[group].has_key?("-MR") and i =~ /#{@config[group]["-MR"]}/
 				print "Marking '#{i}' as read\n"
 				@articles.group_update_newsrc(i)
-				next
+			# get the juicy bits
-			end
+			elsif !(@config[group].has_key?("-X") and i =~ /#{@config[group]["-X"]}/) and
-			if !(@config[group].has_key?("-X") and i =~ /#{@config[group]["-X"]}/) and
 			   i =~ /#{@config[group]["-I"]}/
 				print "Match: #{i}\n" if Debuglevel > 0
 				if @articles.group_is_complete(i)
@@ -667,21 +667,24 @@ def main
 						elsif @articles.group_is_multipart(i)
 							get_multi(i, group)
 						end
-					#rescue Article::TempError, Article::PermError
 					rescue TempError, PermError
 						print "#{$!}\n"
 						print "	Skipping article...\n"
 						#print "Caught #{$!.class}\n"
 						#print "Error: #{$!}\n"
-						next
 					end
 				else
 					print "Not complete: #{i}\n"
 				end
+			# if Mark Remaining Read is set do so
+			elsif @config[group].has_key?("-MRR") and @config[group]["-MRR"] and
+			    !(@config[group].has_key?("-X") and i =~ /#{@config[group]["-X"]}/)
+				print "Marking remaining '#{i}' as read\n"
+				@articles.group_update_newsrc(i)
 			end
 		end
 
-		# hier wachten op evt. threads...
+		# wait for threads if there are any
 		if ! @decode_threads.empty?
 			@articles.disconnect
 			puts "Waiting for decode threads..."