ward/ripnews
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

haal een redelijke hoeveelheid oude articles op

Browse source
This commit is contained in:
Ward Wouts 2005-02-05 10:48:31 +00:00
parent 4ad42edf90
commit f77ca9ea9c
1 changed files with 18 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

30
trunk/ripnews/news/article.rb
View file

@ -1,4 +1,4 @@
# $Dwarf: article.rb,v 1.104 2005/02/01 22:09:22 ward Exp $ # $Dwarf: article.rb,v 1.105 2005/02/05 08:26:44 ward Exp $
# $Source$ # $Source$
# #
@ -176,20 +176,26 @@ def get_articles(cachedir=false)
# print "############################################################\n" # print "############################################################\n"
# print "skip_ids #{server}: #{@connections[server]["skip_ids"].run_list}\n" # print "skip_ids #{server}: #{@connections[server]["skip_ids"].run_list}\n"
# end # end
# spul dat echt te oud is gaat nooit gevuld worden, dus doe ook geen poging het op te halen
# wil wel wat ophalen aangezien logging aantoont dat er wel oudere articles gedownload worden
articles = @connections[server]["last"] - @connections[server]["first"]
if articles > 10000
fillerend = (@connections[server]["last"] - (articles/10)).to_i
else
fillerend = @connections[server]["last"] - 1000
end
if fillerend > @connections[server]["skip_ids"].min
@connections[server]["skip_ids"] = @connections[server]["skip_ids"].union("#{@connections[server]["skip_ids"].min}-#{fillerend}")
# p "filling #{@connections[server]["skip_ids"].min}-#{fillerend}"
end
for server in @connections.keys for server in @connections.keys
print " reading articles from server: #{server}\n" print " reading articles from server: #{server}\n"
# range = Set::IntSpan.new("#{@connections[server]["first"]}-#{@connections[server]["last"]}") range = Set::IntSpan.new("#{@connections[server]["first"]}-#{@connections[server]["last"]}")
# is dit wel handig? ik denk dat het eigenlijk beter is om alleen de articles op te halen
# die nieuwe zijn dan de laatste die je al hebt rangelist = rechunk_runlist(range.diff(@connections[server]["skip_ids"]).run_list)
# al de gaten krijg je toch niet gevuld en duren kei lang
# rangelist = rechunk_runlist(range.diff(@connections[server]["skip_ids"]).run_list)
# dat idee maar eens testen dan:
if @connections[server]["skip_ids"].max < @connections[server]["last"]
rangelist = Set::IntSpan.new("#{@connections[server]["skip_ids"].max}-#{@connections[server]["last"]}").run_list
else
rangelist = ""
end
print "rangelist: #{rangelist}\n" if Debuglevel > 2 print "rangelist: #{rangelist}\n" if Debuglevel > 2
print "rangelist: #{rangelist.class.to_s}\n" if Debuglevel > 2 print "rangelist: #{rangelist.class.to_s}\n" if Debuglevel > 2
print "rangelist elements: #{range.diff(@connections[server]["skip_ids"]).elements}\n" if Debuglevel > 2 print "rangelist elements: #{range.diff(@connections[server]["skip_ids"]).elements}\n" if Debuglevel > 2