sunflower 0.3 → 0.4

data/lib/sunflower/listmaker.rb

@@ -1,152 +1,160 @@
-# coding: utf-8
-class Sunflower
-	# Makes a list of articles. Returns array of titles.
-	def make_list type, *parameters
-		type=type.downcase.gsub(/[^a-z]/, '')
-		first=parameters[0]
-		firstE=CGI.escape first.to_s
-		
-		case type
-		when 'file'
-			f=File.open first
-			list=f.read.sub(/\357\273\277/,'').strip.split(/\r?\n/)
-			f.close
-			
-		when 'page', 'pages'
-			list=parameters
-			
-		when 'input'
-			puts 'Insert titles of articles to edit:'
-			puts 'Press [Enter] without inputting any text to finish.'
-			puts 'Press [Ctrl]+[C] to kill bot.'
-			list=[]
-			while true
-				input=gets.strip
-				break if input==''
-				
-				list<<input
-			end
-			
-		when 'categorieson'
-			r=self.API('action=query&prop=categories&cllimit=500&titles='+firstE)
-			list=r['query']['pages'].first['categories'].map{|v| v['title']}
-			
-		when 'category'
-			r=self.API('action=query&list=categorymembers&cmprop=title&cmlimit=5000&cmtitle='+firstE)
-			list=r['query']['categorymembers'].map{|v| v['title']}
-			
-		when 'categoryr', 'categoryrecursive'
-			list=[] #list of articles
-			catsToProcess=[first] #list of categories to be processes
-			while !catsToProcess.empty?
-				list2=self.make_list('category',catsToProcess[0]) # get contents of first cat in list
-				catsToProcess=catsToProcess+list2.select{|el| el=~/\AKategoria:/} # find categories in it and queue them to be processes
-				catsToProcess.delete_at 0 # remove first category from list
-				list=list+list2 #add articles to main list
-			end
-			list.uniq! #remove dupes
-			
-		when 'linkson'
-			r=self.API('action=query&prop=links&pllimit=5000&titles='+firstE)
-			list=r['query']['pages'].first['links'].map{|v| v['title']}
-			
-		when 'transclusionson', 'templateson'
-			r=self.API('action=query&prop=templates&tllimit=5000&titles='+firstE)
-			list=r['query']['pages'].first['templates'].map{|v| v['title']}
-			
-		when 'usercontribs', 'contribs'
-			r=self.API('action=query&list=usercontribs&uclimit=5000&ucprop=title&ucuser='+firstE)
-			list=r['query']['usercontribs'].map{|v| v['title']}
-			
-		when 'whatlinksto', 'whatlinkshere'
-			r=self.API('action=query&list=backlinks&bllimit=5000&bltitle='+firstE)
-			list=r['query']['backlinks'].map{|v| v['title']}
-			
-		when 'whattranscludes', 'whatembeds'
-			r=self.API('action=query&list=embeddedin&eilimit=5000&eititle='+firstE)
-			list=r['query']['embeddedin'].map{|v| v['title']}
-			
-		when 'image', 'imageusage'
-			r=self.API('action=query&list=imageusage&iulimit=5000&iutitle='+firstE)
-			list=r['query']['imageusage'].map{|v| v['title']}
-			
-		when 'search'
-			r=self.API('action=query&list=search&srwhat=text&srlimit=5000&srnamespace='+(parameters[1]=='allns' ? CGI.escape('0|1|2|3|4|5|6|7|8|9|10|11|12|13|14|15|100|101|102|103') : '0')+'&srsearch='+firstE)
-			list=r['query']['search'].map{|v| v['title']}
-			
-		when 'searchtitles'
-			r=self.API('action=query&list=search&srwhat=title&srlimit=5000&srnamespace='+(parameters[1]=='allns' ? CGI.escape('0|1|2|3|4|5|6|7|8|9|10|11|12|13|14|15|100|101|102|103') : '0')+'&srsearch='+firstE)
-			list=r['query']['search'].map{|v| v['title']}
-		
-		when 'random'
-			r=self.API('action=query&list=random&rnnamespace=0&rnlimit='+firstE)
-			list=r['query']['random'].map{|v| v['title']}
-			
-		when 'external', 'linksearch'
-			r=self.API('action=query&euprop=title&list=exturlusage&eulimit=5000&euquery='+firstE)
-			list=r['query']['exturlusage'].map{|v| v['title']}
-			
-		when 'google'
-			limit=[parameters[1].to_i,999].min
-			from=0
-			list=[]
-			
-			while from<limit
-				p=HTTP.get(URI.parse("http://www.google.pl/custom?q=kot&start=#{from}&sitesearch=#{@wikiURL}"))
-				p.scan(/<div class=g><h2 class=r><a href="http:\/\/#{@wikiURL}\/wiki\/([^#<>\[\]\|\{\}]+?)" class=l>/){
-					list<<CGI.unescape($1).gsub('_',' ')
-				}
-				
-				from+=10
-			end
-		
-		when 'grep', 'regex', 'regexp'
-			split=@wikiURL.split('.')
-			ns=(parameters[1] ? parameters[1].to_s.gsub(/\D/,'') : '0')
-			redirs=(parameters[2] ? '&redirects=on' : '')
-			list=[]
-			
-			p=HTTP.get(URI.parse("http://toolserver.org/~nikola/grep.php?pattern=#{firstE}&lang=#{split[0]}&wiki=#{split[1]}&ns=#{ns}#{redirs}"))
-			p.scan(/<tr><td><a href="http:\/\/#{@wikiURL}\/wiki\/([^#<>\[\]\|\{\}]+?)(?:\?redirect=no|)">/){
-				list<<CGI.unescape($1).gsub('_',' ')
-			}
-		end
-		
-		return list
-	end
-end
-
-if $0==__FILE__
-	puts 'What kind of list do you want to create?'
-	if !(t=ARGV.shift)
-		t=gets
-	else
-		t=t.strip
-		puts t
-	end
-	puts ''
-	
-	puts 'Supply arguments to pass to listmaker:'
-	puts '(press [Enter] without writing anything to finish)'
-	arg=[]
-	ARGV.each do |i|
-		arg<<i.strip
-		puts i.strip
-	end
-	while (a=gets.strip)!=''
-		arg<<a
-	end
-	
-	puts 'Making list, wait patiently...'
-	
-	s=Sunflower.new
-	s.login
-	
-	l=s.make_list(t, *arg)
-	l.sort!
-	f=File.open('list.txt','w')
-	f.write(l.join("\n"))
-	f.close
-	
-	puts 'Done! List saved to "list.txt".'
-end
+# coding: utf-8
+class Sunflower
+	# Makes a list of articles. Returns array of titles.
+	def make_list type, *parameters
+		type=type.downcase.gsub(/[^a-z]/, '')
+		first=parameters[0]
+		firstE=CGI.escape first.to_s
+		
+		case type
+		when 'file'
+			f=File.open first
+			list=f.read.sub(/\357\273\277/,'').strip.split(/\r?\n/)
+			f.close
+			
+		when 'page', 'pages'
+			list=parameters
+			
+		when 'input'
+			puts 'Insert titles of articles to edit:'
+			puts 'Press [Enter] without inputting any text to finish.'
+			puts 'Press [Ctrl]+[C] to kill bot.'
+			list=[]
+			while true
+				input=gets.strip
+				break if input==''
+				
+				list<<input
+			end
+			
+		when 'categorieson'
+			r=self.API('action=query&prop=categories&cllimit=500&titles='+firstE)
+			list=r['query']['pages'].first['categories'].map{|v| v['title']}
+			
+		when 'category'
+			r=self.API('action=query&list=categorymembers&cmprop=title&cmlimit=5000&cmtitle='+firstE)
+			list=r['query']['categorymembers'].map{|v| v['title']}
+			
+		when 'categoryr', 'categoryrecursive'
+			list = [] # list of articles
+			processed = []
+			cats_to_process = [first] # list of categories to be processes
+			while !cats_to_process.empty?
+				now = cats_to_process.shift
+				processed << now # make sure we do not get stuck in infinite loop
+				
+				list2 = self.make_list 'category', now # get contents of first cat in list
+				
+				 # find categories and queue them
+				cats_to_process += list2
+					.select{|el| el=~/\AKategoria:/}
+					.reject{|el| processed.include? el or cats_to_process.include? el}
+				
+				list += list2 # add articles to main list
+			end
+			list.uniq!
+			
+		when 'linkson'
+			r=self.API('action=query&prop=links&pllimit=5000&titles='+firstE)
+			list=r['query']['pages'].first['links'].map{|v| v['title']}
+			
+		when 'transclusionson', 'templateson'
+			r=self.API('action=query&prop=templates&tllimit=5000&titles='+firstE)
+			list=r['query']['pages'].first['templates'].map{|v| v['title']}
+			
+		when 'usercontribs', 'contribs'
+			r=self.API('action=query&list=usercontribs&uclimit=5000&ucprop=title&ucuser='+firstE)
+			list=r['query']['usercontribs'].map{|v| v['title']}
+			
+		when 'whatlinksto', 'whatlinkshere'
+			r=self.API('action=query&list=backlinks&bllimit=5000&bltitle='+firstE)
+			list=r['query']['backlinks'].map{|v| v['title']}
+			
+		when 'whattranscludes', 'whatembeds'
+			r=self.API('action=query&list=embeddedin&eilimit=5000&eititle='+firstE)
+			list=r['query']['embeddedin'].map{|v| v['title']}
+			
+		when 'image', 'imageusage'
+			r=self.API('action=query&list=imageusage&iulimit=5000&iutitle='+firstE)
+			list=r['query']['imageusage'].map{|v| v['title']}
+			
+		when 'search'
+			r=self.API('action=query&list=search&srwhat=text&srlimit=5000&srnamespace='+(parameters[1]=='allns' ? CGI.escape('0|1|2|3|4|5|6|7|8|9|10|11|12|13|14|15|100|101|102|103') : '0')+'&srsearch='+firstE)
+			list=r['query']['search'].map{|v| v['title']}
+			
+		when 'searchtitles'
+			r=self.API('action=query&list=search&srwhat=title&srlimit=5000&srnamespace='+(parameters[1]=='allns' ? CGI.escape('0|1|2|3|4|5|6|7|8|9|10|11|12|13|14|15|100|101|102|103') : '0')+'&srsearch='+firstE)
+			list=r['query']['search'].map{|v| v['title']}
+		
+		when 'random'
+			r=self.API('action=query&list=random&rnnamespace=0&rnlimit='+firstE)
+			list=r['query']['random'].map{|v| v['title']}
+			
+		when 'external', 'linksearch'
+			r=self.API('action=query&euprop=title&list=exturlusage&eulimit=5000&euquery='+firstE)
+			list=r['query']['exturlusage'].map{|v| v['title']}
+			
+		when 'google'
+			limit=[parameters[1].to_i,999].min
+			from=0
+			list=[]
+			
+			while from<limit
+				p=HTTP.get(URI.parse("http://www.google.pl/custom?q=kot&start=#{from}&sitesearch=#{@wikiURL}"))
+				p.scan(/<div class=g><h2 class=r><a href="http:\/\/#{@wikiURL}\/wiki\/([^#<>\[\]\|\{\}]+?)" class=l>/){
+					list<<CGI.unescape($1).gsub('_',' ')
+				}
+				
+				from+=10
+			end
+		
+		when 'grep', 'regex', 'regexp'
+			split=@wikiURL.split('.')
+			ns=(parameters[1] ? parameters[1].to_s.gsub(/\D/,'') : '0')
+			redirs=(parameters[2] ? '&redirects=on' : '')
+			list=[]
+			
+			p=HTTP.get(URI.parse("http://toolserver.org/~nikola/grep.php?pattern=#{firstE}&lang=#{split[0]}&wiki=#{split[1]}&ns=#{ns}#{redirs}"))
+			p.scan(/<tr><td><a href="http:\/\/#{@wikiURL}\/wiki\/([^#<>\[\]\|\{\}]+?)(?:\?redirect=no|)">/){
+				list<<CGI.unescape($1).gsub('_',' ')
+			}
+		end
+		
+		return list
+	end
+end
+
+if $0==__FILE__
+	puts 'What kind of list do you want to create?'
+	if !(t=ARGV.shift)
+		t=gets
+	else
+		t=t.strip
+		puts t
+	end
+	puts ''
+	
+	puts 'Supply arguments to pass to listmaker:'
+	puts '(press [Enter] without writing anything to finish)'
+	arg=[]
+	ARGV.each do |i|
+		arg<<i.strip
+		puts i.strip
+	end
+	while (a=gets.strip)!=''
+		arg<<a
+	end
+	
+	puts 'Making list, wait patiently...'
+	
+	s=Sunflower.new
+	s.login
+	
+	l=s.make_list(t, *arg)
+	l.sort!
+	f=File.open('list.txt','w')
+	f.write(l.join("\n"))
+	f.close
+	
+	puts 'Done! List saved to "list.txt".'
+end

data/scripts/ZDBOT.rb

@@ -1,62 +1,62 @@
-require 'sunflower-core.rb'
-require 'sunflower-commontasks.rb'
-s=Sunflower.new
-s.login
-
-$summary='archiwizacja zadań'
-
-pp=Page.get('Wikipedia:Zadania dla botów')
-tasks=pp.text
-
-tasksDone=[]
-tasksError=[]
-tasksOld=[]
-
-tasks=tasks.gsub(/\n==\s*(.+?)\s*==\s*\{\{\/Status\|([^}]+)\}\}([\s\S]+?)(?=\r?\n==|\s*\Z)/) do
-	title=$1.strip
-	status=$2.strip
-	text=$3.strip
-	
-	bval=''
-	
-	if (['wykonane','zrobione','błąd','błędne','stare'].index(status)==nil)
-		bval=$&
-	elsif (status=='wykonane' || status=='zrobione')
-		tasksDone<<"== "+title+" ==\n{{/Status|"+status+"}}\n"+text
-	elsif (status=='błąd' || status=='błędne')
-		tasksError<<"== "+title+" ==\n{{/Status|"+status+"}}\n"+text
-	elsif (status=='stare')
-		tasksOld<<"== "+title+" ==\n{{/Status|"+status+"}}\n"+text
-	end
-	
-	bval
-end
-
-puts 'Data loaded. Saving...'
-
-p=Page.get('Wikipedia:Zadania_dla_botów/Archiwum/błędne')
-p.append tasksError.join("\n\n") unless tasksError.empty?
-p.save unless tasksError.empty?
-puts 'Error - saved.'
-
-p=Page.get('Wikipedia:Zadania_dla_botów/Archiwum/wykonane')
-p.append tasksDone.join("\n\n") unless tasksDone.empty?
-p.save unless tasksDone.empty?
-puts 'Done - saved.'
-
-p=Page.get('Wikipedia:Zadania_dla_botów/Archiwum/stare')
-p.append tasksOld.join("\n\n") unless tasksOld.empty?
-p.save unless tasksOld.empty?
-puts 'Old - saved.'
-
-pp.text=tasks
-pp.save
-puts 'Main - saved.'
-
-# File.open('ZDBOT_main.txt','w').write(tasks)
-# File.open('ZDBOT_done.txt','w').write(tasksDone.join("\n\n")) unless tasksDone.empty?
-# File.open('ZDBOT_error.txt','w').write(tasksError.join("\n\n")) unless tasksError.empty?
-# File.open('ZDBOT_old.txt','w').write(tasksOld.join("\n\n")) unless tasksOld.empty?
-
-puts "Stats: done: #{tasksDone.length}; error: #{tasksError.length}; old: #{tasksOld.length}"
+require 'sunflower-core.rb'
+require 'sunflower-commontasks.rb'
+s=Sunflower.new
+s.login
+
+$summary='archiwizacja zadań'
+
+pp=Page.get('Wikipedia:Zadania dla botów')
+tasks=pp.text
+
+tasksDone=[]
+tasksError=[]
+tasksOld=[]
+
+tasks=tasks.gsub(/\n==\s*(.+?)\s*==\s*\{\{\/Status\|([^}]+)\}\}([\s\S]+?)(?=\r?\n==|\s*\Z)/) do
+	title=$1.strip
+	status=$2.strip
+	text=$3.strip
+	
+	bval=''
+	
+	if (['wykonane','zrobione','błąd','błędne','stare'].index(status)==nil)
+		bval=$&
+	elsif (status=='wykonane' || status=='zrobione')
+		tasksDone<<"== "+title+" ==\n{{/Status|"+status+"}}\n"+text
+	elsif (status=='błąd' || status=='błędne')
+		tasksError<<"== "+title+" ==\n{{/Status|"+status+"}}\n"+text
+	elsif (status=='stare')
+		tasksOld<<"== "+title+" ==\n{{/Status|"+status+"}}\n"+text
+	end
+	
+	bval
+end
+
+puts 'Data loaded. Saving...'
+
+p=Page.get('Wikipedia:Zadania_dla_botów/Archiwum/błędne')
+p.append tasksError.join("\n\n") unless tasksError.empty?
+p.save unless tasksError.empty?
+puts 'Error - saved.'
+
+p=Page.get('Wikipedia:Zadania_dla_botów/Archiwum/wykonane')
+p.append tasksDone.join("\n\n") unless tasksDone.empty?
+p.save unless tasksDone.empty?
+puts 'Done - saved.'
+
+p=Page.get('Wikipedia:Zadania_dla_botów/Archiwum/stare')
+p.append tasksOld.join("\n\n") unless tasksOld.empty?
+p.save unless tasksOld.empty?
+puts 'Old - saved.'
+
+pp.text=tasks
+pp.save
+puts 'Main - saved.'
+
+# File.open('ZDBOT_main.txt','w').write(tasks)
+# File.open('ZDBOT_done.txt','w').write(tasksDone.join("\n\n")) unless tasksDone.empty?
+# File.open('ZDBOT_error.txt','w').write(tasksError.join("\n\n")) unless tasksError.empty?
+# File.open('ZDBOT_old.txt','w').write(tasksOld.join("\n\n")) unless tasksOld.empty?
+
+puts "Stats: done: #{tasksDone.length}; error: #{tasksError.length}; old: #{tasksOld.length}"
 gets