RubyGems - clwiki - Versions diffs - 2.0.0 - Mend

clwiki 2.0.0

Files changed (134) hide show

data/lib/cl_wiki/format/format.opml.rb ADDED Viewed

@@ -0,0 +1,105 @@
+if __FILE__ == $0
+  $LOAD_PATH << ".."
+  require 'clwikipage'
+end
+class FormatOPML < ClWiki::CustomFormatter
+  def FormatOPML.match_re
+    /<opml.*?>.*?<\/opml>/m
+  end
+  def FormatOPML.format_content(content, page)
+    out = ['<NoWikiLinks>']
+    content.grep(/<outline.*?>|<\/outline>/).each do |ln|
+      title = ln.scan(/title=\"(.*?)\"/).compact
+      html = ln.scan(/htmlUrl=\"(.*?)\"/).compact
+      xml = ln.scan(/xmlUrl=\"(.*?)\"/).compact
+      if html.empty? && xml.empty?
+        if !title.empty?
+          out << "<h4>#{title}</h4>"
+          out << '<blockquote>'
+        else
+          out << '</blockquote>'
+        end
+      else
+        out << "<a href='#{xml}'>[xml]</a> <a href='#{html}'>#{title}</a>"
+      end
+    end
+    out.join("\n") + content
+  end
+end
+ClWiki::CustomFormatters.instance.register(FormatOPML)
+if __FILE__ == $0
+  sample_opml = <<-OPMLTEXT
+    <opml xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
+      <head>
+        <title>Generated by SharpReader - http://www.sharpreader.net</title>
+      </head>
+      <body>
+        <outline type="rss" title="{ | one, step, back | }" description="Jim Weirich's Blog" xmlUrl="http://onestepback.org/index.cgi/index.rss" htmlUrl="http://onestepback.org/index.cgi" />
+        <outline type="rss" title="A Few Comments (Bill Caputo)" description="" xmlUrl="http://www.williamcaputo.com/index.rdf" htmlUrl="http://www.williamcaputo.com/" />
+        <outline type="rss" title="Allen Bauer's blog..." description="Borland Delphi and C#Builder IDE Architect.&#xA;Just jumping on the blogging bandwagon... oh look a cliff.." xmlUrl="http://homepages.borland.com/abauer/rss.xml" htmlUrl="http://homepages.borland.com/abauer" />
+        <outline type="rss" title="Artima Weblogs" description="Artima Weblogs is a community of bloggers posting on a wide range of topics of interest to software developers." xmlUrl="http://www.artima.com/weblogs/feeds/weblogs.rss" htmlUrl="http://www.artima.com/weblogs/" />
+        <outline type="rss" title="Bit Banger" description="The definitive source of everything Adam Keys." xmlUrl="http://www.trmk.org/~adam/blog/index.rdf" htmlUrl="http://trmk.org/~adam/blog/" />
+        <outline type="rss" title="bt.etree.org" description="etree.org BitTorrent Tracker" xmlUrl="http://bt.etree.org/rss/bt_etree_org.rdf" htmlUrl="http://bt.etree.org/" />
+        <outline type="rss" title="Cem Kaner's blog" description="Cem Kaner's weblog&#xA;Software testing, software safety, software law." xmlUrl="http://blackbox.cs.fit.edu/blog/kaner/index.rdf" htmlUrl="http://blackbox.cs.fit.edu/blog/kaner/" />
+        <outline type="rss" title="ChadFowler.com" description="Chad Fowler's Random Posts on Computing, Language, and Travel" xmlUrl="http://www.chadfowler.com/?rss " htmlUrl="http://www.chadfowler.com/index.cgi" />
+        <outline type="rss" title="cLabs Blogki" description="cLabs Blogki" xmlUrl="http://www.clabs.org/blogki/blogki.rss.cgi " htmlUrl="http://www.clabs.org/blogki" />
+        <outline type="rss" title="Clay Shirky's Essays" description="Clay Shirky's Essays" xmlUrl="http://www.shirky.com/writings/rss.cgi" htmlUrl="http://www.shirky.com/writings/rss.cgi" />
+        <outline type="rss" title="Collaborative Software Testing (Jonathan Kohl)" description="Jonathan Kohl's blog. Exploring tester and developer collaboration." xmlUrl="http://www.kohl.ca/blog/index.rdf" htmlUrl="http://www.kohl.ca/blog/" />
+        <outline type="rss" title="Common Content: Newest Items" description="Common Content's latest posted items." xmlUrl="http://www.commoncontent.org/rss/newest.cgi" htmlUrl="http://www.commoncontent.org/" />
+        <outline type="rss" title="Conversations with Dale" description="Dale H. Emery's Journal" xmlUrl="http://www.dhemery.com/journal/index.rdf " htmlUrl="http://www.dhemery.com/journal/" />
+        <outline type="rss" title="Creative Commons: weblog" description="Creative Commons: weblog" xmlUrl="http://www.creativecommons.org/weblog/rss " htmlUrl="http://creativecommons.org/weblog/" />
+        <outline type="rss" title="Dan Bricklin's Log" description="VisiCalc co-creator Dan Bricklin chronicles his life in the computer world with pictures, text, and commentary." xmlUrl="http://danbricklin.com/log_rss.xml" htmlUrl="http://danbricklin.com/log" />
+        <outline type="rss" title="Don Box's Spoutlet" description="Rants from the SOAP box" xmlUrl="http://www.gotdotnet.com/team/dbox/rss.aspx" htmlUrl="http://www.gotdotnet.com/team/dbox/default.aspx" />
+        <outline type="rss" title="Eric.Weblog()" description="Thoughts about software from yet another person who invented the Internet" xmlUrl="http://biztech.ericsink.com/rss.xml" htmlUrl="http://software.ericsink.com/" />
+        <outline type="rss" title="Exploration Through Example (Brian Marick)" description="Exploration Through Example - Brian Marick" xmlUrl="http://www.testing.com/cgi-bin/blog/index.rss " htmlUrl="http://www.testing.com/cgi-bin/blog" />
+        <outline title="Fluffy">
+          <outline type="rss" title="/\ndy's Weblog" description="" xmlUrl="http://www.toolshed.com/blog/index.rss " htmlUrl="http://www.toolshed.com/blog" />
+          <outline type="rss" title="Bill Dudney's Weblog" description="Bill Dudney's Weblog" xmlUrl="http://bill.dudney.net/roller/rss/bill" htmlUrl="http://bill.dudney.net/roller/page/bill" />
+          <outline type="rss" title="Duncan's Blog" description="Personal website for James Duncan Davidson" xmlUrl="http://x180.net/Blog/index.rss " htmlUrl="http://x180.net" />
+          <outline type="rss" title="Glenn Vanderburg: Weblog" description="Glenn Vanderburg's personal weblog." xmlUrl="http://www.vanderburg.org/cgi-bin/glv/blosxom?flav=rss " htmlUrl="http://www.vanderburg.org/cgi-bin/glv/blosxom" />
+          <outline type="rss" title="Mike Clark" description="Mike's soapbox of life in the trenches" xmlUrl="http://www.clarkware.com/cgi/blosxom/index.rss" htmlUrl="http://www.clarkware.com/cgi/blosxom" />
+          <outline type="rss" title="Ockham's Flashlight (Stuart Halloway)" description="Stuart Halloway on software development, technology, and the future." xmlUrl="http://www.relevancellc.com/halloway/weblog/rss.xml" htmlUrl="http://www.relevancellc.com/halloway/weblog/" />
+          <outline type="rss" title="Potential Differences (Greg Vaughn)" description="Greg Vaughn on Java, Agile methodologies, OS X, whatever piques my interest!" xmlUrl="http://gigavolt.net/blog/index.rss" htmlUrl="http://gigavolt.net/blog" />
+          <outline type="rss" title="PragDave" description="Dave's Weblog: Pragmatic Programming." xmlUrl="http://pragprog.com/pragdave/index.rss " htmlUrl="http://pragprog.com/pragdave" />
+          <outline type="rss" title="Servlets.com Weblog (Jason Hunter)" description="Java, Open Source, XML, Web Services, and (gasp) .NET" xmlUrl="http://www.servlets.com/blog/index-all.xml" htmlUrl="http://www.servlets.com/blog/" />
+        </outline>
+        <outline type="rss" title="Joel on Software" description="Painless Software Management" xmlUrl="http://www.joelonsoftware.com/rss.xml " htmlUrl="http://www.joelonsoftware.com" />
+        <outline type="rss" title="Luke Hutteman's Weblog" description="Luke Hutteman on Java, C#, J2EE, RSS and whatever else comes to mind..." xmlUrl="http://www.hutteman.com/weblog/rss.xml" htmlUrl="http://www.hutteman.com/weblog/" />
+        <outline type="rss" title="Managing Product Development" description="Management, especially good management, is hard to do. This blog is for people who want to think about how they manage people, projects, and risk." xmlUrl="http://www.jrothman.com/weblog/RSS/mpdblogger_rss.xml" htmlUrl="http://www.jrothman.com/weblog/blogger.html" />
+        <outline type="rss" title="Martin Fowler's Bliki" description="A cross between a blog and wiki of my partly-formed ideas on software development" xmlUrl="http://martinfowler.com/bliki/bliki.rss" htmlUrl="http://martinfowler.com/bliki" />
+        <outline type="rss" title="mezzoblue" description="" xmlUrl="http://www.mezzoblue.com/rss/index.xml" htmlUrl="http://www.mezzoblue.com/" />
+        <outline type="rss" title="Michael Feathers' Weblog" description="Let's Reconsider That" xmlUrl="http://www.artima.com/weblogs/feeds/bloggers/mfeathers.rss" htmlUrl="http://www.artima.com/weblogs/index.jsp?blogger=mfeathers" />
+        <outline type="rss" title="OK/Cancel" description="OK/Cancel is a comic strip written for a very specific audience, but much of what we talk about is quite universal. Most everybody can relate to things in the world which don't work like they should. You needn't be a usability specialist, interaction designer, industrial designer or any sort of designer to appreciate that frustration. But if you ARE any of those aforementioned people or have had the pleasure and pain of working with one or more of this rare breed, this strip is for you." xmlUrl="http://www.ok-cancel.com/index.rdf" htmlUrl="http://www.ok-cancel.com/" />
+        <outline type="rss" title="open.neurosaudio.com" description="" xmlUrl="http://open.neurosaudio.com/index.rdf" htmlUrl="http://open.neurosaudio.com/" />
+        <outline title="Ruby">
+          <outline type="rss" title="Ruby Application Archive" description="Summary for Ruby Application Archive, provided by Bulknews." xmlUrl="http://bulknews.net/rss/rdf.cgi?RAA" htmlUrl="http://www.ruby-lang.org/en/raa.html" />
+          <outline type="rss" title="Ruby Garden Wiki" description="Recent Changes to the Ruby Garden" xmlUrl="http://www.rubygarden.com/rdf/cached/rubygarden-wiki.rdf" htmlUrl="http://www.rubygarden.org/ruby" />
+          <outline type="rss" title="Ruby Weekly News" description="Recent news about Ruby" xmlUrl="http://www.rubygarden.com//rdf/cached/rurl.rdf" htmlUrl="http://www.rubygarden.org/rurl/html/index.html" />
+          <outline type="rss" title="Ruby XML" description="" xmlUrl="http://www.rubyxml.com/rss0.91.xml" htmlUrl="" />
+          <outline type="rss" title="ruby-doc" description="Recent postings to the Ruby Documentation Project web site." xmlUrl="http://www.ruby-doc.org/index.rb/rss0.91.xml" htmlUrl="http://www.ruby-doc.org/index.rb" />
+        </outline>
+        <outline type="rss" title="Ruminations" description="" xmlUrl="http://www.mcmains.net/ruminations/rss " htmlUrl="http://www.mcmains.net/ruminations" />
+        <outline type="rss" title="SATN" description="Bob, David, and Dan's comments" xmlUrl="http://www.satn.org/satn_rss.xml" htmlUrl="http://www.satn.org" />
+        <outline type="rss" title="Secure Programming News" description="News &amp; information related to secure programming topics" xmlUrl="http://www.secureprogramming.com/?action=rss&amp;feature=weblog" htmlUrl="http://www.secureprogramming.com/" />
+        <outline type="rss" title="Secure Programming Recipes" description="Cookbook-style recipes for tackling programming problems securely." xmlUrl="http://www.secureprogramming.com/website.py?action=rss&amp;feature=recipes" htmlUrl="http://www.secureprogramming.com/?action=browse&amp;feature=recipes" />
+        <outline type="rss" title="simplegeek (Chris Anderson - MS Architect)" description="" xmlUrl="http://www.simplegeek.com/blogxbrowsing.asmx/GetRss?" htmlUrl="http://www.simplegeek.com" />
+        <outline type="rss" title="Slashdot" description="News for nerds, stuff that matters" xmlUrl="http://slashdot.org/slashdot.rss" htmlUrl="http://slashdot.org/" />
+        <outline type="rss" title="Software (Management) Process Improvement" description="&quot;Poor management can increase software costs more rapidly than any other factor.&quot; (Barry Boehm)" xmlUrl="http://www.estherderby.com/weblog/RSS/blogger_rss.xml" htmlUrl="http://www.estherderby.com/weblog/blogger.html" />
+        <outline type="rss" title="SourceForge.net: Project File Releases: Neuros Database Manipulator" description="SF.net File Releases: Neuros Database Manipulator (neurosdbm project) - Neuros Database Manipulator - Browse and modify the database of your Neuros Audio Computer.  Neuros Database Manipulator is written in Java for cross platform support." xmlUrl="http://sourceforge.net/export/rss2_projfiles.php?group_id=83367" htmlUrl="http://sourceforge.net/projects/neurosdbm/" />
+        <outline type="rss" title="SQLServerCentral.Com - Articles" description="Articles posted on the SQLServercentral.com site." xmlUrl="http://www.sqlservercentral.com/sscrss.xml" htmlUrl="http://www.sqlservercentral.com" />
+        <outline type="rss" title="Testing Hotlist Update" description="Bret Pettichord's Weblog. Observations of a Software Tester." xmlUrl="http://www.io.com/~wazmo/blog/index.rdf" htmlUrl="http://www.io.com/~wazmo/blog/" />
+        <outline type="rss" title="The Idea Ether" description="Rich Kilmer's place to express the ideas that bounce around in his head." xmlUrl="http://richkilmer.blogs.com/ether/index.rdf" htmlUrl="http://richkilmer.blogs.com/ether/" />
+        <outline type="rss" title="The Old New Thing" description="" xmlUrl="http://blogs.gotdotnet.com/raymondc/blogxbrowsing.asmx/GetRss?" htmlUrl="http://blogs.gotdotnet.com/raymondc/" />
+        <outline type="rss" title="Thinking About Computing (Bruce Eckel)" description="Bruce Eckel's Web Log" xmlUrl="http://mindview.net/WebLog/RSS.xml" htmlUrl="http://www.MindView.net/WebLog/" />
+        <outline type="rss" title="Ward Cunningham's Weblog" description="Ward Says, Don't Try This at Home" xmlUrl="http://www.artima.com/weblogs/feeds/bloggers/ward.rss " htmlUrl="http://www.artima.com/weblogs/index.jsp?blogger=ward" />
+        <outline type="rss" title="Web Testing with Ruby" description="Web Testing with Ruby" xmlUrl="http://www.clabs.org/wtr/blogki.rss.cgi" htmlUrl="http://www.clabs.org//wtr/index.cgi" />
+        <outline type="rss" title="whytheluckystiff.net" description="we've all got our ways of dealing with it." xmlUrl="http://whytheluckystiff.net/why.xml" htmlUrl="http://www.whytheluckystiff.net/" />
+      </body>
+    </opml>
+  OPMLTEXT
+  puts FormatOPML.format_content(sample_opml, nil)
+end

data/lib/cl_wiki/format/format.pre.blockquote.rb ADDED Viewed

@@ -0,0 +1,15 @@
+require 'cgi'
+class FormatPreBlockquote < ClWiki::CustomFormatter
+  def FormatPreBlockquote.match_re
+    /\[p\].*?\[\/p\]/mi
+  end
+  def FormatPreBlockquote.format_content(content, page)
+    content = CGI.escapeHTML(content)
+    content.gsub!(/\[p\]/i, "<blockquote><pre>")
+    content.gsub!(/\[\/p\]/i, "</pre></blockquote>")
+  end
+end
+ClWiki::CustomFormatters.instance.register(FormatPreBlockquote)

data/lib/cl_wiki/format/format.simpletable.rb ADDED Viewed

@@ -0,0 +1,25 @@
+class FormatSimpleTable < ClWiki::CustomFormatter
+  def FormatSimpleTable.match_re
+    /<simpletable.*?>.*?<\/simpletable>/m
+  end
+  def FormatSimpleTable.format_content(content, page=nil)
+    table_attr = content.scan(/<simpletable(.*?)>/m).to_s.strip
+    table_attr = 'border="1"' if table_attr.empty?
+    content.gsub!(/<simpletable.*?>/m, '')
+    content.gsub!(/<\/simpletable>/m, '')
+    content.strip!
+    lines = content.split("\n")
+    lines.collect! do |ln|
+      ln.gsub!(/\t/, '  ')
+      '<tr><td>' + ln.gsub(/  +/, '</td><td>') + '</td></tr>'
+    end
+    lines.collect! do |ln| ln.gsub(/<td>\s*?<\/td>/, '<td>&nbsp;</td>') end
+    # if you do a .join("\n"), then the \n will be converted to <br>
+    # ... so don't do that
+    "<table #{table_attr}>\n" + lines.join("") + "</table>"
+  end
+end
+ClWiki::CustomFormatters.instance.register(FormatSimpleTable)

data/lib/cl_wiki/index.rb ADDED Viewed

@@ -0,0 +1,455 @@
+require 'rubygems'
+require File.dirname(__FILE__) + '/page'
+require File.dirname(__FILE__) + '/configuration'
+require 'cl/util/progress'
+require 'cl/util/console'
+gem 'clindex'
+require 'index'
+require 'drb'
+module ClWiki
+  class Indexer
+    attr_reader :index
+    WAIT = true
+    def self.defaultPort
+      '9111'
+    end
+    def initialize(wiki_conf=$wiki_conf, fn=nil)
+      @wiki_conf = wiki_conf
+      @index = ClIndex.new
+      @recent = ClIndex.new
+      @pages = ClIndex.new
+      @hits = ClIndex.new if @wiki_conf.access_log_index
+      @rootDir = @wiki_conf.wiki_path
+      @fn = fn
+      @record_hits = true
+      load
+    end
+    def do_puts(text)
+      if @fn
+        File.open(@fn, 'a+') do |f|
+          f.puts text
+        end
+      else
+        puts text
+      end
+    end
+    def build(limit=-1, purge=false)
+      @record_hits = false
+      begin
+        fileCount = 0
+        raise '$wikiPageExt not set' if $wikiPageExt.empty? # for debugging only, really
+        files = Dir[::File.join(@rootDir, '**/*' + $wikiPageExt)]
+        if limit == -1
+          p = Progress.new(files.length)
+        else
+          p = Progress.new(limit)
+        end
+        p.start
+        files.each do |fn|
+          next if !::File.file?(fn)
+          break if (limit > -1) && (fileCount >= limit)
+          fileCount += 1
+          fullName = fn.sub(@rootDir, '')
+          fullName = fullName.sub(/#{$wikiPageExt}/, '')
+          index_page(fullName, purge)
+          do_puts p.progress(true)
+        end
+      ensure
+        @record_hits = true
+      end
+    end
+    def index_page(fullName, purge=false)
+      put_status "indexing #{fullName}" do
+        pg = ClWiki::Page.new(fullName, @rootDir)
+        pg.read_raw_content
+        if purge && pg.content_never_edited?
+          put_status("purging #{fullName}")
+          pg.delete
+          remove_page_from_index(fullName)
+        else
+          formatter = ClWiki::PageFormatter.new(pg.raw_content, fullName)
+          formatter.formatLinks do |word|
+            if formatter.is_wiki_name?(word)
+              word = formatter.expand_path(word, fullName)
+            else
+              word.downcase!
+            end
+            add_to_index(word, fullName)
+          end
+          add_to_index(fullName, fullName)
+          add_to_pages(fullName)
+          add_to_recent(pg.mtime, fullName)
+        end
+      end
+    end
+    def add_to_index(term, fullPageName)
+      @index.add(term, fullPageName, WAIT)
+    end
+    def add_to_recent(modTime, fullPageName)
+      # remove all other instances of this page, we only need the current modTime
+      @recent.remove(fullPageName, WAIT)
+      @recent.add(modTime, fullPageName, WAIT)
+    end
+    def add_to_pages(fullPageName)
+      @pages.add(fullPageName, nil, WAIT)
+    end
+    def hits_filename
+      ::File.join(::File.expand_path('.'), 'hits.dat')
+    end
+    def index_filename
+      ::File.join(::File.expand_path('.'), 'index.dat')
+    end
+    def recent_filename
+      ::File.join(::File.expand_path('.'), 'recent.dat')
+    end
+    def pages_filename
+      ::File.join(::File.expand_path('.'), 'pages.dat')
+    end
+    def remove_page_from_index(fullPageName)
+      @index.remove(fullPageName, WAIT)
+      @recent.remove(fullPageName, WAIT)
+    end
+    def put_status(status)
+      if block_given?
+        do_puts Time.now.strftime("%I:%M:%S") + ' ' + status + '... '
+        yield
+        do_puts Time.now.strftime("%I:%M:%S") + ' ' + status + ' done '
+      else
+        do_puts Time.now.strftime("%I:%M:%S") + ' ' + status
+      end
+    end
+    def reindex_and_save_async(fullPageName)
+      thread = Thread.new do
+        reindex_page(fullPageName)
+        save
+      end
+      @wiki_conf.wait_on_thread(thread)
+    end
+    def reindex_page(fullPageName)
+      put_status 'Reindexing ' + fullPageName do
+        remove_page_from_index(fullPageName)
+        index_page(fullPageName)
+      end
+    end
+    def save
+      put_status 'Saving' do
+        put_status 'Saving Main' do
+          @index.save(index_filename, WAIT)
+        end
+        put_status 'Saving Recent' do
+          @recent.save(recent_filename, WAIT)
+        end
+        put_status 'Saving Pages' do
+          @pages.save(pages_filename, WAIT)
+        end
+        put_status 'Saving Hits' do
+          @hits.save(hits_filename, WAIT) if @wiki_conf.access_log_index
+        end
+      end
+    end
+    def load
+      put_status 'Loading' do
+        put_status 'Loading Main' do
+          @index.load(index_filename, WAIT) if ::File.exists?(index_filename)
+        end
+        put_status 'Loading Recent' do
+          @recent.load(recent_filename, WAIT) if ::File.exists?(recent_filename)
+        end
+        put_status 'Loading Pages' do
+          @pages.load(pages_filename, WAIT) if ::File.exists?(pages_filename)
+        end
+        if @wiki_conf.access_log_index
+          put_status 'Loading Hits' do
+            @hits.load(hits_filename, WAIT) if ::File.exists?(hits_filename)
+          end
+        end
+      end
+    end
+    def dump_clindex(aindex, fn_prefix)
+      put_status "Dumping #{fn_prefix}..." do
+        hash = aindex.index
+        ::File.open(fn_prefix + '.keys.dump.txt', 'w+') do |f|
+          keys = hash.keys
+          keys.sort.each do |key|
+            f.puts key
+          end
+        end
+        File.open(fn_prefix + '.full.dump.txt', 'w+') do |f|
+          fullary = hash.to_a
+          fullary.sort!
+          fullary.each do |keyValueAry|
+            f.puts keyValueAry[0].inspect + " => " + keyValueAry[1].inspect
+          end
+        end
+      end
+    end
+    def dump
+      dump_clindex(@index, 'index')
+      dump_clindex(@recent, 'recent')
+      dump_clindex(@pages, 'pages')
+      dump_clindex(@hits, 'hits') if @wiki_conf.access_log_index
+    end
+    def search(text)
+      terms = text.split(' ')
+      allhits = nil
+      terms.each do |term|
+        termhits = []
+        @index.search(term, termhits, WAIT)
+        termhits.flatten!
+        if !allhits
+          allhits = termhits
+        else
+          allhits = allhits & termhits
+        end
+      end
+      allhits = [] if !allhits # shouldn't ever happen I'd wager
+      p allhits if $debug
+      allhits.flatten!
+      allhits.uniq!
+      allhits.sort!
+      p allhits if $debug
+      allhits
+    end
+    def sort_hits_by_recent(hits, top=-1)
+      hits_by_date = {}
+      # don't send top into this call to recent, we need all recent, then
+      # we filter that down to all matches, /then/ we take the topmost
+      # of that matching list
+      recent.each do |date, page_name_array|
+        hits_at_this_time = page_name_array & hits
+        hits_by_date[date] = hits_at_this_time if !hits_at_this_time.empty?
+      end
+      hits_by_date.sort { |a, b| b[0] <=> a[0] }[0..top]
+    end
+    def recent(top=-1)
+      @recent.do_read(WAIT) do
+        hash = @recent.index
+        hash.sort { |a, b| b[0] <=> a[0] }[0..top]
+      end
+    end
+    def pages_out(rootPage)
+      all = @index.all_terms(rootPage, WAIT)
+      #all.delete_if do |term|
+      #  term[0..0] != '/' || !ClWikiPage.page_exists?(term.dup)
+      #end
+      all.delete_if do |term|
+        (term[0..0] != '/') || (term == '/') || (term == '//')
+      end
+      all.delete_if do |term|
+        !ClWikiPage.page_exists?(term.dup)
+      end
+      all
+    end
+    def page_exists?(fullPageName)
+      exists = false
+      exists = @pages.term_exists?(fullPageName, WAIT)
+      exists
+    end
+    def add_hit(fullPageName)
+      if @record_hits && @wiki_conf.access_log_index
+        put_status('Hit on ' + fullPageName)
+        @hits.add(fullPageName, Time.now, WAIT)
+        thread = Thread.new do
+          @hits.save(hits_filename, WAIT)
+        end
+        @wiki_conf.wait_on_thread(thread)
+      end
+    end
+    def hit_summary(start_index=0, end_index=-1)
+      if @wiki_conf.access_log_index
+        hit_index = nil
+        @hits.do_read(WAIT) do
+          hit_index = @hits.index.dup
+        end
+        hit_index.sort { |a, b| b[1].length <=> a[1].length }[start_index..end_index]
+      end
+    end
+  end
+  class IndexClient
+    def initialize(wiki_conf=$wiki_conf)
+      case wiki_conf.useIndex
+        when ClWiki::Configuration::USE_INDEX_NO
+          raise 'wikiConf.useIndex says to not use an index'
+        when ClWiki::Configuration::USE_INDEX_DRB
+          DRb.start_service()
+          @indexer = DRbObject.new(nil, "druby://localhost:#{wiki_conf.indexPort}")
+        when ClWiki::Configuration::USE_INDEX_LOCAL
+          $indexer ||= ClWiki::Indexer.new(wiki_conf, wiki_conf.index_log_fn)
+          @indexer = $indexer
+      end
+    end
+    def reindex_page(fullPageName)
+      @indexer.reindex_and_save_async(fullPageName)
+    end
+    def search(term, titles_only=false)
+      hits = @indexer.search(term).flatten
+      if titles_only
+        hits.delete_if do |fullName|
+          !(fullName =~ /#{term}/i)
+        end
+      end
+      hits
+    end
+    def page_exists?(fullPageName)
+      @indexer.page_exists?(fullPageName)
+    end
+    def sort_hits_by_recent(hits, top=-1)
+      @indexer.sort_hits_by_recent(hits, top)
+    end
+    def recent(top=-1)
+      @indexer.recent(top)
+    end
+    def add_hit(fullPageName)
+      @indexer.add_hit(fullPageName)
+    end
+    def hit_summary(start_index=0, end_index=-1)
+      @indexer.hit_summary(start_index, end_index)
+    end
+  end
+end
+def launch_server(port=nil, fn=nil)
+  port = ClWiki::Indexer.defaultPort if !port
+  idxServer = ClWiki::Indexer.new(fn)
+  puts "ClWikiIndexer launching on localhost:#{port}..."
+  DRb.start_service("druby://localhost:#{port}", idxServer)
+  DRb.thread.join
+end
+if __FILE__ == $0
+  def do_page_exists(fullPageName)
+    if @i.page_exists?(fullPageName)
+      puts fullPageName + ' exists'
+    else
+      puts fullPageName + ' does not exist'
+    end
+  end
+  def do_search(search)
+    puts @i.search(search).join("\n")
+    puts
+  end
+  def do_index_dump
+    puts 'Dumping...'
+    @i.dump
+  end
+  def do_recent
+    puts @i.recent
+    puts
+  end
+  def do_hits
+    puts @i.hit_summary.inspect
+    puts
+  end
+  def show_help
+    puts 'ClWikiIndexer'
+    puts
+    puts '-h        Show this help'
+    puts
+    puts '-s        Launch drb server'
+    puts "-p        Drb port. Default is #{ClWiki::Indexer.defaultPort}"
+    puts '-f [fn]   File to route output to. stdout used if not specified'
+    puts '-b        Do a full re-build of the index'
+    puts '-bp       Do a full re-build, purging unused pages. An unused page'
+    puts '          is one where the contents are the default content after'
+    puts '          creation, but has never been edited.'
+    puts '-l [x]    If -b, limit number of pages built to x'
+    puts '<none>    load index to search for terms entered in stdin'
+    puts '-q [term] load index and search for term'
+    puts '-r [page] load index and see if page exists'
+    puts '-x [page] load index and re-index the specified page'
+    puts '-d        debug'
+    puts '-dump     dumps full index to text file'
+    puts '-recent   show 1st recent hits'
+    puts '-hits     show 1st hit count'
+  end
+  $debug = if_switch('-d')
+  if if_switch('-h')
+    show_help
+  elsif if_switch('-s')
+    launch_server(get_switch('-p'), get_switch('-f'))
+  elsif if_switch('-b') || if_switch('-bp')
+    limit = -1
+    limit = get_switch('-l').to_i if get_switch('-l')
+    @i = ClWiki::Indexer.new
+    $wiki_conf.access_log_index = false
+    @i.build(limit, if_switch('-bp'))
+    @i.save
+  else
+    puts 'loading index...'
+    @i = ClWiki::Indexer.new
+    $wiki_conf.access_log_index = false
+    #@i.load
+    if get_switch('-q')
+      do_search(get_switch('-q'))
+    elsif if_switch('-recent')
+      do_recent
+    elsif if_switch('-hits')
+      do_hits
+    elsif get_switch('-r')
+      do_page_exists(get_switch('-r'))
+    elsif if_switch('-dump')
+      do_index_dump
+    elsif if_switch('-x')
+      @i.index_page(get_switch('-x'))
+      @i.save
+    else
+      begin
+        print 'input search term (empty to quit): '
+        search = gets.chomp
+        break if search.empty?
+        do_search(search)
+      end while true
+    end
+  end
+end