ruletagger 0.0.1

data/tasks/deployment.rake

@@ -0,0 +1,34 @@
+desc 'Release the website and new gem version'
+task :deploy => [:check_version, :website, :release] do
+  puts "Remember to create SVN tag:"
+  puts "svn copy svn+ssh://#{rubyforge_username}@rubyforge.org/var/svn/#{PATH}/trunk " +
+    "svn+ssh://#{rubyforge_username}@rubyforge.org/var/svn/#{PATH}/tags/REL-#{VERS} "
+  puts "Suggested comment:"
+  puts "Tagging release #{CHANGES}"
+end
+
+desc 'Runs tasks website_generate and install_gem as a local deployment of the gem'
+task :local_deploy => [:website_generate, :install_gem]
+
+task :check_version do
+  unless ENV['VERSION']
+    puts 'Must pass a VERSION=x.y.z release version'
+    exit
+  end
+  unless ENV['VERSION'] == VERS
+    puts "Please update your version.rb to match the release version, currently #{VERS}"
+    exit
+  end
+end
+
+desc 'Install the package as a gem, without generating documentation(ri/rdoc)'
+task :install_gem_no_doc => [:clean, :package] do
+  sh "#{'sudo ' unless Hoe::WINDOZE }gem install pkg/*.gem --no-rdoc --no-ri"
+end
+
+namespace :manifest do
+  desc 'Recreate Manifest.txt to include ALL files'
+  task :refresh do
+    `rake check_manifest | patch -p0 > Manifest.txt`
+  end
+end

data/tasks/environment.rake

@@ -0,0 +1,7 @@
+task :ruby_env do
+  RUBY_APP = if RUBY_PLATFORM =~ /java/
+    "jruby"
+  else
+    "ruby"
+  end unless defined? RUBY_APP
+end

data/tasks/website.rake

@@ -0,0 +1,17 @@
+desc 'Generate website files'
+task :website_generate => :ruby_env do
+  (Dir['website/**/*.txt'] - Dir['website/version*.txt']).each do |txt|
+    sh %{ #{RUBY_APP} script/txt2html #{txt} > #{txt.gsub(/txt$/,'html')} }
+  end
+end
+
+desc 'Upload website files to rubyforge'
+task :website_upload do
+  host = "#{rubyforge_username}@rubyforge.org"
+  remote_dir = "/var/www/gforge-projects/#{PATH}/"
+  local_dir = 'website'
+  sh %{rsync -aCv #{local_dir}/ #{host}:#{remote_dir}}
+end
+
+desc 'Generate and upload website files'
+task :website => [:website_generate, :website_upload, :publish_docs]

data/test/CONTEXTUALRULEFILE

@@ -0,0 +1,284 @@
+NN VB PREVTAG TO
+VBP VB PREV1OR2OR3TAG MD
+NN VB PREV1OR2TAG MD
+VB NN PREV1OR2TAG DT
+VBD VBN PREV1OR2OR3TAG VBZ
+VBN VBD PREVTAG PRP
+VBN VBD PREVTAG NNP
+VBD VBN PREVTAG VBD
+VBP VB PREVTAG TO
+POS VBZ PREVTAG PRP
+VB VBP PREVTAG NNS
+IN RB WDAND2AFT as as
+VBD VBN PREV1OR2WD have
+IN WDT NEXT1OR2TAG VB
+VB VBP PREVTAG PRP
+VBP VB PREV1OR2WD n't
+IN WDT NEXTTAG VBZ
+IN DT NEXTTAG NN
+JJ NNP NEXTTAG NNP
+IN WDT NEXTTAG VBD
+JJ NN NEXTWD of
+VBD VBN PREV1OR2WD be
+JJR RBR NEXTTAG JJ
+IN WDT NEXTTAG VBP
+JJS RBS WDNEXTTAG most JJ
+VBN VBD SURROUNDTAG NN DT
+NNS VBZ PREVTAG PRP
+POS VBZ NEXT1OR2TAG DT
+NNP NN SURROUNDTAG STAART NNS
+VBD VBN NEXTWD by
+VB NN PREV1OR2TAG IN
+VB VBP PREVTAG WDT
+VBG NN PREVTAG JJ
+NNS VBZ NEXTTAG DT
+VBN VBD PREVTAG WP
+NN VBP PREVTAG NNS
+VB NN PREVTAG NN
+NN VB PREVWD n't
+NN VBG NEXTTAG DT
+RB JJ NEXTTAG NN
+NN VBP PREVTAG PRP
+VBN VBD SURROUNDTAG NNS DT
+VB NN PREV1OR2TAG POS
+JJ NN NEXTTAG VBD
+RB RP WDNEXTTAG up DT
+JJ VB PREVTAG TO
+VBN VBD SURROUNDTAG , DT
+VBN VBD PREVWD that
+VB VBP PREVBIGRAM NNS RB
+NNP JJ SURROUNDTAG STAART NN
+VB VBN PREVTAG VBZ
+NNP JJ WDNEXTTAG American NNS
+JJ RB NEXTTAG JJR
+NNS NN CURWD yen
+IN WDT NEXTTAG VBD
+DT IN WDAND2TAGAFT that NNS
+POS VBZ PREVWD that
+JJ VB PREVTAG MD
+VB NN PREVTAG JJ
+JJR RBR NEXTTAG RB
+VBD VBN PREV1OR2WD are
+NN JJ WDNEXTTAG executive NN
+NNP JJ WDNEXTTAG American NN
+VBN VBD PREVTAG WDT
+VBD VBN PREVBIGRAM VBD RB
+JJ NN SURROUNDTAG DT .
+NNP JJ NEXTWD German
+VBN VB PREVTAG TO
+VBN VBD PREVBIGRAM NNP RB
+RB IN RBIGRAM up to
+VB VBP PREVTAG WP
+JJ NN SURROUNDTAG DT IN
+IN DT NEXTWD 's
+VBD VBN WDNEXTTAG ended NNP
+VBD VBN SURROUNDTAG DT NN
+NNS NNP NEXTTAG NNP
+NN NNP NEXTTAG NNP
+VBG NN SURROUNDTAG DT IN
+NNP JJ SURROUNDTAG STAART NNS
+RB RP WDPREVTAG VB up
+VBN VBD PREVBIGRAM PRP RB
+JJ RB NEXTTAG VBN
+NN VBP PREVTAG RB
+NNS VBZ PREVTAG RB
+POS VBZ PREVTAG WP
+VB VBN PREVWD have
+NN PDT WDNEXTTAG half DT
+IN DT PREVTAG IN
+IN WDT NEXTTAG MD
+POS VBZ PREVTAG DT
+NN NNP CURWD Integrated
+POS '' NEXT1OR2TAG ''
+VBD VBN PREVTAG IN
+JJR RBR NEXT1OR2TAG VBN
+JJS RBS WDNEXTTAG most RB
+JJ NN SURROUNDTAG JJ IN
+VBZ NNS PREVTAG JJ
+NNS VBZ WDPREVTAG JJ is
+JJ NN NEXTTAG VBZ
+VBP NN PREVTAG DT
+JJ NN SURROUNDTAG JJ .
+NNPS NNP NEXTTAG NNP
+WDT DT PREVTAG CC
+RB IN WDNEXTTAG so PRP
+VBP NN PREVWD earnings
+NN VBG PREVWD is
+NNS VBZ PREV1OR2WD Mr.
+VBZ NNS PREVWD the
+RB RP WDPREVTAG VBN up
+NNPS NNS PREVTAG STAART
+VBN VBD SURROUNDTAG NN JJ
+VBP VB PREV2TAG VB
+RBR JJR NEXTTAG NNS
+JJ NN SURROUNDTAG DT ,
+JJ NN SURROUNDTAG IN .
+NN VB PREVTAG TO
+VB NN PREVTAG VB
+NN VBP PREVWD who
+RB RP WDPREVTAG VBG up
+NN RB WDNEXTTAG right RB
+VBZ POS WDPREVTAG NNP 's
+JJ RP WDNEXTTAG up NN
+VBN VBD SURROUNDTAG NN NN
+VBN VBD SURROUNDTAG CC DT
+JJ NN NEXTBIGRAM MD VB
+JJ RB WDNEXTTAG early IN
+JJ VBN SURROUNDTAG STAART IN
+IN RB RBIGRAM though ,
+VBD VBN PREV1OR2WD been
+DT PDT WDNEXTTAG all DT
+VBN VBD PREVBIGRAM NN RB
+NN VB PREVWD help
+VBP VB PREV1OR2WD not
+VBP NN PREVTAG JJ
+DT WDT PREVTAG NNS
+NN VBP PREVTAG WDT
+VB RB RBIGRAM close to
+NNS VBZ PREVBIGRAM , WDT
+IN RP WDNEXTTAG out DT
+DT RB NEXTWD longer
+IN JJ SURROUNDTAG DT NN
+DT WDT SURROUNDTAG NN VBZ
+IN VB NEXT2TAG VB
+IN NN PREVTAG DT
+VBN VBD SURROUNDTAG NNS NNS
+IN RB RBIGRAM about $
+EX RB NEXT1OR2TAG IN
+NN VBG NEXTTAG PRP$
+NN VBG CURWD living
+VBZ NNS PREVTAG PRP$
+RBR JJR NEXTTAG NN
+RBR JJR CURWD higher
+VB VBP PREVBIGRAM PRP RB
+NN VB PREVTAG MD
+VB NN PREV1OR2TAG PRP$
+RP IN PREV1OR2TAG ,
+VB JJ PREVTAG DT
+DT IN PREVWD out
+POS VBZ PREVTAG EX
+JJ NN NEXTTAG POS
+NN JJ CURWD first
+VBD VBN PREVWD the
+NNS VBZ WDPREVTAG NNP plans
+NNP NNS SURROUNDTAG STAART IN
+RB JJ NEXTTAG NNS
+JJ RB CURWD just
+VBP NN PREVWD sales
+NNS NNPS PREVWD Orange
+VB VBN PREVTAG VBD
+WDT DT PREVTAG IN
+NN JJ WDNEXTTAG right NN
+NN VBG WDNEXTTAG operating IN
+JJ VBN CURWD insured
+JJ NNP LBIGRAM STAART U.S.
+IN DT NEXT1OR2OR3TAG STAART
+POS '' PREV1OR2OR3TAG ``
+NN JJ WDNEXTTAG official NN
+NNP JJ CURWD Irish
+JJ RB NEXTTAG RBR
+VBG NN WDPREVTAG DT selling
+VBP VB PREV1OR2OR3TAG MD
+WDT IN NEXTTAG PRP
+EX RB NEXTTAG .
+VBN VBD SURROUNDTAG NNS PRP$
+VBN VBD CURWD said
+JJ RB PREVTAG MD
+NN VBG NEXTBIGRAM JJ NNS
+JJ RB WDNEXTTAG late IN
+VBG NN PREVTAG PRP$
+VBZ NNS NEXTTAG VBP
+NN NNP WDPREVTAG DT CD
+NN VBN PREVWD be
+JJS RBS NEXTTAG VBN
+VBN VBD SURROUNDTAG NN PRP$
+VBN VBD SURROUNDTAG NNS JJ
+VBN VBD SURROUNDTAG NNS NN
+VBD VBN WDNEXTTAG increased NN
+VBZ NNS NEXTWD of
+IN RP WDAND2TAGAFT out NNS
+JJ NNP NEXTTAG POS
+RB RP WDNEXTTAG down DT
+CD NNS CURWD 1970s
+VBG NNP CURWD Working
+VBN VB PREVTAG MD
+JJ NN NEXTBIGRAM CC NN
+NN JJ SURROUNDTAG STAART NNS
+VBN VBD PREVBIGRAM , CC
+IN RB NEXTBIGRAM . STAART
+NN VBG PREVWD was
+NNP NNPS CURWD Cowboys
+VBZ NNS PREVWD phone
+NNP NNS SURROUNDTAG STAART VBP
+RBR JJR WDNEXTTAG lower JJ
+PRP$ PRP NEXTTAG IN
+VBD VB PREVTAG TO
+JJ NN WDPREVTAG NN chief
+JJ NN SURROUNDTAG JJ ,
+NN JJ WDPREVTAG DT third
+VBN VBD SURROUNDTAG NNS NNP
+NNP NN SURROUNDTAG STAART NN
+NNP NN CURWD HDTV
+VBG NN SURROUNDTAG DT ,
+VBG NN SURROUNDTAG DT .
+NNS VBZ PREVTAG WP
+NN VB SURROUNDTAG CC DT
+NNPS NNP WDAND2TAGBFR IN Securities
+RP IN PREVTAG NNS
+VBP NN LBIGRAM funds rate
+VBP NN WDPREVTAG NNS market
+DT RB RBIGRAM either .
+VBN NN SURROUNDTAG DT IN
+VBD VB PREV1OR2OR3TAG MD
+NN JJ NEXTWD oil
+VBN VBD SURROUNDTAG , $
+VBD VBN PREVBIGRAM DT RB
+VBN JJ PREVWD by
+NNP JJ WDNEXTTAG American JJ
+NN VBG PREVTAG VBP
+JJ RB LBIGRAM very much
+NN VBG RBIGRAM operating officer
+RB IN RBIGRAM up for
+NNS VBZ NEXTBIGRAM JJ NNS
+NNS VBZ SURROUNDTAG , IN
+VB VBP PREVTAG NNPS
+IN RP WDAND2TAGAFT out IN
+NNPS NNP PREVBIGRAM CC NNP
+NN RB RBIGRAM close to
+RBR RB PREVWD no
+JJ VBD NEXTTAG DT
+RB NNP PREVTAG NNP
+MD NN PREVWD good
+JJ NN WDPREVTAG NN giant
+NN JJ WDNEXTTAG official NNS
+VBN VBD SURROUNDTAG , PRP$
+VBN VBD SURROUNDTAG , RB
+VBN VBD SURROUNDTAG NN PRP
+NNP JJ WDNEXTTAG South JJ
+NN VBG PREVTAG RB
+NNS VBZ SURROUNDTAG , TO
+VBZ NNS SURROUNDTAG NN .
+NN VB NEXTTAG PRP$
+VBP VB PREV1OR2WD do
+VB JJ NEXTWD countries
+IN WDT NEXTBIGRAM RB VBZ
+JJ VB NEXTTAG DT
+WDT DT NEXTBIGRAM VBZ ,
+NNP RB RBIGRAM First ,
+DT NNP WDNEXTTAG A VBZ
+JJ RBR RBIGRAM further ,
+CD PRP WDNEXTTAG one MD
+POS '' PREV1OR2OR3TAG .
+PRP NN PREVTAG -LRB-
+VBN VBD SURROUNDTAG , PRP
+VBN VBD SURROUNDTAG NN NNS
+VBN VBD SURROUNDTAG NN RP
+NNP NN LBIGRAM STAART Business
+VBD VBN PREVTAG VBG
+IN RB RBIGRAM before ,
+IN RB WDAND2AFT As as
+NNP JJ LBIGRAM New York-based
+NNP JJ CURWD Mexican
+NNP NNPS WDNEXTTAG Motors NNP
+NNP NNPS WDPREVTAG NNP Enterprises
+JJ RB WDNEXTTAG long IN

data/test/LEXICALRULEFILE

@@ -0,0 +1,148 @@
+NN s fhassuf 1 NNS x
+NN . fchar CD x
+NN - fchar JJ x
+NN ed fhassuf 2 VBN x
+NN ing fhassuf 3 VBG x
+ly hassuf 2 RB x
+ly addsuf 2 JJ x
+NN $ fgoodright CD x
+NN al fhassuf 2 JJ x
+NN would fgoodright VB x
+NN 0 fchar CD x
+NN be fgoodright JJ x
+NNS us fhassuf 2 JJ x
+NNS it fgoodright VBZ x
+NN ble fhassuf 3 JJ x
+NN ic fhassuf 2 JJ x
+NN 1 fchar CD x
+NNS ss fhassuf 2 NN x
+un deletepref 2 JJ x
+NN ive fhassuf 3 JJ x
+NNP ed fhassuf 2 JJ x
+NN n't fgoodright VB x
+VB the fgoodright NN x
+NNS he fgoodright VBZ x
+VBN he fgoodright VBD x
+NN are fgoodright JJ x
+JJ was fgoodleft NN x
+NN est fhassuf 3 JJS x
+VBZ The fgoodright NNS x
+NNP ts fhassuf 2 NNS x
+NN 4 fchar CD x
+NN ize fhassuf 3 VB x
+.. hassuf 2 : x
+ful hassuf 3 JJ x
+NN ate fhassuf 3 VB x
+NNP ing fhassuf 3 VBG x
+VBG is fgoodleft NN x
+NN less fhassuf 4 JJ x
+NN ary fhassuf 3 JJ x
+Co. goodleft NNP x
+NN ant fhassuf 3 JJ x
+million goodleft CD x
+JJ their fgoodleft IN x
+NN he fgoodright VBD x
+Mr. goodright NNP x
+JJ of fgoodleft NN x
+NN so fgoodright JJ x
+NN y fdeletesuf 1 JJ x
+VBN which fgoodright VBD x
+VBD been fgoodright VBN x
+VB a fgoodright NN x
+NN economic fgoodleft JJ x
+9 char CD x
+CD t fchar JJ x
+NN can fgoodright VB x
+VB the fgoodright NN x
+JJ S-T-A-R-T fgoodright VBN x
+VBN - fchar JJ x
+NN lar fhassuf 3 JJ x
+NNP ans fhassuf 3 NNPS x
+NN men fhassuf 3 NNS x
+CD d fchar JJ x
+JJ n fdeletesuf 1 VBN x
+JJ 's fgoodleft NN x
+NNS is fhassuf 2 NN x
+ES hassuf 2 NNS x
+JJ er fdeletesuf 2 JJR x
+Inc. goodleft NNP x
+NN 2 fchar CD x
+VBD be fgoodleft MD x
+ons hassuf 3 NNS x
+RB - fchar JJ x
+NN very fgoodright JJ x
+ous hassuf 3 JJ x
+NN a fdeletepref 1 RB x
+NNP people fgoodleft JJ x
+VB have fgoodleft RB x
+NNS It fgoodright VBZ x
+NN id fhassuf 2 JJ x
+JJ may fgoodleft NN x
+VBN but fgoodright VBD x
+RS hassuf 2 NNS x
+JJ stry fhassuf 4 NN x
+NNS them fgoodleft VBZ x
+VBZ were fgoodleft NNS x
+NN ing faddsuf 3 VB x
+JJ s faddsuf 1 NN x
+NN 7 fchar CD x
+NN d faddsuf 1 VB x
+VB but fgoodleft NN x
+NN 3 fchar CD x
+NN est faddsuf 3 JJ x
+NN en fhassuf 2 VBN x
+NN costs fgoodright IN x
+NN 8 fchar CD x
+VB b fhaspref 1 NN x
+zes hassuf 3 VBZ x
+VBN s faddsuf 1 NN x
+some hassuf 4 JJ x
+NN ic fhassuf 2 JJ x
+ly addsuf 2 JJ x
+ness addsuf 4 JJ x
+JJS s faddsuf 1 NN x
+NN ier fhassuf 3 JJR x
+NN ky fhassuf 2 JJ x
+tyle hassuf 4 JJ x
+NNS ates fhassuf 4 VBZ x
+fy hassuf 2 VB x
+body addsuf 4 DT x
+NN ways fgoodleft JJ x
+NNP ies fhassuf 3 NNPS x
+VB negative fgoodright NN x
+ders hassuf 4 NNS x
+ds hassuf 2 NNS x
+-day addsuf 4 CD x
+nian hassuf 4 JJ x
+JJR s faddsuf 1 NN x
+ppy hassuf 3 JJ x
+NN ish fhassuf 3 JJ x
+tors hassuf 4 NNS x
+oses hassuf 4 VBZ x
+NNS oves fhassuf 4 VBZ x
+VBN un fhaspref 2 JJ x
+lent hassuf 4 JJ x
+NN ward fdeletesuf 4 RB x
+VB k fchar NN x
+VB r fhassuf 1 NN x
+VB e fdeletesuf 1 NN x
+NNS Engelken fgoodright VBZ x
+NN ient fhassuf 4 JJ x
+ED hassuf 2 VBD x
+VBG B fchar NNP x
+VB le fhassuf 2 NN x
+ment addsuf 4 VB x
+ING hassuf 3 NN x
+JJ ery fhassuf 3 NN x
+JJ tus fhassuf 3 NN x
+JJ car fhassuf 3 NN x
+NN 6 fchar CD x
+NNS 0 fchar CD x
+JJ ing fdeletesuf 3 VBG x
+here hassuf 4 RB x
+VBN scr fhaspref 3 VBD x
+uces hassuf 4 VBZ x
+fies hassuf 4 VBZ x
+self deletesuf 4 PRP x
+NNP $ fchar $ x
+VBN wa fhaspref 2 VBD x