rbtagger 0.2.9 → 0.3.0

data/Manifest.txt

@@ -46,6 +46,9 @@ lib/brill/tagger.rb
 lib/rbtagger.rb
 lib/rbtagger/version.rb
 lib/word/tagger.rb
+lib/brill/brown/CONTEXTUALRULEFILE
+lib/brill/brown/LEXICALRULEFILE
+lib/brill/brown/LEXICON
 script/console
 script/destroy
 script/generate
@@ -57,9 +60,6 @@ tasks/extconf.rake
 tasks/extconf/rule_tagger.rake
 tasks/extconf/word_tagger.rake
 tasks/website.rake
-test/CONTEXTUALRULEFILE
-test/LEXICALRULEFILE
-test/LEXICON
 test/docs/doc0.txt
 test/docs/doc1.txt
 test/docs/doc2.txt

data/ext/rule_tagger/mkmf.log

@@ -1,6 +1,6 @@
 have_header: checking for stdlib.h... -------------------- yes
 
-"gcc -E -I. -I/usr/lib64/ruby/1.8/x86_64-linux -I.   -O2 -g -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=4 -m64 -mtune=generic -Wall  -fPIC  conftest.c -o conftest.i"
+"/usr/bin/cpp-4.0 -I. -I/opt/local/lib/ruby/1.8/i686-darwin9.6.0 -I. -I/opt/local/include -D_XOPEN_SOURCE -D_DARWIN_C_SOURCE  -I/opt/local/include -O2  -fno-common -pipe -fno-common    conftest.c -o conftest.i"
 checked program was:
 /* begin */
 1: #include <stdlib.h>
@@ -10,7 +10,7 @@ checked program was:
 
 have_header: checking for string.h... -------------------- yes
 
-"gcc -E -I. -I/usr/lib64/ruby/1.8/x86_64-linux -I.   -O2 -g -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=4 -m64 -mtune=generic -Wall  -fPIC  conftest.c -o conftest.i"
+"/usr/bin/cpp-4.0 -I. -I/opt/local/lib/ruby/1.8/i686-darwin9.6.0 -I. -I/opt/local/include -D_XOPEN_SOURCE -D_DARWIN_C_SOURCE  -I/opt/local/include -O2  -fno-common -pipe -fno-common    conftest.c -o conftest.i"
 checked program was:
 /* begin */
 1: #include <string.h>
@@ -20,7 +20,7 @@ checked program was:
 
 have_library: checking for main() in -lc... -------------------- yes
 
-"gcc -o conftest -I. -I/usr/lib64/ruby/1.8/x86_64-linux -I.   -O2 -g -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=4 -m64 -mtune=generic -Wall  -fPIC conftest.c  -L. -L/usr/lib64 -L.  -rdynamic -Wl,-export-dynamic     -lruby-static -lc  -lpthread -ldl -lcrypt -lm   -lc"
+"/usr/bin/gcc-4.0 -o conftest -I. -I/opt/local/lib/ruby/1.8/i686-darwin9.6.0 -I. -I/opt/local/include -D_XOPEN_SOURCE -D_DARWIN_C_SOURCE  -I/opt/local/include -O2  -fno-common -pipe -fno-common   conftest.c  -L. -L/opt/local/lib -L. -L/opt/local/lib     -lruby-static -lc  -lpthread -ldl -lobjc  "
 checked program was:
 /* begin */
 1: /*top*/
@@ -32,7 +32,7 @@ checked program was:
 
 have_func: checking for snprintf() in stdio.h... -------------------- yes
 
-"gcc -o conftest -I. -I/usr/lib64/ruby/1.8/x86_64-linux -I.   -O2 -g -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=4 -m64 -mtune=generic -Wall  -fPIC conftest.c  -L. -L/usr/lib64 -L.  -rdynamic -Wl,-export-dynamic    -lc  -lruby-static -lc  -lpthread -ldl -lcrypt -lm   -lc"
+"/usr/bin/gcc-4.0 -o conftest -I. -I/opt/local/lib/ruby/1.8/i686-darwin9.6.0 -I. -I/opt/local/include -D_XOPEN_SOURCE -D_DARWIN_C_SOURCE  -I/opt/local/include -O2  -fno-common -pipe -fno-common   conftest.c  -L. -L/opt/local/lib -L. -L/opt/local/lib    -lc  -lruby-static -lc  -lpthread -ldl -lobjc  "
 checked program was:
 /* begin */
 1: #include <stdio.h>

data/ext/word_tagger/mkmf.log

@@ -1,6 +1,6 @@
 have_library: checking for main() in -lc... -------------------- yes
 
-"gcc -o conftest -I. -I/usr/lib64/ruby/1.8/x86_64-linux -I.   -O2 -g -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=4 -m64 -mtune=generic -Wall  -fPIC conftest.c  -L. -L/usr/lib64 -L.  -rdynamic -Wl,-export-dynamic     -lruby-static -lc  -lpthread -ldl -lcrypt -lm   -lc"
+"/usr/bin/gcc-4.0 -o conftest -I. -I/opt/local/lib/ruby/1.8/i686-darwin9.6.0 -I. -I/opt/local/include -D_XOPEN_SOURCE -D_DARWIN_C_SOURCE  -I/opt/local/include -O2  -fno-common -pipe -fno-common   conftest.c  -L. -L/opt/local/lib -L. -L/opt/local/lib     -lruby-static -lc  -lpthread -ldl -lobjc  "
 checked program was:
 /* begin */
 1: /*top*/
@@ -12,7 +12,7 @@ checked program was:
 
 have_library: checking for main() in -lstdc++... -------------------- yes
 
-"gcc -o conftest -I. -I/usr/lib64/ruby/1.8/x86_64-linux -I.   -O2 -g -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=4 -m64 -mtune=generic -Wall  -fPIC conftest.c  -L. -L/usr/lib64 -L.  -rdynamic -Wl,-export-dynamic    -lc  -lruby-static -lstdc++ -lc  -lpthread -ldl -lcrypt -lm   -lc"
+"/usr/bin/gcc-4.0 -o conftest -I. -I/opt/local/lib/ruby/1.8/i686-darwin9.6.0 -I. -I/opt/local/include -D_XOPEN_SOURCE -D_DARWIN_C_SOURCE  -I/opt/local/include -O2  -fno-common -pipe -fno-common   conftest.c  -L. -L/opt/local/lib -L. -L/opt/local/lib    -lc  -lruby-static -lstdc++ -lc  -lpthread -ldl -lobjc  "
 checked program was:
 /* begin */
 1: /*top*/

data/lib/brill/tagger.rb

@@ -2,11 +2,26 @@ require 'rule_tagger'
 
 module Brill
   class Tagger
-    def initialize( lexicon, lexical_rules, contextual_rules )
+    #
+    # will use the brown corpus as the default
+    #
+    def initialize( lexicon = nil, lexical_rules = nil, contextual_rules = nil)
       @tagger = ::Tagger::BrillTagger.new
-      Brill::Tagger.load_lexicon(@tagger,lexicon)
-      Brill::Tagger.load_lexical_rules(@tagger,lexical_rules)
-      Brill::Tagger.load_contextual_rules(@tagger,contextual_rules)
+      lexicon ||= File.join(File.dirname(__FILE__),"brown","LEXICON")
+      lexical_rules ||= File.join(File.dirname(__FILE__),"brown","LEXICALRULEFILE")
+      contextual_rules ||= File.join(File.dirname(__FILE__),"brown","CONTEXTUALRULEFILE")
+
+      Brill::Tagger.load_lexicon(@tagger, lexicon )
+      Brill::Tagger.load_lexical_rules(@tagger, lexical_rules )
+      Brill::Tagger.load_contextual_rules(@tagger, contextual_rules )
+    end
+
+    # given a body of text return a list of adjectives
+    def adjectives( text )
+    end
+
+    # given a body of text return a list of nouns
+    def nouns( text )
     end
 
     # returns similar results as tag, but further reduced by only selecting nouns

data/lib/rbtagger/version.rb

@@ -1,8 +1,8 @@
 module RbTagger #:nodoc:
   module VERSION #:nodoc:
     MAJOR = 0
-    MINOR = 2
-    TINY  = 9
+    MINOR = 3
+    TINY  = 0
 
     STRING = [MAJOR, MINOR, TINY].join('.')
   end

data/test/test_rule_tagger.rb

@@ -32,12 +32,13 @@ The details of her visitation, however, are unclear.
 Asked by Us if she were happy with the court outcome, Spears (clutching an Ed Hardy purse) smiled and told Us, "Yes."
 Next up: A status hearing set for July 15.
 The couple last appeared in court May 6. Spears was granted extended visitation — three days a week from 9 a.m. to 5 p.m. — of Sean Preston, 2, and Jayden James, 20 months. 
+)
+SAMPLE_DOC3=%q(
+TMZ.com: Britney celebrated getting overnights with her kids by going on a wild shopping trip for herself.With L.A.'s finest at her service, it was a total clusterf**k outside of Fred Segal as Brit Brit made her way out. The scene was crazy -- and it was all... Read more
 )
   def setup
     if !defined?($tagger)
-      $rtagger = Brill::Tagger.new( File.join(File.dirname(__FILE__),"LEXICON"),
-                                    File.join(File.dirname(__FILE__),"LEXICALRULEFILE"),
-                                    File.join(File.dirname(__FILE__),"CONTEXTUALRULEFILE") )
+      $rtagger = Brill::Tagger.new
     end
   end
 
@@ -134,6 +135,8 @@ The couple last appeared in court May 6. Spears was granted extended visitation
     assert results.include?(["Britney Spears", "NNP", 6])
     assert results.include?(["Jamie Spears", "NNP", 12])
 #    puts results.inspect
+    results = tagger.suggest( SAMPLE_DOC3, 5 )
+    puts results.inspect
   end
 
 private

data/website/index.html

@@ -160,32 +160,19 @@
     <h1>rbtagger</h1>
     <div id="version" class="clickable" onclick='document.location = "http://rubyforge.org/projects/rbtagger"; return false'>
       <p>Get Version</p>
-      <a href="http://rubyforge.org/projects/rbtagger" class="numbers">0.2.6</a>
+      <a href="http://rubyforge.org/projects/rbtagger" class="numbers">0.3.0</a>
     </div>
-    <h4 style="float:right;padding-right:10px;"> &#x2192; &#8216;rbtagger&#8217;</h4>
-
-	<h2>What</h2>
-
-
-	<p>A Simple Ruby Rule-Based Part of Speech Tagger</p>
-
-
-	<p>This work is based on the work of Eric Brill</p>
-
-
-	<h2>Installing</h2>
-
-
-	<p><pre class='syntax'>
+    <h4 style="float:right;padding-right:10px;"> &amp;#x2192; &#8216;rbtagger&#8217;</h4>
+<h2>What</h2>
+<p>A Simple Ruby Rule-Based Part of Speech Tagger</p>
+<p>This work is based on the work of Eric Brill</p>
+<h2>Installing</h2>
+<p><pre class='syntax'>
 gem install rbtagger
 </pre></p>
-
-
-	<h2>The basics</h2>
-
-
+<h2>The basics</h2>
 <h4>Using the rule tagger</h4>
-<pre class='syntax'>
+<p><pre class='syntax'>
 <span class="ident">require</span> <span class="punct">'</span><span class="string">rbtagger</span><span class="punct">'</span>
 
 <span class="ident">tagger</span> <span class="punct">=</span> <span class="constant">Brill</span><span class="punct">::</span><span class="constant">Tagger</span><span class="punct">.</span><span class="ident">new</span><span class="punct">(</span> <span class="constant">File</span><span class="punct">.</span><span class="ident">join</span><span class="punct">(</span><span class="constant">File</span><span class="punct">.</span><span class="ident">dirname</span><span class="punct">(</span><span class="constant">__FILE__</span><span class="punct">),&quot;</span><span class="string">LEXICON</span><span class="punct">&quot;),</span>
@@ -197,53 +184,31 @@ gem install rbtagger
 
 <span class="ident">tagger</span><span class="punct">.</span><span class="ident">suggest</span><span class="punct">(</span> <span class="constant">File</span><span class="punct">.</span><span class="ident">read</span><span class="punct">(&quot;</span><span class="string">sample.txt</span><span class="punct">&quot;)</span> <span class="punct">)</span>
 <span class="punct">=&gt;</span> <span class="punct">[[&quot;</span><span class="string">doctor</span><span class="punct">&quot;,</span> <span class="punct">&quot;</span><span class="string">NN</span><span class="punct">&quot;,</span> <span class="number">3</span><span class="punct">],</span> <span class="punct">[&quot;</span><span class="string">treatment</span><span class="punct">&quot;,</span> <span class="punct">&quot;</span><span class="string">NN</span><span class="punct">&quot;,</span> <span class="number">5</span><span class="punct">]]</span>
-</pre>
-
+</pre></p>
 <h4>Using the word tagger</h4>
-<pre class='syntax'>
+<p><pre class='syntax'>
 <span class="ident">require</span> <span class="punct">'</span><span class="string">rbtagger</span><span class="punct">'</span>
 
 <span class="ident">tagger</span> <span class="punct">=</span> <span class="constant">Word</span><span class="punct">::</span><span class="constant">Tagger</span><span class="punct">.</span><span class="ident">new</span><span class="punct">(</span> <span class="punct">['</span><span class="string">cat</span><span class="punct">','</span><span class="string">hat</span><span class="punct">'],</span> <span class="symbol">:words</span> <span class="punct">=&gt;</span> <span class="number">4</span> <span class="punct">)</span>
 <span class="ident">tags</span> <span class="punct">=</span> <span class="ident">tagger</span><span class="punct">.</span><span class="ident">execute</span><span class="punct">(</span> <span class="punct">'</span><span class="string">the cat and the hat</span><span class="punct">'</span> <span class="punct">)</span>
 <span class="ident">assert_equal</span><span class="punct">(</span> <span class="punct">[&quot;</span><span class="string">cat</span><span class="punct">&quot;,</span> <span class="punct">&quot;</span><span class="string">hat</span><span class="punct">&quot;],</span> <span class="ident">tags</span> <span class="punct">)</span>
-</pre>
-
-	<h2>Forum</h2>
-
-
-	<p><a href="http://groups.google.com/group/rb-brill-tagger">http://groups.google.com/group/rb-brill-tagger</a></p>
-
-
-	<h2>How to submit patches</h2>
-
-
-	<p>Read the <a href="http://drnicwilliams.com/2007/06/01/8-steps-for-fixing-other-peoples-code/">8 steps for fixing other people&#8217;s code</a> and for section <a href="http://drnicwilliams.com/2007/06/01/8-steps-for-fixing-other-peoples-code/#8b-google-groups">8b: Submit patch to Google Groups</a>, use the Google Group above.</p>
-
-
-	<ul>
+</pre></p>
+<h2>Forum</h2>
+<p><a href="http://groups.google.com/group/rb-brill-tagger">http://groups.google.com/group/rb-brill-tagger</a></p>
+<h2>How to submit patches</h2>
+<p>Read the <a href="http://drnicwilliams.com/2007/06/01/8-steps-for-fixing-other-peoples-code/">8 steps for fixing other people&#8217;s code</a> and for section <a href="http://drnicwilliams.com/2007/06/01/8-steps-for-fixing-other-peoples-code/#8b-google-groups">8b: Submit patch to Google Groups</a>, use the Google Group above.</p>
+<ul>
 	<li>github: <a href="http://github.com/taf2/rb-brill-tagger/tree/master">http://github.com/taf2/rb-brill-tagger/tree/master</a></li>
-	</ul>
-
-
+</ul>
 <pre>git clone git://github.com/taf2/rb-brill-tagger.git</pre>
-
-	<h3>Build and test instructions</h3>
-
-
+<h3>Build and test instructions</h3>
 <pre>cd rb-brill-tagger
 rake test
 rake install_gem</pre>
-
-	<h2>License</h2>
-
-
-	<p>This code is free to use under the terms of the <span class="caps">MIT</span> license.</p>
-
-
-	<h2>Contact</h2>
-
-
-	<p>Comments are welcome. Send an email to <a href="mailto:rb-brill-tagger@googlegroups.com">Todd A. Fisher</a> email via the <a href="http://groups.google.com/group/rb-brill-tagger">forum</a></p>
+<h2>License</h2>
+<p>This code is free to use under the terms of the <span class="caps">MIT</span> license.</p>
+<h2>Contact</h2>
+<p>Comments are welcome. Send an email to <a href="mailto:rb-brill-tagger@googlegroups.com">Todd A. Fisher</a> email via the <a href="http://groups.google.com/group/rb-brill-tagger">forum</a></p>
     <p class="coda">
       <a href="http://xullicious.blogspot.com/">Todd A. Fisher</a>, 23rd June 2008<br>
       Theme extended from <a href="http://rb2js.rubyforge.org/">Paul Battley</a>

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: rbtagger
 version: !ruby/object:Gem::Version 
-  version: 0.2.9
+  version: 0.3.0
 platform: ruby
 authors: 
 - Todd A. Fisher
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2008-08-28 00:00:00 -04:00
+date: 2009-05-21 00:00:00 -04:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -20,7 +20,7 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        version: 1.7.0
+        version: 1.8.0
     version: 
 description: A Simple Ruby Rule-Based Part of Speech Tagger
 email: 
@@ -28,8 +28,8 @@ email:
 executables: []
 
 extensions: 
-- ext/word_tagger/extconf.rb
 - ext/rule_tagger/extconf.rb
+- ext/word_tagger/extconf.rb
 extra_rdoc_files: 
 - History.txt
 - License.txt
@@ -98,6 +98,9 @@ files:
 - lib/rbtagger.rb
 - lib/rbtagger/version.rb
 - lib/word/tagger.rb
+- lib/brill/brown/CONTEXTUALRULEFILE
+- lib/brill/brown/LEXICALRULEFILE
+- lib/brill/brown/LEXICON
 - script/console
 - script/destroy
 - script/generate
@@ -109,9 +112,6 @@ files:
 - tasks/extconf/rule_tagger.rake
 - tasks/extconf/word_tagger.rake
 - tasks/website.rake
-- test/CONTEXTUALRULEFILE
-- test/LEXICALRULEFILE
-- test/LEXICON
 - test/docs/doc0.txt
 - test/docs/doc1.txt
 - test/docs/doc2.txt
@@ -134,16 +134,18 @@ files:
 - website/template.html.erb
 has_rdoc: true
 homepage: http://rbtagger.rubyforge.org
+licenses: []
+
 post_install_message: |
   For more information on rbtagger, see http://rbtagger.rubyforge.org
 
 rdoc_options: 
 - --main
-- README.txt
+- README
 require_paths: 
 - lib
-- ext/word_tagger
 - ext/rule_tagger
+- ext/word_tagger
 required_ruby_version: !ruby/object:Gem::Requirement 
   requirements: 
   - - ">="
@@ -159,11 +161,11 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 
 rubyforge_project: rbtagger
-rubygems_version: 1.2.0
+rubygems_version: 1.3.2
 signing_key: 
-specification_version: 2
+specification_version: 3
 summary: A Simple Ruby Rule-Based Part of Speech Tagger
 test_files: 
-- test/test_rule_tagger.rb
 - test/test_helper.rb
+- test/test_rule_tagger.rb
 - test/test_word_tagger.rb