rbtagger 0.4.6 → 0.4.7

data/Rakefile

@@ -1,6 +1,9 @@
 require 'rake/clean'
 require 'rake/testtask'
 require 'rake/rdoctask'
+$:.unshift File.expand_path(File.dirname(__FILE__))
+$:.unshift File.expand_path(File.dirname(__FILE__), 'lib')
+$:.unshift File.expand_path(File.dirname(__FILE__), 'ext')
 
 CLEAN.include '**/*.o'
 CLEAN.include "**/*.#{Config::MAKEFILE_CONFIG['DLEXT']}"

data/lib/brill/tagger.rb

@@ -1,3 +1,5 @@
+# encoding: utf-8
+
 require 'rule_tagger/rule_tagger'
 
 module Brill
@@ -29,7 +31,7 @@ module Brill
     # see: http://cpansearch.perl.org/src/ACOBURN/Lingua-EN-Tagger-0.15/Tagger.pm
     def noun_phrases(text)
       # ?:$PREP|$DET|$NUM)
-      # 
+      #
       tags = tag(text.gsub(/[^\w]/,' '))
       phrases = []
       phrase = []
@@ -62,7 +64,7 @@ module Brill
       # join NNP's together for names
       reduced_tags = []
       mappings = {} # keep a mapping of the joined words to expand
-      tags.each{|tag| 
+      tags.each{|tag|
         if ptag.last == 'NNP' and tag.last == 'NNP' and !ptag.first.match(/\.$/)
           ptag[0] += " " + tag.first
           # before combining these two create a mapping for each word to each word
@@ -119,7 +121,7 @@ module Brill
     end
 
     # Tag a body of text
-    # returns an array like [[token,tag],[token,tag]...[token,tag]] 
+    # returns an array like [[token,tag],[token,tag]...[token,tag]]
     #
     def tag( text )
       # XXX: the list of contractions is much larger then this... find'em
@@ -130,14 +132,14 @@ module Brill
 
       @tagger.apply_lexical_rules( tokens, tags, [], 0 )
       @tagger.default_tag_finish( tokens, tags )
- 
+
       # Brill uses these fake "STAART" tags to delimit the start & end of sentence.
-      tokens << "STAART" 
-      tokens << "STAART" 
+      tokens << "STAART"
+      tokens << "STAART"
       tokens.unshift "STAART"
       tokens.unshift "STAART"
-      tags << "STAART" 
-      tags << "STAART" 
+      tags << "STAART"
+      tags << "STAART"
       tags.unshift "STAART"
       tags.unshift "STAART"
 
@@ -166,7 +168,7 @@ module Brill
       end
       lines
     end
-    # load LEXICON 
+    # load LEXICON
     def self.load_lexicon(tagger,lexicon)
       lines = Brill::Tagger.lines(lexicon)
       i = 0
@@ -187,7 +189,7 @@ module Brill
       end
     end
 
-    # load LEXICALRULEFILE 
+    # load LEXICALRULEFILE
     def self.load_lexical_rules(tagger,rules)
       lines = self.lines(rules)
       i = 0
@@ -273,7 +275,7 @@ module Brill
       # Isolate any embedded punctuation chars
       #   s{([,;:\@\#\$\%&])} { $1 }g;
       text.gsub!(/([,;:\@\#\$\%&])/, ' \1 ')
-  
+
       # Assume sentence tokenization has been done first, so split FINAL
       # periods only.
       # s/ ([^.]) \.  ([\]\)\}\>\"\']*) [ \t]* $ /$1 .$2 /gx;
@@ -329,7 +331,7 @@ module Brill
       text.gsub!(/ (\'t)(is|was) /i,' \1 \2 ')
       #s/ (wan)(na) / $1 $2 /ig;
       text.gsub!(/ (wan)(na) /i,' \1 \2 ')
- 
+
       text.split(/\s/)
     end
 

data/lib/rbtagger.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 module RbTagger
   class << self
     def tags_from_file( file )

data/lib/rbtagger/version.rb

@@ -1,8 +1,9 @@
+# encoding: utf-8
 module RbTagger #:nodoc:
   module VERSION #:nodoc:
     MAJOR = 0
     MINOR = 4
-    TINY  = 6
+    TINY  = 7
 
     STRING = [MAJOR, MINOR, TINY].join('.')
   end

data/lib/word/tagger.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require 'word_tagger/word_tagger'
 
 module Word

metadata

@@ -1,7 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: rbtagger
 version: !ruby/object:Gem::Version 
-  version: 0.4.6
+  hash: 1
+  prerelease: false
+  segments: 
+  - 0
+  - 4
+  - 7
+  version: 0.4.7
 platform: ruby
 authors: 
 - Todd A. Fisher
@@ -9,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-01-25 00:00:00 -05:00
+date: 2011-03-30 00:00:00 -04:00
 default_executable: 
 dependencies: []
 
@@ -76,21 +82,27 @@ require_paths:
 - lib
 - ext
 required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
       version: "0"
-  version: 
 required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
       version: "0"
-  version: 
 requirements: []
 
 rubyforge_project: curb
-rubygems_version: 1.3.5
+rubygems_version: 1.3.7
 signing_key: 
 specification_version: 3
 summary: Ruby libcurl bindings